Reinforcement learning for source location estimation: a multi-step approach

Research output: Chapter in Book/Report/Conference proceedingConference Contribution (Conference Proceeding)

Abstract

Gas leaks present an undeniable safety concern, the ability to swiftly and accurately detect the source of a leak and pertinent details is critical for effective emergency response. The limited precision of sensors and environmental noise introduce significant uncertainty and randomness, complicating the resolution of such issues. To address these challenges, this study introduces a new approach that integrates multi-step deep reinforcement learning algorithms with Bayesian inference to estimate source information. Compared to single-step Reinforcement Learning and Entrotaxis methods, the multi-step update mechanism in this problem allows the agent to locate sources position more efficiently. This approach not only increases the search’s success rate but also decreases the number of time steps needed for successful detection. Experiments conducted in continuous and discrete environments of equal scale and parameters corroborate the efficiency of our method in tracing the source of gas leaks.
Original languageEnglish
Title of host publicationProceedings of the 25th IEEE International Conference on Industrial Technology (ICIT'24)
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Number of pages9
ISBN (Electronic)9798350340266
ISBN (Print)9798350340273
DOIs
Publication statusPublished - 5 Jun 2024
Event2024 ICIT – 25th IEEE International Conference on Industrial Technology - Bristol, United Kingdom
Duration: 25 Mar 202427 Mar 2024
https://iten.ieee-ies.org/past-events/2023/2024-icit-25th-ieee-international-conference-on-industrial-technology/

Publication series

NameIEEE International Conference on Industrial Technology
PublisherIEEE
ISSN (Print)2641-0184
ISSN (Electronic)2643-2978

Conference

Conference2024 ICIT – 25th IEEE International Conference on Industrial Technology
Abbreviated titleICIT 2024
Country/TerritoryUnited Kingdom
CityBristol
Period25/03/2427/03/24
Internet address

Bibliographical note

Publisher Copyright:
Copyright © 2024 by the Institute of Electrical and Electronics Engineers, Inc.

Fingerprint

Dive into the research topics of 'Reinforcement learning for source location estimation: a multi-step approach'. Together they form a unique fingerprint.

Cite this