SEAIROJul 20, 2023

Boundary State Generation for Testing and Improvement of Autonomous Driving Systems

arXiv:2307.10590v217 citationsh-index: 61
Originality Incremental advance
AI Analysis

This addresses the critical need for more effective testing and improvement of autonomous driving systems, representing an incremental advance in domain-specific testing methods.

The paper tackles the problem of assessing dependability in autonomous driving systems by introducing GENBO, a test generator that efficiently creates challenging driving conditions at the behavior boundary, and shows that retraining with these conditions improves the model's success rate by up to 3x on evaluation tracks.

Recent advances in Deep Neural Networks (DNNs) and sensor technologies are enabling autonomous driving systems (ADSs) with an ever-increasing level of autonomy. However, assessing their dependability remains a critical concern. State-of-the-art ADS testing approaches modify the controllable attributes of a simulated driving environment until the ADS misbehaves. In such approaches, environment instances in which the ADS is successful are discarded, despite the possibility that they could contain hidden driving conditions in which the ADS may misbehave. In this paper, we present GENBO (GENerator of BOundary state pairs), a novel test generator for ADS testing. GENBO mutates the driving conditions of the ego vehicle (position, velocity and orientation), collected in a failure-free environment instance, and efficiently generates challenging driving conditions at the behavior boundary (i.e., where the model starts to misbehave) in the same environment instance. We use such boundary conditions to augment the initial training dataset and retrain the DNN model under test. Our evaluation results show that the retrained model has, on average, up to 3x higher success rate on a separate set of evaluation tracks with respect to the original DNN model.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes