Skip to content

A PyTorch-based deep inverse reinforcement learning pipeline for vehicle motion forecasting

License

Notifications You must be signed in to change notification settings

UMich-CURLY/medirl

This branch is 10 commits ahead of yfzhang/vehicle-motion-forecasting:master.

Folders and files

NameName
Last commit message
Last commit date

Latest commit

Apr 16, 2024
66ce61a · Apr 16, 2024

History

35 Commits
Oct 16, 2018
Apr 16, 2024
Jan 24, 2024
Jan 24, 2024
Apr 16, 2024
Apr 16, 2024
Apr 16, 2024
Oct 19, 2018
Dec 17, 2018
Oct 16, 2018
Nov 22, 2018
Oct 19, 2018
Apr 16, 2024
Apr 16, 2024
Feb 2, 2024
Sep 29, 2018
Sep 29, 2018
Nov 13, 2023
Jan 7, 2024
Sep 29, 2018
Jan 24, 2024
Feb 2, 2024
Feb 2, 2024
Sep 29, 2018
Jan 24, 2024
Apr 16, 2024
Jan 7, 2024
Oct 16, 2018

Repository files navigation

vehicle-motion-forecasting

Work in progress.

This repository contains the training and inference code used in our paper Integrating kinematics and environment context into deep inverse reinforcement learning for predicting off-road vehicle trajectories. This work proposes a inverse reinforcement learning based framework that infers the reward structure and forecasts the vehicle's motion.

video

click to view

Installation

conda

We recommend using conda to install dependencies with the environment.yml provided in this repository.

conda env create -f environment.yml
source activate vehicle_motion_forecasting

pip

You can also use pip to install dependencies with the requirements.txt provided.

pip install -r requirements.txt

Inference

We provide the trained weights and example data for inference. Please check demo.ipynb.

jupyter notebook demo.ipynb

Training

Training examples will be made available later after we open source the dataset.

Citation

Please consider citing the corresponding publication.

@inproceedings{zhang2018integrating,
  title={Integrating kinematics and environment context into deep inverse reinforcement learning for predicting off-road vehicle trajectories},
  author={Zhang, Yanfu and Wang, Wenshan and Bonatti, Rogerio and Maturana, Daniel and Scherer, Sebastian},
  booktitle={Conference on Robot Learning},
  pages={894--905},
  year={2018}
}

About

A PyTorch-based deep inverse reinforcement learning pipeline for vehicle motion forecasting

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 68.7%
  • Jupyter Notebook 30.5%
  • Other 0.8%