Deep Neuro-Adaptive Sliding Mode Controller for Higher-Order Heterogeneous Nonlinear Multi-Agent Teams with Leader

TL;DR

This paper introduces a deep neural network-based neuro-adaptive sliding mode control strategy for leader-follower tracking in complex multi-agent systems with unknown nonlinear dynamics, ensuring robustness and improved accuracy.

Contribution

It presents a novel DNN-based control framework with set-theoretic robustness guarantees for higher-order heterogeneous multi-agent systems.

Findings

Demonstrates effective tracking in simulations

Shows robustness against disturbances and model uncertainties

Achieves higher accuracy than shallow neural networks

Abstract

This letter proposes a deep neural network (DNN)-based neuro-adaptive sliding mode control (SMC) strategy for leader-follower tracking in multi-agent systems with higher-order, heterogeneous, nonlinear, and unknown dynamics under external disturbances. The DNN is used to compensate the unknown nonlinear dynamics with higher accuracy than shallow neural networks (NNs) and SMC ensures robust tracking. This framework employs restricted potential functions within a set-theoretic paradigm to ensure system trajectories remain bounded within a compact set, improving robustness against approximation errors and external disturbances. The control scheme is grounded in non-smooth Lyapunov stability theory, with update laws derived for both inner and outer layer network weights of DNN. A numerical example is simulated that showcases the proposed controller's effectiveness, adaptability, and robustness.