Adaptive Prescribed-Time Optimal Control for Flexible-Joint Robots via Reinforcement Learning
针对柔性关节机器人，提出一种预设时间模糊最优控制方法，利用强化学习策略在预设时间内实现最优跟踪，并通过仿真验证了有效性。
This article proposes a prescribed-time fuzzy optimal control approach for flexible-joint (FJ) robot systems utilizing the reinforcement learning (RL) strategy. The uniqueness of this method lies in its ability to ensure optimal tracking performance for n-link flexible joint robots within the prescribed-time frame, while the actor and critic fuzzy logic system effectively approximate the optimal cost and evaluates system performance. First, the optimal controllers with the auxiliary compensation term are constructed by utilizing the online approximation of the modified performance index function and RL actor-critic structure. The designed controller can deal with unknown structure impacts and avoid model identification. Besides, in designing the prescribed-time scale function, the introduced constant term not only prevents singularity but also allows flexible setting of constraint regions. The proposed scheme is theoretically verified to satisfy the Bellman optimality principle and ensure the tracking error converges to the desired zone within the prescribed time. Finally, the practicability of the designed control scheme is further demonstrated by the 2-link FJ robot simulation example.