TY - GEN
T1 - Force Sensorless Admittance Control for Physical Human-Robot Interaction with Direct-Drive Manipulators
AU - Liu, Yang
AU - Wang, Xiaojuan
AU - Xie, Cheng
AU - He, Yuxiang
AU - Geng, Jiabao
AU - Chen, Songlin
N1 - Publisher Copyright:
© 2025 IEEE.
PY - 2025
Y1 - 2025
N2 - To enhance the compliance of direct-drive manipulators in physical human-robot interaction (pHRI), this paper introduces a force-sensorless admittance control method. First, a generalized momentum observer (GMO) is adopted to estimate the external interaction force, which is then transformed into an end-effector displacement correction through an admittance control algorithm. Then, a radial basis function neural network (RBFNN) is introduced to offset unmodeled dynamics, ensuring accurate tracking of the corrected reference trajectory. Finally, simulations on a 6 degree of freedom (DOF) direct-drive manipulator demonstrate that the proposed method enables precise trajectory tracking and responsive adaptation to human movements, thereby verifying its effectiveness and feasibility.
AB - To enhance the compliance of direct-drive manipulators in physical human-robot interaction (pHRI), this paper introduces a force-sensorless admittance control method. First, a generalized momentum observer (GMO) is adopted to estimate the external interaction force, which is then transformed into an end-effector displacement correction through an admittance control algorithm. Then, a radial basis function neural network (RBFNN) is introduced to offset unmodeled dynamics, ensuring accurate tracking of the corrected reference trajectory. Finally, simulations on a 6 degree of freedom (DOF) direct-drive manipulator demonstrate that the proposed method enables precise trajectory tracking and responsive adaptation to human movements, thereby verifying its effectiveness and feasibility.
KW - admittance control
KW - direct-drive manipulator
KW - physical human-robot interaction (pHRI)
KW - radial basis function neural network (RBFNN)
UR - https://www.scopus.com/pages/publications/105036001030
U2 - 10.1109/AIHCIR67580.2025.11405053
DO - 10.1109/AIHCIR67580.2025.11405053
M3 - 会议稿件
AN - SCOPUS:105036001030
T3 - 2025 4th International Conference on Artificial Intelligence, Human-Computer Interaction and Robotics, AIHCIR 2025
BT - 2025 4th International Conference on Artificial Intelligence, Human-Computer Interaction and Robotics, AIHCIR 2025
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2025 4th International Conference on Artificial Intelligence, Human-Computer Interaction and Robotics, AIHCIR 2025
Y2 - 28 November 2025 through 30 November 2025
ER -