Evolving robot behaviours with diffusing gas networks
This paper introduces a new type of artificial nervous system and shows that it is possible to use evolutionary computing techniques to find robot controllers based on them. The controllers are built from networks inspired by the modulatory effects of freely diffusing gases, especially nitric oxide,...
Gespeichert in:
| 1. Verfasser: | |
|---|---|
| Format: | Tagungsbericht |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 86 |
|---|---|
| container_issue | |
| container_start_page | 71 |
| container_title | |
| container_volume | |
| creator | Husbands, Phil |
| description | This paper introduces a new type of artificial nervous system and shows that it is possible to use evolutionary computing techniques to find robot controllers based on them. The controllers are built from networks inspired by the modulatory effects of freely diffusing gases, especially nitric oxide, in real neuronal networks. Using Jakobi's radical minimal simulations, successful behaviours have been consistently evolved in far fewer evaluations than were needed when using more conventional connectionist style networks. Indeed the reduction is by a factor of roughly one order of magnitude. |
| doi_str_mv | 10.1007/3-540-64957-3_65 |
| format | Conference Proceeding |
| fullrecord | <record><control><sourceid>pascalfrancis_sprin</sourceid><recordid>TN_cdi_pascalfrancis_primary_2290854</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2290854</sourcerecordid><originalsourceid>FETCH-LOGICAL-p1385-9ef113cabd0899da885c5dddc7eb33ad83f43732829b73200c5d196d7e8cfd8a3</originalsourceid><addsrcrecordid>eNo9kEtvAiEUhekrqbHuu5xFt1jgwgDLxthHYtJNuybMADrVDgZ0TP99UZvezUnOd3IXH0L3lEwpIfIRsOAE11wLicHU4gJNtFRQSq41YewSjWhNKQbg-uqfnfb0Go0IEIa15HCLJjl_kXLASkdGSMyHuBm6flml2MRd1fiVHbq4T7k6dLtV5boQ9vnIlzZXvd8dYlrnO3QT7Cb7yV-O0efz_GP2ihfvL2-zpwXeUlACax8ohdY2jiitnVVKtMI510rfAFinIHCQwBTTTQlCCqW6dtKrNjhlYYwezn-3Nrd2E5Lt2y6bbeq-bfoxjGmiBC-z6XmWC-mXPpkmxnU2lJijPgOm2DAnHeaoD34BKmddFw</addsrcrecordid><sourcetype>Index Database</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Evolving robot behaviours with diffusing gas networks</title><source>Springer Books</source><creator>Husbands, Phil</creator><contributor>Husbands, Philip ; Meyer, Jean-Arcady</contributor><creatorcontrib>Husbands, Phil ; Husbands, Philip ; Meyer, Jean-Arcady</creatorcontrib><description>This paper introduces a new type of artificial nervous system and shows that it is possible to use evolutionary computing techniques to find robot controllers based on them. The controllers are built from networks inspired by the modulatory effects of freely diffusing gases, especially nitric oxide, in real neuronal networks. Using Jakobi's radical minimal simulations, successful behaviours have been consistently evolved in far fewer evaluations than were needed when using more conventional connectionist style networks. Indeed the reduction is by a factor of roughly one order of magnitude.</description><identifier>ISSN: 0302-9743</identifier><identifier>ISBN: 9783540649571</identifier><identifier>ISBN: 3540649573</identifier><identifier>EISSN: 1611-3349</identifier><identifier>EISBN: 9783540499022</identifier><identifier>EISBN: 3540499024</identifier><identifier>DOI: 10.1007/3-540-64957-3_65</identifier><language>eng</language><publisher>Berlin, Heidelberg: Springer Berlin Heidelberg</publisher><subject>Applied sciences ; Computer science; control theory; systems ; Control theory. Systems ; Evolutionary Robotic ; Exact sciences and technology ; Negative Segment ; Recurrent Connection ; Robotics ; Successful Behaviour ; Successful Controller</subject><ispartof>Evolutionary Robotics, 2005, p.71-86</ispartof><rights>Springer-Verlag Berlin Heidelberg 1998</rights><rights>1998 INIST-CNRS</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://link.springer.com/content/pdf/10.1007/3-540-64957-3_65$$EPDF$$P50$$Gspringer$$H</linktopdf><linktohtml>$$Uhttps://link.springer.com/10.1007/3-540-64957-3_65$$EHTML$$P50$$Gspringer$$H</linktohtml><link.rule.ids>309,310,776,777,781,786,787,790,4036,4037,27906,38236,41423,42492</link.rule.ids><backlink>$$Uhttp://pascal-francis.inist.fr/vibad/index.php?action=getRecordDetail&idt=2290854$$DView record in Pascal Francis$$Hfree_for_read</backlink></links><search><contributor>Husbands, Philip</contributor><contributor>Meyer, Jean-Arcady</contributor><creatorcontrib>Husbands, Phil</creatorcontrib><title>Evolving robot behaviours with diffusing gas networks</title><title>Evolutionary Robotics</title><description>This paper introduces a new type of artificial nervous system and shows that it is possible to use evolutionary computing techniques to find robot controllers based on them. The controllers are built from networks inspired by the modulatory effects of freely diffusing gases, especially nitric oxide, in real neuronal networks. Using Jakobi's radical minimal simulations, successful behaviours have been consistently evolved in far fewer evaluations than were needed when using more conventional connectionist style networks. Indeed the reduction is by a factor of roughly one order of magnitude.