Autonomous robots: potential, advances and future direction
Abstract Recent advances in machine learning, such as deep neural networks, have caused a huge boost in many different areas of artificial intelligence and robotics. These methods typically require a large corpus of well-prepared and labelled training data, which limits the applicability to robotics...
Ausführliche Beschreibung
Autor*in: |
Hangl, Simon [verfasserIn] |
---|
Format: |
Artikel |
---|---|
Sprache: |
Englisch |
Erschienen: |
2017 |
---|
Schlagwörter: |
---|
Anmerkung: |
© Springer-Verlag GmbH Austria 2017 |
---|
Übergeordnetes Werk: |
Enthalten in: Elektrotechnik und Informationstechnik - Springer Vienna, 1988, 134(2017), 6 vom: Sept., Seite 293-298 |
---|---|
Übergeordnetes Werk: |
volume:134 ; year:2017 ; number:6 ; month:09 ; pages:293-298 |
Links: |
---|
DOI / URN: |
10.1007/s00502-017-0516-0 |
---|
Katalog-ID: |
OLC2065341335 |
---|
LEADER | 01000caa a22002652 4500 | ||
---|---|---|---|
001 | OLC2065341335 | ||
003 | DE-627 | ||
005 | 20230502112549.0 | ||
007 | tu | ||
008 | 200820s2017 xx ||||| 00| ||eng c | ||
024 | 7 | |a 10.1007/s00502-017-0516-0 |2 doi | |
035 | |a (DE-627)OLC2065341335 | ||
035 | |a (DE-He213)s00502-017-0516-0-p | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
082 | 0 | 4 | |a 620 |a 004 |a 070 |q VZ |
100 | 1 | |a Hangl, Simon |e verfasserin |4 aut | |
245 | 1 | 0 | |a Autonomous robots: potential, advances and future direction |
264 | 1 | |c 2017 | |
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 © Springer-Verlag GmbH Austria 2017 | ||
520 | |a Abstract Recent advances in machine learning, such as deep neural networks, have caused a huge boost in many different areas of artificial intelligence and robotics. These methods typically require a large corpus of well-prepared and labelled training data, which limits the applicability to robotics. In our opinion, a fundamental challenge in autonomous robotics is to design systems that are simple enough to solve simple tasks. These systems should grow in complexity step by step and more complex models like neural networks should be trained by re-using the information acquired over the robot’s lifetime. Ultimately, high-level abstractions should be generated from these models, bridging the gap from low-level sensor data to high-level AI systems. We present first steps into this direction and analyse their limitations and future extensions in order to achieve the goal of designing autonomous agents. | ||
650 | 4 | |a autonomous robots | |
650 | 4 | |a cognitive robotics | |
650 | 4 | |a developmental robotics | |
650 | 4 | |a lifelong learning | |
650 | 4 | |a robot creativity | |
650 | 4 | |a robot playing | |
700 | 1 | |a Ugur, Emre |4 aut | |
700 | 1 | |a Piater, Justus |4 aut | |
773 | 0 | 8 | |i Enthalten in |t Elektrotechnik und Informationstechnik |d Springer Vienna, 1988 |g 134(2017), 6 vom: Sept., Seite 293-298 |h 30 cm |w (DE-627)129622184 |w (DE-600)246725-2 |w (DE-576)015132323 |x 0932-383X |7 nnns |
773 | 1 | 8 | |g volume:134 |g year:2017 |g number:6 |g month:09 |g pages:293-298 |
856 | 4 | 1 | |u https://doi.org/10.1007/s00502-017-0516-0 |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 | ||
912 | |a GBV_ILN_70 | ||
912 | |a GBV_ILN_161 | ||
912 | |a GBV_ILN_207 | ||
912 | |a GBV_ILN_267 | ||
912 | |a GBV_ILN_2014 | ||
912 | |a GBV_ILN_4328 | ||
951 | |a AR | ||
952 | |d 134 |j 2017 |e 6 |c 09 |h 293-298 |
author_variant |
s h sh e u eu j p jp |
---|---|
matchkey_str |
article:0932383X:2017----::uooosoosoetaavnead |
hierarchy_sort_str |
2017 |
publishDate |
2017 |
allfields |
10.1007/s00502-017-0516-0 doi (DE-627)OLC2065341335 (DE-He213)s00502-017-0516-0-p DE-627 ger DE-627 rakwb eng 620 004 070 VZ Hangl, Simon verfasserin aut Autonomous robots: potential, advances and future direction 2017 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © Springer-Verlag GmbH Austria 2017 Abstract Recent advances in machine learning, such as deep neural networks, have caused a huge boost in many different areas of artificial intelligence and robotics. These methods typically require a large corpus of well-prepared and labelled training data, which limits the applicability to robotics. In our opinion, a fundamental challenge in autonomous robotics is to design systems that are simple enough to solve simple tasks. These systems should grow in complexity step by step and more complex models like neural networks should be trained by re-using the information acquired over the robot’s lifetime. Ultimately, high-level abstractions should be generated from these models, bridging