“…Sharkawy et al designed a multilayer feedforward neural network-based and trained it using data acquired from the coupled dynamics of the manipulator with and without external contacts to detect unwanted collisions and to identify the collided link using only the intrinsic joint position and torque sensors [51]. Li et al proposed an adaptive compliant control in which the end-effector's motions are constrained by human arm joint limits.…”
Purpose of Review Research in assistive and rehabilitation robotics is a growing, promising, and challenging field emerged due to various social and medical needs such as aging populations, neuromuscular, and musculoskeletal disorders. Such robots can be used in various day-today scenarios or to support motor functionality, training, and rehabilitation. This paper reflects on the human-robot interaction perspective in rehabilitation and assistive robotics and reports on current issues and developments in the field. Recent Findings The survey on the literature reveals that new efforts are put on utilizing machine learning approaches alongside novel developments in sensing technology to adapt the systems with user routines in terms of activities for assistive systems and exercises for rehabilitation devices to fit each user's need and maximize their effectiveness. Summary A review of recent research and development efforts on human-robot interaction in assistive and rehabilitation robotics is presented in this paper. First, different subdomains in assistive and rehabilitation robotic research are identified, and accordingly, a survey on the background and trends of such developments is provided.
“…Sharkawy et al designed a multilayer feedforward neural network-based and trained it using data acquired from the coupled dynamics of the manipulator with and without external contacts to detect unwanted collisions and to identify the collided link using only the intrinsic joint position and torque sensors [51]. Li et al proposed an adaptive compliant control in which the end-effector's motions are constrained by human arm joint limits.…”
Purpose of Review Research in assistive and rehabilitation robotics is a growing, promising, and challenging field emerged due to various social and medical needs such as aging populations, neuromuscular, and musculoskeletal disorders. Such robots can be used in various day-today scenarios or to support motor functionality, training, and rehabilitation. This paper reflects on the human-robot interaction perspective in rehabilitation and assistive robotics and reports on current issues and developments in the field. Recent Findings The survey on the literature reveals that new efforts are put on utilizing machine learning approaches alongside novel developments in sensing technology to adapt the systems with user routines in terms of activities for assistive systems and exercises for rehabilitation devices to fit each user's need and maximize their effectiveness. Summary A review of recent research and development efforts on human-robot interaction in assistive and rehabilitation robotics is presented in this paper. First, different subdomains in assistive and rehabilitation robotic research are identified, and accordingly, a survey on the background and trends of such developments is provided.
“…In [46], the generalization ability to unseen objects and backgrounds has been largely improved, and both the attentional model and the auxiliary classification task were necessary to get this improvement. In [47], the MLFFNN was proposed for the human-robot collision detections and the collided link identification. In that work, the training of the MLFFNN happened using a robot joint motion with limited range of the joins' angles.…”
Section: Mlffnn Generalizationmentioning
confidence: 99%
“…The method in these cases presented high effectiveness and generalization. This case is presented in Table 2 [47].…”
In this paper, an overview of the artificial neural networks is presented. Their main and popular types such as the multilayer feedforward neural network (MLFFNN), the recurrent neural network (RNN), and the radial basis function (RBF) are investigated. Furthermore, the main advantages and disadvantages of each type are included as well as the training process.
“…ANYexo [7], a versatile exoskeleton based on series elastic actuation, overcomes this problem by its light-weight hardware design. Advancements in haptic force rendering, such as calculating reaction forces with a spring-damping system upon penetration of the object [8], or using neural networks [9] to determine repulsive forces, build on the work by [10] and [11]. Salisbury et al [10] determines the required update frequency for smooth haptic interaction and proposes a ground lying architecture, while [11] presents a method on how to successfully render obstacles with adequate sense of touch.…”
Section: A Related Workmentioning
confidence: 99%
“…Salisbury et al [10] determines the required update frequency for smooth haptic interaction and proposes a ground lying architecture, while [11] presents a method on how to successfully render obstacles with adequate sense of touch. [8] does not take occlusion problems into account, and [9] only considers static collision objects. The authors in [12] extend the initial methods to streaming (unfiltered) point cloud data and improve the robustness of the slip-through problem for the proxy object.…”
During robot-assisted therapy of hemiplegic patients, interaction with the patient must be intrinsically safe. Straightforward collision avoidance solutions can provide this safety requirement with conservative margins. These margins heavily reduce the robot's workspace and make interaction with the patient's unguided body parts impossible. However, interaction with the own body is highly beneficial from a therapeutic point of view. We tackle this problem by combining haptic rendering techniques with classical computer vision methods. Our proposed solution consists of a pipeline that builds collision objects from point clouds in real-time and a controller that renders haptic interaction. The raw sensor data is processed to overcome noise and occlusion problems. Our proposed approach is validated on the 6 DoF exoskeleton ANYexo for direct impacts, sliding scenarios, and dynamic collision surfaces. The results show that this method has the potential to successfully prevent collisions and allow haptic interaction for highly dynamic environments. We believe that this work significantly adds to the usability of current exoskeletons by enabling virtual haptic interaction with the patient's body parts in human-robot therapy.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.