# OmniV2X: A Generative Foundation Planner for Efficient End-to-End Cooperative Driving

Source: [OmniV2X: A Generative Foundation Planner for Efficient End-to-End Cooperative Driving](<https://www.sota2.com/research/paper/6a3a12e1206542251d7c6dd1>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-08-12T05:00:05.228Z

Authors: Juntong Peng, Juanwu Lu, Yupeng Zhou, Can Cui, Yaobin Chen, Ziran Wang

Published: 2026-06-19T07:00:14.000Z

## Abstract

We present OmniV2X, a generative foundation model for vehicle-to-everything (V2X) cooperative driving. The model directly interprets independent context sequences comprising multi-modal and multi-agent observations. The new design mitigates the computational cost of dense 3D perception, the vulnerability to data scarcity in cooperative scenarios, and the poor compliance with standardized messaging in existing methods that fuse multi-modal inputs into a shared representation. For training, we present an end-to-end supervised pipeline using a downstream trajectory generation loss, in which a high-capacity generative sequence planner implicitly learns to steer the model and leverage multi-modal inputs via cross-attention injection. As a foundation model, we demonstrate that OmniV2X pre-trained on large-scale single-agent planning datasets can efficiently adapt to cooperative environments by integrating the conditioning context with lightweight, standard-compliant V2X tokens. Evaluated on the DAIR-V2X-Seq dataset, OmniV2X outperforms existing end-to-end cooperative driving baselines, achieving state-of-the-art performance with less than 10% of the fine-tune V2X dataset and less than 1% of the communication bandwidth. We conduct comprehensive evaluations to demonstrate its computational efficiency and robustness under real-world constraints.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Open-loop trajectory planning on DAIR-V2X-Seq (val)](<https://www.sota2.com/research/sota/open-loop-trajectory-planning-on-dair-v2x-seq-val.md>): Open-Loop Trajectory Planning; DAIR-V2X-Seq (val); L2 Error (1s): 0.45.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2606.21165>)

[PDF](<https://arxiv.org/pdf/2606.21165.pdf>)