A Novel CNN-BiLSTM Ensemble Model With Attention Mechanism for Sit-to-Stand Phase Identification Using Wearable Inertial Sensors.

Sit-to-stand transition phase identification is vital in the control of a wearable exoskeleton robot for assisting patients to stand stably. In this study, we aim to propose a method for segmenting and identifying the sit-to-stand phase using two inertial sensors. First, we defined the sit-to-stand transition into five phases, namely, the initial sitting phase, the flexion momentum phase, the momentum transfer phase, the extension phase, and the stable standing phase based on the preprocessed acceleration and angular velocity data. We then employed a threshold method to recognize the initial sitting and the stable standing phases. Finally, we designed a novel CNN-BiLSTM-Attention algorithm to identify the three transition phases, namely, the flexion momentum phase, the momentum transfer phase, and the extension phase. Fifteen subjects were recruited to perform sit-to-stand transition experiments under a specific paradigm. A combination of the acceleration and angular velocity data features for the sit-to-stand transition phase identification were validated for the model performance improvements. The integration of the CNN, Bi-LSTM, and Attention modules demonstrated the reasonableness of the proposed algorithms. The experimental results showed that the proposed CNN-BiLSTM-Attention algorithm achieved the highest average classification accuracy of 99.5% for all five phases when compared to both traditional machine learning algorithms and deep learning algorithms on our customized dataset (STS-PD). The proposed sit-to-stand phase recognition algorithm could serve as a foundation for the control of wearable exoskeletons and is important for the further development of intelligent wearable exoskeleton rehabilitation robots.

A Semi-Autonomous Hierarchical Control Framework for Prosthetic Hands Inspired by Dual Streams of Human.

The routine use of prosthetic hands significantly enhances amputees' daily lives, yet it often introduces cognitive load and reduces reaction speed. To address this issue, we introduce a wearable semi-autonomous hierarchical control framework tailored for amputees. Drawing inspiration from the visual processing stream in humans, a fully autonomous bionic controller is integrated into the prosthetic hand control system to offload cognitive burden, complemented by a Human-in-the-Loop (HIL) control method. In the ventral-stream phase, the controller integrates multi-modal information from the user's hand-eye coordination and biological instincts to analyze the user's movement intention and manipulate primitive switches in the variable domain of view. Transitioning to the dorsal-stream phase, precise force control is attained through the HIL control strategy, combining feedback from the prosthetic hand's sensors and the user's electromyographic (EMG) signals. The effectiveness of the proposed interface is demonstrated by the experimental results. Our approach presents a more effective method of interaction between a robotic control system and the human.

Dynamic and Real-Time Object Detection Based on Deep Learning for Home Service Robots.

Home service robots operating indoors, such as inside houses and offices, require the real-time and accurate identification and location of target objects to perform service tasks efficiently. However, images captured by visual sensors while in motion states usually contain varying degrees of blurriness, presenting a significant challenge for object detection. In particular, daily life scenes contain small objects like fruits and tableware, which are often occluded, further complicating object recognition and positioning. A dynamic and real-time object detection algorithm is proposed for home service robots. This is composed of an image deblurring algorithm and an object detection algorithm. To improve the clarity of motion-blurred images, the DA-Multi-DCGAN algorithm is proposed. It comprises an embedded dynamic adjustment mechanism and a multimodal multiscale fusion structure based on robot motion and surrounding environmental information, enabling the deblurring processing of images that are captured under different motion states. Compared with DeblurGAN, DA-Multi-DCGAN had a 5.07 improvement in Peak Signal-to-Noise Ratio (PSNR) and a 0.022 improvement in Structural Similarity (SSIM). An AT-LI-YOLO method is proposed for small and occluded object detection. Based on depthwise separable convolution, this method highlights key areas and integrates salient features by embedding the attention module in the AT-Resblock to improve the sensitivity and detection precision of small objects and partially occluded objects. It also employs a lightweight network unit Lightblock to reduce the network's parameters and computational complexity, which improves its computational efficiency. Compared with YOLOv3, the mean average precision (mAP) of AT-LI-YOLO increased by 3.19%, and the detection precision of small objects, such as apples and oranges and partially occluded objects, increased by 19.12% and 29.52%, respectively. Moreover, the model inference efficiency had a 7 ms reduction in processing time. Based on the typical home activities of older people and children, the dataset Grasp-17 was established for the training and testing of the proposed method. Using the TensorRT neural network inference engine of the developed service robot prototype, the proposed dynamic and real-time object detection algorithm required 29 ms, which meets the real-time requirement of smooth vision.

A High-Efficient Reinforcement Learning Approach for Dexterous Manipulation.

