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

• URL: http://arxiv.org/abs/2607.24199v1
• Date: Mon, 27 Jul 2026 09:24:41 GMT
• Title: Reasoning to Regulate: Chain-of-Thought for Traffic Rule Understanding
• Abstract summary: MapDR provides fine-grained annotations that link each traffic sign's regulatory rules to the specific lanes they govern.<n>Existing methods, however, largely treat this as direct sequence prediction.<n>We propose a framework that equips vision-language models with chain-of-thought capabilities.
• Score: 43.741376405232295
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Enhancing Multimodal In-Context Learning via Inductive-Deductive Reasoning [65.15766304205657]
  In-context learning (ICL) allows large models to adapt to tasks using a few examples, yet its extension to vision-language models (VLMs) remains fragile.<n>Our analysis reveals that the fundamental limitation lies in an inductive gap, models often produce correct answers from flawed reasoning.<n>We introduce a framework that restructures multimodal ICL as a principled inductive-deductive process.
  arXiv  Detail & Related papers  (2026-05-04T09:18:19Z)
• Reinforcing Structured Chain-of-Thought for Video Understanding [49.3086326382764]
  We introduce Summary-Driven Reinforcement Learning (SDRL)<n>SDRL is a single-stage RL framework that obviates the need forSupervised Fine-Tuning (SFT)<n>Our method achieves state-of-the-art performance on seven public VideoQA datasets.
  arXiv  Detail & Related papers  (2026-03-26T22:11:14Z)
• A Progressive Visual-Logic-Aligned Framework for Ride-Hailing Adjudication [19.51385161254594]
  RideJudge is a Progressive Visual-Logic-Aligned Framework to bridge the gap between general visual semantics and rigorous evidentiary protocols.<n>Our framework achieves 88.41% accuracy, surpassing 32B-scale baselines and establishing a new standard for interpretable adjudication.
  arXiv  Detail & Related papers  (2026-03-18T03:46:30Z)
• DriveCombo: Benchmarking Compositional Traffic Rule Reasoning in Autonomous Driving [34.19974984127512]
  We present DriveCombo, a text-based benchmark for compositional traffic rule reasoning.<n>Inspired by human drivers' cognitive development, we propose a systematic Five-Level Cognitive Ladder.<n>We also propose a Rule2Scene Agent that maps language-based traffic rules to dynamic driving scenes.
  arXiv  Detail & Related papers  (2026-03-02T09:12:40Z)
• ReAL-AD: Towards Human-Like Reasoning in End-to-End Autonomous Driving [27.75047397292818]
  End-to-end autonomous driving has emerged as a promising approach to unify perception, prediction, and planning within a single framework.<n>We propose ReAL-AD, a Reasoning-Augmented Learning framework that structures decision-making in autonomous driving based on the three-tier human cognitive model.<n>We show that integrating our framework improves planning accuracy and safety by over 30%, making end-to-end autonomous driving more interpretable and aligned with human-like hierarchical reasoning.
  arXiv  Detail & Related papers  (2025-07-16T02:23:24Z)
• RelTopo: Multi-Level Relational Modeling for Driving Scene Topology Reasoning [74.58385332488227]
  Road topology reasoning is critical for autonomous driving, enabling effective navigation and adherence to traffic regulations.<n>Existing methods typically focus on either lane detection or Lane-to-Lane (L2L) topology reasoning, often textitneglecting Lane-to-Traffic-element (L2T) relationships to optimize these tasks jointly.<n>We argue that relational modeling is beneficial for both perception and reasoning, as humans naturally leverage contextual relationships for road element recognition and their connectivity inference.
  arXiv  Detail & Related papers  (2025-06-16T14:40:28Z)
• Predictive Traffic Rule Compliance using Reinforcement Learning [7.280087547993983]
  This paper presents an approach that integrates a motion planner with a deep reinforcement learning model to predict potential traffic rule violations.<n>Our main innovation is replacing the standard actor network in an actor-critic method with a motion planning module, which ensures both stable and interpretable trajectory generation.<n> Experiments on an open German highway dataset show that the model can predict and prevent traffic rule violations beyond the planning horizon.
  arXiv  Detail & Related papers  (2025-03-29T01:04:08Z)
• Deliberative Alignment: Reasoning Enables Safer Language Models [64.60765108418062]
  We introduce Deliberative Alignment, a new paradigm that teaches the model safety specifications and trains it to explicitly recall and accurately reason over the specifications before answering.<n>We used this approach to align OpenAI's o-series models, and achieved highly precise adherence to OpenAI's safety policies, without requiring human-written chain-of-thoughts or answers.
  arXiv  Detail & Related papers  (2024-12-20T21:00:11Z)
• Driving by the Rules: A Benchmark for Integrating Traffic Sign Regulations into Vectorized HD Map [15.57801519192153]
  We introduce MapDR, a dataset designed for the extraction of Driving Rules from traffic signs.<n>MapDR features over $10,000$ annotated video clips that capture the intricate correlation between traffic sign regulations and lanes.<n>It fills a critical gap in the integration of traffic sign rules, contributing to the development of reliable autonomous driving systems.
  arXiv  Detail & Related papers  (2024-10-31T09:53:21Z)
• Driving with Regulation: Interpretable Decision-Making for Autonomous Vehicles with Retrieval-Augmented Reasoning via LLM [11.725133614445093]
  This work presents an interpretable decision-making framework for autonomous vehicles.<n>We develop a Traffic Regulation Retrieval (TRR) Agent based on Retrieval-Augmented Generation (RAG)<n>Given the semantic complexity of the retrieved rules, we also design a reasoning module powered by a Large Language Model (LLM)
  arXiv  Detail & Related papers  (2024-10-07T05:27:22Z)
• End-to-End Intersection Handling using Multi-Agent Deep Reinforcement Learning [63.56464608571663]
  Navigating through intersections is one of the main challenging tasks for an autonomous vehicle. In this work, we focus on the implementation of a system able to navigate through intersections where only traffic signs are provided. We propose a multi-agent system using a continuous, model-free Deep Reinforcement Learning algorithm used to train a neural network for predicting both the acceleration and the steering angle at each time step.
  arXiv  Detail & Related papers  (2021-04-28T07:54:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.