Unifying Language-Action Understanding and Generation for Autonomous Driving
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908860033269760 |
|---|---|
| author | Wang, Xinyang Liu, Qian Ding, Wenjie Yang, Zhao Li, Wei Liu, Chang Li, Bailin Zhan, Kun Lang, Xianpeng Chen, Wei |
| author_facet | Wang, Xinyang Liu, Qian Ding, Wenjie Yang, Zhao Li, Wei Liu, Chang Li, Bailin Zhan, Kun Lang, Xianpeng Chen, Wei |
| contents | Vision-Language-Action (VLA) models are emerging as a promising paradigm for end-to-end autonomous driving, valued for their potential to leverage world knowledge and reason about complex driving scenes. However, existing methods suffer from two critical limitations: a persistent misalignment between language instructions and action outputs, and the inherent inefficiency of typical auto-regressive action generation. In this paper, we introduce LinkVLA, a novel architecture that directly addresses these challenges to enhance both alignment and efficiency. First, we establish a structural link by unifying language and action tokens into a shared discrete codebook, processed within a single multi-modal model. This structurally enforces cross-modal consistency from the ground up. Second, to create a deep semantic link, we introduce an auxiliary action understanding objective that trains the model to generate descriptive captions from trajectories, fostering a bidirectional language-action mapping. Finally, we replace the slow, step-by-step generation with a two-step coarse-to-fine generation method C2F that efficiently decodes the action sequence, saving 86% inference time. Experiments on closed-loop driving benchmarks show consistent gains in instruction following accuracy and driving performance, alongside reduced inference latency. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_01441 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Unifying Language-Action Understanding and Generation for Autonomous Driving Wang, Xinyang Liu, Qian Ding, Wenjie Yang, Zhao Li, Wei Liu, Chang Li, Bailin Zhan, Kun Lang, Xianpeng Chen, Wei Computer Vision and Pattern Recognition Robotics Vision-Language-Action (VLA) models are emerging as a promising paradigm for end-to-end autonomous driving, valued for their potential to leverage world knowledge and reason about complex driving scenes. However, existing methods suffer from two critical limitations: a persistent misalignment between language instructions and action outputs, and the inherent inefficiency of typical auto-regressive action generation. In this paper, we introduce LinkVLA, a novel architecture that directly addresses these challenges to enhance both alignment and efficiency. First, we establish a structural link by unifying language and action tokens into a shared discrete codebook, processed within a single multi-modal model. This structurally enforces cross-modal consistency from the ground up. Second, to create a deep semantic link, we introduce an auxiliary action understanding objective that trains the model to generate descriptive captions from trajectories, fostering a bidirectional language-action mapping. Finally, we replace the slow, step-by-step generation with a two-step coarse-to-fine generation method C2F that efficiently decodes the action sequence, saving 86% inference time. Experiments on closed-loop driving benchmarks show consistent gains in instruction following accuracy and driving performance, alongside reduced inference latency. |
| title | Unifying Language-Action Understanding and Generation for Autonomous Driving |
| topic | Computer Vision and Pattern Recognition Robotics |
| url | https://arxiv.org/abs/2603.01441 |