NTU4DRadLM: 4D Radar-centric Multi-Modal Dataset for Localization and Mapping

TL;DR

NTU4DRadLM is a comprehensive multi-modal dataset designed for SLAM research, featuring six sensors, diverse environments, and detailed ground truth, addressing the lack of suitable datasets for radar-based SLAM in adverse conditions.

Contribution

This paper introduces NTU4DRadLM, the first dataset combining 4D radar, thermal camera, IMU, LiDAR, visual camera, and GPS specifically for SLAM, with extensive ground truth and varied environments.

Findings

Evaluated three SLAM algorithms using the dataset.

Demonstrated robustness of radar-based SLAM in adverse conditions.

Provided detailed ground truth for diverse outdoor environments.

Abstract

Simultaneous Localization and Mapping (SLAM) is moving towards a robust perception age. However, LiDAR- and visual- SLAM may easily fail in adverse conditions (rain, snow, smoke and fog, etc.). In comparison, SLAM based on 4D Radar, thermal camera and IMU can work robustly. But only a few literature can be found. A major reason is the lack of related datasets, which seriously hinders the research. Even though some datasets are proposed based on 4D radar in past four years, they are mainly designed for object detection, rather than SLAM. Furthermore, they normally do not include thermal camera. Therefore, in this paper, NTU4DRadLM is presented to meet this requirement. The main characteristics are: 1) It is the only dataset that simultaneously includes all 6 sensors: 4D radar, thermal camera, IMU, 3D LiDAR, visual camera and RTK GPS. 2) Specifically designed for SLAM tasks, which provides fine-tuned ground truth odometry and intentionally formulated loop closures. 3) Considered both low-speed robot platform and fast-speed unmanned vehicle platform. 4) Covered structured, unstructured and semi-structured environments. 5) Considered both middle- and large- scale outdoor environments, i.e., the 6 trajectories range from 246m to 6.95km. 6) Comprehensively evaluated three types of SLAM algorithms. Totally, the dataset is around 17.6km, 85mins, 50GB and it will be accessible from this link: https://github.com/junzhang2016/NTU4DRadLM