Relational attention-based Markov logic network for visual navigation
Abstract We argue the agent’s low generalization problem for searching target object in challenging visual navigation could be solved by "how" and "where" allowing the agent utilizing the scene priors. Although, recent works endow scene priors as fixed spatial features to provide...
Ausführliche Beschreibung
Gespeichert in:
| Autor*in: |
Zhou, Kang [verfasserIn] |
|---|
| Format: |
Artikel |
|---|---|
| Sprache: |
Englisch |
| Erschienen: |
2022 |
|---|
| Schlagwörter: |
|---|
| Anmerkung: |
© The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2022 |
|---|
| Übergeordnetes Werk: |
Enthalten in: The journal of supercomputing - Springer US, 1987, 78(2022), 7 vom: 20. Jan., Seite 9907-9933 |
|---|---|
| Übergeordnetes Werk: |
volume:78 ; year:2022 ; number:7 ; day:20 ; month:01 ; pages:9907-9933 |
| Links: |
|---|
| DOI / URN: |
10.1007/s11227-021-04283-5 |
|---|
| Katalog-ID: |
OLC2078498319 |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | OLC2078498319 | ||
| 003 | DE-627 | ||
| 005 | 20230506010615.0 | ||
| 007 | tu | ||
| 008 | 221220s2022 xx ||||| 00| ||eng c | ||
| 024 | 7 | |a 10.1007/s11227-021-04283-5 |2 doi | |
| 035 | |a (DE-627)OLC2078498319 | ||
| 035 | |a (DE-He213)s11227-021-04283-5-p | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 082 | 0 | 4 | |a 004 |a 620 |q VZ |
| 100 | 1 | |a Zhou, Kang |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Relational attention-based Markov logic network for visual navigation |
| 264 | 1 | |c 2022 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a ohne Hilfsmittel zu benutzen |b n |2 rdamedia | ||
| 338 | |a Band |b nc |2 rdacarrier | ||
| 500 | |a © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2022 | ||
| 520 | |a Abstract We argue the agent’s low generalization problem for searching target object in challenging visual navigation could be solved by "how" and "where" allowing the agent utilizing the scene priors. Although, recent works endow scene priors as fixed spatial features to provide good generalization in novel environment. However, these priors cannot adapt to new scenes. How to build scene priors and where to use the priors in visual navigation has not been well explored. We propose visual relationship detection module to adaptively build relational scene graph as priors. Besides, in order to use priors, we propose Graph attention Markov logical inference Network (GMN) module, which encodes the scene priors and performs precise action inference. GMN updates the graph structure in an unknown scene and estimates the shortest path in scene graph, whose emission probabilities from path to actions are pointwised by action samples in reinforcement learning to get optimal navigation policy. The whole navigation framework is driven by unsupervised reinforcement learning (RL) to exploit the environment. We conduct experiments on the AI2THOR virtual environment, and the results outperform the current most state-of-the-art both in SPL (Success weighted by Path Length) and success rate. | ||
| 650 | 4 | |a Graph attention network | |
| 650 | 4 | |a Visual navigation | |
| 650 | 4 | |a Markov logical network | |
| 650 | 4 | |a Visual relationship Detection | |
| 700 | 1 | |a Guo, Chi |4 aut | |
| 700 | 1 | |a Zhang, Huyin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t The journal of supercomputing |d Springer US, 1987 |g 78(2022), 7 vom: 20. Jan., Seite 9907-9933 |w (DE-627)13046466X |w (DE-600)740510-8 |w (DE-576)018667775 |x 0920-8542 |7 nnns |
| 773 | 1 | 8 | |g volume:78 |g year:2022 |g number:7 |g day:20 |g month:01 |g pages:9907-9933 |
| 856 | 4 | 1 | |u https://doi.org/10.1007/s11227-021-04283-5 |z lizenzpflichtig |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a SYSFLAG_A | ||
| 912 | |a GBV_OLC | ||
| 912 | |a SSG-OLC-TEC | ||
| 912 | |a SSG-OLC-MAT | ||
| 951 | |a AR | ||
| 952 | |d 78 |j 2022 |e 7 |b 20 |c 01 |h 9907-9933 | ||
| author_variant |
k z kz c g cg h z hz |
|---|---|
| matchkey_str |
article:09208542:2022----::eainltetobsdakvointoko |
| hierarchy_sort_str |
2022 |
| publishDate |
2022 |
| allfields |
