{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:31:58Z","timestamp":1785544318171,"version":"3.56.0"},"reference-count":34,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2024,1,29]],"date-time":"2024-01-29T00:00:00Z","timestamp":1706486400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Neurorobot."],"abstract":"<jats:p>To address traditional impedance control methods' difficulty with obtaining stable forces during robot-skin contact, a force control based on the Gaussian mixture model\/Gaussian mixture regression (GMM\/GMR) algorithm fusing different compensation strategies is proposed. The contact relationship between a robot end effector and human skin is established through an impedance control model. To allow the robot to adapt to flexible skin environments, reinforcement learning algorithms and a strategy based on the skin mechanics model compensate for the impedance control strategy. Two different environment dynamics models for reinforcement learning that can be trained offline are proposed to quickly obtain reinforcement learning strategies. Three different compensation strategies are fused based on the GMM\/GMR algorithm, exploiting the online calculation of physical models and offline strategies of reinforcement learning, which can improve the robustness and versatility of the algorithm when adapting to different skin environments. The experimental results show that the contact force obtained by the robot force control based on the GMM\/GMR algorithm fusing different compensation strategies is relatively stable. It has better versatility than impedance control, and the force error is within ~\u00b10.2 N.<\/jats:p>","DOI":"10.3389\/fnbot.2024.1290853","type":"journal-article","created":{"date-parts":[[2024,1,29]],"date-time":"2024-01-29T04:23:31Z","timestamp":1706502211000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["A study on robot force control based on the GMM\/GMR algorithm fusing different compensation strategies"],"prefix":"10.3389","volume":"18","author":[{"given":"Meng","family":"Xiao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuefei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tie","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shouyan","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanbiao","family":"Zou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wen","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2024,1,29]]},"reference":[{"key":"B1","first-page":"83","article-title":"Evaluation of variable impedance- and hybrid force\/motioncontrollers for learning force tracking skills","volume-title":"2022 IEEE\/SICE International Symposium on System Integration","author":"Anand","year":"2022"},{"key":"B2","doi-asserted-by":"publisher","first-page":"6129","DOI":"10.1109\/LRA.2020.3011379","article-title":"Learning variable impedance control for contact sensitive tasks","volume":"5","author":"Bogdanovic","year":"2020","journal-title":"IEEE Robot. Automat. Lett"},{"key":"B3","doi-asserted-by":"publisher","first-page":"585656","DOI":"10.3389\/fdgth.2020.585656","article-title":"The upcoming role for nursing and assistive robotics: opportunities and challenges ahead","volume":"2","author":"Christoforou","year":"2020","journal-title":"Front. Digit. Health"},{"key":"B4","doi-asserted-by":"publisher","first-page":"216","DOI":"10.1177\/09544054221100004","article-title":"Impedance control and parameter optimization of surface polishing robot based on reinforcement learning","volume":"237","author":"Ding","year":"2023","journal-title":"Proc. Inst. Mech. Eng. B"},{"key":"B5","doi-asserted-by":"publisher","first-page":"296","DOI":"10.1007\/978-3-030-66645-3_25","article-title":"Variable impedance control of manipulator based on DQN. Intelligent Robotics and Applications. ICIRA 2020","volume":"12595","author":"Hou","year":"2020","journal-title":"Lect. Not. Comput. Sci"},{"key":"B6","doi-asserted-by":"publisher","first-page":"789","DOI":"10.1007\/s10845-021-01825-9","article-title":"Adaptive obstacle avoidance in path planning of collaborative robots for dynamic manufacturing","volume":"34","author":"Hu","year":"2023","journal-title":"J. Intell. Manuf"},{"key":"B7","doi-asserted-by":"publisher","first-page":"348","DOI":"10.1017\/S0263574714000228","article-title":"Anthropomorphic robotic arm with integrated elastic joints for TCM remedial massage","volume":"33","author":"Huang","year":"2015","journal-title":"Robotica"},{"key":"B8","doi-asserted-by":"publisher","first-page":"1136","DOI":"10.3390\/s23031136","article-title":"Pleasant stroke touch on human back by a human and a robot","volume":"23","author":"Ishikura","year":"2023","journal-title":"Sensors"},{"key":"B9","doi-asserted-by":"publisher","first-page":"323","DOI":"10.1177\/0954411918759801","article-title":"Skin mechanical properties and modeling: a review","volume":"232","author":"Joodaki","year":"2018","journal-title":"Proc. Inst. Mech. Eng. H"},{"key":"B10","doi-asserted-by":"publisher","first-page":"43","DOI":"10.3389\/fnbot.2017.00043","article-title":"Impedance control for robotic rehabilitation: a robust Markovian approach","volume":"11","author":"Jutinico","year":"2017","journal-title":"Front. Neurorobot"},{"key":"B11","doi-asserted-by":"publisher","first-page":"598898","DOI":"10.3389\/fphys.2020.598898","article-title":"Selective effects of manual massage and foam rolling on perceived recovery and performance: current knowledge and future directions toward robotic massages","volume":"11","author":"Kerautret","year":"2020","journal-title":"Front. Physiol"},{"key":"B12","first-page":"4724","article-title":"Arm-hand motion-force coordination for physical interactions with non-flat surfaces using dynamical systems: toward compliant robotic massage","volume-title":"2020 IEEE International Conference on Robotics and Automation","author":"Khoramshahi","year":"2020"},{"key":"B13","doi-asserted-by":"publisher","first-page":"165","DOI":"10.1007\/s10846-020-01176-2","article-title":"A control scheme for physical human-robot interaction coupled with an environment of unknown stiffness","volume":"100","author":"Li","year":"2020","journal-title":"J. Intell. Robot Syst"},{"key":"B14","doi-asserted-by":"crossref","first-page":"553","DOI":"10.1007\/978-3-642-30223-7_87","article-title":"Brief introduction of back propagation (BP) neural network algorithm and its improvement","volume-title":"Adv. Comput. Sci. Inform. Eng","author":"Li","year":"2012"},{"key":"B15","doi-asserted-by":"publisher","first-page":"1307","DOI":"10.1007\/s11771-017-3536-3","article-title":"Design and implementation of robot serial integrated rotary joint with safety compliance","volume":"24","author":"Li","year":"2017","journal-title":"J. Cent. South Univ"},{"key":"B16","doi-asserted-by":"publisher","first-page":"1170","DOI":"10.1109\/TRO.2018.2830405","article-title":"Force, impedance, and trajectory learning for contact tooling and haptic identification","volume":"34","author":"Li","year":"2018","journal-title":"IEEE Trans. Robot"},{"key":"B17","doi-asserted-by":"publisher","first-page":"8013","DOI":"10.1109\/TIE.2017.2694391","article-title":"Adaptive impedance control of human-robot cooperation using reinforcement learning","volume":"64","author":"Li","year":"2017","journal-title":"IEEE Trans. Ind. Electron"},{"key":"B18","doi-asserted-by":"publisher","first-page":"2888","DOI":"10.1109\/TMECH.2020.3047919","article-title":"Optimized interaction control for robot manipulator interacting with flexible environment","volume":"26","author":"Liu","year":"2021","journal-title":"IEEE\/ASME Trans. Mechatron"},{"key":"B19","doi-asserted-by":"crossref","first-page":"1338","DOI":"10.1109\/CAC53003.2021.9728103","article-title":"Impedance control of slag removal robot based on Q-Learning","volume-title":"2021 China Automation Congress","author":"Luo","year":"2021"},{"key":"B20","doi-asserted-by":"crossref","first-page":"235","DOI":"10.1007\/978-3-030-89098-8_22","article-title":"Robot bolt skill learning based on GMM-GMR","volume-title":"Lecture Notes in Computer Science: Intelligent Robotics and Applications","author":"Man","year":"2021"},{"key":"B21","first-page":"560","article-title":"Reinforcement learning based variable