Collaborative infotaxis: Searching for a signal-emitting source based on particle filter and Gaussian fitting
To effectively leverage the spatio-temporal sensing capabilities of the team searching for a signal-emitting source, this paper presents a collaborative search method, in which each robot employs the weighted social Bayesian estimation and executes the distributed infotaxis search for the source. Co...
Gespeichert in:
Veröffentlicht in: | Robotics and autonomous systems 2020-03, Vol.125, p.103414, Article 103414 |
---|---|
Hauptverfasser: | , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | |
---|---|
container_issue | |
container_start_page | 103414 |
container_title | Robotics and autonomous systems |
container_volume | 125 |
creator | Song, Cheng He, Yuyao Ristic, Branko Lei, Xiaokang |
description | To effectively leverage the spatio-temporal sensing capabilities of the team searching for a signal-emitting source, this paper presents a collaborative search method, in which each robot employs the weighted social Bayesian estimation and executes the distributed infotaxis search for the source. Cognition difference between robots, measuring the dissimilarity of probability maps, is specially introduced to obtain the heterogeneous weights of Bayesian estimation. However, the requirement of exchanging the whole probability map presents additional challenges in computation and communication for real-time applications. In this work, a solution for fast low-cost collaborative infotaxis method based on a combination of particle filter and Gaussian fitting is proposed. A particle filter is first employed for the representation of the source probability distribution, which makes the infotaxis strategy computationally tractable for large complex spaces using the limited and tractable amount of randomly drawn particles. By fitting a Gaussian density to the particles, each robot obtains the likelihood weight for social Bayesian estimation by only reporting the mean and the covariance matrix of Gaussian distribution rather than exchanging the whole probability maps. The simulation shows the proposed collaborative infotaxis can achieve an efficient search behavior in complex environments using a small number of particles and a lower communication bandwidth.
•Weighted Bayesian estimation implemented by particle filter with a resampling scheme.•Identifying the reliability of the detections from others with cognition differences.•Cognition difference is measured by KL-divergence between two Gaussian densities.•Free energy is substitute for the entropy in the infotaxis decision. |
doi_str_mv | 10.1016/j.robot.2019.103414 |
format | Article |
fullrecord | <record><control><sourceid>elsevier_webof</sourceid><recordid>TN_cdi_webofscience_primary_000515203900006</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S0921889019306451</els_id><sourcerecordid>S0921889019306451</sourcerecordid><originalsourceid>FETCH-LOGICAL-c369t-33ce30301a3c0a180c3d74896d1b8421dfc720ec8067d3f360252729e2a06d973</originalsourceid><addsrcrecordid>eNqNkMtKBDEQRYMoOD6-wE320mMlmenuCC6k8QWCCxXchXRSrRl6EkkyPv7ejCMuxVUVl3uK4hByxGDKgNUni2kMfchTDkyWRMzYbItMWNvwqpHiaZtMQHJWta2EXbKX0gIAxLwRE7LswjjqPkSd3RtS54eQ9YdLp_QedTQvzj_TIUSqaXLPXo8VLl3O6zSFVTRIe53Q0uDpq47ZmRHp4MaMhfCWXulVSk77kn1DB2Rn0GPCw5-5Tx4vLx666-r27uqmO7-tjKhlroQwKEAA08KAZi0YYZtZK2vL-nbGmR1MwwFNC3VjxSBq4HPecIlcQ21lI_aJ2Nw1MaQUcVCv0S11_FQM1NqYWqhvY2ptTG2MFep4Q71jH4ZkHHqDv2RRNmdzDkKWDerSbv_f7lwugoPvwsrngp5tUCwO3hxG9YNbF9FkZYP789EvpO2XYQ</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Collaborative infotaxis: Searching for a signal-emitting source based on particle filter and Gaussian fitting</title><source>Web of Science - Science Citation Index Expanded - 2020<img src="https://exlibris-pub.s3.amazonaws.com/fromwos-v2.jpg" /></source><source>Access via ScienceDirect (Elsevier)</source><creator>Song, Cheng ; He, Yuyao ; Ristic, Branko ; Lei, Xiaokang</creator><creatorcontrib>Song, Cheng ; He, Yuyao ; Ristic, Branko ; Lei, Xiaokang</creatorcontrib><description>To effectively leverage the spatio-temporal sensing capabilities of the team searching for a signal-emitting source, this paper presents a collaborative search method, in which each robot employs the weighted social Bayesian estimation and executes the distributed infotaxis search for the source. Cognition difference between robots, measuring the dissimilarity of probability maps, is specially introduced to obtain the heterogeneous weights of Bayesian