Decentralized robust optimal control for modular robot manipulators via critic-identifier structure-based adaptive dynamic programming.
Bo DongFan ZhouKeping LiuYuanchun LiPublished in: Neural Comput. Appl. (2020)
Keyphrases
- optimal control
- dynamic programming
- robot manipulators
- actor critic
- control of robot manipulators
- control problems
- feedback control
- control strategy
- infinite horizon
- reinforcement learning
- policy gradient
- control law
- optimal control problems
- control scheme
- lyapunov function
- machine learning
- optimal policy
- state space
- adaptive fuzzy
- adaptive control
- dynamic model
- tracking error
- multi objective