Cerebellar Model Articulation Neural Network-Based Distributed Fault Tolerant Tracking Control with Obstacle Avoidance for Fixed-Wing UAVs
Moshu Qian, Zhu Wu, Bin Jiang
Abstract
In this paper, the distributed fault-tolerant tracking control (FTTC) and obstacle avoidance problem is investigated for multiple unmanned aerial vehicles (UAVs) considering lumped disturbances and communication link faults. Firstly, a cerebellar model articulation neural network (CMANN) is introduced to esti-mate the lumped disturbances. Meanwhile, the distributed virtual leader state observers are used to address unknown communication faults. Then, a distributed nonsingular fast terminal sliding mode formation controller is implemented to track desired trajectory, and an virtual-agent artificial potential function (VAAPF) is designed to accomplish obstacle avoidance. Furthermore, the stability of the closed loop formation control systems with obstacle avoidance is proved using graph theory and Lyapunov theory. Finally, simulation results of three fixed-wing UAVs are given to show the effectiveness and good performance of the proposed scheme.