Collaborative Robotics

A comparison between two machine learning approaches viz., Genetic Fuzzy Methodology and Q-learning, is presented in this paper. The approaches are used to model controllers for a set of collaborative robots that need to work together to bring an object to a target position. The robots are fixed and are attached to the object through elastic cables. A major constraint considered in this problem is that the robots cannot communicate with each other. This means that at any instant, each robot has no motion or control information of the other robots and it can only pull or release its cable based only on the motion states of the object. This decentralized control problem provides a good example to test the capabilities and restrictions of these two machine learning approaches. The system is first trained using a set of training scenarios and then applied to an extensive test set to check the generalization achieved by each method.

This paper presents a novel robotic painting system able to create artworks using the palette knife technique. The implementation of this method with a robotic system is particularly challenging, since the robot needs to precisely manipulate the palette knife to pick up and release the color on the canvas. The painting system comprises a 6-DOF collaborative robot, a camera to acquire the information on the color position, and several algorithms for the artistic rendering of the images and for the planning of the trajectories that the robot has to follow. During the painting process the user can modify multiple parameters: both software, for example, stroke position and orientation, and hardware, for example, palette knife inclination and height, to obtain different stroke effects. Finally, the experimental results are discussed by analyzing the artworks painted by the novel robotic system.

In this paper, we present a novel robotic system that produces watercolour paintings by means of a 6-degree-of-freedom collaborative robot. After an analysis of traditional watercolour, different non-photorealistic rendering techniques are applied in order to elaborate digital images into artworks. Several algorithms, aimed at processing both the backgrounds and the details, are implemented. Then, the resulting rendering is converted into a sequence of trajectories that the robot reproduces on paper. During the process, the artist controlling the system can change both the algorithm parameters and the hardware variables (e.g. brush type, colour dilution, etc.) in order to obtain a different artistic rendering. The challenge is indeed not to faithfully reproduce an image but to introduce a personal and original contribution to the artwork. The robotic painting system described in this paper was named "Busker Robot" and it is the first automatic system that uses the watercolour technique for artistic rendering. It was installed at the "Algorithmic Arts and Robotics" exhibition during the international event "Trieste Next" (Trieste, Italy, September 2017) and won an Honorable Mention at the 2018 International Robotic Art Competition (RobotArt). Keywords robotic painting • watercolour • non-photorealistic rendering • artistic rendering • collaborative robotics.

Whether we look at Europe, the USA or Japan, in many areas in the world new possibilities of employing robotic systems in work settings essentially rely on direct collaborative interaction be-tween human workers and collaborative robots leading to new distributions of agency between them and making available robotic operations as resources for performing different forms of work, work which otherwise would remain out of reach for robotic automation for the time being. In this paper we introduce our concepts of studying the social construction of these collaborative work settings and the distribution of agency, accordingly. Referring to the basic idea of actor-network theory that technology in use should be analysed in a symmetrical manner, treating all the human and nonhuman entities involved as actors, our concept of distributed agency goes beyond actor-network theory in that it introduces the notion of gradualised action, which allows distinguishing between different levels of distributed agency. Therefore, we can precisely describe, in which way and to what extent activities and actor positions are delegated to robot co-workers or remain with its human counterpart. For analysing how the distribution of agency between human and robot co-workers is socially constructed in different stages, first in laboratory settings and then in increas-ingly realistic real-world settings, we interpret the spectrum of manifestations of human-robot col-laboration as prototypically realised scenarios at different stages of elaboration. In doing so we introduce the current state of collaborative robots in the areas of industrial production and care work as they represent contrastive cases: In industrial production collaborative robots are the next step in a long-standing history of robotic automation whereas in care work the new robots are also the first robots to be employed there. We believe that in both fields a perspective on collaborative work between humans and robots as a socio-technical constellation is helpful in order to be able to identify new distributions of work tasks.

This paper presents a novel robotic painting system able to create artworks using the palette knife technique. The implementation of this method with a robotic system is particularly challenging, since the robot needs to precisely manipulate the palette knife to pick up and release the color on the canvas. The painting system comprises a 6-DOF collaborative robot, a camera to acquire the information on the color position, and several algorithms for the artistic rendering of the images and for the planning of the trajectories that the robot has to follow. During the painting process the user can modify multiple parameters: both software, for example, stroke position and orientation, and hardware, for example, palette knife inclination and height, to obtain different stroke effects. Finally, the experimental results are discussed by analyzing the artworks painted by the novel robotic system.

This paper presents a novel robotic painting system able to create artworks using the palette knife technique. The implementation of this method with a robotic system is particularly challenging, since the robot needs to precisely manipulate the palette knife to pick up and release the color on the canvas. The painting system comprises a 6-DOF collaborative robot, a camera to acquire the information on the color position, and several algorithms for the artistic rendering of the images and for the planning of the trajectories that the robot has to follow. During the painting process the user can modify multiple parameters: both software, for example, stroke position and orientation, and hardware, for example, palette knife inclination and height, to obtain different stroke effects. Finally, the experimental results are discussed by analyzing the artworks painted by the novel robotic system.

Collaborative Robotics is one of the high-interest research topics in the area of academia and industry. It has been progressively utilized in numerous applications, particularly in intelligent surveillance systems. It allows the deployment of smart cameras or optical sensors with computer vision techniques, which may serve in several object detection and tracking tasks. These tasks have been considered challenging and high-level perceptual problems, frequently dominated by relative information about the environment, where main concerns such as occlusion, illumination, background, object deformation, and object class variations are commonplace. In order to show the importance of top view surveillance, a collaborative robotics framework has been presented. It can assist in the detection and tracking of multiple objects in top view surveillance. The framework consists of a smart robotic camera embedded with the visual processing unit. The existing pre-trained deep learning models named SSD and YOLO has been adopted for object detection and localization. The detection models are further combined with different tracking algorithms, including GOTURN, MEDIANFLOW, TLD, KCF, MIL, and BOOSTING. These algorithms, along with detection models, help to track and predict the trajectories of detected objects. The pre-trained models are employed; therefore, the generalization performance is also investigated through testing the models on various sequences of top view data set. The detection models achieved maximum True Detection Rate 93% to 90% with a maximum 0.6% False Detection Rate. The tracking results of different algorithms are nearly identical, with tracking accuracy ranging from 90% to 94%. Furthermore, a discussion has been carried out on output results along with future guidelines.

