Reinforcement Learning-Based Admittance Control for Physical Human–Robot Interaction With Output Constraints

Abstract

Focused on the scientific issues of collision avoidance and compliant operation of physical human-robot interaction (pHRI) systems, this paper proposes a reinforcement learning (RL) strategy based on admittance control to achieve compliant collision avoidance and accurate trajectory tracking of pHRI. Firstly, a differentiable reference trajectory is generated using a soft saturation function with an admittance model. Subsequently, a reinforcement learning strategy based on an actor-critic structure is implemented to address dynamic uncertainty and enhance tracking performance and compliance. Different from existing studies, a reinforcement learning admittance controller containing an integral barrier Lyapunov function (IBLF) is constructed to attain accurate tracking while ensuring that the end-effector achieves the position constraints. Lyapunov stability theory is employed to proof that all states of the closed-loop system remain semiglobally uniformly ultimately bounded (SGUUB). Finally, a suite of tests on Baxter robot experimental platform have been conducted to validate the superiority of the proposed algorithm compared with adaptive impedance control and conventional admittance control.