Neural Network-based Task-space Region Reaching Control for Multiple Euler-Lagrange Systems

This paper addresses the cooperative control problem of multiple Euler-Lagrange systems (MELSs) in task-space for region reaching, proposing a novel neural network (NN)-based distributed adaptive control scheme. By developing the NN adaptive mechanism to effectively estimate system dynamic uncertainties, and design the distributed position observer architecture incorporating potential field guidance strategies, enabling agents to autonomously perceive spatial characteristics of the target region through local information interaction. A comprehensive theoretical analysis framework is established based on Lyapunov stability theory, rigorously proving the asymptotic stability of the closed-loop system through integrated analysis of control laws, observer dynamics, and NN compensation. Numerical simulations demonstrate the superiority of the proposed control scheme in convergence accuracy, disturbance rejection capability, and collaborative efficiency.