Corner Case Generation and Analysis for Safety Assessment of Autonomous Vehicles

Abstract

Testing and evaluation is a crucial step in the development and deployment of connected and automated vehicles (CAVs). To comprehensively evaluate the performance of CAVs, it is necessary to test the CAVs in safety-critical scenarios, which rarely happen in a naturalistic driving environment. Therefore, how to purposely and systematically generate these corner cases becomes an important problem. Most existing studies focus on generating adversarial examples for perception systems of CAVs, whereas limited efforts have been put into decision-making systems, which is the highlight of this paper. As the CAVs need to interact with numerous background vehicles (BVs) for a long duration, variables that define the corner cases are usually high-dimensional, which makes the generation a challenging problem. In this paper, a unified framework is proposed to generate corner cases for decision-making systems. To address the challenge brought by high dimensionality, the driving environment is formulated based on the Markov decision process, and the deep reinforcement learning techniques are applied to learn the behavior policy of BVs. With the learned policy, BVs behave and interact with the CAVs more aggressively, resulting in more corner cases. To further analyze the generated corner cases, the techniques of feature extraction and clustering are utilized. By selecting representative cases of each cluster and outliers, the valuable corner cases can be identified from all generated corner cases. Simulation results of a highway driving environment show that the proposed methods can effectively generate and identify the valuable corner cases.

A Survey on Model-based Reinforcement Learning

“…A single unrealistic simulator can also be used to facilitate policy training using some data collected in real-world task . Simulators are also useful for generating specific situations that are a rarity in real-world environments for learning robust policies [Zhou et al, 2021, Chou et al, 2018, Sun et al, 2021.…”

A-Eye: Driving with the Eyes of AI for Corner Case Generation

“…A decision-making corner case generation method for connected and automated vehicles (CAVs) for test and evaluation purposes is proposed in [18]. For this, the behavioral policy of background vehicles (BV) is learned through reinforcement learning and Markov's decision process, which leads to a more aggressive interaction with the CAV which forces more corner cases under test conditions.…”

Automatic Generation System for Autonomous Driving Simulation Scenarios Based on PreScan

“…Among them, the scenario combination test method [5][6][7] arranges and filters scenario elements, enabling the rapid generation of a multitude of scenarios. Some studies specifically focus on generating scenarios for automotive systems within simulated road environments [8,9], and some generate corner cases based on interactions with other vehicles [10,11]. While algorithmic modeling can produce numerous scenarios, the screening process, which relies on personal experience and judgment, necessitates significant effort to sift out useful scenarios from the large pool of possibilities.…”