Giter VIP home page Giter VIP logo

barriernet's Introduction

BarrierNet

A safety guaranteed neural network controller for autonomous systems

pipeline

There are three simple control demos (traffic merging, 2D and 3D robot control) and one vision-based end-to-end autonomous driving demo.

Setup

conda create -n bnet python=3.8
conda activate bnet
pip install torch==1.10.1+cu113 torchvision==0.11.2+cu113 -f https://download.pytorch.org/whl/cu113/torch_stable.html
pip install pytorch-lightning==1.5.8 opencv-python==4.5.2.54 matplotlib==3.5.1 ffio==0.1.0  descartes==1.1.0  pyrender==0.1.45  pandas==1.3.5 shapely==1.7.1 scikit-video==1.1.11 scipy==1.6.3 h5py==3.1.0
pip install qpth cvxpy cvxopt

Install vista.

conda activate bnet
cd vista
pip install -e .

Testing vision-based driving in VISTA

Download trained Barrier_Net: https://drive.google.com/file/d/1hyiUeyr1l9-239MT3YMxNDXvwgjj7ghF/view?usp=drive_link

Download trained state_net: https://drive.google.com/file/d/1YnWFuD7Xse_dgERC0gq3lEDDruYwiD_R/view?usp=drive_link

Download testing trace: https://drive.google.com/file/d/1z3BN9DbDDc0o1qir7VF64Rf5t-4F6czW/view?usp=drive_link

Download carpack01 (for VISTA): https://drive.google.com/file/d/13ENk6GEKGUfIkVc4Na0CiWlUCMJRqew5/view?usp=drive_link

bash scripts/eval_example.sh --trace-paths ./fakepath/20220113-131922_lexus_devens_outerloop_reverse --ckpt ./fakepath/version_5/checkpoints/epoch\=9-step\=29239.ckpt --state-net-ckpt ./fakepath/version_1/checkpoints/epoch=7-step=36374.ckpt --mesh-dir ./fakepath/carpack01/

Reference

If you find this useful, please cite our work:

@article{xiao2023bnet,
        title={BarrierNet: Differentiable Control Barrier Functions for Learning of Safe Robot Control},
        author={Wei Xiao and Tsun-Hsuan Wang and Ramin Hasani and Makram Chahine and Alexander Amini and Xiao Li and Daniela Rus},
        journal={IEEE Transactions on Robotics},
        year={2023},
        publisher={IEEE}
    }

barriernet's People

Contributors

weixy21 avatar zswang666 avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar

barriernet's Issues

No module named 'eval_tools'

While trying to run the example provided, I am getting error at file eval.py in Line 10 "from eval_tools import utils" which says
ModuleNotFoundError: No module named 'eval_tools'

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.