10.1007/s11227-021-04283-5 doi (DE-627)OLC2078498319 (DE-He213)s11227-021-04283-5-p DE-627 ger DE-627 rakwb eng 004 620 VZ Zhou, Kang verfasserin aut Relational attention-based Markov logic network for visual navigation 2022 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2022 Abstract We argue the agent’s low generalization problem for searching target object in challenging visual navigation could be solved by "how" and "where" allowing the agent utilizing the scene priors. Although, recent works endow scene priors as fixed spatial features to provide good generalization in novel environment. However, these priors cannot adapt to new scenes. How to build scene priors and where to use the priors in visual navigation has not been well explored. We propose visual relationship detection module to adaptively build relational scene graph as priors. Besides, in order to use priors, we propose Graph attention Markov logical inference Network (GMN) module, which encodes the scene priors and performs precise action inference. GMN updates the graph structure in an unknown scene and estimates the shortest path in scene graph, whose emission probabilities from path to actions are pointwised by action samples in reinforcement learning to get optimal navigation policy. The whole navigation framework is driven by unsupervised reinforcement learning (RL) to exploit the environment. We conduct experiments on the AI2THOR virtual environment, and the results outperform the current most state-of-the-art both in SPL (Success weighted by Path Length) and success rate. Graph attention network Visual navigation Markov logical network Visual relationship Detection Guo, Chi aut Zhang, Huyin aut Enthalten in The journal of supercomputing Springer US, 1987 78(2022), 7 vom: 20. Jan., Seite 9907-9933 (DE-627)13046466X (DE-600)740510-8 (DE-576)018667775 0920-8542 nnns volume:78 year:2022 number:7 day:20 month:01 pages:9907-9933 https://doi.org/10.1007/s11227-021-04283-5 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-TEC SSG-OLC-MAT AR 78 2022 7 20 01 9907-9933 |
| spelling |
10.1007/s11227-021-04283-5 doi (DE-627)OLC2078498319 (DE-He213)s11227-021-04283-5-p DE-627 ger DE-627 rakwb eng 004 620 VZ Zhou, Kang verfasserin aut Relational attention-based Markov logic network for visual navigation 2022 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2022 Abstract We argue the agent’s low generalization problem for searching target object in challenging visual navigation could be solved by "how" and "where" allowing the agent utilizing the scene priors. Although, recent works endow scene priors as fixed spatial features to provide good generalization in novel environment. However, these priors cannot adapt to new scenes. How to build scene priors and where to use the priors in visual navigation has not been well explored. We propose visual relationship detection module to adaptively build relational scene graph as priors. Besides, in order to use priors, we propose Graph attention Markov logical inference Network (GMN) module, which encodes the scene priors and performs precise action inference. GMN updates the graph structure in an unknown scene and estimates the shortest path in scene graph, whose emission probabilities from path to actions are pointwised by action samples in reinforcement learning to get optimal navigation policy. The whole navigation framework is driven by unsupervised reinforcement learning (RL) to exploit the environment. We conduct experiments on the AI2THOR virtual environment, and the results outperform the current most state-of-the-art both in SPL (Success weighted by Path Length) and success rate. Graph attention network Visual navigation Markov logical network Visual relationship Detection Guo, Chi aut Zhang, Huyin aut Enthalten in The journal of supercomputing Springer US, 1987 78(2022), 7 vom: 20. Jan., Seite 9907-9933 (DE-627)13046466X (DE-600)740510-8 (DE-576)018667775 0920-8542 nnns volume:78 year:2022 number:7 day:20 month:01 pages:9907-9933 https://doi.org/10.1007/s11227-021-04283-5 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-TEC SSG-OLC-MAT AR 78 2022 7 20 01 9907-9933 |
| allfields_unstemmed |