the gap from low-level sensor data to high-level AI systems. We present first steps into this direction and analyse their limitations and future extensions in order to achieve the goal of designing autonomous agents. autonomous robots cognitive robotics developmental robotics lifelong learning robot creativity robot playing Ugur, Emre aut Piater, Justus aut Enthalten in Elektrotechnik und Informationstechnik Springer Vienna, 1988 134(2017), 6 vom: Sept., Seite 293-298 30 cm (DE-627)129622184 (DE-600)246725-2 (DE-576)015132323 0932-383X nnns volume:134 year:2017 number:6 month:09 pages:293-298 https://doi.org/10.1007/s00502-017-0516-0 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-TEC SSG-OLC-MAT GBV_ILN_70 GBV_ILN_161 GBV_ILN_207 GBV_ILN_267 GBV_ILN_2014 GBV_ILN_4328 AR 134 2017 6 09 293-298 |
spelling |
10.1007/s00502-017-0516-0 doi (DE-627)OLC2065341335 (DE-He213)s00502-017-0516-0-p DE-627 ger DE-627 rakwb eng 620 004 070 VZ Hangl, Simon verfasserin aut Autonomous robots: potential, advances and future direction 2017 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © Springer-Verlag GmbH Austria 2017 Abstract Recent advances in machine learning, such as deep neural networks, have caused a huge boost in many different areas of artificial intelligence and robotics. These methods typically require a large corpus of well-prepared and labelled training data, which limits the applicability to robotics. In our opinion, a fundamental challenge in autonomous robotics is to design systems that are simple enough to solve simple tasks. These systems should grow in complexity step by step and more complex models like neural networks should be trained by re-using the information acquired over the robot’s lifetime. Ultimately, high-level abstractions should be generated from these models, bridging the gap from low-level sensor data to high-level AI systems. We present first steps into this direction and analyse their limitations and future extensions in order to achieve the goal of designing autonomous agents. autonomous robots cognitive robotics developmental robotics lifelong learning robot creativity robot playing Ugur, Emre aut Piater, Justus aut Enthalten in Elektrotechnik und Informationstechnik Springer Vienna, 1988 134(2017), 6 vom: Sept., Seite 293-298 30 cm (DE-627)129622184 (DE-600)246725-2 (DE-576)015132323 0932-383X nnns volume:134 year:2017 number:6 month:09 pages:293-298 https://doi.org/10.1007/s00502-017-0516-0 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-TEC SSG-OLC-MAT GBV_ILN_70 GBV_ILN_161 GBV_ILN_207 GBV_ILN_267 GBV_ILN_2014 GBV_ILN_4328 AR 134 2017 6 09 293-298 |
allfields_unstemmed |
10.1007/s00502-017-0516-0 doi (DE-627)OLC2065341335 (DE-He213)s00502-017-0516-0-p DE-627 ger DE-627 rakwb eng 620 004 070 VZ Hangl, Simon verfasserin aut Autonomous robots: potential, advances and future direction 2017 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © Springer-Verlag GmbH Austria 2017 Abstract Recent advances in machine learning, such as deep neural networks, have caused a huge boost in many different areas of artificial intelligence and robotics. These methods typically require a large corpus of well-prepared and labelled training data, which limits the applicability to robotics. In our opinion, a fundamental challenge in autonomous robotics is to design systems that are simple enough to solve simple tasks. These systems should grow in complexity step by step and more complex models like neural networks should be trained by re-using the information acquired over the robot’s lifetime. Ultimately, high-level abstractions should be generated from these models, bridging the gap from low-level sensor data to high-level AI systems. We present first steps into this direction and analyse their limitations and future extensions in order to achieve the goal of designing autonomous agents. autonomous robots cognitive robotics developmental robotics lifelong learning robot creativity robot playing Ugur, Emre aut Piater, Justus aut Enthalten in Elektrotechnik und Informationstechnik Springer Vienna, 1988 134(2017), 6 vom: Sept., Seite 293-298 30 cm (DE-627)129622184 (DE-600)246725-2 (DE-576)015132323 0932-383X nnns volume:134 year:2017 number:6 month:09 pages:293-298 https://doi.org/10.1007/s00502-017-0516-0 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-TEC SSG-OLC-MAT GBV_ILN_70 GBV_ILN_161 GBV_ILN_207 GBV_ILN_267 GBV_ILN_2014 GBV_ILN_4328 AR 134 2017 6 09 293-298 |
allfieldsGer |
