GraphAD: Interaction Scene Graph for End-to-end Autonomous Driving

Zhang, Yunpeng; Qian, Deheng; Li, Ding; Pan, Yifeng; Chen, Yong; Liang, Zhenbao; Zhang, Zhiyao; Liu, Yingzong; Mei, Jianhui; Fu, Maolei; Ye, Yun; Liang, Zhujin; Shan, Yi; Du, Dalong

doi:10.24963/ijcai.2025/270

GraphAD: Interaction Scene Graph for End-to-end Autonomous Driving

Yunpeng Zhang, Deheng Qian, Ding Li, Yifeng Pan, Yong Chen, Zhenbao Liang, Zhiyao Zhang, Yingzong Liu, Jianhui Mei, Maolei Fu, Yun Ye, Zhujin Liang, Yi Shan, Dalong Du

Download BibTeX Cite

Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence. Main Track. Pages 2422-2430.

https://doi.org/10.24963/ijcai.2025/270

Keywords

Computer Vision: CV: 3D computer vision
Computer Vision: CV: Scene analysis and understanding
Computer Vision: CV: Motion and tracking

Abstract

Modeling complicated interactions among the ego-vehicle, road agents, and map elements has been a crucial part for safety-critical autonomous driving. Previous work on end-to-end autonomous driving relies on the attention mechanism to handle heterogeneous interactions, which fails to capture geometric priors and is also computationally intensive. In this paper, we propose the Interaction Scene Graph (ISG) as a unified method to model the interactions among the ego-vehicle, road agents, and map elements. With the representation of the ISG, the driving agents aggregate essential information from the most influential elements, including the road agents with potential collisions and the map elements to follow. Since a mass of unnecessary interactions are omitted, the more efficient scene-graph-based framework is able to focus on indispensable connections and leads to better performance. We evaluate the proposed method for end-to-end autonomous driving on the nuScenes dataset. Compared with strong baselines, our method significantly outperforms in full-stack driving tasks.

Yunpeng Zhang, Deheng Qian, Ding Li, Yifeng Pan, Yong Chen, Zhenbao Liang, Zhiyao Zhang, Yingzong Liu, Jianhui Mei, Maolei Fu, Yun Ye, Zhujin Liang, Yi Shan, and Dalong Du. 2025. GraphAD: Interaction Scene Graph for End-to-end Autonomous Driving. In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25. IJCAI, 2422–2430. https://doi.org/10.24963/ijcai.2025/270

@inproceedings{ijcai2025p270,
  title     = {GraphAD: Interaction Scene Graph for End-to-end Autonomous Driving},
  author    = {Zhang, Yunpeng and Qian, Deheng and Li, Ding and Pan, Yifeng and Chen, Yong and Liang, Zhenbao and Zhang, Zhiyao and Liu, Yingzong and Mei, Jianhui and Fu, Maolei and Ye, Yun and Liang, Zhujin and Shan, Yi and Du, Dalong},
  booktitle = {Proceedings of the Thirty-Fourth International Joint Conference on
               Artificial Intelligence, {IJCAI-25}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {James Kwok},
  pages     = {2422--2430},
  year      = {2025},
  month     = {8},
  note      = {Main Track},
  doi       = {10.24963/ijcai.2025/270},
  url       = {https://doi.org/10.24963/ijcai.2025/270},
}

TY  - CPAPER
TI  - GraphAD: Interaction Scene Graph for End-to-end Autonomous Driving
AU  - Zhang, Yunpeng
AU  - Qian, Deheng
AU  - Li, Ding
AU  - Pan, Yifeng
AU  - Chen, Yong
AU  - Liang, Zhenbao
AU  - Zhang, Zhiyao
AU  - Liu, Yingzong
AU  - Mei, Jianhui
AU  - Fu, Maolei
AU  - Ye, Yun
AU  - Liang, Zhujin
AU  - Shan, Yi
AU  - Du, Dalong
T2  - Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25
PB  - International Joint Conferences on Artificial Intelligence Organization
PY  - 2025
SP  - 2422
EP  - 2430
DO  - 10.24963/ijcai.2025/270
UR  - https://doi.org/10.24963/ijcai.2025/270
ER  -