MapATM: Enhancing HD Map Construction through Actor Trajectory Modeling

TL;DR

MapATM is a deep neural network that uses historical actor trajectories to improve HD map construction, significantly enhancing lane detection accuracy under challenging conditions.

Contribution

Introduces MapATM, a novel approach leveraging actor trajectory data as structural priors to boost HD map accuracy in autonomous driving.

Findings

Increases AP by 4.6 for lane dividers on NuScenes dataset.

Achieves a 2.6 mAP improvement, a 6.1% relative gain.

Demonstrates stable map reconstruction across complex scenarios.

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.