Reasoning to Regulate: Chain-of-Thought for Traffic Rule Understanding

ICLR 2026 Conference Submission12671 Authors

Keywords: Autonomous Driving, Driving Rule Understanding, Traffic Scene CoT, Driving Scene Topology Reasoning

TL;DR: We enhance traffic rule understanding using CoT‑generated reasoning for SFT followed by RFT with designed rewards for improved rule-to-lane understanding.

Abstract:

Understanding and complying with traffic regulations is a safety-critical requirement for autonomous driving, yet remains challenging due to the diversity and context dependence of traffic signage. Importantly, regulation understanding is not a simple recognition task, but a reasoning problem: whether a rule applies depends on interpreting the sign in relation to the spatial layout of lanes and scene context.
To support such reasoning, MapDR provide fine-grained annotations that link each traffic sign’s regulatory rules to the specific lanes they govern. Existing methods, however, largely treat this as direct sequence prediction, ignoring the underlying reasoning that connects sign semantics and map structure.
To address this limitation, we explicitly incorporate reasoning into this task and propose a framework that equips vision-language models (VLMs) with chain-of-thought (CoT) capabilities. We first design a scalable CoT curation pipeline that bootstraps rationales from a strong LLM through a two-round strategy and employs a VLM-based verifier to filter out incorrect cases, yielding a high-quality set of (CoT, answer) pairs. Building on this foundation, we adopt a two-stage training scheme: supervised fine-tuning (SFT) to teach rationale-to-answer generation, followed by GRPO reinforcement learning with answer-grounded, fine-grained rewards to further improve final answer accuracy.
Extensive experiments on MapDR show that our approach significantly improves both interpretability and accuracy, establishing the first reasoning-based framework for regulation-aware autonomous driving.

Primary Area: applications to robotics, autonomy, planning

Submission Number: 12671