Value Iteration-Based Optimal Tracking Control for Robot Visual Servoing Under Time-Varying Disturbances
Summary
No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.
Summarise with VIRAT Free to try with your Science Catalogs account.Abstract
This paper proposes an optimal tracking control scheme based on value iteration for robotic visual servoing under time-varying disturbances. The control input and the time-varying disturbance is used as two opposing players in the zero-sum game framework. A value iteration algorithm is used to online solve a zero-sum game for the robust optimal policy, while a neural network is employed as a function approximator to adaptively fit the value function and optimal control law, thereby achieving optimal tracking control. The asymptotic stability of the closed-loop manipulator system is then rigorously ensured based on Lyapunov stability theory. Finally, comprehensive numerical simulations confirm the algorithm's practical effectiveness and robustness.
Fields of Study & Subjects
Adaptive Dynamic Programming Control
Reinforcement Learning in Robotics
Adaptive Control of Nonlinear Systems
Publication details
- Journal / source
- International Conference on Electrical Automation and Artificial Intelligence (ICEAAI)
- Pages
- 817–820
- Publication date
- 16 January 2026
- Language
- EN