10.1007/s00502-017-0516-0 doi (DE-627)OLC2065341335 (DE-He213)s00502-017-0516-0-p DE-627 ger DE-627 rakwb eng 620 004 070 VZ Hangl, Simon verfasserin aut Autonomous robots: potential, advances and future direction 2017 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © Springer-Verlag GmbH Austria 2017 Abstract Recent advances in machine learning, such as deep neural networks, have caused a huge boost in many different areas of artificial intelligence and robotics. These methods typically require a large corpus of well-prepared and labelled training data, which limits the applicability to robotics. In our opinion, a fundamental challenge in autonomous robotics is to design systems that are simple enough to solve simple tasks. These systems should grow in complexity step by step and more complex models like neural networks should be trained by re-using the information acquired over the robot’s lifetime. Ultimately, high-level abstractions should be generated from these models, bridging the gap from low-level sensor data to high-level AI systems. We present first steps into this direction and analyse their limitations and future extensions in order to achieve the goal of designing autonomous agents. autonomous robots cognitive robotics developmental robotics lifelong learning robot creativity robot playing Ugur, Emre aut Piater, Justus aut Enthalten in Elektrotechnik und Informationstechnik Springer Vienna, 1988 134(2017), 6 vom: Sept., Seite 293-298 30 cm (DE-627)129622184 (DE-600)246725-2 (DE-576)015132323 0932-383X nnns volume:134 year:2017 number:6 month:09 pages:293-298 https://doi.org/10.1007/s00502-017-0516-0 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-TEC SSG-OLC-MAT GBV_ILN_70 GBV_ILN_161 GBV_ILN_207 GBV_ILN_267 GBV_ILN_2014 GBV_ILN_4328 AR 134 2017 6 09 293-298 |
allfieldsSound |
10.1007/s00502-017-0516-0 doi (DE-627)OLC2065341335 (DE-He213)s00502-017-0516-0-p DE-627 ger DE-627 rakwb eng 620 004 070 VZ Hangl, Simon verfasserin aut Autonomous robots: potential, advances and future direction 2017 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © Springer-Verlag GmbH Austria 2017 Abstract Recent advances in machine learning, such as deep neural networks, have caused a huge boost in many different areas of artificial intelligence and robotics. These methods typically require a large corpus of well-prepared and labelled training data, which limits the applicability to robotics. In our opinion, a fundamental challenge in autonomous robotics is to design systems that are simple enough to solve simple tasks. These systems should grow in complexity step by step and more complex models like neural networks should be trained by re-using the information acquired over the robot’s lifetime. Ultimately, high-level abstractions should be generated from these models, bridging the gap from low-level sensor data to high-level AI systems. We present first steps into this direction and analyse their limitations and future extensions in order to achieve the goal of designing autonomous agents. autonomous robots cognitive robotics developmental robotics lifelong learning robot creativity robot playing Ugur, Emre aut Piater, Justus aut Enthalten in Elektrotechnik und Informationstechnik Springer Vienna, 1988 134(2017), 6 vom: Sept., Seite 293-298 30 cm (DE-627)129622184 (DE-600)246725-2 (DE-576)015132323 0932-383X nnns volume:134 year:2017 number:6 month:09 pages:293-298 https://doi.org/10.1007/s00502-017-0516-0 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-TEC SSG-OLC-MAT GBV_ILN_70 GBV_ILN_161 GBV_ILN_207 GBV_ILN_267 GBV_ILN_2014 GBV_ILN_4328 AR 134 2017 6 09 293-298 |
language |
English |
source |
Enthalten in Elektrotechnik und Informationstechnik 134(2017), 6 vom: Sept., Seite 293-298 volume:134 year:2017 number:6 month:09 pages:293-298 |
sourceStr |
Enthalten in Elektrotechnik und Informationstechnik 134(2017), 6 vom: Sept., Seite 293-298 volume:134 year:2017 number:6 month:09 pages:293-298 |
format_phy_str_mv |
Article |
institution |
findex.gbv.de |
topic_facet |
autonomous robots cognitive robotics developmental robotics lifelong learning robot creativity robot playing |
dewey-raw |
620 |
isfreeaccess_bool |
false |
container_title |
Elektrotechnik und Informationstechnik |
authorswithroles_txt_mv |
Hangl, Simon @@aut@@ Ugur, Emre @@aut@@ Piater, Justus @@aut@@ |
publishDateDaySort_date |
2017-09-01T00:00:00Z |
hierarchy_top_id |
129622184 |
dewey-sort |
3620 |
id |
OLC2065341335 |
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">OLC2065341335</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230502112549.0</controlfield><controlfield tag="007">tu</controlfield><controlfield tag="008">200820s2017 xx ||||| 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1007/s00502-017-0516-0</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)OLC2065341335</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-He213)s00502-017-0516-0-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">620</subfield><subfield code="a">004</subfield><subfield code="a">070</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Hangl, Simon</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Autonomous robots: potential, advances and future direction</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2017</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">© Springer-Verlag GmbH Austria 2017</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Abstract Recent advances in machine learning, such as deep neural networks, have caused a huge boost in many different areas of artificial intelligence and robotics. These methods typically require a large corpus of well-prepared and labelled training data, which limits the applicability to robotics. In our opinion, a fundamental challenge in autonomous robotics is to design systems that are simple enough to solve simple tasks. These systems should grow in complexity step by step and more complex models like neural networks should be trained by re-using the information acquired over the robot’s lifetime. Ultimately, high-level abstractions should be generated from these models, bridging the gap from low-level sensor data to high-level AI systems. We present first steps into this direction and analyse their limitations and future extensions in order to achieve the goal of designing autonomous agents.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">autonomous robots</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">cognitive robotics</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">developmental robotics</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">lifelong learning</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">robot creativity</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">robot playing</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Ugur, Emre</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Piater, Justus</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">Elektrotechnik und Informationstechnik</subfield><subfield code="d">Springer Vienna, 1988</subfield><subfield code="g">134(2017), 6 vom: Sept., Seite 293-298</subfield><subfield code="h">30 cm</subfield><subfield code="w">(DE-627)129622184</subfield><subfield code="w">(DE-600)246725-2</subfield><subfield code="w">(DE-576)015132323</subfield><subfield code="x">0932-383X</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:134</subfield><subfield code="g">year:2017</subfield><subfield code="g">number:6</subfield><subfield code="g">month:09</subfield><subfield code="g">pages:293-298</subfield></datafield><datafield tag="856" ind1="4" ind2="1"><subfield code="u">https://doi.org/10.1007/s00502-017-0516-0</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="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_70</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_161</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_207</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_267</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2014</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4328</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">134</subfield><subfield code="j">2017</subfield><subfield code="e">6</subfield><subfield code="c">09</subfield><subfield code="h">293-298</subfield></datafield></record></collection>
|
author |
Hangl, Simon |
spellingShingle |
Hangl, Simon ddc 620 misc autonomous robots misc cognitive robotics misc developmental robotics misc lifelong learning misc robot creativity misc robot playing Autonomous robots: potential, advances and future direction |
authorStr |
Hangl, Simon |
ppnlink_with_tag_str_mv |
@@773@@(DE-627)129622184 |
format |
Article |
dewey-ones |
620 - Engineering & allied operations 004 - Data processing & computer science 070 - News media, journalism & publishing |
delete_txt_mv |
keep |
author_role |
aut aut aut |
collection |
OLC |
remote_str |
false |
illustrated |
Not Illustrated |
issn |
0932-383X |
topic_title |
620 004 070 VZ Autonomous robots: potential, advances and future direction autonomous robots cognitive robotics developmental robotics lifelong learning robot creativity robot playing |
topic |
ddc 620 misc autonomous robots misc cognitive robotics misc developmental robotics misc lifelong learning misc robot creativity misc robot playing |
