Evaluating movement skills from extended neural complexity

For a robot to learn complex movement skills, programming by demonstration and/or learning by trial and error is necessary. Measuring the complexity of such movement skills is important to decide the appropriate learning model, and the required size of dataset and additional prior knowledge. To deal...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Woo Young Kwon, Il Hong Suh, Bum-Jae You, Sang-Rok Oh
Format: Tagungsbericht
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 2573
container_issue
container_start_page 2568
container_title
container_volume
creator Woo Young Kwon
Il Hong Suh
Bum-Jae You
Sang-Rok Oh
description For a robot to learn complex movement skills, programming by demonstration and/or learning by trial and error is necessary. Measuring the complexity of such movement skills is important to decide the appropriate learning model, and the required size of dataset and additional prior knowledge. To deal with measuring the complexity of movement skills for robots, we propose an information-theoretic complexity measure. By modeling proprioceptive as well as exteroceptive sensory data as a multivariate Gaussian distribution, movement skills can be modeled as a probabilistic model. Next, complexity of the movement skills is measured by using neural complexity. In addition to the original neural complexity measure, endogeneous changes in time of the movement skills are modeled by sampling in time and modeling as individual random variables. To evaluate our proposed complexity measure, several experiments are performed on real robotic movement skills.
doi_str_mv 10.1109/ICSMC.2012.6378132
format Conference Proceeding
fullrecord <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_6378132</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>6378132</ieee_id><sourcerecordid>6378132</sourcerecordid><originalsourceid>FETCH-LOGICAL-i175t-db6abb9bd6deb60740d6b459835ccd4442795cf8fd00e91291c056517b73b2733</originalsourceid><addsrcrecordid>eNotkMlOwzAURc0kkZb-AGz8Awl-HmN2KCpQqYgFILGr7PgFGTJUSVq1f18ksrqLc3QWl5BbYBkAs_er4v21yDgDnmlhchD8jMxAaiPAgJTnJOHKmBS0UhdkYf-MiQl7SRJgmqeW869rMhuGH8Y4k5An5GG5d_XOjbH9pk23xwbbkQ6_sa4HWvVdQ_EwYhsw0BZ3vatp2TXbGg9xPN6Qq8rVAy6mnZPPp-VH8ZKu355XxeM6jWDUmAavnffWBx3Qa2YkC9pLZXOhyjJIKbmxqqzyKjCGFriFkimtwHgjPDdCzMndfzci4mbbx8b1x830gTgBL89MOA</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Evaluating movement skills from extended neural complexity</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Woo Young Kwon ; Il Hong Suh ; Bum-Jae You ; Sang-Rok Oh</creator><creatorcontrib>Woo Young Kwon ; Il Hong Suh ; Bum-Jae You ; Sang-Rok Oh</creatorcontrib><description>For a robot to learn complex movement skills, programming by demonstration and/or learning by trial and error is necessary. Measuring the complexity of such movement skills is important to decide the appropriate learning model, and the required size of dataset and additional prior knowledge. To deal with measuring the complexity of movement skills for robots, we propose an information-theoretic complexity measure. By modeling proprioceptive as well as exteroceptive sensory data as a multivariate Gaussian distribution, movement skills can be modeled as a probabilistic model. Next, complexity of the movement skills is measured by using neural complexity. In addition to the original neural complexity measure, endogeneous changes in time of the movement skills are modeled by sampling in time and modeling as individual random variables. To evaluate our proposed complexity measure, several experiments are performed on real robotic movement skills.</description><identifier>ISSN: 1062-922X</identifier><identifier>ISBN: 9781467317139</identifier><identifier>ISBN: 1467317136</identifier><identifier>EISSN: 2577-1655</identifier><identifier>EISBN: 1467317144</identifier><identifier>EISBN: 9781467317122</identifier><identifier>EISBN: 9781467317146</identifier><identifier>EISBN: 1467317128</identifier><identifier>DOI: 10.1109/ICSMC.2012.6378132</identifier><language>eng</language><publisher>IEEE</publisher><subject>Complexity measure ; Complexity theory ; Entropy ; Gaussian distribution ; Movement skills ; Mutual information ; Neural complexity ; Random variables ; Robots ; Time measurement ; Time-sliced Neural Complexity</subject><ispartof>2012 IEEE International Conference on Systems, Man, and Cybernetics (SMC), 2012, p.2568-2573</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/6378132$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,777,781,786,787,2052,27906,54901</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/6378132$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Woo Young Kwon</creatorcontrib><creatorcontrib>Il Hong Suh</creatorcontrib><creatorcontrib>Bum-Jae You</creatorcontrib><creatorcontrib>Sang-Rok Oh</creatorcontrib><title>Evaluating movement skills from extended neural complexity</title><title>2012 IEEE International Conference on Systems, Man, and Cybernetics (SMC)</title><addtitle>ICSMC</addtitle><description>For a robot to learn complex movement skills, programming by demonstration and/or learning by trial and error is necessary. Measuring the complexity of such movement skills is important to decide the appropriate learning model, and the required size of dataset and additional prior knowledge. To deal with measuring the complexity of movement skills for robots, we propose an information-theoretic complexity measure. By modeling proprioceptive as well as exteroceptive sensory data as a multivariate Gaussian distribution, movement skills can be modeled as a probabilistic model. Next, complexity of the movement skills is measured by using neural complexity. In addition to the original neural complexity measure, endogeneous changes in time of the movement skills are modeled by sampling in time and modeling as individual random variables. To evaluate our proposed complexity measure, several experiments are performed on real robotic movement skills.