A Synthetic Actor model for long-term computer games

Abstract

Virtual Reality and Artificial Intelligence provide suitable techniques to improve computer games quality. While the former offers mechanisms to model environment and characters' physical features, the latter provides models and tools for building characters, namely Synthetic Actors or Believable Agents, which can exhibit intelligent social behaviour and express personality and emotions. The current architecture proposals for Synthetic Actors do not fully meet the requirements for tong-term games development, such as strategy and adventure ones, it is necessary to guarantee both personality stability and reactive emotional responses, which may be contradictory. In this work, we propose a new Synthetic Actor model that tightly connects emotions and social attitudes to personality, providing a tong-term coherent behaviour. This model has been applied to two games presented here as case studies.

A conceptual affective design framework for the use of emotions in computer game design

“…The researchers' goal is to create a character whose behaviour is consistent and believable for long-term interactions with a player. This is also the objective for Silva et al (2000) who present a framework for long-term personality cohesion using OCC. Other research projects in the same vein include Laureano-Cruces, Acevedo-Moreno, Mora-Torres, and Ramirez-Rodriguez (2012) reactive agent that can reorder its goals based on its priorities and current emotional state and Peña, Peña, and Ossowski's (2011) Mood Vector Space, that combines OCC and PAD to enable mathematical manipulation of emotion constructs.…”

Una arquitectura cognitiva multinivel para agentes con comportamiento influido por características individuales y emociones, propias y de otros agentes

“…Posiblemente, el área en la que más han sido aplicados este tipo de modelos ha sido en la de los personajes virtuales sintéticos y, más particularmente, en la generación de comportamientos creíbles. En este contexto, Silva et al (Silva et al, 1996) proponen una arquitectura propia, basada en emociones discretas, para controlar el proceso de generación de metas de personajes virtuales autónomos influidos por personalidad y emociones. El proceso de generación de metas que siguen es el siguiente:…”