Driving by the Rules: A Benchmark for Integrating Traffic Sign Regulations into Vectorized HD Map

Abstract

Ensuring adherence to traffic sign regulations is essential for both human and autonomous vehicle navigation. While current online mapping solutions often prioritize the construction of the geometric and connectivity layers of HD maps, overlooking the construction of the traffic regulation layer within HD maps. Addressing this gap, we introduce MapDR, a novel dataset designed for the extraction of Driving Rules from traffic signs and their association with vectorized, locally perceived HD Maps. MapDR features over 10,000 annotated video clips that capture the intricate correlation between traffic sign regulations and lanes. Built upon this benchmark and the newly defined task of integrating traffic regulations into online HD maps, we provide modular and end-to-end solutions: VLE-MEE and RuleVLM, offering a strong baseline for advancing autonomous driving technology. It fills a critical gap in the integration of traffic sign rules, contributing to the development of reliable autonomous driving systems.

Task Definition

Overview of the sub-tasks. Step1 ~ Step4 shows a case of driving by the rules. Step2 and Step3 demonstrates the specific role of two sub-tasks, respectively.

The ability to discern rules from traffic signs and to associate them with specific lanes is pivotal for autonomous navigation. As depicted in Figure above, traffic signs are primary indicators of lane-level rules. Our proposed task involves two core sub-tasks: 1) Extracting lane-level rules from traffic signs, and 2) Establishing correspondence between these rules and centerlines. Generally, vehicles follow the center of lanes. Therefore, we use centerlines to represent lanes. This approach mirrors human drivers' instinct to observe traffic signs and then relate the indicated rules to the lanes they govern.

MapDR Dataset

Visualization of dataset demo. Multiple lane-level rules of a single traffic sign are annotated in {key:value} format. Directed lines indicate the correspondence between rules and particular centerlines.

Geographic location distribution of the collected traffic signs and proportions of various lane types represented in all signs. The geographic distribution is visualized based on OpenStreetMap.

Visualization of traffic signs. MapDR includes various types and layouts of traffic signs, which contain various driving rules. This presents challenges and necessity for accurately interpreting these traffic signs and associating them with the corresponding lanes.

Modular Approach

Overview of the modular approach. Entire approach can be divided into two main parts: Rule Extraction from Traffic Sign (top) and Correspondence Reasoning(bottom). Rule Extraction model consists of two sequential stages with the same structure VLE but unshared parameters, and the training procedure is independent.

End-to-End Approach

Overview of end-to-end approaches. Based on different vectorized HD maps encoding methods, approaches can be categorized into three types.

Baseline Experiment

Evaluation of the overall task. The heuristic method and the Qwen-VL(TextPrompt) method serve as the baselines for the modular and end-to-end approach, respectively. "-" denotes end-to-end approach is not suitable to independent evaluations of C.R. because these approaches do not utilize ground truth of rules for correspondence reasoning independently.

Citation

@misc{chang2025drivingrulesbenchmarkintegrating,
      title={Driving by the Rules: A Benchmark for Integrating Traffic Sign Regulations into Vectorized HD Map}, 
      author={Xinyuan Chang and Maixuan Xue and Xinran Liu and Zheng Pan and Xing Wei},
      year={2025},
      eprint={2410.23780},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2410.23780}
}