An incremental dialogue planner that monitors execution

Abstract: "This paper describes an incremental planner which chooses among alternate plans based on an evaluation technique, monitors plan execution, and applies recovery strategies if a plan has failed to have the desired effect. The planner operates in a domain where two computer agents engag...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
1. Verfasser: Carletta, Jean (VerfasserIn)
Format: Buch
Sprache:English
Veröffentlicht: Edinburgh 1990
Schriftenreihe:University <Edinburgh> / Department of Artificial Intelligence: DAI research paper 480
Schlagworte:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!

MARC

LEADER 00000nam a2200000 cb4500
001 BV010452221
003 DE-604
005 20001211
007 t|
008 951027s1990 xx |||| 00||| engod
035 |a (OCoLC)23158903 
035 |a (DE-599)BVBBV010452221 
040 |a DE-604  |b ger  |e rakddb 
041 0 |a eng 
049 |a DE-91G 
100 1 |a Carletta, Jean  |e Verfasser  |4 aut 
245 1 0 |a An incremental dialogue planner that monitors execution 
264 1 |a Edinburgh  |c 1990 
300 |a 11 S. 
336 |b txt  |2 rdacontent 
337 |b n  |2 rdamedia 
338 |b nc  |2 rdacarrier 
490 1 |a University <Edinburgh> / Department of Artificial Intelligence: DAI research paper  |v 480 
520 3 |a Abstract: "This paper describes an incremental planner which chooses among alternate plans based on an evaluation technique, monitors plan execution, and applies recovery strategies if a plan has failed to have the desired effect. The planner operates in a domain where two computer agents engage in dialogue to complete a simple map navigation task. This domain has the properties that there are always several ways of achieving goals and that execution monitoring and reconsidering plans are essential to completing the task. The planning agent chooses among the possible plans for a goal using an evaluation technique designed to choose the most efficient plan which will satisfactorily complete the task 
520 3 |a Execution monitoring is allowed by attaching special postconditions to plan operators which check with the dialogue partner that the goal has been achieved, and by allowing the dialogue partner to interrupt during the course of an interaction. Finally, three recovery strategies are included: repair where the problem is diagnosed by the partner, repair which must be diagnosed by looking at possible failed preconditions in the plan, and replanning with a different operator or a different instantiation of the same operator. These capabilities make this planning architecture appropriate for domains where the effects of actions are uncertain but can be monitored. 
650 7 |a Bionics and artificial intelligence  |2 sigle 
650 7 |a Computer software  |2 sigle 
650 4 |a Künstliche Intelligenz 
650 4 |a Artificial intelligence 
650 4 |a Planning 
810 2 |a Department of Artificial Intelligence: DAI research paper  |t University <Edinburgh>  |v 480  |w (DE-604)BV010450646  |9 480 
943 1 |a oai:aleph.bib-bvb.de:BVB01-006965163 

Datensatz im Suchindex

DE-BY-TUM_call_number 0111 2001 B 6034
DE-BY-TUM_katkey 663793
DE-BY-TUM_location 01
DE-BY-TUM_media_number 040010001862
_version_ 1820855157935570944
any_adam_object
author Carletta, Jean
author_facet Carletta, Jean
author_role aut
author_sort Carletta, Jean
author_variant j c jc
building Verbundindex
bvnumber BV010452221
ctrlnum (OCoLC)23158903
(DE-599)BVBBV010452221
format Book
fullrecord <?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>02482nam a2200349 cb4500</leader><controlfield tag="001">BV010452221</controlfield><controlfield tag="003">DE-604</controlfield><controlfield tag="005">20001211 </controlfield><controlfield tag="007">t|</controlfield><controlfield tag="008">951027s1990 xx |||| 00||| engod</controlfield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(OCoLC)23158903</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)BVBBV010452221</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-91G</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Carletta, Jean</subfield><subfield code="e">Verfasser</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">An incremental dialogue planner that monitors execution</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="a">Edinburgh</subfield><subfield code="c">1990</subfield></datafield><datafield tag="300" ind1=" " ind2=" "><subfield code="a">11 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">University &lt;Edinburgh&gt; / Department of Artificial Intelligence: DAI research paper</subfield><subfield code="v">480</subfield></datafield><datafield tag="520" ind1="3" ind2=" "><subfield code="a">Abstract: "This paper describes an incremental planner which chooses among alternate plans based on an evaluation technique, monitors plan execution, and applies recovery strategies if a plan has failed to have the desired effect. The planner operates in a domain where two computer agents engage in dialogue to complete a simple map navigation task. This domain has the properties that there are always several ways of achieving goals and that execution monitoring and reconsidering plans are essential to completing the task. The planning agent chooses among the possible plans for a goal using an evaluation technique designed to choose the most efficient plan which will satisfactorily complete the task</subfield></datafield><datafield tag="520" ind1="3" ind2=" "><subfield code="a">Execution monitoring is allowed by attaching special postconditions to plan operators which check with the dialogue partner that the goal has been achieved, and by allowing the dialogue partner to interrupt during the course of an interaction. Finally, three recovery strategies are included: repair where the problem is diagnosed by the partner, repair which must be diagnosed by looking at possible failed preconditions in the plan, and replanning with a different operator or a different instantiation of the same operator. These capabilities make this planning architecture appropriate for domains where the effects of actions are uncertain but can be monitored.</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Bionics and artificial intelligence</subfield><subfield code="2">sigle</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Computer software</subfield><subfield code="2">sigle</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">Planning</subfield></datafield><datafield tag="810" ind1="2" ind2=" "><subfield code="a">Department of Artificial Intelligence: DAI research paper</subfield><subfield code="t">University &lt;Edinburgh&gt;</subfield><subfield code="v">480</subfield><subfield code="w">(DE-604)BV010450646</subfield><subfield code="9">480</subfield></datafield><datafield tag="943" ind1="1" ind2=" "><subfield code="a">oai:aleph.bib-bvb.de:BVB01-006965163</subfield></datafield></record></collection>
id DE-604.BV010452221
illustrated Not Illustrated
indexdate 2024-12-23T13:59:30Z
institution BVB
language English
oai_aleph_id oai:aleph.bib-bvb.de:BVB01-006965163
oclc_num 23158903
open_access_boolean
owner DE-91G
DE-BY-TUM
owner_facet DE-91G
DE-BY-TUM
physical 11 S.
publishDate 1990
publishDateSearch 1990
publishDateSort 1990
record_format marc
series2 University <Edinburgh> / Department of Artificial Intelligence: DAI research paper
spellingShingle Carletta, Jean
An incremental dialogue planner that monitors execution
Bionics and artificial intelligence sigle
Computer software sigle
Künstliche Intelligenz
Artificial intelligence
Planning
title An incremental dialogue planner that monitors execution
title_auth An incremental dialogue planner that monitors execution
title_exact_search An incremental dialogue planner that monitors execution
title_full An incremental dialogue planner that monitors execution
title_fullStr An incremental dialogue planner that monitors execution
title_full_unstemmed An incremental dialogue planner that monitors execution
title_short An incremental dialogue planner that monitors execution
title_sort an incremental dialogue planner that monitors execution
topic Bionics and artificial intelligence sigle
Computer software sigle
Künstliche Intelligenz
Artificial intelligence
Planning
topic_facet Bionics and artificial intelligence
Computer software
Künstliche Intelligenz
Artificial intelligence
Planning
volume_link (DE-604)BV010450646
work_keys_str_mv AT carlettajean anincrementaldialogueplannerthatmonitorsexecution