Robotic hands have the potential to perform complex tasks in unstructured environments owing to their bionic design, inspired by the most agile biological hand. However, the modeling, planning and control of dexterous hands remain unresolved, open challenges, resulting in the simple movements and relatively clumsy motions of current robotic end effectors. This paper proposed a dynamic model based on generative adversarial architecture to learn the state mode of the dexterous hand, reducing the model's prediction error in long spans. An adaptive trajectory planning kernel was also developed to generate High-Value Area Trajectory (HVAT) data according to the control task and dynamic model, with adaptive trajectory adjustment achieved by changing the Levenberg-Marquardt (LM) coefficient and the linear searching coefficient. Furthermore, an improved Soft Actor-Critic (SAC) algorithm is designed by combining maximum entropy value iteration and HVAT value iteration. An experimental platform and simulation program were built to verify the proposed method with two manipulating tasks. The experimental results indicate that the proposed dexterous hand reinforcement learning algorithm has better training efficiency and requires fewer training samples to achieve quite satisfactory learning and control performance.

Analysis of Damping Characteristics of Magnetorheological Damper under Impact Load.

Compared to magnetorheological fluid, magnetorheological gel has better anti-settling performance and stability. Therefore, magnetorheological gel is suitable for devices that can meet operational requirements in all aspects after long-term storage, such as the anti-recoil application of weapons. To study this in-depth, the mechanism of the influence of magnetorheological gel micro-magnetic-mechanical properties on the macro-output damping mechanics of the damper, a parallel plate model of the mixed flow mode composed of Couette shear flow and Poiseuille pressure flow was established. The theoretical analysis was of the output damping of the damper. Finally, the controllability of the damper under impact load employed magnetorheological gel was preliminarily analyzed. The results indicate that the damping coefficient of the damper increases with the increase of dynamic viscosity ηB of the magnetorheological gel, piston effective cross-sectional area AP, magnetic pole L, and Bingham coefficient Bi. Magnetorheological damper has controllability under impact load and can reach a wide controllable range under the condition under small magnetic field ranging from 0 mT to 131 mT.

RBF network-based adaptive sliding mode control strategy for the tendon-sheath driven joint of a prosthetic hand.

BACKGROUND: The complex in-hand manipulation puts forward higher requirements for the dexterity and joint control accuracy of the prosthetic hand. The tendon-sheath drive has important application potential in the fields of prosthetic hand to obtain higher dexterity. However, the existing control methods of tendon-sheath driven joint are mainly open-loop compensation based on friction model, which makes it difficult to achieve high-precision joint control. OBJECTIVE: The purpose of this work is to improve the position control accuracy of the tendon-sheath driven joint for the prosthetic hand. METHODS: The structure of the prosthetic hand is introduced, and the encoder and potentiometer are mounted on the driving motor and joint respectively. Then, the transfer function of the joint is established based on the dynamic model. The adaptive sliding mode control strategy based on RBF network is applied to realize the closed-loop feedback position control of the prosthetic hand joint. The stability of the system is demonstrated by Lyapunov theorem. RESULTS: Under the condition of constant and variable sheath curvature, the effectiveness of the controller is demonstrated by simulation and joint motion experiments, respectively. The results show that the closed-loop control has better position tracking ability than the open-loop control, and the designed controller can reduce the tracking error more obviously than the traditional algorithm. The high-precision position control can be realized by designing the controller based on the joint angle feedback. CONCLUSIONS: The research content has certain theoretical and practical significance for the development of joint high-precision control of tendon-sheath driven prosthetic hand. This is beneficial to the implementation of complex in-hand manipulation for prosthetic hand.

Corrections to "Academic Review and Perspectives on Robotic Exoskeletons".

We have noticed some errors in the above-titled paper (DOI: 10.1109/TNSRE.2019.2944655) [1].

Academic Review and Perspectives on Robotic Exoskeletons.

Since the first robotic exoskeleton was developed in 1960, this research field has attracted much interest from both the academic and industrial communities resulting in scientific publications, prototype developments and commercialized products. In this article, to document the progress in and current status of this field, we performed a bibliometric analysis. This analysis evaluated the publications in the field of robotic exoskeletons from 1990 to July 2019 that were retrieved from the Science Citation Index Expanded database. The bibliometric analyses were presented in terms of author keywords, year, country, institution, journal, author, and the citation. Results show that currently the United States has taken the leading position in this field and has built the largest collaborative network with other countries. The Massachusetts Institute of Technology (MIT) made the greatest contribution to the field of robotic exoskeleton investigations in terms of the number of publications, average citations per publication and the h-index. In addition, the Journal of NeuroEngineering and Rehabilitation ranks first among the top 20 academic journals in terms of the number of publications related to robotic exoskeletons during the period investigated. Author keyword analysis indicates that most research has focused on rehabilitation robotics. Biomedical engineering, rehabilitation and the neurosciences are the most common disciplines conducting research in this area according to the Web of Science (WoS). Our study comprehensively assesses the current research status and collaboration network of robotic exoskeletons, thus helping researchers steer their projects or locate potential collaborators.