Here're some resources about Machine Learning-based Planning
Intros:
- Recently, machine learning techniques, especially reinforcement learning and imitation learning, have been increasingly applied to planning problems in autonomous driving. These methods learn from large amounts of data to make decisions, potentially handling complex situations better than traditional methods.
paper link: here
citation:
@misc{li2022efficient,
title={Efficient Learning of Safe Driving Policy via Human-AI Copilot Optimization},
author={Quanyi Li and Zhenghao Peng and Bolei Zhou},
year={2022},
eprint={2202.10341},
archivePrefix={arXiv},
primaryClass={id='cs.LG' full_name='Machine Learning' is_active=True alt_name=None in_archive='cs' is_general=False description='Papers on all aspects of machine learning research (supervised, unsupervised, reinforcement learning, bandit problems, and so on) including also robustness, explanation, fairness, and methodology. cs.LG is also an appropriate primary category for applications of machine learning methods.'}
}End-to-end interactive prediction and planning with optical flow distillation for autonomous driving
paper link: here
citation:
@inproceedings{wang2021end,
title={End-to-end interactive prediction and planning with optical flow distillation for autonomous driving},
author={Wang, Hengli and Cai, Peide and Fan, Rui and Sun, Yuxiang and Liu, Ming},
booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
pages={2229--2238},
year={2021}
}paper link: here
citation:
@misc{peng2021safe,
title={Safe Driving via Expert Guided Policy Optimization},
author={Zhenghao Peng and Quanyi Li and Chunxiao Liu and Bolei Zhou},
year={2021},
eprint={2110.06831},
archivePrefix={arXiv},
primaryClass={id='cs.AI' full_name='Artificial Intelligence' is_active=True alt_name=None in_archive='cs' is_general=False description='Covers all areas of AI except Vision, Robotics, Machine Learning, Multiagent Systems, and Computation and Language (Natural Language Processing), which have separate subject areas. In particular, includes Expert Systems, Theorem Proving (although this may overlap with Logic in Computer Science), Knowledge Representation, Planning, and Uncertainty in AI. Roughly includes material in ACM Subject Classes I.2.0, I.2.1, I.2.3, I.2.4, I.2.8, and I.2.11.'}
}paper link: here
citation:
@article{Sun_2022,
title={PlaTe: Visually-Grounded Planning With Transformers in Procedural Tasks},
volume={7},
ISSN={2377-3774},
url={http://dx.doi.org/10.1109/LRA.2022.3150855},
DOI={10.1109/lra.2022.3150855},
number={2},
journal={IEEE Robotics and Automation Letters},
publisher={Institute of Electrical and Electronics Engineers (IEEE)},
author={Sun, Jiankai and Huang, De-An and Lu, Bo and Liu, Yun-Hui and Zhou, Bolei and Garg, Animesh},
year={2022},
month=apr, pages={4924–4930}
}paper link: here
citation:
@inproceedings{huang2021learning,
title={Learning a decision module by imitating driver’s control behaviors},
author={Huang, Junning and Xie, Sirui and Sun, Jiankai and Ma, Qiurui and Liu, Chunxiao and Lin, Dahua and Zhou, Bolei},
booktitle={Conference on Robot Learning},
pages={1--10},
year={2021},
organization={PMLR}
}Combining planning and deep reinforcement learning in tactical decision making for autonomous driving
paper link: here
citation:
@article{hoel2019combining,
title={Combining planning and deep reinforcement learning in tactical decision making for autonomous driving},
author={Hoel, Carl-Johan and Driggs-Campbell, Katherine and Wolff, Krister and Laine, Leo and Kochenderfer, Mykel J},
journal={IEEE transactions on intelligent vehicles},
volume={5},
number={2},
pages={294--305},
year={2019},
publisher={IEEE}
}paper link: here
citation:
@inproceedings{hafner2019learning,
title={Learning latent dynamics for planning from pixels},
author={Hafner, Danijar and Lillicrap, Timothy and Fischer, Ian and Villegas, Ruben and Ha, David and Lee, Honglak and Davidson, James},
booktitle={International conference on machine learning},
pages={2555--2565},
year={2019},
organization={PMLR}
}paper link: here
citation:
@inproceedings{zeng2019end,
title={End-to-end interpretable neural motion planner},
author={Zeng, Wenyuan and Luo, Wenjie and Suo, Simon and Sadat, Abbas and Yang, Bin and Casas, Sergio and Urtasun, Raquel},
booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
pages={8660--8669},
year={2019}
}paper link: here
citation:
@article{pereira2018mpc,
title={Mpc-inspired neural network policies for sequential decision making},
author={Pereira, Marcus and Fan, David D and An, Gabriel Nakajima and Theodorou, Evangelos},
journal={arXiv preprint arXiv:1802.05803},
year={2018}
}paper link: here
citation:
@inproceedings{codevilla2018end,
title={End-to-end driving via conditional imitation learning},
author={Codevilla, Felipe and M{\"u}ller, Matthias and L{\'o}pez, Antonio and Koltun, Vladlen and Dosovitskiy, Alexey},
booktitle={2018 IEEE international conference on robotics and automation (ICRA)},
pages={4693--4700},
year={2018},
organization={IEEE}
}From perception to decision: A data-driven approach to end-to-end motion planning for autonomous ground robots
paper link: here
citation:
@inproceedings{pfeiffer2017perception,
title={From perception to decision: A data-driven approach to end-to-end motion planning for autonomous ground robots},
author={Pfeiffer, Mark and Schaeuble, Michael and Nieto, Juan and Siegwart, Roland and Cadena, Cesar},
booktitle={2017 ieee international conference on robotics and automation (icra)},
pages={1527--1533},
year={2017},
organization={IEEE}
}paper link: here
citation:
@article{karkus2017qmdp,
title={Qmdp-net: Deep learning for planning under partial observability},
author={Karkus, Peter and Hsu, David and Lee, Wee Sun},
journal={Advances in neural information processing systems},
volume={30},
year={2017}
}