An OpenAI gym wrapper for CARLA simulator
Setup conda environment
$ conda create -n env_name python=3.6 $ conda activate env_name
Clone this git repo in an appropriate folder
$ git clone https://github.com/cjy1992/gym-carla.git
Enter the repo root folder and install the packages:
$ pip install -r requirements.txt $ pip install -e .
Download CARLA_0.9.6, extract it to some folder, and add CARLA to
$ export PYTHONPATH=$PYTHONPATH:$YourFolder$/CARLA_0.9.6/PythonAPI/carla/dist/carla-0.9.6-py3.5-linux-x86_64.egg
$ ./CarlaUE4.sh -windowed -carla-port=2000You can use
Alt+F1to get back your mouse control.
Or you can run in non-display mode by:
$ DISPLAY= ./CarlaUE4.sh -opengl -carla-port=2000
$ python test.pySee details of
test.pyabout how to use the CARLA gym wrapper.
We provide a dictionary observation including front view camera (obs['camera']), birdeye view lidar point cloud (obs['lidar']) and birdeye view semantic representation (obs['birdeye']):
The termination condition is either the ego vehicle collides, runs out of lane, reaches a destination, or reaches the maximum episode timesteps. Users may modify function terminal in carlaenv.py to enable customized termination condition.
The reward is a weighted combination of longitudinal speed and penalties for collision, exceeding maximum speed, out of lane, large steering and large lateral accleration. Users may modify function getreward in carla_env.py to enable customized reward function.