Interactive task learning: humans, robots, and agents acquiring new tasks through natural interactions
Experts from a range of disciplines explore how humans and artificial agents can quickly learn completely new tasks through natural interactions with each other. Humans are not limited to a fixed set of innate or preprogrammed tasks. We learn quickly through language and other forms of natural inter...
Gespeichert in:
| Weitere beteiligte Personen: | , , |
|---|---|
| Format: | E-Book |
| Sprache: | Englisch |
| Veröffentlicht: |
Cambridge
The MIT Press
2018
|
| Schriftenreihe: | Strüngmann Forum reports
|
| Links: | https://doi.org/10.7551/mitpress/11956.001.0001?locatt=mode:legacy |
| Zusammenfassung: | Experts from a range of disciplines explore how humans and artificial agents can quickly learn completely new tasks through natural interactions with each other. Humans are not limited to a fixed set of innate or preprogrammed tasks. We learn quickly through language and other forms of natural interaction, and we improve our performance and teach others what we have learned. Understanding the mechanisms that underlie the acquisition of new tasks through natural interaction is an ongoing challenge. Advances in artificial intelligence, cognitive science, and robotics are leading us to future systems with human-like capabilities. A huge gap exists, however, between the highly specialized niche capabilities of current machine learning systems and the generality, flexibility, and in situ robustness of human instruction and learning. Drawing on expertise from multiple disciplines, this Strüngmann Forum Report explores how humans and artificial agents can quickly learn completely new tasks through natural interactions with each other. The contributors consider functional knowledge requirements, the ontology of interactive task learning, and the representation of task knowledge at multiple levels of abstraction. They explore natural forms of interactions among humans as well as the use of interaction to teach robots and software agents new tasks in complex, dynamic environments. They discuss research challenges and opportunities, including ethical considerations, and make proposals to further understanding of interactive task learning and create new capabilities in assistive robotics, healthcare, education, training, and gaming. |
| Umfang: | 1 Online-Ressource (344 Seiten) Illustrationen |
| ISBN: | 0262349426 9780262349420 |
Internformat
MARC
| LEADER | 00000cam a2200000Ki 4500 | ||
|---|---|---|---|
| 001 | ZDB-260-MPOB-11956 | ||
| 003 | MaCbMITP | ||
| 005 | 20190503073441.0 | ||
| 006 | m o d | ||
| 007 | cr cnu|||unuuu | ||
| 008 | 180511s2018 maua o 000 0 eng d | ||
| 020 | |a 0262349426 | ||
| 020 | |a 9780262349420 | ||
| 245 | 0 | 0 | |a Interactive task learning |b humans, robots, and agents acquiring new tasks through natural interactions |c [edited by] Kevin A. Gluck, John E. Laird, Julia Lupp |
| 264 | 1 | |a Cambridge |b The MIT Press |c 2018 | |
| 300 | |a 1 Online-Ressource (344 Seiten) |b Illustrationen | ||
| 336 | |b txt | ||
| 337 | |b c | ||
| 338 | |b cr | ||
| 490 | 1 | |a Strüngmann Forum reports | |
| 520 | |a Experts from a range of disciplines explore how humans and artificial agents can quickly learn completely new tasks through natural interactions with each other. Humans are not limited to a fixed set of innate or preprogrammed tasks. We learn quickly through language and other forms of natural interaction, and we improve our performance and teach others what we have learned. Understanding the mechanisms that underlie the acquisition of new tasks through natural interaction is an ongoing challenge. Advances in artificial intelligence, cognitive science, and robotics are leading us to future systems with human-like capabilities. A huge gap exists, however, between the highly specialized niche capabilities of current machine learning systems and the generality, flexibility, and in situ robustness of human instruction and learning. Drawing on expertise from multiple disciplines, this Strüngmann Forum Report explores how humans and artificial agents can quickly learn completely new tasks through natural interactions with each other. The contributors consider functional knowledge requirements, the ontology of interactive task learning, and the representation of task knowledge at multiple levels of abstraction. They explore natural forms of interactions among humans as well as the use of interaction to teach robots and software agents new tasks in complex, dynamic environments. They discuss research challenges and opportunities, including ethical considerations, and make proposals to further understanding of interactive task learning and create new capabilities in assistive robotics, healthcare, education, training, and gaming. | ||
