Observer-based distributed adaptive neural network containment control for uncertain nonlinear multi-agent systems under DoS attacks

This paper addresses the containment control issue in high-order nonlinear multi-agent systems (MASs) under denial of service (DoS) attacks. First, a neural network-based switching observer with adaptive mechanism is developed to reconstruct unmeasurable agent states under intermittent DoS-induced communication disruptions, establishing new theoretical pathways for directed network topologies. Second, a command-filtered backstepping control framework is proposed to circumvent the inherent complexity explosion in traditional recursive designs by eliminating redundant differentiations of virtual control laws. Ultimately, a distributed adaptive neural network containment control (DANNCC) scheme is established, ensuring all follower agents asymptotically converge into the convex hull spanned by multiple leaders. Furthermore, systematic stability analysis with constructed Lyapunov functions yields boundedness of all closed-loop signals in the system. Moreover, the containment errors can be asymptotically driven to an arbitrarily small magnitude through systematic parameter adjustment. The developed approach’s operational efficacy and real-world applicability are validated through comprehensive simulations across heterogeneous attack scenarios, demonstrating strict adherence to convergence requirements without control performance degradation.