TY - GEN
T1 - Effect of Kernel Function to Magnetic Map and Evaluation of Localization of Magnetic Navigation
AU - Takebayashi, Takumi
AU - Miyagusuku, Renato
AU - Ozaki, Koichi
N1 - Publisher Copyright:
© 2020 IEEE.
PY - 2020/9/14
Y1 - 2020/9/14
N2 - Localization is one of the most fundamental requirements for the use of autonomous robots. In this work, we use magnetic-based localization; which, while not as accurate as laser rangefinder or camera-based systems, is not affected by a large number of people on its surrounding, making it ideal for applications where this is expected, such as service robotics in supermarkets, hotels, etc. Magnetic-based localization systems first create a magnetic map of the environment using magnetic samples acquired a priori. An approach for generating this map is to use collected data to training a Gaussian Process model. Gaussian Processes are non-parametric, data-drive models, where the most important design choice is the selection of an adequate kernel function. The purpose of this study is to improve the accuracy of the magnetic localization by testing several kernel functions and experimentally verifying its effects on robot localization.
AB - Localization is one of the most fundamental requirements for the use of autonomous robots. In this work, we use magnetic-based localization; which, while not as accurate as laser rangefinder or camera-based systems, is not affected by a large number of people on its surrounding, making it ideal for applications where this is expected, such as service robotics in supermarkets, hotels, etc. Magnetic-based localization systems first create a magnetic map of the environment using magnetic samples acquired a priori. An approach for generating this map is to use collected data to training a Gaussian Process model. Gaussian Processes are non-parametric, data-drive models, where the most important design choice is the selection of an adequate kernel function. The purpose of this study is to improve the accuracy of the magnetic localization by testing several kernel functions and experimentally verifying its effects on robot localization.
UR - http://www.scopus.com/inward/record.url?scp=85096091574&partnerID=8YFLogxK
U2 - 10.1109/MFI49285.2020.9235259
DO - 10.1109/MFI49285.2020.9235259
M3 - Conference contribution
AN - SCOPUS:85096091574
T3 - IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems
SP - 381
EP - 386
BT - 2020 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems, MFI 2020
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2020 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems, MFI 2020
Y2 - 14 September 2020 through 16 September 2020
ER -