机器人2026，Vol.48Issue(4)：672-683,12.DOI:10.13973/j.cnki.robot.250163
面向人机交互的导纳与强化学习融合控制策略
Admittance and Reinforcement Learning Integrated Control Strategy for Human-Robot Interaction
摘要
Abstract
In response to the issues of insufficient interaction compliance,high collision risk,and poor tracking perfor-mance in human-robot interaction tasks,a reinforcement learning strategy based on admittance control is proposed.Firstly,a smooth and differentiable reference trajectory is generated using a soft saturation function and an expected admittance mod-el.Secondly,a reinforcement learning method based on the AC(actor-critic)structure is introduced to deal with the system dynamic uncertainties.Unlike existing studies,a controller incorporating a time-varying asymmetric barrier Lyapunov func-tion is constructed.This controller ensures accurate trajectory tracking of the end-effector while strictly satisfying position constraints,thus guaranteeing the system safety and reliability in complex interaction scenarios.Finally,the semi-global uniform ultimate boundedness of the closed-loop system is demonstrated through Lyapunov stability theory.A series of experiments are conducted on the Baxter robot experimental platform,and the proposed control method is compared with adaptive impedance control,fuzzy adaptive impedance control and traditional impedance control.The comparison results show that the proposed control method outperforms the other methods in terms of tracking accuracy,compliance and colli-sion avoidance,thereby fully validating the feasibility of the proposed method.关键词
人机交互(HRI)/导纳控制/强化学习/位置约束/时变非对称障碍李雅普诺夫函数Key words
human-robot interaction(HRI)/admittance control/reinforcement learning/position constraint/time-varying asymmetric barrier Lyapunov function引用本文复制引用
高赫佳,杨洋,陈探宇,孙长银..面向人机交互的导纳与强化学习融合控制策略[J].机器人,2026,48(4):672-683,12.基金项目
国家自然科学基金(62388010,62303101) （62388010,62303101）
安徽省高校协同创新计划(GXXT-2023-039). （GXXT-2023-039）
