Generating and Explaining Corner Cases Using Learnt Probabilistic Lane Graphs

TL;DR

This paper introduces Probabilistic Lane Graphs learned from traffic data to generate and explain realistic corner cases for autonomous vehicle safety testing, enhancing scenario coverage and interpretability.

Contribution

It presents a novel method using Probabilistic Lane Graphs and reinforcement learning to generate and explain safety-critical corner cases based on real traffic data.

Findings

Generated realistic corner cases for AV testing.

Provided explanations for safety-critical scenarios.

Improved coverage of traffic conditions in simulations.

Abstract

Validating the safety of Autonomous Vehicles (AVs) operating in open-ended, dynamic environments is challenging as vehicles will eventually encounter safety-critical situations for which there is not representative training data. By increasing the coverage of different road and traffic conditions and by including corner cases in simulation-based scenario testing, the safety of AVs can be improved. However, the creation of corner case scenarios including multiple agents is non-trivial. Our approach allows engineers to generate novel, realistic corner cases based on historic traffic data and to explain why situations were safety-critical. In this paper, we introduce Probabilistic Lane Graphs (PLGs) to describe a finite set of lane positions and directions in which vehicles might travel. The structure of PLGs is learnt directly from spatio-temporal traffic data. The graph model represents the actions of the drivers in response to a given state in the form of a probabilistic policy. We use reinforcement learning techniques to modify this policy and to generate realistic and explainable corner case scenarios which can be used for assessing the safety of AVs.