Manifold-Guided Lyapunov Control with Diffusion Models

Autor:	Mukherjee, Amartya, Quartz, Thanin, Liu, Jun
Rok vydání:	2024
Předmět:	Computer Science - Computer Vision and Pattern Recognition Computer Science - Machine Learning Mathematics - Differential Geometry Mathematics - Optimization and Control Statistics - Computation
Druh dokumentu:	Working Paper
Popis:	This paper presents a novel approach to generating stabilizing controllers for a large class of dynamical systems using diffusion models. The core objective is to develop stabilizing control functions by identifying the closest asymptotically stable vector field relative to a predetermined manifold and adjusting the control function based on this finding. To achieve this, we employ a diffusion model trained on pairs consisting of asymptotically stable vector fields and their corresponding Lyapunov functions. Our numerical results demonstrate that this pre-trained model can achieve stabilization over previously unseen systems efficiently and rapidly, showcasing the potential of our approach in fast zero-shot control and generalizability. Comment: 14 pages
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2403.17692 Zobrazit plný text záznamu View this record from Arxiv