</description><subject>Applied sciences</subject><subject>Computer science; control theory; systems</subject><subject>Control theory. Systems</subject><subject>Evolutionary Robotic</subject><subject>Exact sciences and technology</subject><subject>Negative Segment</subject><subject>Recurrent Connection</subject><subject>Robotics</subject><subject>Successful Behaviour</subject><subject>Successful Controller</subject><issn>0302-9743</issn><issn>1611-3349</issn><isbn>9783540649571</isbn><isbn>3540649573</isbn><isbn>9783540499022</isbn><isbn>3540499024</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2005</creationdate><recordtype>conference_proceeding</recordtype><recordid>eNo9kEtvAiEUhekrqbHuu5xFt1jgwgDLxthHYtJNuybMADrVDgZ0TP99UZvezUnOd3IXH0L3lEwpIfIRsOAE11wLicHU4gJNtFRQSq41YewSjWhNKQbg-uqfnfb0Go0IEIa15HCLJjl_kXLASkdGSMyHuBm6flml2MRd1fiVHbq4T7k6dLtV5boQ9vnIlzZXvd8dYlrnO3QT7Cb7yV-O0efz_GP2ihfvL2-zpwXeUlACax8ohdY2jiitnVVKtMI510rfAFinIHCQwBTTTQlCCqW6dtKrNjhlYYwezn-3Nrd2E5Lt2y6bbeq-bfoxjGmiBC-z6XmWC-mXPpkmxnU2lJijPgOm2DAnHeaoD34BKmddFw</recordid><startdate>20050806</startdate><enddate>20050806</enddate><creator>Husbands, Phil</creator><general>Springer Berlin Heidelberg</general><general>Springer</general><scope>IQODW</scope></search><sort><creationdate>20050806</creationdate><title>Evolving robot behaviours with diffusing gas networks</title><author>Husbands, Phil</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-p1385-9ef113cabd0899da885c5dddc7eb33ad83f43732829b73200c5d196d7e8cfd8a3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2005</creationdate><topic>Applied sciences</topic><topic>Computer science; control theory; systems</topic><topic>Control theory. Systems</topic><topic>Evolutionary Robotic</topic><topic>Exact sciences and technology</topic><topic>Negative Segment</topic><topic>Recurrent Connection</topic><topic>Robotics</topic><topic>Successful Behaviour</topic><topic>Successful Controller</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Husbands, Phil</creatorcontrib><collection>Pascal-Francis</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Husbands, Phil</au><au>Husbands, Philip</au><au>Meyer, Jean-Arcady</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Evolving robot behaviours with diffusing gas networks</atitle><btitle>Evolutionary Robotics</btitle><date>2005-08-06</date><risdate>2005</risdate><spage>71</spage><epage>86</epage><pages>71-86</pages><issn>0302-9743</issn><eissn>1611-3349</eissn><isbn>9783540649571</isbn><isbn>3540649573</isbn><eisbn>9783540499022</eisbn><eisbn>3540499024</eisbn><abstract>This paper introduces a new type of artificial nervous system and shows that it is possible to use evolutionary computing techniques to find robot controllers based on them. The controllers are built from networks inspired by the modulatory effects of freely diffusing gases, especially nitric oxide, in real neuronal networks. Using Jakobi's radical minimal simulations, successful behaviours have been consistently evolved in far fewer evaluations than were needed when using more conventional connectionist style networks. Indeed the reduction is by a factor of roughly one order of magnitude.</abstract><cop>Berlin, Heidelberg</cop><pub>Springer Berlin Heidelberg</pub><doi>10.1007/3-540-64957-3_65</doi><tpages>16</tpages></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 0302-9743 |
| ispartof | Evolutionary Robotics, 2005, p.71-86 |
| issn | 0302-9743 1611-3349 |
| language | eng |
| recordid | cdi_pascalfrancis_primary_2290854 |
| source | Springer Books |
| subjects | Applied sciences Computer science control theory systems Control theory. Systems Evolutionary Robotic Exact sciences and technology Negative Segment Recurrent Connection Robotics Successful Behaviour Successful Controller |
| title | Evolving robot behaviours with diffusing gas networks |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-17T13%3A47%3A24IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-pascalfrancis_sprin&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Evolving%20robot%20behaviours%20with%20diffusing%20gas%20networks&rft.btitle=Evolutionary%20Robotics&rft.au=Husbands,%20Phil&rft.date=2005-08-06&rft.spage=71&rft.epage=86&rft.pages=71-86&rft.issn=0302-9743&rft.eissn=1611-3349&rft.isbn=9783540649571&rft.isbn_list=3540649573&rft_id=info:doi/10.1007/3-540-64957-3_65&rft_dat=%3Cpascalfrancis_sprin%3E2290854%3C/pascalfrancis_sprin%3E%3Curl%3E%3C/url%3E&rft.eisbn=9783540499022&rft.eisbn_list=3540499024&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true |