Title: Cogent: a coherence-driven cognitive agent modelling and experimentation framework

Authors: Sunit Sivaraj; Levent Yilmaz

Addresses: Department of Computer Science and Software Engineering, Auburn University, Auburn, Alabama 36849, USA ' Department of Computer Science and Software Engineering, Auburn University, Auburn, Alabama 36849, USA

Abstract: Most agent modelling and simulation languages lack high-level syntactic features necessary for cognitive modelling. In this paper, we present Cogent, an interactive coherence-driven agent specification and simulation platform and demonstrate its use in ethical decision making. The underlying strategy is based on the concept of a connectionist, interactive activation model that implements the theory of coherence. Agents in the Cogent language are specified by a domain-specific language (DSL). The DSL provides the syntax for specifying the decision-making strategy along with its cognitive coherence model. The framework also provides the ability to model complex hierarchical cognitive network structures. To illustrate the utility of Cogent, we explore a machine ethics case study.

Keywords: cognitive agent; coherence; ethical decision making; cognitive computing; domain-specific language; DSL.

DOI: 10.1504/IJSPM.2019.097707

International Journal of Simulation and Process Modelling, 2019 Vol.14 No.1, pp.36 - 50

Received: 23 May 2018
Accepted: 15 Jul 2018
Published online: 05 Feb 2019 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article