2024 International Conference on Artificial Intelligence and Quantum Computation-Based Sensor Application (ICAIQSA)

Interactive Smart Robot using raspberry pi 4.

2024 International Conference on Artificial Intelligence and Quantum Computation-Based Sensor Application (ICAIQSA) | 979-8-3315-1795-3/24/$31.00 ©2024 IEEE | DOI: 10.1109/ICAIQSA64000.2024.11021011

Dr. Prof. Vijay Mane Pranav Chougule

Department of Electronics & Telecommunication Engineering Department of Electronics & Telecommunication Engineering
Vishwakarma Institute of Technology, pune Vishwakarma Institute of Technology, pune
Pune, India Pune, India
[email protected] [email protected]

Siddhant Pusate Shyam Pawar

Department of Electronics & Telecommunication Engineering Department of Electronics & Telecommunication Engineering
Vishwakarma Institute of Technology, pune Vishwakarma Institute of Technology, pune
Pune, India Pune, India
[email protected] [email protected]

Abstract —This research paper focuses on the design and Functioning as a multi-functional device, this robot can
construction of an Interactive Smart Robot based on Raspberry listen, understand, fetch information, and speak to the user
Pi 4 system. The aim of the project is to design a voice-controlDC as well. Speech synthesis adds an audio-visual element to
motor robot which is able to answer user questions and search the user interface through application of animation to basic
for information on Wikipedia and read it while dancing. To
allow user-n-Human-robot interaction the system incorporates
robot actions and prompts using pre-recorded texts.
speech recognition, Wikipedia API, and text-to-speech software.
Hardware consists of Raspberry Pi 4, sound sensor, speaker, and This document includes a comprehensive explanation of the
Robo. The software is bordered with the libraries background hardware such as DC motor, software like
SpeechRecognition, gTTS, PyAudio, pygame and controls sound. SpeechRecognition, gTTS, and PyAudio supporting
The experimental work that was carried out has shown the development of the robot. Along with the above, it explains
adequacy of the developed system in recognition of speech with the techniques that were used for audio capturing and
good accuracy and in dealing with spoken dialogue in real time. production as well as speech recognition and speech
The project illustrates that there is a future for Raspberry Pi generation. In addition, the results of skirmishes
driven robotics in the development of such human computer
interaction scenarios.
(experiments) conducted to check the system’s efficacy are
shown, showcasing the possibilities of using Raspberry Pi
Keywords— Interactive Smart Robot, Raspberry Pi 4 Model B, in robotics for building interesting interactive systems and
Voice Control, Speech Recognition, Wikipedia API, Text-to- answering the issues of privacy and control raised in the
Speech Synthesis, Human-Computer Interaction, Robotics, available systems.
Educational Technology.
II. LITERATURE REVIEW
I. INTRODUCTION
Lately, smart interactive robots represent a modern It is not a surprise that different voice-control DC motor
innovation in the integration of human-robot robots and Raspberry Pi based projects have become
communication and Robotic science Its features enable popular recently and so many efforts have been made in
users to experience technological interaction in mastered these areas. Now this particular review seeks to analyze
contexts, that is, they aid users to engage in question and some of the studies that are relevant to the current work on
answer interactions in natural languages. However existing the development of smart interactive robots on the
systems like Amazon Alexa and other voice activated Raspberry Pi platform. The reason for such a trend is the
systems mostly grapple with the issue of outrigger continuous innovation in DC motor robot voice control
microphone engagement which is on throughout the technologies. One of the works by Li and Zhang (2018) [1]
interaction and constitutes a privacy concern and user as well as Wang et al. (2019) [2] investigated ways of
experience limitation. The focus of this project is to devise a making voice recognition strategies more accurate hence
more interactive system that can be controlled by the user in more efficient in clinical applications using deep learning
order to alleviate such problems. strategies for acoustic modeling. The popularity of the
Raspberry Pi in the recent past has made it a very versatile
Since the arrival of the Raspberry Pi 4, an affordable single- device worn by hobbyists for the development of projects
board computer which has many applications, the that are entertaining and enlightening. Upton & Halfacree
implementation of such interactive systems has become (2014) [3] resolve especially deeply the research of the
much easier thanks to the computational power offered and Raspberry Pi promising device and its implementation’s
the various applications available. The main goal of this prospects in such areas as home automation, home robotics,
research paper is the design and development of Interactive and education. In the same way, O’Leary (2016) [4] and
Smart Robot based on Raspberry Pi 4 which supersedes the Rosebrock (2019) [5] research also provides beneficial step
previous versions in the extent of control the users will have by step instructions for building the projects on Raspberry
over themselves hence reducing the effects of continuous Pi including the smart home devices and the voice-
listening. controlled DC motor assistants. An example of research was
done by Norman (2013) [6].

sed use limited to: CENTRE FOR DEVELOPMENT OF ADVANCED COMPUTING - CDAC - Thiruvananthapuram & Kochi. Downloaded on June 11,2025 at 10:19:13 UTC from IEEE Xplore. Re

979-8-3315-1795-3/24/$31.00©2024 IEEE
 (2004) [7] studies the issues conceptual and theoretical of which enables it to be used to boost audio signals of many
interactive system design in the area of human-computer consumer devices.
interaction.

