Formally Verified Neural Lyapunov Function for Incremental Input-to-State Stability of Unknown Systems

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Basu, Ahan, Dey, Bhabani Shankar, Jagtap, Pushpak
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909453581811712
author Basu, Ahan
Dey, Bhabani Shankar
Jagtap, Pushpak
author_facet Basu, Ahan
Dey, Bhabani Shankar
Jagtap, Pushpak
contents This work presents an approach to synthesize a Lyapunov-like function to ensure incrementally input-to-state stability ($δ$-ISS) property for an unknown discrete-time system. To deal with challenges posed by unknown system dynamics, we parameterize the Lyapunov-like function as a neural network, which we train using the data samples collected from the unknown system along with appropriately designed loss functions. We propose a validity condition to test the obtained function and incorporate it into the training framework to ensure provable correctness at the end of the training. Finally, the usefulness of the proposed technique is proved using two case studies: a scalar non-linear dynamical system and a permanent magnet DC motor.
format Preprint
id arxiv_https___arxiv_org_abs_2501_05778
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Formally Verified Neural Lyapunov Function for Incremental Input-to-State Stability of Unknown Systems
Basu, Ahan
Dey, Bhabani Shankar
Jagtap, Pushpak
Systems and Control
This work presents an approach to synthesize a Lyapunov-like function to ensure incrementally input-to-state stability ($δ$-ISS) property for an unknown discrete-time system. To deal with challenges posed by unknown system dynamics, we parameterize the Lyapunov-like function as a neural network, which we train using the data samples collected from the unknown system along with appropriately designed loss functions. We propose a validity condition to test the obtained function and incorporate it into the training framework to ensure provable correctness at the end of the training. Finally, the usefulness of the proposed technique is proved using two case studies: a scalar non-linear dynamical system and a permanent magnet DC motor.
title Formally Verified Neural Lyapunov Function for Incremental Input-to-State Stability of Unknown Systems
topic Systems and Control
url https://arxiv.org/abs/2501.05778