Work

Reinforcement-Learning-Based Fixed-Time Prescribed Performance Consensus Control for Stochastic Nonlinear MASs with Sensor Faults

Year: 2024

Type: article

Abstract: This paper proposes the fixed-time prescribed performance optimal consensus control method for stochastic nonlinear multi-agent systems with sensor faults. The consensus error converges to the prescribed performance bounds in fixed-time by an improved performance function and coordinate transformation. Due to the unknown faults in sensors, the system states cannot be gained correctly; therefore, an adaptive compensation strategy is constructed based on the approximation capabilities of neural networks to solve the negative impact of sensor failures. The reinforcement-learning-based backstepping method is proposed to realize the optimal control of the system. Utilizing Lyapunov stability theory, it is shown that the designed controller enables the consensus error to converge to the prescribed performance bounds in fixed time and that all signals in the closed-loop system are bounded in probability. Finally, the simulation results prove the effectiveness of the proposed method.

Source: Sensors

DOI: 10.3390/s24247906

Authors: Zhenyou Wang, Xiaoquan Cai, Ao Luo, Hui Ma, Shengbing Xu

Institution: Guangdong University of Technology

Language: English

Topic: Distributed Control Multi-Agent Systems

Subfield: Computer Networks and Communications

Field: Computer Science

Domain: Physical Sciences

Open Access status: gold

Estimated APC paid: $2,955

Funders: National Natural Science Foundation of China, Natural Science Foundation of Guangdong Province