Approaches to time-dependent gas distribution modelling

Sahar Asadi, Achim Lilienthal

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

4 Scopus citations

Abstract

Mobile robot olfaction solutions for gas distribution modelling offer a number of advantages, among them au- tonomous monitoring in different environments, mobility to select sampling locations, and ability to cooperate with other systems. However, most data-driven, statistical gas distribution modelling approaches assume that the gas distribution is generated by a time-invariant random process. Such time-invariant approaches cannot model well developing plumes or fundamental changes in the gas distribution. In this paper, we discuss approaches that explicitly consider the measurement time, either by sub-sampling according to a given time-scale or by introducing a recency weight that relates measurement and prediction time. We evaluate the performance of these time-dependent approaches in simulation and in real-world experiments using mobile robots. The results demonstrate that in dynamic scenarios improved gas distribution models can be obtained with time-dependent approaches.

Original languageEnglish
Title of host publication2015 European Conference on Mobile Robots, ECMR 2015 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781467391634
DOIs
StatePublished - 10 Nov 2015
Externally publishedYes
EventEuropean Conference on Mobile Robots, ECMR 2015 - Lincoln, United Kingdom
Duration: 2 Sep 20154 Sep 2015

Publication series

Name2015 European Conference on Mobile Robots, ECMR 2015 - Proceedings

Conference

ConferenceEuropean Conference on Mobile Robots, ECMR 2015
Country/TerritoryUnited Kingdom
CityLincoln
Period2/09/154/09/15

Keywords

  • Dispersion
  • Kernel
  • Pollution measurement
  • Predictive models
  • Robot sensing systems
  • Time measurement
  • Weight measurement

Fingerprint

Dive into the research topics of 'Approaches to time-dependent gas distribution modelling'. Together they form a unique fingerprint.

Cite this