On the evolution of adaptive behaviour:
Abstract: "Current research in behaviour-based robotics focuses on the design of behavioural modules in order to achieve flexible robot actions [Arkins, 1989a], [Brooks, 1986]. Appropriate behaviours are designed, tested, modified and finally added to others already existing until the desired r...
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Buch |
| Sprache: | English |
| Veröffentlicht: |
Sankt Augustin
1990
|
| Schriftenreihe: | Gesellschaft für Mathematik und Datenverarbeitung <Sankt Augustin>: Arbeitspapiere der GMD
495 |
| Schlagworte: | |
| Zusammenfassung: | Abstract: "Current research in behaviour-based robotics focuses on the design of behavioural modules in order to achieve flexible robot actions [Arkins, 1989a], [Brooks, 1986]. Appropriate behaviours are designed, tested, modified and finally added to others already existing until the desired robot performance has been achieved. This allows the development of reliable and robust behaviour-based robot controllers. However, as far as research into Artificial Intelligence (AI) and the development of intelligent autonomous systems are concerned, the approach is insufficient. Important questions such as how useful information actually enters an autonomous agent, how adaptive behaviour is generated, and how learning can be achieved are neglected In this paper it is argued that for the design of intelligent autonomous systems it is important to equip the robot with the ability to create, to test, and to modify its own behaviour on the basis of primitive and acquired motor skills or so-called motor schemas. A generic approach will be presented which enables the robot to 'generalise' from the observation of useful and useless behaviour to new, more general behaviours and to bootstrap itself to the next level of behavioural complexity. The observation of useful and useless behaviour is based on a system of so- called hedonic stimuli which has to be defined for a robot in order to provide a measuring scale The evolution in the behavioural repertoire of robots is based on the selection of promising candidates and on the duplication of their behavioural repertoire (ethological selection and offspring generation). This way we expect to develop robots well-adapted to their environment as well as to gain insights in the evolution of information processing based on the development of motor and perceptual schemas [Arbib et al., 1987]. |
| Beschreibung: | 13 S. |
Internformat
MARC
| LEADER | 00000nam a2200000 cb4500 | ||
|---|---|---|---|
| 001 | BV008983511 | ||
| 003 | DE-604 | ||
| 005 | 20040813 | ||
| 007 | t | ||
| 008 | 940206s1990 |||| 10||| eng d | ||
| 035 | |a (OCoLC)25974897 | ||
| 035 | |a (DE-599)BVBBV008983511 | ||
| 040 | |a DE-604 |b ger |e rakddb | ||
| 041 | 0 | |a eng | |
| 049 | |a DE-N2 | ||
| 100 | 1 | |a Schnepf, Uwe |e Verfasser |4 aut | |
| 245 | 1 | 0 | |a On the evolution of adaptive behaviour |c Uwe Schnepf ; Marcos Aurelio Rodrigues |
| 264 | 1 | |a Sankt Augustin |c 1990 | |
| 300 | |a 13 S. | ||
| 336 | |b txt |2 rdacontent | ||
| 337 | |b n |2 rdamedia | ||
| 338 | |b nc |2 rdacarrier | ||
| 490 | 1 | |a Gesellschaft für Mathematik und Datenverarbeitung <Sankt Augustin>: Arbeitspapiere der GMD |v 495 | |
| 520 | 3 | |a Abstract: "Current research in behaviour-based robotics focuses on the design of behavioural modules in order to achieve flexible robot actions [Arkins, 1989a], [Brooks, 1986]. Appropriate behaviours are designed, tested, modified and finally added to others already existing until the desired robot performance has been achieved. This allows the development of reliable and robust behaviour-based robot controllers. However, as far as research into Artificial Intelligence (AI) and the development of intelligent autonomous systems are concerned, the approach is insufficient. Important questions such as how useful information actually enters an autonomous agent, how adaptive behaviour is generated, and how learning can be achieved are neglected | |
| 520 | 3 | |a In this paper it is argued that for the design of intelligent autonomous systems it is important to equip the robot with the ability to create, to test, and to modify its own behaviour on the basis of primitive and acquired motor skills or so-called motor schemas. A generic approach will be presented which enables the robot to 'generalise' from the observation of useful and useless behaviour to new, more general behaviours and to bootstrap itself to the next level of behavioural complexity. The observation of useful and useless behaviour is based on a system of so- called hedonic stimuli which has to be defined for a robot in order to provide a measuring scale | |
| 520 | 3 | |a The evolution in the behavioural repertoire of robots is based on the selection of promising candidates and on the duplication of their behavioural repertoire (ethological selection and offspring generation). This way we expect to develop robots well-adapted to their environment as well as to gain insights in the evolution of information processing based on the development of motor and perceptual schemas [Arbib et al., 1987]. | |