All of the above studies have underscored the importance of

interaction, usability, and user interface design in creating
exciting and productive users and environments.

In addition, Projects such as Google Home and Amazon

Echo have proved the commercial potential of DC motor
assistants with voice activation and smart speakers. These
devices allow users to perform information, entertainment
and home automation operations in a hands free way with
the use of advanced speech recognition and natural
language processing technologies.

This research paper is meant to contribute to the area of Fig 2: PAM8403 Audio Amplifire.
interactive robotics and HCI through the building on the
ideas and methods available in the existing work innovation. 3. SPEAKERS
This project seeks to show that continuous and cheap Speakers are devices that receive audio signals and convert
technology can be deployed to create entertaining and electric energy into sound energy. Take speakers as an
educational experiences for all the people by developing an instance, they are composed of a diaphragm, voice coil and
Interactive Smart Robot with the Raspberry Pi 4. magnet, which are made to move in the air for sound to be
produced. Their specifications include impedance,
III. HARDWARE frequency response, power handling, and sensitivity. In
many applications such as audio systems, loudspeakers are
1. RASPBERRY PI 4 MODEL B very important, Respondents are approaching this challenge
The Raspberry Pi 4 Model B is a small, affordable, single- using distractions effective as internet and mobile phone
board computer developed by the Raspberry Pi Foundation. pertaining to their comments famous and children?
It expands and improves upon its previous generations with Such_devices assisted people function than implementing
a more powerful quad-core ARM Cortex-A72 processor, sound articulate communication of delicate matters.
more memory options such as 4GB of RAM, Ethernet and
Dual Band WiFi and Bluetooth 5.0, USB 3.0 and 4K video
output ports. It is in such low cost and capable of such a
variety of purposes, from education to hobby and even to
small computing applications within research.

Fig 3: Speakers

4. LM393 SOUND SENSOR

The sound sensor LM393 is a permanent electronic
component used in almost all electronics that require sound
detection. Such devices consist of a small microphone that
captures surrounding sound waves and transforms them into
Fig 1: Raspberry pi 4 model B electrical energy. Electric systems that are activated only
when the sub-threshold input-signal is within a certain level
2. PAM8403 AUDIO AMPLIFIRE are called', 'voltage comparators' In other words, when a
PAM8403 is a typical stereo audio power amplifier solution, sound is present, the LM393 output pulsates whether the
effective, compact and cheap that usually appears in devices comment is on the on or off input.
such as portable speakers, headphones and audio systems.
Its working voltage is low and it is a low power consuming
device making it amenable for operation on batteries. Such
is its size and ease of implementation that the PAM8403 is
loved by DIY and electronics hobbyists for almost any
audio amplification projects. It combines of high efficiency
low distortion, along with internal over current protection

sed use limited to: CENTRE FOR DEVELOPMENT OF ADVANCED COMPUTING - CDAC - Thiruvananthapuram & Kochi. Downloaded on June 11,2025 at 10:19:13 UTC from IEEE Xplore. Re
 7. Relay Module
A relay module is an electronic component that acts as a
switch controlled by an electrical signal. It consists of a coil
and one or more sets of contacts. When current flows
through the coil, it generates a magnetic field, which causes
the contacts to open or close, thus completing or
interrupting a circuit. Relay modules are commonly used in
various applications for automation, controlling high-power
devices, and interfacing between different voltage levels.
Fig 4: LM393 Sound Sensor They offer isolation between input and output circuits and
can handle different voltages and currents, making them
5. MICROPHONE versatile for a wide range of applications.
Usually, this calls for the use of a high-quality sound
recorder. A microphone is called also electric looking glass
since it transforms sound energy into a transitory flow of
electric current. These includes an active diaphragm which
vibrates due to sound wave pressure and attached
crossheads such as coils or capacitors which causes them to
move and thereby induce a tone related electric current
proportional to sound waves. Most especially a voltage bias
is required to operate the LM393. In addition, it has a very
good frequency response of up to 20kHz. Other than piezos,
there are inductive microphones and tubing voices also with Fig 7: Relay Module
magnetic ribbon microphones inside where devices
amplifying vocal sounds are fixed. Their applications range IV. METHODOLOGY
from telecommunication systems to sound recording
systems, voice recognition systems and sound The development of the Interactive Smart Robot using the
reinforcement systems. Raspberry Pi 4 involves several key steps, including
hardware setup which hardware do I use in project as above,
software configuration, and implementation of various
functionalities such as speech recognition, information
retrieval, and text-to-speech synthesis. I also provide a
Flowchart for better understanding in Fig 8.

