This repo is the implementation of the following two papers:
Velocity Field: An Informative Traveling Cost Representation for Trajectory Planning
Xin, Ren, Cheng, Jie, Wang, Sheng, Liu, Ming
[arXiv] [Website]
RiskMap: A Unified Driving Context Representation for Autonomous Motion Planning in Urban Driving Environment
Xin, Ren, Wang, Sheng, Chen, Yingbing, Cheng, Jie, Liu, Ming , Ma, Jun
[arXiv] [Website]
Download the Waymo Open Motion Dataset v1.1; only the files in uncompressed/scenario/training_20s are needed. Place the downloaded files into training and testing folders separately.
sudo apt-get install libsuitesparse-devconda env create -f environment.yml
conda activate DIPPInstall the Theseus library, follow the guidelines.
Run sh start_data_process.sh.
Run sh start_train_test.sh for single GPU.
Run sh start_train.sh for multiple GPUs.
Run sh start_ol_test.sh.
Run sh start_cl_test.sh.
If you find our repo or our paper useful, please star this repo or use the following citation:
@INPROCEEDINGS{10355004,
author={Xin, Ren and Cheng, Jie and Wang, Sheng and Liu, Ming},
booktitle={2023 IEEE International Conference on Robotics and Biomimetics (ROBIO)},
title={Velocity Field: An Informative Traveling Cost Representation for Trajectory Planning},
year={2023},
pages={1-6},
keywords={Costs;Trajectory planning;Planning;Trajectory;Iterative methods;Reliability;Task analysis},
doi={10.1109/ROBIO58561.2023.10355004}}
}
@inproceedings{xin2024riskmapunifieddrivingcontext,
title = {{RiskMap:} A Unified Driving Context Representation for Autonomous Motion Planning in Urban Driving Environment},
author = {Xin, Ren and Wang, Sheng and Chen, Yingbing and Cheng, Jie and Liu, Ming and Ma, Jun},
booktitle = {Proceedings of the IEEE International Conference on Robotics and Biomimetics},
year = {2024},
eprint = {2406.04451},
archiveprefix = {arXiv},
primaryclass = {cs.RO},
url = {https://arxiv.org/abs/2406.04451},
}