Designing a knowledge representation interface for cognitive agents

Conference Paper (2015)
Author(s)

T. Bagosi (TU Delft - Electrical Engineering, Mathematics and Computer Science)

J. de Greeff (TU Delft - Electrical Engineering, Mathematics and Computer Science)

KV Hindriks (TU Delft - Electrical Engineering, Mathematics and Computer Science)

MA Neerincx (TU Delft - Electrical Engineering, Mathematics and Computer Science)

Research Group
Interactive Intelligence
DOI related publication
https://doi.org/10.1007/978-3-319-26184-3_3 Final published version
More Info
expand_more
Publication Year
2015
Language
English
Research Group
Interactive Intelligence
Pages (from-to)
33-50
Publisher
Springer
ISBN (print)
978-3-319-26183-6
ISBN (electronic)
978-3-319-26184-3
Event
EMAS 2015, Istanbul, Turkey, Dordrecht
Downloads counter
196
Collections
Institutional Repository

Abstract

The design of cognitive agents involves a knowledge representation (KR) to formally represent and manipulate information relevant for that agent. In practice, agent programming frameworks are dedicated to a specific KR, limiting the use of other possible ones. In this paper we address the issue of creating a flexible choice for agent programmers regarding the technology they want to use. We propose a generic interface, that provides an easy choice of KR for cognitive agents. Our proposal is governed by a number of design principles, an analysis of functional requirements that cognitive agents pose towards a KR, and the identification of various features provided by KR technologies that the interface should capture. We provide two use-cases of the interface by describing its implementation for Prolog and OWL with rules.