SNAIL Radar: A large-scale diverse benchmark for evaluating 4D-radar-based SLAM

TL;DR

This paper introduces a large-scale, diverse dataset for 4D radar-based SLAM, collected across multiple platforms and environmental conditions, to advance research in autonomous localization and mapping.

Contribution

The paper presents a comprehensive, multi-platform dataset for 4D radar SLAM, including synchronized sensor data and a new reference motion generation method, filling a gap in existing datasets.

Findings

Existing radar SLAM methods face significant challenges in diverse environments.

The dataset enables evaluation of radar-based odometry and place recognition.

Baseline assessments highlight areas for future improvement in radar SLAM.

Abstract

4D radars are increasingly favored for odometry and mapping of autonomous systems due to their robustness in harsh weather and dynamic environments. Existing datasets, however, often cover limited areas and are typically captured using a single platform. To address this gap, we present a diverse large-scale dataset specifically designed for 4D radar-based localization and mapping. This dataset was gathered using three different platforms: a handheld device, an e-bike, and an SUV, under a variety of environmental conditions, including clear days, nighttime, and heavy rain. The data collection occurred from September 2023 to February 2024, encompassing diverse settings such as roads in a vegetated campus and tunnels on highways. Each route was traversed multiple times to facilitate place recognition evaluations. The sensor suite included a 3D lidar, 4D radars, stereo cameras, consumer-grade IMUs, and a GNSS/INS system. Sensor data packets were synchronized to GNSS time using a two-step process including a convex-hull-based smoothing and a correlation-based correction. The reference motion for the platforms was generated by registering lidar scans to a terrestrial laser scanner (TLS) point cloud map by a lidar inertial sequential localizer which supports forward and backward processing. The backward pass enables detailed quantitative and qualitative assessments of reference motion accuracy. To demonstrate the dataset's utility, we evaluated several state-of-the-art radar-based odometry and place recognition methods, indicating existing challenges in radar-based SLAM.