拡散モデルによる安全クリティカル自律システム評価のための故障サンプリング
Diffusion-Based Failure Sampling for Evaluating Safety-Critical Autonomous Systems
条件付き拡散モデルを反復学習し、高次元ロボティクスにおける故障軌道を効率的にサンプリングする手法を提案。既存のブラックボックス手法より少ないサンプルで多様な故障モードを網羅できることを示した。
著者: Harrison Delecki, Marc R. Schlichting, Mansur Arief, Anthony Corso, Marcell Vazquez-Chanlatte, Mykel J. Kochenderfer
分類: cs.RO, cs.AI, cs.SY, eess.SY
原文アブストラクト
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.
