Robust trajectory segmentation for programming by demonstration

A novel trajectory segmentation and modeling approach is presented. Trajectory segmentation and matching is an important step in the programming by demonstration (PbD) process to extract the user's intentions from multiple trajectories. To match multiple trajectories, the segmentation and model...

Full description

Saved in:
Bibliographic Details
Main Authors: Abbas, T., MacDonald, B.A.
Format: Conference Proceeding
Language:English
Subjects:
Hidden Markov models
Humans
Image segmentation
Mobile robots
Navigation
Robot kinematics
Robot programming
Robot sensing systems
Robustness
Wheels
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page 1209
container_issue
container_start_page 1204
container_title
container_volume
creator Abbas, T.
MacDonald, B.A.
description A novel trajectory segmentation and modeling approach is presented. Trajectory segmentation and matching is an important step in the programming by demonstration (PbD) process to extract the user's intentions from multiple trajectories. To match multiple trajectories, the segmentation and modeling approach must be consistent and robust to disparities caused by robot dynamics and human imperfections. Several curve segmentation approaches have demonstrated substantial potential in the field of image processing and gesture recognition. They emphasize reduction of the degree of mismatch between given and model curves. However they fail to reduce mismatch between models of multiple trajectories recorded to demonstrate the same intention.We propose an M-estimator for trajectory modeling and set up a new segmentation criterion to address the issue. The proposed approach is better suited for PbD of mobile robots. The approach is evaluated for real robot trajectories.
doi_str_mv 10.1109/ROMAN.2009.5326281
format conference_proceeding
fullrecord <record><control><sourceid>ieee_CHZPO</sourceid><recordid>TN_cdi_ieee_primary_5326281</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>5326281</ieee_id><sourcerecordid>5326281</sourcerecordid><originalsourceid>FETCH-LOGICAL-i90t-1a714ee6a726781f48ad57b48ca074b9019ced0765496697eaa0566d8efd947d3</originalsourceid><addsrcrecordid>eNo9j81Kw0AUhUdRsNa-gG7mBRLnJnf-VlKKf1AtlO7LJHMTUkxSZsZF3t6KxbM5Z_GdA4exexA5gLCP283H8jMvhLC5LAtVGLhgt4AFohQGxCWbgUXMLJb66j-jvGGLGA_iJIsAWs7Y03asvmPiKbgD1WkME4_U9jQkl7px4M0Y-DGMbXB93w0trybuqR-HeCr8AnfsunFfkRZnn7Pdy_Nu9ZatN6_vq-U666xIGTgNSKScLpQ20KBxXuoKTe2ExsoKsDV5oZVEq5TV5JyQSnlDjbeofTlnD3-zHRHtj6HrXZj25-vlD0sfS_0</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Robust trajectory segmentation for programming by demonstration</title><source>IEEE Xplore All Conference Series</source><creator>Abbas, T. ; MacDonald, B.A.</creator><creatorcontrib>Abbas, T. ; MacDonald, B.A.</creatorcontrib><description>A novel trajectory segmentation and modeling approach is presented. Trajectory segmentation and matching is an important step in the programming by demonstration (PbD) process to extract the user's intentions from multiple trajectories. To match multiple trajectories, the segmentation and modeling approach must be consistent and robust to disparities caused by robot dynamics and human imperfections. Several curve segmentation approaches have demonstrated substantial potential in the field of image processing and gesture recognition. They emphasize reduction of the degree of mismatch between given and model curves. However they fail to reduce mismatch between models of multiple trajectories recorded to demonstrate the same intention.We propose an M-estimator for trajectory modeling and set up a new segmentation criterion to address the issue. The proposed approach is better suited for PbD of mobile robots. The approach is evaluated for real robot trajectories.</description><identifier>ISSN: 1944-9445</identifier><identifier>EISSN: 1944-9437</identifier><identifier>EISBN: 1424450810</identifier><identifier>EISBN: 9781424450817</identifier><identifier>DOI: 10.1109/ROMAN.2009.5326281</identifier><language>eng</language><publisher>IEEE</publisher><subject>Hidden Markov models ; Humans ; Image segmentation ; Mobile robots ; Navigation ; Robot kinematics ; Robot programming ; Robot sensing systems ; Robustness ; Wheels</subject><ispartof>RO-MAN 2009 - The 18th IEEE International Symposium on Robot and Human Interactive Communication, 2009, p.1204-1209</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/5326281$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,23930,23931,25140,27925,54555,54932</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/5326281$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Abbas, T.</creatorcontrib><creatorcontrib>MacDonald, B.A.</creatorcontrib><title>Robust trajectory segmentation for programming by demonstration</title><title>RO-MAN 2009 - The 18th IEEE International Symposium on Robot and Human Interactive Communication</title><addtitle>ROMAN</addtitle><description>A novel trajectory segmentation and modeling approach is presented. Trajectory segmentation and matching is an important step in the programming by demonstration (PbD) process to extract the user's intentions from multiple trajectories. To match multiple trajectories, the segmentation and modeling approach must be consistent and robust to disparities caused by robot dynamics and human imperfections. Several curve segmentation approaches have demonstrated substantial potential in the field of image processing and gesture recognition. They emphasize reduction of the degree of mismatch between given and model curves. However they fail to reduce mismatch between models of multiple trajectories recorded to demonstrate the same intention.We propose an M-estimator for trajectory modeling and set up a new segmentation criterion to address the issue. The proposed approach is better suited for PbD of mobile robots. The approach is evaluated for real robot trajectories.