Efficient and Explainable End-to-End Autonomous Driving via Masked Vision-Language-Action Diffusion
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917291040440320 |
|---|---|
| author | Zhang, Jiaru Gagvani, Manav Cui, Can Peng, Juntong Zhang, Ruqi Wang, Ziran |
| author_facet | Zhang, Jiaru Gagvani, Manav Cui, Can Peng, Juntong Zhang, Ruqi Wang, Ziran |
| contents | Large Language Models (LLMs) and Vision-Language Models (VLMs) have emerged as promising candidates for end-to-end autonomous driving. However, these models typically face challenges in inference latency, action precision, and explainability. Existing autoregressive approaches struggle with slow token-by-token generation, while prior diffusion-based planners often rely on verbose, general-purpose language tokens that lack explicit geometric structure. In this work, we propose Masked Vision-Language-Action Diffusion for Autonomous Driving (MVLAD-AD), a novel framework designed to bridge the gap between efficient planning and semantic explainability via a masked vision-language-action diffusion model. Unlike methods that force actions into the language space, we introduce a discrete action tokenization strategy that constructs a compact codebook of kinematically feasible waypoints from real-world driving distributions. Moreover, we propose geometry-aware embedding learning to ensure that embeddings in the latent space approximate physical geometric metrics. Finally, an action-priority decoding strategy is introduced to prioritize trajectory generation. Extensive experiments on nuScenes and derived benchmarks demonstrate that MVLAD-AD achieves superior efficiency and outperforms state-of-the-art autoregressive and diffusion baselines in planning precision, while providing high-fidelity and explainable reasoning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_20577 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Efficient and Explainable End-to-End Autonomous Driving via Masked Vision-Language-Action Diffusion Zhang, Jiaru Gagvani, Manav Cui, Can Peng, Juntong Zhang, Ruqi Wang, Ziran Computer Vision and Pattern Recognition Large Language Models (LLMs) and Vision-Language Models (VLMs) have emerged as promising candidates for end-to-end autonomous driving. However, these models typically face challenges in inference latency, action precision, and explainability. Existing autoregressive approaches struggle with slow token-by-token generation, while prior diffusion-based planners often rely on verbose, general-purpose language tokens that lack explicit geometric structure. In this work, we propose Masked Vision-Language-Action Diffusion for Autonomous Driving (MVLAD-AD), a novel framework designed to bridge the gap between efficient planning and semantic explainability via a masked vision-language-action diffusion model. Unlike methods that force actions into the language space, we introduce a discrete action tokenization strategy that constructs a compact codebook of kinematically feasible waypoints from real-world driving distributions. Moreover, we propose geometry-aware embedding learning to ensure that embeddings in the latent space approximate physical geometric metrics. Finally, an action-priority decoding strategy is introduced to prioritize trajectory generation. Extensive experiments on nuScenes and derived benchmarks demonstrate that MVLAD-AD achieves superior efficiency and outperforms state-of-the-art autoregressive and diffusion baselines in planning precision, while providing high-fidelity and explainable reasoning. |
| title | Efficient and Explainable End-to-End Autonomous Driving via Masked Vision-Language-Action Diffusion |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2602.20577 |