Soft Prescribed Performance-Based Reinforcement Learning Control for a PAM-Actuated Rehabilitation Exoskeleton
针对康复外骨骼训练中性能约束与系统退化间的冲突，提出一种软预设性能的强化学习控制方法，通过动态调整安全边界确保高精度和安全运行，实验验证了有效性。
In a rehabilitation exoskeleton, stable and safe operation is of central importance in rehabilitation training. This article develops a soft prescribed performance (SPP)-based reinforcement learning (RL) control method to address the conflict between performance constraints and system degradation, ensuring high accuracy and safe operation. First, a tunnel-type prescribed performance function is used to achieve faster convergence and smaller overshoot. Safety boundaries are used to define the tolerable error range, and an intermediate system links the safety and soft boundaries. The soft boundaries are dynamically adjusted to ensure safe operation by temporarily relaxing constraints during performance degradation. An RL approach based on an actor-critic (AC) structure is employed to handle unknown lumped disturbance. Theoretical analysis confirms the stability of the closed-loop system. Furthermore, a series of experiments is conducted on a self-built upper-limb rehabilitation exoskeleton robot driven by pneumatic artificial muscles to validate the effectiveness and robustness of the proposed method.