Article

Research and Education in Robotics: A Comprehensive

Review, Trends, Challenges, and Future Directions
1, 1 1 1 1,2
Mutaz Ryalat * , Natheer Almtireen , Ghaith Al-refai , Hisham Elmoaqet and Nathir Rawashdeh

1
Mechatronics Engineering Department, German Jordanian University, Amman 11180, Jordan;
[email protected] (N.A.); [email protected] (G.A.-r.); [email protected] (H.E.);
[email protected] (N.R.)
2
Department of Applied Computing, Michigan Technological University, Houghton, MI 49931, USA
* Correspondence: [email protected]

Abstract

Robotics has emerged as a transformative discipline at the intersection of the engineering,

computer science, and cognitive sciences. This state-of-the-art review explores the current
trends, methodologies, and challenges in both robotics research and education. This paper
presents a comprehensive review of the evolution of robotics, tracing its development from
early automation to intelligent, autonomous systems. Key enabling technologies, such as
Artificial Intelligence (AI), soft robotics, the Internet of Things (IoT), and swarm intelligence,
are examined along with real-world applications in healthcare, manufacturing, agriculture,
and sustainable smart cities. A central focus is placed on robotics education, where hands
on, interdisciplinary learning is reshaping curricula from K–12 to postgraduate levels. This
paper analyzes instructional models including project-based learning, laboratory work,
capstone design courses, and robotics competitions, highlighting their effectiveness in
developing both technical and creative competencies. Widely adopted platforms such as the
Robot Operating System (ROS) are briefly discussed in the context of their educational value
and real-world alignment. Through case studies, institutional insights, and synthesis of
academic and industry practices, this review underscores the vital role of robotics education
in fostering innovation, systems thinking, and workforce readiness. The paper concludes
Academic Editor: Guangjie Han
learning; robotics; robotics pedagogy; ROS; smart
Received: 19 June 2025 manufacturing; soft robotics; sustainability
Revised: 8 July 2025
Accepted: 14 July 2025
Published: 16 July 2025
Citation: Ryalat, M.; Almtireen, N.; Al-refai, G.; Elmoaqet, H.; Rawashdeh, N. Research
and Education in Robotics: A Comprehensive Review, Trends, Challenges, and Future
Directions. J. Sens. Actuator Netw. 2025, 14, 76. https://doi.org/10.3390/ 1. Introduction
jsan14040076
Robotics constitutes a multidisciplinary domain that
Copyright: © 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an
open access article synthesizes principles from en gineering, computer
distributed under the terms and conditions of the Creative Commons Attribution (CC BY) science, artificial intelligence (AI), and cognitive science to
license
(https://creativecommons.org/ licenses/by/4.0/). design, develop, and deploy intelligent systems known as
by identifying the key challenges and future directions to robots. These systems operate under two primary
guide researchers, educators, industry stakeholders, and paradigms: teleoperation, where human oversight guides
policymakers in advancing robotics as both technological and functionality, and autonomous operation, which leverages
educational frontiers. advanced algorithms and sensory feedback for independent
decision-making [1,2]. This field has emerged as a
Keywords: artificial intelligence; autonomous systems; transformative force across diverse sectors, addressing
career development; engineering education; human–robot challenges in industrial automation, healthcare, education, and
interaction; industry 4.0; mechatronics; project-based exploration by undertaking tasks that are repetitive,
hazardous, or cognitively demanding

J. Sens. Actuator Netw. 2025, 14, 76 https://doi.org/10.3390/jsan14040076

J. Sens. Actuator Netw. 2025, 14, 76
2 of 40

for humans [3]. Beyond mere machine creation, robotics encompasses the integration of
interconnected devices and adaptive systems that collaborate with humans to augment ca
pabilities, optimize efficiency, and pioneer innovative solutions [4]. As an interdisciplinary
endeavor, robotics bridges theoretical frameworks and applied methodologies, fostering
synergistic convergence between technological innovation and domain-specific implemen
tations. This integration advances operational paradigms and redefines the frontiers of
human–machine collaboration through adaptive socio-technical ecosystems [5]. Recent
advancements in cognitive intelligence have enabled machines to act as peer collaborators,
leveraging autonomous decision-making, reasoning, and situational awareness to augment
human capabilities.
Robots are deployed across a broad spectrum of domains and demonstrate exceptional
versatility and adaptability in structured and unstructured environments. In the industrial
contexts, they play a critical role in automating manufacturing processes and enhancing
precision, efficiency, and safety. Their integration into fields such as deep-sea exploration
and space missions has enabled access to environments that are otherwise hazardous or
inaccessible to humans [6]. Beyond technical applications, robots are increasingly utilized
in behavioral sciences to study human and animal interactions and in healthcare to support
individuals with disabilities through assistive technologies [7]. Moreover, robotic systems
actively shape domains such as logistics, autonomous delivery, and defense operations. In
addition to utilitarian functions, robots have been engineered for entertainment and leisure,
enriching user engagement through interactive and socially responsive designs.
An effective robotic performance across diverse applications requires advanced pro
gramming architectures and highly precise control systems. As a fundamentally interdis
ciplinary field, robotics synthesizes concepts from mechanical, electrical, and electronic
engineering, alongside computer, cognitive, and biomedical sciences [4]. Central to this in
tegration is the field of mechatronics, which combines mechanical engineering, electronics,
computer control, and system design. Mechatronics has become instrumental in driving in
novations in adaptive and intelligent robotic systems, enabling responsive and autonomous
behaviors [8]. The overarching objective of robotics research is to develop systems capa
ble of operating autonomously or collaboratively with humans, dynamically adapting to
complex environments, and executing specialized tasks efficiently and reliably [9].
Robotics research has become a foundational pillar of contemporary technological
innovation propelled by dynamic, interdisciplinary collaboration across a wide array of
scientific and engineering disciplines. The field is witnessing rapid convergence between
artificial intelligence, materials science, and biomechatronics, an interplay that is accelerat ing
advancements from nanoscale medical robots to autonomous planetary exploration
systems. Recent breakthroughs in neuromorphic computing have enabled robotic systems
to process sensory information with a level of efficiency and biological fidelity that mir
rors the neural architectures in nature [10]. Simultaneously, progress in soft robotics is
reshaping the landscape of human–machine interaction, offering safer, more adaptable, and
context-aware interfaces [11]. These developments underscore the centrality of cutting-edge
research in expanding the boundaries of the perception, learning, and accomplishment of
robotic systems.
The escalating global demand for skilled roboticists has led to a surge in educational
initiatives aimed at cultivating expertise in this rapidly evolving field. As robotics has be come
increasingly integrated into industries such as healthcare, manufacturing, agriculture,
and autonomous systems, the need for professionals with interdisciplinary knowledge has
never become more critical [12]. Robotics education spans from early STEM outreach to
advanced graduate research, building skills in mechanical design, embedded systems, AI,
and human–robot interaction. The demand for roboticists has catalyzed global educational
J. Sens. Actuator Netw. 2025, 14, 76
3 of 40

initiatives by blending project-based learning with cloud-enabled simulation platforms [13].

Modern curricula emphasize three competency pillars: computational thinking through
visual programming interfaces [14], mechatronic system integration using modular kits [15],
and cross-disciplinary collaboration through international robot competitions [16]. Leading
institutions worldwide are reshaping curricula to reflect the convergence of disciplines
within robotics, emphasizing not only technical proficiency but also ethical, social, and
collaborative dimensions [17]. This educational momentum is essential to sustaining inno
vation, ensuring responsible deployment, and preparing the next generation of researchers,
engineers, and educators who will define the future of robotics.
 Robotics: Global impact and market trends
The global robotics sector is undergoing rapid expansion, driven by technological
convergence and increasing demand across industries. Table 1 summarizes the key statistics
that highlight the scale and diversity of this transformation. The total robotics market
is projected to surpass USD 165 billion by 2028, underscoring the sector’s commercial
viability. A particularly striking trend is the explosive growth in educational robotics, which
is expected to grow at a CAGR of 28.8%, reflecting the surging demand for robotics
competencies and STEM education.

Table 1. Global impact of robotics on business and employment (Sources: International Federation of
Robotics (IFR) [18], The World Economic Forum (WEF) [19], Statista [20], MIT Sloan [21]).

Category Key Statistics

Global Market Size Robotics market projected to reach USD 165 Billion
by 2028
Valued at USD 1.37 Billion in 2024 and is estimated to
Educational Robot Market Size
grow at a CAGR of 28.8% from 2025 to 2030
Industrial Robot Deployment 4.28 million operational robots worldwide (2023)

Major Markets China, Japan, US, Republic of Korea, and Germany

(account for 74% of global robot installations)

Service Robotics Expected to generate USD 40.6 Billion in revenue by

2025
Automation expected to displace 85M jobs and create
Economic Impact
97 Million new roles by 2025 (WEF)

Wage Impact Each robot added per 1000 workers decreases wages
by 0.42% in the US

Future Projection By 2030, 80% of humans expected to interact with

robots daily

The deployment of over 4.28 million industrial robots globally, primarily concen
trated in China, Japan, the US, Republic of Korea, and Germany, reveals a geographic
imbalance in robotics adoption. These countries dominate 74% of the global installations,
highlighting both opportunities and disparities in technological access. Service robotics, an
emerging category in logistics, healthcare, and consumer markets, is forecast to generate
USD 40.6 billion by 2025, signaling diversification beyond manufacturing.
Societal impact is also profound. According to the World Economic Forum, automation
is projected to displace 85 million jobs and create 97 million new roles by 2025. While this
suggests a net positive effect on employment, disruption necessitates urgent educational
reform to retrain and reskill the workforce. Furthermore, wage suppression data, showing
a 0.42% decline per robot added per 1000 workers, raises equity concerns that demand
policy attention. By 2030, it is estimated that 80% of the population will interact with
robots daily, illustrating not only economic but also cultural and behavioral shifts in
human–robot coexistence.
J. Sens. Actuator Netw. 2025, 14, 76
4 of 40

Collectively, these data underscore the urgency for educational systems, particu
larly at the university level, to evolve in tandem with the robotics industry, equipping
learners not only with technical know-how, but also adaptability, ethical foresight, and
interdisciplinary fluency.
This rapid development necessitates a new generation of roboticists equipped with
both practical skills and theoretical knowledge to effectively design, develop, and deploy
intelligent robotic systems. As robots increasingly transition from controlled laboratory
settings to complex, real-world environments, the demands for research innovation and
educational frameworks continue to intensify.
 This article explores robotics through both technological and educational lenses, with
the aim of supporting researchers, educators, and policymakers in understanding current
developments and anticipating future needs. It integrates historical analysis, technological
trends, instructional strategies, and global initiatives to present a unified perspective on the
evolving robotic landscape.
Main Contributions
This review distinguishes itself from the existing literature by offering a holistic and
integrative analysis of robotics from both technological and educational perspectives.
Specifically, the article makes the following novel contributions:
• It presents a multi-dimensional taxonomy of robotics technologies encompassing AI,
soft robotics, quantum robotics, IoRT, and neuromorphic computing, framed through
recent advancements and real-world implementations.
• It systematically connects these technological developments to evolving educational
practices at all levels, from K–12 to postgraduate research, highlighting instructional
innovations such as digital twins, remote laboratories, and AI-driven tutoring.
• It offers a comparative analysis of educational tools, platforms, and curricula sup
ported by detailed tables and figures.
• It outlines forward-looking, feasible future directions that incorporate technological,
ethical, sustainable, and inclusive principles across robotics research and pedagogy.
• It introduces a curriculum-level case study from the German Jordanian University
(GJU), showcasing a structured robotics integration across undergraduate coursework,
project-based learning, capstone design, and competitive activities. This example
demonstrates a scalable, practice-driven educational model that bridges theory and
application within an industry-aligned academic framework.
This dual focus provides an actionable roadmap for researchers, educators, students
and policymakers, filling a critical gap in the robotics literature.

2. Review Methodology
To ensure scholarly rigor and replicability, this review followed a structured method
ology for literature selection and synthesis. This process was conducted in three stages:
(1) database search and literature identification, (2) screening and inclusion, and (3) thematic
categorization and synthesis.

2.1. Literature Search Strategy

A comprehensive literature search was performed using major academic databases
including IEEE Xplore, Scopus, Web of Science, SpringerLink, ACM Digital Library, and
Google Scholar. The search was restricted to peer-reviewed journal articles, conference
proceedings, and authoritative reports published between 2010 and 2025, with a particular
focus on publications from the last 5 years to capture recent advances.
J. Sens. Actuator Netw. 2025, 14, 76
5 of 40

2.2. Search Terms and Keywords

The search queries combined the keywords relevant to robotics research and education.
The sample search strings included the following:
• “robotics research” AND “technological trends”
• “robotics education” OR “educational robotics” AND “STEM learning”
• “robot manipulation” AND “grasping techniques”
• “human-robot interaction” OR “collaborative robotics”
• “robotics curriculum” AND “university education”
Boolean operators and truncation were used to expand the scope and improve relevance.

2.3. Inclusion and Exclusion Criteria

Articles were included based on the following criteria:
• Focused on robotics technologies, education, applications, or pedagogical tools.
• Peer-reviewed publications or reputable white papers.
• Published in English between 2010 and 2025.
 • Relevance to core themes, such as HRI, perception, motion planning, curriculum
design, and educational tools.
Exclusion criteria included:
• Duplicate records or inaccessible full texts.
• Studies not directly related to robotics or educational implementations.
• Publications in non-peer-reviewed outlets lacking technical or empirical contributions.

2.4. Thematic Organization

The final selection of 121 sources was categorized into thematic clusters representing
key areas of interest: robotics research domains (e.g., manipulation, sensing, and motion
planning), robotics applications, and robotics in education (e.g., K–12, undergraduate, and
graduate programs). This categorization informed the structure of the review and allowed
for integrative synthesis from technological and pedagogical perspectives.

3. Robotics
3.1. A Journey Through Time: The Evolution of Robotics
The concept of creating machines that mimic human actions has fascinated humanity
for several centuries. While the term “robot” was coined relatively recently, the seeds
of robotics were sown long ago, with ancient civilizations dreaming of automata and
self-operating devices.

3.1.1. The Dawn of Automata: Early Civilizations and the Greek Legacy [22]
The earliest examples of automata can be traced to ancient Egypt and Greece. With
their rich tradition of philosophy and mechanics, Greeks envisioned complex machines that
could perform tasks autonomously. Hero of Alexandria, a renowned mathematician and en
gineer, designed intricate devices powered by water, steam, and air pressure. His automata,
including self-filling vessels and moving figures, showcased the early inventors’ ingenuity.

3.1.2. The Golden Age of Islamic Civilization: Al-Jazari, the Father of Robotics [23,24]
While the concept of automata continued to intrigue scholars throughout the Middle
Ages, it was during the Islamic Golden Age that the field truly flourished. Ismail al-Jazari, a
brilliant polymath from 13th-century Mesopotamia, is often hailed as the “father of
robotics” [25]. His magnum opus, “The Book of Knowledge of Ingenious Mechanical
J. Sens. Actuator Netw. 2025, 14, 76
6 of 40

Devices,“ detailed a vast array of automata, including musical automata, humanoid robots,
and intricate clockwork mechanisms. Al-Jazari’s innovations, such as the use of cams
and cranks to control movements, laid the foundation for many principles that underpin
modern robotics.

