Add model card and metadata
#1
by nielsr HF Staff - opened
README.md
CHANGED
|
@@ -1,3 +1,45 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: cc-by-4.0
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: cc-by-nc-nd-4.0
|
| 3 |
+
pipeline_tag: robotics
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# TCP-Speed
|
| 7 |
+
|
| 8 |
+
**TCP-Speed** is a baseline model for desired-speed conditioned autonomous driving, introduced as part of the **Bench2Drive-Speed** benchmark.
|
| 9 |
+
|
| 10 |
+
[**Project Page**](https://thinklab-sjtu.github.io/Bench2Drive-Speed/) | [**Paper**](https://huggingface.co/papers/2603.25672) | [**Github**](https://github.com/Thinklab-SJTU/Bench2Drive-Speed)
|
| 11 |
+
|
| 12 |
+
## Overview
|
| 13 |
+
|
| 14 |
+
Bench2Drive-Speed is a closed-loop benchmark for desired-speed conditioned autonomous driving. It enables explicit control over vehicle behavior through:
|
| 15 |
+
* 🎯 **Target-speed conditioning**: Users can specify the desired driving speed.
|
| 16 |
+
* 🚘 **Overtake / Follow commands**: Users can specify whether the vehicle should overtake or follow others.
|
| 17 |
+
|
| 18 |
+
The TCP-Speed model serves as a baseline that processes these user preferences to generate driving actions within the CARLA simulator.
|
| 19 |
+
|
| 20 |
+
## Usage
|
| 21 |
+
|
| 22 |
+
To use or build upon this agent, refer to the official [Bench2Drive-Speed repository](https://github.com/Thinklab-SJTU/Bench2Drive-Speed).
|
| 23 |
+
|
| 24 |
+
The agent inherits from `AutonomousAgent`. In addition to standard CARLA inputs, you can access the user-specified conditions within the agent logic as follows:
|
| 25 |
+
|
| 26 |
+
```python
|
| 27 |
+
# Extract target speed and overtake commands within the agent class
|
| 28 |
+
target_speed = self.get_planned_speed() # float (km/h)
|
| 29 |
+
do_overtake = self.do_overtake # boolean
|
| 30 |
+
```
|
| 31 |
+
|
| 32 |
+
For full setup, training, and evaluation instructions, please follow the documentation in the [Github README](https://github.com/Thinklab-SJTU/Bench2Drive-Speed).
|
| 33 |
+
|
| 34 |
+
## Citation
|
| 35 |
+
|
| 36 |
+
```bibtex
|
| 37 |
+
@article{Bench2DriveSpeed,
|
| 38 |
+
title={Can Users Specify Driving Speed? Bench2Drive-Speed: Benchmark and Baselines for Desired-Speed Conditioned Autonomous Driving},
|
| 39 |
+
author={Yuqian Shao and Xiaosong Jia and Langechuan Liu and Junchi Yan},
|
| 40 |
+
year={2026},
|
| 41 |
+
eprint={2603.25672},
|
| 42 |
+
archivePrefix={arXiv},
|
| 43 |
+
primaryClass={cs.RO},
|
| 44 |
+
}
|
| 45 |
+
```
|