DriveMA: Driving Vision-Language-Action Models with verifiable Meta-Actions
Driving Vision-Language-Action Models (Driving VLAs) aim to use language to improve end-to-end planning, but the language-action gap limits this promise. We propose DriveMA, a Driving VLA framework built on verifiable meta-actions, which summarize future ego motion into compact language-domain intentions and can be constructed from expert trajectories with a trajectory-grounded annotation pipeline and can be verified against generated trajectories through rule-based projection. DriveMA exploits this verifiability with action-centric supervised training and a data-efficient turn-level credit assignment reinforcement learning framework, explicitly aligning high-level decisions with low-leve...
| Authors | Weicheng Zheng, Yixin Huang, Qiao Sun et al. |
|---|---|
| Primary category | cs.CV |
| Published | 29 May 2026 |
| Last updated at source | 10 July 2026 |
Models and datasets referencing this paper
- zwc2003/DriveMA-2BModel
- Mike087/Language2DriveDataset
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.