A New Technique to Improve Estimation of Position for Serial Robots
This paper presents a new method to improve the estimation of the positions for serial robots using power-activated feed-forward neural network. In the paper, a six-input three-output neural network is created with robot joint angle sine values as inputs and positions in the world frame as outputs....
Gespeichert in:
Veröffentlicht in: | Applied Mechanics and Materials 2014-02, Vol.511-512 (Sensors, Mechatronics and Automation), p.817-821 |
---|---|
Hauptverfasser: | , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | 821 |
---|---|
container_issue | Sensors, Mechatronics and Automation |
container_start_page | 817 |
container_title | Applied Mechanics and Materials |
container_volume | 511-512 |
creator | Shao, Ming Wei Wei, Zhen Zhong Zhang, Guang Jun Wang, Ya Li |
description | This paper presents a new method to improve the estimation of the positions for serial robots using power-activated feed-forward neural network. In the paper, a six-input three-output neural network is created with robot joint angle sine values as inputs and positions in the world frame as outputs. The neuron is activated with an orthogonal polynomial sequence,and the neural weights can be calculated directly without involving iterative and convergent problem. It is found that, the RMS error is less than 0.25 mm for the whole work space. And the absolute and relative errors of this method are smaller than those of built in kinematics model and the traditional back propagation (BP) neural network method. Experimental results show that the proposed method can effectively predict the positioning of the given joint angles. |
doi_str_mv | 10.4028/www.scientific.net/AMM.511-512.817 |
format | Article |
fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_1762097869</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>3826670901</sourcerecordid><originalsourceid>FETCH-LOGICAL-c336t-f8bb3e25b4681c19fe9a6278dde27e1cd56720cdc90026fa7f51ff16db811363</originalsourceid><addsrcrecordid>eNqNkFtLBCEYhqUDdNr_IHQTwUx-OqPO5bYdoRO19zLjKBm7Y6nb0r_PdoOiqy5EwZfne78HoWMgZUWoPFkul2XUzgzJWafLwaST8e1tWQMUNdBSgthAu8A5LUQl6SYaNUIywiSrCQiytfojRcMY30F7Mb4Qwiuo5C6ajPGdWeKp0c-De1sYnDy-nr8G_27weUxu3ibnB-wtfvDRrd7WB_xkgmtn-NF3PsUDtG3bWTSj73sfTS_Op5Or4ub-8noyvil0npsKK7uOGVp3FZegobGmaTkVsu8NFQZ0X3NBie51QwjlthW2BmuB950EYJzto6M1NrfLTWNScxe1mc3awfhFVCA4JXlv3uTo4Z_oi1-EIZfLKZANYYR_AU_XKR18jMFY9RrywuFDAVFf2lXWrn60q6xdZe0qa8-Hqqw9Q87WkBTaIabs8des_2M-AaVUkfk</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>1718903066</pqid></control><display><type>article</type><title>A New Technique to Improve Estimation of Position for Serial Robots</title><source>Scientific.net Journals</source><creator>Shao, Ming Wei ; Wei, Zhen Zhong ; Zhang, Guang Jun ; Wang, Ya Li</creator><creatorcontrib>Shao, Ming Wei ; Wei, Zhen Zhong ; Zhang, Guang Jun ; Wang, Ya Li</creatorcontrib><description>This paper presents a new method to improve the estimation of the positions for serial robots using power-activated feed-forward neural network. In the paper, a six-input three-output neural network is created with robot joint angle sine values as inputs and positions in the world frame as outputs. The neuron is activated with an orthogonal polynomial sequence,and the neural weights can be calculated directly without involving iterative and convergent problem. It is found that, the RMS error is less than 0.25 mm for the whole work space. And the absolute and relative errors of this method are smaller than those of built in kinematics model and the traditional back propagation (BP) neural network method. Experimental results show that the proposed method can effectively predict the positioning of the given joint angles.