TY - JOUR
T1 - Deep Sensor Fusion between 2D Laser Scanner and IMU for Mobile Robot Localization
AU - Li, Chi
AU - Wang, Sen
AU - Zhuang, Yan
AU - Yan, Fei
N1 - Funding Information:
Manuscript received January 30, 2019; revised April 4, 2019; accepted April 6, 2019. Date of publication April 12, 2019; date of current version February 17, 2021. This work was supported by the National Natural Science Foundation of China under Grant 61503056 and Grant U1508208. The associate editor coordinating the review of this article and approving it for publication was Prof. Subhas C. Mukhopadhyay. (Corresponding author: Yan Zhuang.) C. Li, Y. Zhuang, and F. Yan are with the School of Control Science and Engineering, Dalian University of Technology, Dalian 116024, China (e-mail: lichiduter@mail.dlut.edu.cn; zhuang@dlut.edu.cn; fyan@dlut.edu.cn).
Publisher Copyright:
© 2001-2012 IEEE.
Copyright:
Copyright 2021 Elsevier B.V., All rights reserved.
PY - 2021/3/15
Y1 - 2021/3/15
N2 - Multi-sensor fusion plays a key role in 2D laser-based robot location and navigation. Although it has achieved great success, there are still some challenges, e.g., being fragile when having a large angular rotation. In this paper, we present a deep learning-based approach to localizing a mobile robot using a 2D laser and an inertial measurement unit. A novel recurrent convolutional neural network (RCNN)-based architecture is developed to fuse laser and inertial data for scan-to-scan pose estimation. A scan-to-submap optimization is also introduced to optimize the poses estimated by the RCNN for enhanced robustness and accuracy. Extensive experiments have been conducted in both simulation and practice with a real mobile robot, verifying the effectiveness of the proposed deep sensor fusion system.
AB - Multi-sensor fusion plays a key role in 2D laser-based robot location and navigation. Although it has achieved great success, there are still some challenges, e.g., being fragile when having a large angular rotation. In this paper, we present a deep learning-based approach to localizing a mobile robot using a 2D laser and an inertial measurement unit. A novel recurrent convolutional neural network (RCNN)-based architecture is developed to fuse laser and inertial data for scan-to-scan pose estimation. A scan-to-submap optimization is also introduced to optimize the poses estimated by the RCNN for enhanced robustness and accuracy. Extensive experiments have been conducted in both simulation and practice with a real mobile robot, verifying the effectiveness of the proposed deep sensor fusion system.
KW - 2D laser scanning
KW - Data fusion
KW - inertial measurement unit (IMU)
KW - pose estimation
UR - http://www.scopus.com/inward/record.url?scp=85101778962&partnerID=8YFLogxK
U2 - 10.1109/JSEN.2019.2910826
DO - 10.1109/JSEN.2019.2910826
M3 - Article
SN - 1530-437X
VL - 21
SP - 8501
EP - 8509
JO - IEEE Sensors Journal
JF - IEEE Sensors Journal
IS - 6
ER -