A robotic system with reinforcement learning for lower extremity hemiparesis rehabilitation

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Jiajun Xu ◽  
Linsen Xu ◽  
Gaoxin Cheng ◽  
Jia Shi ◽  
Jinfu Liu ◽  
...  
Keyword(s):  
Reinforcement Learning ◽  
Lower Extremity ◽  
Muscle Activation ◽  
High Efficiency ◽  
Impedance Control ◽  
Robotic System ◽  
Mirror Therapy ◽  
Content Type ◽  
Model Reference Adaptive ◽  
Rehabilitation Exercise

Purpose This paper aims to propose a bilateral robotic system for lower extremity hemiparesis rehabilitation. The hemiplegic patients can complete rehabilitation exercise voluntarily with the assistance of the robot. The reinforcement learning is included in the robot control system, enhancing the muscle activation of the impaired limbs (ILs) efficiently with ensuring the patients’ safety. Design/methodology/approach A bilateral leader–follower robotic system is constructed for lower extremity hemiparesis rehabilitation, where the leader robot interacts with the healthy limb (HL) and the follow robot is worn by the IL. The therapeutic training is transferred from the HL to the IL with the assistance of the robot, and the IL follows the motion trajectory prescribed by the HL, which is called the mirror therapy. The model reference adaptive impedance control is used for the leader robot, and the reinforcement learning controller is designed for the follower robot. The reinforcement learning aims to increase the muscle activation of the IL and ensure that its motion can be mastered by the HL for safety. An asynchronous algorithm is designed by improving experience relay to run in parallel on multiple robotic platforms to reduce learning time. Findings Through clinical tests, the lower extremity hemiplegic patients can rehabilitate with high efficiency using the robotic system. Also, the proposed scheme outperforms other state-of-the-art methods in tracking performance, muscle activation, learning efficiency and rehabilitation efficacy. Originality/value Using the aimed robotic system, the lower extremity hemiplegic patients with different movement abilities can obtain better rehabilitation efficacy.

Which impedance strategy is the most effective for cooperative object manipulation?

2017 ◽  
Vol 44 (2) ◽  
pp. 198-209 ◽  
Author(s):  
Payam Zarafshan ◽  
Reza Larimi ◽  
S. Ali A. Moosavian ◽  
Bruno Siciliano
Keyword(s):  
Conceptual Model ◽  
Degrees Of Freedom ◽  
Impedance Control ◽  
Object Manipulation ◽  
Robotic System ◽  
Control Algorithms ◽  
Practical Implementation ◽  
Content Type ◽  
Manipulation Task ◽  
Cooperative Object Manipulation

Purpose The purpose of this paper is to present a comparison study of cooperative object manipulation control algorithms. To this end, a full comprehensive survey of the existing control algorithms in this field is presented. Design/methodology/approach Cooperative manipulation occurs when manipulators are mechanically coupled to the object being manipulated, and the manipulators may not be treated as an isolated system. The most important and basic impedance control (IC) strategies for an assumed cooperative object manipulation task are the Augmented Object Model (AOM) control and the multiple impedance control (MIC) which are found based on the IC, where the former is designed based on the object movement, and the latter is designed based on the whole robot movement. Thus, the basis of these two algorithms are fully studied. Findings The results are fully analyzed, and it is practically verified that the MIC algorithm has the better performance. In fact, the results reveal that the MIC system could successfully perform the object manipulation task, as opposed to the AOM controller: for the same controller gains, the MIC strategy showed better performance than the AOM strategy. This means that because there is no control on the robot base with the AOM algorithm, the object manipulation task cannot be satisfactorily performed whenever the desired path is not within the robot work space. On the other hand, with the MIC algorithm, satisfactory object manipulation is achieved for a mobile robotic system in which the robot base, the manipulator endpoints and the manipulated object shall be moved. Practical implications A simple conceptual model for cooperative object manipulation is considered, and a suitable setup is designed for practical implementation of the two ICs. Originality/value The basis of these two aspects or these two algorithms is fully studied and compared which is the foundation of this paper. For this purpose, a case study is considered, in which a space free-flying robotic system, which contains two 2-degrees of freedom planar cooperative manipulators, is simulated to manipulate an object using the above control strategies. The system also includes a rotating antenna and camera as its third and fourth arm. Finally, a simple conceptual model for cooperative object manipulation is considered, and a suitable setup is designed for practical implementation of the two ICs.

