SAVME: メタ学習を用いた自律システムの効率的な安全性検証
SAVME: Efficient Safety Validation for Autonomous Systems Using Meta-Learning
メタ学習とマルチアームドバンディットを組み合わせ、自律システムの故障シナリオを効率的に探索し、シミュレーションの忠実度を適応的に選ぶことで検証を最大18倍高速化した。
著者: Marc R. Schlichting, Nina V. Boord, Anthony L. Corso, Mykel J. Kochenderfer
分類: cs.RO, cs.AI, cs.CY, cs.ET, cs.SY, eess.SY
原文アブストラクト
Discovering potential failures of an autonomous system is important prior to deployment. Falsification-based methods are often used to assess the safety of such systems, but the cost of running many accurate simulation can be high. The validation can be accelerated by identifying critical failure scenarios for the system under test and by reducing the simulation runtime. We propose a Bayesian approach that integrates meta-learning strategies with a multi-armed bandit framework. Our method involves learning distributions over scenario parameters that are prone to triggering failures in the system under test, as well as a distribution over fidelity settings that enable fast and accurate simulations. In the spirit of meta-learning, we also assess whether the learned fidelity settings distribution facilitates faster learning of the scenario parameter distributions for new scenarios. We showcase our methodology using a cutting-edge 3D driving simulator, incorporating 16 fidelity settings for an autonomous vehicle stack that includes camera and lidar sensors. We evaluate various scenarios based on an autonomous vehicle pre-crash typology. As a result, our approach achieves a significant speedup, up to 18 times faster compared to traditional methods that solely rely on a high-fidelity simulator.
