Fault-Tolerant Control for the Formation of Multiple Unknown Nonlinear Quadrotors via Reinforcement Learning. Issue 2 (2020)

• Record Type: Journal Article
• Authors: Zhao, Wanbing; Liu, Hao; Lewis, Frank L.
• Is Part Of: IFAC-PapersOnLine. Volume 53:Issue 2(2020)
• Page Start: 2465
• Page End: 2470
• Publication Date: 2020
• Subjects: Fault-tolerant control -- formation control -- reinforcement learning -- model-free -- quadrotor system; Automatic control -- Periodicals; 629.805
• DOI: 10.1016/j.ifacol.2020.12.194
• Languages: English
• ISSNs: 2405-8963

Abstract

Abstract: In this paper, the fault-tolerant control problem for the formation of unknown quadrotor team with nonlinearities, couplings, and actuator faults in the dynamics is investigated. A distributed observer is designed to estimate the position references for each quadrotor. A hierarchical control scheme is constructed including a fault-tolerant position controller to achieve the desired formation and a fault-tolerant attitude controller to track the attitude references. Reinforcement learning algorithms are designed to learn the optimal control policies of the position and attitude controllers. Simulation results are given to illustrate the effectiveness of the proposed controller.