3.1.3. The Renaissance and Industrial Revolution: Mechanical Marvels and Rise of
Automation [26]
The Renaissance witnessed renewed interest in automata, with figures such as
Leonardo da Vinci designing intricate mechanical knights and other human-like machines.
However, the Industrial Revolution has transformed the landscape of automation. The
development of steam engines and other power sources has fueled the development of
increasingly complex machines, from automated looms to early factory robots. These
machines, which do not resemble humans, have marked a significant step towards the
automation of labor-intensive tasks.

3.1.4. The 20th Century: The Birth of Modern Robotics [27]

The 20th century saw a remarkable acceleration in the development of robotics. The
term “robot” itself was coined by Czech playwright Karel Capek in his 1920 play Rossum’s
Universal Robots. The 20th century marked the advent of modern robotics, with signifi
cant milestones shaping automated industries. In 1954, George Devol patented the first
programmable robot in 1961, which led to the creation of Unimate, the world’s first indus trial
 robot. Unimate was initially deployed in General Motors’ assembly lines to handle
tasks such as die casting, welding, and revolutionizing manufacturing processes. This era
also witnessed the development of the Stanford Arm in 1969, an all-electric, 6-axis articu
lated robot designed by Victor Scheinman, which expanded the applications of robotics to
more sophisticated tasks such as assembly and welding. These innovations have laid the
groundwork for the complex automation systems prevalent in modern industries.

3.1.5. The Digital Age: [3,28,29]

The rapid advancement of modern robotics has been propelled by digital computing
and is largely attributed to the seamless convergence of advanced information and commu
nication technologies (ICT), embedded systems, high-performance sensors and actuators,
AI, 3D printing, smart materials, real-time cloud robotics, IoT, and progress in control
theory. Real-time cloud robotics and the IoT have revolutionized robotic capabilities by
enabling interconnected systems to share computational power and data instantaneously,
thereby enhancing scalability and collaboration. Smart materials, such as self-healing poly
mers and shape-memory alloys, add flexibility and adaptability, whereas the control theory
ensures stability and precision in operation. Embedded systems and AI facilitate autonomy,
real-time decision-making, and learning, and 3D printing accelerates the development of
highly customized designs. These technologies collectively underpin the transformative
potential of modern robotics in smart manufacturing, autonomous vehicles, healthcare,
and swarm robotics.

3.2. A Taxonomy of Robotics

Robotics, an interdisciplinary domain that integrates engineering, computer science,
and applied mathematics, encompasses a diverse array of systems and applications. These
systems can be systematically classified through a structured taxonomy based on key
attributes, such as functional purpose, autonomy level, morphological characteristics, and
operational environment [30]. A clear taxonomic framework simplifies the complexity
of the field and aligns robotic systems with their technologies and applications. This
classification serves as a foundational tool for advancing research, design, and interdisci-
J. Sens. Actuator Netw. 2025, 14, 76
7 of 40

plinary collaboration. A comprehensive classification matrix delineating these categories

accompanied by representative robotic archetypes is presented in Table 2.

Table 2. Classification of robots based on their types and functionalities.

Class of Robots Types Examples

• Articulated Robots
• SCARA Robots
• Cartesian Robots (Gantry)
Industrial Biologically Inspired
Robots

Service Robots
Autonomous Mobile Robots • Cylindrical Robots
• Delta Robots (Parallel) • Polar
Robots (Spherical) •
Collaborative Robots (Cobots)

• Wheeled Robots (UGV) •

Legged Robots
• Tracked Robots
Flying Robots, Drones, UAVs • Underwater Robots
(ROVs/AUVs)
• Hybrid Robots
• Autonomous Vehicles
Wing-Type Security/Surveillance • Delivery Robots
• Flapping-wing UAVs • Fixed-
wing UAVs
• Blimps, Gliders, VTOL Rotor-
Type (Drones)
• Cyclo-copters
• Tri/Quad-copters
• Hexa/Octa-copters

• Humanoids
• Soft Robots
• Snake Robots
• Climbing Robots

• Household Robots
• Healthcare Robots
• Education/Entertainment •

3.2.1. By Functionality (Application) [18,31]

Robotic systems can be categorized into two primary domains based on their func
tional applications: industrial and service. Industrial robots, as defined by the International
Federation of Robotics (IFR), are programmable automation platforms engineered for man
ufacturing processes, such as precision assembly, welding, and material handling, adhering
to globally standardized operational protocols. Conversely, service robots are designed for
non-industrial operational parameters, fulfilling roles in healthcare (surgical assistance and
rehabilitation), logistics (warehouse automation), and personal care.
J. Sens. Actuator Netw. 2025, 14, 76
8 of 40

3.2.2. By Level of Autonomy [32]

Robotic systems encompass a continuum of autonomy, ranging from manually op
erated platforms that require full human control to fully autonomous agents that are
capable of self-directed task execution in dynamic environments. At the lowest auton
omy tier, manual systems (e.g., teleoperated industrial arms) depend entirely on human
operators for guidance. At the highest tier, fully autonomous robots leverage advanced
perception, decision-making frameworks, and adaptive control architectures to operate
independently in unstructured settings. This continuum of autonomy is often formalized
through frameworks such as the level of robot autonomy (LORA) [32,33].

3.2.3. By Physical Configuration [34,35]

Robotic systems can be taxonomically categorized on the basis of their morphological
design, which defines their physical architecture, mobility mechanisms, and environmental
interaction capabilities. Morphology encompasses structural attributes such as kinematic
chain topology (e.g., serial vs. parallel linkages), joint configuration (revolute, prismatic,
or spherical), actuator characteristics (e.g., torque density, power-to-weight ratios), mate
rial composition, and sensor distribution [36], and directly governs a robot’s kinematic
dexterity, dynamic performance, and adaptability to operational constraints. These param
eters collectively enable task-specific optimization from precision manipulation to terrain
traversal. Key morphological categories include anthropomorphic robots (humanoids),
zoomorphic (bioinspired) robots, wheeled robots, legged robots, and domain-specialized
robots. These morphologies are tailored for unique operational media, including aerial
drones (rotary/fixed-wing), underwater gliders, and swarm robots with decentralized
coordination architectures.

3.2.4. Domain-Based Classification of Robots [4,37]

Robotic systems can also be grouped according to their application domains, which
reflect their specific operational environments and functional roles. For example, industrial
 robots excel in factory settings and perform repetitive and precise tasks such as welding,
painting, and handling materials. Service robots assist in everyday environments, includ ing
hospitals, homes, and public spaces, by providing support for cleaning, deliveries,
healthcare, or customer interaction. Exploration robots such as drones, submarines, and
planetary rovers are built for extreme or unreachable locations. In contrast, military robots
are designed for defense-related missions such as surveillance and bomb disposal. Agricul
tural robots contribute to modern farming using automated monitoring and harvesting
systems. Finally, social and personal robots focus on interacting with humans in roles rang
ing from educational to emotional. This classification illustrates how robotic technologies
are customized to meet the demands of specific sectors and real-world challenges.

3.2.5. By Enabling Technology [3]

Robotic systems can be classified by their enabling technologies, revealing seven key
domains that define their evolving capabilities and innovation paradigms.
(i) Advanced Sensor Integration: Modern robotic systems rely on multi-modal sensor
arrays to achieve environmental cognition. Cutting-edge technologies, including
LiDAR, stereoscopic vision systems, and biomimetic tactile sensors, enable millimeter
scale spatial resolution and multispectral perception [38,39].
(ii) Industry 4.0 and smart factories: Industry 4.0 integrates robotics with AI, IoT, and big data
to enable real-time analytics, predictive maintenance, and adaptive automation
in smart factories [40,41]. Collaborative robots (cobots) enhance flexibility and safety
by working alongside humans in precise and ergonomically demanding tasks.
J. Sens. Actuator Netw. 2025, 14, 76
9 of 40

(iii) AI-driven robotics leverages machine learning, computer vision, and decision-making
algorithms to enhance adaptability. AI-driven robots can interpret sensor data, recog
nize patterns, and adapt to changing scenarios [42].
(iv) IOT: The Internet of Robotic Things (IoRT) merges robotics with IoT for real-time
data exchange, remote control, and predictive analytics in logistics and smart
infrastructure [43]. 5G and blockchain enhance latency and data security, whereas
Fog Robotics reduces cloud reliance and hardware costs in distributed simultaneous
localization and mapping (SLAM) [44].
(v) Soft Robotics: Soft robotics uses compliant materials such as elastomers and hydrogels,
for safe and adaptive interaction with complex environments [45]. Ideal for medical,
assistive, and rehabilitation applications, it also supports inspection and repair in
hazardous settings such as nuclear facilities and aero-engines [46].
(vi) Swarm robotics: Inspired by natural systems such as ant colonies, it enables large
groups of simple robots to coordinate via decentralized control and local communica
tion. Through self-organization and redundancy, these systems achieve scalable and
resilient collective behaviors [47,48].
(vii) Sustainable Robotics: Robotics supports the UN SDGs through innovations such
as AI-powered waste-sorting robots that enhance recycling and promote circular
economies [49]. In smart cities, IoT-integrated robots enable energy optimiza
tion, traffic control, air quality monitoring, and driving data-informed urban
sustainability [50].
(viii) Agricultural Robotics [51,52]: Robotic systems are transforming agriculture by en
abling precision farming, a data-driven method that boosts productivity while reduc
ing environmental impact. Throughout the crop lifecycle, from soil preparation to
harvesting, autonomous tractors, drones, and robotic sprayers leverage sensors, GPS,
and AI for targeted operations. For instance, drones detect diseases or pests early,
whereas robot seeders and sprayers precisely deliver inputs and minimize waste.

4. Robotics in Research
Robotic research is the cornerstone of modern technological advancement, transform
ing industries, and tackling pressing global challenges. Robotics is reaching an elevated
level of maturity and continues to benefit from advances and innovations in enabling tech
nologies. Recent breakthroughs have propelled robots to become increasingly agile, adapt
able, and intelligent, thereby expanding their capabilities across diverse applications [53,54].
This section highlights several key areas of robotics research and showcasing innovations
that shape the future of this field. Table 2 lists examples of robots developed for various
applications, each originating from a distinct research initiative.

4.1. Grasping and Manipulation [55–58]

Grasping and manipulation are fundamental to enable robots to interact in diverse
and dynamic environments. Research has focused on improving dexterity, precision, and
adaptability through innovations such as soft robotics and bio-inspired grippers, allowing
for the safe handling of objects with varying shapes and fragility. Challenges span the
design and control of robotic hands, including the gripper architecture, actuation, and trans
mission systems. Sensing technologies enhance performance, whereas anthropomorphic
grippers replicate human-like dexterity. The integration of computer vision and machine
learning has significantly improved perception and grasp planning in unstructured settings.
These advances support real-world applications in manufacturing, logistics, and healthcare.
Examples are assembling parts, packaging, preparing food, folding laundry, and assisting
in surgery, thereby showcasing the growing versatility of robotic systems.
J. Sens. Actuator Netw. 2025, 14, 76
10 of 40

4.2. Motion Planning and Control [59–61]

Motion planning and control are critical for autonomous robotics, as they allow
systems to navigate and perform tasks in dynamic environments. This process integrates
perception, state estimation, and planning with core components such as localization,
mapping, and world modeling, providing essential situational awareness. Advanced path
planning and control techniques ensure precise, efficient, and collision-free movements.
Key approaches include SLAM, probabilistic and sampling-based planners such as rapidly
exploring random trees (RRT) and probabilistic roadmaps (PRM), and trajectory optimizers
such as CHOMP and STOMP. Control strategies include model predictive control (MPC),
kinematic and dynamic modeling, reinforcement learning, inverse kinematics, and visual
servoing. These tools collectively enable stable and adaptive autonomy in both structured
and unstructured environments.

4.3. Robot Vision, Sensing, and Perception [62,63]

Robot vision and perception enable intelligent interactions with the environment
by acquiring, processing, and interpreting sensory data [54]. Robots use proprioceptive
sensors (e.g., encoders, IMUs, and force/torque sensors) to monitor internal states and
exteroceptive sensors (e.g., RGB cameras, LiDAR, radar, and sonar) to gather external data.
Perception relies on image processing, computer vision, and sensor fusion techniques
for tasks such as object recognition, scene understanding, and motion tracking. These
functions support robust environmental modeling which is essential for decision-making
in unstructured contexts such as industrial automation and autonomous navigation. Re
cent advances have integrated AI-driven perception systems that are capable of semantic
mapping and adaptive behavior. Applications range from collaborative robots in manu
facturing to search-and-rescue drones and precision medical systems in which real-time
interpretation and contextual awareness are critical.

4.4. Human–Robot Interaction [64–67]

HRI focuses on optimizing communication and collaboration between humans and
robots, especially as robotic systems are integrated into the manufacturing, healthcare, and
service domains to ensure intuitive, safe, and effective interaction. Advancements in natural
language processing, gesture recognition, and affective computing have enhanced the
ability of robots to interpret human inputs and respond appropriately. These technologies
improve ergonomics by aligning robot behavior with human expectations, reducing fatigue,
and improving usability.
HRI blends insights from robotics, AI, human–computer interaction, and psychology
to develop socially aware robots. Robots such as Probo, NAO, and RAMCIP assist vulnera
ble populations by using affective computing to detect emotions through facial expressions,
voice, and body language, adjusting interactions accordingly [68]. In industry, collaborative
robots (cobots) improve productivity while ensuring worker safety. In healthcare, HRI sup
ports devices, such as smart wheelchairs, prosthetics, and exoskeletons. Augmented reality
interfaces further enhance interactions, enabling immersive and therapeutic applications.

4.5. Sensing and Actuation Technologies [69–71]

Sensors and actuators form the sensory-motor backbone of robotic systems. Their
design, integration, and control dictate how robots perceive their environment and execute
physical tasks. As robotics evolves toward greater autonomy and human–robot interaction,
these technologies are undergoing rapid innovation.
J. Sens. Actuator Netw. 2025, 14, 76
11 of 40

4.5.1. Sensors
Robotic sensing systems are broadly classified into:
• Proprioceptive sensors, such as encoders, IMUs, electromyography (EMG), and
force-torque sensors, provide internal state feedback (e.g., joint angles, orientation,
andmotor loads).
• Exteroceptive sensors, such as LiDAR, stereo cameras, depth sensors, radar, and tactile
arrays, deliver information about the external environment.
Emerging technologies are pushing boundaries:
• Event-based vision sensors capture pixel changes with microsecond latency, ideal for
fast dynamic tasks like drone flight or sports robotics.
• Quantum sensors, including atomic interferometry-based accelerometers and magne
tometers, offer unmatched precision in inertial navigation and SLAM.
• Neuromorphic sensors mimic biological sensing and are optimized for energy-efficient
edge perception in swarm and micro-robotics applications.
• Flexible e-skin sensors enable conformal surface sensing for wearable robots and safe
human–robot interaction.

