This article presents a novel learning-based collaborative control framework to ensure communication security and formation safety of nonlinear multiagent systems (MASs) subject to denial-of-service (DoS) attacks, model uncertainties, and barriers in environments. The framework has a distributed and decoupled design at the cyber-layer and the physical layer. A resilient control Lyapunov function-quadratic programming (RCLF-QP)-based observer is first proposed to achieve secure reference state estimation under DoS attacks at the cyber-layer. Based on deep reinforcement learning (RL) and control barrier function (CBF), a safety-critical formation controller is designed at the physical layer to ensure safe collaborations between uncertain agents in dynamic environments. The framework is applied to autonomous vehicles for area scanning formations with barriers in environments. The comparative experimental results demonstrate that the proposed framework can effectively improve the resilience and robustness of the system.

This article presents a novel event and learning-based resilient formation control strategy for heterogeneous multiagent systems subjected to denial-of-service (DoS) attacks and uncertainties. It involves a decoupled cyber-layer and physical system layer design that enables a distributed and model-free approach. In the cyber-layer, the design is an event-triggered resilient observer for a reference exosystem estimation under DoS attacks using dual adaptive laws and an optimal algorithm. This approach eliminates the need for global information of the communication topology and enhances system resilience under attacks. In the physical system layer, the design is a model-free formation output controller for heterogeneous agents based on off-policy reinforcement learning. The incorporation of a new rank condition improves the convergence performance. Experiments using unmanned ground vehicles are conducted for scanning a physical area to verify the effectiveness and resilience of the proposed control strategy.

In this article, we design an adaptive leader–follower consensus controller for a class of nonlinear multiagent systems in the presence of time-varying asymmetric output constraints and unknown control directions. A new state transformation approach is introduced for each agent to transform the output into an equivalent unconstrained state. An adaptive neural network-based backstepping control method and a Nussbaum function approach are integrated to design the leader–follower consensus controller that compensates for the unknown control directions and guarantees that the consensus tracking error converges to a small compact set. Examples are given to demonstrate the effectiveness of the proposed new design techniques.