scholarly journals Lower Extremity Rehabilitation in Patients with Post-Stroke Sequelae through Virtual Reality Associated with Mirror Therapy

2021 ◽  
Vol 18 (5) ◽  
pp. 2654
Author(s):  
Roxana Steliana Miclaus ◽  
Nadinne Roman ◽  
Ramona Henter ◽  
Silviu Caloian
Keyword(s):  
Virtual Reality ◽  
Muscle Strength ◽  
Lower Extremity ◽  
Range Of Motion ◽  
Control Group ◽  
Mirror Therapy ◽  
Cohen’S D ◽  
Cohen's D ◽  
Experimental Group ◽  
Post Therapy

More innovative technologies are used worldwide in patient’s rehabilitation after stroke, as it represents a significant cause of disability. The majority of the studies use a single type of therapy in therapeutic protocols. We aimed to identify if the association of virtual reality (VR) therapy and mirror therapy (MT) exercises have better outcomes in lower extremity rehabilitation in post-stroke patients compared to standard physiotherapy. Fifty-nine inpatients from 76 initially identified were included in the research. One experimental group (n = 31) received VR therapy and MT, while the control group (n = 28) received standard physiotherapy. Each group performed seventy minutes of therapy per day for ten days. Statistical analysis was performed with nonparametric tests. Wilcoxon Signed-Rank test showed that both groups registered significant differences between pre-and post-therapy clinical status for the range of motion and muscle strength (p < 0.001 and Cohen’s d between 0.324 and 0.645). Motor Fugl Meyer Lower Extremity Assessment also suggested significant differences pre-and post-therapy for both groups (p < 0.05 and Cohen’s d 0.254 for the control group and 0.685 for the experimental group). Mann-Whitney results suggested that VR and MT as a therapeutic intervention have better outcomes than standard physiotherapy in range of motion (p < 0.05, Cohen’s d 0.693), muscle strength (p < 0.05, Cohen’s d 0.924), lower extremity functionality (p < 0.05, Cohen’s d 0.984) and postural balance (p < 0.05, Cohen’s d 0.936). Our research suggests that VR therapy associated with MT may successfully substitute classic physiotherapy in lower extremity rehabilitation after stroke.

The study of impedance control of lower extremity exoskeleton

2020 ◽  
Author(s):  
Yali Han ◽  
Jinfei Shi ◽  
Han Sun ◽  
Weijie Zhou ◽  
Hongyao Guan ◽  
...  
Keyword(s):  
Lower Extremity ◽  
Impedance Control

Development of an autonomous robotic system for beard shaving assistance of disabled people based on an adaptive force tracking impedance control

2021 ◽  
pp. 095440622098482
Author(s):  
Oladayo S Ajani ◽  
Samy FM Assal
Keyword(s):  
Impedance Control ◽  
Environmental Parameters ◽  
Robotic System ◽  
Robotic Systems ◽  
Full Potential ◽  
Robotic Assistance ◽  
Head Pose ◽  
Detection And Tracking ◽  
Control Scheme ◽  
Force Tracking

Recently, people with upper arm disabilities due to neurological disorders, stroke or old age are receiving robotic assistance to perform several activities such as shaving, eating, brushing and drinking. Although the full potential of robotic assistance lies in the use of fully autonomous robotic systems, these systems are limited in design due to the complexities and the associated risks. Hence, rather than the shared controlled or active robotic systems used for such tasks around the head, an adaptive compliance control scheme-based autonomous robotic system for beard shaving assistance is proposed. The system includes an autonomous online face detection and tracking as well as selected geometrical features-based beard region estimation using the Kinect RGB-D camera. Online trajectory planning for achieving the shaving task is enabled; with the capability of online re-planning trajectories in case of unintended head pose movement and occlusion. Based on the dynamics of the UR-10 6-DOF manipulator using ADAMS and MATLAB, an adaptive force tracking impedance controller whose parameters are tuned using Genetic Algorithm (GA) with force/torque constraints is developed. This controller can regulate the contact force under head pose changing and varying shaving region stiffness by adjusting the target stiffness of the controller. Simulation results demonstrate the system capability to achieve beard shaving autonomously with varying environmental parameters that can be extended for achieving other tasks around the head such as feeding, drinking and brushing.

