Robust optimal control law learning for heterogeneous rotorcraft formation involving unknown parameters
Hao Liu, Qingyao Meng, Liang Yang, Hui Tian, Junya Yuan · 2020
A distributed robust optimal formation control problem is discussed via reinforcement learning for the heterogeneous rotorcrafts with unknown parameters. The formation system involves equivalent disturbance including nonlinearity and external disturbance. The proposed robust optimal controller consists of a nominal controller and a robust compensator. The reinforcement learning algorithm is used to obtain the unknown system parameters. Then, the nominal controller is applied to achieve the desired optimal control input; the robust compensator is constructed to counteract the equivalent disturbance in the overall system. Simulation result verifies the effectiveness of the proposed control approach.