MapAgent: An Industrial-Grade Agentic Framework for City-scale Lane-level Map Generation
2026-06-03 • Artificial Intelligence
Artificial Intelligence
AI summaryⓘ
The authors developed MapAgent, a system that improves how lane-level maps for self-driving cars are made. Instead of just relying on visual data, MapAgent checks the map against traffic rules and known standards to fix mistakes automatically. It focuses on tricky map areas where it's hard to tell lanes clearly and only works when needed to keep things fast. Their tests showed it works better than current methods and it is now used in Baidu Maps for over 360 cities, making map production mostly automated.
lane-level mapsautonomous drivingvectorized mappingmap topologytraffic regulationsconstraint-aware reasoningvision-language modelsagent architecturemap editingBaidu Maps
Authors
Deguo Xia, Zihan Li, Haochen Zhao, Dong Xie, Yuyao Kong, Xiyan Liu, Jizhou Huang, Mengmeng Yang, Diange Yang
Abstract
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.