{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,5]],"date-time":"2025-10-05T19:55:10Z","timestamp":1759694110106,"version":"3.41.2"},"reference-count":28,"publisher":"Emerald","issue":"3","license":[{"start":{"date-parts":[[2021,2,8]],"date-time":"2021-02-08T00:00:00Z","timestamp":1612742400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.emerald.com\/insight\/site-policies"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IR"],"published-print":{"date-parts":[[2021,8,3]]},"abstract":"<jats:sec>\n<jats:title content-type=\"abstract-subheading\">Purpose<\/jats:title>\n<jats:p>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\u2019 safety.<\/jats:p>\n<\/jats:sec>\n<jats:sec>\n<jats:title content-type=\"abstract-subheading\">Design\/methodology\/approach<\/jats:title>\n<jats:p>A bilateral leader\u2013follower 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.<\/jats:p>\n<\/jats:sec>\n<jats:sec>\n<jats:title content-type=\"abstract-subheading\">Findings<\/jats:title>\n<jats:p>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.<\/jats:p>\n<\/jats:sec>\n<jats:sec>\n<jats:title content-type=\"abstract-subheading\">Originality\/value<\/jats:title>\n<jats:p>Using the aimed robotic system, the lower extremity hemiplegic patients with different movement abilities can obtain better rehabilitation efficacy.<\/jats:p>\n<\/jats:sec>","DOI":"10.1108\/ir-10-2020-0230","type":"journal-article","created":{"date-parts":[[2021,2,9]],"date-time":"2021-02-09T10:59:13Z","timestamp":1612868353000},"page":"388-400","source":"Crossref","is-referenced-by-count":7,"title":["A robotic system with reinforcement learning for lower extremity hemiparesis rehabilitation"],"prefix":"10.1108","volume":"48","author":[{"given":"Jiajun","family":"Xu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Linsen","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gaoxin","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jia","family":"Shi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinfu","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xingcan","family":"Liang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shengyao","family":"Fan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"140","published-online":{"date-parts":[[2021,2,8]]},"reference":[{"key":"key2021080209262575000_ref001","first-page":"537","article-title":"A deep reinforcement learning based approach towards generating human walking behavior with a neuromuscular model","volume-title":"Proceedings of IEEE-RAS International Conference on Humanoid Robots","year":"2019"},{"key":"key2021080209262575000_ref002","first-page":"20","article-title":"Relative entropy inverse reinforcement learning","year":"2011","journal-title":"Proceedings of Artificial Intelligences and Statistics"},{"issue":"4","key":"key2021080209262575000_ref003","doi-asserted-by":"crossref","first-page":"489","DOI":"10.1108\/IR-02-2020-0041","article-title":"Design and control of an exoskeleton with EMG-driven electrical stimulation for upper limb rehabilitation","volume":"47","year":"2020","journal-title":"Industrial Robot: The International Journal of Robotics Research and Application"},{"issue":"2","key":"key2021080209262575000_ref004","doi-asserted-by":"crossref","first-page":"231","DOI":"10.1108\/IR-09-2019-0191","article-title":"Smooth adaptive hybrid impedance control for robotic contact force tracking in dynamic environments","volume":"47","year":"2020","journal-title":"Industrial Robot: The International Journal of Robotics Research and Application"},{"issue":"8","key":"key2021080209262575000_ref005","doi-asserted-by":"crossref","first-page":"2142","DOI":"10.1016\/j.automatica.2007.12.002","article-title":"Synchronization of bilateral teleoperators with time delay","volume":"44","year":"2008","journal-title":"Automatica"},{"first-page":"3389","article-title":"Deep reinforcement learning for robotic manipulation with asynchronous off-policy updates","year":"2017","key":"key2021080209262575000_ref006"},{"key":"key2021080209262575000_ref007","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1016\/j.patrec.2017.04.007","article-title":"Learning assistive strategies for exoskeleton robots from user-robot physical interaction","volume":"99","year":"2017","journal-title":"Pattern Recognition Letters"},{"issue":"4","key":"key2021080209262575000_ref008","doi-asserted-by":"crossref","first-page":"6217","DOI":"10.1109\/LRA.2020.3011351","article-title":"Actor-critic reinforcement learning for control with stability guarantee","volume":"5","year":"2020","journal-title":"IEEE Robotics and Automation Letters"},{"issue":"3","key":"key2021080209262575000_ref009","doi-asserted-by":"crossref","first-page":"753","DOI":"10.1109\/TNNLS.2015.2511658","article-title":"Model-based reinforcement learning for infinite-horizon approximate optimal tracking","volume":"28","year":"2017","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"article-title":"Continuous control with deep reinforcement learning","volume-title":"Proceedings of International Conference on Learning Representations, arXiv: 1509.02971, 2016","year":"2016","key":"key2021080209262575000_ref010"},{"issue":"5","key":"key2021080209262575000_ref011","doi-asserted-by":"crossref","first-page":"2550","DOI":"10.1109\/TMECH.2015.2388555","article-title":"Adaptive control for nonlinear teleoperators with uncertain kinematics and dynamics","volume":"20","year":"2015","journal-title":"IEEE\/ASME Transactions on Mechatronics"},{"key":"key2021080209262575000_ref012","first-page":"511","article-title":"The MIME robotic system for upper-limb neuro-rehabilitation: results from a clinical trial in subacute stroke","volume-title":"Proceedings of IEEE International Conference on Rehabilitation