| 650 | 4 | |a Künstliche Intelligenz | |
| 650 | 4 | |a Artificial intelligence | |
| 650 | 4 | |a Robotics | |
| 655 | 7 | |0 (DE-588)1071861417 |a Konferenzschrift |2 gnd-content | |
| 700 | 1 | |a Aurelio Rodrigues, Marcos |e Verfasser |4 aut | |
| 830 | 0 | |a Gesellschaft für Mathematik und Datenverarbeitung <Sankt Augustin>: Arbeitspapiere der GMD |v 495 |w (DE-604)BV000613796 |9 495 | |
| 999 | |a oai:aleph.bib-bvb.de:BVB01-005933636 | ||
Datensatz im Suchindex
| _version_ | 1804123323118911488 |
|---|---|
| any_adam_object | |
| author | Schnepf, Uwe Aurelio Rodrigues, Marcos |
| author_facet | Schnepf, Uwe Aurelio Rodrigues, Marcos |
| author_role | aut aut |
| author_sort | Schnepf, Uwe |
| author_variant | u s us r m a rm rma |
| building | Verbundindex |
| bvnumber | BV008983511 |
| ctrlnum | (OCoLC)25974897 (DE-599)BVBBV008983511 |
| format | Book |
| fullrecord | <?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>03035nam a2200361 cb4500</leader><controlfield tag="001">BV008983511</controlfield><controlfield tag="003">DE-604</controlfield><controlfield tag="005">20040813 </controlfield><controlfield tag="007">t</controlfield><controlfield tag="008">940206s1990 |||| 10||| eng d</controlfield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(OCoLC)25974897</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)BVBBV008983511</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-604</subfield><subfield code="b">ger</subfield><subfield code="e">rakddb</subfield></datafield><datafield tag="041" ind1="0" ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="049" ind1=" " ind2=" "><subfield code="a">DE-N2</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Schnepf, Uwe</subfield><subfield code="e">Verfasser</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">On the evolution of adaptive behaviour</subfield><subfield code="c">Uwe Schnepf ; Marcos Aurelio Rodrigues</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="a">Sankt Augustin</subfield><subfield code="c">1990</subfield></datafield><datafield tag="300" ind1=" " ind2=" "><subfield code="a">13 S.</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="b">n</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="b">nc</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="490" ind1="1" ind2=" "><subfield code="a">Gesellschaft für Mathematik und Datenverarbeitung <Sankt Augustin>: Arbeitspapiere der GMD</subfield><subfield code="v">495</subfield></datafield><datafield tag="520" ind1="3" ind2=" "><subfield code="a">Abstract: "Current research in behaviour-based robotics focuses on the design of behavioural modules in order to achieve flexible robot actions [Arkins, 1989a], [Brooks, 1986]. Appropriate behaviours are designed, tested, modified and finally added to others already existing until the desired robot performance has been achieved. This allows the development of reliable and robust behaviour-based robot controllers. However, as far as research into Artificial Intelligence (AI) and the development of intelligent autonomous systems are concerned, the approach is insufficient. Important questions such as how useful information actually enters an autonomous agent, how adaptive behaviour is generated, and how learning can be achieved are neglected</subfield></datafield><datafield tag="520" ind1="3" ind2=" "><subfield code="a">In this paper it is argued that for the design of intelligent autonomous systems it is important to equip the robot with the ability to create, to test, and to modify its own behaviour on the basis of primitive and acquired motor skills or so-called motor schemas. A generic approach will be presented which enables the robot to 'generalise' from the observation of useful and useless behaviour to new, more general behaviours and to bootstrap itself to the next level of behavioural complexity. The observation of useful and useless behaviour is based on a system of so- called hedonic stimuli which has to be defined for a robot in order to provide a measuring scale</subfield></datafield><datafield tag="520" ind1="3" ind2=" "><subfield code="a">The evolution in the behavioural repertoire of robots is based on the selection of promising candidates and on the duplication of their behavioural repertoire (ethological selection and offspring generation). This way we expect to develop robots well-adapted to their environment as well as to gain insights in the evolution of information processing based on the development of motor and perceptual schemas [Arbib et al., 1987].</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Künstliche Intelligenz</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Artificial intelligence</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Robotics</subfield></datafield><datafield tag="655" ind1=" " ind2="7"><subfield code="0">(DE-588)1071861417</subfield><subfield code="a">Konferenzschrift</subfield><subfield code="2">gnd-content</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Aurelio Rodrigues, Marcos</subfield><subfield code="e">Verfasser</subfield><subfield code="4">aut</subfield></datafield><datafield tag="830" ind1=" " ind2="0"><subfield code="a">Gesellschaft für Mathematik und Datenverarbeitung <Sankt Augustin>: Arbeitspapiere der GMD</subfield><subfield code="v">495</subfield><subfield code="w">(DE-604)BV000613796</subfield><subfield code="9">495</subfield></datafield><datafield tag="999" ind1=" " ind2=" "><subfield code="a">oai:aleph.bib-bvb.de:BVB01-005933636</subfield></datafield></record></collection> |
