The loss of a hand can significantly affect one’s work and social life. For many patients, an artificial limb can improve their mobility and ability to manage everyday activities, as well as provide the means to remain independent. This paper provides an extensive review of available biosensing methods to implement the control system for transradial prostheses based on the measured activity in remnant muscles. Covered techniques include electromyography, magnetomyography, electrical impedance tomography, capacitance sensing, near-infrared spectroscopy, sonomyography, optical myography, force myography, phonomyography, myokinetic control, and modern approaches to cineplasty. The paper also covers combinations of these approaches, which, in many cases, achieve better accuracy while mitigating the weaknesses of individual methods. The work is focused on the practical applicability of the approaches, and analyses present challenges associated with each technique along with their relationship with proprioceptive feedback, which is an important factor for intuitive control over the prosthetic device, especially for high dexterity prosthetic hands.
The paper presents a new version of the existing elastic band algorithm used for path finding, with application in the field of collaborative robotics and point-to-point movements. The algorithm places control points on the path and dynamically modifies the position of these control points in reaction to any obstacles located or moving in the workspace. The control points are updated in the robot space (TCP space), obstacles are represented by a set of grid-aligned voxels acquired by a camera system. Repulsive forces are created between the obstacles and the robot body (represented by a set of points covering evenly the surface of individual links) and transferred to the locations of the elastic band control points. The method is computationally effective and provides a smooth and length-optimal path while considering collisions in a more accurate manner than traditional usage of simple bounding volumes. The dynamic iterative updating of elastic band provides a clear principle for modification of the trajectory even close to the actual location of the robot as it is following the trajectory. The algorithm is verified on a set of practical experiments made on a physical UR3 robot with simulated obstacles, and the results are also compared to other commonly used methods for dynamic obstacle avoidance.
In this paper, a new method for the calibration of robotic cell components is presented and demonstrated by identification of an industrial robotic manipulator’s base and end-effector frames in a workplace. It is based on a mathematical approach using a Jacobian matrix. In addition, using the presented method, identification of other kinematic parameters of a robot is possible. The Universal Robot UR3 was later chosen to prove the working principle in both simulations and experiment, with a simple repeatable low-cost solution for such a task—image analysis to detect tag markers. The results showing the accuracy of the system are included and discussed.
Human–robot interaction is becoming an integral part of practice. There is a greater emphasis on safety in workplaces where a robot may bump into a worker. In practice, there are solutions that control the robot based on the potential energy in a collision or a robot re-planning the straight-line trajectory. However, a sensor system must be designed to detect obstacles across the human–robot shared workspace. So far, there is no procedure that engineers can follow in practice to deploy sensors ideally. We come up with the idea of classifying the space as an importance index, which determines what part of the workspace sensors should sense to ensure ideal obstacle sensing. Then, the ideal camera positions can be automatically found according to this classified map. Based on the experiment, the coverage of the important volume by the calculated camera position in the workspace was found to be on average 37% greater compared to a camera placed intuitively by test subjects. Using two cameras at the workplace, the calculated positions were 27% more effective than the subjects’ camera positions. Furthermore, for three cameras, the calculated positions were 13% better than the subjects’ camera positions, with a total coverage of more than 99% of the classified map.
In this paper, we focus on the problem of applying domain randomization to produce synthetic datasets for training depth image segmentation models for the task of hand localization. We provide new synthetic datasets for industrial environments suitable for various hand tracking applications, as well as ready-to-use pre-trained models. The presented datasets are analyzed to evaluate the characteristics of these datasets that affect the generalizability of the trained models, and recommendations are given for adapting the simulation environment to achieve satisfactory results when creating datasets for specialized applications. Our approach is not limited by the shortcomings of standard analytical methods, such as color, specific gestures, or hand orientation. The models in this paper were trained solely on a synthetic dataset and were never trained on real camera images; nevertheless, we demonstrate that our most diverse datasets allow the models to achieve up to 90% accuracy. The proposed hand localization system is designed for industrial applications where the operator shares the workspace with the robot.
This work focuses on improving a camera system for sensing a workspace in which dynamic obstacles need to be detected. The currently available state-of-the-art solution (MoveIt!) processes data in a centralized manner from cameras that have to be registered before the system starts. Our solution enables distributed data processing and dynamic change in the number of sensors at runtime. The distributed camera data processing is implemented using a dedicated control unit on which the filtering is performed by comparing the real and expected depth images. Measurements of the processing speed of all sensor data into a global voxel map were compared between the centralized system (MoveIt!) and the new distributed system as part of a performance benchmark. The distributed system is more flexible in terms of sensitivity to a number of cameras, better framerate stability and the possibility of changing the camera number on the go. The effects of voxel grid size and camera resolution were also compared during the benchmark, where the distributed system showed better results. Finally, the overhead of data transmission in the network was discussed where the distributed system is considerably more efficient. The decentralized system proves to be faster by 38.7% with one camera and 71.5% with four cameras.