ArgoTweak: Towards Self-Updating HD Maps through Structured Priors

2025-09-10

AI Summary

Existing HD map self-updating methods are hindered by the absence of real-world “sensor data–current map–ground-truth prior map” triplets in public benchmarks, forcing reliance on synthetic priors and resulting in substantial sim-to-real gaps and poor interpretability. To address this, we introduce the first publicly available HD map updating dataset featuring *real*, structured prior maps. We propose a bijective mapping framework that decomposes large-scale map changes into atomic-level element modifications, enabling precise change modeling. Our framework includes fine-grained annotations, a dedicated change detection and fusion algorithm, and an integrated editing toolkit. Experiments demonstrate significant improvements in change detection accuracy and real-world generalizability, substantially narrowing the sim-to-real performance gap. This work establishes the first interpretable, extensible, and continuously optimizable benchmark for autonomous HD map updating.

Technology Category

• Planning, Routing, and Scheduling: Activity and Plan Recognition
• Intelligent Robots: Localization, Mapping, and Navigation
• Computer Vision: Visual Reasoning & Symbolic Representations

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies

Abstract

Reliable integration of prior information is crucial for self-verifying and self-updating HD maps. However, no public dataset includes the required triplet of prior maps, current maps, and sensor data. As a result, existing methods must rely on synthetic priors, which create inconsistencies and lead to a significant sim2real gap. To address this, we introduce ArgoTweak, the first dataset to complete the triplet with realistic map priors. At its core, ArgoTweak employs a bijective mapping framework, breaking down large-scale modifications into fine-grained atomic changes at the map element level, thus ensuring interpretability. This paradigm shift enables accurate change detection and integration while preserving unchanged elements with high fidelity. Experiments show that training models on ArgoTweak significantly reduces the sim2real gap compared to synthetic priors. Extensive ablations further highlight the impact of structured priors and detailed change annotations. By establishing a benchmark for explainable, prior-aided HD mapping, ArgoTweak advances scalable, self-improving mapping solutions. The dataset, baselines, map modification toolbox, and further resources are available at https://kth-rpl.github.io/ArgoTweak/.

Problem

• Addressing lack of real prior maps for self-updating HD maps
• Providing realistic map priors to reduce sim2real performance gap
• Enabling interpretable change detection through structured atomic modifications

Innovation

• Bijective mapping framework for atomic map element changes
• Realistic map priors dataset completing required information triplet
• Structured priors enabling explainable self-updating HD mapping