Multi-USV Adaptive Exploration Using Kernel Information and Residual Variance
Using a team of robots for estimating scalar environmental fields is an emerging approach. The aim of such an approach is to reduce the mission time for collecting informative data as compared to a single robot. However, increasing the number of robots requires coordination and efficient use of the...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2021-05-01
|
Series: | Frontiers in Robotics and AI |
Subjects: | |
Online Access: | https://www.frontiersin.org/articles/10.3389/frobt.2021.572243/full |
id |
doaj-d305e1222b3840a08292c0514ad66893 |
---|---|
record_format |
Article |
spelling |
doaj-d305e1222b3840a08292c0514ad668932021-05-28T09:54:06ZengFrontiers Media S.A.Frontiers in Robotics and AI2296-91442021-05-01810.3389/frobt.2021.572243572243Multi-USV Adaptive Exploration Using Kernel Information and Residual VarianceRajat Mishra0Teong Beng Koay1Teong Beng Koay2Mandar Chitre3Mandar Chitre4Sanjay Swarup5Sanjay Swarup6Sanjay Swarup7Acoustic Research Laboratory, Tropical Marine Science Institute, National University of Singapore, Singapore, SingaporeAcoustic Research Laboratory, Tropical Marine Science Institute, National University of Singapore, Singapore, SingaporeNUS Environmental Research Institute, National University of Singapore, Singapore, SingaporeAcoustic Research Laboratory, Tropical Marine Science Institute, National University of Singapore, Singapore, SingaporeDepartment of Electrical & Computer Engineering, Faculty of Engineering, National University of Singapore, Singapore, SingaporeNUS Environmental Research Institute, National University of Singapore, Singapore, SingaporeSingapore Centre for Environmental Life Sciences Engineering, Singapore, SingaporeDepartment of Biological Sciences, Faculty of Science, National University of Singapore, Singapore, SingaporeUsing a team of robots for estimating scalar environmental fields is an emerging approach. The aim of such an approach is to reduce the mission time for collecting informative data as compared to a single robot. However, increasing the number of robots requires coordination and efficient use of the mission time to provide a good approximation of the scalar field. We suggest an online multi-robot framework m-AdaPP to handle this coordination. We test our framework for estimating a scalar environmental field with no prior information and benchmark the performance via field experiments against conventional approaches such as lawn mower patterns. We demonstrated that our framework is capable of handling a team of robots for estimating a scalar field and outperforms conventional approaches used for approximating water quality parameters. The suggested framework can be used for estimating other scalar functions such as air temperature or vegetative index using land or aerial robots as well. Finally, we show an example use case of our adaptive algorithm in a scientific study for understanding micro-level interactions.https://www.frontiersin.org/articles/10.3389/frobt.2021.572243/fullmulti-robot systemsinformative path planningGaussian processfield validatedsampling hotspotsfreshwater analysis |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Rajat Mishra Teong Beng Koay Teong Beng Koay Mandar Chitre Mandar Chitre Sanjay Swarup Sanjay Swarup Sanjay Swarup |
spellingShingle |
Rajat Mishra Teong Beng Koay Teong Beng Koay Mandar Chitre Mandar Chitre Sanjay Swarup Sanjay Swarup Sanjay Swarup Multi-USV Adaptive Exploration Using Kernel Information and Residual Variance Frontiers in Robotics and AI multi-robot systems informative path planning Gaussian process field validated sampling hotspots freshwater analysis |
author_facet |
Rajat Mishra Teong Beng Koay Teong Beng Koay Mandar Chitre Mandar Chitre Sanjay Swarup Sanjay Swarup Sanjay Swarup |
author_sort |
Rajat Mishra |
title |
Multi-USV Adaptive Exploration Using Kernel Information and Residual Variance |
title_short |
Multi-USV Adaptive Exploration Using Kernel Information and Residual Variance |
title_full |
Multi-USV Adaptive Exploration Using Kernel Information and Residual Variance |
title_fullStr |
Multi-USV Adaptive Exploration Using Kernel Information and Residual Variance |
title_full_unstemmed |
Multi-USV Adaptive Exploration Using Kernel Information and Residual Variance |
title_sort |
multi-usv adaptive exploration using kernel information and residual variance |
publisher |
Frontiers Media S.A. |
series |
Frontiers in Robotics and AI |
issn |
2296-9144 |
publishDate |
2021-05-01 |
description |
Using a team of robots for estimating scalar environmental fields is an emerging approach. The aim of such an approach is to reduce the mission time for collecting informative data as compared to a single robot. However, increasing the number of robots requires coordination and efficient use of the mission time to provide a good approximation of the scalar field. We suggest an online multi-robot framework m-AdaPP to handle this coordination. We test our framework for estimating a scalar environmental field with no prior information and benchmark the performance via field experiments against conventional approaches such as lawn mower patterns. We demonstrated that our framework is capable of handling a team of robots for estimating a scalar field and outperforms conventional approaches used for approximating water quality parameters. The suggested framework can be used for estimating other scalar functions such as air temperature or vegetative index using land or aerial robots as well. Finally, we show an example use case of our adaptive algorithm in a scientific study for understanding micro-level interactions. |
topic |
multi-robot systems informative path planning Gaussian process field validated sampling hotspots freshwater analysis |
url |
https://www.frontiersin.org/articles/10.3389/frobt.2021.572243/full |
work_keys_str_mv |
AT rajatmishra multiusvadaptiveexplorationusingkernelinformationandresidualvariance AT teongbengkoay multiusvadaptiveexplorationusingkernelinformationandresidualvariance AT teongbengkoay multiusvadaptiveexplorationusingkernelinformationandresidualvariance AT mandarchitre multiusvadaptiveexplorationusingkernelinformationandresidualvariance AT mandarchitre multiusvadaptiveexplorationusingkernelinformationandresidualvariance AT sanjayswarup multiusvadaptiveexplorationusingkernelinformationandresidualvariance AT sanjayswarup multiusvadaptiveexplorationusingkernelinformationandresidualvariance AT sanjayswarup multiusvadaptiveexplorationusingkernelinformationandresidualvariance |
_version_ |
1721424265834659840 |