A learning integrated framework for group problem-solving in distributed AI systems

Problem solving activity by groups of agents is an increasingly common phenomenon in a vast variety of domains. This phenomenon may be attributed to a combination of factors: an increasing trend towards specialization of skills in narrow functional areas and increased complexity of problems which transcend functional boundaries. Coordination of this group problem solving (GPS) activity so that it is effective and coherent requires an understanding of several GPS related issues such as organization of agents, decomposability of problems, etc. This research proposes a generic framework for GPS that identifies a set of design dimensions and develops generic mechanisms for achieving the problem solving and coordination processes characterizing GPS. This framework is then used to build prototypical GPS systems in two application domains--group decision support systems (GDSS) and computer integrated manufacturing (CIM)--so that key research issues of GPS can be studied.

Name thesis:degree_name

Ph.D.

Level thesis:degree_level

Dissertation

Discipline thesis:degree_discipline

Business Administration

Grantor

University of Illinois at Urbana-Champaign

Year dc:date

2011

Author dc:creator

• Menon, Uday Chandran

Contributors dc:contributor

• Cohen, Susan

• Business Administration, General
• Engineering, Mechanical
• Artificial Intelligence
• Computer Science

Statement dc:rights

• Copyright 1992 Menon, Uday Chandran

Language dc:language

eng

Identifier

AAI9236541
(UMI)AAI9236541

OAI identifier oai:identifier

oai:www.ideals.illinois.edu:2142/20322