README.md

Natural Traffic Flow Generation

Here're some resources about Natural Traffic Flow Generation

Intros:

• Natural traffic flow generation for ADS testing refers to the simulation of realistic, dynamic, and diverse traffic conditions that an autonomous vehicle might encounter in real-world scenarios.
• Achieving natural traffic flow in simulation is a challenging task. It requires accurately replicating the behavior of various road users, including cars, trucks, motorcycles, bicycles, pedestrians, and even animals. These entities need to move and interact in a way that is indistinguishable from real-world traffic.
• Creating natural traffic flow for AV testing ensures that the AV can operate safely and efficiently under real-world conditions, thereby ensuring the reliability of the autonomous driving system. It also helps identify and correct potential issues in the AV system, thus significantly reducing the risks before actual road tests.

---

DriveDreamer-2: LLM-Enhanced World Models for Diverse Driving Video Generation

paper link: here

citation:

@misc{zhao2024drivedreamer2,
      title={DriveDreamer-2: LLM-Enhanced World Models for Diverse Driving Video Generation}, 
      author={Guosheng Zhao and Xiaofeng Wang and Zheng Zhu and Xinze Chen and Guan Huang and Xiaoyi Bao and Xingang Wang},
      year={2024},
      eprint={2403.06845},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

GAIA-1: A Generative World Model for Autonomous Driving

paper link: here

citation:

@misc{hu2023gaia1,
      title={GAIA-1: A Generative World Model for Autonomous Driving}, 
      author={Anthony Hu and Lloyd Russell and Hudson Yeo and Zak Murez and George Fedoseev and Alex Kendall and Jamie Shotton and Gianluca Corrado},
      year={2023},
      eprint={2309.17080},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

Scenegen: Learning to generate realistic traffic scenes

paper link: here

citation:

@inproceedings{tan2021scenegen,
  title={Scenegen: Learning to generate realistic traffic scenes},
  author={Tan, Shuhan and Wong, Kelvin and Wang, Shenlong and Manivasagam, Sivabalan and Ren, Mengye and Urtasun, Raquel},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={892--901},
  year={2021}
}

Learning to Simulate Self-Driven Particles System with Coordinated Policy Optimization (CoPO)

paper link: here

citation:

@misc{peng2022learning,
      title={Learning to Simulate Self-Driven Particles System with Coordinated Policy Optimization}, 
      author={Zhenghao Peng and Quanyi Li and Ka Ming Hui and Chunxiao Liu and Bolei Zhou},
      year={2022},
      eprint={2110.13827},
      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.'}
}

An overview of microscopic and macroscopic traffic models

paper link: here

citation:

@article{popping2013overview,
  title={An overview of microscopic and macroscopic traffic models},
  author={Popping, J},
  year={2013},
  publisher={Faculty of Science and Engineering}
}

Microscopic modeling of traffic flow: Investigation of collision free vehicle dynamics

paper link: here

citation:

@article{krauss1998microscopic,
  title={Microscopic modeling of traffic flow: Investigation of collision free vehicle dynamics},
  author={Krau{\ss}, Stefan},
  year={1998}
}

Fundamentals of traffic simulation

book link: here, with extraction code: zr11