| genre | (DE-588)1071861417 Konferenzschrift gnd-content |
| genre_facet | Konferenzschrift |
| id | DE-604.BV008983511 |
| illustrated | Not Illustrated |
| indexdate | 2024-07-09T17:27:56Z |
| institution | BVB |
| language | English |
| oai_aleph_id | oai:aleph.bib-bvb.de:BVB01-005933636 |
| oclc_num | 25974897 |
| open_access_boolean | |
| owner | DE-N2 |
| owner_facet | DE-N2 |
| physical | 13 S. |
| publishDate | 1990 |
| publishDateSearch | 1990 |
| publishDateSort | 1990 |
| record_format | marc |
| series | Gesellschaft für Mathematik und Datenverarbeitung <Sankt Augustin>: Arbeitspapiere der GMD |
| series2 | Gesellschaft für Mathematik und Datenverarbeitung <Sankt Augustin>: Arbeitspapiere der GMD |
| spelling | Schnepf, Uwe Verfasser aut On the evolution of adaptive behaviour Uwe Schnepf ; Marcos Aurelio Rodrigues Sankt Augustin 1990 13 S. txt rdacontent n rdamedia nc rdacarrier Gesellschaft für Mathematik und Datenverarbeitung <Sankt Augustin>: Arbeitspapiere der GMD 495 Abstract: "Current research in behaviour-based robotics focuses on the design of behavioural modules in order to achieve flexible robot actions [Arkins, 1989a], [Brooks, 1986]. Appropriate behaviours are designed, tested, modified and finally added to others already existing until the desired robot performance has been achieved. This allows the development of reliable and robust behaviour-based robot controllers. However, as far as research into Artificial Intelligence (AI) and the development of intelligent autonomous systems are concerned, the approach is insufficient. Important questions such as how useful information actually enters an autonomous agent, how adaptive behaviour is generated, and how learning can be achieved are neglected In this paper it is argued that for the design of intelligent autonomous systems it is important to equip the robot with the ability to create, to test, and to modify its own behaviour on the basis of primitive and acquired motor skills or so-called motor schemas. A generic approach will be presented which enables the robot to 'generalise' from the observation of useful and useless behaviour to new, more general behaviours and to bootstrap itself to the next level of behavioural complexity. The observation of useful and useless behaviour is based on a system of so- called hedonic stimuli which has to be defined for a robot in order to provide a measuring scale The evolution in the behavioural repertoire of robots is based on the selection of promising candidates and on the duplication of their behavioural repertoire (ethological selection and offspring generation). This way we expect to develop robots well-adapted to their environment as well as to gain insights in the evolution of information processing based on the development of motor and perceptual schemas [Arbib et al., 1987]. Künstliche Intelligenz Artificial intelligence Robotics (DE-588)1071861417 Konferenzschrift gnd-content Aurelio Rodrigues, Marcos Verfasser aut Gesellschaft für Mathematik und Datenverarbeitung <Sankt Augustin>: Arbeitspapiere der GMD 495 (DE-604)BV000613796 495 |
| spellingShingle | Schnepf, Uwe Aurelio Rodrigues, Marcos On the evolution of adaptive behaviour Gesellschaft für Mathematik und Datenverarbeitung <Sankt Augustin>: Arbeitspapiere der GMD Künstliche Intelligenz Artificial intelligence Robotics |
| subject_GND | (DE-588)1071861417 |
| title | On the evolution of adaptive behaviour |
| title_auth | On the evolution of adaptive behaviour |
| title_exact_search | On the evolution of adaptive behaviour |
| title_full | On the evolution of adaptive behaviour Uwe Schnepf ; Marcos Aurelio Rodrigues |
| title_fullStr | On the evolution of adaptive behaviour Uwe Schnepf ; Marcos Aurelio Rodrigues |
| title_full_unstemmed | On the evolution of adaptive behaviour Uwe Schnepf ; Marcos Aurelio Rodrigues |
| title_short | On the evolution of adaptive behaviour |
| title_sort | on the evolution of adaptive behaviour |
| topic | Künstliche Intelligenz Artificial intelligence Robotics |
| topic_facet | Künstliche Intelligenz Artificial intelligence Robotics Konferenzschrift |
| volume_link | (DE-604)BV000613796 |
| work_keys_str_mv | AT schnepfuwe ontheevolutionofadaptivebehaviour AT aureliorodriguesmarcos ontheevolutionofadaptivebehaviour |