GOOSE: Goal-Conditioned Reinforcement Learning for Safety-Critical Scenario Generation

TL;DR

GOOSE employs goal-conditioned reinforcement learning to automatically generate safety-critical driving scenarios, enhancing the testing of ADAS and ADS systems by creating challenging situations for safety validation.

Contribution

This paper introduces GOOSE, a novel RL-based method that controls vehicle trajectories at the scenario level using goal-conditioning and NURBS modeling for efficient safety-critical scenario generation.

Findings

Successfully generates safety-critical scenarios for ADAS/ADS testing

Demonstrates effectiveness on pre-crash scenarios from UN Regulation No. 157

Enhances scenario diversity and challenge level in safety validation

Abstract

Scenario-based testing is considered state-of-the-art for verifying and validating Advanced Driver Assistance Systems (ADASs) and Automated Driving Systems (ADSs). However, the practical application of scenario-based testing requires an efficient method to generate or collect the scenarios that are needed for the safety assessment. In this paper, we propose Goal-conditioned Scenario Generation (GOOSE), a goal-conditioned reinforcement learning (RL) approach that automatically generates safety-critical scenarios to challenge ADASs or ADSs. In order to simultaneously set up and optimize scenarios, we propose to control vehicle trajectories at the scenario level. Each step in the RL framework corresponds to a scenario simulation. We use Non-Uniform Rational B-Splines (NURBS) for trajectory modeling. To guide the goal-conditioned agent, we formulate test-specific, constraint-based goals inspired by the OpenScenario Domain Specific Language(DSL). Through experiments conducted on multiple pre-crash scenarios derived from UN Regulation No. 157 for Active Lane Keeping Systems (ALKS), we demonstrate the effectiveness of GOOSE in generating scenarios that lead to safety-critical events.