10.1007/s11227-021-04283-5 doi (DE-627)OLC2078498319 (DE-He213)s11227-021-04283-5-p DE-627 ger DE-627 rakwb eng 004 620 VZ Zhou, Kang verfasserin aut Relational attention-based Markov logic network for visual navigation 2022 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2022 Abstract We argue the agent’s low generalization problem for searching target object in challenging visual navigation could be solved by "how" and "where" allowing the agent utilizing the scene priors. Although, recent works endow scene priors as fixed spatial features to provide good generalization in novel environment. However, these priors cannot adapt to new scenes. How to build scene priors and where to use the priors in visual navigation has not been well explored. We propose visual relationship detection module to adaptively build relational scene graph as priors. Besides, in order to use priors, we propose Graph attention Markov logical inference Network (GMN) module, which encodes the scene priors and performs precise action inference. GMN updates the graph structure in an unknown scene and estimates the shortest path in scene graph, whose emission probabilities from path to actions are pointwised by action samples in reinforcement learning to get optimal navigation policy. The whole navigation framework is driven by unsupervised reinforcement learning (RL) to exploit the environment. We conduct experiments on the AI2THOR virtual environment, and the results outperform the current most state-of-the-art both in SPL (Success weighted by Path Length) and success rate. Graph attention network Visual navigation Markov logical network Visual relationship Detection Guo, Chi aut Zhang, Huyin aut Enthalten in The journal of supercomputing Springer US, 1987 78(2022), 7 vom: 20. Jan., Seite 9907-9933 (DE-627)13046466X (DE-600)740510-8 (DE-576)018667775 0920-8542 nnns volume:78 year:2022 number:7 day:20 month:01 pages:9907-9933 https://doi.org/10.1007/s11227-021-04283-5 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-TEC SSG-OLC-MAT AR 78 2022 7 20 01 9907-9933 |
| allfieldsGer |
10.1007/s11227-021-04283-5 doi (DE-627)OLC2078498319 (DE-He213)s11227-021-04283-5-p DE-627 ger DE-627 rakwb eng 004 620 VZ Zhou, Kang verfasserin aut Relational attention-based Markov logic network for visual navigation 2022 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2022 Abstract We argue the agent’s low generalization problem for searching target object in challenging visual navigation could be solved by "how" and "where" allowing the agent utilizing the scene priors. Although, recent works endow scene priors as fixed spatial features to provide good generalization in novel environment. However, these priors cannot adapt to new scenes. How to build scene priors and where to use the priors in visual navigation has not been well explored. We propose visual relationship detection module to adaptively build relational scene graph as priors. Besides, in order to use priors, we propose Graph attention Markov logical inference Network (GMN) module, which encodes the scene priors and performs precise action inference. GMN updates the graph structure in an unknown scene and estimates the shortest path in scene graph, whose emission probabilities from path to actions are pointwised by action samples in reinforcement learning to get optimal navigation policy. The whole navigation framework is driven by unsupervised reinforcement learning (RL) to exploit the environment. We conduct experiments on the AI2THOR virtual environment, and the results outperform the current most state-of-the-art both in SPL (Success weighted by Path Length) and success rate. Graph attention network Visual navigation Markov logical network Visual relationship Detection Guo, Chi aut Zhang, Huyin aut Enthalten in The journal of supercomputing Springer US, 1987 78(2022), 7 vom: 20. Jan., Seite 9907-9933 (DE-627)13046466X (DE-600)740510-8 (DE-576)018667775 0920-8542 nnns volume:78 year:2022 number:7 day:20 month:01 pages:9907-9933 https://doi.org/10.1007/s11227-021-04283-5 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-TEC SSG-OLC-MAT AR 78 2022 7 20 01 9907-9933 |
| allfieldsSound |
10.1007/s11227-021-04283-5 doi (DE-627)OLC2078498319 (DE-He213)s11227-021-04283-5-p DE-627 ger DE-627 rakwb eng 004 620 VZ Zhou, Kang verfasserin aut Relational attention-based Markov logic network for visual navigation 2022 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2022 Abstract We argue the agent’s low generalization problem for searching target object in challenging visual navigation could be solved by "how" and "where" allowing the agent utilizing the scene priors. Although, recent works endow scene priors as fixed spatial features to provide good generalization in novel environment. However, these priors cannot adapt to new scenes. How to build scene priors and where to use the priors in visual navigation has not been well explored. We propose visual relationship detection module to adaptively build relational scene graph as priors. Besides, in order to use priors, we propose Graph attention Markov logical inference Network (GMN) module, which encodes the scene priors and performs precise action inference. GMN updates the graph structure in an unknown scene and estimates the shortest path in scene graph, whose emission probabilities from path to actions are pointwised by action samples in reinforcement learning to get optimal navigation policy. The whole navigation framework is driven by unsupervised reinforcement learning (RL) to exploit the environment. We conduct experiments on the AI2THOR virtual environment, and the results outperform the current most state-of-the-art both in SPL (Success weighted by Path Length) and success rate. Graph attention network Visual navigation Markov logical network Visual relationship Detection Guo, Chi aut Zhang, Huyin aut Enthalten in The journal of supercomputing Springer US, 1987 78(2022), 7 vom: 20. Jan., Seite 9907-9933 (DE-627)13046466X (DE-600)740510-8 (DE-576)018667775 0920-8542 nnns volume:78 year:2022 number:7 day:20 month:01 pages:9907-9933 https://doi.org/10.1007/s11227-021-04283-5 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-TEC SSG-OLC-MAT AR 78 2022 7 20 01 9907-9933 |
| language |
English |
| source |
Enthalten in The journal of supercomputing 78(2022), 7 vom: 20. Jan., Seite 9907-9933 volume:78 year:2022 number:7 day:20 month:01 pages:9907-9933 |
| sourceStr |
Enthalten in The journal of supercomputing 78(2022), 7 vom: 20. Jan., Seite 9907-9933 volume:78 year:2022 number:7 day:20 month:01 pages:9907-9933 |
| format_phy_str_mv |
Article |
| institution |
findex.gbv.de |
| topic_facet |
Graph attention network Visual navigation Markov logical network Visual relationship Detection |
| dewey-raw |
004 |
| isfreeaccess_bool |
false |
| container_title |
The journal of supercomputing |
| authorswithroles_txt_mv |
Zhou, Kang @@aut@@ Guo, Chi @@aut@@ Zhang, Huyin @@aut@@ |
| publishDateDaySort_date |
2022-01-20T00:00:00Z |
| hierarchy_top_id |
13046466X |
| dewey-sort |
14 |
| id |
OLC2078498319 |
| language_de |
englisch |
| fullrecord |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a22002652 4500</leader><controlfield tag="001">OLC2078498319</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230506010615.0</controlfield><controlfield tag="007">tu</controlfield><controlfield tag="008">221220s2022 xx ||||| 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1007/s11227-021-04283-5</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)OLC2078498319</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-He213)s11227-021-04283-5-p</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">004</subfield><subfield code="a">620</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Zhou, Kang</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Relational attention-based Markov logic network for visual navigation</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2022</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">Text</subfield><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">ohne Hilfsmittel zu benutzen</subfield><subfield code="b">n</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Band</subfield><subfield code="b">nc</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="500" ind1=" " ind2=" "><subfield code="a">© The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2022</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Abstract We argue the agent’s low generalization problem for searching target object in challenging visual navigation could be solved by "how" and "where" allowing the agent utilizing the scene priors. Although, recent works endow scene priors as fixed spatial features to provide good generalization in novel environment. However, these priors cannot adapt to new scenes. How to build scene priors and where to use the priors in visual navigation has not been well explored. We propose visual relationship detection module to adaptively build relational scene graph as priors. Besides, in order to use priors, we propose Graph attention Markov logical inference Network (GMN) module, which encodes the scene priors and performs precise action inference. GMN updates the graph structure in an unknown scene and estimates the shortest path in scene graph, whose emission probabilities from path to actions are pointwised by action samples in reinforcement learning to get optimal navigation policy. The whole navigation framework is driven by unsupervised reinforcement learning (RL) to exploit the environment. We conduct experiments on the AI2THOR virtual environment, and the results outperform the current most state-of-the-art both in SPL (Success weighted by Path Length) and success rate.