Learning Environmental Field Exploration with Computationally Constrained Underwater Robots: Gaussian Processes Meet Stochastic Optimal Control
Autonomous exploration of environmental fields is one of the most promising tasks to be performed by fleets of mobile underwater robots. The goal is to maximize the information gain during the exploration process by integrating an information-metric into the path-planning and control step. Therefore...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-05-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/19/9/2094 |
| _version_ | 1828150814961565696 |
|---|---|
| author | Daniel Andre Duecker Andreas Rene Geist Edwin Kreuzer Eugen Solowjow |
| author_facet | Daniel Andre Duecker Andreas Rene Geist Edwin Kreuzer Eugen Solowjow |
| author_sort | Daniel Andre Duecker |
| collection | DOAJ |
| description | Autonomous exploration of environmental fields is one of the most promising tasks to be performed by fleets of mobile underwater robots. The goal is to maximize the information gain during the exploration process by integrating an information-metric into the path-planning and control step. Therefore, the system maintains an internal belief representation of the environmental field which incorporates previously collected measurements from the real field. In contrast to surface robots, mobile underwater systems are forced to run all computations on-board due to the limited communication bandwidth in underwater domains. Thus, reducing the computational cost of field exploration algorithms constitutes a key challenge for in-field implementations on micro underwater robot teams. In this work, we present a computationally efficient exploration algorithm which utilizes field belief models based on Gaussian Processes, such as Gaussian Markov random fields or Kalman regression, to enable field estimation with constant computational cost over time. We extend the belief models by the use of weighted shape functions to directly incorporate spatially continuous field observations. The developed belief models function as information-theoretic value functions to enable path planning through stochastic optimal control with path integrals. We demonstrate the efficiency of our exploration algorithm in a series of simulations including the case of a stationary spatio-temporal field. |
| first_indexed | 2024-04-11T21:48:14Z |
| format | Article |
| id | doaj.art-015469d477f84035973afc5199b2a76f |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-11T21:48:14Z |
| publishDate | 2019-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-015469d477f84035973afc5199b2a76f2022-12-22T04:01:19ZengMDPI AGSensors1424-82202019-05-01199209410.3390/s19092094s19092094Learning Environmental Field Exploration with Computationally Constrained Underwater Robots: Gaussian Processes Meet Stochastic Optimal ControlDaniel Andre Duecker0Andreas Rene Geist1Edwin Kreuzer2Eugen Solowjow3Institute of Mechanics and Ocean Engineering, Hamburg University of Technology, 21073 Hamburg, GermanyInstitute of Mechanics and Ocean Engineering, Hamburg University of Technology, 21073 Hamburg, GermanyInstitute of Mechanics and Ocean Engineering, Hamburg University of Technology, 21073 Hamburg, GermanySiemens Corporate Technology, Berkeley, CA 94704, USAAutonomous exploration of environmental fields is one of the most promising tasks to be performed by fleets of mobile underwater robots. The goal is to maximize the information gain during the exploration process by integrating an information-metric into the path-planning and control step. Therefore, the system maintains an internal belief representation of the environmental field which incorporates previously collected measurements from the real field. In contrast to surface robots, mobile underwater systems are forced to run all computations on-board due to the limited communication bandwidth in underwater domains. Thus, reducing the computational cost of field exploration algorithms constitutes a key challenge for in-field implementations on micro underwater robot teams. In this work, we present a computationally efficient exploration algorithm which utilizes field belief models based on Gaussian Processes, such as Gaussian Markov random fields or Kalman regression, to enable field estimation with constant computational cost over time. We extend the belief models by the use of weighted shape functions to directly incorporate spatially continuous field observations. The developed belief models function as information-theoretic value functions to enable path planning through stochastic optimal control with path integrals. We demonstrate the efficiency of our exploration algorithm in a series of simulations including the case of a stationary spatio-temporal field.https://www.mdpi.com/1424-8220/19/9/2094autonomous explorationenvironmental field monitoringgaussian processesgaussian markov random fieldskalman filteringstochastic optimal control |
| spellingShingle | Daniel Andre Duecker Andreas Rene Geist Edwin Kreuzer Eugen Solowjow Learning Environmental Field Exploration with Computationally Constrained Underwater Robots: Gaussian Processes Meet Stochastic Optimal Control Sensors autonomous exploration environmental field monitoring gaussian processes gaussian markov random fields kalman filtering stochastic optimal control |
| title | Learning Environmental Field Exploration with Computationally Constrained Underwater Robots: Gaussian Processes Meet Stochastic Optimal Control |
| title_full | Learning Environmental Field Exploration with Computationally Constrained Underwater Robots: Gaussian Processes Meet Stochastic Optimal Control |
| title_fullStr | Learning Environmental Field Exploration with Computationally Constrained Underwater Robots: Gaussian Processes Meet Stochastic Optimal Control |
| title_full_unstemmed | Learning Environmental Field Exploration with Computationally Constrained Underwater Robots: Gaussian Processes Meet Stochastic Optimal Control |
| title_short | Learning Environmental Field Exploration with Computationally Constrained Underwater Robots: Gaussian Processes Meet Stochastic Optimal Control |
| title_sort | learning environmental field exploration with computationally constrained underwater robots gaussian processes meet stochastic optimal control |
| topic | autonomous exploration environmental field monitoring gaussian processes gaussian markov random fields kalman filtering stochastic optimal control |
| url | https://www.mdpi.com/1424-8220/19/9/2094 |
| work_keys_str_mv | AT danielandreduecker learningenvironmentalfieldexplorationwithcomputationallyconstrainedunderwaterrobotsgaussianprocessesmeetstochasticoptimalcontrol AT andreasrenegeist learningenvironmentalfieldexplorationwithcomputationallyconstrainedunderwaterrobotsgaussianprocessesmeetstochasticoptimalcontrol AT edwinkreuzer learningenvironmentalfieldexplorationwithcomputationallyconstrainedunderwaterrobotsgaussianprocessesmeetstochasticoptimalcontrol AT eugensolowjow learningenvironmentalfieldexplorationwithcomputationallyconstrainedunderwaterrobotsgaussianprocessesmeetstochasticoptimalcontrol |