SOURCE-LINKED INTELLIGENCE

GRAVA: Grounded Reasoning-to-Action Representation and Learning for Autonomous Driving

arXiv · AI, language, vision and robotics · article · Sep 14, 2026 · UTC

Driving vision-language-action (VLA) models increasingly reason before acting, but their intermediate reasoning is often weakly grounded in physical scene evidence and loosely connected to executable behavior. We present GRAVA, a framework built around Grounded Reasoning-to-Action (GRA), which unifies grounding, reasoning, and action generation in a single autoregressive stream. GRA links action-relevant language references to 2D visual regions and ego-centric physical states, organizes object interactions and decisions in a trajectory-anchored typed graph, and serializes this structure into g

Read original source ↗ Open in workspace

recordType

paper

region

Global