Scholarlink

<p>In this article, an adaptive finite-time neural optimal control technique is proposed for flexible-joint (FJ) Robots by applying reinforcement learning (RL) technique of identifier-critic-actor architecture. Radial basis function neural networks (RBFNNs) are used to estimate the uncertain functions in the considered system. Therefore, the finite-time update rules for the critic and actor networks are formulated on the basis of the negative gradient of a positive function, which is derived from the partial derivatives of the Hamilton-Jacobi-Bellman (HJB) equation discussed herein. Using the discussed approach, the RL algorithm is simplified and two preconditions are released: persistent excitation and known dynamics. The controller design method proposed in this article not only simplifies the control way, but also solves the singularity problem that occurs in the traditional backstepping optimal control techniques. Stability analysis reveals that the tracking error inclines to a vicinity of zero, while the boundedness of all system signals is ensured within finite time. Finally, the practicability of the designed control scheme is further demonstrated by the 2-link FJ robot simulation example.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Adaptive finite-time optimal control for flexible-joint robots via an identifier-critic-actor reinforcement learning algorithm

  • 期刊论文

  • 发表日期：

    2025年9月18日

查看全文
  • Huanqing Wang,
  • Sijia Jia,
  • Siwen Liu,
  • Xiaoping Liu

摘要

In this article, an adaptive finite-time neural optimal control technique is proposed for flexible-joint (FJ) Robots by applying reinforcement learning (RL) technique of identifier-critic-actor architecture. Radial basis function neural networks (RBFNNs) are used to estimate the uncertain functions in the considered system. Therefore, the finite-time update rules for the critic and actor networks are formulated on the basis of the negative gradient of a positive function, which is derived from the partial derivatives of the Hamilton-Jacobi-Bellman (HJB) equation discussed herein. Using the discussed approach, the RL algorithm is simplified and two preconditions are released: persistent excitation and known dynamics. The controller design method proposed in this article not only simplifies the control way, but also solves the singularity problem that occurs in the traditional backstepping optimal control techniques. Stability analysis reveals that the tracking error inclines to a vicinity of zero, while the boundedness of all system signals is ensured within finite time. Finally, the practicability of the designed control scheme is further demonstrated by the 2-link FJ robot simulation example.