RLPR: Radar-to-LiDAR Place Recognition via Two-Stage Asymmetric Cross-Modal Alignment for Autonomous Driving

TL;DR

This paper introduces RLPR, a novel framework for radar-to-LiDAR place recognition that enhances robustness and generalization across diverse weather conditions and radar types, using a two-stage asymmetric alignment strategy.

Contribution

The work presents a dual-stream network and a two-stage asymmetric cross-modal alignment method to improve radar-to-LiDAR place recognition, addressing data scarcity and sensor heterogeneity.

Findings

Achieves state-of-the-art accuracy on four datasets.

Demonstrates strong zero-shot generalization capabilities.

Compatible with various radar types, including single-chip, scanning, and 4D radars.

Abstract

All-weather autonomy is critical for autonomous driving, which necessitates reliable localization across diverse scenarios. While LiDAR place recognition is widely deployed for this task, its performance degrades in adverse weather. Conversely, radar-based methods, though weather-resilient, are hindered by the general unavailability of radar maps. To bridge this gap, radar-to-LiDAR place recognition, which localizes radar scans within existing LiDAR maps, has garnered increasing interest. However, extracting discriminative and generalizable features shared between modalities remains challenging, compounded by the scarcity of large-scale paired training data and the signal heterogeneity across radar types. In this work, we propose RLPR, a robust radar-to-LiDAR place recognition framework compatible with single-chip, scanning, and 4D radars. We first design a dual-stream network to extract structural features that abstract away from sensor-specific signal properties (e.g., Doppler or RCS). Subsequently, motivated by our task-specific asymmetry observation between radar and LiDAR, we introduce a two-stage asymmetric cross-modal alignment (TACMA) strategy, which leverages the pre-trained radar branch as a discriminative anchor to guide the alignment process. Experiments on four datasets demonstrate that RLPR achieves state-of-the-art recognition accuracy with strong zero-shot generalization capabilities.