</description><subject>Complexity measure</subject><subject>Complexity theory</subject><subject>Entropy</subject><subject>Gaussian distribution</subject><subject>Movement skills</subject><subject>Mutual information</subject><subject>Neural complexity</subject><subject>Random variables</subject><subject>Robots</subject><subject>Time measurement</subject><subject>Time-sliced Neural Complexity</subject><issn>1062-922X</issn><issn>2577-1655</issn><isbn>9781467317139</isbn><isbn>1467317136</isbn><isbn>1467317144</isbn><isbn>9781467317122</isbn><isbn>9781467317146</isbn><isbn>1467317128</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2012</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNotkMlOwzAURc0kkZb-AGz8Awl-HmN2KCpQqYgFILGr7PgFGTJUSVq1f18ksrqLc3QWl5BbYBkAs_er4v21yDgDnmlhchD8jMxAaiPAgJTnJOHKmBS0UhdkYf-MiQl7SRJgmqeW869rMhuGH8Y4k5An5GG5d_XOjbH9pk23xwbbkQ6_sa4HWvVdQ_EwYhsw0BZ3vatp2TXbGg9xPN6Qq8rVAy6mnZPPp-VH8ZKu355XxeM6jWDUmAavnffWBx3Qa2YkC9pLZXOhyjJIKbmxqqzyKjCGFriFkimtwHgjPDdCzMndfzci4mbbx8b1x830gTgBL89MOA</recordid><startdate>201210</startdate><enddate>201210</enddate><creator>Woo Young Kwon</creator><creator>Il Hong Suh</creator><creator>Bum-Jae You</creator><creator>Sang-Rok Oh</creator><general>IEEE</general><scope>6IE</scope><scope>6IH</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIO</scope></search><sort><creationdate>201210</creationdate><title>Evaluating movement skills from extended neural complexity</title><author>Woo Young Kwon ; Il Hong Suh ; Bum-Jae You ; Sang-Rok Oh</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i175t-db6abb9bd6deb60740d6b459835ccd4442795cf8fd00e91291c056517b73b2733</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2012</creationdate><topic>Complexity measure</topic><topic>Complexity theory</topic><topic>Entropy</topic><topic>Gaussian distribution</topic><topic>Movement skills</topic><topic>Mutual information</topic><topic>Neural complexity</topic><topic>Random variables</topic><topic>Robots</topic><topic>Time measurement</topic><topic>Time-sliced Neural Complexity</topic><toplevel>online_resources</toplevel><creatorcontrib>Woo Young Kwon</creatorcontrib><creatorcontrib>Il Hong Suh</creatorcontrib><creatorcontrib>Bum-Jae You</creatorcontrib><creatorcontrib>Sang-Rok Oh</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan (POP) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Electronic Library (IEL)</collection><collection>IEEE Proceedings Order Plans (POP) 1998-present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Woo Young Kwon</au><au>Il Hong Suh</au><au>Bum-Jae You</au><au>Sang-Rok Oh</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Evaluating movement skills from extended neural complexity</atitle><btitle>2012 IEEE International Conference on Systems, Man, and Cybernetics (SMC)</btitle><stitle>ICSMC</stitle><date>2012-10</date><risdate>2012</risdate><spage>2568</spage><epage>2573</epage><pages>2568-2573</pages><issn>1062-922X</issn><eissn>2577-1655</eissn><isbn>9781467317139</isbn><isbn>1467317136</isbn><eisbn>1467317144</eisbn><eisbn>9781467317122</eisbn><eisbn>9781467317146</eisbn><eisbn>1467317128</eisbn><abstract>For a robot to learn complex movement skills, programming by demonstration and/or learning by trial and error is necessary. Measuring the complexity of such movement skills is important to decide the appropriate learning model, and the required size of dataset and additional prior knowledge. To deal with measuring the complexity of movement skills for robots, we propose an information-theoretic complexity measure. By modeling proprioceptive as well as exteroceptive sensory data as a multivariate Gaussian distribution, movement skills can be modeled as a probabilistic model. Next, complexity of the movement skills is measured by using neural complexity. In addition to the original neural complexity measure, endogeneous changes in time of the movement skills are modeled by sampling in time and modeling as individual random variables. To evaluate our proposed complexity measure, several experiments are performed on real robotic movement skills.</abstract><pub>IEEE</pub><doi>10.1109/ICSMC.2012.6378132</doi><tpages>6</tpages></addata></record>
fulltext fulltext_linktorsrc
identifier ISSN: 1062-922X
ispartof 2012 IEEE International Conference on Systems, Man, and Cybernetics (SMC), 2012, p.2568-2573
issn 1062-922X
2577-1655
language eng
recordid cdi_ieee_primary_6378132
source IEEE Electronic Library (IEL) Conference Proceedings
subjects Complexity measure
Complexity theory
Entropy
Gaussian distribution
Movement skills
Mutual information
Neural complexity
Random variables
Robots
Time measurement
Time-sliced Neural Complexity
title Evaluating movement skills from extended neural complexity
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-20T19%3A03%3A35IST&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=Evaluating%20movement%20skills%20from%20extended%20neural%20complexity&rft.btitle=2012%20IEEE%20International%20Conference%20on%20Systems,%20Man,%20and%20Cybernetics%20(SMC)&rft.au=Woo%20Young%20Kwon&rft.date=2012-10&rft.spage=2568&rft.epage=2573&rft.pages=2568-2573&rft.issn=1062-922X&rft.eissn=2577-1655&rft.isbn=9781467317139&rft.isbn_list=1467317136&rft_id=info:doi/10.1109/ICSMC.2012.6378132&rft_dat=%3Cieee_6IE%3E6378132%3C/ieee_6IE%3E%3Curl%3E%3C/url%3E&rft.eisbn=1467317144&rft.eisbn_list=9781467317122&rft.eisbn_list=9781467317146&rft.eisbn_list=1467317128&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=6378132&rfr_iscdi=true