Reproduction of Real-World Scenarios in CARLA: An Extension of CARLA Functionality George Mason University

Format:

Book

Conference/Event

Author/Creator:

Ai, Yan, author.

Contributor:

Adhikari, Bikram

Kan, Cing-Dao

Park, Chung-Kyu

Wijesekera, Duminda

Conference Name:

WCX SAE World Congress Experience (2025-04-08 : Detroit, Michigan, United States)

Language:

English

Physical Description:

1 online resource cm

Place of Publication:

Warrendale, PA SAE International 2025

Summary:

Reproducing driving scenarios involving near-collisions and collisions in a simulator can be useful in the development and testing of autonomous vehicles, as it provides a safe environment to explore detailed vehicular behavior during these critical events. CARLA, an open-source driving simulator, has been widely used for reproducing driving scenarios. CARLA allows for both manual control and traffic manager control (the module that controls vehicles in autopilot manner in the simulation). However, current versions of CARLA are limited to setting the start and destination points for vehicles that are controlled by traffic manager, and are unable to replay precise waypoint paths that are collected from real-world collision and near-collision scenarios, due to the fact that the collision-free pathfinding modules are built into the system. This paper presents an extension to CARLA's source code, enabling the replay of exact vehicle trajectories, irrespective of safety implications encountered during laid out scenarios. With this functionality, researchers can now simulate real-world scenarios with higher fidelity irrespective of the scenarios, so that the vehicular automation can avoid unsafe driving conditions and allow for root-cause analysis of near-collisions inherent in a given driving automation. It can bridge the gap between simulation and real-life testing and also support validation of autonomous driving system under controlled and repeatable conditions. The extension will improve CARLA's utility in autonomous vehicle research, particularly in areas such as safety validation and machine learning model training using safety margins produced by near-collision scenarios

Notes:

Vendor supplied data

Publisher Number:

2025-01-8059

Access Restriction:

Restricted for use by site license