estimation. However, the requirement of exchanging the whole probability map presents additional challenges in computation and communication for real-time applications. In this work, a solution for fast low-cost collaborative infotaxis method based on a combination of particle filter and Gaussian fitting is proposed. A particle filter is first employed for the representation of the source probability distribution, which makes the infotaxis strategy computationally tractable for large complex spaces using the limited and tractable amount of randomly drawn particles. By fitting a Gaussian density to the particles, each robot obtains the likelihood weight for social Bayesian estimation by only reporting the mean and the covariance matrix of Gaussian distribution rather than exchanging the whole probability maps. The simulation shows the proposed collaborative infotaxis can achieve an efficient search behavior in complex environments using a small number of particles and a lower communication bandwidth.
•Weighted Bayesian estimation implemented by particle filter with a resampling scheme.•Identifying the reliability of the detections from others with cognition differences.•Cognition difference is measured by KL-divergence between two Gaussian densities.•Free energy is substitute for the entropy in the infotaxis decision.</description><identifier>ISSN: 0921-8890</identifier><identifier>EISSN: 1872-793X</identifier><identifier>DOI: 10.1016/j.robot.2019.103414</identifier><language>eng</language><publisher>AMSTERDAM: Elsevier B.V</publisher><subject>Automation & Control Systems ; Bayesian estimation ; Cognition difference ; Collaborative infotaxis ; Computer Science ; Computer Science, Artificial Intelligence ; Gaussian fitting ; Particle filter ; Robotics ; Science & Technology ; Technology</subject><ispartof>Robotics and autonomous systems, 2020-03, Vol.125, p.103414, Article 103414</ispartof><rights>2020 Elsevier B.V.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>true</woscitedreferencessubscribed><woscitedreferencescount>23</woscitedreferencescount><woscitedreferencesoriginalsourcerecordid>wos000515203900006</woscitedreferencesoriginalsourcerecordid><citedby>FETCH-LOGICAL-c369t-33ce30301a3c0a180c3d74896d1b8421dfc720ec8067d3f360252729e2a06d973</citedby><cites>FETCH-LOGICAL-c369t-33ce30301a3c0a180c3d74896d1b8421dfc720ec8067d3f360252729e2a06d973</cites><orcidid>0000-0001-8561-4412</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://dx.doi.org/10.1016/j.robot.2019.103414$$EHTML$$P50$$Gelsevier$$H</linktohtml><link.rule.ids>315,781,785,3551,27929,27930,28253,46000</link.rule.ids></links><search><creatorcontrib>Song, Cheng</creatorcontrib><creatorcontrib>He, Yuyao</creatorcontrib><creatorcontrib>Ristic, Branko</creatorcontrib><creatorcontrib>Lei, Xiaokang</creatorcontrib><title>Collaborative infotaxis: Searching for a signal-emitting source based on particle filter and Gaussian fitting</title><title>Robotics and autonomous systems</title><addtitle>ROBOT AUTON SYST</addtitle><description>To effectively leverage the spatio-temporal sensing capabilities of the team searching for a signal-emitting source, this paper presents a collaborative search method, in which each robot employs the weighted social Bayesian estimation and executes the distributed infotaxis search for the source. Cognition difference between robots, measuring the dissimilarity of probability maps, is specially introduced to obtain the heterogeneous weights of Bayesian estimation. However, the requirement of exchanging the whole probability map presents additional challenges in computation and communication for real-time applications. In this work, a solution for fast low-cost collaborative infotaxis method based on a combination of particle filter and Gaussian fitting is proposed. A particle filter is first employed for the representation of the source probability distribution, which makes the infotaxis strategy computationally tractable for large complex spaces using the limited and tractable amount of randomly drawn particles. By fitting a Gaussian density to the particles, each robot obtains the likelihood weight for social Bayesian estimation by only reporting the mean and the covariance matrix of Gaussian distribution rather than exchanging the whole probability maps. The simulation shows the proposed collaborative infotaxis can achieve an efficient search behavior in complex environments using a small number of particles and a lower communication bandwidth.
