Neural Observer-Based Intelligent Fault-Tolerant Control of Multi-Helicopters Under Actuator Faults: A Fully Actuated System Approach

This paper investigates the fault-tolerant formation control of multiple unmanned helicopters under actuator faults through a neural-based fully actuated system approach (FASA). First, the kinematic and dynamic model of the helicopter with actuator faults is established, from which the fully actuated system description of a helicopter is derived. Second, to mitigate the dependence on model accuracy, a neural observer is designed to approximate the lumped uncertainty including the nonlinear, coupling, and faulty terms of a helicopter. Third, based on the estimated system dynamic, a triple-layered FASA controller is proposed to achieve the leader-follower formation control of helicopters. Finally, numerical simulations are conducted to validate the efficiency of the proposed algorithm.