4.5.2. Actuators
Robotic actuation systems convert control signals into motion or force. Key
categories include the following:
• Electric actuators, particularly brushless DC motors and servos, are dominant in
industrial arms and mobile platforms owing to their precision and efficiency.
• Pneumatic and hydraulic actuators offer high power density and are often used in
legged or bioinspired robots where compliance and strength are required.
• Soft actuators, made of elastomers, shape-memory alloys, and dielectric elastomers,
are used in rehabilitation, surgical robotics, and wearable systems.

4.5.3. Recent Trends and Research

Current research explores hybrid actuation systems that combine rigid and soft com
ponents for an adaptable morphology. Modular and reconfigurable actuator–sensor units
are being designed to simplify robot customization. Closed-loop sensorimotor systems are
increasingly being controlled via reinforcement learning and neuromorphic architectures
to support agile, robust, and adaptive behaviors.

4.5.4. Future Outlook

Future directions include the following:
• Self-healing actuators and sensors for long-term operation in remote or
hazardous environments.
• Biohybrid systems, integrating living tissues with artificial components.
• Integrated perception–action chips, which co-locate sensing, computation, and actua
tion for real-time responsiveness in microrobotics.
• Microactuators, as robotic systems continue to evolve toward higher precision, minia
turization, and bio-integration, the development of micro-actuators is gaining con
 siderable momentum. These actuators are often based on electroactive polymers
(EAPs), shape-memory alloys (SMAs), piezoelectric materials, or even microfluidics
and offer high responsiveness and adaptability at the micro/nano and sub-scales.
Their compact form makes them particularly suitable for minimally invasive surgical
tools, micro-grippers, bio-inspired robots, and implantable robotic systems.
J. Sens. Actuator Netw. 2025, 14, 76
12 of 40

The fusion of intelligent sensing and advanced actuation will be instrumental in

realizing next-generation robotic systems capable of safe, responsive, and context-aware
interactions with the physical world.

4.6. Quantum Robotics

Quantum technologies increasingly influence the future of robotics by introducing
novel computational and sensing capabilities. Quantum computing, which leverages
qubits to perform parallel computations, offers significant advantages in solving complex
problems such as route optimization and machine learning tasks, enabling faster and
more efficient robotic decision-making [72]. In parallel, quantum sensing technologies
provide ultra-sensitive navigation capabilities through quantum-enhanced position and
magnetic field sensors. These advancements promise to revolutionize robotic performance
in GPS-denied or magnetically complex environments [72]. Moreover, the application of
quantum algorithms, such as the Quantum Approximate Optimization Algorithm (QAOA),
has shown potential for optimizing coordination and control in multi-agent systems. It has
also improved safety, robustness, and reliability in autonomous robotic applications [73].
The latest research and experimentation of quantum-enhanced robotics, though in
the early stages, introduced quantum-inspired optimization techniques for multi-robot
coordination. The improved quantum optimization algorithm has shown superior perfor
mance in combinatorial tasks such as path planning for single and swarm robotics [74].
Another real-world experimental implementation is a compact quantum sensing system
developed by Aquark Technologies, a University of Southampton spinout, which has re
cently undergone navigation trials onboard the Royal Navy’s HMS Pursuer [72]. The same
system, weighing less than 10 kg, was successfully integrated into the quadcopter drone.
The company employs a patented laser cooling technique that enables the construction of
cold atom quantum sensors without relying on magnetic fields, significantly reducing the
device size, weight, power requirements, and cost.

4.7. Neural Morphology Computing

Neural morphology computing (NMC) represents a paradigm shift in robotics, moving
beyond traditional centralized control by tightly integrating neural-inspired information
processing (“neural”) with the physical structure and dynamics of the robot’s body (“mor
phology”) to achieve embodied intelligence. This approach posits that intelligence emerges
not only from a robot’s controller, but also from interactions between its computational
substrate (often neuromorphic hardware or spiking neural networks) and the physical
properties of its mechanical form—such as material compliance, limb geometry, or environ
mental interactions [75].
Inspired by the human brain architecture, neural networks facilitate parallel process
ing, allowing robots to adapt and learn from their environments more effectively. Recent
advances in neuromorphic computing have introduced energy-efficient, brain-inspired
models of computation that offer promising capabilities for robotics. Neuromorphic proces
sors such as Intel’s Loihi 2 and BrainChip’s Akida support spiking neural networks (SNNs),
enabling real-time sensory processing and control with ultra-low power consumption more
efficienly than conventional architectures [76,77]. For instance, Intel’s Loihi neuromorphic
processor demonstrated fully neuromorphic vision and control for autonomous drone
flight [76]. Another practical example is the deployment of BrainChip’s Akida to create a
neuromorphic E-Puck robot for obstacle avoidance applications [77].

4.8. Applications
Robots are transforming industries and improving lives across diverse sectors. In
 manufacturing, robotic arms and cobots perform assembly, welding, and quality control
J. Sens. Actuator Netw. 2025, 14, 76
13 of 40

with high precision and efficiency [78]. Autonomous robotics underpins Industry 4.0,
driving automation, adaptability, and innovation in smart factories [79].
In healthcare, robots enhance surgical precision and support rehabilitation through
prosthetics and assistive devices [80]. Agricultural robots, including drones and au
tonomous vehicles, automate planting, spraying, and harvesting and improve sustainability
and productivity [81].
Logistics benefits from AGVs, drones, and mobile robots for warehouse automation,
inventory tracking, and last-mile delivery [82]. In disaster response, robots, such as UAVs
and underwater systems, aid in search-and-rescue, hazard assessment, and real-time
situational awareness [83]. These applications highlight the pivotal role of robotics in
addressing the complex industrial and societal needs.
Robotics research and education are advancing rapidly and are being supported by
high-impact journals and prestigious conferences. These venues provide a platform for
disseminating cutting-edge findings and fostering academic collaborations. Tables 3 and 4
list the most influential journals and conferences in this field, based on SCOPUS [84] and
Google Scholar [85].

Table 3. Top robotics journals and their metrics.

Journal Title CiteScore 2020–2023 Citations % Cited Publisher

Science Robotics 30.6 9480 81 American Association for the Advancement of Science
Annual Review of Control, Robotics, and

Autonomous Systems 28.3 2489 99 Annual Reviews Inc. Robotics and Computer-Integrated

Manufacturing 24.1 14,118 97 Elsevier

International Journal of Robotics Research 22.2 5921 84 SAGE
Soft Robotics 15.5 4976 88 Mary Ann Liebert Journal of Field Robotics 15.0 4207 81 Wiley
IEEE Transactions on Robotics 14.9 11,685 84 IEEE
Robotics: Science and Systems 12.0 3230 94 MIT Press
International Journal of Social Robotics 9.8 4503 83 Springer Nature IEEE Robotics and Automation Letters 9.6 44,648
83 IEEE
Robotics and Autonomous Systems 9.0 5741 84 Elsevier
IEEE Robotics and Automation Magazine 8.8 1673 76 IEEE
Cognitive Robotics 8.4 565 72 KeAi Communications IEEE Transactions on Medical

Robotics and Bionics 6.8 2483 81 IEEE

Robotics 6.7 3747 78 MDPI
Frontiers in Robotics and AI 6.5 7497 78 Frontiers Media Journal of Robotics and Control (JRC) 6.3 1980 82 Universitas Muhammadiyah
Yogyakarta Intelligent Service Robotics 5.7 1001 78 Springer Nature Journal of Mechanisms and Robotics 5.6 2510 87 ASME
International Journal of Medical Robotics and

Computer Assisted Surgery 5.3 2631 83 Wiley

Frontiers in Neurorobotics 5.2 3968 70 Frontiers Media Advanced Robotics 4.1 1747 69 Taylor & Francis Journal of Micro
and Bio Robotics 3.8 139 59 Springer Nature
J. Sens. Actuator Netw. 2025, 14, 76
14 of 40

Table 3. Cont.

Journal Title CiteScore 2020–2023 Citations % Cited Publisher

International Journal of Intelligent

Robotics and Applications 3.8 662 79 Springer Nature Journal of Robotics 3.7 626 77 Wiley
Biomimetic Intelligence and Robotics 3.7 223 65 Elsevier
IET Cyber-systems and Robotics 3.7 407 66 Wiley
International Journal of Humanoid Robotics 3.5 350 75 World Scientific International Journal of

Robotics and Control Systems 3.1 476 72 ASCEE

Springer Proceedings in Advanced Robotics 2.6 1774 59 Springer Nature Journal of Robotics and Mechatronics 2.2 1194 62
Fuji Technology Press
 Table 4. Major robotics conferences and their focus areas.

Conference Name Organizer Focus Frequency

IEEE International Conference Robotics: Science and Robotics advancements, Theoretical robotics, including
on Robotics and Automation including AI, control,
IEEE Robotics and Automation
(ICRA) perception, and autonomous Annual
Society
systems.

ML, computer vision, and motion Annual

Systems (RSS) RSS Foundation planning.

IEEE/RSJ International
Conference on Intelligent
Robots and Systems (IROS)

International Symposium on
IEEE Robotics and Automation
Society, RSJ
Intelligent systems, sensing,
AI, robot manipulation, and
multi-robot systems.

Annual
 Advanced robotics methodologies
Robotics Research (ISRR) RSJ, Springer and fundamental research. Biennial

Conference on Robot Annual IEEE Robotics and

Learning (CoRL) ML and Robotics Humanoid robotics, locomotion, HRI, and

Community International Conference on Humanoid
Robotics and machine learning, including Robots (Humanoids) social robotics. Annual
reinforcement learning, perception, and
planning. International Conference on Industrial automation, robotics
IEEE Robotics and Automation Society
Automation Science and International Conference on Automation Society smart manufacturing.
Engineering (CASE) systems, and Annual

Social Robotics (ICSR) Springer, various institutions Social robotics, human–robot interaction, and ethical concerns.
Annual
International Conference on Advanced Robotics Association Robotics in collaboration, and
Robotics (ICAR) policy development.
IEEE Robotics and Automation Society
Emerging and innovative Educational robotics, curriculum design,
Education (RiE) International RiE pedagogical tools, STEAM education
concepts in robotics. Biennial Robotics Annual Annual
research, industry
European Robotics Forum (ERF) EU Committee

J. Sens. Actuator Netw. 2025, 14, 76

15 of 40

5. Robotics in Education
The rising global demand for skilled roboticists has driven educational initiatives that
focus on building expertise in this rapidly evolving field. At the university level, robotic
integration has transformed learning by promoting innovation, entrepreneurship, and
student engagement. Offering a hands-on, interdisciplinary approach, robotics bridges
theory and application, aligning with the growing need for industry-ready skills [86].
Universities are central to this shift, serving as hubs for both education and advanced
robotics research [87]. The inclusion of robotics in the curriculum fosters the next generation
of innovators by developing essential technical and problem-solving abilities.
Robotics has become a powerful educational tool across all academic levels, fostering
interdisciplinary competencies in STEM fields [88]. Early K–12 exposure to specialized
undergraduate and postgraduate programs enhances creativity, problem-solving skills,
and experiential learning. Educational robotics supports cognitive development while
aligning with evolving workforce demands. Its integration can be structured into three
key stages: K–12 education, undergraduate education, and postgraduate and research
oriented education.

5.1. K-12 Education [89,90]

Educational robotics significantly enriches K–12 learning by fostering creativity,
problem-solving, and technical skills. It introduces students to robot design and pro
gramming, promoting logical thinking, spatial perception, and hands-on learning. Robotics
also enhances collaboration, self-confidence, and interdisciplinary learning across subjects
such as math, science, and art.
As part of STEAM education, robotics equips learners with practical knowledge
and engages them in competitions such as the FIRST LEGO League, VEX IQ, RoboCup
Junior, and World Robot Olympiad. These events cultivate innovation, teamwork, and
technical proficiency.

5.1.1. Educational Robotics Tools and Platforms

Robotics education at this level uses a range of hardware and software:
 Construction Kits:LEGO® Technic, TETRIX®, and VEX kits allow students to build
functional robots.
Sensors and Actuators: Infrared, ultrasonic, and tactile sensors paired with motors
and servos bring interactivity into projects.
Microcontrollers: Platforms such as Arduino, LEGO Mindstorms EV3, VEX Cortex,
and Micro:bit introduce the coding and hardware integration.

5.1.2. Software and Programming Platforms

Block-Based Programming: Tools such as Scratch, Blockly, and RoboBlockly offer
intuitive visual coding environments for beginners.
Text-Based Programming: More advanced learners use Python, Arduino IDE, or
hybrid tools such as MakeCode for deeper engagement.
Educational robotics delivers a dynamic way to teach STEM, combining theory with
hands-on practice and fostering skills essential for the digital age.

5.2. Higher Education

Robotics is revolutionizing industries, from manufacturing and healthcare to au
tonomous systems and AI. This field has witnessed exponential growth, necessitating an
advanced workforce capable of innovating and implementing robotic systems [2]. Higher
education institutions play a pivotal role in the development of skilled professionals
J. Sens. Actuator Netw. 2025, 14, 76
16 of 40

through structured undergraduate and postgraduate programs. Here, we discuss the

role of robotics education at different academic levels, focusing on curriculum, research
opportunities, and industry collaboration.
Robotics-related topics are offered either in specialized robotics programs (BSc or MSc)
or within other engineering disciplines, with Mechatronics Engineering being a notable
example. Table 5 outlines the key robotics topics and courses categorized by specific
areas of focus, and Table 6 provides a comparison between undergraduate and graduate
robotics programs.

Table 5. Robotics education: categories, course fields, and corresponding topics.

