Study of a neural network controller for robotic applications
Computer simulations have been performed for analysing the learning behaviour of a neural network when it is used as a controller in a robotic control system. Specifically, the effect of the backpropagation parameters on the convergence and stability of the network have been investigated. The neural...
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 | 256 vol.4 |
|---|---|
| container_issue | |
| container_start_page | 252 |
| container_title | |
| container_volume | 4 |
| creator | Chin, L. Sundararajan, N. Yip Kim San Low Kee Ley |
| description | Computer simulations have been performed for analysing the learning behaviour of a neural network when it is used as a controller in a robotic control system. Specifically, the effect of the backpropagation parameters on the convergence and stability of the network have been investigated. The neural network is configured as a feedforward inverse controller. Results indicated that increasing the number of neurons in the hidden layer will improve the convergence speed. However, beyond a certain limit additional neurons will cause system oscillations and finally instability. The main contribution of this paper is the derivation of a relationship between the rms error and the number of iterations used in the training of the neural network. Guidelines for selecting the neural network parameters are also given.< > |
| doi_str_mv | 10.1109/TENCON.1993.320480 |
| format | Conference Proceeding |
| fullrecord | <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_320480</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>320480</ieee_id><sourcerecordid>320480</sourcerecordid><originalsourceid>FETCH-LOGICAL-i104t-8cf8e8e364c63badb6c0349cdb9a8c09b3a39846e11d3f4fd0d7cbcc06f2efc63</originalsourceid><addsrcrecordid>eNotj8tqwzAURAWl0DbND2SlH7B75SscadFFMekDQrJIug7SlQRqXcvICiV_X0M6m7OaMwxjKwG1EKCfjptdt9_VQmussQGp4IY9wFoBigYR79hymr5gjpTYSnHPng_l7C48BW744M_Z9DPKb8rfnNJQcup7n3lImedkU4nEzTj2kUyJaZge2W0w_eSX_1ywz9fNsXuvtvu3j-5lW0UBslSKgvLKz4vUojXOtgQoNTmrjSLQFg1qJVsvhMMggwO3JksEbWh8mDsLtrp6o_f-NOb4Y_LldD2If396SF0</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Study of a neural network controller for robotic applications</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Chin, L. ; Sundararajan, N. ; Yip Kim San ; Low Kee Ley</creator><creatorcontrib>Chin, L. ; Sundararajan, N. ; Yip Kim San ; Low Kee Ley</creatorcontrib><description>Computer simulations have been performed for analysing the learning behaviour of a neural network when it is used as a controller in a robotic control system. Specifically, the effect of the backpropagation parameters on the convergence and stability of the network have been investigated. The neural network is configured as a feedforward inverse controller. Results indicated that increasing the number of neurons in the hidden layer will improve the convergence speed. However, beyond a certain limit additional neurons will cause system oscillations and finally instability. The main contribution of this paper is the derivation of a relationship between the rms error and the number of iterations used in the training of the neural network. Guidelines for selecting the neural network parameters are also given.< ></description><identifier>ISBN: 0780312333</identifier><identifier>ISBN: 9780780312333</identifier><identifier>DOI: 10.1109/TENCON.1993.320480</identifier><language>eng</language><publisher>IEEE</publisher><subject>Application software ; Backpropagation ; Computer simulation ; Control system synthesis ; Convergence ; Neural networks ; Neurons ; Performance analysis ; Robot control ; Stability</subject><ispartof>Proceedings of TENCON '93. IEEE Region 10 International Conference on Computers, Communications and Automation, 1993, Vol.4, p.252-256 vol.4</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/320480$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,776,780,785,786,2052,4036,4037,27902,54895</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/320480$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Chin, L.</creatorcontrib><creatorcontrib>Sundararajan, N.</creatorcontrib><creatorcontrib>Yip Kim San</creatorcontrib><creatorcontrib>Low Kee Ley</creatorcontrib><title>Study of a neural network controller for robotic applications</title><title>Proceedings of TENCON '93. IEEE Region 10 International Conference on Computers, Communications and Automation</title><addtitle>TENCON</addtitle><description>Computer simulations have been performed for analysing the learning behaviour of a neural network when it is used as a controller in a robotic control system. Specifically, the effect of the backpropagation parameters on the convergence and stability of the network have been investigated. The neural network is configured as a feedforward inverse controller. Results indicated that increasing the number of neurons in the hidden layer will improve the convergence speed. However, beyond a certain limit additional neurons will cause system oscillations and finally instability. The main contribution of this paper is the derivation of a relationship between the rms error and the number of iterations used in the training of the neural network. Guidelines for selecting the neural network parameters are also given.