Robust Tracking Control with Neural Network Dynamic Models under Input Perturbations

Autor:	Cheng, Huixuan, Hu, Hanjiang, Liu, Changliu
Rok vydání:	2024
Předmět:	Electrical Engineering and Systems Science - Systems and Control
Druh dokumentu:	Working Paper
Popis:	Robust control problem has significant practical implication since external disturbances can significantly impact the performance of control method. Existing robust control method excels at control-affine system but fails at neural network dynamic models. Developing robust control methods for such systems remains a complex challenge. In this paper, we focus on robust tracking method for neural network dynamic models. We first propose reachability analysis tool designed for this system and then introduce how to reformulate robust tracking problem with the reachable sets. In addition, we prove the existence of feedback policy that bounds the growth of reachable set over infinite horizon. The effectiveness of proposed approach is validated through numerical tracking task simulations, where we compare it with a standard tube MPC method. Comment: 8 pages, 8 figures, conference
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2410.10387 Zobrazit plný text záznamu View this record from Arxiv