A study on robot force control based on the GMM/GMR algorithm fusing different compensation strategies
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...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2024-01-01
|
| Series: | Frontiers in Neurorobotics |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fnbot.2024.1290853/full |
| _version_ | 1797341195954814976 |
|---|---|
| author | Meng Xiao Xuefei Zhang Tie Zhang Shouyan Chen Yanbiao Zou Wen Wu Wen Wu |
| author_facet | Meng Xiao Xuefei Zhang Tie Zhang Shouyan Chen Yanbiao Zou Wen Wu Wen Wu |
| author_sort | Meng Xiao |
| collection | DOAJ |
| description | 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 ~±0.2 N. |
| first_indexed | 2024-03-08T10:14:26Z |
| format | Article |
| id | doaj.art-395d6dd04ff342e2b7383bdfb313160a |
| institution | Directory Open Access Journal |
| issn | 1662-5218 |
| language | English |
| last_indexed | 2024-03-08T10:14:26Z |
| publishDate | 2024-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Neurorobotics |
| spelling | doaj.art-395d6dd04ff342e2b7383bdfb313160a2024-01-29T04:23:22ZengFrontiers Media S.A.Frontiers in Neurorobotics1662-52182024-01-011810.3389/fnbot.2024.12908531290853A study on robot force control based on the GMM/GMR algorithm fusing different compensation strategiesMeng Xiao0Xuefei Zhang1Tie Zhang2Shouyan Chen3Yanbiao Zou4Wen Wu5Wen Wu6Department of Rehabilitation, Zhujiang Hospital, Southern Medical University, Guangzhou, ChinaDepartment of Rehabilitation, Zhujiang Hospital, Southern Medical University, Guangzhou, ChinaSchool of Mechanical and Automotive Engineering, South China University of Technology, Guangzhou, ChinaSchool of Mechanical and Engineering, Guangzhou University, Guangzhou, ChinaSchool of Mechanical and Automotive Engineering, South China University of Technology, Guangzhou, ChinaDepartment of Rehabilitation, Zhujiang Hospital, Southern Medical University, Guangzhou, ChinaRehabilitation Medical School, Southern Medical University, Guangzhou, ChinaTo 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 ~±0.2 N.https://www.frontiersin.org/articles/10.3389/fnbot.2024.1290853/fullrobot force controlimpedance controlreinforcement learningdeep Q-network (DQN)Gaussian mixture model/Gaussian mixture regression (GMM/GMR) |
| spellingShingle | Meng Xiao Xuefei Zhang Tie Zhang Shouyan Chen Yanbiao Zou Wen Wu Wen Wu A study on robot force control based on the GMM/GMR algorithm fusing different compensation strategies Frontiers in Neurorobotics robot force control impedance control reinforcement learning deep Q-network (DQN) Gaussian mixture model/Gaussian mixture regression (GMM/GMR) |
| title | A study on robot force control based on the GMM/GMR algorithm fusing different compensation strategies |
| title_full | A study on robot force control based on the GMM/GMR algorithm fusing different compensation strategies |
| title_fullStr | A study on robot force control based on the GMM/GMR algorithm fusing different compensation strategies |
| title_full_unstemmed | A study on robot force control based on the GMM/GMR algorithm fusing different compensation strategies |
| title_short | A study on robot force control based on the GMM/GMR algorithm fusing different compensation strategies |
| title_sort | study on robot force control based on the gmm gmr algorithm fusing different compensation strategies |
| topic | robot force control impedance control reinforcement learning deep Q-network (DQN) Gaussian mixture model/Gaussian mixture regression (GMM/GMR) |
| url | https://www.frontiersin.org/articles/10.3389/fnbot.2024.1290853/full |
| work_keys_str_mv | AT mengxiao astudyonrobotforcecontrolbasedonthegmmgmralgorithmfusingdifferentcompensationstrategies AT xuefeizhang astudyonrobotforcecontrolbasedonthegmmgmralgorithmfusingdifferentcompensationstrategies AT tiezhang astudyonrobotforcecontrolbasedonthegmmgmralgorithmfusingdifferentcompensationstrategies AT shouyanchen astudyonrobotforcecontrolbasedonthegmmgmralgorithmfusingdifferentcompensationstrategies AT yanbiaozou astudyonrobotforcecontrolbasedonthegmmgmralgorithmfusingdifferentcompensationstrategies AT wenwu astudyonrobotforcecontrolbasedonthegmmgmralgorithmfusingdifferentcompensationstrategies AT wenwu astudyonrobotforcecontrolbasedonthegmmgmralgorithmfusingdifferentcompensationstrategies AT mengxiao studyonrobotforcecontrolbasedonthegmmgmralgorithmfusingdifferentcompensationstrategies AT xuefeizhang studyonrobotforcecontrolbasedonthegmmgmralgorithmfusingdifferentcompensationstrategies AT tiezhang studyonrobotforcecontrolbasedonthegmmgmralgorithmfusingdifferentcompensationstrategies AT shouyanchen studyonrobotforcecontrolbasedonthegmmgmralgorithmfusingdifferentcompensationstrategies AT yanbiaozou studyonrobotforcecontrolbasedonthegmmgmralgorithmfusingdifferentcompensationstrategies AT wenwu studyonrobotforcecontrolbasedonthegmmgmralgorithmfusingdifferentcompensationstrategies AT wenwu studyonrobotforcecontrolbasedonthegmmgmralgorithmfusingdifferentcompensationstrategies |