Neural Network-Based Adaptive Leader-Following Consensus Control for a Class of Nonlinear Multiagent State-Delay Systems
提出一种基于神经网络的自适应一致性控制方法，通过在线更新少量参数降低计算负担，并补偿状态时滞，使多智能体系统同步到参考信号。
Compared with the existing neural network (NN) or fuzzy logic system (FLS) based adaptive consensus methods, the proposed approach can greatly alleviate the computation burden because it needs only to update a few adaptive parameters online. In the multiagent agreement control, the system uncertainties derive from the unknown nonlinear dynamics are counteracted by employing the adaptive NNs; the state delays are compensated by designing a Lyapunov-Krasovskii functional. Finally, based on Lyapunov stability theory, it is demonstrated that the proposed consensus scheme can steer a multiagent system synchronizing to the predefined reference signals. Two simulation examples, a numerical multiagent system and a practical multimanipulator system, are carried out to further verify and testify the effectiveness of the proposed agreement approach.