Robotic motion compensation for bone movement, using ultrasound images

2015 ◽  
Vol 42 (5) ◽  
pp. 466-474 ◽  
Author(s):  
P.M.B. Torres ◽  
P. J. S. Gonçalves ◽  
J.M.M. Martins
Keyword(s):  
Motion Compensation ◽  
Optical Measurement ◽  
Three Dimensional ◽  
Point Clouds ◽  
Robotic System ◽  
Ultrasound Images ◽  
Bone Drilling ◽  
Content Type ◽  
3D Point Clouds ◽  
Robotic Motion

Purpose – The purpose of this paper is to present a robotic motion compensation system, using ultrasound images, to assist orthopedic surgery. The robotic system can compensate for femur movements during bone drilling procedures. Although it may have other applications, the system was thought to be used in hip resurfacing (HR) prosthesis surgery to implant the initial guide tool. The system requires no fiducial markers implanted in the patient, by using only non-invasive ultrasound images. Design/methodology/approach – The femur location in the operating room is obtained by processing ultrasound (USA) and computer tomography (CT) images, obtained, respectively, in the intra-operative and pre-operative scenarios. During surgery, the bone position and orientation is obtained by registration of USA and CT three-dimensional (3D) point clouds, using an optical measurement system and also passive markers attached to the USA probe and to the drill. The system description, image processing, calibration procedures and results with simulated and real experiments are presented and described to illustrate the system in operation. Findings – The robotic system can compensate for femur movements, during bone drilling procedures. In most experiments, the update was always validated, with errors of 2 mm/4°. Originality/value – The navigation system is based entirely on the information extracted from images obtained from CT pre-operatively and USA intra-operatively. Contrary to current surgical systems, it does not use any type of implant in the bone to track the femur movements.

scholarly journals Role of Occupational Footwear and Prolonged Walking on Lower Extremity Muscle Activation during Maximal Exertions and Postural Stability Tasks

Biomechanics ◽  
2021 ◽  
Vol 1 (2) ◽  
pp. 202-213
Author(s):  
Harish Chander ◽  
Sachini N. K. Kodithuwakku Arachchige ◽  
Alana J. Turner ◽  
Reuben F. Burch V ◽  
Adam C. Knight ◽  
...  
Keyword(s):  
Lower Extremity ◽  
Muscle Activity ◽  
Repeated Measures ◽  
Postural Stability ◽  
Muscle Activation ◽  
Medial Gastrocnemius ◽  
Lower Extremity Muscle ◽  
Prolonged Duration ◽  
The Mean ◽  
The Impact

Background: Occupational footwear and a prolonged duration of walking have been previously reported to play a role in maintaining postural stability. The purpose of this paper was to analyze the impact of three types of occupational footwear: the steel-toed work boot (ST), the tactical work boot (TB), and the low-top work shoe (LT) on previously unreported lower extremity muscle activity during postural stability tasks. Methods: Electromyography (EMG) muscle activity was measured from four lower extremity muscles (vastus medialis (VM), medial hamstrings (MH), tibialis anterior (TA), and medial gastrocnemius (MG) during maximal voluntary isometric contractions (MVIC) and during a sensory organization test (SOT) every 30 min over a 4 h simulated workload while wearing ST, TB, and LT footwear. The mean MVIC and the mean and percentage MVIC during each SOT condition from each muscle was analyzed individually using a repeated measures ANOVA at an alpha level of 0.05. Results: Significant differences (p < 0.05) were found for maximal exertions, but this was limited to only the time main effect. No significant differences existed for EMG measures during the SOT. Conclusion: The findings suggest that occupational footwear type does not influence lower extremity muscle activity during both MVIC and SOT. Significantly lower muscle activity during maximal exertions over the course of the 4 h workload was evident, which can be attributed to localized muscular fatigue, but this was not sufficient to impact muscle activity during postural stability tasks.

Robotic system design and development for automated dismantling of PCB waste

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Ioan Doroftei ◽  
Daniel Chirita ◽  
Ciprian Stamate ◽  
Stelian Cazan ◽  
Carlos Pascal ◽  
...  
Keyword(s):  
Design Methodology ◽  
Printed Circuit Board ◽  
Vision System ◽  
Electronic Waste ◽  
Robotic System ◽  
Circuit Board ◽  
Short Introduction ◽  
Content Type ◽  
Printed Circuit ◽  
System A