impedance control for high precision human-robot collaboration tasks","volume-title":"2021 6th IEEE International Conference on Advanced Robotics and Mechatronics","author":"Meng","year":"2021"},{"key":"B22","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"Mnih","year":"2015","journal-title":"Nature"},{"key":"B23","doi-asserted-by":"publisher","first-page":"417","DOI":"10.1007\/s10846-020-01183-3","article-title":"Model-based reinforcement learning variable impedance control for human-robot collaboration","volume":"100","author":"Roveda","year":"2020","journal-title":"J. Intell. Robot. Syst"},{"key":"B24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TRO.2017.2776318","article-title":"Online identification of environment Hunt-Crossley models using polynomial linearization","volume":"34","author":"Schindeler","year":"2018","journal-title":"IEEE Trans. Robot"},{"key":"B25","first-page":"705","article-title":"Hybrid vision-force robot force control for tasks on soft tissues","volume-title":"2021 27th International Conference on Mechatronics and Machine Vision in Practice","author":"Sheng","year":"2021"},{"key":"B26","first-page":"28","volume-title":"Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting. Advances in Neural Information Processing Systems","author":"Shi","year":"2015"},{"key":"B27","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1016\/B978-0-323-85380-4.00003-8","volume-title":"Intelligence Science","author":"Shi","year":"2021"},{"key":"B28","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1109\/CRC.2017.20","article-title":"Impedance control of robots: an overview","volume-title":"2017 2nd International Conference on Cybernetics, Robotics and Control","author":"Song","year":"2017"},{"key":"B29","doi-asserted-by":"publisher","first-page":"801","DOI":"10.1017\/S0263574718001339","article-title":"A tutorial survey and comparison of impedance control on robotic manipulation","volume":"37","author":"Song","year":"2019","journal-title":"Robotica"},{"key":"B30","doi-asserted-by":"crossref","first-page":"1951","DOI":"10.1109\/CDC40024.2019.9029686","article-title":"Adaptive impedance control with setpoint force tracking for unknown soft environment interactions","volume-title":"2019 IEEE 58th Conference on Decision and Control","author":"Stephens","year":"2019"},{"key":"B31","doi-asserted-by":"publisher","first-page":"104224","DOI":"10.1016\/j.robot.2022.104224","article-title":"A survey of robot manipulation in contact","volume":"156","author":"Suomalainen","year":"2022","journal-title":"Robot. Autonom. Syst"},{"key":"B32","doi-asserted-by":"crossref","first-page":"6800","DOI":"10.1109\/CAC51589.2020.9327397","article-title":"Overview of robot force control algorithms based on neural network","volume-title":"2020 Chinese Automation Congress","author":"Weng","year":"2020"},{"key":"B33","doi-asserted-by":"publisher","first-page":"13225","DOI":"10.1109\/TIE.2021.3134082","article-title":"Model-based actor\u2013critic learning of robotic impedance control in complex interactive environment","volume":"69","author":"Zhao","year":"2022","journal-title":"IEEE Trans. Industr. Electr"},{"key":"B34","doi-asserted-by":"publisher","first-page":"104667","DOI":"10.1016\/j.jmbbm.2021.104667","article-title":"Extended Kalman filter for online soft tissue characterization based on Hunt-Crossley contact model","volume":"123","author":"Zhu","year":"2021","journal-title":"J. Mech. Behav. Biomed. Mater"}],"container-title":["Frontiers in Neurorobotics"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnbot.2024.1290853\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,29]],"date-time":"2024-01-29T04:23:40Z","timestamp":1706502220000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnbot.2024.1290853\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,29]]},"references-count":34,"alternative-id":["10.3389\/fnbot.2024.1290853"],"URL":"https:\/\/doi.org\/10.3389\/fnbot.2024.1290853","relation":{},"ISSN":["1662-5218"],"issn-type":[{"value":"1662-5218","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1,29]]},"article-number":"1290853"}}