Structured Deep Neural Networks-Based Backstepping Trajectory Tracking Control for Lagrangian Systems

arXiv:2403.00381v1 Announce Type: cross
Abstract: Deep neural networks (DNN) are increasingly being used to learn controllers due to their excellent approximation capabilities. However, their black-box nature poses significant challenges to closed-loop stability guarantees and performance analysis. In this paper, we introduce a structured DNN-based controller for the trajectory tracking control of Lagrangian systems using backing techniques. By properly designing neural network structures, the proposed controller can ensure closed-loop stability for any compatible neural network parameters. In addition, improved control performance …

abstract analysis approximation arxiv box capabilities challenges control cs.lg cs.ro cs.sy dnn eess.sy learn loop nature networks neural networks paper performance performance analysis stability systems tracking trajectory type