A3C-Based Intelligent Event-Triggering Control of Networked Nonlinear Unmanned Marine Vehicles Subject to Hybrid Attacks

This paper is concerned with the intelligent event-triggering-based positioning control of networked unmanned marine vehicle (UMV) systems with hybrid attacks, where the UMV and control station is connected by a communication network and the DoS attack and Deception attack are studied. Firstly, a stochastic switched Takagi-Sugeno (T-S) fuzzy system model is proposed for the networked nonlinear UMV systems subject to aperiodic DoS attack and random Deception attack. Then, a novel asynchronous advantage actor-critic (A3C) learning-based event-triggering approach is introduced to alleviate the communication load. By using the Lyapunov stability theory and switched system analysis method, the mean-square exponential stability condition of the closed-loop system and the design method of observer-based controller are devised. Finally, an example of a networked UMV system is given to verify the effectiveness of the proposed resilient control strategy.

Automated summary

This paper focuses on the intelligent event-triggering-based positioning control of networked unmanned marine vehicle (UMV) systems with hybrid attacks. A stochastic switched Takagi-Sugeno (T-S) fuzzy system model is proposed for the UMV systems subject to DoS and Deception attacks, and an asynchronous advantage actor-critic (A3C) learning-based event-triggering approach is introduced to reduce communication load. The stability of the closed-loop system is analyzed using Lyapunov stability theory and switched system analysis, and the effectiveness of the proposed resilient control strategy is verified through a networked UMV system example.