Improve model card for Fail2Drive and TransFuser++

README.md

@@ -1,7 +1,10 @@
 ---
-license: cc-by-4.0
+language:
+- en
 library_name: pytorch
-
+license: cc-by-4.0
+model_name: TransFuser++ (TFv5) CARLA Garage Checkpoints
+pipeline_tag: robotics
 tags:
 - carla
 - carla-simulator
@@ -11,20 +14,48 @@ tags:
 - carla-leaderboard
 - transfuser
 - transfuser++
-
-model_name: TransFuser++ (TFv5) CARLA Garage Checkpoints
-language:
-- en
 ---
 
 # TransFuser++ (TFv5) CARLA Garage Checkpoints
 
-This repository re-uploads the pretrained checkpoints originally released by the CARLA Garage project:
+This repository contains pretrained checkpoints for the TransFuser++ (TFv5) model, which serves as a baseline for the **Fail2Drive** benchmark. 
+
+[**Fail2Drive: Benchmarking Closed-Loop Driving Generalization**](https://huggingface.co/papers/2604.08535)
+
+[**Project Page**](https://simonger.github.io/fail2drive/) | [**Code**](https://github.com/autonomousvision/fail2drive)
+
+## Introduction
+
+Fail2Drive is a paired-route benchmark for closed-loop generalization in CARLA, featuring 200 routes and 17 new scenario classes. It highlights failure modes in state-of-the-art models when facing distribution shifts in appearance, layout, behavior, and robustness. TransFuser++ is an end-to-end autonomous driving agent that utilizes both LiDAR and camera inputs.
+
+## Sample Usage
+
+To run the TransFuser++ model within the Fail2Drive environment, follow the installation instructions in the [official repository](https://github.com/autonomousvision/fail2drive). 
+
+Once the environment and simulator are set up, you can evaluate the agent using the following command:
+
+```bash
+LIVE_VISU=1 python leaderboard/leaderboard/leaderboard_evaluator_local.py \
+  --routes ${WORK_DIR}/fail2drive_split/Generalization_PedestriansOnRoad_1085.xml \
+  --agent ${WORK_DIR}/team_code/sensor_agent.py \
+  --agent-config /path/to/checkpoint_folder
+```
+
+*Note: The `--agent-config` parameter should point to the directory containing both `model.pth` and `config.json`.*
+
+## Attribution
 
-https://github.com/autonomousvision/carla_garage
+This repository re-uploads the pretrained checkpoints originally released by the [CARLA Garage](https://github.com/autonomousvision/carla_garage) project. All credit and attribution belong to the original authors.
 
-https://s3.eu-central-1.amazonaws.com/avg-projects-2/garage_2/models/pretrained_models.zip
+Original source: [CARLA Garage Models](https://s3.eu-central-1.amazonaws.com/avg-projects-2/garage_2/models/pretrained_models.zip)
 
-All credit and attribution belong to the original authors.
+## Citation
 
-Please refer to the original repository for code, training setup, evaluation details, and citations.
+```bibtex
+@article{ger2024fail2drive,
+  title={Fail2Drive: Benchmarking Closed-Loop Driving Generalization},
+  author={Ger, Simon and others},
+  journal={arXiv preprint arXiv:2604.08535},
+  year={2024}
+}
+```