ln2697/tfv6_navsim

LEAD: Minimizing Learner–Expert Asymmetry in End-to-End Driving

Project Page | Paper | Code

Official model weights for Latent TransFuser v6 (LTFv6), a NAVSIM checkpoint accompanies our paper LEAD: Minimizing Learner–Expert Asymmetry in End-to-End Driving.

We release the complete pipeline (covering scenario descriptions, expert driver, data preprocessing scripts, training code, and evaluation infrastructure) required to achieve state-of-the-art closed-loop performance on the Bench2Drive benchmark. Built around the CARLA simulator, the stack features a data-centric design with:

• Extensive visualization suite and runtime type validation for easier debugging.
• Optimized storage format, packs 72 hours of driving in ~200GB.
• Native support for NAVSIM and Waymo Vision-based E2E, with LEAD extending these benchmarks through closed-loop simulation and synthetic data for additional supervision during training

Find more information on https://github.com/autonomousvision/lead.

Usage

Install dependencies

pip install torch timm numpy opencv-python jaxtyping beartype omegaconf huggingface_hub

See example.ipynb to inspect data format and example inference.

Data Format

We also provide example NAVSIM cache here.

Input:

• RGB: (256, 1920, 3), range [0, 255]
• Command: [left, straight, right, unknown], e.g. [0, 1, 0, 0] for straight
• Speed: m/s
• Acceleration: m/s²

Output:

• waypoints: (N, 2) predicted positions
• headings: (N,) predicted angles

Citation

If you find this work useful, please cite:

@article{Nguyen2025ARXIV,
  title={LEAD: Minimizing Learner-Expert Asymmetry in End-to-End Driving},
  author={Nguyen, Long and Fauth, Micha and Jaeger, Bernhard and Dauner, Daniel and Igl, Maximilian and Geiger, Andreas and Chitta, Kashyap},
  journal={arXiv preprint arXiv:2512.20563},
  year={2025}
}