3CSim: CARLA Corner Case Simulation for Control Assessment in Autonomous Driving

TL;DR

3CSim is a simulation framework in CARLA designed to evaluate autonomous driving systems against rare, challenging scenarios to improve safety and control robustness.

Contribution

It introduces a taxonomy and customizable set of corner cases for systematic testing of autonomous vehicle control in simulation.

Findings

Implemented 32 unique corner cases with adjustable parameters

Facilitates repeatable and comprehensive scenario evaluation

Enhances safety testing for autonomous driving systems

Abstract

We present the CARLA corner case simulation (3CSim) for evaluating autonomous driving (AD) systems within the CARLA simulator. This framework is designed to address the limitations of traditional AD model training by focusing on non-standard, rare, and cognitively challenging scenarios. These corner cases are crucial for ensuring vehicle safety and reliability, as they test advanced control capabilities under unusual conditions. Our approach introduces a taxonomy of corner cases categorized into state anomalies, behavior anomalies, and evidence-based anomalies. We implement 32 unique corner cases with adjustable parameters, including 9 predefined weather conditions, timing, and traffic density. The framework enables repeatable and modifiable scenario evaluations, facilitating the creation of a comprehensive dataset for further analysis.