Category Course Field Topics

Core Topics Mathematics Linear Algebra, Calculus (differential and integral), Probability and Statistics. Physics Mechanics, Electronics, Materials
Science,

Computer Science Algorithms, Programming (Python, C++, ROS), AI and Machine Learning,
Embedded Software

Engineering Principles Electrical Engineering, Mechanical Engineering, Systems Integration

Specialized Topics Robot Kinematics and Dynamics Forward/Inverse Kinematics, Motion Planning, Multi-body Dynamics Control Systems Feedback

Control (PID), Nonlinear/Adaptive Control, State Estimation,

Kalman Filters

Sensing and Actuating Sensors (LiDAR, Cameras), Computer Vision, Sensor Fusion, motors,
servos, pneumatics

AI for Robotics Path Planning (A*, RRT), Reinforcement Learning, NLP, Swarm Intelligence

Human–Robot Interaction User Interfaces, Collaborative Robots, Ethical and Social Considerations

Embedded Systems Microcontrollers (Arduino, Raspberry Pi), Real-Time Operating

Systems (RTOS), communication

Emerging Topics Soft Robotics Bio-Inspired Robotics, Design and Control of Soft Materials Autonomous Systems Autonomous Vehicles,
Marine Robotics, Space Robotics, SLAM

Robotics and AI Integration Deep Learning, Cognitive Robotics, Ethical AI

Additive Manufacturing 3D Printing, Customizable Components

Cybersecurity Securing Robotic Systems, Cyberattack Prevention

 Research and Practical Skills Hands-On Prototyping Building and Programming Robots, Debugging, Testing, Capstone Projects Simulation and
Modeling Robotics Simulators (Gazebo, Webots), Digital Twin Technology

Communication and Teamwork Collaborative Projects, Technical Writing, Multidisciplinary Team Management Ethical
and Societal Topics Ethical Design Responsible Robotics, Ethical Use

Environmental Impact Sustainability in Robotics

Social Implications Workforce Displacement, Addressing Societal Challenges

5.2.1. Undergraduate Robotics Education [16,17,91]

Curriculum Structure
Undergraduate robotics programs are offered either as a standalone B.Sc./B.Eng.
degrees or as concentrations within fields such as mechatronics or computer engineering,
are structured to reflect the interdisciplinary nature of robotics [91,92]. These programs
typically consist of four core components: foundational disciplines, core robotics courses,
elective specializations, and capstone projects [16,17].
Key Components
J. Sens. Actuator Netw. 2025, 14, 76
17 of 40

(Table 5).
• Core Foundations: Mathematics, physics, computer science, and systems engineering
provide the analytical basis for robotics. These are typically covered during the first
two years [92].
• Core Robotics Courses: Covering robot kinematics, dynamics, control systems, and
AI, these modules emphasize lab work with tools such as ROS, MATLAB, and
Arduino [17].
• Electives: Depending on the institutional offerings, students may specialize in areas
such as soft robotics, HRI, or IoT-based systems. Interdisciplinary tracks include ethics,
design, or business modules [91].
• Capstone Project: This final-year experience involves designing a full robotic system,
such as autonomous drone or robotic arm, often in collaboration with industry or
university laboratories. The deliverables include documentation, prototypes, and
seminar presentations [16].

Table 6. Comparison of undergraduate and graduate robotics programs.

Aspect Undergraduate Programs (BSc) Graduate Programs (MSc)

Program Names Focus Areas Science (Robotics Focus) Autonomous Systems, or Mechatronics and
Robotics
Fundamentals of robotics,
mechanical/electrical/software engineering,
BSc in Robotics Engineering, Mechatronics, Advanced robotics concepts, AI and machine
hands-on design and prototyping
Automation and Robotics, or Computer learning in robotics, automation, control
MSc in Robotics, AI and Robotics, systems, and autonomy

Duration 3–4 years 1–2 years

High school diploma (background in math, Introduction to Robotics, Sensors and Actuators,
Entry Requirements BSc in robotics, mechatronics, or related fields; sometimes
physics, GRE/GMAT, research experience, or portfolio required
programming optional)
Advanced Robotics Programming, Machine
Key Courses
Programming for Robotics, Robot Kinematics
and Dynamics, Control Systems
Learning for Robotics, Robot Perception,
Advanced Mechatronic Design, Research
Methodology
 Automation
Skills Developed Engineering fundamentals, programming, robot Engineer, Embedded Systems Developer
design, problem-solving, teamwork Advanced research, AI and autonomy specialization, system
integration, innovation
Entry-level roles: Robotics Technician,
Career Opportunities Advanced roles: Robotics Scientist, AI Specialist, Control Systems
Engineer, Researcher, Academic positions

Industries Manufacturing, automotive, healthcare, logistics Advanced R&D, aerospace, defense, high-tech healthcare robotics,
academia

Strong emphasis on research; often requires a thesis

Research Component Minimal; hands-on and coursework-focused or project

Research thesis or advanced project contributing to

Capstone/Thesis Capstone project with practical applications the field

Preferred in research-intensive institutions and high-tech industries

Global Popularity High demand in developing nations and entry-level
robotics markets Doctoral studies (PhD) or leadership roles in robotics research and
innovation
Future Pathways Further education (MSc) or immediate industry entry
J. Sens. Actuator Netw. 2025, 14, 76
18 of 40

Table 7 presents the selection of the most widely used robotics textbooks across academic
and professional settings, along with their primary focus areas and common applications.

Table 7. Representative robotics textbooks categorized by focus area.

Category Textbook Title and Authors Key Focus/Typical Use Cases Introductory textbook covering mechanical
Robot Dynamics and Control
General Robotics Introduction to Robotics: Mechanics and Control John J. Mark W. Spong et al.
Craig
Introduction to Autonomous Mobile Robots
foundations, actuators, sensors, and basic control. Widely used in
Modern Robotics: Mechanics, Planning, and undergraduate courses.
Control
Kevin M. Lynch and Frank C. Park Balanced coverage of theory and
implementation, ideal for undergrad and grad courses.

Robotics: Control, Sensing, Vision, and Intelligence Comprehensive introduction to robotics, including control systems, sensors,
K.S. Fu, R.C. Gonzalez, C.S.G. Lee vision, and artificial intelligence. Suitable for both beginners and advanced
learners.

Comprehensive reference that spans foundational theories, robot kinematics,

dynamics, control, sensing, learning, HRI, and ethics. Ideal for graduate-level
study, multidisciplinary research.
Springer Handbook of Robotics
Edited by Bruno Siciliano and Oussama Khatib In-depth treatment of kinematics, dynamics, control, and trajectory planning;
suitable for advanced learners.

Focus on dynamic modeling and feedback control techniques.

Robot Kinematics and Dynamics Robotics: Modelling, Planning and Control
Bruno Siciliano et al. Core principles of mobility, navigation,
Autonomous Robots and Mobile Robotics Probabilistic Robotics Covers probabilistic models, SLAM, Bayesian
Roland Siegwart, Illah Nourbakhsh, and Sebastian Thrun, Wolfram Burgard, and filtering; ideal for autonomous
Davide Scaramuzza Dieter Fox systems research.
localization, and perception for mobile robots.

Keras, and TensorFlow: Concepts, Tools, and

Computer Vision and Perception in Robotics Computer Vision: Algorithms and Techniques to Build Intelligent Systems
Applications Richard Szeliski Aurélien Géron

Multiple View Geometry in Computer Vision

Richard Hartley and Andrew Zisserman
Cognitive Robotics Cognitive Robotics
Angelo Cangelosi and Minija Tamosiunaite
Comprehensive guide to vision algorithms used in robotics and AI applications.
Robotics, Vision and Control: Fundamental Focuses on 3D vision, structure from motion, stereo vision—used in advanced
Algorithms in MATLAB / Python robotics perception.
Peter Corke
Practical integration of robotics and computer vision algorithms, with detailed
implementations in MATLAB and Python. Covers kinematics, visual servoing,
and perception pipelines. Widely used in labs, projects, and applied robotics
courses.
AI and Machine Learning for Robotics Introduction to AI Robotics Robin R.
Murphy Broad AI textbook, foundational for reasoning, planning, and learning in
robotics.
Artificial Intelligence: A Modern Approach
Stuart Russell and Peter Norvig Broad AI textbook, foundational for reasoning, planning, and learning in
robotics.

Hands-On Machine Learning with Scikit-Learn, Practical guide to implementing machine learning and deep learning algorithms
using Python libraries. Covers neural networks, CNNs, RNNs, and Explores cognitive architectures, learning, reasoning, and human–robot
reinforcement learning. Widely used in robotics projects involving perception, interaction.
control, and adaptive behaviors.
J. Sens. Actuator Netw. 2025, 14, 76
19 of 40

Industry Collaboration and Internships

Partnerships with industry leaders expose students to real-world applications. Com
panies such as Boston Dynamics, KUKA, and ABB Robotics offer internship programs that
bridge the gap between academia and the industry.

5.2.2. Postgraduate Robotics Education [87,88]

Postgraduate robotics education builds on undergraduate foundations to provide a
focused, research-intensive pathway through M.Sc, M.Eng, and Ph.D. programs. These pro
grams cultivate deep technical expertise and prepare graduates for leadership in academia,
industry, and research institutions [90,91].
Curriculum and Specialization
Master’s programs emphasize advanced robotics topics such as nonlinear control,
robot learning, optimization, and SLAM. Students often pursue electives in specialized
tracks, including bio-inspired robotics, HRI, swarm intelligence, and medical robotics [88].
This enables engagement with the frontier technologies and interdisciplinary challenges.
Research and Thesis Integration
A central component of postgraduate robotics education is the research thesis, through
which students engage in comprehensive literature analysis, design and implement experi
mental or simulation-based systems, and aim to generate publishable research
outcomes. Doctoral candidates further extend this process by undertaking long-term, original
investi
gations, often involving interdisciplinary or inter-institutional collaboration [87].
Industry Collaboration and Applied Research
Many programs integrate applied research through internships, sponsored theses,
and partnerships with laboratories such as MIT CSAIL or Stanford’s Robotics Lab. These
experiences help align academic learning with real-world applications and industrial needs
(see Table 8).

Table 8. Examples of postgraduate robotics programs and their research partnerships.

University Program Partner Research Institutions/Focus Areas Robotics Institute, National Robotics
Carnegie Mellon University (USA) M.S./Ph.D. in Robotics Engineering Center; collaborations with NASA, DARPA, Google; focus on
autonomous systems, HRI, soft robotics

ETH Robotics Systems Lab, Autonomous Systems Lab; aerial robotics, legged
robots, mechatronic systems
ETH Zurich (Switzerland) M.Sc. in Robotics, Systems, and Control Technical
Munich Institute of Robotics and Machine Intelligence (MIRMI); partnerships
with Siemens, BMW; cognitive robotics, AI

University of Munich (Germany) M.Sc. in Robotics, Cognition, Intelligence

University of Tokyo (Japan) Graduate Program in Information Science JSK Robotics Lab; cooperation with RIKEN, AIST; humanoid robotics, soft
robotics

Hamlyn Centre for Robotic Surgery; NHS

Imperial College London (UK) M.Sc. in Medical Robotics National University of

Singapore (NUS) M.Sc./Ph.D. in Robotics

Tsinghua University (China) M.E./Ph.D. in Control Science and Engineering

(Robotics Track)
collaborations, Intuitive Surgical; surgical robotics, medical AI

Advanced Robotics Centre; collaborations with A*STAR and global institutions;

smart mobility, assistive robotics

Partners with the Institute of Automation, Chinese Academy of Sciences

(CASIA); focus on intelligent robotics, computer vision, human–robot
interaction
 J. Sens. Actuator Netw. 2025, 14, 76
20 of 40

Academic Development and Professional Skills

Beyond technical mastery, postgraduate programs emphasize academic literacy, com
munication, and leadership. Common components include the following.
• Research methods and scientific writing.
• Presentation skills and conference participation.
• Ethics in robotics research.
• Grant writing and innovation management.
Graduate students are often encouraged, or required, to present at international
conferences, as shown in Table 4, and publish their work in peer-reviewed journals, as
shown in Table 3. These experiences foster not only scholarly maturity but also professional
confidence and networking.
In summary, postgraduate robotics education offers a platform for intellectual spe
cialization, original research, and high-level engagement with industry and society. As
robotics continues to permeate every facet of modern life, postgraduate programs are vital
in shaping the next generation of roboticists capable of leading in both the technological
and ethical dimensions.

6. Career Prospects in Robotics

The rapid proliferation of robotics across industrial, commercial, and societal domains
has significantly expanded career opportunities for robotics graduates. Both undergraduate
and postgraduate robotics degrees provide access to a wide spectrum of roles that blend
engineering, computer science, artificial intelligence, and human-centric designs. Career
prospects span not only traditional engineering sectors, but also emerging industries where
intelligent automation and autonomous systems are critical.

6.1. Industry Roles and Sectors

Robotics graduates are in high demand across a variety of industries, including, but
not limited to:
• Manufacturing and Industrial Automation: Development of robotic arms, assembly
automation, and smart factories using Industry 4.0.
• Healthcare and Medical Robotics: Design of surgical robots, rehabilitation devices,
prosthetics, and assistive technologies.
• Autonomous Vehicles and Drones: Roles in perception, navigation, and control of
land, aerial, and underwater autonomous systems.
• Agriculture and Environmental Robotics: Automation of precision farming, crop
monitoring, and conservation applications.
• Logistics and Warehouse Automation: Robotics solutions for inventory management,
package handling, and autonomous delivery.
• Consumer Robotics and AI Assistants: Development of domestic robots, smart devices,
and embodied AI interfaces.
Job titles for graduates may include Robotics Engineer, Automation Specialist, Ma
chine Learning Engineer, Mechatronics Engineer, AI Developer, or Research Scientist in
robotics-related domains.

6.2. Academic and Research Careers

Graduates with advanced degrees (M.Sc. and Ph.D.) often pursue research-intensive
careers in academia, government laboratories, and corporate R&D. These roles emphasize
the following:
• Fundamental research in robotic perception, control, learning, and human–robot interaction.
J. Sens. Actuator Netw. 2025, 14, 76
21 of 40

• Development of novel robotic systems and algorithms for scientific exploration or

 societal benefit.
• Contribution to interdisciplinary initiatives in neuroscience, cognitive science, or ethics.
• Mentorship and teaching in robotics, engineering, and computer science programs.

6.3. Entrepreneurship and Startups

The dynamic growth of the robotics ecosystem has led to an increase in entrepreneurial
activity. Many graduates, especially those from research-focused or innovation-centered
programs, leverage their expertise to launch robotic start-ups. Common focus areas include
the following.
• Service robotics (e.g., elder care, cleaning, delivery).
• Robotic platforms for education and STEM training.
• Niche automation tools for vertical industries (e.g., mining, construction).
• AI-enhanced robotics software and simulation tools.
University incubators, venture capital funding, and tech accelerators often support
early-stage ventures by offering an alternative to traditional employment pathways.

6.4. Global Demand and Emerging Markets

The global demand for robotics professionals continues to grow, driven by strategic
initiatives such as:
• Germany’s Industrie 4.0.
• Japan’s Robot Strategy.
• Republic of Korea’s Fourth Intelligent Robot Basic Plan.
• U.S. National Robotics Initiative.
• China’s Made in China 2025.
• Government Labs: Opportunities at NASA, CERN for large-scale robotics projects.
Robotics graduates benefit from a dynamic, multidisciplinary career landscape. Re
gardless of whether they pursue roles in industry, research, entrepreneurship, or policy, they
are uniquely positioned to shape the next generation of intelligent systems that transform
how we work, live, and interact with technology.

7. Robotics Education: Tools and Platforms for Experiential Learning

University-level robotics education blends software frameworks, hardware platforms,
and simulators to link theory with hands-on experience, fostering systems thinking and
cross-disciplinary collaboration. Below is an overview of the essential tools used in under
graduate and graduate curricula.

