Disturbance rejection and high dynamic quadrotor control based on reinforcement learning and supervised learning.
Mingjun LiZhihao CaiJiang ZhaoJinyan WangYingxun WangPublished in: Neural Comput. Appl. (2022)
Keyphrases
- disturbance rejection
- reinforcement learning
- supervised learning
- control system
- closed loop
- pid controller
- learning algorithm
- training data
- dynamic environments
- kernel based learning
- limit cycle
- optimal control
- real time
- learning tasks
- neural network
- fault diagnosis
- semi supervised
- fuzzy logic
- control algorithm
- state space
- control law
- temporal difference
- matlab simulink
- training set
- machine learning