SHeRLoc: Synchronized Heterogeneous Radar Place Recognition for Cross-Modal Localization

TL;DR

SHeRLoc is a deep learning framework that enables cross-modal place recognition using heterogeneous radar data, significantly improving recognition accuracy and robustness across diverse radar types and modalities.

Contribution

It introduces the first deep network designed for heterogeneous radar, utilizing RCS polar matching, hierarchical feature aggregation, and metric learning for robust cross-modal localization.

Findings

Achieves order of magnitude improvement in place recognition accuracy.

Increases recall@1 from below 0.1 to 0.9 on a public dataset.

Outperforms existing state-of-the-art methods.

Abstract

Despite the growing adoption of radar in robotics, the majority of research has been confined to homogeneous sensor types, overlooking the integration and cross-modality challenges inherent in heterogeneous radar technologies. This leads to significant difficulties in generalizing across diverse radar data types, with modality-aware approaches that could leverage the complementary strengths of heterogeneous radar remaining unexplored. To bridge these gaps, we propose SHeRLoc, the first deep network tailored for heterogeneous radar, which utilizes RCS polar matching to align multimodal radar data. Our hierarchical optimal transport-based feature aggregation method generates rotationally robust multi-scale descriptors. By employing FFT-similarity-based data mining and adaptive margin-based triplet loss, SHeRLoc enables FOV-aware metric learning. SHeRLoc achieves an order of magnitude improvement in heterogeneous radar place recognition, increasing recall@1 from below 0.1 to 0.9 on a public dataset and outperforming state of-the-art methods. Also applicable to LiDAR, SHeRLoc paves the way for cross-modal place recognition and heterogeneous sensor SLAM. The supplementary materials and source code are available at https://sites.google.com/view/radar-sherloc.