August 1, 2025Open Access

Improved Adaptive Neural Control for USV-UAV via Gaussian Filter and Sigmoid RBF Networks

XYXu YangAnhui University GZGuoqing ZhangDalian University of Technology FHFei HuangHainan University

Key Points

The strategy ensures robust tracking of reference signals despite external disturbances and noise.
Key elements include adaptive neural control, Gaussian filter, and sigmoid RBF networks to mitigate complexities.
Simulation results confirm the proposed method's ability to maintain stability under varying marine conditions.
This research could enhance operational effectiveness for autonomous maritime and aerial vehicles.

Abstract

Abstract This note investigates the cooperative control for the unmanned surface vessel and unmanned aerial vehicle (USV-UAV) facing model uncertainties and time-varying disturbances. An improved adaptive neural control strategy is presented for tracking the reference signals by combining the backstepping method, Gaussian filter, and sigmoid radial basis function (RBF) networks. The main advantage of this strategy is its ability to manage “complexity explosion” while simultaneously suppressing high-frequency noise from both the system and the marine environment, as well as ensuring adaptation to asymmetric nonlinearities. This algorithm can guarantee that all state variables achieve semi-global uniform ultimate bounded (SGUUB) stability according to the Lyapunov theorem. As verified by the numerical simulation, the proposed strategy shows outstanding effort in the presence of external marine disturbances.

Ask AI

Helpful

Bookmark

View Full Paper