7.1. Software Tools

Robotics software supports algorithm design, simulation, system integration, and
hardware abstraction.
Robot Operating System (ROS): Standard middleware in education and research,
offering modular architecture, sensor/actuator integration, and Gazebo simulation support.
ROS2 enhances real-time performance, security, and multi-platform use [93,94].
MATLAB/Simulink: This software is widely used for modeling, control design, and
reinforcement learning. Its Robotics System Toolbox and Corke’s Robotics Toolbox support
kinematics, trajectory planning, mapping, and localization [95,96].
Python & C++: Python excels in readability and machine learning support (TensorFlow,
NumPy). C++ is crucial for real-time control and embedded applications [97,98].
J. Sens. Actuator Netw. 2025, 14, 76
22 of 40

OpenCV: Essential for computer vision tasks such as image processing, feature extrac
tion, SLAM, and navigation [99].
Gazebo, CoppeliaSim, Webots: Physics-based simulators vital for validating algo
rithms safely. Gazebo integrates closely with ROS, and CoppeliaSim supports scripting
and extensive robotic models [100].

7.2. Hardware Platforms

 Tangible platforms help students to move from theory to implementation by enabling
embedded systems, perceptions, and control practices.
Arduino & Raspberry Pi: Affordable microcontrollers and single-board comput
ers for sensor interfacing, control workflows, and edge computing (e.g., camera and
networking) [101].
NVIDIA Jetson: AI-focused modules (Nano, Xavier, Orin) with onboard GPUs that
support deep learning, object detection, and real-time autonomy [102].
3D Printers: Tools like Ultimaker and Prusa enable custom part fabrication, rapid
prototyping, and creativity enhancement [103].
Sensor and Perception Modules: LiDAR (RPLIDAR, Velodyne), IMUs (MPU-6050,
BNO055), RGB-D cameras (Intel RealSense, Azure Kinect), ToF cameras, stereo vision, GPS,
and force/torque sensors—used for SLAM, mapping, and interaction [104,105].
Industrial and Collaborative Arms: Platforms such as KUKA LBR iiwa, UR3/UR5,
and ABB YuMi are used in advanced laboratories for teaching trajectory planning, control,
and HRI within ROS ecosystems [106]. Table 2 lists additional examples of these platforms.

7.3. Educational Robotics Kits

Modular kits bridge affordable entry-level and advanced robotics learning.
Quanser Kits: High-fidelity manipulators, UAVs, and vehicles compatible with MAT
LAB, LabVIEW, and ROS—they support teaching control, mechatronics, and real-time
systems [107].
TurtleBot3 and Husky UGV: ROS-enabled mobile bases ideal for SLAM, naviga
tion, and perception—TurtleBot3 is compact and teaching-friendly. Husky supports field
robotics [108].
LEGO SPIKE Prime/Mindstorms EV3: Graphic programming tools used in introduc
tory engineering and outreach for teaching basic robotics principles [109].
Humanoid Platforms (OP3/Darwin-OP): Support bipedal locomotion, vision, and
AI-based behaviors in advanced lab courses.
Dobot Magician/Niryo One: Desktop arms for teaching pick-and-place, vision, and
PLC integration in laboratories.
VEX Robotics/TETRIX: Used in design courses and competitions to teach mechanical
design, embedded programming, and teamwork.
Universities often integrate these resources through pipelines: design and simulate
in ROS+Gazebo and then deploy them on TurtleBot3 or UR5. Open source ROS packages
enhance collaborative and adaptable learning environments [110]. Although balancing
costs and scalability poses challenges, adaptability of ROS continues to align educational
platforms with industrial practices [94].

7.4. ROS
ROS is the de facto standard open source middleware for robotics, originally developed
by Willow Garage for the PR2 platform [93] and is now maintained by Open Robotics [111].
Although ROS supports modular, reusable software across diverse platforms, its centralized
communication model and limited real-time capabilities pose challenges. These limitations
J. Sens. Actuator Netw. 2025, 14, 76
23 of 40

are addressed in ROS2, which adopts a Data Distribution Service (DDS)-based architecture
to enhance scalability, reliability, and real-time performance [112].

8. Curriculum-Level Robotics Integration: Insights from the German

Jordanian University
The integration of robotics into undergraduate education plays a pivotal role in fos
tering interdisciplinary learning, bridging the theoretical foundations with practical ap
plications, and equipping students to address emerging technological challenges. At the
Mechatronics Engineering Department of German Jordanian University, robotics has been
strategically embedded throughout the curriculum through class projects, laboratory work,
project-based courses, capstone projects, and robotics competitions. This
comprehensive, hands-on approach not only enhances students’ technical proficiency,
but also cultivates
essential soft skills such as teamwork, innovation, and creative problem-solving.

8.1. Class Projects and Laboratory Work

Robotic concepts are embedded across core courses to bridge theoretical founda
tions with hands-on applications. This integration allows students to apply engineer ing
principles in practical contexts through structured class projects. Examples include
the following:
• Embedded Systems: Students program microcontrollers such as Arduino or Raspberry
Pi to execute basic robotic tasks, including line-following and obstacle-avoidance
robots.
• Control Systems: Student teams design and implement PID and state-space con
trollers for dynamic systems such as balancing inverted pendulums or stabilizing
twin-rotor drones.
• AI: Students develop and deploy path-planning and decision-making algorithms
using ROS on mobile robot platforms.
• Computer-Aided Engineering Courses: Courses involving MATLAB, Simulink, Sim
scape, LabVIEW, Python, and CAD tools support simulation, modeling, and robotic
system design.
Dedicated robotics laboratories have been used to reinforce these concepts through
experimentation. These facilities support a wide range of activities, including:
• Mechatronics Laboratories: Students integrate sensors, actuators, and microcontrollers
to build functional robotic systems such as robotic arms.
• Industrial Robot Programming: Students gain hands-on experience programming
various robotic manipulators, including KUKA, Mitsubishi, and Quanser.
Figure 1 illustrates the robotic tools used in both the coursework and laboratory
projects. These tools support hands-on learning in control systems, embedded program
ming, real-time simulation, and mechatronics integration.
J. Sens. Actuator Netw. 2025, 14, 76
24 of 40

Figure 1. Representative university-level robotics and mechatronics platforms. Shown are KUKA
industrial robotic arms, Quanser mechatronics and servo kits, NI myRIO-based embedded systems,
Arduino prototyping platforms, twin-rotor control systems, and Simulink-based modeling inter
faces. These tools support hands-on learning in control systems, system integration, and real-time
robotics applications.

8.2. Project-Based Courses

Several courses within the curriculum are fully structured around open-ended robotics
challenges, providing students with opportunities to engage in applied project-based
learning. Examples include:
• Robotics Design Course: This course challenges students in designing and building
autonomous robotic systems capable of operating in obstacle-rich environments. Em
phasis is placed on hardware/software co-design, sensor integration, and real-time em
bedded control. An exemplary project involves the creation of agricultural robots that
merge mobile platforms with robotic arms for tasks such as crop monitoring and leaf
picking. These robots incorporate 3D-printed components, machine vision systems,
and AI-based decision-making algorithms. As depicted in Figures 2 and 3, students
performed iterative testing of an autonomous agricultural robot, integrating line
following capabilities, manipulator control, and sensor–actuator feedback loops. This
hands-on experience cultivates essential competencies in embedded systems, control
theory, and precision agriculture—core pillars of contemporary robotics education.
• Quanser Autonomous Vehicles Research Studio: As shown in Figure 4, this specialized
lab supports immersive, project-based learning in swarm and cooperative robotics.
Students design and deploy multi-agent systems using autonomous ground vehicles
and aerial drones. The platforms are equipped with high-resolution vision systems
and precision sensors, enabling real-time experimentation with coordination strategies,
distributed control algorithms, and collective intelligence. This environment fosters
a hands-on understanding of complex system dynamics, scalability, and emergent
behavior in swarm robotics applications.
J. Sens. Actuator Netw. 2025, 14, 76
25 of 40

Figure 2. Autonomous agricultural robot platform with robotic arm for leaf picking.
 Figure 3. 3D-printed components integrated into agricultural robot design.
J. Sens. Actuator Netw. 2025, 14, 76
26 of 40

Figure 4. Multi-agent robotic systems used in the Quanser Autonomous Vehicles Research Studio.
This platform enables the study of swarm coordination, decentralized control, and collective behav iors in
autonomous mobile robots, providing hands-on experience with algorithms applicable to
distributed robotics and real-world multi-agent scenarios.

As illustrated in Figure 5, the final seminar serves as a culminating academic event

in which students present their project outcomes to their peers, faculty, and/or industry
mentors. These presentations foster essential skills in technical communication, critical
thinking, and reflective learning. The seminar provides a platform for showcasing pro
totypes, discussing design challenges, and receiving feedback, thereby reinforcing the
academic rigor and practical relevance of the robotics curriculum.
Figure 5. Capstone seminar presentation where students demonstrate and discuss the outcomes of
their robotics projects, highlighting technical design, innovation, and teamwork.

8.3. Capstone Projects

Capstone projects constitute a cornerstone of the senior-level robotics curriculum,
providing students with a rigorous framework to consolidate and apply their multidis-
J. Sens. Actuator Netw. 2025, 14, 76
27 of 40

ciplinary knowledge to real-world, complex engineering problems. These projects foster

innovation, systems-level thinking, and cross-functional teamwork, simulating the collabo
rative and problem-solving environments encountered in both the industry and research.
Through the capstone experience, students engage in the entire engineering lifecycle,
from problem definition and conceptual design to prototyping, integration, testing, and
final presentation, thus preparing them for advanced roles in robotics, automation, and
cyber-physical systems.
Two illustrative examples of recent capstone projects are highlighted below:
• Hybrid Ground/Aerial Robot: This project involved the development of a dual
modality robotic platform designed for long-endurance autonomous mobility across
heterogeneous environments. As shown in Figure 6, the system integrates a wheeled
ground vehicle with a quadrotor drone, thereby enabling terrain-adaptive navigation
and aerial surveillance. Constructed using lightweight 3D-printed components and
powered by an NVIDIA Jetson platform running ROS2, the robot supports real-time
SLAM, LiDAR-based localization, and multi-sensor fusion for perception-driven
autonomy. This project exemplifies the advanced capabilities of embedded systems,
multi-modal locomotion, and autonomous environmental mapping.
 Figure 6. Student-designed hybrid ground–aerial robotic system integrating wheeled mobility with
quadcopter capabilities. The platform supports extended-range autonomous navigation, obstacle
avoidance, and real-time sensor fusion for complex environmental tasks.

• Smart Factory Cyber-Physical System: Another capstone project focused on building a

smart manufacturing prototype aligned with Industry 4.0. As depicted in Figure 7, the
team designed an integrated cyber-physical platform that combine industrial automa
tion, edge computing, and cloud-based monitoring. The key components included a
KUKA KR 6 sixx R900 (Augsburg, Germany) industrial manipulator, Siemens PLC
(Munich, Germany), vision-based inspection module, and web-connected interface.
The robot was programmed using the KUKA Robot Language (KRL), and cloud inte-
J. Sens. Actuator Netw. 2025, 14, 76
28 of 40

gration was achieved via IBM Watson IoT using MQTT and REST protocols. This setup
enabled automated drilling, inspection, and remote diagnostics. This project high
lighted robotics as the central actuator within a smart factory environment, executing
high-precision manipulation, responding to cyber-level decisions, and interacting with
the physical production process. This demonstrated the students’ ability to implement
secure, interoperable, and intelligent robotic systems in modern industrial contexts.
 Figure 7. Industry 4.0-enabled smart factory prototype featuring integration of KUKA robotic
manipulator, PLC systems, and cloud-based monitoring.

8.4. Robotics Competitions

In addition to formal coursework and capstone projects, students are strongly encour
aged to engage in regional and international robotics competitions. These events provide a
high-impact, experiential learning environment that cultivates creativity, resilience, and
collaborative problem-solving. By simulating real-world constraints, such as time pres
sure, hardware limitations, and dynamic task requirements, competitions offer a valuable
extension to traditional classroom instruction.
The scope of these activities spans a diverse array of challenges, including autonomous
firefighting robots, maze navigation, robotic football, and precision line-following systems.
Students also participate in modeling and simulation contests using MATLAB/Simulink,
as well as algorithm-intensive events focused on artificial intelligence, computer vision,
and embedded programming. These hands-on engagements allow participants to deepen
their technical expertise, practice interdisciplinary integration, and stay abreast of current
developments in robotics technologies.
Figures 8 and 9 show student projects developed for robotics competitions, highlight
ing the applications of sensing, control, and autonomous decision-making in constrained
and complex scenarios.
J. Sens. Actuator Netw. 2025, 14, 76
29 of 40
 Figure 8. Autonomous firefighting robot designed and deployed by students during a competitive
event. The robot identifies and extinguishes simulated fire sources using IR sensors, flame detectors,
and an embedded water-spraying mechanism.

Figure 9. Maze-solving robot constructed for a student competition. The robot employs distance
sensors, PID control, and SLAM-based mapping to navigate unknown environments in real time.

8.5. Discussion: The Role of Key Instructional Components in Robotics Education

A holistic robotics curriculum requires careful integration of diverse instructional
components that progressively build student competencies, from foundational technical
skills to advanced system-level thinking and innovation. At German Jordanian University, a
tiered instructional design comprising class projects, laboratory work, project-based
courses, capstone projects, and robotics competitions has proven effective in cultivating
technically proficient, industry-ready graduates.

8.5.1. Class Projects

Class projects serve as the initial touchpoints for experiential learning. Embedded
within core theoretical courses, these projects allow students to apply foundational concepts
J. Sens. Actuator Netw. 2025, 14, 76
30 of 40

to embedded systems, controls, and artificial intelligence in a practical setting. They

promote early engagement, reinforce classroom content, and introduce students to the
basics of systems integration and debugging. The main challenges at this stage include
variability in student preparedness and limitations in project complexity owing to time
and resource constraints. Best practices include scaffolding projects to align with course
objectives and incorporating modular assignments to ensure inclusivity for students with
varying skill levels.

8.5.2. Laboratory Work

Laboratory work provides a structured environment for skill acquisition, offering
hands-on experience by using sensors, actuators, microcontrollers, and commercial robotic
arms. Labs reinforce theoretical knowledge while familiarizing students with standard
industrial tools and protocols. These are critical for developing practical competencies
in circuit integration, embedded programming, and robotic system configuration. One
challenge is maintaining a balance between guided and exploratory learning. Effective lab
design incorporates pre-lab exercises, structured assessments, and a gradual progression
toward open-ended tasks to foster autonomy and problem-solving.

8.5.3. Project-Based Courses

 Project-based courses bridge the gap between structured labs and open-ended design
experience. These courses are built on robotic challenges that require iterative design,
prototyping, and system-level integration. They develop higher-order cognitive skills
such as critical thinking, teamwork, and design trade-off analysis. The iterative nature of
these courses allows experimentation and refinement, mirroring real-world engineering
processes. Challenges include ensuring equitable team participation and managing project
scope. Best practices involve milestone-based grading, peer evaluation, and industry
relevant design briefs.

