Embodied and evolved dynamical neural networks for robust planetary navigation
The N.E.Me.Sys project has the aim of controlling a legged rover for planetary exploration using dynamical recurrent neural networks and evolutionary algorithms. This paper describes the realization of the navigation module of such a rover using a 2D chemiotaxis scenario, in which the agent must rea...
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Tagungsbericht |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 6 |
|---|---|
| container_issue | |
| container_start_page | 1 |
| container_title | |
| container_volume | |
| creator | Cortesi, M. Sangiovanni, G. Zazzera, F.B. |
| description | The N.E.Me.Sys project has the aim of controlling a legged rover for planetary exploration using dynamical recurrent neural networks and evolutionary algorithms. This paper describes the realization of the navigation module of such a rover using a 2D chemiotaxis scenario, in which the agent must reach the source of a chemical signal. The analyses carried out in this work show the high degree of robustness of the neuro-controller versus uncertainties, noise, errors, or unpredicted situations. Moreover an analysis of the topology of the network has been realized in order to find the reasons of the good performances of the proposed methodology: it is possible to prove that different individuals share the same topology, i.e. the evolutionary process looks for the same feedback paths more than for the optimal set of parameters. |
| doi_str_mv | 10.1109/AIM.2007.4412557 |
| format | Conference Proceeding |
| fullrecord | <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_4412557</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>4412557</ieee_id><sourcerecordid>4412557</sourcerecordid><originalsourceid>FETCH-LOGICAL-i90t-dd12b50ac70c64d6bbc776458b57f4b8899e4e72b36223bd4b3b3d59e03c62fc3</originalsourceid><addsrcrecordid>eNo9kElPwzAUhM0mUUruSFz8B1K8L8eqaqFSgUvvlbcgQxJXThrUf0-AwmnezCc9jQaAO4xmGCP9MF8_zwhCcsYYJpzLM1BoqTAj314wdQ4mBHNdihFegJs_QOnlP2DyGhRd944QwkhxQugEvCwbm3wMHprWwzCkehhvf2xNE52pYRsO-Uf6z5Q_OlilDHOyh66H-9qMsclH2Johvpk-pvYWXFWm7kJx0inYrpbbxVO5eX1cL-abMmrUl95jYjkyTiInmBfWOikF48pyWTGrlNaBBUksFWNJ65mllnquA6JOkMrRKbj_fRtDCLt9js1YY3dahn4B7PhToA</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Embodied and evolved dynamical neural networks for robust planetary navigation</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Cortesi, M. ; Sangiovanni, G. ; Zazzera, F.B.</creator><creatorcontrib>Cortesi, M. ; Sangiovanni, G. ; Zazzera, F.B.</creatorcontrib><description>The N.E.Me.Sys project has the aim of controlling a legged rover for planetary exploration using dynamical recurrent neural networks and evolutionary algorithms. This paper describes the realization of the navigation module of such a rover using a 2D chemiotaxis scenario, in which the agent must reach the source of a chemical signal. The analyses carried out in this work show the high degree of robustness of the neuro-controller versus uncertainties, noise, errors, or unpredicted situations. Moreover an analysis of the topology of the network has been realized in order to find the reasons of the good performances of the proposed methodology: it is possible to prove that different individuals share the same topology, i.e. the evolutionary process looks for the same feedback paths more than for the optimal set of parameters.</description><identifier>ISSN: 2159-6247</identifier><identifier>ISBN: 1424412633</identifier><identifier>ISBN: 9781424412631</identifier><identifier>EISSN: 2159-6255</identifier><identifier>EISBN: 9781424412648</identifier><identifier>EISBN: 1424412641</identifier><identifier>DOI: 10.1109/AIM.2007.4412557</identifier><language>eng</language><publisher>IEEE</publisher><subject>biomimicry ; Control systems ; evolutionary algorithms ; Evolutionary computation ; Navigation ; Network topology ; neural controller ; Neural networks ; Neurons ; Recurrent neural networks ; Robust control ; Robustness ; Uncertainty</subject><ispartof>2007 IEEE/ASME international conference on advanced intelligent mechatronics, 2007, p.1-6</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/4412557$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,776,780,785,786,2051,27904,54898</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/4412557$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Cortesi, M.</creatorcontrib><creatorcontrib>Sangiovanni, G.</creatorcontrib><creatorcontrib>Zazzera, F.B.</creatorcontrib><title>Embodied and evolved dynamical neural networks for robust planetary navigation</title><title>2007 IEEE/ASME international conference on advanced intelligent mechatronics</title><addtitle>AIM</addtitle><description>The N.E.Me.Sys project has the aim of controlling a legged rover for planetary exploration using dynamical recurrent neural networks and evolutionary algorithms. This paper describes the realization of the navigation module of such a rover using a 2D chemiotaxis scenario, in which the agent must reach the source of a chemical signal. The analyses carried out in this work show the high degree of robustness of the neuro-controller versus uncertainties, noise, errors, or unpredicted situations. Moreover an analysis of the topology of the network has been realized in order to find the reasons of the good performances of the proposed methodology: it is possible to prove that different individuals share the same topology, i.e. the evolutionary process looks for the same feedback paths more than for the optimal set of parameters.