A core issue in collaborative robotics is that of impact mitigation, especially when collisions happen with operators. Passively compliant structures can be used as the frame of the cobot, although, usually, they are implemented by means of a single-degree-of-freedom (DoF). However, n-DoF preloaded structures offer a number of advantages in terms of flexibility in designing their behavior. In this work, we propose a comprehensive framework for classifying n-DoF preloaded structures, including one-, two-, and three-dimensional arrays. Furthermore, we investigate the implications of the peculiar behavior of these structures—which present sharp stiff-to-compliant transitions at design-determined load thresholds—on impact mitigation. To this regard, an analytical n-DoF dynamic model was developed and numerically implemented. A prototype of a 10DoF structure was tested under static and impact loads, showing a very good agreement with the model. Future developments will see the applicatio...

In this paper, we present a smart hand gesture recognition experimental set up for collaborative robots using a Faster R-CNN object detector to find the accurate position of the hands in the RGB images taken from a Kinect v2 camera. We used MATLAB to code the detector and a purposely designed function for the prediction phase, necessary for detecting static gestures in the way we have defined them. We performed a number of experiments with different datasets to evaluate the performances of the model in different situations: a basic hand gestures dataset with four gestures performed by the combination of both hands, a dataset where the actors wear skin-like color clothes while performing the gestures, a dataset where the actors wear light-blue gloves and a dataset similar to the first one but with the camera placed close to the operator. The same tests have been conducted in a situation where also the face of the operator was detected by the algorithm, in order to improve the prediction accuracy. Our experiments show that the best model accuracy and F1-Score are achieved by the complete model without the face detection. We tested the model in real-time, achieving good performances that can lead to real-time human-robot interaction, being the inference time around 0.2 seconds.

In this paper, we present non-photorealistic rendering techniques that are applied together with a painting robot to realize artworks with original styles. Our robotic painting system is called Busker Robot and it has been considered of interest in recent art fairs and international exhibitions. It consists of a six degree-of-freedom collaborative robot and a series of image processing and path planning algorithms. In particular, here, two different rendering techniques are presented and a description of the experimental set-up is carried out. Finally, the experimental results are discussed by analyzing the elements that can account for the aesthetic appreciation of the artworks.

This paper presents a novel robotic painting system able to create artworks using the palette knife technique. The implementation of this method with a robotic system is particularly challenging, since the robot needs to precisely manipulate the palette knife to pick up and release the color on the canvas. The painting system comprises a 6-DOF collaborative robot, a camera to acquire the information on the color position, and several algorithms for the artistic rendering of the images and for the planning of the trajectories that the robot has to follow. During the painting process the user can modify multiple parameters: both software, for example, stroke position and orientation, and hardware, for example, palette knife inclination and height, to obtain different stroke effects. Finally, the experimental results are discussed by analyzing the artworks painted by the novel robotic system.

Industrial robotics called “collaborative” makes operator share his workspace with a robot or even perform tasks simultaneously with it. Human-robot co-activity situations as all new technologies, modify the operator’s work and raise health and safety issues at work. To prevent occupational accidents and diseases but also to better understand Human-Robot Collaboration in the workplace, a study based on an ergonomics approach was conducted in a food company. Preliminary results show that handling tasks decrease while supervisory tasks increase, Operators have therefore more interest in their activity and feel valued. They think that collaborative robot integration improves their work conditions. However, mechanical moving parts (arms, tools, handled parts) of these cobots have sometimes hit operators. This study tries to work out ways to improve this collaboration in terms of health and safety.

In this paper, a mobile manipulation system for automatized logistic applications is presented. The robotic system is specifically designed for depalletizing/palletizing tasks, namely is product extraction from homogeneous pallets and assembly of new heterogeneous pallets. The robotic system is mainly composed by an autonomous vehicle, a collaborative robotic arm and a lifting device, which is able to collect products from different pallet layers. The handling strategy is not based on lifting items, as in classical pick-and-place operations, but on dragging them aboard the mobile vehicle. As the payload weight is not supported by the arm, the overall robotic system is very light compared to the manipulated items, which is a paramount benefit for a mobile collaborative application. This paper presents the mechanical design, the hardware selection and the experimentation in a laboratory scenario, thus demonstrating the effectiveness of the proposed manipulation strategy.

A core issue in collaborative robotics is that of impact mitigation, especially when collisions happen with operators. Passively compliant structures can be used as the frame of the cobot, although, usually, they are implemented by means of a single DoF. However, n-DoF preloaded structures offer a number of advantages, in terms of flexibility in designing their behavior. In this work we propose a comprehensive framework for classifying n-DoF preloaded structures, including 1-, 2-, and 3-dimensional arrays. Furthermore, we investigate the implications of the peculiar behavior of these structures-which present sharp stiff-to-compliant transitions at design-determined load thresholds-on impact mitigation. To this regard, an analytical n-DoF dynamic model was developed and numerically implemented. A prototype of a 10-DoF structure was tested under static and impact loads, showing a very good agreement with the model. Future developments will see the application of n-DoF preloaded structures to impact-mitigation on cobots and in the field of mobile robots, as well as to the field of novel architected materials.