</description><identifier>ISSN: 1660-9336</identifier><identifier>ISSN: 1662-7482</identifier><identifier>ISBN: 9783038350170</identifier><identifier>ISBN: 3038350176</identifier><identifier>EISSN: 1662-7482</identifier><identifier>DOI: 10.4028/www.scientific.net/AMM.511-512.817</identifier><language>eng</language><publisher>Zurich: Trans Tech Publications Ltd</publisher><subject>Back propagation ; Errors ; Mathematical models ; Neural networks ; Neurons ; Polynomials ; Robots ; Serials</subject><ispartof>Applied Mechanics and Materials, 2014-02, Vol.511-512 (Sensors, Mechatronics and Automation), p.817-821</ispartof><rights>2014 Trans Tech Publications Ltd</rights><rights>Copyright Trans Tech Publications Ltd. Feb 2014</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c336t-f8bb3e25b4681c19fe9a6278dde27e1cd56720cdc90026fa7f51ff16db811363</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Uhttps://www.scientific.net/Image/TitleCover/3006?width=600</thumbnail><link.rule.ids>314,776,780,27901,27902</link.rule.ids></links><search><creatorcontrib>Shao, Ming Wei</creatorcontrib><creatorcontrib>Wei, Zhen Zhong</creatorcontrib><creatorcontrib>Zhang, Guang Jun</creatorcontrib><creatorcontrib>Wang, Ya Li</creatorcontrib><title>A New Technique to Improve Estimation of Position for Serial Robots</title><title>Applied Mechanics and Materials</title><description>This paper presents a new method to improve the estimation of the positions for serial robots using power-activated feed-forward neural network. In the paper, a six-input three-output neural network is created with robot joint angle sine values as inputs and positions in the world frame as outputs. The neuron is activated with an orthogonal polynomial sequence,and the neural weights can be calculated directly without involving iterative and convergent problem. It is found that, the RMS error is less than 0.25 mm for the whole work space. And the absolute and relative errors of this method are smaller than those of built in kinematics model and the traditional back propagation (BP) neural network method. Experimental results show that the proposed method can effectively predict the positioning of the given joint angles.</description><subject>Back propagation</subject><subject>Errors</subject><subject>Mathematical models</subject><subject>Neural networks</subject><subject>Neurons</subject><subject>Polynomials</subject><subject>Robots</subject><subject>Serials</subject><issn>1660-9336</issn><issn>1662-7482</issn><issn>1662-7482</issn><isbn>9783038350170</isbn><isbn>3038350176</isbn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2014</creationdate><recordtype>article</recordtype><sourceid>BENPR</sourceid><recordid>eNqNkFtLBCEYhqUDdNr_IHQTwUx-OqPO5bYdoRO19zLjKBm7Y6nb0r_PdoOiqy5EwZfne78HoWMgZUWoPFkul2XUzgzJWafLwaST8e1tWQMUNdBSgthAu8A5LUQl6SYaNUIywiSrCQiytfojRcMY30F7Mb4Qwiuo5C6ajPGdWeKp0c-De1sYnDy-nr8G_27weUxu3ibnB-wtfvDRrd7WB_xkgmtn-NF3PsUDtG3bWTSj73sfTS_Op5Or4ub-8noyvil0npsKK7uOGVp3FZegobGmaTkVsu8NFQZ0X3NBie51QwjlthW2BmuB950EYJzto6M1NrfLTWNScxe1mc3awfhFVCA4JXlv3uTo4Z_oi1-EIZfLKZANYYR_AU_XKR18jMFY9RrywuFDAVFf2lXWrn60q6xdZe0qa8-Hqqw9Q87WkBTaIabs8des_2M-AaVUkfk</recordid><startdate>20140201</startdate><enddate>20140201</enddate><creator>Shao, Ming Wei</creator><creator>Wei, Zhen Zhong</creator><creator>Zhang, Guang Jun</creator><creator>Wang, Ya Li</creator><general>Trans Tech Publications Ltd</general><scope>AAYXX</scope><scope>CITATION</scope><scope>7SR</scope><scope>7TB</scope><scope>8BQ</scope><scope>8FD</scope><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>BENPR</scope><scope>BFMQW</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>D1I</scope><scope>DWQXO</scope><scope>FR3</scope><scope>HCIFZ</scope><scope>JG9</scope><scope>KB.</scope><scope>KR7</scope><scope>L6V</scope><scope>M7S</scope><scope>PDBOC</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20140201</creationdate><title>A New Technique to Improve Estimation of Position for Serial Robots</title><author>Shao, Ming Wei ; Wei, Zhen Zhong ; Zhang, Guang Jun ; Wang, Ya Li</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c336t-f8bb3e25b4681c19fe9a6278dde27e1cd56720cdc90026fa7f51ff16db811363</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2014</creationdate><topic>Back propagation</topic><topic>Errors</topic><topic>Mathematical models</topic><topic>Neural