</description><subject>biomimicry</subject><subject>Control systems</subject><subject>evolutionary algorithms</subject><subject>Evolutionary computation</subject><subject>Navigation</subject><subject>Network topology</subject><subject>neural controller</subject><subject>Neural networks</subject><subject>Neurons</subject><subject>Recurrent neural networks</subject><subject>Robust control</subject><subject>Robustness</subject><subject>Uncertainty</subject><issn>2159-6247</issn><issn>2159-6255</issn><isbn>1424412633</isbn><isbn>9781424412631</isbn><isbn>9781424412648</isbn><isbn>1424412641</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2007</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNo9kElPwzAUhM0mUUruSFz8B1K8L8eqaqFSgUvvlbcgQxJXThrUf0-AwmnezCc9jQaAO4xmGCP9MF8_zwhCcsYYJpzLM1BoqTAj314wdQ4mBHNdihFegJs_QOnlP2DyGhRd944QwkhxQugEvCwbm3wMHprWwzCkehhvf2xNE52pYRsO-Uf6z5Q_OlilDHOyh66H-9qMsclH2Johvpk-pvYWXFWm7kJx0inYrpbbxVO5eX1cL-abMmrUl95jYjkyTiInmBfWOikF48pyWTGrlNaBBUksFWNJ65mllnquA6JOkMrRKbj_fRtDCLt9js1YY3dahn4B7PhToA</recordid><startdate>200709</startdate><enddate>200709</enddate><creator>Cortesi, M.</creator><creator>Sangiovanni, G.</creator><creator>Zazzera, F.B.</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>200709</creationdate><title>Embodied and evolved dynamical neural networks for robust planetary navigation</title><author>Cortesi, M. ; Sangiovanni, G. ; Zazzera, F.B.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i90t-dd12b50ac70c64d6bbc776458b57f4b8899e4e72b36223bd4b3b3d59e03c62fc3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2007</creationdate><topic>biomimicry</topic><topic>Control systems</topic><topic>evolutionary algorithms</topic><topic>Evolutionary computation</topic><topic>Navigation</topic><topic>Network topology</topic><topic>neural controller</topic><topic>Neural networks</topic><topic>Neurons</topic><topic>Recurrent neural networks</topic><topic>Robust control</topic><topic>Robustness</topic><topic>Uncertainty</topic><toplevel>online_resources</toplevel><creatorcontrib>Cortesi, M.</creatorcontrib><creatorcontrib>Sangiovanni, G.</creatorcontrib><creatorcontrib>Zazzera, F.B.</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Electronic Library (IEL)</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Cortesi, M.</au><au>Sangiovanni, G.</au><au>Zazzera, F.B.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Embodied and evolved dynamical neural networks for robust planetary navigation</atitle><btitle>2007 IEEE/ASME international conference on advanced intelligent mechatronics</btitle><stitle>AIM</stitle><date>2007-09</date><risdate>2007</risdate><spage>1</spage><epage>6</epage><pages>1-6</pages><issn>2159-6247</issn><eissn>2159-6255</eissn><isbn>1424412633</isbn><isbn>9781424412631</isbn><eisbn>9781424412648</eisbn><eisbn>1424412641</eisbn><abstract>The N.E.Me.Sys project has the aim of controlling a legged rover for planetary exploration using dynamical recurrent neural networks and evolutionary algorithms. This paper describes the realization of the navigation module of such a rover using a 2D chemiotaxis scenario, in which the agent must reach the source of a chemical signal. The analyses carried out in this work show the high degree of robustness of the neuro-controller versus uncertainties, noise, errors, or unpredicted situations. Moreover an analysis of the topology of the network has been realized in order to find the reasons of the good performances of the proposed methodology: it is possible to prove that different individuals share the same topology, i.e. the evolutionary process looks for the same feedback paths more than for the optimal set of parameters.</abstract><pub>IEEE</pub><doi>10.1109/AIM.2007.4412557</doi><tpages>6</tpages></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 2159-6247 |
| ispartof | 2007 IEEE/ASME international conference on advanced intelligent mechatronics, 2007, p.1-6 |
| issn | 2159-6247 2159-6255 |
| language | eng |
| recordid | cdi_ieee_primary_4412557 |
| source | IEEE Electronic Library (IEL) Conference Proceedings |
| subjects | biomimicry Control systems evolutionary algorithms Evolutionary computation Navigation Network topology neural controller Neural networks Neurons Recurrent neural networks Robust control Robustness Uncertainty |
| title | Embodied and evolved dynamical neural networks for robust planetary navigation |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-25T08%3A15%3A55IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_6IE&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Embodied%20and%20evolved%20dynamical%20neural%20networks%20for%20robust%20planetary%20navigation&rft.btitle=2007%20IEEE/ASME%20international%20conference%20on%20advanced%20intelligent%20mechatronics&rft.au=Cortesi,%20M.&rft.date=2007-09&rft.spage=1&rft.epage=6&rft.pages=1-6&rft.issn=2159-6247&rft.eissn=2159-6255&rft.isbn=1424412633&rft.isbn_list=9781424412631&rft_id=info:doi/10.1109/AIM.2007.4412557&rft_dat=%3Cieee_6IE%3E4412557%3C/ieee_6IE%3E%3Curl%3E%3C/url%3E&rft.eisbn=9781424412648&rft.eisbn_list=1424412641&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=4412557&rfr_iscdi=true |