---
license: apache-2.0
tags:
- CARLA
- NAVSIM
- Imitation-Learning
- Closed-Loop-Driving
pipeline_tag: robotics
---

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


> ## ⚠️ Coordinate System Warning
>
> **This model was trained in the left-handed coordinate system of CARLA** (x-forward, **y-right**, z-up), **not** the ISO 8855 convention used by NAVSIM / nuPlan / most AD stacks (x-forward, **y-left**, z-up).
>
> If you use `ltfv6.py` directly, the predicted `waypoints` and `headings` are in CARLA's left-handed frame. **You must convert the planning output back to ISO 8855 before feeding it to any downstream planner, simulator, or evaluation tool that expects the right-handed convention.**
>
> ### ✅ Recommended: use the prepared NAVSIM workspaces
>
> For correct, reproducible evaluation, Use one of the prepared workspaces below — they already wire up the model with the correct coordinate conversion, input preprocessing, and metric computation:
>
> - **NAVSIM v1.1**: [`3rd_party/navsim_workspace/navsimv1.1`](https://github.com/kesai-labs/lead/tree/main/3rd_party/navsim_workspace/navsimv1.1)
> - **NAVSIM v2.2**: [`3rd_party/navsim_workspace/navsimv2.2`](https://github.com/kesai-labs/lead/tree/main/3rd_party/navsim_workspace/navsimv2.2)
>
> These are the only configurations we have validated end-to-end against the reported numbers. If you evaluate outside of them, results may silently disagree with the paper.
>
> ### Manual conversion (only if you must integrate the model yourself)
>
> ```python
> waypoints_iso[..., 0] =  waypoints_carla[..., 0]   # x unchanged
> waypoints_iso[..., 1] = -waypoints_carla[..., 1]   # flip y
> headings_iso          = -headings_carla            # flip yaw sign
> ```


[**Project Page**](https://ln2697.github.io/lead) | [**Paper**](https://huggingface.co/papers/2512.20563) | [**Code**](https://github.com/autonomousvision/lead)

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 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 and extending those benchmarks through closed-loop simulation and synthetic data for additional supervision during training.

Find more information on [https://github.com/autonomousvision/lead](https://github.com/autonomousvision/lead).

<p align="center">
  <img src="https://ln2697.github.io/lead/static/images/tfv6.png" alt="TFv6 Architecture" width="80%" >
</p>

## Usage

Install dependencies

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

See [example.ipynb](https://huggingface.co/ln2697/tfv6_navsim/blob/main/example.ipynb) to inspect data format and example inference.

## Data Format

We also provide example NAVSIM cache [here](https://huggingface.co/ln2697/tfv6_navsim/tree/main/data).

**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:

```bibtex
@inproceedings{Nguyen2026CVPR,
	author = {Long Nguyen and Micha Fauth and Bernhard Jaeger and Daniel Dauner and Maximilian Igl and Andreas Geiger and Kashyap Chitta},
	title = {LEAD: Minimizing Learner-Expert Asymmetry in End-to-End Driving},
	booktitle = {Conference on Computer Vision and Pattern Recognition (CVPR)},
	year = {2026},
}
```