MapATM: Enhancing HD Map Construction through Actor Trajectory Modeling

2026-04-13

AI Summary

This work addresses the significant degradation in accuracy and robustness of high-definition (HD) map lane detection under non-ideal conditions such as occlusion, long-range scenarios, and adverse weather. To mitigate this challenge, we propose MapATM, a novel deep neural network that, for the first time, incorporates historical vehicle trajectories as geometric priors into HD map construction. By deeply integrating trajectory modeling with lane detection, MapATM enhances reconstruction performance in complex environments. Experimental results on the NuScenes dataset demonstrate that our method improves the average precision (AP) of lane dividers by 4.6 points (a relative gain of 10.1%) and boosts mean AP (mAP) by 2.6 points (a relative increase of 6.1%), substantially advancing the accuracy and stability of map reconstruction.

Technology Category

• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Search and Optimization: Learning to Search
• Machine Learning: Feature Construction/Reformulation

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

High-definition (HD) mapping tasks, which perform lane detections and predictions, are extremely challenging due to non-ideal conditions such as view occlusions, distant lane visibility, and adverse weather conditions. Those conditions often result in compromised lane detection accuracy and reduced reliability within autonomous driving systems. To address these challenges, we introduce MapATM, a novel deep neural network that effectively leverages historical actor trajectory information to improve lane detection accuracy, where actors refer to moving vehicles. By utilizing actor trajectories as structural priors for road geometry, MapATM achieves substantial performance enhancements, notably increasing AP by 4.6 for lane dividers and mAP by 2.6 on the challenging NuScenes dataset, representing relative improvements of 10.1% and 6.1%, respectively, compared to strong baseline methods. Extensive qualitative evaluations further demonstrate MapATM's capability to consistently maintain stable and robust map reconstruction across diverse and complex driving scenarios, underscoring its practical value for autonomous driving applications.

Problem

• HD map construction
• lane detection
• view occlusions
• adverse weather conditions
• autonomous driving

Innovation

• actor trajectory modeling
• HD map construction
• structural prior
• lane detection
• autonomous driving