Liu, Hao (Beihang University), Meng, Qingyao (Beihang University), Liang, Yang (Beihang University), Tian, Hui (Beihang University), Junya, Yuan (Beihang University)

Robust Optimal Control Law Learning for Heterogeneous Rotorcraft Formation Involving Unknown Parameters

Scheduled for presentation during the Invited Session "Artificial Intelligence and its Applications to Unmanned Flight Systems" (WeC1), Wednesday, September 2, 2020, 17:20−17:40, Macedonia Hall

2020 International Conference on Unmanned Aircraft Systems (ICUAS), September 1-4, 2020 (Postponed from June 9-12, 2020), Athens, Greece

This information is tentative and subject to change. Compiled on April 18, 2024

Abstract

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.