Learning-Based Fault-Tolerant Optimal Formation Control of Helicopters: An Incremental Fully Actuated System Approach
Ke Zhang, Qiyang Miao, Bin Jiang
Abstract
To elevate the robustness and optimality of helicopter formation, this article proposes the incremental fully actuated system approach (FASA) integrated with reinforcement learning (RL) for the formation control of multiple helicopters with faulty swash plates. First, the helicopter model encompassing aerodynamics, flapping dynamics, and swash plate dynamics under actuator faults is established. Then, the entire helicopter formation is reinterpreted and stabilized by the incremental FASA that offers the replacement of model information, the suppression of lumped uncertainty, and the rearrangement of system dynamics, with mitigated reliance on model accuracy and computing resources. Next, considering the influence of the actuator faults of a single helicopter on the convergence of the entire formation, RL is applied to pursue the optimal control strategy against fault impact through the critic network, which updates along the dynamics revised by the incremental FASA, ensuring satisfactory formation performance throughout the flight, augmenting the cost efficiency of the control scheme, and relieving any means of identification or approximation on helicopter dynamics. Finally, the stability of the control scheme is proved, and numerical simulations are conducted to illustrate it is efficiency.