</description><subject>Hidden Markov models</subject><subject>Humans</subject><subject>Image segmentation</subject><subject>Mobile robots</subject><subject>Navigation</subject><subject>Robot kinematics</subject><subject>Robot programming</subject><subject>Robot sensing systems</subject><subject>Robustness</subject><subject>Wheels</subject><issn>1944-9445</issn><issn>1944-9437</issn><isbn>1424450810</isbn><isbn>9781424450817</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2009</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNo9j81Kw0AUhUdRsNa-gG7mBRLnJnf-VlKKf1AtlO7LJHMTUkxSZsZF3t6KxbM5Z_GdA4exexA5gLCP283H8jMvhLC5LAtVGLhgt4AFohQGxCWbgUXMLJb66j-jvGGLGA_iJIsAWs7Y03asvmPiKbgD1WkME4_U9jQkl7px4M0Y-DGMbXB93w0trybuqR-HeCr8AnfsunFfkRZnn7Pdy_Nu9ZatN6_vq-U666xIGTgNSKScLpQ20KBxXuoKTe2ExsoKsDV5oZVEq5TV5JyQSnlDjbeofTlnD3-zHRHtj6HrXZj25-vlD0sfS_0</recordid><startdate>200909</startdate><enddate>200909</enddate><creator>Abbas, T.</creator><creator>MacDonald, B.A.</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>200909</creationdate><title>Robust trajectory segmentation for programming by demonstration</title><author>Abbas, T. ; MacDonald, B.A.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i90t-1a714ee6a726781f48ad57b48ca074b9019ced0765496697eaa0566d8efd947d3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2009</creationdate><topic>Hidden Markov models</topic><topic>Humans</topic><topic>Image segmentation</topic><topic>Mobile robots</topic><topic>Navigation</topic><topic>Robot kinematics</topic><topic>Robot programming</topic><topic>Robot sensing systems</topic><topic>Robustness</topic><topic>Wheels</topic><toplevel>online_resources</toplevel><creatorcontrib>Abbas, T.</creatorcontrib><creatorcontrib>MacDonald, B.A.</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 Online</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>Abbas, T.</au><au>MacDonald, B.A.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Robust trajectory segmentation for programming by demonstration</atitle><btitle>RO-MAN 2009 - The 18th IEEE International Symposium on Robot and Human Interactive Communication</btitle><stitle>ROMAN</stitle><date>2009-09</date><risdate>2009</risdate><spage>1204</spage><epage>1209</epage><pages>1204-1209</pages><issn>1944-9445</issn><eissn>1944-9437</eissn><eisbn>1424450810</eisbn><eisbn>9781424450817</eisbn><abstract>A novel trajectory segmentation and modeling approach is presented. Trajectory segmentation and matching is an important step in the programming by demonstration (PbD) process to extract the user's intentions from multiple trajectories. To match multiple trajectories, the segmentation and modeling approach must be consistent and robust to disparities caused by robot dynamics and human imperfections. Several curve segmentation approaches have demonstrated substantial potential in the field of image processing and gesture recognition. They emphasize reduction of the degree of mismatch between given and model curves. However they fail to reduce mismatch between models of multiple trajectories recorded to demonstrate the same intention.We propose an M-estimator for trajectory modeling and set up a new segmentation criterion to address the issue. The proposed approach is better suited for PbD of mobile robots. The approach is evaluated for real robot trajectories.</abstract><pub>IEEE</pub><doi>10.1109/ROMAN.2009.5326281</doi><tpages>6</tpages></addata></record>
fulltext fulltext_linktorsrc
identifier ISSN: 1944-9445
ispartof RO-MAN 2009 - The 18th IEEE International Symposium on Robot and Human Interactive Communication, 2009, p.1204-1209
issn 1944-9445
1944-9437
language eng
recordid cdi_ieee_primary_5326281
source IEEE Xplore All Conference Series
subjects Hidden Markov models
Humans
Image segmentation
Mobile robots
Navigation
Robot kinematics
Robot programming
Robot sensing systems
Robustness
Wheels
title Robust trajectory segmentation for programming by demonstration
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-23T01%3A25%3A35IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_CHZPO&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Robust%20trajectory%20segmentation%20for%20programming%20by%20demonstration&rft.btitle=RO-MAN%202009%20-%20The%2018th%20IEEE%20International%20Symposium%20on%20Robot%20and%20Human%20Interactive%20Communication&rft.au=Abbas,%20T.&rft.date=2009-09&rft.spage=1204&rft.epage=1209&rft.pages=1204-1209&rft.issn=1944-9445&rft.eissn=1944-9437&rft_id=info:doi/10.1109/ROMAN.2009.5326281&rft.eisbn=1424450810&rft.eisbn_list=9781424450817&rft_dat=%3Cieee_CHZPO%3E5326281%3C/ieee_CHZPO%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i90t-1a714ee6a726781f48ad57b48ca074b9019ced0765496697eaa0566d8efd947d3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=5326281&rfr_iscdi=true