| 700 | 1 | |a Gluck, Kevin A. | |
| 700 | 1 | |a Laird, John |d 1954- | |
| 700 | 1 | |a Lupp, Julia | |
| 776 | 0 | 8 | |i Erscheint auch als |n Druck-Ausgabe |z 9780262038829 |
| 966 | 4 | 0 | |l DE-91 |p ZDB-260-MPOB |q TUM_PDA_MPOB |3 MIT Press |u https://doi.org/10.7551/mitpress/11956.001.0001?locatt=mode:legacy |3 Volltext |
| 912 | |a ZDB-260-MPOB | ||
| 912 | |a ZDB-260-MPOB | ||
| 049 | |a DE-91 | ||
Datensatz im Suchindex
| DE-BY-TUM_katkey | ZDB-260-MPOB-11956 |
|---|---|
| _version_ | 1821493840794615808 |
| adam_text | |
| any_adam_object | |
| author2 | Gluck, Kevin A. Laird, John 1954- Lupp, Julia |
| author2_role | |
| author2_variant | k a g ka kag j l jl j l jl |
| author_facet | Gluck, Kevin A. Laird, John 1954- Lupp, Julia |
| author_sort | Gluck, Kevin A. |
| building | Verbundindex |
| bvnumber | localTUM |
| collection | ZDB-260-MPOB |
| format | eBook |
| fullrecord | <?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>02597cam a2200289Ki 4500</leader><controlfield tag="001">ZDB-260-MPOB-11956</controlfield><controlfield tag="003">MaCbMITP</controlfield><controlfield tag="005">20190503073441.0</controlfield><controlfield tag="006">m o d </controlfield><controlfield tag="007">cr cnu|||unuuu</controlfield><controlfield tag="008">180511s2018 maua o 000 0 eng d</controlfield><datafield tag="020" ind1=" " ind2=" "><subfield code="a">0262349426</subfield></datafield><datafield tag="020" ind1=" " ind2=" "><subfield code="a">9780262349420</subfield></datafield><datafield tag="245" ind1="0" ind2="0"><subfield code="a">Interactive task learning</subfield><subfield code="b">humans, robots, and agents acquiring new tasks through natural interactions</subfield><subfield code="c">[edited by] Kevin A. Gluck, John E. Laird, Julia Lupp</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="a">Cambridge</subfield><subfield code="b">The MIT Press</subfield><subfield code="c">2018</subfield></datafield><datafield tag="300" ind1=" " ind2=" "><subfield code="a">1 Online-Ressource (344 Seiten)</subfield><subfield code="b">Illustrationen</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="b">txt</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="b">c</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="b">cr</subfield></datafield><datafield tag="490" ind1="1" ind2=" "><subfield code="a">Strüngmann Forum reports</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Experts from a range of disciplines explore how humans and artificial agents can quickly learn completely new tasks through natural interactions with each other. Humans are not limited to a fixed set of innate or preprogrammed tasks. We learn quickly through language and other forms of natural interaction, and we improve our performance and teach others what we have learned. Understanding the mechanisms that underlie the acquisition of new tasks through natural interaction is an ongoing challenge. Advances in artificial intelligence, cognitive science, and robotics are leading us to future systems with human-like capabilities. A huge gap exists, however, between the highly specialized niche capabilities of current machine learning systems and the generality, flexibility, and in situ robustness of human instruction and learning. Drawing on expertise from multiple disciplines, this Strüngmann Forum Report explores how humans and artificial agents can quickly learn completely new tasks through natural interactions with each other. The contributors consider functional knowledge requirements, the ontology of interactive task learning, and the representation of task knowledge at multiple levels of abstraction. They explore natural forms of interactions among humans as well as the use of interaction to teach robots and software agents new tasks in complex, dynamic environments. They discuss research challenges and opportunities, including ethical considerations, and make proposals to further understanding of interactive task learning and create new capabilities in assistive robotics, healthcare, education, training, and gaming.</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Gluck, Kevin A.</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Laird, John</subfield><subfield code="d">1954-</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Lupp, Julia</subfield></datafield><datafield tag="776" ind1="0" ind2="8"><subfield code="i">Erscheint auch als</subfield><subfield code="n">Druck-Ausgabe</subfield><subfield code="z">9780262038829</subfield></datafield><datafield tag="966" ind1="4" ind2="0"><subfield code="l">DE-91</subfield><subfield code="p">ZDB-260-MPOB</subfield><subfield code="q">TUM_PDA_MPOB</subfield><subfield code="3">MIT Press</subfield><subfield code="u">https://doi.org/10.7551/mitpress/11956.001.0001?locatt=mode:legacy</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">ZDB-260-MPOB</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">ZDB-260-MPOB</subfield></datafield><datafield tag="049" ind1=" " ind2=" "><subfield code="a">DE-91</subfield></datafield></record></collection> |
