ResearcharXivNEW

SafeDriveVLA: Navigation-Conditioned World Model Dreaming for Conflict-Aware End-to-End Autonomous Driving

Xie 2026-10-14

Shaoyuan XieZihan ZhangJingxuan Wang

Vision-Language-Action (VLA) models are gaining attention in autonomous driving, inheriting commonsense priors from large language models (LLMs) and widening the navigation interface from a fixed command set to free-form natural-language instructions. However, this open-ended interface exposes a new vulnerability surface: an inattentive driver may issue instructions that are unsafe given the curre

Read on arXiv

Data aggregated and editorially reviewed by TrendMing.

Key Contributions

Vision-Language-Action (VLA) models are gaining attention in autonomous driving, inheriting commonsense priors from large language models (LLMs) and widening the navigation interface from a fixed command set to free-form natural-language instructions.
However, this open-ended interface exposes a new vulnerability surface: an inattentive driver may issue instructions that are unsafe given the curre

Research Themes

AIResearch

Back to AI Research