Adaptive sensing of time series with application to remote exploration

David R. Thompson, Nathalie A. Cabrol, Michael Furlong, Craig Hardgrove, Bryan Kian Hsiang Low, Jeffrey Moersch, David Wettergreen

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

We address the problem of adaptive information-optimal data collection in time series. Here a remote sensor or explorer agent throttles its sampling rate in order to track anomalous events while obeying constraints on time and power. This problem is challenging because the agent has limited visibility - all collected datapoints lie in the past, but its resource allocation decisions require predicting far into the future. Our solution is to continually fit a Gaussian process model to the latest data and optimize the sampling plan on line to maximize information gain. We compare the performance characteristics of stationary and nonstationary Gaussian process models. We also describe an application based on geologic analysis during planetary rover exploration. Here adaptive sampling can improve coverage of localized anomalies and potentially benefit mission science yield of long autonomous traverses.

Original languageEnglish (US)
Title of host publication2013 IEEE International Conference on Robotics and Automation, ICRA 2013
Pages3463-3468
Number of pages6
DOIs
StatePublished - 2013
Event2013 IEEE International Conference on Robotics and Automation, ICRA 2013 - Karlsruhe, Germany
Duration: May 6 2013May 10 2013

Other

Other2013 IEEE International Conference on Robotics and Automation, ICRA 2013
CountryGermany
CityKarlsruhe
Period5/6/135/10/13

Fingerprint

Time series
Sampling
Visibility
Resource allocation
Sensors

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence
  • Control and Systems Engineering
  • Electrical and Electronic Engineering

Cite this

Thompson, D. R., Cabrol, N. A., Furlong, M., Hardgrove, C., Low, B. K. H., Moersch, J., & Wettergreen, D. (2013). Adaptive sensing of time series with application to remote exploration. In 2013 IEEE International Conference on Robotics and Automation, ICRA 2013 (pp. 3463-3468). [6631061] https://doi.org/10.1109/ICRA.2013.6631061

Adaptive sensing of time series with application to remote exploration. / Thompson, David R.; Cabrol, Nathalie A.; Furlong, Michael; Hardgrove, Craig; Low, Bryan Kian Hsiang; Moersch, Jeffrey; Wettergreen, David.

2013 IEEE International Conference on Robotics and Automation, ICRA 2013. 2013. p. 3463-3468 6631061.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Thompson, DR, Cabrol, NA, Furlong, M, Hardgrove, C, Low, BKH, Moersch, J & Wettergreen, D 2013, Adaptive sensing of time series with application to remote exploration. in 2013 IEEE International Conference on Robotics and Automation, ICRA 2013., 6631061, pp. 3463-3468, 2013 IEEE International Conference on Robotics and Automation, ICRA 2013, Karlsruhe, Germany, 5/6/13. https://doi.org/10.1109/ICRA.2013.6631061
Thompson DR, Cabrol NA, Furlong M, Hardgrove C, Low BKH, Moersch J et al. Adaptive sensing of time series with application to remote exploration. In 2013 IEEE International Conference on Robotics and Automation, ICRA 2013. 2013. p. 3463-3468. 6631061 https://doi.org/10.1109/ICRA.2013.6631061
Thompson, David R. ; Cabrol, Nathalie A. ; Furlong, Michael ; Hardgrove, Craig ; Low, Bryan Kian Hsiang ; Moersch, Jeffrey ; Wettergreen, David. / Adaptive sensing of time series with application to remote exploration. 2013 IEEE International Conference on Robotics and Automation, ICRA 2013. 2013. pp. 3463-3468
@inproceedings{7d1f19acf0444e6a8781e7de6db0598a,
title = "Adaptive sensing of time series with application to remote exploration",
abstract = "We address the problem of adaptive information-optimal data collection in time series. Here a remote sensor or explorer agent throttles its sampling rate in order to track anomalous events while obeying constraints on time and power. This problem is challenging because the agent has limited visibility - all collected datapoints lie in the past, but its resource allocation decisions require predicting far into the future. Our solution is to continually fit a Gaussian process model to the latest data and optimize the sampling plan on line to maximize information gain. We compare the performance characteristics of stationary and nonstationary Gaussian process models. We also describe an application based on geologic analysis during planetary rover exploration. Here adaptive sampling can improve coverage of localized anomalies and potentially benefit mission science yield of long autonomous traverses.",
author = "Thompson, {David R.} and Cabrol, {Nathalie A.} and Michael Furlong and Craig Hardgrove and Low, {Bryan Kian Hsiang} and Jeffrey Moersch and David Wettergreen",
year = "2013",
doi = "10.1109/ICRA.2013.6631061",
language = "English (US)",
isbn = "9781467356411",
pages = "3463--3468",
booktitle = "2013 IEEE International Conference on Robotics and Automation, ICRA 2013",

}

TY - GEN

T1 - Adaptive sensing of time series with application to remote exploration

AU - Thompson, David R.

AU - Cabrol, Nathalie A.

AU - Furlong, Michael

AU - Hardgrove, Craig

AU - Low, Bryan Kian Hsiang

AU - Moersch, Jeffrey

AU - Wettergreen, David

PY - 2013

Y1 - 2013

N2 - We address the problem of adaptive information-optimal data collection in time series. Here a remote sensor or explorer agent throttles its sampling rate in order to track anomalous events while obeying constraints on time and power. This problem is challenging because the agent has limited visibility - all collected datapoints lie in the past, but its resource allocation decisions require predicting far into the future. Our solution is to continually fit a Gaussian process model to the latest data and optimize the sampling plan on line to maximize information gain. We compare the performance characteristics of stationary and nonstationary Gaussian process models. We also describe an application based on geologic analysis during planetary rover exploration. Here adaptive sampling can improve coverage of localized anomalies and potentially benefit mission science yield of long autonomous traverses.

AB - We address the problem of adaptive information-optimal data collection in time series. Here a remote sensor or explorer agent throttles its sampling rate in order to track anomalous events while obeying constraints on time and power. This problem is challenging because the agent has limited visibility - all collected datapoints lie in the past, but its resource allocation decisions require predicting far into the future. Our solution is to continually fit a Gaussian process model to the latest data and optimize the sampling plan on line to maximize information gain. We compare the performance characteristics of stationary and nonstationary Gaussian process models. We also describe an application based on geologic analysis during planetary rover exploration. Here adaptive sampling can improve coverage of localized anomalies and potentially benefit mission science yield of long autonomous traverses.

UR - http://www.scopus.com/inward/record.url?scp=84887305247&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84887305247&partnerID=8YFLogxK

U2 - 10.1109/ICRA.2013.6631061

DO - 10.1109/ICRA.2013.6631061

M3 - Conference contribution

AN - SCOPUS:84887305247

SN - 9781467356411

SP - 3463

EP - 3468

BT - 2013 IEEE International Conference on Robotics and Automation, ICRA 2013

ER -