This is the authors' abstract. We don't add key points for this paper.
This paper focuses on the problem of formation control (FC) for unknown nonlinear iterative multi-agent systems (IMASs) with input saturation constraints. To ensure both boundedness and convergence of the formation error while conserving computational resources, a neural network (NN)-based distributed event-triggered iterative learning control (NN-DETILC) method is proposed. To construct the iterative linear model of each agent, an enhanced pseudo Jacobi matrix (PJM) estimation algorithm is designed, which fully utilizes the advantages of generalized regression NNs (GRNNs) and incorporates an estimation error compensation mechanism. On this basis, the FC problem with input saturation constraints is reformulated as a quadratic programming (QP) problem related to the control inputs, and a memristive programming NN (MPNN)-based anti-saturation control input (MPNN-ACI) solving algorithm is further introduced. Additionally, a distributed event-triggered (DET) communication protocol is proposed to schedule agents orderly while saving computational resources. Furthermore, sufficient conditions for the boundedness and convergence of formation errors are established, and the effectiveness of the method is validated through two simulation examples.
Answers are grounded in this paper and cite their sources.
No takes yet. Share an insight, caveat, or question.
Shi et al. (2025) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: