TY - GEN
T1 - Neural control for constrained human-robot interaction with human motion intention estimation and impedance learning
AU - Yu, Xinbo
AU - He, Wei
AU - Li, Yanan
AU - Yang, Chenguang
AU - Sun, Changyin
N1 - Publisher Copyright:
© 2017 IEEE.
PY - 2017/12/29
Y1 - 2017/12/29
N2 - In this paper, an impedance control strategy is proposed for a rigid robot collaborating with human by considering impedance learning and human motion intention estimation. The least square method is used in human impedance identification, and the robot can adjust its impedance parameters according to human impedance model for guaranteeing compliant collaboration. Neural networks (NNs) are employed in human motion intention estimation, so that the robot follows the human actively and human partner costs less control effort. On the other hand, the full-state constraints are considered for operational safety in human-robot interactive processes. Neural control is presented in the control strategy to deal with the dynamic uncertainties and improve the system robustness. Simulation results are carried out to show the effectiveness of the proposed control design.
AB - In this paper, an impedance control strategy is proposed for a rigid robot collaborating with human by considering impedance learning and human motion intention estimation. The least square method is used in human impedance identification, and the robot can adjust its impedance parameters according to human impedance model for guaranteeing compliant collaboration. Neural networks (NNs) are employed in human motion intention estimation, so that the robot follows the human actively and human partner costs less control effort. On the other hand, the full-state constraints are considered for operational safety in human-robot interactive processes. Neural control is presented in the control strategy to deal with the dynamic uncertainties and improve the system robustness. Simulation results are carried out to show the effectiveness of the proposed control design.
KW - adaptive control
KW - full-state constraints
KW - human-robot interaction (HRI)
KW - impedance learning
KW - motion intention estimation
KW - neural networks (NNs)
UR - https://www.scopus.com/pages/publications/85050357141
U2 - 10.1109/CAC.2017.8243230
DO - 10.1109/CAC.2017.8243230
M3 - 会议稿件
AN - SCOPUS:85050357141
T3 - Proceedings - 2017 Chinese Automation Congress, CAC 2017
SP - 2682
EP - 2687
BT - Proceedings - 2017 Chinese Automation Congress, CAC 2017
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2017 Chinese Automation Congress, CAC 2017
Y2 - 20 October 2017 through 22 October 2017
ER -