Go to file
felipecode 78187b83d0 log not lazy fix 2018-01-22 10:53:08 +01:00
Docs Update benchmark.md 2018-01-17 15:37:38 +01:00
PythonClient log not lazy fix 2018-01-22 10:53:08 +01:00
Unreal/CarlaUE4 Fix warning and make Cppcheck quiet again 2018-01-09 16:23:50 +01:00
Util Update coding standard 2018-01-10 13:29:52 +01:00
.gitattributes Remove git lfs 2017-07-25 17:07:35 +02:00
.gitignore Some improvements to setup.py 2017-12-22 19:14:16 +01:00
.travis.yml Fix warning and make Cppcheck quiet again 2018-01-09 16:23:50 +01:00
CARLA.sublime-project Fix client tests 2017-11-20 19:42:24 +01:00
CHANGELOG.md Release file change to add info about the map 2017-11-28 15:42:06 +01:00
Doxyfile Remove python from Doxyfile 2017-11-09 15:37:21 +01:00
LICENSE Add MIT license 2017-07-28 18:42:59 +02:00
Makefile #32 Remove what is left of TestingClient 2017-11-18 17:58:54 +01:00
README.md Benchmarking added to main README 2018-01-17 15:28:47 +01:00
Rebuild.bat Adapt Linux build system 2017-10-25 17:26:31 +02:00
Rebuild.sh Adapt Linux build system 2017-10-25 17:26:31 +02:00
Setup.sh Update script 2017-11-27 13:15:49 +01:00
Update.sh Update script 2017-11-27 13:15:49 +01:00
mkdocs.yml Add benchmark to documentation 2017-12-22 18:38:10 +01:00

README.md

CARLA Simulator

CARLA is 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.

CARLA Video

Get the latest release here.

For instructions on how to use and compile CARLA, check out CARLA Documentation.

If you want to benchmark your model in the same conditions as in our CoRL17 paper, check out Benchmarking.

News

Roadmap

We are continuously working on improving CARLA, and we appreciate contributions from the community. Our most immediate goals are:

  • Releasing the methods evaluated in the CARLA paper
  • Adding a LiDAR sensor
  • Allowing for flexible and user-friendly import and editing of maps
  • Allowing the users to control non-player characters (and therefore set up user-specified scenarios)

We will post a detailed roadmap and contribution guidelines soon - stay tuned!

Paper

If you use CARLA, please cite our CoRL17 paper.

CARLA: An Open Urban Driving Simulator
Alexey Dosovitskiy, German Ros, Felipe Codevilla, Antonio Lopez, Vladlen Koltun; PMLR 78:1-16 [PDF]

@inproceedings{Dosovitskiy17,
  title = {{CARLA}: {An} Open Urban Driving Simulator},
  author = {Alexey Dosovitskiy and German Ros and Felipe Codevilla and Antonio Lopez and Vladlen Koltun},
  booktitle = {Proceedings of the 1st Annual Conference on Robot Learning},
  pages = {1--16},
  year = {2017}
}

License

CARLA specific code is distributed under MIT License.

CARLA specific assets are distributed under CC-BY License.

Note that UE4 itself and the UE4 free automotive materials follow their own license terms.

CARLA uses free automotive materials from Epic Games. For compiling CARLA, these materials must be downloaded from the UE4 marketplace and manually linked in CARLA following the instructions provided in the documentation.

CARLA uses pedestrians created with Adobe Fuse, which is a free tool for that purpose. Currently, we cannot redistribute these pedestrians models. They can only be used in the provided executable.