FusionPortable: A Multi-Sensor Campus-Scene Dataset for Evaluation of Localization and Mapping Accuracy on Diverse Platforms
Combining multiple sensors enables a robot to maximize its perceptual awareness of environments and enhance its robustness to external disturbance, crucial to robotic navigation in complex environments. This paper proposes the FusionPortable benchmark, a novel multi-sensor dataset with a diverse set of sequences for mobile robots. This paper presents three contributions. We first advance a portable and versatile multi-sensor suite that offers rich sensory information: 10Hz LiDAR point clouds, 20Hz stereo frame images, high-rate and asynchronous events from stereo event cameras, 200Hz acceleration and angular velocity readings from a tacticalgrade IMU, and 10Hz GPS signal outdoors. Sensors are already temporally synchronized in hardware. This device is lightweight, self-contained, and has plug-and-play support for mobile robots. Second, we construct a dataset by collecting 18 sequences that cover a variety of environments on the campus by exploiting multiple platforms for data collection. Some sequences present issues that are challenging to existing SLAM algorithms. Third, we provide ground truth for the decouple localization and mapping performance evaluation. We additionally evaluate several state-of-the-art SLAM approaches and identify their limitations.
Authors: Jianhao Jiao, Hexiang Wei, Tianshuai Hu, Xiangcheng Hu, Yilong Zhu, Zhijian He, Jin Wu, Jingwen Yu, Xupeng Xie, Huaiyang Huang, Ruoyu Geng, Lujia Wang, Ming Liu.
Affiliation: The Hong Kong University of Science and Technology (HKUST), Cheng Kar-Shun Robotics Institute, IADC, RAM-LAB.
[PDF Conference Paper]: Paper to be published in IROS 2022
[PDF Supplementary Materials]: Supplementary materials