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Graph attention network</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Visual navigation</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Markov logical network</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Visual relationship Detection</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Guo, Chi</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Zhang, Huyin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">The journal of supercomputing</subfield><subfield code="d">Springer US, 1987</subfield><subfield code="g">78(2022), 7 vom: 20. Jan., Seite 9907-9933</subfield><subfield code="w">(DE-627)13046466X</subfield><subfield code="w">(DE-600)740510-8</subfield><subfield code="w">(DE-576)018667775</subfield><subfield code="x">0920-8542</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:78</subfield><subfield code="g">year:2022</subfield><subfield code="g">number:7</subfield><subfield code="g">day:20</subfield><subfield code="g">month:01</subfield><subfield code="g">pages:9907-9933</subfield></datafield><datafield tag="856" ind1="4" ind2="1"><subfield code="u">https://doi.org/10.1007/s11227-021-04283-5</subfield><subfield code="z">lizenzpflichtig</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_OLC</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-TEC</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-MAT</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">78</subfield><subfield code="j">2022</subfield><subfield code="e">7</subfield><subfield code="b">20</subfield><subfield code="c">01</subfield><subfield code="h">9907-9933</subfield></datafield></record></collection>
|
| author |
Zhou, Kang |
| spellingShingle |
Zhou, Kang ddc 004 misc Graph attention network misc Visual navigation misc Markov logical network misc Visual relationship Detection Relational attention-based Markov logic network for visual navigation |
| authorStr |
Zhou, Kang |
| ppnlink_with_tag_str_mv |
@@773@@(DE-627)13046466X |
| format |
Article |
| dewey-ones |
004 - Data processing & computer science 620 - Engineering & allied operations |
| delete_txt_mv |
keep |
| author_role |
aut aut aut |
| collection |
OLC |
| remote_str |
false |
| illustrated |
Not Illustrated |
| issn |
0920-8542 |
| topic_title |
004 620 VZ Relational attention-based Markov logic network for visual navigation Graph attention network Visual navigation Markov logical network Visual relationship Detection |
| topic |
ddc 004 misc Graph attention network misc Visual navigation misc Markov logical network misc Visual relationship Detection |
| topic_unstemmed |
ddc 004 misc Graph attention network misc Visual navigation misc Markov logical network misc Visual relationship Detection |
| topic_browse |
ddc 004 misc Graph attention network misc Visual navigation misc Markov logical network misc Visual relationship Detection |
| format_facet |
Aufsätze Gedruckte Aufsätze |
| format_main_str_mv |
Text Zeitschrift/Artikel |
| carriertype_str_mv |
nc |
| hierarchy_parent_title |
The journal of supercomputing |
| hierarchy_parent_id |
13046466X |
| dewey-tens |
000 - Computer science, knowledge & systems 620 - Engineering |
| hierarchy_top_title |
The journal of supercomputing |
| isfreeaccess_txt |
false |
| familylinks_str_mv |
(DE-627)13046466X (DE-600)740510-8 (DE-576)018667775 |
| title |
Relational attention-based Markov logic network for visual navigation |
| ctrlnum |
(DE-627)OLC2078498319 (DE-He213)s11227-021-04283-5-p |
| title_full |
Relational attention-based Markov logic network for visual navigation |
| author_sort |
Zhou, Kang |
| journal |
The journal of supercomputing |
| journalStr |
The journal of supercomputing |
| lang_code |
eng |
| isOA_bool |
false |
| dewey-hundreds |
000 - Computer science, information & general works 600 - Technology |
| recordtype |
marc |
| publishDateSort |
2022 |
| contenttype_str_mv |
txt |
| container_start_page |
9907 |
| author_browse |
Zhou, Kang Guo, Chi Zhang, Huyin |
| container_volume |
78 |
| class |
004 620 VZ |
| format_se |
Aufsätze |
| author-letter |
Zhou, Kang |
| doi_str_mv |
10.1007/s11227-021-04283-5 |
| dewey-full |
004 620 |
| title_sort |
relational attention-based markov logic network for visual navigation |
| title_auth |
Relational attention-based Markov logic network for visual navigation |
| abstract |