< ></description><subject>Application software</subject><subject>Backpropagation</subject><subject>Computer simulation</subject><subject>Control system synthesis</subject><subject>Convergence</subject><subject>Neural networks</subject><subject>Neurons</subject><subject>Performance analysis</subject><subject>Robot control</subject><subject>Stability</subject><isbn>0780312333</isbn><isbn>9780780312333</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>1993</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNotj8tqwzAURAWl0DbND2SlH7B75SscadFFMekDQrJIug7SlQRqXcvICiV_X0M6m7OaMwxjKwG1EKCfjptdt9_VQmussQGp4IY9wFoBigYR79hymr5gjpTYSnHPng_l7C48BW744M_Z9DPKb8rfnNJQcup7n3lImedkU4nEzTj2kUyJaZge2W0w_eSX_1ywz9fNsXuvtvu3j-5lW0UBslSKgvLKz4vUojXOtgQoNTmrjSLQFg1qJVsvhMMggwO3JksEbWh8mDsLtrp6o_f-NOb4Y_LldD2If396SF0</recordid><startdate>1993</startdate><enddate>1993</enddate><creator>Chin, L.</creator><creator>Sundararajan, N.</creator><creator>Yip Kim San</creator><creator>Low Kee Ley</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>1993</creationdate><title>Study of a neural network controller for robotic applications</title><author>Chin, L. ; Sundararajan, N. ; Yip Kim San ; Low Kee Ley</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i104t-8cf8e8e364c63badb6c0349cdb9a8c09b3a39846e11d3f4fd0d7cbcc06f2efc63</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>1993</creationdate><topic>Application software</topic><topic>Backpropagation</topic><topic>Computer simulation</topic><topic>Control system synthesis</topic><topic>Convergence</topic><topic>Neural networks</topic><topic>Neurons</topic><topic>Performance analysis</topic><topic>Robot control</topic><topic>Stability</topic><toplevel>online_resources</toplevel><creatorcontrib>Chin, L.</creatorcontrib><creatorcontrib>Sundararajan, N.</creatorcontrib><creatorcontrib>Yip Kim San</creatorcontrib><creatorcontrib>Low Kee Ley</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 Xplore</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>Chin, L.</au><au>Sundararajan, N.</au><au>Yip Kim San</au><au>Low Kee Ley</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Study of a neural network controller for robotic applications</atitle><btitle>Proceedings of TENCON '93. IEEE Region 10 International Conference on Computers, Communications and Automation</btitle><stitle>TENCON</stitle><date>1993</date><risdate>1993</risdate><volume>4</volume><spage>252</spage><epage>256 vol.4</epage><pages>252-256 vol.4</pages><isbn>0780312333</isbn><isbn>9780780312333</isbn><abstract>Computer simulations have been performed for analysing the learning behaviour of a neural network when it is used as a controller in a robotic control system. Specifically, the effect of the backpropagation parameters on the convergence and stability of the network have been investigated. The neural network is configured as a feedforward inverse controller. Results indicated that increasing the number of neurons in the hidden layer will improve the convergence speed. However, beyond a certain limit additional neurons will cause system oscillations and finally instability. The main contribution of this paper is the derivation of a relationship between the rms error and the number of iterations used in the training of the neural network. Guidelines for selecting the neural network parameters are also given.< ></abstract><pub>IEEE</pub><doi>10.1109/TENCON.1993.320480</doi></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISBN: 0780312333 |
| ispartof | Proceedings of TENCON '93. IEEE Region 10 International Conference on Computers, Communications and Automation, 1993, Vol.4, p.252-256 vol.4 |
| issn | |
| language | eng |
| recordid | cdi_ieee_primary_320480 |
| source | IEEE Electronic Library (IEL) Conference Proceedings |
| subjects | Application software Backpropagation Computer simulation Control system synthesis Convergence Neural networks Neurons Performance analysis Robot control Stability |
| title | Study of a neural network controller for robotic applications |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-07T17%3A44%3A10IST&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=Study%20of%20a%20neural%20network%20controller%20for%20robotic%20applications&rft.btitle=Proceedings%20of%20TENCON%20'93.%20IEEE%20Region%2010%20International%20Conference%20on%20Computers,%20Communications%20and%20Automation&rft.au=Chin,%20L.&rft.date=1993&rft.volume=4&rft.spage=252&rft.epage=256%20vol.4&rft.pages=252-256%20vol.4&rft.isbn=0780312333&rft.isbn_list=9780780312333&rft_id=info:doi/10.1109/TENCON.1993.320480&rft_dat=%3Cieee_6IE%3E320480%3C/ieee_6IE%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_ieee_id=320480&rfr_iscdi=true |