Overview | Installation | Baselines | Paper
PyPI Python Version PyPI version arXiv GitHub license
OATomobile is a library for autonomous driving research. OATomobile strives to expose simple, efficient, well-tuned and readable agents, that serve both as reference implementations of popular algorithms and as strong baselines, while still providing enough flexibility to do novel research.
If you just want to get started using OATomobile quickly, the first thing to know about the framework is that we wrap CARLA towns and scenarios in OpenAI gyms:
import oatomobile # Initializes a CARLA environment. environment = oatomobile.envs.CARLAEnv(town="Town01") # Makes an initial observation. observation = environment.reset() done = False while not done: # Selects a random action. action = environment.action_space.sample() observation, reward, done, info = environment.step(action) # Renders interactive display. environment.render(mode="human") # Book-keeping: closes environment.close()
Baselines can also be used out-of-the-box:
# Rule-based agents. import oatomobile.baselines.rulebased agent = oatomobile.baselines.rulebased.AutopilotAgent(environment) action = agent.act(observation) # Imitation-learners. import torch import oatomobile.baselines.torch models = [oatomobile.baselines.torch.ImitativeModel() for _ in range(4)] ckpts = ... # Paths to the model checkpoints. for model, ckpt in zip(models, ckpts): model.load_state_dict(torch.load(ckpt)) agent = oatomobile.baselines.torch.RIPAgent( environment=environment, models=models, algorithm="WCM", ) action = agent.act(observation)
We have tested OATomobile on Python 3.5.
-
To install the core libraries (including CARLA, the backend simulator):
# The path to download CARLA 0.9.6. export CARLA_ROOT=... mkdir -p $CARLA_ROOT # Downloads hosted binaries. wget http://carla-assets-internal.s3.amazonaws.com/Releases/Linux/CARLA_0.9.6.tar.gz # CARLA 0.9.6 installation. tar -xvzf CARLA_0.9.6.tar.gz -C $CARLA_ROOT # Installs CARLA 0.9.6 Python API. easy_install $CARLA_ROOT/PythonAPI/carla/dist/carla-0.9.6-py3.5-linux-x86_64.egg
-
To install the OATomobile core API:
pip install --upgrade pip setuptools pip install oatomobile
-
To install dependencies for our PyTorch- or TensorFlow-based agents:
pip install oatomobile[torch] # and/or pip install oatomobile[tf]
If you use OATomobile in your work, please cite the accompanying technical report:
@inproceedings{filos2020can, title={Can Autonomous Vehicles Identify, Recover From, and Adapt to Distribution Shifts?}, author={Filos, Angelos and Tigas, Panagiotis and McAllister, Rowan and Rhinehart, Nicholas and Levine, Sergey and Gal, Yarin}, booktitle={International Conference on Machine Learning (ICML)}, year={2020} }