DriveCombo: Benchmarking Compositional Traffic Rule Reasoning in Autonomous Driving

• URL: http://arxiv.org/abs/2603.01637v1
• Date: Mon, 02 Mar 2026 09:12:40 GMT
• Title: DriveCombo: Benchmarking Compositional Traffic Rule Reasoning in Autonomous Driving
• Authors: Enhui Ma, Jiahuan Zhang, Guantian Zheng, Tao Tang, Shengbo Eben Li, Yuhang Lu, Xia Zhou, Xueyang Zhang, Yifei Zhan, Kun Zhan, Zhihui Hao, Xianpeng Lang, Kaicheng Yu,
• Abstract summary: 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.
• Score: 34.19974984127512
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multimodal Large Language Models (MLLMs) are rapidly becoming the intelligence brain of end-to-end autonomous driving systems. A key challenge is to assess whether MLLMs can truly understand and follow complex real-world traffic rules. However, existing benchmarks mainly focus on single-rule scenarios like traffic sign recognition, neglecting the complexity of multi-rule concurrency and conflicts in real driving. Consequently, models perform well on simple tasks but often fail or violate rules in real world complex situations. To bridge this gap, we propose DriveCombo, a text and vision-based benchmark for compositional traffic rule reasoning. Inspired by human drivers' cognitive development, we propose a systematic Five-Level Cognitive Ladder that evaluates reasoning from single-rule understanding to multi-rule integration and conflict resolution, enabling quantitative assessment across cognitive stages. We further propose a Rule2Scene Agent that maps language-based traffic rules to dynamic driving scenes through rule crafting and scene generation, enabling scene-level traffic rule visual reasoning. Evaluations of 14 mainstream MLLMs reveal performance drops as task complexity grows, particularly during rule conflicts. After splitting the dataset and fine-tuning on the training set, we further observe substantial improvements in both traffic rule reasoning and downstream planning capabilities. These results highlight the effectiveness of DriveCombo in advancing compliant and intelligent autonomous driving systems.

Related papers

• SGDrive: Scene-to-Goal Hierarchical World Cognition for Autonomous Driving [52.02379432801349]
  We propose SGDrive, a novel framework that structures the VLM's representation learning around driving-specific knowledge hierarchies.<n>Built upon a pre-trained VLM backbone, SGDrive decomposes driving understanding into a scene-agent-goal hierarchy that mirrors human driving cognition.
  arXiv  Detail & Related papers  (2026-01-09T08:55:42Z)
• LMAD: Integrated End-to-End Vision-Language Model for Explainable Autonomous Driving [58.535516533697425]
  Large vision-language models (VLMs) have shown promising capabilities in scene understanding.<n>We propose a novel vision-language framework tailored for autonomous driving, called LMAD.<n>Our framework emulates modern end-to-end driving paradigms by incorporating comprehensive scene understanding and a task-specialized structure with VLMs.
  arXiv  Detail & Related papers  (2025-08-17T15:42:54Z)
• ImagiDrive: A Unified Imagination-and-Planning Framework for Autonomous Driving [64.12414815634847]
  Vision-Language Models (VLMs) and Driving World Models (DWMs) have independently emerged as powerful recipes addressing different aspects of this challenge.<n>We propose ImagiDrive, a novel end-to-end autonomous driving framework that integrates a VLM-based driving agent with a DWM-based scene imaginer.
  arXiv  Detail & Related papers  (2025-08-15T12:06:55Z)
• 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)
• SafeAuto: Knowledge-Enhanced Safe Autonomous Driving with Multimodal Foundation Models [63.71984266104757]
  We propose SafeAuto, a framework that enhances MLLM-based autonomous driving by incorporating both unstructured and structured knowledge.<n>To explicitly integrate safety knowledge, we develop a reasoning component that translates traffic rules into first-order logic.<n>Our Multimodal Retrieval-Augmented Generation model leverages video, control signals, and environmental attributes to learn from past driving experiences.
  arXiv  Detail & Related papers  (2025-02-28T21:53:47Z)
• Sce2DriveX: A Generalized MLLM Framework for Scene-to-Drive Learning [24.511628941825116]
  We introduce Sce2DriveX, a human-like driving chain-of-thought (CoT) reasoning framework framework.<n>It reconstructs the implicit cognitive chain inherent in human driving, covering scene understanding, meta-action reasoning, behavior interpretation analysis, motion planning and control.<n>It achieves state-of-the-art performance from scene understanding to end-to-end driving, as well as robust generalization on the CARLA Bench2Drive benchmark.
  arXiv  Detail & Related papers  (2025-02-19T09:50:44Z)
• A Framework for Learning Scoring Rules in Autonomous Driving Planning Systems [2.4578723416255754]
  FLoRA is a framework that learns interpretable scoring rules represented in temporal logic.<n>Our approach effectively learns to evaluate driving behavior even though the training data only contains positive examples.<n> Evaluations in closed-loop planning simulations demonstrate that our learned scoring rules outperform existing techniques.
  arXiv  Detail & Related papers  (2025-02-17T02:06:57Z)
• On the Road with GPT-4V(ision): Early Explorations of Visual-Language Model on Autonomous Driving [37.617793990547625]
  This report provides an exhaustive evaluation of the latest state-of-the-art VLM, GPT-4V. We explore the model's abilities to understand and reason about driving scenes, make decisions, and ultimately act in the capacity of a driver. Our findings reveal that GPT-4V demonstrates superior performance in scene understanding and causal reasoning compared to existing autonomous systems.
  arXiv  Detail & Related papers  (2023-11-09T12:58:37Z)
• LanguageMPC: Large Language Models as Decision Makers for Autonomous Driving [84.31119464141631]
  This work employs Large Language Models (LLMs) as a decision-making component for complex autonomous driving scenarios.<n>Extensive experiments demonstrate that our proposed method not only consistently surpasses baseline approaches in single-vehicle tasks, but also helps handle complex driving behaviors even multi-vehicle coordination.
  arXiv  Detail & Related papers  (2023-10-04T17:59:49Z)
• 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.