VAD-Speed is a baseline model for desired-speed conditioned autonomous driving, introduced as part of the Bench2Drive-Speed benchmark. For other baseline models, you can find TCP-Speed here.
Model source
Source description
VAD-Speed is a baseline model for desired-speed conditioned autonomous driving, introduced as part of the Bench2Drive-Speed benchmark. For other baseline models, you can find TCP-Speed here.
| |
Sources
1 sourceVerified Aug 7
Model artifacts
6 artifactsSource excerpts
2 excerptsBench2Drive-Speed is a closed-loop benchmark for desired-speed conditioned autonomous driving. It enables explicit control over vehicle behavior through:
The VAD-Speed model serves as a baseline that processes these user preferences to generate driving actions within the CARLA simulator.
To use or build upon this agent, refer to the official Bench2Drive-Speed repository.
The agent inherits from AutonomousAgent. In addition to standard CARLA inputs, you can access the user-specified conditions within the agent logic as follows:
# Extract target speed and overtake commands within the agent class
target_speed = self.get_planned_speed() # float (km/h)
do_overtake = self.do_overtake # boolean
For full setup, training, and evaluation instructions, please follow the documentation in the Github README.
@article{Bench2DriveSpeed,
title={Can Users Specify Driving Speed? Bench2Drive-Speed: Benchmark and Baselines for Desired-Speed Conditioned Autonomous Driving},
author={Yuqian Shao and Xiaosong Jia and Langechuan Liu and Junchi Yan},
year={2026},
eprint={2603.25672},
archivePrefix={arXiv},
primaryClass={cs.RO},
}
VAD-Speed_B2D1kShort.pth
pth · 677 MB · SHA-256 28c18b5205c3…d8ae · Hugging Face
--- license: cc-by-nc-nd-4.0 pipeline_tag: robotics --- # VAD-Speed **VAD-Speed** is a baseline model for desired-speed conditioned autonomous driving, introduced as part of the **Bench2Drive-Speed** benchmark. For other baseline models, you can find TCP-Speed [here](https://huggingface.co/rethinklab/TCP-Speed/edit/main/README.md). [**Project Page**](https://thinklab-sjtu.github.io/Bench2Drive-Speed/) | [**Paper**](https://huggingface.co/papers/2603.25672) | [**Github**](https://github.com/Thinklab-SJTU/Bench2Drive-Speed) ## Overview Bench2Drive-Speed is a closed-loop benchmark for desired-speed conditioned autonomous driving. It enables explicit control over vehicle behavior through: * 🎯 **Target-speed conditioning**: Users can specify the desired driving speed. * 🚘 **Overtake / Follow commands**: Users can specify whether the vehicle should overtake or follow others. The VAD-Speed model serves as a baseline that processes these user preferences to generate driving actions within the CARLA simulator. ## Usage To use or build upon this agent, refer to the official [Bench2Drive-Speed repository](https://github.com/Thinklab-SJTU/Bench2Drive-Speed). The agent inherits from `AutonomousAgent`. In addition to standard CARLA inputs, you can access the user-specified conditions within the agent logic as follows: ```python # Extract target speed and overtake commands within the agent class target_speed = self.get_planned_speed() # float (km/h) do_overtake = self.do_overtake # boolean ``` For full setup, training, and evaluation instructions, please follow the documentation in the [Github README](https://github.com/Thinklab-SJTU/Bench2Drive-Speed). ## Citation ```bibtex @article{Bench2DriveSpeed, title={Can Users Specify Driving Speed? Bench2Drive-Speed: Benchmark and Baselines for Desired-Speed Conditioned Autonomous Driving}, author={Yuqian Shao and Xiaosong Jia and Langechuan Liu and Junchi Yan}, year={2026}, eprint={2603.25672}, archivePrefix={arXiv}, primaryClass={cs.RO}, } ```
Source context: 0 downloads · 0 likes · Pipeline robotics · Repo Telkwevr/VAD-Speed