JAIST Repository >
School of Information Science >
Articles >
Journal Articles >

Please use this identifier to cite or link to this item: http://hdl.handle.net/10119/15370

Title: Point-Wise Fusion of Distributed Gaussian Process Experts (FuDGE) Using a Fully Decentralized Robot Team Operating in Communication-Devoid Environment
Authors: Tiwari, Kshitij
Jeong, Sungmoon
Chong, Nak Young
Keywords: distributed robot systems
field robots
model fusion
Gaussian process
path planning for multiple mobile robot systems
Issue Date: 2018-02-28
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Magazine name: IEEE Transactions on Robotics
Volume: 34
Number: 3
Start page: 820
End page: 828
DOI: 10.1109/TRO.2018.2794535
Abstract: In this paper, we focus on large-scale environment monitoring by utilizing a fully decentralized team of mobile robots. The robots utilize the resource constrained-decentralized active sensing scheme to select the most informative (uncertain) locations to observe while conserving allocated resources (battery, travel distance, etc.). We utilize a distributed Gaussian process (GP) framework to split the computational load over ourfleet of robots. Since each robot is individually generating a model of the environment, there may be conflicting predictions for test locations. Thus, in this paper, we propose an algorithm for aggregating individual prediction models into a single globally consistent model that can be used to infer the overall spatial dynamics of the environment. To make a prediction at a previously unobserved location, we propose a novel gating network fora mixture-of-experts model wherein the weight of an expert is determined by the responsibility of the expert over the unvisited location. The benefit of posing our problem as a centralized fusion with a distributed GP computationapproach is that the robots never communicate with each other, individually optimize their own GP models based on their respective observations, and off-load all their learnt models on the base station only at the end of their respective mission times. We demonstrate the effectiveness of our approach using publicly available datasets.
Rights: This is the author's version of the work. Copyright (C) 2018 IEEE. IEEE Transactions on Robotics, 34(3), 2018, 820-828. 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.
URI: http://hdl.handle.net/10119/15370
Material Type: author
Appears in Collections:b10-1. 雑誌掲載論文 (Journal Articles)

Files in This Item:

File Description SizeFormat
24237.pdf2958KbAdobe PDFView/Open

All items in DSpace are protected by copyright, with all rights reserved.


Contact : Library Information Section, Japan Advanced Institute of Science and Technology