Neural Network-Based Formation Control With Target Tracking for Second-Order Nonlinear Multiagent Systems

Abstract

This article proposes a distance-based formation control and target tracking for multiagent systems, where agents are modeled using second-order nonlinear systems in the presence of disturbance. By applying a rigid graph theory, we developed a neural network (NN)-based backstepping controller to address the distance-based formation control problem of nonlinear multiagent systems. To compensate for the unknown nonlinearity in the system dynamics, the radial basis function NN was used where the NN tuning law was derived based on Lyapunov stability theory. We rigorously proved the uniform ultimate boundedness of the formation distance error and NN weights’ norm estimation error. Finally, using simulation results, we demonstrated the proposed method’s performance on the second-order, nonlinear multiagent systems. To provide further evaluation, we compared the proposed distance-based method and existing displacement-based methods.