This paper proposes an enhanced learning anti-disturbance control method for cruise missile. In order to deal with time-varying matched and mismatched disturbances, STDO and HDO disturbance observers were designed for inner and outer rings respectively. By introducing STDO and HDO, the disturbance of inner and outer loop of the system is effectively solved. In order to improve the robustness and adaptability of the system to uncertainty, this paper introduces the perfect fitting long and short time memory (LSTM) network based on reinforcement learning control framework, and proposes a reinforcement learning control method based on LSTM. The simulation results show that the control output of the system is stable and bounded, which verifies the good performance of the proposed control structure.
Reinforcement Learning Adaptive Anti-disturbance Control Method for a Class of Cruise Missile
Lect. Notes Electrical Eng.
International Conference on Autonomous Unmanned Systems ; 2021 ; Changsha, China September 24, 2021 - September 26, 2021
Proceedings of 2021 International Conference on Autonomous Unmanned Systems (ICAUS 2021) ; Chapter : 36 ; 358-367
2022-03-18
10 pages
Article/Chapter (Book)
Electronic Resource
English
Multi-Objective Adaptive Cruise Control via Deep Reinforcement Learning
British Library Conference Proceedings | 2022
|Multi-Objective Adaptive Cruise Control via Deep Reinforcement Learning
British Library Conference Proceedings | 2022
|Multi-Objective Adaptive Cruise Control via Deep Reinforcement Learning
British Library Conference Proceedings | 2022
|