Deep Sensor Fusion between 2D Laser Scanner and IMU for Mobile Robot Localization

Chi Li; Sen Wang; Yan Zhuang; Fei Yan

doi:10.1109/JSEN.2019.2910826

Deep Sensor Fusion between 2D Laser Scanner and IMU for Mobile Robot Localization

Chi Li, Sen Wang, Yan Zhuang, Fei Yan

Research output: Contribution to journal › Article › peer-review

103 Downloads (Pure)

Abstract

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 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.

Original language	English
Journal	IEEE Sensors Journal
Early online date	12 Apr 2019
DOIs	https://doi.org/10.1109/JSEN.2019.2910826
Publication status	E-pub ahead of print - 12 Apr 2019

Keywords

Data fusion
Pose estimation
2D laser scanning
Inertial measurement unit (IMU)

Access to Document

10.1109/JSEN.2019.2910826

Download pdf
© 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Accepted author manuscript, 8.9 MB

Fingerprint Dive into the research topics of 'Deep Sensor Fusion between 2D Laser Scanner and IMU for Mobile Robot Localization'. Together they form a unique fingerprint.

Sen Wang
- s.wang@hw.ac.uk
- School of Engineering & Physical Sciences - Associate Professor
- School of Engineering & Physical Sciences, Institute of Sensors, Signals & Systems - Associate Professor
Person: Academic (Research & Teaching)

Cite this

@article{bd87a5847be54ae9bbd4fd13da01943b,

title = "Deep Sensor Fusion between 2D Laser Scanner and IMU for Mobile Robot Localization",

abstract = "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 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.",

keywords = "Data fusion, Pose estimation, 2D laser scanning, Inertial measurement unit (IMU)",

author = "Chi Li and Sen Wang and Yan Zhuang and Fei Yan",

year = "2019",

month = apr,

day = "12",

doi = "10.1109/JSEN.2019.2910826",

language = "English",

journal = "IEEE Sensors Journal",

issn = "1530-437X",

publisher = "IEEE",

}

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

PY - 2019/4/12

Y1 - 2019/4/12

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 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 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 - Data fusion

KW - Pose estimation

KW - 2D laser scanning

KW - Inertial measurement unit (IMU)

U2 - 10.1109/JSEN.2019.2910826

DO - 10.1109/JSEN.2019.2910826

M3 - Article

JO - IEEE Sensors Journal

JF - IEEE Sensors Journal

SN - 1530-437X

ER -