While recent online HD mapping methods relieve burdened offline pipelines and solve map freshness, they remain limited by perceptual inaccuracies, occlusion in dense traffic, and an inability to fuse multi-agent observations. We propose RTMap to enhance these single-traversal methods by persistently crowdsourcing a multi-traversal HD map as a self-evolutional memory. On onboard agents, RTMap simultaneously addresses three core challenges in an end-to-end fashion: (1) Uncertainty-aware positional modeling for HD map elements, (2) probabilistic-aware localization w.r.t. the crowdsourced prior-map, and (3) real-time detection for possible road structural changes. Experiments on several public autonomous driving datasets demonstrate our solid performance on both the prior-aided map quality and the localization accuracy, demonstrating our effectiveness of robustly serving downstream prediction and planning modules while gradually improving the accuracy and freshness of the crowdsourced prior-map asynchronously. Our source-code will be made publicly available at https://github.com/CN-ADLab/RTMap.
@article{arxiv.2507.00980,
title = {RTMap: Real-Time Recursive Mapping with Change Detection and Localization},
author = {Yuheng Du and Sheng Yang and Lingxuan Wang and Zhenghua Hou and Chengying Cai and Zhitao Tan and Mingxia Chen and Shi-Sheng Huang and Qiang Li},
journal= {arXiv preprint arXiv:2507.00980},
year = {2025}
}