Purpose The mass electronics sector is one of the most critical sources of waste, in terms of volume and content with dangerous effects on the environment. The purpose of this study is to provide an automated and accurate dismantling system that can improve the outcome of recycling. Design/methodology/approach Following a short introduction, the paper details the implementation layout and highlights the advantages of using a custom architecture for the automated dismantling of printed circuit board waste. Findings Currently, the amount of electronic waste is impressive while manual dismantling is a very common and non-efficient approach. Designing an automatic procedure that can be replicated, is one of the tasks for efficient electronic waste recovery. This paper proposes an automated dismantling system for the advanced recovery of particular waste materials from computer and telecommunications equipment. The automated dismantling architecture is built using a robotic system, a custom device and an eye-to-hand configuration for a stereo vision system. Originality/value The proposed approach is innovative because of its custom device design. The custom device is built using a programmable screwdriver combined with an innovative rotary dismantling tool. The dismantling torque can be tuned empirically.

Robot obstacle avoidance system using deep reinforcement learning

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Xiaojun Zhu ◽  
Yinghao Liang ◽  
Hanxu Sun ◽  
Xueqian Wang ◽  
Bin Ren
Keyword(s):  
Reinforcement Learning ◽  
Collision Avoidance ◽  
Obstacle Avoidance ◽  
Learning Algorithm ◽  
Optimal Path ◽  
Environmental Parameters ◽  
Working Environment ◽  
Content Type ◽  
Practical Applications ◽  
Human Operators

Purpose Most manufacturing plants choose the easy way of completely separating human operators from robots to prevent accidents, but as a result, it dramatically affects the overall quality and speed that is expected from human–robot collaboration. It is not an easy task to ensure human safety when he/she has entered a robot’s workspace, and the unstructured nature of those working environments makes it even harder. The purpose of this paper is to propose a real-time robot collision avoidance method to alleviate this problem. Design/methodology/approach In this paper, a model is trained to learn the direct control commands from the raw depth images through self-supervised reinforcement learning algorithm. To reduce the effect of sample inefficiency and safety during initial training, a virtual reality platform is used to simulate a natural working environment and generate obstacle avoidance data for training. To ensure a smooth transfer to a real robot, the automatic domain randomization technique is used to generate randomly distributed environmental parameters through the obstacle avoidance simulation of virtual robots in the virtual environment, contributing to better performance in the natural environment. Findings The method has been tested in both simulations with a real UR3 robot for several practical applications. The results of this paper indicate that the proposed approach can effectively make the robot safety-aware and learn how to divert its trajectory to avoid accidents with humans within the workspace. Research limitations/implications The method has been tested in both simulations with a real UR3 robot in several practical applications. The results indicate that the proposed approach can effectively make the robot be aware of safety and learn how to change its trajectory to avoid accidents with persons within the workspace. Originality/value This paper provides a novel collision avoidance framework that allows robots to work alongside human operators in unstructured and complex environments. The method uses end-to-end policy training to directly extract the optimal path from the visual inputs for the scene.

Novel fractional hybrid impedance control of series elastic muscle-tendon actuator

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Mohammad Javad Fotuhi ◽  
Zafer Bingul
Keyword(s):  
Contact Stress ◽  
Impedance Control ◽  
Robustness Analysis ◽  
Simulation Models ◽  
Experimental Results ◽  
Uncertain Environments ◽  
Content Type ◽  
Force Tracking ◽  
Comparative Results ◽  
Series Elastic

Purpose This paper aims to develope a novel fractional hybrid impedance control (FHIC) approach for high-sensitive contact stress force tracking control of the series elastic muscle-tendon actuator (SEM-TA) in uncertain environments. Design/methodology/approach In three different cases, the fractional parameters of the FHIC were optimized with the particle swarm optimization algorithm. Its adaptability to the pressure of the sole of the foot on real environments such as grass (soft), carpet (medium) and solid floors (hard) is far superior to traditional impedance control. The main aim of this paper is to derive the dynamic simulation models of the SEM-TA, to develop a control architecture allowing for high-sensitive contact stress force control in three cases and to verify the simulation models and the proposed controller with experimental results. The performance of the optimized controllers was evaluated according to these parameters, namely, maximum overshoot, steady-state error, settling time and root mean squared errors of the positions. Moreover, the frequency robustness analysis of the controllers was made in three cases. Findings Different simulations and experimental results were conducted to verify the control performance of the controllers. According to the comparative results of the performance, the responses of the proposed controller in simulation and experimental works are very similar. Originality/value Origin approach and origin experiment.

Sign in / Sign up

Export Citation Format

Share Document