Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2511.09013 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917075852722176 |
|---|---|
| author | Song, Ziyi Xia, Chen Wang, Chenbing Yu, Haibao Zhou, Sheng Niu, Zhisheng |
| author_facet | Song, Ziyi Xia, Chen Wang, Chenbing Yu, Haibao Zhou, Sheng Niu, Zhisheng |
| contents | Autonomous driving holds transformative potential but remains fundamentally constrained by the limited perception and isolated decision-making with standalone intelligence. While recent multi-agent approaches introduce cooperation, they often focus merely on perception-level tasks, overlooking the alignment with downstream planning and control, or fall short in leveraging the full capacity of the recent emerging end-to-end autonomous driving. In this paper, we present UniMM-V2X, a novel end-to-end multi-agent framework that enables hierarchical cooperation across perception, prediction, and planning. At the core of our framework is a multi-level fusion strategy that unifies perception and prediction cooperation, allowing agents to share queries and reason cooperatively for consistent and safe decision-making. To adapt to diverse downstream tasks and further enhance the quality of multi-level fusion, we incorporate a Mixture-of-Experts (MoE) architecture to dynamically enhance the BEV representations. We further extend MoE into the decoder to better capture diverse motion patterns. Extensive experiments on the DAIR-V2X dataset demonstrate our approach achieves state-of-the-art (SOTA) performance with a 39.7% improvement in perception accuracy, a 7.2% reduction in prediction error, and a 33.2% improvement in planning performance compared with UniV2X, showcasing the strength of our MoE-enhanced multi-level cooperative paradigm. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_09013 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | UniMM-V2X: MoE-Enhanced Multi-Level Fusion for End-to-End Cooperative Autonomous Driving Song, Ziyi Xia, Chen Wang, Chenbing Yu, Haibao Zhou, Sheng Niu, Zhisheng Robotics Computer Vision and Pattern Recognition Autonomous driving holds transformative potential but remains fundamentally constrained by the limited perception and isolated decision-making with standalone intelligence. While recent multi-agent approaches introduce cooperation, they often focus merely on perception-level tasks, overlooking the alignment with downstream planning and control, or fall short in leveraging the full capacity of the recent emerging end-to-end autonomous driving. In this paper, we present UniMM-V2X, a novel end-to-end multi-agent framework that enables hierarchical cooperation across perception, prediction, and planning. At the core of our framework is a multi-level fusion strategy that unifies perception and prediction cooperation, allowing agents to share queries and reason cooperatively for consistent and safe decision-making. To adapt to diverse downstream tasks and further enhance the quality of multi-level fusion, we incorporate a Mixture-of-Experts (MoE) architecture to dynamically enhance the BEV representations. We further extend MoE into the decoder to better capture diverse motion patterns. Extensive experiments on the DAIR-V2X dataset demonstrate our approach achieves state-of-the-art (SOTA) performance with a 39.7% improvement in perception accuracy, a 7.2% reduction in prediction error, and a 33.2% improvement in planning performance compared with UniV2X, showcasing the strength of our MoE-enhanced multi-level cooperative paradigm. |
| title | UniMM-V2X: MoE-Enhanced Multi-Level Fusion for End-to-End Cooperative Autonomous Driving |
| topic | Robotics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2511.09013 |