TY  - CONF
AU  - Alexey Dosovitskiy
AU  - German Ros
AU  - Felipe Codevilla
AU  - Antonio Lopez
AU  - Vladlen Koltun
A2  - CORL
PY  - 2017//
TI  - CARLA: An Open Urban Driving Simulator
BT  - 1st Annual Conference on Robot Learning. Proceedings of Machine Learning
SP  - 1
EP  - 16
VL  - 78
KW  - Autonomous driving
KW  - sensorimotor control
KW  - simulation
N2  - 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 endto-endmodel trained via imitation learning, and an end-to-end model trained viareinforcement learning. The approaches are evaluated in controlled scenarios ofincreasing difficulty, and their performance is examined via metrics provided by CARLA, illustrating the platform’s utility for autonomous driving research.
L1  - http://refbase.cvc.uab.es/files/DRC2017.pdf
N1  - ADAS; 600.085; 600.118
ID  - Alexey Dosovitskiy2017
ER  -