8.5.4. Capstone Projects

Capstone projects mark the culmination of the robotics learning journey, demanding
the application of interdisciplinary knowledge to solve complex and often ill-defined
problems. These projects simulate industrial- or research-level challenges and encourage
innovation, technical depth, and professional accountability. Students engage in all phases
of the engineering lifecycle, including documentation and presentation. A key challenge
is ensuring sufficient project mentorship, access to specialized resources, and funding
for projects. Successful capstone experiences are often supported by multi-disciplinary
supervision, industry collaboration, and iterative project review.

8.5.5. Robotics Competitions

Participation in robotics competitions offers students a high-stakes, externally vali
dated environment that drives both technical rigor and creative problem-solving. These
events cultivate essential skills such as rapid prototyping, collaborative teamwork under
pressure, and the design of robust, field-ready systems. Additionally, competitions expose
participants to emerging technologies, provide opportunities for peer benchmarking, and
facilitate professional networking. Despite challenges related to resource demands and
team coordination, competitive settings foster experiential learning and innovation beyond
traditional classrooms. To maximize educational value, institutions should promote in
clusive team dynamics and provide comprehensive support through funding, laboratory
access, and faculty mentorships.
J. Sens. Actuator Netw. 2025, 14, 76
31 of 40

8.5.6. Cumulative and Incremental Skill-Building

Structured layering of these instructional elements supports incremental skill devel
opment. Class projects introduce basic design thinking, laboratory work builds hands-on
competence, project-based courses develop integration and teamwork skills, capstone
projects foster systems-level thinking, and competitions enhance adaptability and real
world problem-solving. Collectively, this ecosystem of experiences ensures that students
graduate with not only strong technical foundations, but also the soft skills necessary for
success in the robotics industry and research.
Challenges and Best Practices
Although the integration of robotics has significantly enriched engineering education,
several challenges must be addressed to sustain and scale its impact.
• Resource Limitations: The acquisition and maintenance of advanced hardware and
software platforms can be cost-prohibitive. Strategic partnerships with industry
leaders such as NVIDIA, Boston Dynamics, and Quanser are essential to provide
access to state-of-the-art technologies and funding opportunities.
• Interdisciplinary Coordination: Robotics inherently spans multiple domains, including
mechanical design, control systems, artificial intelligence, and embedded computing.
Aligning learning outcomes and content delivery across departments requires an
intentional collaborative curriculum planning.
• Rapid Technological Evolution: With continuous advancements in areas such as AI,
soft robotics, and edge computing, curricula and laboratory infrastructure must be
updated regularly to remain relevant and forward-looking.
To mitigate these challenges and maximize educational outcomes, the following best
practices were identified:
 • Industry–Academia Partnerships: Collaborations with industry not only provide
mentorship and funding, but also expose students to real-world problem statements,
tools, and workflows, enhancing the relevance of their education.
• Modular Curriculum Design: Structuring the curriculum in modular blocks facilitates
progressive skill development, ranging from introductory topics, such as kinematics
and embedded systems, to advanced subjects such as multi-agent autonomy and
machine vision.
• Utilization of Open Source Tools: Leveraging open source platforms such as ROS,
Gazebo, and TensorFlow democratizes access to robotics education and fosters a
culture of experimentation and innovation.
The Mechatronics Engineering Department at German Jordanian University demon
strates a scalable and sustainable model for experiential and interdisciplinary learning
by systematically embedding robotics into class projects, laboratory work, project-based
courses, capstone projects, and competitive activities. This approach equips students
with deep technical expertise and cultivates the adaptability, creativity, and collaborative
mindset required to lead in the rapidly evolving fields of robotics and intelligent systems.
Integrating robotics experiments into undergraduate education through class projects,
project-based courses, and capstone projects creates a progressive learning pathway that
aligns with academic and industrial needs. Each component builds upon the previous
one, which gradually increases complexity and autonomy. By engaging in these activities,
students gain practical skills, develop creative solutions, and prepare to address the chal
lenges of tomorrow’s technological landscape. This framework not only enhances teaching
effectiveness, but also inspires the next generation of robotics researchers and practitioners.
J. Sens. Actuator Netw. 2025, 14, 76
32 of 40

9. Conclusions and Future Directions

9.1. Conclusions
Robotics is transforming industries by integrating AI, embedded systems, and in
terdisciplinary engineering. This synergy enables advanced automation, precision, and
adaptability, driving innovation in sectors ranging from manufacturing and healthcare to
aerospace and autonomous transportion. By combining computational intelligence with
optimized hardware and system design, robotics enhances efficiency and expands the
technological frontiers.
This paper reviewed the evolution of robotics from early automata to intelligent
systems and provided a taxonomy of robotic types and applications. Key research areas,
such as motion planning, manipulation, and HRI have been explored, highlighting their
growing impact. A major focus was robotics education, in which project-based learning,
labs, and competitions nurtured creativity, systems thinking, and technical fluency across
all academic levels. The integration of ROS into curricula enables modular hands-on
learning in real-time control and algorithm development, thus supporting both education
and innovation.
A case study from the German Jordanian University demonstrated a tiered robotics
curriculum. Incorporating robotics into projects, labs, and capstones, the Mechatronics
Engineering Department equips students with core competencies in embedded systems, AI,
and control. This structured experiential model exemplifies how practical learning bridges
theory with industry readiness.
While this review presents a comprehensive analysis of instructional practices in
robotics education, highlighting approaches such as project-based learning, capstone
courses, competitions, and lab experimentation, the quantitative evaluation of their effec
tiveness remains a limitation. As many of these pedagogical models have only recently
been implemented, empirical outcome data (e.g., student learning gains, performance
metrics, or longitudinal tracking) are not yet available. Section 8.5 offers a qualitative
assessment, emphasizing both benefits and challenges. Future work will focus on collect
ing and analyzing multi-semester data to rigorously evaluate the educational impact and
inform curriculum refinement through evidence-based practices.
9.2. Future Directions
The rapid evolution of robotics demands proactive anticipation of emerging paradigms.
This section outlines seven critical trajectories shaping the next decade of robotics research
and education, with an emphasis on specific implementation strategies, costs, expected
outcomes, and potential obstacles.

9.2.1. Embodied AI and Neuromorphic Computing

Recent progress in deep learning and large language models (LLMs) has provided
opportunities to develop robotic systems with human-like reasoning and environmental
understanding [113]. However, these models require substantial computational power and
may lack adaptability to resource-constrained environments.
A promising implementation path involves integrating neuromorphic processors with
SNNs to enable real-time decision-making at the edge [10]. When combined with morpho
logical computation, in which a robot’s physical structure contributes to computation, these
systems offer improved energy efficiency, robustness, and adaptability. Future systems
must address sim-to-real gaps through physics-aware learning frameworks [114] and a
co-design methodology where control algorithms are developed in tandem with compliant
robotic morphologies, such as soft limbs or tendon-driven actuators.
J. Sens. Actuator Netw. 2025, 14, 76
33 of 40

Anticipated outcome: Robots capable of real-time, adaptive behavior in unstructured

environments (e.g., search-and-rescue, elder care) with lower power consumption, reduced
controller complexity, and improved autonomy in unstructured environments.
Obstacles: Lack of mature development tools and limited standardization; hardware
availability constraints due to limited off-the-shelf neuromorphic systems; high initial R&D
expenses due to specialized hardware and fabrication.

9.2.2. Human-Centric Collaborative Robotics

Future cobots must ensure both safety and natural interaction in shared human–robot
workspaces. Key implementation strategies include the following:
• Developing multi-modal perception systems (vision, force, voice) for real-time human–
robot interaction [115].
• Incorporating affective computing for emotional recognition [116].
• Establishing trust calibration protocols across user demographics and cultural contexts
through user studies and human trials.
Anticipated outcome: Safer, more intuitive cobots usable in healthcare, services,
and manufacturing.
Obstacles: Ethical concerns, privacy in emotion-sensing, cultural variability in human–
robot trust dynamics, and additional costs for regulatory compliance.

9.2.3. Sustainable Robotics Ecosystem

To align robotics with sustainability goals, recommended strategies include:
• Adopting lifecycle analysis (LCA) tools during robot design [117].
• Using biodegradable materials (e.g., soft robots made of gelatin-based or mycelium
structures) [118].
• Integrating low-power electronics and energy harvesting systems [119].
Anticipated outcomes: Circular economy-compliant robotic platforms with reduced
carbon footprints, minimal lifecycle waste, and longer off-grid deployment capacity.
Obstacles: Trade-offs in performance and durability of eco-materials; limited avail
ability of recyclable actuators and batteries; cost for LCA adoption and the integration of
biodegradable materials and energy harvesting modules.

9.2.4. Challenges and Future Prospects in University Robotics Education

University-level robotics education is undergoing rapid transformation, driven by
technological advancements and the growing societal demand for automation and in
telligent systems. Adaptive cognitive tutoring and AI-powered personalized learning
 platforms [120] promise to tailor content delivery according to individual learning styles
and progress. Meanwhile, immersive technologies—such as virtual reality (VR), augmented
reality (AR), and digital twins—facilitate scalable, hands-on experimentation, especially
when physical robotics hardware is inaccessible [121]. Recent AI-assisted classroom behav
ior analysis has shown measurable improvements in engineering education engagement
and outcomes [122], while studies on mixed reality (MR) device adoption have highlighted
educators’ increasing acceptance of immersive tools as part of pedagogical innovation [123].
These innovations are supported by open source modular kits and 5G-enabled phygital
labs, that integrate tangible components with real-time virtual simulations.
Despite these promising developments, several persistent challenges hinder the full
realization of the potential of robotics education [124–126]:
1. Resource Inequality: Many institutions, especially in low-income regions, lack access
to modern robotics infrastructure, which limits experiential learning.
J. Sens. Actuator Netw. 2025, 14, 76
34 of 40

2. Curricular Discontinuity: Robotics remains fragmented across disciplines (e.g., me

chanical engineering, computer science), lacking cohesive, interdisciplinary curricula.
3. Insufficient Industry Alignment: Educational programs often lag behind industrial
trends, leaving graduates underprepared for evolving job market demands.
4. Limited Undergraduate Research Exposure: Few opportunities exist for undergradu ates to
participate in real research, which stifles early critical thinking and innovation.
To address these gaps, the following forward-looking strategies are proposed:
• Co-designed Curricula: Partnering with industry to develop course content, capstone
projects, and internships ensures alignment with emerging technological needs.
• Research-Integrated Teaching: Embedding active faculty research projects into under
graduate coursework fosters deeper learning and innovation.
• Remote and Cloud Robotics Labs: Digital twin systems and remote-access labs
democratize access to high-quality robotics education across geographical and
economic boundaries.
• Ecosystem Integration: Robotics programs should be embedded within innovation
ecosystems such as incubators, smart factories, and research centers to enhance trans
lational skills and entrepreneurship.
As robotics extends into sectors such as healthcare, sustainability, and domestic au
tomation, academic programs must evolve to not only develop technical excellence but
also cultivate ethical, inclusive, and socially responsive innovation. The future of robotics
education lies in bridging research, industry, and pedagogy to equip learners with the
technical and human dimensions of this transformative field.

9.2.5. Quantum-Enhanced Robotics

Quantum technologies hold promise for revolutionizing robot sensing and decision
making. The key implementation steps are as follows:
• Adopting quantum machine learning algorithms (e.g., QAOA) for optimization in
multi-agent navigation or object recognition tasks [73,127].
• Deploying quantum sensors in field robotics for high-precision localization, particu
larly in GPS-denied environments [128].
• Testing hybrid quantum-classical systems in simulation environments before transi
tioning to physical robot control.
Anticipated outcome: Breakthroughs in real-time motion planning, ultra-precise
indoor/outdoor navigation, and improved computational performance in complex tasks.
Obstacles: The immaturity of quantum hardware, steep learning curves, limited
availability of deployable devices, high costs associated with expensive quantum devices
and simulators, and need for specialized maintenance and operation.

9.2.6. Ethical and Regulatory Foundations

As robotics becomes increasingly integrated into society, there is a pressing need
 for robust ethical frameworks and policy guidelines. Addressing concerns related to
privacy, security, and bias is crucial to ensure the responsible development and deployment
of robotic technologies. To ensure responsible development, the following initiatives
are crucial:
• Integration of robot ethics modules into core engineering curricula, promoting aware
ness of bias, safety, and fairness.
• Adoption of international safety and performance standards, during design and
certification, such as
J. Sens. Actuator Netw. 2025, 14, 76
35 of 40

– ISO/TC 299, the International Organization for Standardization Technical Com

mittee on Robotics.
– IEEE IAB/SCSA, IEEE Industry Activities Board/Standards Coordinating Sub
committee on Autonomous Systems [129].
• Establishment of interdisciplinary ethics boards for large-scale robotics research
projects, especially those involving AI or artificial general intelligence (AGI) [130].
Anticipated outcome: Trustworthy robotic systems that can be deployable in health
care, defense, and public services while ensuring compliance with global safety and
equity standards.
Obstacles: Evolving legal landscapes, cross-border inconsistencies, balancing innova
tion versus oversight, and cost of compliance testing.

Author Contributions: Conceptualization, M.R., H.E., N.A., N.R and G.A.-r.; Methodology, M.R.
and N.A.; Software, M.R.; Validation, M.R., N.A., G.A.-r. H.E. and N.R.; Formal analysis, M.R. and
N.A.; Investigation, M.R., N.A., G.A.-r., H.E. and N.R.; Resources, M.R.; Data curation, M.R.;
Writing—original draft, M.R.; Writing—review & editing, M.R., N.A., G.A.-r. H.E. and N.R.; Project
administration, M.R. All authors have read and agreed to the published version of the manuscript.

Funding: This research received no external funding.

Institutional Review Board Statement: Not applicable.

Informed Consent Statement: Not applicable.

Data Availability Statement: No new data were created or analyzed in this study. Data sharing is
not applicable to this article.

Conflicts of Interest: The authors declare no conflicts of interest.

