Adaptive dynamic programming enhanced admittance control for robots with environment interaction and actuator saturation
International Journal of Intelligent Robotics and Applications(2021)
摘要
This paper focuses on the optimal tracking control problem for robot systems with environment interaction and actuator saturation. A control scheme combined with admittance adaptation and adaptive dynamic programming (ADP) is developed. The unknown environment is modelled as a linear system and admittance controller is derived to achieve compliant behaviour of the robot. In the ADP framework, the cost function is defined with non-quadratic form and the critic network is designed with radial basis function neural network which introduces to obtain an approximate optimal control of the Hamilton–Jacobi–Bellman equation, which guarantees the optimal trajectory tracking. The system stability is analysed by Lyapunov theorem and simulations demonstrate the effectiveness of the proposed strategy.
更多查看译文
关键词
Adaptive dynamic programming, Admittance control, Robot-environment interaction, Actuator saturation, Optimal control, Neural network
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要