AdvSim: Generating Safety-Critical Scenarios for Self-Driving Vehicles

Abstract

As self-driving systems become better, simulating scenarios where the autonomy stack may fail becomes more important. Traditionally, those scenarios are generated for a few scenes with respect to the planning module that takes ground-truth actor states as input. This does not scale and cannot identify all possible autonomy failures, such as perception failures due to occlusion. In this paper, we propose AdvSim, an adversarial framework to generate safety-critical scenarios for any LiDAR-based autonomy system. Given an initial traffic scenario, AdvSim modifies the actors' trajectories in a physically plausible manner and updates the LiDAR sensor data to match the perturbed world. Importantly, by simulating directly from sensor data, we obtain adversarial scenarios that are safety-critical for the full autonomy stack. Our experiments show that our approach is general and can identify thousands of semantically meaningful safety-critical scenarios for a wide range of modern self-driving systems. Furthermore, we show that the robustness and safety of these systems can be further improved by training them with scenarios generated by AdvSim.

arXiv commentCVPR 2021. Corrected typos in the adversarial objective

References in corpus (12)

• End to End Learning for Self-Driving Cars
• Fast and Furious: Real Time End-to-End 3D Detection, Tracking and Motion Forecasting with a Single Convolutional Net
• IntentNet: Learning to Predict Intention from Raw Sensor Data
• Prior Convictions: Black-Box Adversarial Attacks with Bandits and Priors
• Driving Policy Transfer via Modularity and Abstraction
• Simple Black-box Adversarial Attacks
• Towards Robust LiDAR-based Perception in Autonomous Driving: General Black-box Adversarial Sensor Attack and Countermeasures
• Adversarial Objects Against LiDAR-Based Autonomous Driving Systems
• Efficient Black-box Assessment of Autonomous Vehicle Safety
• Adversarial Evaluation of Autonomous Vehicles in Lane-Change Scenarios
• Learning to Collide: An Adaptive Safety-Critical Scenarios Generating Method
• A Software Architecture for Autonomous Vehicles: Team LRM-B Entry in the First CARLA Autonomous Driving Challenge

Cited by in corpus (2)

• A Survey on Scenario-Based Testing for Automated Driving Systems in High-Fidelity Simulation
• Neural Network Guided Evolutionary Fuzzing for Finding Traffic Violations of Autonomous Vehicles