References
1. Choset, H.; Lynch, K.M.; Hutchinson, S.; Kantor, G.; Burgard, W.; Kavraki, L.E.; Thrun, S. Principles of Robot Motion: Theory,
Algorithms, and Implementations; MIT Press: Cambridge, MA, USA, 2005.
2. Siciliano, B.; Khatib, O. (Eds.) Springer Handbook of Robotics, 2nd ed.; Springer: Berlin/Heidelberg, Germany, 2016. 3. Licardo, J.T.;
Domjan, M.; Orehovaˇcki, T. Intelligent Robotics—A Systematic Review of Emerging Technologies and Trends. Electronics 2024, 13,
542. [CrossRef]
4. Niku, S.B. Introduction to Robotics: Analysis, Control, Applications, 3rd ed.; John Wiley & Sons: Hoboken, NJ, USA, 2019. 5. Ren, M.;
Chen, N.; Qiu, H. Human-machine Collaborative Decision-making: An Evolutionary Roadmap Based on Cognitive Intelligence. Int. J.
Soc. Robot. 2023, 15, 1101–1114. [CrossRef]
6. Song, Q.; Zhao, Q. Recent Advances in Robotics and Intelligent Robots Applications. Appl. Sci. 2024, 14, 4279. [CrossRef] 7. Sheridan,
T.B. Human–Robot Interaction: Status and Challenges. Hum. Factors 2016, 58, 525–532. [CrossRef] [PubMed] 8. Ryalat, M.; Franco, E.;
Elmoaqet, H.; Almtireen, N.; Al-Refai, G. The Integration of Advanced Mechatronic Systems into Industry 4.0 for Smart Manufacturing.
Sustainability 2024, 16, 8504. [CrossRef]
9. Harashima, F.; Suzuki, S. Intelligent mechatronics and robotics. In Proceedings of the 2008 IEEE International Conference on
Emerging Technologies and Factory Automation, Hamburg, Germany, 15–18 September 2008; pp. xviii–xix. 10. Yang, Y.; Bartolozzi, C.;
Zhang, H.H.; Nawrocki, R.A. Neuromorphic electronics for robotic perception, navigation and control: A survey. Eng. Appl. Artif. Intell. 2023,
126, 106838. [CrossRef]
11. Sut, D.J.; Sethuramalingam, P. Soft manipulator for soft robotic applications: A review. J. Intell. Robot. Syst. 2023, 108, 10.
[CrossRef]
12. Lepuschitz, W.; Koppensteiner, G.; Balogh, R.; Obdržálek, D. Robotics in Education; Springer: Berlin/Heidelberg, Germany, 2022. 13.
Vrochidou, E.; Manios, M.; Papakostas, G.A.; Aitsidis, C.N.; Panagiotopoulos, F. Open-Source Robotics: Investigation on Existing
Platforms and Their Application in Education. In Proceedings of the 2018 26th International Conference on Software,
Telecommunications and Computer Networks (SoftCOM), Split, Croatia, 13–15 September 2018; pp. 1–6. 14. Chevalier, M.; Giang,
C.; Piatti, A.; Mondada, F. Fostering computational thinking through educational robotics: A model for creative computational problem
solving. Int. J. STEM Educ. 2020, 7, 39. [CrossRef]
15. Phan, M.H.; Ngo, H.Q.T. A Multidisciplinary Mechatronics Program: From Project-Based Learning to a Community-Based
Approach on an Open Platform. Electronics 2020, 9, 954. [CrossRef]
J. Sens. Actuator Netw. 2025, 14, 76
36 of 40

16. Evripidou, S.; Georgiou, K.; Doitsidis, L.; Amanatiadis, A.A.; Zinonos, Z.; Chatzichristofis, S.A. Educational Robotics: Platforms,
Competitions and Expected Learning Outcomes. IEEE Access 2020, 8, 219534–219562. [CrossRef]
17. Rosillo, N.; Montés, N.; Alves, J.P.; Ferreira, N.M.F. A generalized Matlab/ROS/Robotic platform framework for teaching robotics. In
Proceedings of the Robotics in Education: Current Research and Innovations 10, Vienna, Austria, 10–12 April 2020; Springer:
Berlin/Heidelberg, Germany, 2020; pp. 159–169.
18. Internation Federation of Robotics, I.F. World Robotics Report 2023: Industrial and Service Robots. Available online: https://ifr
org.webpkgcache.com/doc/-/s/ifr.org/img/worldrobotics/2023_WR_extended_version.pdf (accessed on 15 February 2025). 19. World
Economic Forum. Search Results for “Robot”. Available online: https://ifr.org/ (accessed on 15 February 2025). 20. Statista. Forecast of the
Robotics Market Worldwide; Statista: Hamburg, Germany, 2025.
21. Dixon, J.; Hong, B.; Wu, L. The Robot Revolution: Managerial and Employment Consequences for Firms. Manag. Sci. 2021, 67,
5586–5605. [CrossRef]
22. Rosheim, M.E. Robot Evolution: The Development of Anthrobotics; John Wiley & Sons: Hoboken, NJ, USA, 1994. 23. Al-Jazari, I. The
Book of Knowledge of Ingenious Mechanical Devices; Springer: Berlin/Heidelberg, Germany, 1974; Originally Written in 1206.
24. Herath, D.; St-Onge, D. Foundations of Robotics: A Multidisciplinary Approach with Python and ROS; Springer: Berlin/Heidelberg,
Germany, 2022.
25. Elices, J. Ismail al-Jazari, the Muslim Inventor whom Some Call the Father of Robotics. Available online: https://www.
nationalgeographic.com/history/history-magazine/article/ismail-al-jazari-muslim-inventor-called-father-robotics (accessed on 30
January 2025).
26. Herman, D. A Renaissance Robot. Mech. Eng. 1998, 120, 80–82. [CrossRef]
27. Gasparetto, A.; Scalera, L. A brief history of industrial robotics in the 20th century. Adv. Hist. Stud. 2019, 8, 24–35. [CrossRef] 28.
Kose, T.; Yamano, H.; Sakata, I. Detecting Emerging Complex Technological Fields in Robotics. In Proceedings of the Portland
International Conference on Management of Engineering and Technology, Portland, OR, USA, 25–29 August 2019; pp. 1–12. 29. Soori, M.;
Dastres, R.; Arezoo, B.; Karimi Ghaleh Jough, F. Intelligent robotic systems in Industry 4.0: A review. J. Adv. Manuf. Sci. Technol. 2024,
2024007. [CrossRef]
30. Isaka, S. A Taxonomic Classification and Identification System for Robots: Abstract. In Proceedings of the 2024 IEEE International
Conference on Systems, Man, and Cybernetics (SMC), Kuching, Malaysia, 6–10 October 2024; pp. 3799–3800. 31. Ben-Ari, M.; Mondada,
F. Robots and Their Applications. In Elements of Robotics; Springer: Cham, Switzerland, 2018; pp. 1–20. 32. Beer, J.M.; Fisk, A.D.;
Rogers, W.A. Toward a framework for levels of robot autonomy in human-robot interaction. J. Hum. Robot Interact. 2014, 3, 74–99.
[CrossRef] [PubMed]
33. Basañez, L.; Nuño, E.; Aldana, C.I. Teleoperation and Level of Automation. In Springer Handbook of Automation; Nof, S.Y., Ed.;
Springer: Berlin/Heidelberg, Germany, 2023; pp. 457–482.
34. Rubio, F.; Valero, F.; Llopis-Albert, C. A review of mobile robots: Concepts, methods, theoretical framework, and applications.
Int. J. Adv. Robot. Syst. 2019, 16, 1729881419839596. [CrossRef]
35. Mobed, D.A.O.; Wodehouse, A.; Maier, A. The aesthetics of robot design: Towards a classification of morphologies. Proc. Des.
Soc. 2024, 4, 2413–2422. [CrossRef]
36. Paul, C. Morphological computation: A basis for the analysis of morphology and control requirements. Robot. Auton. Syst. 2006, 54,
619–630. [CrossRef]
37. Yang, G.; Hu, S. Review of Robotics Technologies and Its Applications. In Proceedings of the 2023 International Conference on
Advanced Robotics and Mechatronics (ICARM), Sanya, China, 8–10 July 2023; pp. 322–329.
38. Luo, J.; Zhou, X.; Zeng, C.; Jiang, Y.; Qi, W.; Xiang, K.; Pang, M.; Tang, B. Robotics Perception and Control: Key Technologies and
Applications. Micromachines 2024, 15, 531. [CrossRef] [PubMed]
39. Che, C.; Zheng, H.; Huang, Z.; Jiang, W.; Liu, B. Intelligent Robotic Control System Based on Computer Vision Technology. arXiv 2024,
arXiv:2404.01116. [CrossRef]
40. Huang, Z.; Shen, Y.; Li, J.; Fey, M.; Brecher, C. A Survey on AI-Driven Digital Twins in Industry 4.0: Smart Manufacturing and
Advanced Robotics. Sensors 2021, 21, 6340. [CrossRef] [PubMed]
41. Tantawi, K.H.; Sokolov, A.; Tantawi, O. Advances in Industrial Robotics: From Industry 3.0 Automation to Industry 4.0
Collaboration. In Proceedings of the 2019 4th Technology Innovation Management and Engineering Science International
Conference (TIMES-iCON), Bangkok, Thailand, 11–13 December 2019; pp. 1–4.
42. Soori, M.; Arezoo, B.; Dastres, R. Artificial intelligence, machine learning and deep learning in advanced robotics, a review. Cogn.
Robot. 2023, 3, 54–70. [CrossRef]
43. Ray, P.P. Internet of Robotic Things: Concept, Technologies, and Challenges. IEEE Access 2016, 4, 9489–9500. [CrossRef] 44.
Tanwani, A.K.; Mor, N.; Kubiatowicz, J.; Gonzalez, J.E.; Goldberg, K. A Fog Robotics Approach to Deep Robot Learning:
Application to Object Recognition and Grasp Planning in Surface Decluttering. In Proceedings of the 2019 International Conference
on Robotics and Automation (ICRA), Montreal, QC, Canada, 20–24 May 2019; pp. 4559–4566.
J. Sens. Actuator Netw. 2025, 14, 76
37 of 40
45. Treratanakulchai, S.; Franco, E.; Garriga-Casanovas, A.; Minghao, H.; Kassanos, P.; y Baena, F.R. Development of a 6 DOF
Soft Robotic Manipulator with Integrated Sensing Skin. In Proceedings of the 2022 IEEE/RSJ International Conference on Intelligent
Robots and Systems (IROS), Kyoto, Japan, 23–27 October 2022; pp. 6944–6951.
46. Wang, L.; Chen, K.; Franco, E. Robust and Adaptive Control of a Soft Continuum Manipulator for Minimally Invasive Surgery. Robotics
2024, 13, 162. [CrossRef]
47. Cheraghi, A.R.; Shahzad, S.; Graffi, K. Past, Present, and Future of Swarm Robotics. In Proceedings of the Intelligent Systems
and Applications; Arai, K., Ed.; Elsevier: Cham, Switzerland, 2022; pp. 190–233.
48. Dabass, V.; Sangwan, S. Strategic allocation: Exploring optimization techniques in multi-robot systems. Int. J. Intell. Robot. Appl. 2025.
[CrossRef]
49. Rivera, R.; Amorim, M.; Reis, J. Robotic Services in Smart Cities: An Exploratory Literature Review. In Proceedings of the 2020 15th
Iberian Conference on Information Systems and Technologies (CISTI), Seville, Spain, 24–27 June 2020; pp. 1–7. 50. Roldán-Gómez, J.J.;
Garcia-Aunon, P.; Mazariegos, P.; Barrientos, A. SwarmCity project: Monitoring traffic, pedestrians, climate, and pollution with an aerial
robotic swarm. Pers. Ubiquitous Comput. 2022, 26, 1151–1167. [CrossRef] 51. Oliveira, L.F.P.; Moreira, A.P.; Silva, M.F. Advances in
Agriculture Robotics: A State-of-the-Art Review and Challenges Ahead. Robotics 2021, 10, 52. [CrossRef]
52. Rose, D.C.; Lyon, J.; de Boon, A.; Hanheide, M.; Pearson, S. Responsible development of autonomous robotics in agriculture. Nat.
Food 2021, 2, 306–309. [CrossRef] [PubMed]
53. Yang, G.Z.; Bellingham, J.; Dupont, P.E.; Fischer, P.; Floridi, L.; Full, R.; Jacobstein, N.; Kumar, V.; McNutt, M.; Merrifield, R.; et al. The
grand challenges of Science Robotics. Sci. Robot. 2018, 3, 7650. [CrossRef] [PubMed]
54. Billard, A.; Asfour, T.; Khatib, O. Robotics Research; Springer: Berlin/Heidelberg, Germany, 2023; Volume 27. 55. Sun, Y.; Falco, J.;
Roa, M.A.; Calli, B. Research Challenges and Progress in Robotic Grasping and Manipulation Competitions. IEEE Robot. Autom.
Lett. 2022, 7, 874–881. [CrossRef]
56. Babin, V.; Gosselin, C. Mechanisms for Robotic Grasping and Manipulation. Annu. Rev. Control. Robot. Auton. Syst. 2021, 4,
573–593. [CrossRef]
57. Hernandez, J.; Sunny, M.S.H.; Sanjuan, J.; Rulik, I.; Zarif, M.I.I.; Ahamed, S.I.; Ahmed, H.U.; Rahman, M.H. Current Designs of Robotic
Arm Grippers: A Comprehensive Systematic Review. Robotics 2023, 12, 5. [CrossRef]
58. Billard, A.; Kragic, D. Trends and challenges in robot manipulation. Science 2019, 364, eaat8414. [CrossRef] [PubMed] 59. Zhou, C.;
Huang, B.; Fränti, P. A review of motion planning algorithms for intelligent robots. J. Intell. Manuf. 2022, 33, 387–424. [CrossRef]
60. Rybczak, M.; Popowniak, N.; Lazarowska, A. A Survey of Machine Learning Approaches for Mobile Robot Control. Robotics
2024, 13, 12. [CrossRef]
61. Wang, J.; Zhang, T.; Ma, N.; Li, Z.; Ma, H.; Meng, F.; Meng, M.Q.H. A survey of learning-based robot motion planning. IET Cyber Syst.
Robot. 2021, 3, 302–314. [CrossRef]
62. Yang, J.; Wang, C.; Jiang, B.; Song, H.; Meng, Q. Visual Perception Enabled Industry Intelligence: State of the Art, Challenges and
Prospects. IEEE Trans. Ind. Inform. 2021, 17, 2204–2219. [CrossRef]
63. Bai, Y.; Zhang, B.; Xu, N.; Zhou, J.; Shi, J.; Diao, Z. Vision-based navigation and guidance for agricultural autonomous vehicles and
robots: A review. Comput. Electron. Agric. 2023, 205, 107584. [CrossRef]
64. Rodríguez-Guerra, D.; Sorrosal, G.; Cabanes, I.; Calleja, C. Human-Robot Interaction Review: Challenges and Solutions for
Modern Industrial Environments. IEEE Access 2021, 9, 108557–108578. [CrossRef]
65. Gervasi, R.; Barravecchia, F.; Mastrogiacomo, L.; Franceschini, F. Applications of affective computing in human-robot interaction: State-
of-art and challenges for manufacturing. Proc. Inst. Mech. Eng. B Part J. Eng. Manuf. 2023, 237, 815–832. [CrossRef] 66. Subramanian,
K.; Thomas, L.; Sahin, M.; Sahin, F. Supporting Human–Robot Interaction in Manufacturing with Augmented Reality and Effective
Human–Computer Interaction: A Review and Framework. Machines 2024, 12, 706. [CrossRef] 67. Mohebbi, A. Human-robot interaction in
rehabilitation and assistance: A review. Curr. Robot. Rep. 2020, 1, 131–144. [CrossRef] 68. Seyito˘glu, F.; Ivanov, S. Robots and emotional
intelligence: A thematic analysis. Technol. Soc. 2024, 77, 102512. [CrossRef] 69. Hao, Y.; Zhang, S.; Fang, B.; Sun, F.; Liu, H.; Li, H. A
Review of Smart Materials for the Boost of Soft Actuators, Soft Sensors, and Robotics Applications. Chin. J. Mech. Eng. 2022, 35, 37.
[CrossRef]
70. Ogenyi, U.E.; Liu, J.; Yang, C.; Ju, Z.; Liu, H. Physical Human–Robot Collaboration: Robotic Systems, Learning Methods,
Collaborative Strategies, Sensors, and Actuators. IEEE Trans. Cybern. 2021, 51, 1888–1901. [CrossRef] [PubMed] 71. Raj, R.; Kos, A.
Study of Human–Robot Interactions for Assistive Robots Using Machine Learning and Sensor Fusion Technologies. Electronics 2024, 13,
3285. [CrossRef]
72. Bogue, R. Quantum technologies in robotics: A preliminary appraisal. Ind. Robot. Int. J. Robot. Res. Appl. 2025, 52, 1–8. [CrossRef] 73.
Taghavi, M. Quantum Computing and Neuromorphic Computing for Safe, Reliable, and explainable Multi-Agent Reinforcement Learning:
Optimal Control in Autonomous Robotics. arXiv 2024, arXiv:2408.03884. [CrossRef]
J. Sens. Actuator Netw. 2025, 14, 76
38 of 40

