Dataset for Fusion of Stereo Thermal, Optical, Scanning Mirror LiDAR, and Inertial Sensors for Navigation in Urban and Unstructured Environments

Tuan Dinh Luong, Arden Markin, and Jordan Larson

Peer Reviewed

Abstract:	For autonomous robotic systems to receive widespread adoption, their sensor, navigation, and perception systems need to be robust to various operating environments. Thermal cameras have been proposed as a potential supplemental exteroceptive sensor for navigation and perception to address optical cameras’ degradation under low-light and LiDAR’s high cost and sparse data products. However, their adoption into navigation systems, especially in a stereo configuration, has not been sufficiently studied and the amount of datasets featuring thermal sensors in the sensor fusion context for navigation systems is noticeably lacking. To the best of the author’s knowledge, there are only three publicly available datasets with a stereo thermal camera setup for autonomous robot localization context albeit with several shortcomings, e.g., sensor synchronization, operating environments, and lacking LiDAR modalities. To address these shortcomings, the proposed work seeks to acquire a high quality dataset featuring stereo optical, stereo thermal, and micro-electro mechanical system (MEMS) LiDAR alongside two inertial navigation systems (INS) with different grades to enable navigation research. The planned sequences include traversals in an urban environment as well as a wooded environment. Furthermore, each route will be recorded at three different times, i.e., mid-day, twilight, and before sunrise to provide a variety of environmental conditions with varied temperature profiles. This further diversifies the operating environments that could be considered for navigation. The dataset will be publicly available as both raw data and Robot Operating System (ROS) bags to accommodate different preferences by navigation researchers. The resulting dataset aims to provide a means for investigation of the efficacy of thermal cameras in the context of navigation, especially in unstructured environments. The dataset is publicly available at https://sites.google.com/view/lager-nigel. Index Terms—sensor fusion, thermal cameras, optical cameras, LiDAR, IMU
Published in:	2025 IEEE/ION Position, Location and Navigation Symposium (PLANS) April 28 - 1, 2025 Salt Lake Marriott Downtown at City Creek Salt Lake City, UT
Pages:	146 - 156
Cite this article:	Luong, Tuan Dinh, Markin, Arden, Larson, Jordan, "Dataset for Fusion of Stereo Thermal, Optical, Scanning Mirror LiDAR, and Inertial Sensors for Navigation in Urban and Unstructured Environments," 2025 IEEE/ION Position, Location and Navigation Symposium (PLANS), Salt Lake City, UT, April 2025, pp. 146-156.
Full Paper:	ION Members/Non-Members: 1 Download Credit Sign In