arXiv AI
Grounding What Shapes the Plan: Rethinking Groundedness for Physical Intelligence in Autonomous Driving
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Computer Vision
Sep 15
GRAVA: Grounded Reasoning-to-Action Representation and Learning for Autonomous Driving
arXiv:2609.15169v1 Announce Type: new Abstract: Driving vision-language-action (VLA) models increasingly reason before acting, but their intermediate reasoning is often weakly grounded in physical sc...
arXiv Computation and Language
Sep 3
Beyond Textual Chain-of-Thought: A Survey on Action-Grounded Reasoning in Autonomous Driving
The paper surveys the transition from textual chain-of-thought reasoning to action-grounded reasoning in autonomous driving, highlighting that driving decisions require continuous actions that mirror the spatiotemporal structure of the physical world. It reviews 171 papers, categorizing 130 methods into four main types—language-based, visual-spatial, latent-dynamic, and externalized reasoning—along with 13 subtypes linked to specific regions of interest. The authors argue that the future of driving agent reasoning lies in intermediate representations that are grounded in reality, linked to real-time actions, and verifiable within safety-critical systems.
arXiv AI
Jun 24
Neuro-Symbolic Drive: Rule-Grounded Faithful Reasoning for Driving VLAs
arXiv:2606. 23938v1 Announce Type: new Abstract: Driving VLA models incorporating Chain-of-Thought (CoT) reasoning are attractive because they leverage pretrained VLM representations and expose intermediate decisions in natural language, yet current rationales often lack the step-by-step decision semantics needed to keep the rationale causally connected to the planned motion.
arXiv AI
Sep 24
AnchorReasoning: A Visual Grounding and Causal Reasoning Dataset in Long-Tail Autonomous Driving Scenarios
arXiv:2609. 28366v1 Announce Type: cross Abstract: Vision-language models (VLMs) offer a promising approach to long-tail autonomous driving, but existing driving datasets provide limited supervision for connecting decision-critical visual evidence with reasoning and planning.
arXiv Computer Vision
Aug 31
Reasoning models do not yet follow their reasoning in autonomous driving: The KITScenes LongTail Dataset
The paper introduces the KITScenes LongTail dataset, a curated collection of rare driving scenarios designed to evaluate how well reasoning models in autonomous driving follow their own reasoning. The authors find that many current models frequently diverge between the actions they state in their reasoning chains and the actions they actually execute, a phenomenon they term incoherence. They show that when the reasoning and execution disagree, the reasoning is often correct, and enforcing coherence via a kinematic model can improve motion planning, indicating that coherent action based on stated reasoning is essential for trustworthy autonomous driving.
arXiv Computer Vision
Oct 8
Explicit Geometric Chain-of-Thought for Vision-Language-Action in Autonomous Driving
arXiv:2610.10390v1 Announce Type: new Abstract: Vision-language-action~(VLA) models have emerged as a promising paradigm for autonomous driving. However, existing VLA models still suffer from a funda...