| id | ZDB-260-MPOB-11956 |
| illustrated | Illustrated |
| indexdate | 2025-01-17T11:04:53Z |
| institution | BVB |
| isbn | 0262349426 9780262349420 |
| language | English |
| open_access_boolean | |
| owner | DE-91 DE-BY-TUM |
| owner_facet | DE-91 DE-BY-TUM |
| physical | 1 Online-Ressource (344 Seiten) Illustrationen |
| psigel | ZDB-260-MPOB TUM_PDA_MPOB ZDB-260-MPOB |
| publishDate | 2018 |
| publishDateSearch | 2018 |
| publishDateSort | 2018 |
| publisher | The MIT Press |
| record_format | marc |
| series2 | Strüngmann Forum reports |
| spelling | Interactive task learning humans, robots, and agents acquiring new tasks through natural interactions [edited by] Kevin A. Gluck, John E. Laird, Julia Lupp Cambridge The MIT Press 2018 1 Online-Ressource (344 Seiten) Illustrationen txt c cr Strüngmann Forum reports Experts from a range of disciplines explore how humans and artificial agents can quickly learn completely new tasks through natural interactions with each other. Humans are not limited to a fixed set of innate or preprogrammed tasks. We learn quickly through language and other forms of natural interaction, and we improve our performance and teach others what we have learned. Understanding the mechanisms that underlie the acquisition of new tasks through natural interaction is an ongoing challenge. Advances in artificial intelligence, cognitive science, and robotics are leading us to future systems with human-like capabilities. A huge gap exists, however, between the highly specialized niche capabilities of current machine learning systems and the generality, flexibility, and in situ robustness of human instruction and learning. Drawing on expertise from multiple disciplines, this Strüngmann Forum Report explores how humans and artificial agents can quickly learn completely new tasks through natural interactions with each other. The contributors consider functional knowledge requirements, the ontology of interactive task learning, and the representation of task knowledge at multiple levels of abstraction. They explore natural forms of interactions among humans as well as the use of interaction to teach robots and software agents new tasks in complex, dynamic environments. They discuss research challenges and opportunities, including ethical considerations, and make proposals to further understanding of interactive task learning and create new capabilities in assistive robotics, healthcare, education, training, and gaming. Gluck, Kevin A. Laird, John 1954- Lupp, Julia Erscheint auch als Druck-Ausgabe 9780262038829 |
| spellingShingle | Interactive task learning humans, robots, and agents acquiring new tasks through natural interactions |
| title | Interactive task learning humans, robots, and agents acquiring new tasks through natural interactions |
| title_auth | Interactive task learning humans, robots, and agents acquiring new tasks through natural interactions |
| title_exact_search | Interactive task learning humans, robots, and agents acquiring new tasks through natural interactions |
| title_full | Interactive task learning humans, robots, and agents acquiring new tasks through natural interactions [edited by] Kevin A. Gluck, John E. Laird, Julia Lupp |
| title_fullStr | Interactive task learning humans, robots, and agents acquiring new tasks through natural interactions [edited by] Kevin A. Gluck, John E. Laird, Julia Lupp |
| title_full_unstemmed | Interactive task learning humans, robots, and agents acquiring new tasks through natural interactions [edited by] Kevin A. Gluck, John E. Laird, Julia Lupp |
| title_short | Interactive task learning |
| title_sort | interactive task learning humans robots and agents acquiring new tasks through natural interactions |
| title_sub | humans, robots, and agents acquiring new tasks through natural interactions |
| work_keys_str_mv | AT gluckkevina interactivetasklearninghumansrobotsandagentsacquiringnewtasksthroughnaturalinteractions AT lairdjohn interactivetasklearninghumansrobotsandagentsacquiringnewtasksthroughnaturalinteractions AT luppjulia interactivetasklearninghumansrobotsandagentsacquiringnewtasksthroughnaturalinteractions |