Learning to Drive via Real-World Simulation at Scale

Haochen Tian, Tianyu Li, Haochen Liu, Jiazhi Yang, Yihang Qiu, Guang Li, Junli Wang, Yinfeng Gao, Zhang Zhang, Liang Wang, Hangjun Ye, Tieniu Tan, Long Chen, Hongyang Li

• 📧 Primary Contact: Haochen Tian ([email protected])
• 📜 Materials: 🌐 𝕏 | 📰 Media | 🗂️ Slides TODO

---

🔥 Highlights

• 🏗️ A scalable simulation pipepline that synthesizes diverse and high-fidelity reactive driving scenarios with pseudo-expert demonstrations.
• 🚀 An effective sim-real co-training strategy that improves robustness and generalization synergistically across various end-to-end planners.
• 🔬 A comprehensive recipe that reveals crucial insights into the underlying scaling properties of sim-real learning systems for end-to-end autonomy.

📢 News

• [2025/12/31] We released the data, and models v1.0. Happy New Year ! 🎄
• [2025/12/1] We released our paper on arXiv.

📋 TODO List

• Sim-Real Co-training Code release (Jan. 2026).
• Simulation Data release (Dec. 2025).
• Checkpoints release (Dec. 2025).

---

📌 Table of Contents

• 🤗 Model Zoo

• 📦 Data Preparation
  • Download Dataset

• ⭐ License and Citation

🤗 Model Zoo

Model	Backbone	Sim-Real Config	NAVSIM v2 navhard		NAVSIM v2 navtest
			EPDMS	CKPT	EPDMS	CKPT
LTF	ResNet34	w/ pseudo-expert	30.3 | +6.9	Link	84.4 | +2.9	Link
DiffusionDrive	ResNet34	w/ pseudo-expert	32.6 | +5.1	Link	85.9 | +1.7	Link
GTRS-Dense	ResNet34	w/ pseudo-expert	46.1 | +7.8	Link	84.0 | +1.7	Link
		rewards only	46.9 | +8.6	Link	84.6 | +2.3	Link
	V2-99	w/ pseudo-expert	47.7 | +5.8	Link	84.5 | +0.5	Link
		rewards only	48.0 | +6.1	Link	84.8 | +0.8	Link

Note

We fixed a minor error in the simulation process without changing the method, resulting in better performance than the numbers reported in the arXiv version. We will update the arXiv paper soon.

📦 Data Preparation

Our released simulation data is based on nuPlan and NAVSIM. We recommend first preparing the real-world data by following the instructions in Download NAVSIM.

1. Download Dataset

Our simulation data format follows that of OpenScene, with each clip/log has a fixed temporal horizon of 6 seconds (2s history + 4s future).

We provide scripts for downloading the simulation data.

❤️ Acknowledgements

We acknowledge all the open-source contributors for the following projects to make this work possible:

• NAVSIM | MTGS | GTRS | DiffusionDrive

⭐ License and Citation

All content in this repository is under the Apache-2.0 license. The released data is based on nuPlan and is under the CC-BY-NC-SA 4.0 license.

If any parts of our paper and code help your research, please consider citing us and giving a star to our repository.

@article{tian2025simscale,
  title={SimScale: Learning to Drive via Real-World Simulation at Scale},
  author={Haochen Tian and Tianyu Li and Haochen Liu and Jiazhi Yang and Yihang Qiu and Guang Li and Junli Wang and Yinfeng Gao and Zhang Zhang and Liang Wang and Hangjun Ye and Tieniu Tan and Long Chen and Hongyang Li},
  journal={arXiv preprint arXiv:2511.23369},
  year={2025}
}