topic_unstemmed |
ddc 620 misc autonomous robots misc cognitive robotics misc developmental robotics misc lifelong learning misc robot creativity misc robot playing |
topic_browse |
ddc 620 misc autonomous robots misc cognitive robotics misc developmental robotics misc lifelong learning misc robot creativity misc robot playing |
format_facet |
Aufsätze Gedruckte Aufsätze |
format_main_str_mv |
Text Zeitschrift/Artikel |
carriertype_str_mv |
nc |
hierarchy_parent_title |
Elektrotechnik und Informationstechnik |
hierarchy_parent_id |
129622184 |
dewey-tens |
620 - Engineering 000 - Computer science, knowledge & systems 070 - News media, journalism & publishing |
hierarchy_top_title |
Elektrotechnik und Informationstechnik |
isfreeaccess_txt |
false |
familylinks_str_mv |
(DE-627)129622184 (DE-600)246725-2 (DE-576)015132323 |
title |
Autonomous robots: potential, advances and future direction |
ctrlnum |
(DE-627)OLC2065341335 (DE-He213)s00502-017-0516-0-p |
title_full |
Autonomous robots: potential, advances and future direction |
author_sort |
Hangl, Simon |
journal |
Elektrotechnik und Informationstechnik |
journalStr |
Elektrotechnik und Informationstechnik |
lang_code |
eng |
isOA_bool |
false |
dewey-hundreds |
600 - Technology 000 - Computer science, information & general works |
recordtype |
marc |
publishDateSort |
2017 |
contenttype_str_mv |
txt |
container_start_page |
293 |
author_browse |
Hangl, Simon Ugur, Emre Piater, Justus |
container_volume |
134 |
class |
620 004 070 VZ |
format_se |
Aufsätze |
author-letter |
Hangl, Simon |
doi_str_mv |
10.1007/s00502-017-0516-0 |
dewey-full |
620 004 070 |
title_sort |
autonomous robots: potential, advances and future direction |
title_auth |
Autonomous robots: potential, advances and future direction |
abstract |
Abstract Recent advances in machine learning, such as deep neural networks, have caused a huge boost in many different areas of artificial intelligence and robotics. These methods typically require a large corpus of well-prepared and labelled training data, which limits the applicability to robotics. In our opinion, a fundamental challenge in autonomous robotics is to design systems that are simple enough to solve simple tasks. These systems should grow in complexity step by step and more complex models like neural networks should be trained by re-using the information acquired over the robot’s lifetime. Ultimately, high-level abstractions should be generated from these models, bridging the gap from low-level sensor data to high-level AI systems. We present first steps into this direction and analyse their limitations and future extensions in order to achieve the goal of designing autonomous agents. © Springer-Verlag GmbH Austria 2017 |
abstractGer |
Abstract Recent advances in machine learning, such as deep neural networks, have caused a huge boost in many different areas of artificial intelligence and robotics. These methods typically require a large corpus of well-prepared and labelled training data, which limits the applicability to robotics. In our opinion, a fundamental challenge in autonomous robotics is to design systems that are simple enough to solve simple tasks. These systems should grow in complexity step by step and more complex models like neural networks should be trained by re-using the information acquired over the robot’s lifetime. Ultimately, high-level abstractions should be generated from these models, bridging the gap from low-level sensor data to high-level AI systems. We present first steps into this direction and analyse their limitations and future extensions in order to achieve the goal of designing autonomous agents. © Springer-Verlag GmbH Austria 2017 |
abstract_unstemmed |
Abstract Recent advances in machine learning, such as deep neural networks, have caused a huge boost in many different areas of artificial intelligence and robotics. These methods typically require a large corpus of well-prepared and labelled training data, which limits the applicability to robotics. In our opinion, a fundamental challenge in autonomous robotics is to design systems that are simple enough to solve simple tasks. These systems should grow in complexity step by step and more complex models like neural networks should be trained by re-using the information acquired over the robot’s lifetime. Ultimately, high-level abstractions should be generated from these models, bridging the gap from low-level sensor data to high-level AI systems. We present first steps into this direction and analyse their limitations and future extensions in order to achieve the goal of designing autonomous agents. © Springer-Verlag GmbH Austria 2017 |
