CARLA: An Open Urban Driving Simulator

TL;DR

CARLA is an open-source urban driving simulator designed to support autonomous driving research, enabling development, training, validation, and comparison of different autonomous driving approaches in diverse simulated environments.

Contribution

It introduces a versatile, open-source simulation platform with customizable environments and sensor configurations, facilitating comprehensive autonomous driving research and evaluation.

Findings

Compared three autonomous driving approaches in controlled scenarios

Demonstrated CARLA's effectiveness for performance evaluation

Provided metrics for assessing autonomous driving systems

Abstract

We introduce CARLA, an open-source simulator for autonomous driving research. CARLA has been developed from the ground up to support development, training, and validation of autonomous urban driving systems. In addition to open-source code and protocols, CARLA provides open digital assets (urban layouts, buildings, vehicles) that were created for this purpose and can be used freely. The simulation platform supports flexible specification of sensor suites and environmental conditions. We use CARLA to study the performance of three approaches to autonomous driving: a classic modular pipeline, an end-to-end model trained via imitation learning, and an end-to-end model trained via reinforcement learning. The approaches are evaluated in controlled scenarios of increasing difficulty, and their performance is examined via metrics provided by CARLA, illustrating the platform's utility for autonomous driving research. The supplementary video can be viewed at https://youtu.be/Hp8Dz-Zek2E