ReRadar: Robust Radar Global Localization via Rotation-Equivariant Descriptor Learning

2026-09-15

AI Summary

研究解决了雷达全局定位问题，通过旋转等变描述符学习方法提高位置识别准确性。

Abstract

Global localization with scanning millimeter-wave radar remains challenging because place-recognition descriptors often discard spatial structure needed for accurate pose retrieval. We present ReRadar, a radar global localization pipeline that extracts rotation-equivariant intermediate features using steerable convolutional neural networks, forms rotation-invariant descriptors through group pooling and NetVLAD aggregation, and combines descriptor retrieval with landmark-based matching to estimate the robot's three-degree-of-freedom (3-DoF) pose. Across fixed database-query evaluations, ReRadar with target-dataset adaptation achieves 99.37% Recall@1 on OORD Bellmouth, 91.44% Recall@1 with 80.99% F1_max on Mulran DCC01, and 99.38% Recall@1 on falling-snow Boreas sequence. Without target-dataset data, the cross-dataset model reaches 98.07% Recall@1 on OORD, performing comparably to the evaluated state-of-the-art methods.

Problem

• global localization
• millimeter-wave radar
• place recognition
• spatial structure
• pose retrieval

Innovation

• rotation-equivariant descriptor
• steerable convolutional neural networks
• group pooling
• NetVLAD aggregation
• 3-DoF pose