collection_details |
GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-TEC SSG-OLC-MAT GBV_ILN_70 GBV_ILN_161 GBV_ILN_207 GBV_ILN_267 GBV_ILN_2014 GBV_ILN_4328 |
container_issue |
6 |
title_short |
Autonomous robots: potential, advances and future direction |
url |
https://doi.org/10.1007/s00502-017-0516-0 |
remote_bool |
false |
author2 |
Ugur, Emre Piater, Justus |
author2Str |
Ugur, Emre Piater, Justus |
ppnlink |
129622184 |
mediatype_str_mv |
n |
isOA_txt |
false |
hochschulschrift_bool |
false |
doi_str |
10.1007/s00502-017-0516-0 |
up_date |
2024-07-04T02:00:45.947Z |
_version_ |
1803612005017321472 |
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">OLC2065341335</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230502112549.0</controlfield><controlfield tag="007">tu</controlfield><controlfield tag="008">200820s2017 xx ||||| 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1007/s00502-017-0516-0</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)OLC2065341335</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-He213)s00502-017-0516-0-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">620</subfield><subfield code="a">004</subfield><subfield code="a">070</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Hangl, Simon</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Autonomous robots: potential, advances and future direction</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2017</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">© Springer-Verlag GmbH Austria 2017</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Abstract Recent advances in machine learning, such as deep neural networks, have caused a huge boost in many different areas of artificial intelligence and robotics. These methods typically require a large corpus of well-prepared and labelled training data, which limits the applicability to robotics. In our opinion, a fundamental challenge in autonomous robotics is to design systems that are simple enough to solve simple tasks. These systems should grow in complexity step by step and more complex models like neural networks should be trained by re-using the information acquired over the robot’s lifetime. Ultimately, high-level abstractions should be generated from these models, bridging the gap from low-level sensor data to high-level AI systems. We present first steps into this direction and analyse their limitations and future extensions in order to achieve the goal of designing autonomous agents.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">autonomous robots</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">cognitive robotics</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">developmental robotics</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">lifelong learning</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">robot creativity</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">robot playing</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Ugur, Emre</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Piater, Justus</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">Elektrotechnik und Informationstechnik</subfield><subfield code="d">Springer Vienna, 1988</subfield><subfield code="g">134(2017), 6 vom: Sept., Seite 293-298</subfield><subfield code="h">30 cm</subfield><subfield code="w">(DE-627)129622184</subfield><subfield code="w">(DE-600)246725-2</subfield><subfield code="w">(DE-576)015132323</subfield><subfield code="x">0932-383X</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:134</subfield><subfield code="g">year:2017</subfield><subfield code="g">number:6</subfield><subfield code="g">month:09</subfield><subfield code="g">pages:293-298</subfield></datafield><datafield tag="856" ind1="4" ind2="1"><subfield code="u">https://doi.org/10.1007/s00502-017-0516-0</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="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_70</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_161</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_207</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_267</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2014</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4328</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">134</subfield><subfield code="j">2017</subfield><subfield code="e">6</subfield><subfield code="c">09</subfield><subfield code="h">293-298</subfield></datafield></record></collection>
|
score |
7.3991747 |