RNN Learning-Based Prescribed-Time Safe and Robust Cooperative Group Formation Control for High-Speed Flight Vehicle Swarm Under Dynamic Event-Triggered Communication

Concurrent and complex aerial missions with multiple targets exceed the capabilities of a single cooperative formation of high-speed flight vehicles (HSFVs). To address this challenge, this article decomposes a fleet of HSFVs (subject to multiple compounding factors, including unknown aerodynamic disturbances, unmodeled or parametric uncertainties, actuator faults, and potential intervehicle collisions) into several subgroups and develops a recurrent neural network (RNN) online learning-based prescribed-time safe and robust cooperative group formation control protocol under dynamic event-triggered communication. A distributed prescribed-time event-triggered estimator (DP-TE-TE) is first developed to drive all HSFVs to acquire the convex hull information (i.e., input, velocity, and position) spanned by multiple virtual leader vehicles (VLVs) before grouping or the input, velocity, and position information of their respective single VLV within the group after grouping. Then, based on the constraint-following theory, the safety distance inequality between any potentially colliding pair of HSFVs, along with the first-order differential equation involving the formation position tracking error, is converted into collision motion constraints and prescribed-time trajectory tracking constraints, respectively. To enhance the flight control performance of the swarm, an RNN is constructed for each HSFV to learn the unknown nonlinear function induced by multiple compounding factors, thereby providing online compensation for the subsequent control design. Finally, by integrating the constraint-following errors derived from collision motion constraints and prescribed-time trajectory tracking constraints, the RNN compensation term, and the estimated information, the prescribed-time safe and robust cooperative group formation control scheme (P-TSRCGFCS) is proposed. In the simulation examples, the effectiveness of the proposed algorithms is verified by dividing 12 HSFVs and three VLVs into three subgroups to perform the desired cooperative group formation task.