74. Du, Z.; Li, H. Research on Application of Improved Quantum Optimization Algorithm in Path Planning. Appl. Sci. 2024, 14, 4613.
[CrossRef]
75. Aitsam, M.; Davies, S.; Di Nuovo, A. Neuromorphic Computing for Interactive Robotics: A Systematic Review. IEEE Access 2022, 10,
122261–122279. [CrossRef]
76. Paredes-Vallés, F.; Hagenaars, J.J.; Dupeyroux, J.; Stroobants, S.; Xu, Y.; de Croon, G.C.H.E. Fully neuromorphic vision and control
for autonomous drone flight. Sci. Robot. 2024, 9, eadi0591. [CrossRef] [PubMed]
77. Niedermeier, L.; Dutt, N.; Krichmar, J.L. An integrated toolbox for creating neuromorphic edge applications. Neuromorphic
Comput. Eng. 2025, 5, 014003. [CrossRef]
78. Arents, J.; Greitans, M. Smart industrial robot control trends, challenges and opportunities within manufacturing. Appl. Sci. 2022, 12,
937. [CrossRef]
79. Ryalat, M.; ElMoaqet, H.; AlFaouri, M. Design of a Smart Factory Based on Cyber-Physical Systems and Internet of Things
towards Industry 4.0. Appl. Sci. 2023, 13, 2156. [CrossRef]
80. Dupont, P.E.; Nelson, B.J.; Goldfarb, M.; Hannaford, B.; Menciassi, A.; O’Malley, M.K.; Simaan, N.; Valdastri, P.; Yang, G.Z. A
decade retrospective of medical robotics research from 2010 to 2020. Sci. Robot. 2021, 6, eabi8017. [CrossRef] [PubMed] 81. Singh, S.;
Vaishnav, R.; Gautam, S.; Banerjee, S. Agricultural Robotics: A Comprehensive Review of Applications, Challenges and Future
Prospects. In Proceedings of the 2024 2nd International Conference on Artificial Intelligence and Machine Learning Applications Theme:
Healthcare and Internet of Things (AIMLA), Namakkal, India, 15–16 March 2024; pp. 1–8. 82. Shamout, M.; Ben-Abdallah, R.; Alshurideh,
M.; Alzoubi, H.; Kurdi, B.a.; Hamadneh, S. A conceptual model for the adoption of autonomous robots in supply chain and logistics industry.
Uncertain Supply Chain. Manag. 2022, 10, 577–592. [CrossRef] 83. Ajith, V.S.; Jolly, K. Unmanned aerial systems in search and rescue
applications with their path planning: A review. J. Phys. Conf. Ser. 2021, 2115, 012020. [CrossRef]
84. Scopus. Scopus Sources CiteScore. Available online: https://www.scopus.com/sources.uri (accessed on 10 February 2025). 85.
Scholar, G. Google Scholar: Top Publication. Available online: https://scholar.google.com/citations?view_op=top_venues&hl=
en&vq=eng_robotics (accessed on 10 February 2025).
86. Alam, A.; Mohanty, A. Integrated constructive robotics in education (ICRE) model: A paradigmatic framework for transformative learning
in educational ecosystem. Cogent Educ. 2024, 11, 2324487. [CrossRef]
87. Petraki, E.; Herath, D. Teaching and Learning Robotics: A Pedagogical Perspective. In Foundations of Robotics: A Multidisciplinary
Approach with Python and ROS; Herath, D., St-Onge, D., Eds.; Springer: Singapore, 2022; pp. 43–62.
88. Pozzi, M.; Prattichizzo, D.; Malvezzi, M. Accessible Educational Resources for Teaching and Learning Robotics. Robotics 2021, 10, 38.
[CrossRef]
89. López-Belmonte, J.; Segura-Robles, A.; Moreno-Guerrero, A.J.; Parra-González, M.E. Robotics in Education: A Scientific Mapping of
the Literature in Web of Science. Electronics 2021, 10, 291. [CrossRef]
90. Atman Uslu, N.; Yavuz, G.O.; Koccak Usluel, Y. A systematic review study on educational robotics and robots. Interact. Learn.
Environ. 2023, 31, 5874–5898. [CrossRef]
91. He, Y.; Liang, L. Application of Robotics in Higher Education in Industry 4.0 Era. Univers. J. Educ. Res. 2019, 7, 1612–1622.
[CrossRef]
92. Craig, J.J. Introduction to Robotics: Mechanics and Control, 4th ed.; Pearson: London, UK, 2017.
93. Quigley, M.; Conley, K.; Gerkey, B.; Faust, J.; Foote, T.; Leibs, J.; Wheeler, R.; Ng, A.Y. ROS: An open-source Robot Operating
System. In Proceedings of the ICRA Workshop on Open Source Software, Kobe, Japan, 12–17 May 2009. 94. Macenski, S.; Foote, T.;
Gerkey, B.; Lalancette, C.; Woodall, W. Robot Operating System 2: Design, architecture, and uses in the wild. Sci. Robot. 2022, 7,
eabm6074. [CrossRef] [PubMed]
95. MathWorks. MATLAB and Simulink for Robotics. 2023. Available online: https://www.mathworks.com/solutions/robotics.html (accessed
on 3 March 2025).
96. Corke, P. Robotics, Vision and Control: Fundamental Algorithms in MATLAB, 3rd ed.; Springer: Berlin/Heidelberg, Germany, 2023. 97.
Koubaa, A. Robot Operating System (ROS): The Complete Reference; Springer: Berlin/Heidelberg, Germany, 2021. 98. Corke, P.
Robotics, Vision and Control: Fundamental Algorithms in Python, 2nd ed.; Springer: Berlin/Heidelberg, Germany, 2021. [CrossRef]
99. OpenCV Team. OpenCV: Open Source Computer Vision Library. 2025. Available online: https://opencv.org/ (accessed on 28
February 2025).
100. Farley, A.; Wang, J.; Marshall, J.A. How to pick a mobile robot simulator: A quantitative comparison of CoppeliaSim, Gazebo,
MORSE and Webots with a focus on accuracy of motion. Simul. Model. Pract. Theory 2022, 120, 102629. [CrossRef] 101. Lee, H.J.; Yi, H.
Development of an Onboard Robotic Platform for Embedded Programming Education. Sensors 2021, 21, 3916. [CrossRef] [PubMed]
102. NVIDIA Corporation. NVIDIA Jetson Orin: Embedded Systems for Autonomous Machines. 2025. Available online: https:
//www.nvidia.com/en-us/autonomous-machines/embedded-systems/jetson-orin/ (accessed on 28 February 2025).
J. Sens. Actuator Netw. 2025, 14, 76
39 of 40

103. Castelli, K.; Giberti, H. Additive Manufacturing as an Essential Element in the Teaching of Robotics. Robotics 2019, 8, 73.
[CrossRef]
104. Yeong, D.J.; Velasco-Hernandez, G.; Barry, J.; Walsh, J. Sensor and Sensor Fusion Technology in Autonomous Vehicles: A Review.
Sensors 2021, 21, 2140. [CrossRef] [PubMed]
105. Li, P.; Liu, X. Common Sensors in Industrial Robots: A Review. In Proceedings of the Journal of Physics: Conference Series,
Proceedings of the 3rd International Conference on Artificial Intelligence (ICAI 2019), Istanbul, Turkey, 26–28 October 2019; IOP
Publishing: Bristol, UK, 2019; Volume 1267.
106. Djuric, A.; Rickli, J.; Sefcovic, J.; Hutchison, D.; Goldin, M.M. Integrating Collaborative Robots in Engineering and Engineering
Technology Programs. ASME Int. Mech. Eng. Congr. Expo. 2018, 5, V005T07A013.
107. Quanser Inc. Quanser Academic Resources. 2025. Available online: https://www.quanser.com/resource-type/academic
resources/ (accessed on 28 March 2025).
108. Clearpath Robotics. Husky Unmanned Ground Vehicle (UGV). 2025. Available online: https://clearpathrobotics.com/husky-a3 00-
unmanned-ground-vehicle-robot/ (accessed on 28 March 2025).
109. LEGO Education. SPIKE Prime and Mindstorms for Robotics Learning. 2025. Available online: https://spike.legoeducation.com/
(accessed on 28 March 2025).
110. Cervera, E. Run to the Source: The Effective Reproducibility of Robotics Code Repositories. IEEE Robot. Autom. Mag. 2024,
31, 125–134. [CrossRef]
111. Open Robotics. Open Robotics. ROS Developer Documentation. 2025. Available online: https://docs.ros.org/ (accessed on 3
April 2025).
112. AlBatati, A.S.; Koubaa, A.; Abdelkader, M. ROS 2 in a Nutshell: A Survey. Preprints 2024.
113. Kwon, T.; Palo, N.D.; Johns, E. Language Models as Zero-Shot Trajectory Generators. IEEE Robot. Autom. Lett. 2024, 9, 6728–6735.
[CrossRef]
114. Rizzardo, C.; Chen, F.; Caldwell, D. Sim-to-real via latent prediction: Transferring visual non-prehensile manipulation policies. Front.
Robot. AI 2023, 9, 1067502. [CrossRef] [PubMed]
115. Wong, C.Y.; Vergez, L.; Suleiman, W. Vision- and Tactile-Based Continuous Multimodal Intention and Attention Recognition for Safer
Physical Human–Robot Interaction. IEEE Trans. Autom. Sci. Eng. 2024, 21, 3205–3215. [CrossRef] 116. Cho, Y.J.; Cho, M.; Jang, M.
Social Robot Intelligence Quotient to Measure Human-Robot Interaction Performance for Human-Care Service Robots. In Proceedings of
the 2023 20th International Conference on Ubiquitous Robots (UR), Honolulu, HI, USA, 25–28 June 2023; pp. 616–621.
117. Battarra, I.; Accorsi, R.; Lupi, G.; Manzini, R. Life cycle assessment of an automated multi-cellular case-picking system. J. Manuf.
Syst. 2025, 79, 419–434. [CrossRef]
118. Hartmann, F.; Baumgartner, M.; Kaltenbrunner, M. Becoming Sustainable, The New Frontier in Soft Robotics. Adv. Mater. 2021, 33,
2004413. [CrossRef] [PubMed]
119. Hajra, S.; Panda, S.; Khanberh, H.; Vivekananthan, V.; Chamanehpour, E.; Mishra, Y.K.; Kim, H.J. Revolutionizing self-powered
robotic systems with triboelectric nanogenerators. Nano Energy 2023, 115, 108729. [CrossRef]
120. Halkiopoulos, C.; Gkintoni, E. Leveraging AI in E-Learning: Personalized Learning and Adaptive Assessment through Cognitive
Neuropsychology—A Systematic Analysis. Electronics 2024, 13, 3762. [CrossRef]
121. Khan, Z.H.; Mekid, S. Designing Remote Labs in Outcome-Based Education Using Digital Twin and Metaverse. Available online:
https://teaching.ieee.org/designing-remote-labs-in-outcome-based-education-using-digital-twin-and-metaverse/ (accessed on 7 May
2025).
122. Hu, J.; Huang, Z.; Li, J.; Xu, L.; Zou, Y. Real-time classroom behavior analysis for enhanced engineering education: An AI-assisted
approach. Int. J. Comput. Intell. Syst. 2024, 17, 167. [CrossRef]
123. Chen, Y.; Zou, Y. Enhancing education quality: Exploring teachers’ attitudes and intentions towards intelligent MR devices. Eur. J.
Educ. 2024, 59, e12692. [CrossRef]
124. Pujol, F.A.; Tomás, D. Introducing Sustainability in a Robotic Engineering Degree: A Case Study. Sustainability 2020, 12,
5574. [CrossRef]
125. Chou, H.S.; Thong, L.T.; Chew, H.S.J.; Lau, Y. Barriers and Facilitators of Robot-Assisted Education in Higher Education: A
Systematic Mixed-Studies Review. Technol. Knowl. Learn. 2023, 28, 477–516. [CrossRef]
126. Van Scoy, B.; Jamieson, P.; Chidurala, V. On First-Principle Robot Building in Undergraduate Robotics Education in the Robotic
System Levels Model. Robotics 2025, 14, 70. [CrossRef]
127. Khobragade, P.; Dhankar, P.K.; Titarmare, A.; Dhone, M.; Thakur, S.; Saraf, P. Quantum-Enhanced AI Robotics for
Sustainable Agriculture: Pioneering Autonomous Systems in Precision Farming. In Proceedings of the 2024 International
Conference on Artificial Intelligence and Quantum Computation-Based Sensor Application (ICAIQSA), Nagpur, India, 20–21
December 2024; pp. 1–7.
J. Sens. Actuator Netw. 2025, 14, 76
40 of 40

128. Hohenfeld, H.; Heimann, D.; Wiebe, F.; Kirchner, F. Quantum Deep Reinforcement Learning for Robot Navigation Tasks. IEEE
Access 2024, 12, 87217–87236. [CrossRef]
129. ISO/TC 299 Robotics; ISO: Geneva, Switzerland. 2025. Available online: https://committee.iso.org/home/tc299 (accessed on 1
May 2025).
130. Fahad, M.; Basri, T.; Hamza, M.A.; Faisal, S.; Akbar, A.; Haider, U.; Hajjami, S.E. The Benefits and Risks of Artificial General
Intelligence (AGI). In Artificial General Intelligence (AGI) Security: Smart Applications and Sustainable Technologies; El
Hajjami, S., Kaushik, K., Khan, I.U., Eds.; Springer: Singapore, 2025.

Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual
author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or
property resulting from any ideas, methods, instructions or products referred to in the content.