BeTop: Reasoning Multi-Agent Behavioral Topology for Interactive Autonomous Driving

• Haochen Liu, Li Chen, Yu Qiao, Chen Lv and Hongyang Li
• Paper | Poster | Challenge Report
• If you have any questions, please feel free to contact: Haochen Liu ( haochen002@e.ntu.edu.sg )

[2025-06] The ensembled version of BeTop BeTop-ens has received 3rd place of 2025 WOMD Interaction Prediction Challenge. Report

[2024-11] Scenario Token released for Test14-Inter. Link

[2024-11] Prediction project released.

Overview

BeTop leverages braid theory to model multi-agent future behaviors in autonomous driving;

The synergetic framework, BeTopNet, integrates topology reasoning with prediction and planning tasks for autonomous driving.

Get Started

Prediction

We provide the full prediction implementation of BeTopNet in Waymo Open Motion Dataset (WOMD).

Features:

• ✅ Full support for WOMD Prediction Challenges
• ✅ Flexible Toolbox for prediction tasks
• ✅ Pipeline for reproduced popular Baselines

Guideline

• Data Preparation
• Training & Evaluation
• Testing & Submission

TODO List

• Initial release
• Prediction pipeline in WOMD
• Planning pipeline in nuPlan

Citation

If you find the project helpful for your research, please consider citing our paper:

@inproceedings{liu2024betop,
 title={Reasoning Multi-Agent Behavioral Topology for Interactive Autonomous Driving}, 
 author={Haochen Liu and Li Chen and Yu Qiao and Chen Lv and Hongyang Li},
 booktitle={NeurIPS},
 year={2024}
}