gym-collision-avoidance - GitLite

KO | EN

gitlite — search

#javascript #ai #typescript #golang #android #machine-learning #rust #deep-learning #docker #macos #java #windows #mcp #open-source

gym-collision-avoidance

(★ 323)

No description available.

File Explorer

Download Latest Version (.zip)

- - 000_CADRL_2agents.png
  - 000_GA3C-CADRL-10_2agents.png
  - 000_RVO_2agents.png
  - a3c_20_agents.gif
  - collision_avoidance_figs.pdf
  - combo.gif
  - example.gif
  - formation_A.gif
  - formation_C.gif
  - gym_arch.png
  - jackal_iros18.gif
  - random_2_agents.gif
- - agent.rst
  - architecture.rst
  - build_docs.rst
  - build_pypi.rst
  - config.rst
  - dynamics.rst
  - env.rst
  - example.rst
  - install.rst
  - policies.rst
  - sensors.rst
  - train_multiagent_rl.rst
  - use_cases.rst
- conf.py
- index.rst
- Makefile
- - __init__.py
  - agent.py
  - collision_avoidance_env.py
  - config.py
  - Map.py
  - test_cases.py
  - util.py
  - vec_env.py
  - visualize.py
  - wrappers.py
- - __init__.py
  - collect_regression_dataset.sh
  - run_cadrl_formations.sh
  - run_full_test_suite.sh
  - run_trajectory_dataset_creator.sh
  - utils.sh
- - test_collision_avoidance.py
- __init__.py
.gitignore
.gitlab-ci.yml
.gitmodules
.readthedocs.yml
example.sh
install.sh
LICENSE
README.md
setup.py

# Installation Guide

1. Get the code

git clone https://github.com/mit-acl/gym-collision-avoidance

Downloads the entire project code from GitHub to your computer.

cd gym-collision-avoidance

Moves into the project folder you just downloaded.

2. Python

Easy Recommended

Prerequisites

Git Needed to download the project code from GitHub.
Python 3 On Windows, be sure to check 'Add Python to PATH' during installation.

pip install .

Installs the package published on PyPI directly — no need to clone the source.

python <실행할 파일명>.py # README에서 정확한 실행 파일명을 확인하세요

Runs the Python script (or module).

✅ If it runs without errors and prints output in the terminal, it worked.

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# gym-collision-avoidance

Updates:
- **2023-04-28:** Updated to be compatible with Python 3.10 and tensorflow 2. Corresponding v0.0.3 available on pypi as well, if you do not intend to modify the source code (`python -m pip install gym-collision-avoidance`)

<img src="docs/_static/combo.gif" alt="Agents spelling ``CADRL''">

This is the code associated with the following publications:

**Journal Version:** M. Everett, Y. Chen, and J. P. How, "Collision Avoidance in Pedestrian-Rich Environments with Deep Reinforcement Learning", IEEE Access Vol. 9, 2021, pp. 10357-10377. [10.1109/ACCESS.2021.3050338](http://doi.org/10.1109/ACCESS.2021.3050338), [Arxiv PDF](https://arxiv.org/abs/1910.11689)

**Conference Version:** M. Everett, Y. Chen, and J. P. How, "Motion Planning Among Dynamic, Decision-Making Agents with Deep Reinforcement Learning", IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2018. [Arxiv PDF](https://arxiv.org/abs/1805.01956), [Link to Video](https://www.youtube.com/watch?v=XHoXkWLhwYQ)

This repo also contains the trained policy for the SA-CADRL paper (referred to as CADRL here) from the proceeding paper: Y. Chen, M. Everett, M. Liu, and J. P. How. “Socially Aware Motion Planning with Deep Reinforcement Learning.” IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). Vancouver, BC, Canada, Sept. 2017. [Arxiv PDF](https://arxiv.org/abs/1703.08862)

If you're looking to train our GA3C-CADRL policy, please see [this repo](https://github.com/mit-acl/rl_collision_avoidance) instead.

---

### About the Code

Please see [the documentation](https://gym-collision-avoidance.readthedocs.io/en/latest/)!

### If you find this code useful, please consider citing:

```
@inproceedings{Everett18_IROS,
  address = {Madrid, Spain},
  author = {Everett, Michael and Chen, Yu Fan and How, Jonathan P.},
  booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
  date-modified = {2018-10-03 06:18:08 -0400},
  month = sep,
  title = {Motion Planning Among Dynamic, Decision-Making Agents with Deep Reinforcement Learning},
  year = {2018},
  url = {https://arxiv.org/pdf/1805.01956.pdf},
  bdsk-url-1 = {https://arxiv.org/pdf/1805.01956.pdf}
}
```

or

```
@article{everett2021collision,
  title={Collision avoidance in pedestrian-rich environments with deep reinforcement learning},
  author={Everett, Michael and Chen, Yu Fan and How, Jonathan P},
  journal={IEEE Access},
  volume={9},
  pages={10357--10377},
  year={2021},
  publisher={IEEE}
}
```