Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
119 tokens/sec
GPT-4o
56 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

CarDreamer: Open-Source Learning Platform for World Model based Autonomous Driving (2405.09111v2)

Published 15 May 2024 in cs.RO and cs.AI

Abstract: To safely navigate intricate real-world scenarios, autonomous vehicles must be able to adapt to diverse road conditions and anticipate future events. World model (WM) based reinforcement learning (RL) has emerged as a promising approach by learning and predicting the complex dynamics of various environments. Nevertheless, to the best of our knowledge, there does not exist an accessible platform for training and testing such algorithms in sophisticated driving environments. To fill this void, we introduce CarDreamer, the first open-source learning platform designed specifically for developing WM based autonomous driving algorithms. It comprises three key components: 1) World model backbone: CarDreamer has integrated some state-of-the-art WMs, which simplifies the reproduction of RL algorithms. The backbone is decoupled from the rest and communicates using the standard Gym interface, so that users can easily integrate and test their own algorithms. 2) Built-in tasks: CarDreamer offers a comprehensive set of highly configurable driving tasks which are compatible with Gym interfaces and are equipped with empirically optimized reward functions. 3) Task development suite: This suite streamlines the creation of driving tasks, enabling easy definition of traffic flows and vehicle routes, along with automatic collection of multi-modal observation data. A visualization server allows users to trace real-time agent driving videos and performance metrics through a browser. Furthermore, we conduct extensive experiments using built-in tasks to evaluate the performance and potential of WMs in autonomous driving. Thanks to the richness and flexibility of CarDreamer, we also systematically study the impact of observation modality, observability, and sharing of vehicle intentions on AV safety and efficiency. All code and documents are accessible on https://github.com/ucd-dare/CarDreamer.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (37)
  1. A survey of deep learning techniques for autonomous driving. Journal of field robotics, 37(3):362–386, 2020.
  2. Waymo public road safety performance data. arXiv preprint arXiv:2011.00038, 2020.
  3. A survey of autonomous driving: Common practices and emerging technologies. IEEE access, 8:58443–58469, 2020.
  4. Motion planning for autonomous driving: The state of the art and future perspectives. IEEE Transactions on Intelligent Vehicles, 2023.
  5. End-to-end autonomous driving: Challenges and frontiers. arXiv preprint arXiv:2306.16927, 2023.
  6. Crash rate calculations by US department of transportation federal highway administration. https://safety.fhwa.dot.gov/local_rural/training/fhwasa1109/app_c.cfm. [Accessed 07-05-2024].
  7. World models. arXiv preprint arXiv:1803.10122, 2018.
  8. Dream to control: Learning behaviors by latent imagination. arXiv preprint arXiv:1912.01603, 2019.
  9. Model-based imitation learning for urban driving. Advances in Neural Information Processing Systems, 35:20703–20716, 2022.
  10. Mastering diverse domains through world models. arXiv preprint arXiv:2301.04104, 2023.
  11. Yang Yu. Towards sample efficient reinforcement learning. In IJCAI, pages 5739–5743, 2018.
  12. Learning latent dynamics for planning from pixels. In International conference on machine learning, pages 2555–2565. PMLR, 2019.
  13. Mastering atari with discrete world models. arXiv preprint arXiv:2010.02193, 2020.
  14. Iso-dream: Isolating and leveraging noncontrollable visual dynamics in world models. Advances in Neural Information Processing Systems, 35:23178–23191, 2022.
  15. Planning to explore via self-supervised world models. In International conference on machine learning, pages 8583–8592. PMLR, 2020.
  16. Discovering and achieving goals via world models. Advances in Neural Information Processing Systems, 34:24379–24391, 2021.
  17. World models for autonomous driving: An initial survey. arXiv preprint arXiv:2403.02622, 2024.
  18. Is sora a world simulator? a comprehensive survey on general world models and beyond. arXiv preprint arXiv:2405.03520, 2024.
  19. Gaia-1: A generative world model for autonomous driving. arXiv preprint arXiv:2309.17080, 2023.
  20. Drivedreamer: Towards real-world-driven world models for autonomous driving. arXiv preprint arXiv:2309.09777, 2023.
  21. Adriver-i: A general world model for autonomous driving. arXiv preprint arXiv:2311.13549, 2023.
  22. Drivedreamer-2: Llm-enhanced world models for diverse driving video generation. arXiv preprint arXiv:2403.06845, 2024.
  23. Enhance sample efficiency and robustness of end-to-end urban autonomous driving via semantic masked world model. arXiv preprint arXiv:2210.04017, 2022.
  24. Think2drive: Efficient reinforcement learning by thinking in latent world model for quasi-realistic autonomous driving (in carla-v2). arXiv preprint arXiv:2402.16720, 2024.
  25. Carla: An open urban driving simulator. In Conference on robot learning, pages 1–16. PMLR, 2017.
  26. Microscopic traffic simulation using sumo. In 2018 21st International Conference on Intelligent Transportation Systems (ITSC), pages 2575–2582, 2018.
  27. Flow: Architecture and benchmarking for reinforcement learning in traffic control. 10 2017.
  28. Openai gym. arXiv preprint arXiv:1606.01540, 2016.
  29. Learning to communicate with deep multi-agent reinforcement learning. Advances in neural information processing systems, 29, 2016.
  30. A survey of multi-agent reinforcement learning with communication. arXiv preprint arXiv:2203.08975, 2022.
  31. Learning by cheating. In Conference on Robot Learning, pages 66–75. PMLR, 2020.
  32. Dense reinforcement learning for safety validation of autonomous vehicles. Nature, 615(7953):620–627, 2023.
  33. Driving to safety: How many miles of driving would it take to demonstrate autonomous vehicle reliability? Transportation Research Part A: Policy and Practice, 94:182–193, 2016.
  34. Curriculum learning. In Proceedings of the 26th annual international conference on machine learning, pages 41–48, 2009.
  35. A continual learning survey: Defying forgetting in classification tasks. IEEE transactions on pattern analysis and machine intelligence, 44(7):3366–3385, 2021.
  36. A survey of transfer learning. Journal of Big data, 3:1–40, 2016.
  37. Meta-learning in neural networks: A survey. IEEE transactions on pattern analysis and machine intelligence, 44(9):5149–5169, 2021.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (6)
  1. Dechen Gao (6 papers)
  2. Shuangyu Cai (1 paper)
  3. Hanchu Zhou (4 papers)
  4. Hang Wang (84 papers)
  5. Iman Soltani (12 papers)
  6. Junshan Zhang (75 papers)
Citations (1)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets