Loading…
Long-term Prediction of Motion Trajectories Using Path Homology Clusters
In order for robots to share their workspace with people, they need to reason about human motion efficiently. In this work we leverage large datasets of paths in order to infer local models that are able to perform long-term predictions of human motion. Further, since our method is based on simple d...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Conference Proceeding |
| Language: | English |
| Online Access: | Request full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| cited_by | |
|---|---|
| cites | |
| container_end_page | 772 |
| container_issue | |
| container_start_page | 765 |
| container_title | |
| container_volume | |
| creator | Frederico Carvalho, J. Vejdemo-Johansson, Mikael Pokorny, Florian T. Kragic, Danica |
| description | In order for robots to share their workspace with people, they need to reason about human motion efficiently. In this work we leverage large datasets of paths in order to infer local models that are able to perform long-term predictions of human motion. Further, since our method is based on simple dynamics, it is conceptually simple to understand and allows one to interpret the predictions produced, as well as to extract a cost function that can be used for planning. The main difference between our method and similar systems, is that we employ a map of the space and translate the motion of groups of paths into vector fields on that map. We test our method on synthetic data and show its performance on the Edinburgh forum pedestrian long-term tracking dataset [1] where we were able to outperform a Gaussian Mixture Model tasked with extracting dynamics from the paths. |
| doi_str_mv | 10.1109/IROS40897.2019.8968125 |
| format | conference_proceeding |
| fullrecord | <record><control><sourceid>ieee_CHZPO</sourceid><recordid>TN_cdi_ieee_primary_8968125</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>8968125</ieee_id><sourcerecordid>8968125</sourcerecordid><originalsourceid>FETCH-LOGICAL-i241t-cb116aa6aac40b9eff15336432bca6c7aa99b9fb2717e710ce0938bc930663523</originalsourceid><addsrcrecordid>eNotT19LwzAcjILgnPsEguQLtP5-SZs_j1LUDiobuj2PNKY1o22kqQ_79pY5OLh7uDvuCHlESBFBP60_Np8ZKC1TBqhTpYVCll-RO5RMYQaQqWuyYJjzBJQQt2QV4xEAEKSezQtSVmFok8mNPd2O7svbyYeBhoa-h7Pajebo7BRG7yLdRz-0dGumb1qGPnShPdGi-41zPN6Tm8Z00a0uvCT715ddUSbV5m1dPFeJZxlOia0RhTEzbAa1dk0zb-Mi46y2RlhpjNa1bmomUTqJYB1ormqrOQjBc8aX5OG_1zvnDj-j7814OlyO8z_3pE25</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Long-term Prediction of Motion Trajectories Using Path Homology Clusters</title><source>IEEE Xplore All Conference Series</source><creator>Frederico Carvalho, J. ; Vejdemo-Johansson, Mikael ; Pokorny, Florian T. ; Kragic, Danica</creator><creatorcontrib>Frederico Carvalho, J. ; Vejdemo-Johansson, Mikael ; Pokorny, Florian T. ; Kragic, Danica</creatorcontrib><description>In order for robots to share their workspace with people, they need to reason about human motion efficiently. In this work we leverage large datasets of paths in order to infer local models that are able to perform long-term predictions of human motion. Further, since our method is based on simple dynamics, it is conceptually simple to understand and allows one to interpret the predictions produced, as well as to extract a cost function that can be used for planning. The main difference between our method and similar systems, is that we employ a map of the space and translate the motion of groups of paths into vector fields on that map. We test our method on synthetic data and show its performance on the Edinburgh forum pedestrian long-term tracking dataset [1] where we were able to outperform a Gaussian Mixture Model tasked with extracting dynamics from the paths.</description><identifier>EISSN: 2153-0866</identifier><identifier>EISBN: 1728140048</identifier><identifier>EISBN: 9781728140049</identifier><identifier>DOI: 10.1109/IROS40897.2019.8968125</identifier><language>eng</language><publisher>IEEE</publisher><ispartof>2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2019, p.765-772</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/8968125$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,776,780,785,786,23909,23910,25118,27902,54530,54907</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/8968125$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Frederico Carvalho, J.</creatorcontrib><creatorcontrib>Vejdemo-Johansson, Mikael</creatorcontrib><creatorcontrib>Pokorny, Florian T.</creatorcontrib><creatorcontrib>Kragic, Danica</creatorcontrib><title>Long-term Prediction of Motion Trajectories Using Path Homology Clusters</title><title>2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)</title><addtitle>IROS</addtitle><description>In order for robots to share their workspace with people, they need to reason about human motion efficiently. In this work we leverage large datasets of paths in order to infer local models that are able to perform long-term predictions of human motion. Further, since our method is based on simple dynamics, it is conceptually simple to understand and allows one to interpret the predictions produced, as well as to extract a cost function that can be used for planning. The main difference between our method and similar systems, is that we employ a map of the space and translate the motion of groups of paths into vector fields on that map. We test our method on synthetic data and show its performance on the Edinburgh forum pedestrian long-term tracking dataset [1] where we were able to outperform a Gaussian Mixture Model tasked with extracting dynamics from the paths.</description><issn>2153-0866</issn><isbn>1728140048</isbn><isbn>9781728140049</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2019</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNotT19LwzAcjILgnPsEguQLtP5-SZs_j1LUDiobuj2PNKY1o22kqQ_79pY5OLh7uDvuCHlESBFBP60_Np8ZKC1TBqhTpYVCll-RO5RMYQaQqWuyYJjzBJQQt2QV4xEAEKSezQtSVmFok8mNPd2O7svbyYeBhoa-h7Pajebo7BRG7yLdRz-0dGumb1qGPnShPdGi-41zPN6Tm8Z00a0uvCT715ddUSbV5m1dPFeJZxlOia0RhTEzbAa1dk0zb-Mi46y2RlhpjNa1bmomUTqJYB1ormqrOQjBc8aX5OG_1zvnDj-j7814OlyO8z_3pE25</recordid><startdate>201911</startdate><enddate>201911</enddate><creator>Frederico Carvalho, J.</creator><creator>Vejdemo-Johansson, Mikael</creator><creator>Pokorny, Florian T.</creator><creator>Kragic, Danica</creator><general>IEEE</general><scope>6IE</scope><scope>6IH</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIO</scope></search><sort><creationdate>201911</creationdate><title>Long-term Prediction of Motion Trajectories Using Path Homology Clusters</title><author>Frederico Carvalho, J. ; Vejdemo-Johansson, Mikael ; Pokorny, Florian T. ; Kragic, Danica</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i241t-cb116aa6aac40b9eff15336432bca6c7aa99b9fb2717e710ce0938bc930663523</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2019</creationdate><toplevel>online_resources</toplevel><creatorcontrib>Frederico Carvalho, J.</creatorcontrib><creatorcontrib>Vejdemo-Johansson, Mikael</creatorcontrib><creatorcontrib>Pokorny, Florian T.</creatorcontrib><creatorcontrib>Kragic, Danica</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>Frederico Carvalho, J.</au><au>Vejdemo-Johansson, Mikael</au><au>Pokorny, Florian T.</au><au>Kragic, Danica</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Long-term Prediction of Motion Trajectories Using Path Homology Clusters</atitle><btitle>2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)</btitle><stitle>IROS</stitle><date>2019-11</date><risdate>2019</risdate><spage>765</spage><epage>772</epage><pages>765-772</pages><eissn>2153-0866</eissn><eisbn>1728140048</eisbn><eisbn>9781728140049</eisbn><abstract>In order for robots to share their workspace with people, they need to reason about human motion efficiently. In this work we leverage large datasets of paths in order to infer local models that are able to perform long-term predictions of human motion. Further, since our method is based on simple dynamics, it is conceptually simple to understand and allows one to interpret the predictions produced, as well as to extract a cost function that can be used for planning. The main difference between our method and similar systems, is that we employ a map of the space and translate the motion of groups of paths into vector fields on that map. We test our method on synthetic data and show its performance on the Edinburgh forum pedestrian long-term tracking dataset [1] where we were able to outperform a Gaussian Mixture Model tasked with extracting dynamics from the paths.</abstract><pub>IEEE</pub><doi>10.1109/IROS40897.2019.8968125</doi><tpages>8</tpages></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | EISSN: 2153-0866 |
| ispartof | 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2019, p.765-772 |
| issn | 2153-0866 |
| language | eng |
| recordid | cdi_ieee_primary_8968125 |
| source | IEEE Xplore All Conference Series |
| title | Long-term Prediction of Motion Trajectories Using Path Homology Clusters |
| url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-06T02%3A55%3A26IST&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=Long-term%20Prediction%20of%20Motion%20Trajectories%20Using%20Path%20Homology%20Clusters&rft.btitle=2019%20IEEE/RSJ%20International%20Conference%20on%20Intelligent%20Robots%20and%20Systems%20(IROS)&rft.au=Frederico%20Carvalho,%20J.&rft.date=2019-11&rft.spage=765&rft.epage=772&rft.pages=765-772&rft.eissn=2153-0866&rft_id=info:doi/10.1109/IROS40897.2019.8968125&rft.eisbn=1728140048&rft.eisbn_list=9781728140049&rft_dat=%3Cieee_CHZPO%3E8968125%3C/ieee_CHZPO%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i241t-cb116aa6aac40b9eff15336432bca6c7aa99b9fb2717e710ce0938bc930663523%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=8968125&rfr_iscdi=true |