Diffusion-Based Failure Sampling for Cyber-Physical Systems

Validating safety-critical autonomous systems in high-dimensional domains such as robotics presents a significant challenge. Existing black-box approaches based on Markov chain Monte Carlo may require an enormous number of samples, while methods based on importance sampling often rely on simple para...

Full description

Saved in:
Bibliographic Details
Main Authors Delecki, Harrison, Schlichting, Marc R, Arief, Mansur, Corso, Anthony, Vazquez-Chanlatte, Marcell, Kochenderfer, Mykel J
Format Journal Article
LanguageEnglish
Published 20.06.2024
Subjects
Computer Science - Artificial Intelligence
Computer Science - Robotics
Computer Science - Systems and Control
Online AccessGet full text

Cover

More Information
Summary:Validating safety-critical autonomous systems in high-dimensional domains such as robotics presents a significant challenge. Existing black-box approaches based on Markov chain Monte Carlo may require an enormous number of samples, while methods based on importance sampling often rely on simple parametric families that may struggle to represent the distribution over failures. We propose to sample the distribution over failures using a conditional denoising diffusion model, which has shown success in complex high-dimensional problems such as robotic task planning. We iteratively train a diffusion model to produce state trajectories closer to failure. We demonstrate the effectiveness of our approach on high-dimensional robotic validation tasks, improving sample efficiency and mode coverage compared to existing black-box techniques.
DOI:10.48550/arxiv.2406.14761