RAVE:基于栅格化与矢量化高精地图的端到端分层视觉定位
RAVE: End-to-end Hierarchical Visual Localization with Rasterized and Vectorized HD map
AI总结:
本文提出端到端视觉定位系统 RAVE,通过 FLORA 融合地图先验与 BEV 特征,并采用 DEMA 和 POET 分层利用栅格化与矢量化高精地图,实现高效、鲁棒且可解释的精确位姿估计。
摘要:
精确定位是自动驾驶系统中的重要组成部分。传统的基于规则的定位涉及许多独立模块,理论上较为脆弱,且需要昂贵的超参数调优,因此牺牲了精度和泛化能力。本文提出了一种端到端视觉定位系统 RAVE,该系统将周围图像与高精地图数据关联以估计位姿。为确保定位所需的高质量观测,开发了一种基于低秩流的先验融合模块 FLORA,用于将未对齐的地图先验融入感知到的 BEV 特征中。为在效率、可解释性和精度之间取得平衡,提出了一种分层定位模块,该模块首先通过基于解耦 BEV 神经匹配的位姿求解器 DEMA,利用栅格化高精地图高效估计位姿,然后通过基于 Transformer 的位姿回归器 POET,利用矢量化高精地图对估计结果进行细化。实验结果表明,该方法能够在不同环境条件下实现鲁棒且精确的定位,同时保持高效运行。
英文摘要:
Accurate localization serves as an important component in autonomous driving systems. Traditional rule-based localization involves many standalone modules, which is theoretically fragile and requires costly hyperparameter tuning, therefore sacrificing the accuracy and generalization. In this paper, we propose an end-to-end visual localization system, RAVE, in which the surrounding images are associated with the HD map data to estimate pose. To ensure high-quality observations for localization, a low-rank flow-based prior fusion module (FLORA) is developed to incorporate misaligned map prior into the perceived BEV features. Pursuing a balance among efficiency, interpretability, and accuracy, a hierarchical localization module is proposed, which efficiently estimates poses through a decoupled BEV neural matching-based pose solver (DEMA) using rasterized HD map, and then refines the estimation through a Transformer-based pose regressor (POET) using vectorized HD map. The experimental results demonstrate that our method can perform robust and accurate localization under varying environmental conditions while running efficiently.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。