Organisation of robot behaviour through genetic learning processes:
Abstract: "Work in the field of artificial intelligence (AI) has led to the development of the so-called knowledge-based approach to build computational models of human intelligence. The main idea therein is that intelligence is based on symbol manipulation, or more explicit, that thinking actu...
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Buch |
| Sprache: | English |
| Veröffentlicht: |
Sankt Augustin
1990
|
| Schriftenreihe: | Gesellschaft für Mathematik und Datenverarbeitung <Sankt Augustin>: Arbeitspapiere der GMD
496 |
| Schlagworte: | |
| Zusammenfassung: | Abstract: "Work in the field of artificial intelligence (AI) has led to the development of the so-called knowledge-based approach to build computational models of human intelligence. The main idea therein is that intelligence is based on symbol manipulation, or more explicit, that thinking actually is symbol manipulation [Harnad, 1990]. But the little progress made so far in understanding human cognition following this approach has given rise to the assumption that intelligent behaviour cannot be totally described in terms of concepts and relations. We believe that this is because these concepts and the ability to verbally describe them are products of human cognition and not what cognition is based on Behaviour-based robotics represents a different approach to modelling the interaction of an autonomous agent with its environment hence providing the basis for the development of cognitive capabilities in artificially intelligent systems. Although we consider this approach to AI of great importance, we realise the deficiencies of current behaviour- based implementations [Brooks, 1989], [Maes/Brooks, 1990] as far as the conceptual foundations of this approach are concerned. In this paper we present a machine learning approach based on genetic algorithms (GAs) and unsupervised reinforcement learning to the generation and organisation of robot behaviour The implementation of an ethological model of behavioural organisation based on genetic-based machine learning will be outlined. Finally, the general implications of future work in behaviour-based robotics on the information processing paradigm currently dominating AI will be discussed. |
| Beschreibung: | 10 S. |
Internformat
MARC
| LEADER | 00000nam a2200000 cb4500 | ||
|---|---|---|---|
| 001 | BV008983510 | ||
| 003 | DE-604 | ||
| 005 | 20040813 | ||
| 007 | t | ||
| 008 | 940206s1990 |||| 00||| eng d | ||
| 035 | |a (OCoLC)26638887 | ||
| 035 | |a (DE-599)BVBBV008983510 | ||
| 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 Organisation of robot behaviour through genetic learning processes |c Uwe Schnepf ; Marco Dorigo |
| 264 | 1 | |a Sankt Augustin |c 1990 | |
| 300 | |a 10 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 496 | |
| 520 | 3 | |a Abstract: "Work in the field of artificial intelligence (AI) has led to the development of the so-called knowledge-based approach to build computational models of human intelligence. The main idea therein is that intelligence is based on symbol manipulation, or more explicit, that thinking actually is symbol manipulation [Harnad, 1990]. But the little progress made so far in understanding human cognition following this approach has given rise to the assumption that intelligent behaviour cannot be totally described in terms of concepts and relations. We believe that this is because these concepts and the ability to verbally describe them are products of human cognition and not what cognition is based on | |
| 520 | 3 | |a Behaviour-based robotics represents a different approach to modelling the interaction of an autonomous agent with its environment hence providing the basis for the development of cognitive capabilities in artificially intelligent systems. Although we consider this approach to AI of great importance, we realise the deficiencies of current behaviour- based implementations [Brooks, 1989], [Maes/Brooks, 1990] as far as the conceptual foundations of this approach are concerned. In this paper we present a machine learning approach based on genetic algorithms (GAs) and unsupervised reinforcement learning to the generation and organisation of robot behaviour | |
| 520 | 3 | |a The implementation of an ethological model of behavioural organisation based on genetic-based machine learning will be outlined. Finally, the general implications of future work in behaviour-based robotics on the information processing paradigm currently dominating AI will be discussed. | |
| 650 | 4 | |a Machine learning | |
| 650 | 4 | |a Robotics | |
| 700 | 1 | |a Dorigo, Marco |e Verfasser |4 aut | |
| 830 | 0 | |a Gesellschaft für Mathematik und Datenverarbeitung <Sankt Augustin>: Arbeitspapiere der GMD |v 496 |w (DE-604)BV000613796 |9 496 | |
| 999 | |a oai:aleph.bib-bvb.de:BVB01-005933635 | ||
Datensatz im Suchindex
| _version_ | 1804123323121008640 |
|---|---|
| any_adam_object | |
| author | Schnepf, Uwe Dorigo, Marco |
| author_facet | Schnepf, Uwe Dorigo, Marco |
| author_role | aut aut |
| author_sort | Schnepf, Uwe |
| author_variant | u s us m d md |
| building | Verbundindex |
| bvnumber | BV008983510 |
| ctrlnum | (OCoLC)26638887 (DE-599)BVBBV008983510 |
| format | Book |