Robotics","year":"2005"},{"issue":"7540","key":"key2021080209262575000_ref013","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","year":"2015","journal-title":"Nature"},{"key":"key2021080209262575000_ref014","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","year":"2016","journal-title":"Proceedings of International Conference Machine Learning"},{"issue":"3","key":"key2021080209262575000_ref015","doi-asserted-by":"crossref","first-page":"655","DOI":"10.1109\/TCYB.2015.2412554","article-title":"Optimized assistive human-robot interaction using reinforcement learning","volume":"46","year":"2016","journal-title":"IEEE Transactions on Cybernetics"},{"key":"key2021080209262575000_ref016","first-page":"5076","article-title":"Deep learning based motion prediction for exoskeleton robot control in upper limb rehabilitation","volume-title":"Proceedings of IEEE International Conference on Robotics and Automation","year":"2019"},{"year":"2017","key":"key2021080209262575000_ref017","article-title":"Proximal policy optimization algorithms"},{"issue":"2","key":"key2021080209262575000_ref018","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1109\/86.242425","article-title":"Improving the efficacy of electrical stimulation-induced leg cycle ergometry: an analysis based on a dynamic musculoskeletal model","volume":"1","year":"1993","journal-title":"IEEE Transactions on Rehabilitation Engineering"},{"issue":"4","key":"key2021080209262575000_ref019","doi-asserted-by":"crossref","first-page":"1668","DOI":"10.1109\/TMECH.2014.2347034","article-title":"Novel cooperative teleoperation framework: multi-master\/single slave system","volume":"20","year":"2015","journal-title":"IEEE\/ASME Transactions on Mechatronics"},{"issue":"4","key":"key2021080209262575000_ref020","doi-asserted-by":"crossref","first-page":"1954","DOI":"10.1109\/TMECH.2016.2551725","article-title":"Robotics-assisted mirror rehabilitation therapy: a therapist-in-the-loop assist-as-needed architecture","volume":"21","year":"2016","journal-title":"IEEE\/ASME Transactions on Mechatronics"},{"key":"key2021080209262575000_ref021","doi-asserted-by":"crossref","first-page":"52","DOI":"10.1016\/j.conengprac.2017.07.002","article-title":"Cooperative modalities in robotic tele-rehabilitation using nonlinear bilateral impedance control","volume":"67","year":"2017","journal-title":"Control Engineering Practice"},{"issue":"12","key":"key2021080209262575000_ref022","doi-asserted-by":"crossref","first-page":"1722","DOI":"10.1049\/iet-cta.2017.1253","article-title":"Impedance control of nonlinear multi-dof teleoperation systems with time delay: absolute stability","volume":"12","year":"2018","journal-title":"IET Control Theory & Applications"},{"issue":"1","key":"key2021080209262575000_ref023","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1108\/IJICC-09-2014-0041","article-title":"Upper limb bilateral symmetric training with robotic assistance and clinical outcomes for stroke: a pilot study","volume":"9","year":"2016","journal-title":"International Journal of Intelligent Computing and Cybernetics"},{"key":"key2021080209262575000_ref024","first-page":"575","article-title":"Adaptive human-robot interaction control of the lower extremity robotic exoskeleton with magetorheological actuators","volume-title":"Proceedings of IEEE International Conference on Advanced Robotics and Mechatronics","year":"2019"},{"issue":"4","key":"key2021080209262575000_ref025","doi-asserted-by":"crossref","first-page":"5385","DOI":"10.1109\/LRA.2020.3007408","article-title":"A multi-channel reinforcement learning framework for robotic mirror therapy","volume":"5","year":"2020","journal-title":"IEEE Robotics and Automation Letters"},{"key":"key2021080209262575000_ref026","first-page":"1294","article-title":"Design and implementation of the lower extremity robotic exoskeleton with magnetorheological actuators","volume-title":"Proceedings of IEEE International Conference on Mechatronics and Automation","year":"2019"},{"issue":"10","key":"key2021080209262575000_ref027","doi-asserted-by":"crossref","first-page":"2216","DOI":"10.1109\/TNSRE.2019.2937000","article-title":"A multi-mode rehabilitation robot with magnetorheological actuators based on human motion intention estimation","volume":"27","year":"2019","journal-title":"IEEE Transactions on Neural Systems and Rehabilitation Engineering"},{"key":"key2021080209262575000_ref028","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2939174","article-title":"Asynchronous episodic deep deterministic policy gradient: toward continuous control in computationally complex environments","year":"2019","journal-title":"IEEE Transactions on Cybernetics"}],"container-title":["Industrial Robot: the international journal of robotics research and application"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.emerald.com\/insight\/content\/doi\/10.1108\/IR-10-2020-0230\/full\/xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.emerald.com\/insight\/content\/doi\/10.1108\/IR-10-2020-0230\/full\/html","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,24]],"date-time":"2025-07-24T21:40:11Z","timestamp":1753393211000},"score":1,"resource":{"primary":{"URL":"http:\/\/www.emerald.com\/ir\/article\/48\/3\/388-400\/176486"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,2,8]]},"references-count":28,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2021,2,8]]},"published-print":{"date-parts":[[2021,8,3]]}},"alternative-id":["10.1108\/IR-10-2020-0230"],"URL":"https:\/\/doi.org\/10.1108\/ir-10-2020-0230","relation":{},"ISSN":["0143-991X","0143-991X"],"issn-type":[{"type":"print","value":"0143-991X"},{"type":"print","value":"0143-991X"}],"subject":[],"published":{"date-parts":[[2021,2,8]]}}}