Neural network-based finite-time formation control of unmanned aerial vehicles with external disturbance

This work tackles the formation tracking issue of multiple unmanned aerial vehicles affected by external disturbances and uncertainties. A radial basis function neural network (RBFNN) is utilized within a finite-time framework to accurately estimate external disturbances and uncertainties. Furthermore, to attain expedited formation configuration and trajectory tracking while improving system robustness, a distributed controller founded on a finite-time framework is developed. The system’s finite-time convergence is convincingly demonstrated by Lyapunov theory. The simulation findings indicate that the suggested method guarantees high accuracy in trajectory tracking while adeptly addressing external disturbances and uncertainties, rendering it appropriate for real applications in multi-robot coordination.