•Weighted Bayesian estimation implemented by particle filter with a resampling scheme.•Identifying the reliability of the detections from others with cognition differences.•Cognition difference is measured by KL-divergence between two Gaussian densities.•Free energy is substitute for the entropy in the infotaxis decision.</description><subject>Automation & Control Systems</subject><subject>Bayesian estimation</subject><subject>Cognition difference</subject><subject>Collaborative infotaxis</subject><subject>Computer Science</subject><subject>Computer Science, Artificial Intelligence</subject><subject>Gaussian fitting</subject><subject>Particle filter</subject><subject>Robotics</subject><subject>Science & Technology</subject><subject>Technology</subject><issn>0921-8890</issn><issn>1872-793X</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><sourceid>AOWDO</sourceid><recordid>eNqNkMtKBDEQRYMoOD6-wE320mMlmenuCC6k8QWCCxXchXRSrRl6EkkyPv7ejCMuxVUVl3uK4hByxGDKgNUni2kMfchTDkyWRMzYbItMWNvwqpHiaZtMQHJWta2EXbKX0gIAxLwRE7LswjjqPkSd3RtS54eQ9YdLp_QedTQvzj_TIUSqaXLPXo8VLl3O6zSFVTRIe53Q0uDpq47ZmRHp4MaMhfCWXulVSk77kn1DB2Rn0GPCw5-5Tx4vLx666-r27uqmO7-tjKhlroQwKEAA08KAZi0YYZtZK2vL-nbGmR1MwwFNC3VjxSBq4HPecIlcQ21lI_aJ2Nw1MaQUcVCv0S11_FQM1NqYWqhvY2ptTG2MFep4Q71jH4ZkHHqDv2RRNmdzDkKWDerSbv_f7lwugoPvwsrngp5tUCwO3hxG9YNbF9FkZYP789EvpO2XYQ</recordid><startdate>202003</startdate><enddate>202003</enddate><creator>Song, Cheng</creator><creator>He, Yuyao</creator><creator>Ristic, Branko</creator><creator>Lei, Xiaokang</creator><general>Elsevier B.V</general><general>Elsevier</general><scope>AOWDO</scope><scope>BLEPL</scope><scope>DTL</scope><scope>AAYXX</scope><scope>CITATION</scope><orcidid>https://orcid.org/0000-0001-8561-4412</orcidid></search><sort><creationdate>202003</creationdate><title>Collaborative infotaxis: Searching for a signal-emitting source based on particle filter and Gaussian fitting</title><author>Song, Cheng ; He, Yuyao ; Ristic, Branko ; Lei, Xiaokang</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c369t-33ce30301a3c0a180c3d74896d1b8421dfc720ec8067d3f360252729e2a06d973</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Automation & Control Systems</topic><topic>Bayesian estimation</topic><topic>Cognition difference</topic><topic>Collaborative infotaxis</topic><topic>Computer Science</topic><topic>Computer Science, Artificial Intelligence</topic><topic>Gaussian fitting</topic><topic>Particle filter</topic><topic>Robotics</topic><topic>Science & Technology</topic><topic>Technology</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Song, Cheng</creatorcontrib><creatorcontrib>He, Yuyao</creatorcontrib><creatorcontrib>Ristic, Branko</creatorcontrib><creatorcontrib>Lei, Xiaokang</creatorcontrib><collection>Web of Science - Science Citation Index Expanded - 2020</collection><collection>Web of Science Core Collection</collection><collection>Science Citation Index Expanded</collection><collection>CrossRef</collection><jtitle>Robotics and autonomous systems</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Song, Cheng</au><au>He, Yuyao</au><au>Ristic, Branko</au><au>Lei, Xiaokang</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Collaborative infotaxis: Searching for a signal-emitting source based on particle filter and Gaussian fitting</atitle><jtitle>Robotics and autonomous systems</jtitle><stitle>ROBOT AUTON SYST</stitle><date>2020-03</date><risdate>2020</risdate><volume>125</volume><spage>103414</spage><pages>103414-</pages><artnum>103414</artnum><issn>0921-8890</issn><eissn>1872-793X</eissn><abstract>To