RTMap: Real-Time Recursive Mapping with Change Detection and Localization

2025-07-01

AI Summary

Existing online high-definition (HD) mapping methods suffer from limited perception accuracy, poor performance under dense occlusions, and inadequate multi-agent collaborative mapping. To address these limitations, this paper proposes an end-to-end real-time HD mapping framework. Its core innovation is a self-evolving map memory mechanism that jointly achieves robust localization, dynamic mapping, and real-time change detection through uncertainty-aware modeling, probabilistic pose matching, and asynchronous multi-agent observation fusion. Furthermore, crowd-sourced prior maps are incorporated to guide online optimization, enabling synchronized updates for dynamic road changes. Extensive experiments on multiple autonomous driving datasets demonstrate significant improvements in geometric map accuracy and localization stability. Consequently, the reliability of downstream prediction and planning modules is substantially enhanced.

Technology Category

• Intelligent Robots: Localization, Mapping, and Navigation
• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Search and Optimization: Learning to Search

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI

Abstract

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 (Camera ready version incorporating reviewer suggestions will be updated soon).

Problem

• Enhance single-traversal HD mapping with multi-agent crowdsourcing
• Address uncertainty in HD map elements and localization
• Detect real-time road structural changes for map freshness

Innovation

• Real-time recursive mapping with change detection
• Uncertainty-aware HD map element modeling
• Probabilistic localization with crowdsourced prior-map