This paper presents an innovative control strategy based on reinforcement learning (RL) to tackle the attitude tracking control problem for unmanned aerial vehicles (UAVs), emphasizing both desired transient performance and an optimal long-term performance index. Firstly, a prescribed performance function along with a corresponding error transformation technique is introduced to meet the desired transient and steady-state performance requirements. Next, by incorporating the Actor-Critic Neural Network (NN), a model-free optimal attitude tracking controller is developed, which compensates for model uncertainties and external perturbations in real time. Finally, comparative numerical simulations are conducted to demonstrate the effectiveness and superiority of the proposed method.
Reinforcement Learning Based Attitude Tracking Control of Unmanned Aerial Vehicles with Prescribed Performance
Lect. Notes Electrical Eng.
International Conference on Guidance, Navigation and Control ; 2024 ; Changsha, China August 09, 2024 - August 11, 2024
2025-02-27
11 pages
Article/Chapter (Book)
Electronic Resource
English
Attitude Control in Unmanned Aerial Vehicles Using Reinforcement Learning—A Survey
Springer Verlag | 2021
|MAINTAINING ATTITUDE CONTROL OF UNMANNED AERIAL VEHICLES
European Patent Office | 2022
|MAINTAINING ATTITUDE CONTROL OF UNMANNED AERIAL VEHICLES
European Patent Office | 2018
|