Abstract We argue the agent’s low generalization problem for searching target object in challenging visual navigation could be solved by "how" and "where" allowing the agent utilizing the scene priors. Although, recent works endow scene priors as fixed spatial features to provide good generalization in novel environment. However, these priors cannot adapt to new scenes. How to build scene priors and where to use the priors in visual navigation has not been well explored. We propose visual relationship detection module to adaptively build relational scene graph as priors. Besides, in order to use priors, we propose Graph attention Markov logical inference Network (GMN) module, which encodes the scene priors and performs precise action inference. GMN updates the graph structure in an unknown scene and estimates the shortest path in scene graph, whose emission probabilities from path to actions are pointwised by action samples in reinforcement learning to get optimal navigation policy. The whole navigation framework is driven by unsupervised reinforcement learning (RL) to exploit the environment. We conduct experiments on the AI2THOR virtual environment, and the results outperform the current most state-of-the-art both in SPL (Success weighted by Path Length) and success rate. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2022 |
| abstractGer |
Abstract We argue the agent’s low generalization problem for searching target object in challenging visual navigation could be solved by "how" and "where" allowing the agent utilizing the scene priors. Although, recent works endow scene priors as fixed spatial features to provide good generalization in novel environment. However, these priors cannot adapt to new scenes. How to build scene priors and where to use the priors in visual navigation has not been well explored. We propose visual relationship detection module to adaptively build relational scene graph as priors. Besides, in order to use priors, we propose Graph attention Markov logical inference Network (GMN) module, which encodes the scene priors and performs precise action inference. GMN updates the graph structure in an unknown scene and estimates the shortest path in scene graph, whose emission probabilities from path to actions are pointwised by action samples in reinforcement learning to get optimal navigation policy. The whole navigation framework is driven by unsupervised reinforcement learning (RL) to exploit the environment. We conduct experiments on the AI2THOR virtual environment, and the results outperform the current most state-of-the-art both in SPL (Success weighted by Path Length) and success rate. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2022 |
| abstract_unstemmed |
Abstract We argue the agent’s low generalization problem for searching target object in challenging visual navigation could be solved by "how" and "where" allowing the agent utilizing the scene priors. Although, recent works endow scene priors as fixed spatial features to provide good generalization in novel environment. However, these priors cannot adapt to new scenes. How to build scene priors and where to use the priors in visual navigation has not been well explored. We propose visual relationship detection module to adaptively build relational scene graph as priors. Besides, in order to use priors, we propose Graph attention Markov logical inference Network (GMN) module, which encodes the scene priors and performs precise action inference. GMN updates the graph structure in an unknown scene and estimates the shortest path in scene graph, whose emission probabilities from path to actions are pointwised by action samples in reinforcement learning to get optimal navigation policy. The whole navigation framework is driven by unsupervised reinforcement learning (RL) to exploit the environment. We conduct experiments on the AI2THOR virtual environment, and the results outperform the current most state-of-the-art both in SPL (Success weighted by Path Length) and success rate. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2022 |
| collection_details |
GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-TEC SSG-OLC-MAT |
| container_issue |
7 |
| title_short |
Relational attention-based Markov logic network for visual navigation |
| url |
https://doi.org/10.1007/s11227-021-04283-5 |
| remote_bool |
false |
| author2 |
Guo, Chi Zhang, Huyin |
| author2Str |
Guo, Chi Zhang, Huyin |
| ppnlink |
13046466X |
| mediatype_str_mv |
n |
| isOA_txt |
false |
| hochschulschrift_bool |