networks</topic><topic>Neurons</topic><topic>Polynomials</topic><topic>Robots</topic><topic>Serials</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Shao, Ming Wei</creatorcontrib><creatorcontrib>Wei, Zhen Zhong</creatorcontrib><creatorcontrib>Zhang, Guang Jun</creatorcontrib><creatorcontrib>Wang, Ya Li</creatorcontrib><collection>CrossRef</collection><collection>Engineered Materials Abstracts</collection><collection>Mechanical & Transportation Engineering Abstracts</collection><collection>METADEX</collection><collection>Technology Research Database</collection><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science & Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central</collection><collection>Continental Europe Database</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Materials Science Collection</collection><collection>ProQuest Central Korea</collection><collection>Engineering Research Database</collection><collection>SciTech Premium Collection</collection><collection>Materials Research Database</collection><collection>Materials Science Database</collection><collection>Civil Engineering Abstracts</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Materials Science Collection</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection><jtitle>Applied Mechanics and Materials</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Shao, Ming Wei</au><au>Wei, Zhen Zhong</au><au>Zhang, Guang Jun</au><au>Wang, Ya Li</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>A New Technique to Improve Estimation of Position for Serial Robots</atitle><jtitle>Applied Mechanics and Materials</jtitle><date>2014-02-01</date><risdate>2014</risdate><volume>511-512</volume><issue>Sensors, Mechatronics and Automation</issue><spage>817</spage><epage>821</epage><pages>817-821</pages><issn>1660-9336</issn><issn>1662-7482</issn><eissn>1662-7482</eissn><isbn>9783038350170</isbn><isbn>3038350176</isbn><abstract>This paper presents a new method to improve the estimation of the positions for serial robots using power-activated feed-forward neural network. In the paper, a six-input three-output neural network is created with robot joint angle sine values as inputs and positions in the world frame as outputs. The neuron is activated with an orthogonal polynomial sequence,and the neural weights can be calculated directly without involving iterative and convergent problem. It is found that, the RMS error is less than 0.25 mm for the whole work space. And the absolute and relative errors of this method are smaller than those of built in kinematics model and the traditional back propagation (BP) neural network method. Experimental results show that the proposed method can effectively predict the positioning of the given joint angles.</abstract><cop>Zurich</cop><pub>Trans Tech Publications Ltd</pub><doi>10.4028/www.scientific.net/AMM.511-512.817</doi><tpages>5</tpages></addata></record> |
fulltext | fulltext |
identifier | ISSN: 1660-9336 |
ispartof | Applied Mechanics and Materials, 2014-02, Vol.511-512 (Sensors, Mechatronics and Automation), p.817-821 |
issn | 1660-9336 1662-7482 1662-7482 |
language | eng |
recordid | cdi_proquest_miscellaneous_1762097869 |
source | Scientific.net Journals |
subjects | Back propagation Errors Mathematical models Neural networks Neurons Polynomials Robots Serials |
title | A New Technique to Improve Estimation of Position for Serial Robots |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-28T18%3A47%3A07IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=A%20New%20Technique%20to%20Improve%20Estimation%20of%20Position%20for%20Serial%20Robots&rft.jtitle=Applied%20Mechanics%20and%20Materials&rft.au=Shao,%20Ming%20Wei&rft.date=2014-02-01&rft.volume=511-512&rft.issue=Sensors,%20Mechatronics%20and%20Automation&rft.spage=817&rft.epage=821&rft.pages=817-821&rft.issn=1660-9336&rft.eissn=1662-7482&rft.isbn=9783038350170&rft.isbn_list=3038350176&rft_id=info:doi/10.4028/www.scientific.net/AMM.511-512.817&rft_dat=%3Cproquest_cross%3E3826670901%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=1718903066&rft_id=info:pmid/&rfr_iscdi=true |