| fullrecord | <?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>02736nam a2200337 cb4500</leader><controlfield tag="001">BV008983510</controlfield><controlfield tag="003">DE-604</controlfield><controlfield tag="005">20040813 </controlfield><controlfield tag="007">t</controlfield><controlfield tag="008">940206s1990 |||| 00||| eng d</controlfield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(OCoLC)26638887</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)BVBBV008983510</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">Organisation of robot behaviour through genetic learning processes</subfield><subfield code="c">Uwe Schnepf ; Marco Dorigo</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">10 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">496</subfield></datafield><datafield tag="520" ind1="3" ind2=" "><subfield code="a">Abstract: "Work in the field of artificial intelligence (AI) has led to the development of the so-called knowledge-based approach to build computational models of human intelligence. The main idea therein is that intelligence is based on symbol manipulation, or more explicit, that thinking actually is symbol manipulation [Harnad, 1990]. But the little progress made so far in understanding human cognition following this approach has given rise to the assumption that intelligent behaviour cannot be totally described in terms of concepts and relations. We believe that this is because these concepts and the ability to verbally describe them are products of human cognition and not what cognition is based on</subfield></datafield><datafield tag="520" ind1="3" ind2=" "><subfield code="a">Behaviour-based robotics represents a different approach to modelling the interaction of an autonomous agent with its environment hence providing the basis for the development of cognitive capabilities in artificially intelligent systems. Although we consider this approach to AI of great importance, we realise the deficiencies of current behaviour- based implementations [Brooks, 1989], [Maes/Brooks, 1990] as far as the conceptual foundations of this approach are concerned. In this paper we present a machine learning approach based on genetic algorithms (GAs) and unsupervised reinforcement learning to the generation and organisation of robot behaviour</subfield></datafield><datafield tag="520" ind1="3" ind2=" "><subfield code="a">The implementation of an ethological model of behavioural organisation based on genetic-based machine learning will be outlined. Finally, the general implications of future work in behaviour-based robotics on the information processing paradigm currently dominating AI will be discussed.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Machine learning</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Robotics</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Dorigo, Marco</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">496</subfield><subfield code="w">(DE-604)BV000613796</subfield><subfield code="9">496</subfield></datafield><datafield tag="999" ind1=" " ind2=" "><subfield code="a">oai:aleph.bib-bvb.de:BVB01-005933635</subfield></datafield></record></collection> |
| id | DE-604.BV008983510 |
| illustrated | Not Illustrated |
| indexdate | 2024-07-09T17:27:56Z |
| institution | BVB |
| language | English |
| oai_aleph_id | oai:aleph.bib-bvb.de:BVB01-005933635 |
| oclc_num | 26638887 |
| open_access_boolean | |
| owner | DE-N2 |
| owner_facet | DE-N2 |
| physical | 10 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 Organisation of robot behaviour through genetic learning processes Uwe Schnepf ; Marco Dorigo Sankt Augustin 1990 10 S. txt rdacontent n rdamedia nc rdacarrier Gesellschaft für Mathematik und Datenverarbeitung <Sankt Augustin>: Arbeitspapiere der GMD 496 Abstract: "Work in the field of artificial intelligence (AI) has led to the development of the so-called knowledge-based approach to build computational models of human intelligence. The main idea therein is that intelligence is based on symbol manipulation, or more explicit, that thinking actually is symbol manipulation [Harnad, 1990]. But the little progress made so far in understanding human cognition following this approach has given rise to the assumption that intelligent behaviour cannot be totally described in terms of concepts and relations. We believe that this is because these concepts and the ability to verbally describe them are products of human cognition and not what cognition is based on Behaviour-based robotics represents a different approach to modelling the interaction of an autonomous agent with its environment hence providing the basis for the development of cognitive capabilities in artificially intelligent systems. Although we consider this approach to AI of great importance, we realise the deficiencies of current behaviour- based implementations [Brooks, 1989], [Maes/Brooks, 1990] as far as the conceptual foundations of this approach are concerned. In this paper we present a machine learning approach based on genetic algorithms (GAs) and unsupervised reinforcement learning to the generation and organisation of robot behaviour The implementation of an ethological model of behavioural organisation based on genetic-based machine learning will be outlined. Finally, the general implications of future work in behaviour-based robotics on the information processing paradigm currently dominating AI will be discussed. Machine learning Robotics Dorigo, Marco Verfasser aut Gesellschaft für Mathematik und Datenverarbeitung <Sankt Augustin>: Arbeitspapiere der GMD 496 (DE-604)BV000613796 496 |
| spellingShingle | Schnepf, Uwe Dorigo, Marco Organisation of robot behaviour through genetic learning processes Gesellschaft für Mathematik und Datenverarbeitung <Sankt Augustin>: Arbeitspapiere der GMD Machine learning Robotics |
| title | Organisation of robot behaviour through genetic learning processes |
| title_auth | Organisation of robot behaviour through genetic learning processes |
| title_exact_search | Organisation of robot behaviour through genetic learning processes |
| title_full | Organisation of robot behaviour through genetic learning processes Uwe Schnepf ; Marco Dorigo |
| title_fullStr | Organisation of robot behaviour through genetic learning processes Uwe Schnepf ; Marco Dorigo |
| title_full_unstemmed | Organisation of robot behaviour through genetic learning processes Uwe Schnepf ; Marco Dorigo |
| title_short | Organisation of robot behaviour through genetic learning processes |
| title_sort | organisation of robot behaviour through genetic learning processes |
| topic | Machine learning Robotics |
| topic_facet | Machine learning Robotics |
| volume_link | (DE-604)BV000613796 |
| work_keys_str_mv | AT schnepfuwe organisationofrobotbehaviourthroughgeneticlearningprocesses AT dorigomarco organisationofrobotbehaviourthroughgeneticlearningprocesses |