The University of Southampton
University of Southampton Institutional Repository

The ACT-R Unity Interface: Integrating ACT-R with the Unity Game Engine

The ACT-R Unity Interface: Integrating ACT-R with the Unity Game Engine
The ACT-R Unity Interface: Integrating ACT-R with the Unity Game Engine
Cognitive architectures are computational frameworks that support the development of computational models of human cognitive processes. They have typically been used to advance our understanding of human cognition in specific task environments; however, they have also been used to support the development of a variety of intelligent systems and agents (e.g., cognitive robots). There are a broad range of reasons to motivate the effort to integrate cognitive architectures with virtual environments. These include the development of intelligent virtual characters for the purposes of training simulations, enhanced gameplay experiences and the modelling of user/gamer behaviour. Virtual environments also support simulations of actual real-world environments (e.g., using physics engines and advanced lighting models) that can be used to perform computational simulations into embedded, extended, and embodied cognition. In the current report, we describe the effort to develop an integration framework that enables the ACT-R cognitive architecture to be used in conjunction with the Unity game engine. The resulting framework, referred to as the ACT-R Unity Integration (ACT-R UI) framework, enables individual ACT-R models to control the behaviour of virtual non-player characters that inhabit 3D virtual environments built on top of Unity. We first provide an overview of the ACT-R architecture and the Unity game engine. We describe the key features of both systems and discuss why they provide such a compelling target for integration. We then go on to describe the nature of the integration solution itself. We outline the extensions to the ACT-R architecture that enable ACT-R models to exchange information with Unity, and we also present the Unity components that enable virtual characters to be controlled or influenced by ACT-R models. Finally, we provide a concrete example of the use of the ACT-R UI. In particular, we show how an ACT-R model can be used to control the behaviour of a virtual robotic character that inhabits a Unity-based virtual environment.
cognitive architecture, virtual environment, game engine, social simulation, embodied cognition, cognitive modelling
University of Southampton
Smart, Paul R.
cd8a3dbf-d963-4009-80fb-76ecc93579df
Sycara, Katia
df200c43-d34d-4093-bb4e-493fea2d0732
Tang, Yuqing
0b26bd4d-f1ab-40ab-8517-3dfc10767fa9
Powell, Gavin
d5ac622b-446b-474e-a968-98eb1b4d30ab
Smart, Paul R.
cd8a3dbf-d963-4009-80fb-76ecc93579df
Sycara, Katia
df200c43-d34d-4093-bb4e-493fea2d0732
Tang, Yuqing
0b26bd4d-f1ab-40ab-8517-3dfc10767fa9
Powell, Gavin
d5ac622b-446b-474e-a968-98eb1b4d30ab

Smart, Paul R., Sycara, Katia, Tang, Yuqing and Powell, Gavin (2015) The ACT-R Unity Interface: Integrating ACT-R with the Unity Game Engine Southampton, UK. University of Southampton (Submitted)

Record type: Monograph (Project Report)

Abstract

Cognitive architectures are computational frameworks that support the development of computational models of human cognitive processes. They have typically been used to advance our understanding of human cognition in specific task environments; however, they have also been used to support the development of a variety of intelligent systems and agents (e.g., cognitive robots). There are a broad range of reasons to motivate the effort to integrate cognitive architectures with virtual environments. These include the development of intelligent virtual characters for the purposes of training simulations, enhanced gameplay experiences and the modelling of user/gamer behaviour. Virtual environments also support simulations of actual real-world environments (e.g., using physics engines and advanced lighting models) that can be used to perform computational simulations into embedded, extended, and embodied cognition. In the current report, we describe the effort to develop an integration framework that enables the ACT-R cognitive architecture to be used in conjunction with the Unity game engine. The resulting framework, referred to as the ACT-R Unity Integration (ACT-R UI) framework, enables individual ACT-R models to control the behaviour of virtual non-player characters that inhabit 3D virtual environments built on top of Unity. We first provide an overview of the ACT-R architecture and the Unity game engine. We describe the key features of both systems and discuss why they provide such a compelling target for integration. We then go on to describe the nature of the integration solution itself. We outline the extensions to the ACT-R architecture that enable ACT-R models to exchange information with Unity, and we also present the Unity components that enable virtual characters to be controlled or influenced by ACT-R models. Finally, we provide a concrete example of the use of the ACT-R UI. In particular, we show how an ACT-R model can be used to control the behaviour of a virtual robotic character that inhabits a Unity-based virtual environment.

This record has no associated files available for download.

More information

Submitted date: 1 December 2015
Keywords: cognitive architecture, virtual environment, game engine, social simulation, embodied cognition, cognitive modelling
Organisations: Web & Internet Science

Identifiers

Local EPrints ID: 384324
URI: http://eprints.soton.ac.uk/id/eprint/384324
PURE UUID: 6e4770c7-8845-4e67-9f92-43d861c1e3a5
ORCID for Paul R. Smart: ORCID iD orcid.org/0000-0001-9989-5307

Catalogue record

Date deposited: 23 Nov 2015 15:28
Last modified: 12 Dec 2021 03:21

Export record

Contributors

Author: Paul R. Smart ORCID iD
Author: Katia Sycara
Author: Yuqing Tang
Author: Gavin Powell

Download statistics

Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.

View more statistics

Atom RSS 1.0 RSS 2.0

Contact ePrints Soton: eprints@soton.ac.uk

ePrints Soton supports OAI 2.0 with a base URL of http://eprints.soton.ac.uk/cgi/oai2

This repository has been built using EPrints software, developed at the University of Southampton, but available to everyone to use.

We use cookies to ensure that we give you the best experience on our website. If you continue without changing your settings, we will assume that you are happy to receive cookies on the University of Southampton website.

×