Effectively addressing the formation control of ABS-assisted hovercraft systems with heterogeneities, unavailable leaders’ convex combination states, nonlinearities, and mixed disturbances poses significant challenges. This paper proposes a distributed neuroadaptive formation tracking strategy of ABS-assisted hovercraft systems for the first time, where aerial base stations (ABSs) are composed of unmanned aerial vehicles (UAVs) for data distribution and computation offloading. Firstly, UAVs are designed to track the virtual-leader while shaping a fixed formation, and the observer is devised for each follower hovercraft to estimate the convex combination states of UAVs. Then, output regulation equations are employed to transform heterogeneous systems into a compact form via the Kronecker product, while neural networks (NNs) are introduced to compensate for model nonlinearities. Furthermore, based on random differential equations (RDEs) combined with Lyapunov theory, the noise-to-state practical stability in probability (NSPS-P) property of the error dynamics under mixed disturbances can be obtained. Finally, simulation examples demonstrate that the outputs of follower hovercrafts rapidly achieve a time-varying formation and rotate around convex combination states of leader UAVs simultaneously.

This article addresses the problem of singularity-free fixed-time tracking control for multiple unmanned surface vehicles (USVs) with model uncertainties. To compensate for the uncertain nonlinearities in the multi-USV systems, fuzzy logic approximators are employed to estimate unknown hydrodynamic parameters. By integrating adaptive fixed-time control theory with backstepping methodology, a novel singularity-free fixed-time consensus control scheme is developed, incorporating a error switching mechanism to prevent singularities arising from the differentiation of speed control laws. Through rigorous analysis via fixed-time stability theory, the proposed control scheme guarantees that consensus tracking errors reach a small region around zero within fixed-time. Numerical simulations demonstrate the efficacy of the presented method.