SimpleVSF: VLM-Scoring Fusion for Trajectory Prediction of End-to-End Autonomous Driving
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914117507350528 |
|---|---|
| author | Zheng, Peiru Zhao, Yun Gong, Zhan Zhu, Hong Wu, Shaohua |
| author_facet | Zheng, Peiru Zhao, Yun Gong, Zhan Zhu, Hong Wu, Shaohua |
| contents | End-to-end autonomous driving has emerged as a promising paradigm for achieving robust and intelligent driving policies. However, existing end-to-end methods still face significant challenges, such as suboptimal decision-making in complex scenarios. In this paper,we propose SimpleVSF (Simple VLM-Scoring Fusion), a novel framework that enhances end-to-end planning by leveraging the cognitive capabilities of Vision-Language Models (VLMs) and advanced trajectory fusion techniques. We utilize the conventional scorers and the novel VLM-enhanced scorers. And we leverage a robust weight fusioner for quantitative aggregation and a powerful VLM-based fusioner for qualitative, context-aware decision-making. As the leading approach in the ICCV 2025 NAVSIM v2 End-to-End Driving Challenge, our SimpleVSF framework demonstrates state-of-the-art performance, achieving a superior balance between safety, comfort, and efficiency. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_17191 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SimpleVSF: VLM-Scoring Fusion for Trajectory Prediction of End-to-End Autonomous Driving Zheng, Peiru Zhao, Yun Gong, Zhan Zhu, Hong Wu, Shaohua Robotics Artificial Intelligence End-to-end autonomous driving has emerged as a promising paradigm for achieving robust and intelligent driving policies. However, existing end-to-end methods still face significant challenges, such as suboptimal decision-making in complex scenarios. In this paper,we propose SimpleVSF (Simple VLM-Scoring Fusion), a novel framework that enhances end-to-end planning by leveraging the cognitive capabilities of Vision-Language Models (VLMs) and advanced trajectory fusion techniques. We utilize the conventional scorers and the novel VLM-enhanced scorers. And we leverage a robust weight fusioner for quantitative aggregation and a powerful VLM-based fusioner for qualitative, context-aware decision-making. As the leading approach in the ICCV 2025 NAVSIM v2 End-to-End Driving Challenge, our SimpleVSF framework demonstrates state-of-the-art performance, achieving a superior balance between safety, comfort, and efficiency. |
| title | SimpleVSF: VLM-Scoring Fusion for Trajectory Prediction of End-to-End Autonomous Driving |
| topic | Robotics Artificial Intelligence |
| url | https://arxiv.org/abs/2510.17191 |