A. Hardware Setup:
To assemble the Raspberry Pi 4, depicted in Fig 1, along
with the necessary peripherals including a microphone (Fig
5), speaker (Fig 3), sound sensor (Fig 4), and DC motor (Fig
Fig 5: Microphone 6), Relay module(Fig 7) follow these steps:

6. DC MOTOR 1. Microphone Connection: Connect the microphone to one

of the available USB ports on the Raspberry Pi 4. show in
A DC motor is regarded as an electro-mechanical device
circuit Diagram(Fig 10) How it is connected.
that converts electrical energy into mechanical energy.
Depending on the current flow direction through the wire,
2. Speaker Connection: The speaker, as shown in Fig 3, is
the conductor inside the magnetic field experiences motion.
connected to the PAM8403 amplifier module (Fig 2). Wire
the speaker to the PAM8403 following its Circuit diagram
(Fig 10).

3. Sound Sensor Connection: Wire the sound sensor,

depicted in Fig 4, to GPIO PIN NO 24 on the Raspberry Pi
4. show in (Fig 10) Ensure proper alignment and secure
connection to avoid any loose contacts.

4. DC Motor Connection: Connect the DC motor, illustrated

in Fig 6, to the relay module (Fig 7). Then, wire the relay
module to GPIO PIN NO 17 on the Raspberry Pi 4. make
sure check the circuit diagram for proper connection of wire
Fig 6: DC Motor in Fig 10.

sed use limited to: CENTRE FOR DEVELOPMENT OF ADVANCED COMPUTING - CDAC - Thiruvananthapuram & Kochi. Downloaded on June 11,2025 at 10:19:13 UTC from IEEE Xplore. Re
 B. Software Configuration:
Install the Raspbian operating system on the Raspberry Pi 4.
Set up the necessary software libraries and dependencies,
including:
SpeechRecognition: for speech recognition functionality.
wikipedia: for accessing Wikipedia API for information
retrieval.
gTTS (Google Text-to-Speech): for text-to-speech synthesis.
PyAudio: for audio recording and playback.
pygame: for controlling audio playback and DC motor.
Configure the GPIO pins for interacting with external
components such as the DC motor and sound sensor.

C. Speech Recognition:
Implement a function to record audio input from the
microphone using PyAudio.
Utilize the SpeechRecognition library to transcribe the
recorded audio into text.
Handle exceptions such as unrecognized speech or errors in
audio input.
Fig 8: Flowchart of Interactive Smart Robot Operation
D. Information Retrieval:
Upon receiving the transcribed text, utilize the Wikipedia The flowchart illustrates the sequential steps involved in the
API to search for relevant articles based on user queries. operation of the Interactive Smart Robot. Beginning with
Process the search results to extract relevant information or the initialization of GPIO, the flowchart illustrates a
summaries from Wikipedia articles. sequence of events such as sound detection, audio input,
Handle exceptions such as disambiguation errors or page speech recognition, search on Wikipedia, information
not found errors. retrieval and conversion to speech, speech synthesis output,
performance of dance and end of the activity. Such stages
E. Text-to-Speech Synthesis: help enhance the interaction of the users with the robot.
Generate speech output based on the retrieved information
using gTTS. V. RESULT
Save the synthesized speech as an audio file for playback.
Utilize pygame to play the synthesized speech through the
speaker.

F. Control Robot and Dance Routine:

Implement functionality to control the DC motor, turning it
on while the robot is speaking and off when speech
playback is complete.
Integrate a dance routine to enhance user engagement
during speech playback.
Coordinate DC motor control and dance routine with speech
synthesis and playback.

G. Testing and Evaluation:

Conduct thorough testing of the interactive robot to ensure
proper functionality and performance.
Evaluate the accuracy of speech recognition, effectiveness
of information retrieval, and user experience during
interaction.Collect feedback from users and iterate on the
design and implementation as necessary.

Fig 9: Interactive Smart Robot Prototype

sed use limited to: CENTRE FOR DEVELOPMENT OF ADVANCED COMPUTING - CDAC - Thiruvananthapuram & Kochi. Downloaded on June 11,2025 at 10:19:13 UTC from IEEE Xplore. Re
 5. Personalization and Customization: Implement
features that would consider the user’s preferences, interests,
and historical interactions with the robot to personalize the
robot’s communication. This could include, for example,
developing user profiles, collecting user feedback and
modifying the robot based on the feedback.

6. Integration with IoT Devices: Extend the functionality

of the robot to include control of Internet of Things (IoT)
devices and smart homes. This would enable a user to
control the lights, television, and appliances, and other
devices through voice enabling interfaces.

