A study on robot force control based on the GMM/GMR algorithm fusing different compensation strategies

• DOI: 10.3389/fnbot.2024.1290853
• Publication Date: 2024-01-29T04:23:31Z
• Authors: Meng Xiao; Xuefei Zhang; Tie Zhang; Shouyan Chen; Yanbiao Zou; Wen Wu
• Keywords: Impedance Control; Robustness; Contact force

To address traditional impedance control methods' difficulty with obtaining stable forces during robot-skin contact, a force based on the Gaussian mixture model/Gaussian regression (GMM/GMR) algorithm fusing different compensation strategies is proposed. The contact relationship between robot end effector and human skin established through an model. allow to adapt flexible environments, reinforcement learning algorithms strategy mechanics model compensate for strategy. Two environment dynamics models that can be trained offline are proposed quickly obtain strategies. Three fused GMM/GMR algorithm, exploiting online calculation of physical learning, which improve robustness versatility when adapting environments. experimental results show obtained by relatively stable. It has better than control, error within ~±0.2 N.