Yu, Ziquan (Northwestern Polytechnical University), Zhang, Youmin (Concordia University), Qu, Yaohong (Northwestern Ploytechnical University), Su, Chun-Yi (Concordia Univ.), Zhang, Yintao (Concordia University), Xing, Zhewen (Northwestern Polytechnical University)

Fault-Tolerant Adaptive Neural Control of Multi-UAVs against Actuator Faults

Scheduled for presentation during the Regular Session "Fault Diagnosis, Accommodation and Fault-Tolerant Control" (WeC1), Wednesday, June 12, 2019, 18:40−19:00, Heritage B

2020 International Conference on Unmanned Aircraft Systems (ICUAS), June 11-14, 2019, Athens, Greece

This information is tentative and subject to change. Compiled on April 25, 2024

Abstract

This paper is concerned with the fault-tolerant cooperative control (FTCC) problem of multiple unmanned aerial vehicles (multi-UAVs) in the communication network. By exploiting neural network (NN) to approximate the nonlinear terms existing in the highly nonlinear multi-UAVs system, a distributed neural adaptive control scheme is proposed when only a subset of follower UAVs has access to the leader UAV's states. To solve the problem of ``explosion of complexity'' in traditional backstepping architecture and reduce the number of online updating parameters of NN, dynamic surface control (DSC) and minimal learning parameter techniques are employed to reduce the computational complexity. Furthermore, by combining graph theory and Lyapunov approach, it is proved that velocities and altitudes of all follower UAVs can track the velocity and altitude of the leader UAV. Finally, simulation results are presented to verify the effectiveness of the proposed control scheme.