false |
| doi_str |
10.1007/s11227-021-04283-5 |
| up_date |
2024-07-03T20:44:16.560Z |
| _version_ |
1803592093274210304 |
| fullrecord_marcxml |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a22002652 4500</leader><controlfield tag="001">OLC2078498319</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230506010615.0</controlfield><controlfield tag="007">tu</controlfield><controlfield tag="008">221220s2022 xx ||||| 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1007/s11227-021-04283-5</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)OLC2078498319</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-He213)s11227-021-04283-5-p</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">004</subfield><subfield code="a">620</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Zhou, Kang</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Relational attention-based Markov logic network for visual navigation</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2022</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">Text</subfield><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">ohne Hilfsmittel zu benutzen</subfield><subfield code="b">n</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Band</subfield><subfield code="b">nc</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="500" ind1=" " ind2=" "><subfield code="a">© The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2022</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Abstract We argue the agent’s low generalization problem for searching target object in challenging visual navigation could be solved by "how" and "where" allowing the agent utilizing the scene priors. Although, recent works endow scene priors as fixed spatial features to provide good generalization in novel environment. However, these priors cannot adapt to new scenes. How to build scene priors and where to use the priors in visual navigation has not been well explored. We propose visual relationship detection module to adaptively build relational scene graph as priors. Besides, in order to use priors, we propose Graph attention Markov logical inference Network (GMN) module, which encodes the scene priors and performs precise action inference. GMN updates the graph structure in an unknown scene and estimates the shortest path in scene graph, whose emission probabilities from path to actions are pointwised by action samples in reinforcement learning to get optimal navigation policy. The whole navigation framework is driven by unsupervised reinforcement learning (RL) to exploit the environment. We conduct experiments on the AI2THOR virtual environment, and the results outperform the current most state-of-the-art both in SPL (Success weighted by Path Length) and success rate.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Graph attention network</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Visual navigation</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Markov logical network</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Visual relationship Detection</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Guo, Chi</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Zhang, Huyin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">The journal of supercomputing</subfield><subfield code="d">Springer US, 1987</subfield><subfield code="g">78(2022), 7 vom: 20. Jan., Seite 9907-9933</subfield><subfield code="w">(DE-627)13046466X</subfield><subfield code="w">(DE-600)740510-8</subfield><subfield code="w">(DE-576)018667775</subfield><subfield code="x">0920-8542</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:78</subfield><subfield code="g">year:2022</subfield><subfield code="g">number:7</subfield><subfield code="g">day:20</subfield><subfield code="g">month:01</subfield><subfield code="g">pages:9907-9933</subfield></datafield><datafield tag="856" ind1="4" ind2="1"><subfield code="u">https://doi.org/10.1007/s11227-021-04283-5</subfield><subfield code="z">lizenzpflichtig</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_OLC</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-TEC</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-MAT</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">78</subfield><subfield code="j">2022</subfield><subfield code="e">7</subfield><subfield code="b">20</subfield><subfield code="c">01</subfield><subfield code="h">9907-9933</subfield></datafield></record></collection>
|
| score |
7.4017696 |