Learning From the Past: Sequential Deep Learning for Gas Distribution MappingShow others and affiliations
2022 (English)In: ROBOT2022: Fifth Iberian Robotics Conference: Advances in Robotics, Volume 2 / [ed] Danilo Tardioli; Vicente Matellán; Guillermo Heredia; Manuel F. Silva; Lino Marques, Springer, 2022, Vol. 590, p. 178-188Conference paper, Published paper (Refereed)
Abstract [en]
To better understand the dynamics in hazardous environments, gas distribution mapping aims to map the gas concentration levels of a specified area precisely. Sampling is typically carried out in a spatially sparse manner, either with a mobile robot or a sensor network and concentration values between known data points have to be interpolated. In this paper, we investigate sequential deep learning models that are able to map the gas distribution based on a multiple time step input from a sensor network. We propose a novel hybrid convolutional LSTM - transpose convolutional structure that we train with synthetic gas distribution data. Our results show that learning the spatial and temporal correlation of gas plume patterns outperforms a non-sequential neural network model.
Place, publisher, year, edition, pages
Springer, 2022. Vol. 590, p. 178-188
Series
Lecture Notes in Networks and Systems, ISSN 2367-3370, E-ISSN 2367-3389 ; 590
Keywords [en]
Convolutional LSTM, Gas Distribution Mapping, Sequential Learning, Spatial Interpolation
National Category
Computer Sciences
Identifiers
URN: urn:nbn:se:oru:diva-102769DOI: 10.1007/978-3-031-21062-4_15ISI: 000906176800015Scopus ID: 2-s2.0-85145267880ISBN: 9783031210617 (print)ISBN: 9783031210624 (electronic)OAI: oai:DiVA.org:oru-102769DiVA, id: diva2:1720225
Conference
ROBOT2022: Fifth Iberian Robotics Conference, Zaragoza, Spain, November 23-25, 2022
Note
Funding agency:
Ministry of Education, Culture, Sports, Science and Technology, Japan (MEXT)
Japan Society for the Promotion of Science 22H04952
2022-12-192022-12-192024-01-03Bibliographically approved