MapAgent：一种面向城市级车道级地图生成的工业级智能体框架

摘要

车道级地图是自动驾驶和车道级导航的关键基础设施，然而为数百个城市构建并维护标准化车道网络仍高度依赖人力。近年来，端到端矢量化制图方法能够直接从传感器数据预测车道几何结构和拓扑关系，但这些方法通常将制图规范与交通规则视为隐含的、依赖数据集的监督信息。此外，在复杂场景（如标线磨损、缺失或被遮挡）中，仅凭视觉证据往往难以确定正确的车道配置，导致规范违例成为人工后期编辑的主要来源。我们提出MapAgent，一种工业级智能体架构，通过增强矢量化主干网络实现符合规范的车道地图生产。MapAgent并非简单地在地图预测中加入智能体循环，而是将主干感知与显式规范验证、约束感知推理以及确定性地图编辑相结合，形成受边界约束且由验证驱动的"裁判-规划器-执行器"循环。其中，视觉语言裁判通过联合检查视觉证据与草稿矢量来诊断错误，而调用工具的执行器则生成最小化修正编辑并进行编辑后重新验证。为实现面向城市规模生产的可扩展性，MapAgent仅在主干网络置信度较低的图块上选择性触发，在保持吞吐量的同时增加适度开销。在真实数据集上的实验表明，该方案在强生产基线基础上持续提升性能，尤其在复杂场景和长尾场景中效果显著。此外，MapAgent已集成至百度地图，支持全国360余个城市的路网级地图生成，并将整体生产自动化率提升至95%以上，充分验证了其在大规模车道级地图生成中的实用性与有效性。

English

Lane-level maps are critical infrastructure for autonomous driving and lane-level navigation, yet constructing and maintaining standardized lane networks for hundreds of cities remains highly labor-intensive. Recent end-to-end vectorized mapping methods can predict lane geometry and topology directly from sensor data, but they typically treat mapping specifications and traffic regulations as implicit, dataset-dependent supervision. Moreover, in complex scenes (e.g., worn or missing markings and occlusions), correct lane configurations are often under-determined by visual evidence alone, making specification violations a major source of human post-editing. We propose MapAgent, an industrial-grade agentic architecture that augments a vectorization backbone for specification-compliant lane-map production. Rather than merely adding an agent loop to map prediction, MapAgent couples backbone perception with explicit specification verification, constraint-aware reasoning, and deterministic map editing under a bounded, verification-driven Judge-Planner-Worker loop. A vision-language Judge diagnoses errors by jointly inspecting visual evidence and draft vectors, while a tool-calling Planner generates minimal corrective edits with post-edit re-validation. To remain scalable for city-scale production, MapAgent is selectively triggered only on tiles with low backbone confidence, adding modest overhead while preserving throughput. Experiments on real-world datasets show consistent gains over strong production baselines, especially in complex and long-tail scenarios. Additionally, MapAgent has been integrated into Baidu Maps, supporting lane-level map generation for over 360 cities nationwide and elevating the overall production automation to over 95%, demonstrating MapAgent's practicality and effectiveness for large-scale lane-level map generation.