7. Educational Applications: Investigate the Interactive

Smart Robot application in educational processes in schools,
museums, etc. Create new content for active users, such as
Fig 10: Circuit Diagram lessons and special educational games which help to learn
science, history, language, etc.
The robot used in the project is of controllable constitution
with Raspberry Pi 4 mini computer, sound sensor, 8. Commercialization and Deployment: Give thought to
microphone, speaker, and DC motor among other the commercialization and deployment of the Interactive
components. Because of these components, the robot can Smart Robot within activities like customer care, interactive
entertain its users through speech commands whereby the entertainment and support, surgery or rehabilitation for the
robot gives out information or plays audio files. elderly, and people with disabilities. Create business in
addition to strategic alliances required to introduce the robot
VI. FUTURE SCOPE in the market.
The construction of the Interactive Smart Robot prototype VII. CONCLUSION
based on the Raspberry Pi 4, paves the way to multiple lines
of further research and innovation. These activities can be The creation and application of Interactive Smart Robot
inclusive of the following: utilizing Raspberry Pi 4 noticeably contributes to interactive
robotics and social robotics as well as robotics and human
1. Natural language processing (NLP): Incorporate more factors. This work has shown that it is possible and
advanced NLP technologies that will address user questions reasonable to realize a voice-controlDC motor robot that
by going beyond simple replies and involving various listens, searches and speaks while dancing to music.r
interactions. This can involve analyzing emotions,
identifying persons or objects and responding accordingly Integrating speech technology, information retrieval and
to the questioned context. NLD technologies, the Interactive Smart Robot allows any
person the possibility to operate the device in natural
2. Machine learning (ML) algorithms: Incorporate language. Also, using the cheap and common, such as
machine learning algorithms that focus on increasing the Raspberry Pi platform, this project seeks to tap on the
recognition of what a person is saying and the nuances and capacity of low-cost and basic technology, to offer high and
especially training the system to users’ speech as time edifying fun experiences for users of all ages.
progresses. These models can be trained on different
languages and accents so that the robot is capable of The hardware and software development of the system was
receiving oral commands from users of different language divided into developing the quite numerous requested
regions. functionalities, including DC motor control system, speech
recognition system and information retrieval system. Wide
3. Expansion of KnowDC motorge Base: Go beyond ranging and intensive testing was conducted to ascertain the
using the knowDC motorge base with only Wikipedia, interactivity and performance of the developed smart robot
instead focusing on other avenues such as online resources, thus proving its viability in practice.
books, and accurate and live information. This would in There are also many more ways in which the Interactive
effect improve the robot's efficiency in responding to user Smart Robot can be enhanced and extended. New features
issues. that could be added for example, are natural language
processing and machine learning which would increase the
4. Multimodal Interaction: Investigate the possibility of robot’s speech recognition system, and further expanding
using cameras and motion sensors integrated within the the robot's knowDC Mote base beyond Wikipedia.
setup, in addition to touch screen interfaces for the purpose
of multimodal interaction rehabilitation. This will also allow All these said, the Interactive Smart Robot demonstrates
communication to the machine by way of gestures, what Raspberry Pi based robotics could do when used to
expressions, and touch, enhancing overall experience design engaging and interactive education tools and
experiences. This project, therefore, enhances the

sed use limited to: CENTRE FOR DEVELOPMENT OF ADVANCED COMPUTING - CDAC - Thiruvananthapuram & Kochi. Downloaded on June 11,2025 at 10:19:13 UTC from IEEE Xplore. Re
 development of human-computer interaction and prepares [2] Wang, Y., Li, S., Zhang, Z., Zhang, Q., & Du, J. (2019). An acoustic
model based on deep learning for speech recognition. IEEE Access, 7,
the platform for the next generation of development in 19283-19293.
interactive robotics and educational technology by [3] Upton, E., & Halfacree, G. (2014). Raspberry Pi User Guide. John
integrating contemporary intelligence capabilities with low- Wiley & Sons.
end computing platforms. [4] O'Leary, D. (2016). Raspberry Pi Projects For Dummies. John Wiley
& Sons.
REFERENCES [5] Rosebrock, A. (2019). Raspberry Pi for Computer Vision.
PyImageSearch.
[6] Norman, D. A. (2013). The Design of Everyday Things. Basic Books.
[1] Li, J., & Zhang, T. (2018). Deep learning-based voice control system
design. 2018 IEEE 3rd International Conference on Cloud Computing [7] Dix, A., Finlay, J., Abowd, G., & Beale, R. (2004). Human-Computer
and Big Data Analysis (ICCCBDA). Interaction. Pearson Education.

sed use limited to: CENTRE FOR DEVELOPMENT OF ADVANCED COMPUTING - CDAC - Thiruvananthapuram & Kochi. Downloaded on June 11,2025 at 10:19:13 UTC from IEEE Xplore. Re