effectively leverage the spatio-temporal sensing capabilities of the team searching for a signal-emitting source, this paper presents a collaborative search method, in which each robot employs the weighted social Bayesian estimation and executes the distributed infotaxis search for the source. Cognition difference between robots, measuring the dissimilarity of probability maps, is specially introduced to obtain the heterogeneous weights of Bayesian estimation. However, the requirement of exchanging the whole probability map presents additional challenges in computation and communication for real-time applications. In this work, a solution for fast low-cost collaborative infotaxis method based on a combination of particle filter and Gaussian fitting is proposed. A particle filter is first employed for the representation of the source probability distribution, which makes the infotaxis strategy computationally tractable for large complex spaces using the limited and tractable amount of randomly drawn particles. By fitting a Gaussian density to the particles, each robot obtains the likelihood weight for social Bayesian estimation by only reporting the mean and the covariance matrix of Gaussian distribution rather than exchanging the whole probability maps. The simulation shows the proposed collaborative infotaxis can achieve an efficient search behavior in complex environments using a small number of particles and a lower communication bandwidth.
•Weighted Bayesian estimation implemented by particle filter with a resampling scheme.•Identifying the reliability of the detections from others with cognition differences.•Cognition difference is measured by KL-divergence between two Gaussian densities.•Free energy is substitute for the entropy in the infotaxis decision.</abstract><cop>AMSTERDAM</cop><pub>Elsevier B.V</pub><doi>10.1016/j.robot.2019.103414</doi><tpages>11</tpages><orcidid>https://orcid.org/0000-0001-8561-4412</orcidid></addata></record> |
fulltext | fulltext |
identifier | ISSN: 0921-8890 |
ispartof | Robotics and autonomous systems, 2020-03, Vol.125, p.103414, Article 103414 |
issn | 0921-8890 1872-793X |
language | eng |
recordid | cdi_webofscience_primary_000515203900006 |
source | Web of Science - Science Citation Index Expanded - 2020<img src="https://exlibris-pub.s3.amazonaws.com/fromwos-v2.jpg" />; Access via ScienceDirect (Elsevier) |
subjects | Automation & Control Systems Bayesian estimation Cognition difference Collaborative infotaxis Computer Science Computer Science, Artificial Intelligence Gaussian fitting Particle filter Robotics Science & Technology Technology |
title | Collaborative infotaxis: Searching for a signal-emitting source based on particle filter and Gaussian fitting |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-12T13%3A38%3A46IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-elsevier_webof&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Collaborative%20infotaxis:%20Searching%20for%20a%20signal-emitting%20source%20based%20on%20particle%20filter%20and%20Gaussian%20fitting&rft.jtitle=Robotics%20and%20autonomous%20systems&rft.au=Song,%20Cheng&rft.date=2020-03&rft.volume=125&rft.spage=103414&rft.pages=103414-&rft.artnum=103414&rft.issn=0921-8890&rft.eissn=1872-793X&rft_id=info:doi/10.1016/j.robot.2019.103414&rft_dat=%3Celsevier_webof%3ES0921889019306451%3C/elsevier_webof%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_els_id=S0921889019306451&rfr_iscdi=true |