SAVME: Efficient Safety Validation for Autonomous Systems Using Meta-Learning

TL;DR

This paper introduces SAVME, a meta-learning based Bayesian approach that accelerates safety validation of autonomous systems by efficiently identifying failure scenarios and optimizing simulation fidelity, achieving up to 18x speedup.

Contribution

The paper presents a novel meta-learning Bayesian framework integrating multi-armed bandits for faster failure scenario discovery in autonomous system validation.

Findings

Achieves up to 18 times faster validation compared to traditional methods.

Effectively learns scenario parameters and fidelity settings for autonomous vehicle safety.

Demonstrates applicability using a 3D driving simulator with multiple fidelity levels.

Abstract

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.