CARLA: An Open Urban Driving Simulator

TLDR

CARLA is an open‑source simulator for autonomous driving research, used to evaluate modular pipelines and end‑to‑end models trained via imitation and reinforcement learning. It offers open‑source code, digital assets, configurable sensor suites and environmental conditions, and built‑in metrics for assessing autonomous driving systems. CARLA supports development, training, and validation of autonomous urban driving systems, and its metrics demonstrate its utility by evaluating approaches across increasing scenario difficulty. Supplementary video available at the provided URL.

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 this https URL