Shared Impedance Control Based on Reinforcement Learning in a Human-Robot Collaboration Task

被引：6

作者：

Wu, Min ^{[1
]}

He, Yanhao ^{[1
]}

Liu, Steven ^{[1
]}

机构：

[1] Tech Univ Kaiserslautern, D-67663 Kaiserslautern, Germany

来源：

ADVANCES IN SERVICE AND INDUSTRIAL ROBOTICS | 2020年 / 980卷

关键词：

Physical human-robot collaboration; Impedance control; Reinforcement learning;

D O I：

10.1007/978-3-030-19648-6_12

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this work a shared impedance control scheme for a hybrid human-robot team is designed for transporting a rigid workpiece to a desired position. Within the scope of proposed control structure, both human and robot are regarded as mechanical impedance and their parameters are adapted continuously in real-time. Reinforcement learning is used to find an impedance parameter set for the whole team to optimize a task-orient cost function. Then the learned parameters are further adjusted by taking human's disagreement into consideration. The proposed method is aimed to reduce human's control effort during collaboration and be flexible to variation of the task or environment. Experimental results are presented to illustrate the performance.

引用

页码：95 / 103

页数：9

共 50 条

[41] Repetitive Impedance Learning-Based Physically Human-Robot Interactive Control
Sun, Tairen
Yang, Jiantao
Pan, Yongping
Yu, Hongliu
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2024, 35 (08) : 10629 - 10638
[42] Spatial Repetitive Learning Control for Trajectory Learning in Human-Robot Collaboration
Xia, Jingkang
Li, Yanan
Yang, Lin
Huang, Deqing
2019 IEEE 58TH CONFERENCE ON DECISION AND CONTROL (CDC), 2019, : 5568 - 5573
[43] Deep reinforcement learning based proactive dynamic obstacle avoidance for safe human-robot collaboration
Xia, Wanqing
Lu, Yuqian
Xu, Weiliang
Xu, Xun
MANUFACTURING LETTERS, 2024, 41 : 1246 - 1256
[44] Hierarchical Human-robot Cooperative Control Based on GPR and Deep Reinforcement Learning
Jin Z.-H.
Liu A.-D.
Yu L.
Zidonghua Xuebao/Acta Automatica Sinica, 2022, 48 (09): : 2352 - 2360
[45] Deterministic Learning with Probabilistic Analysis on Human-Robot Shared Control
Chen, Xiaotian
Stegagno, Paolo
Yuan, Chengzhi
2020 IEEE/ASME INTERNATIONAL CONFERENCE ON ADVANCED INTELLIGENT MECHATRONICS (AIM), 2020, : 1304 - 1309
[46] Q-Learning-Based Model Predictive Variable Impedance Control for Physical Human-Robot Collaboration (Extended Abstract)
Roveda, Loris
Testa, Andrea
Shahid, Asad Ali
Braghin, Francesco
Piga, Dario
PROCEEDINGS OF THE THIRTY-SECOND INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, IJCAI 2023, 2023, : 6959 - 6963
[47] Editorial: Shared Autonomy-Learning of Joint Action and Human-Robot Collaboration
Schilling, Malte
Burgard, Wolfram
Muelling, Katharina
Wrede, Britta
Ritter, Helge
FRONTIERS IN NEUROROBOTICS, 2019, 13
[48] Learning Human-Robot Collaboration with POMDP
Lin, Hsien-I
Nguyen, Xuan-Anh
2016 16TH INTERNATIONAL CONFERENCE ON CONTROL, AUTOMATION AND SYSTEMS (ICCAS), 2016, : 1238 - 1243
[49] Interactive learning in human-robot collaboration
Ogata, T
Masago, N
Sugano, S
Tani, J
IROS 2003: PROCEEDINGS OF THE 2003 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS, VOLS 1-4, 2003, : 162 - 167
[50] An intelligent manufacturing cell based on human-robot collaboration of frequent task learning for flexible manufacturing
Zhang, Shuai
Li, Shiqi
Wang, Haipeng
Li, Xiao
INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY, 2022, 120 (9-10): : 5725 - 5740

← 1 2 3 4 5 →