Learning from the Past: Sequential Deep Learning for Gas Distribution Mapping

Nicolas P. Winkler, Oleksandr Kotlyar, Erik Schaffernicht, Han Fan, Haruka Matsukura, Hiroshi Ishida, Patrick P. Neumann, Achim J. Lilienthal

Publikation: Beitrag in Buch/Bericht/KonferenzbandKonferenzbeitragBegutachtung

1 Zitat (Scopus)

Abstract

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.

OriginalspracheEnglisch
TitelROBOT 2022
Untertitel5th Iberian Robotics Conference - Advances in Robotics
Redakteure/-innenDanilo Tardioli, Vicente Matellán, Guillermo Heredia, Manuel F. Silva, Lino Marques
Herausgeber (Verlag)Springer Science and Business Media Deutschland GmbH
Seiten178-188
Seitenumfang11
ISBN (Print)9783031210617
DOIs
PublikationsstatusVeröffentlicht - 2023
Extern publiziertJa
Veranstaltung5th Iberian Robotics Conference, ROBOT 2022 - Zaragoza, Spanien
Dauer: 23 Nov. 202225 Nov. 2022

Publikationsreihe

NameLecture Notes in Networks and Systems
Band590 LNNS
ISSN (Print)2367-3370
ISSN (elektronisch)2367-3389

Konferenz

Konferenz5th Iberian Robotics Conference, ROBOT 2022
Land/GebietSpanien
OrtZaragoza
Zeitraum23/11/2225/11/22

Fingerprint

Untersuchen Sie die Forschungsthemen von „Learning from the Past: Sequential Deep Learning for Gas Distribution Mapping“. Zusammen bilden sie einen einzigartigen Fingerprint.

Dieses zitieren