Prototyping Teams of Affective Agents in Robocode
António Rebelo
1
, Fábio Catalão
1
, João Alves
1
, Goreti Marreiros
3,4
,
Cesar Analide
1,2
, Paulo Novais
1,2
, José Neves
1,2
1
Universidade do Minho, Campus de Gualtar, 4700 Braga, Portugal
Email: {pg19827, pg19832, pg20688}@alunos.uminho.pt
2
CCTC – Centro de Ciências e Tecnologias da Computação, Portugal
Email: {analide, pjon, jneves}@di.uminho.pt
3
GECAD – Knowledge Engineering and Decision Support Group, Porto, Portugal
Email: mgt@isep.ipp.pt
4
Institute of Engineering – Polytechnic of Porto (ISEP/IPP)
ABSTRACT
The study of the impact of emotion and affect in decision making processes involved in a
working team stands for a multi-disciplinary issue (e.g. with insights from disciplines such
as Psychology, Neuroscience, Philosophy and Computer Science). On the one hand, and
in order to create such an environment we look at a team of affective agents to play into a
battlefield, which present different emotional profiles (e.g. personality and mood). An
emotional system, based on the OCC (Ortony, Clore and Collins) model, was proposed
and implemented. As a way to integrate the personality of a robot with its emotions we
used pleasure-arousal-dominance (PAD) model of mood. On the other hand, to attain
cooperation, a voting mechanism and a decision-making process was implemented, being
Robocode used as the simulation environment. Indeed, the results so far obtained are
quite satisfying; the agent team performs quite well in the battlefield and undertakes
different behaviours depending on the skirmish conditions
Keywords: Affective agents, Team behaviour, Robocode.
Mathematics Subject Classification: 68T42
Computing Classification System: I2.0
1. INTRODUCTION
Traditionally, emotions and affects have been ignored in classic decision making methods (Marreiros
et al., 2005). However, in the last years, re-searchers of distinct areas (e.g. Psychology, Neuroscience
and Philosophy) have begun to explore the role of the affect as a positive influence on human
decision-making. Currently, the representation of human emotions in artificial environments is a
common issue in Artificial Intelligence.
In 2003, Ortony discussed the main characteristics that an agent must have to be considered
believable. There, it was defended that agents should have consistent motivational and behaviours
states. In order to ponder this option, it is reinforced that agents need not only a robust model of
emotions but also have to implement a proper model of personality, which will contribute to give them
coherence, consistence and some degree of predictability.
International Journal of Imaging and Robotics,
[Formerly known as the “International Journal of Imaging” (ISSN 0974-0627)]
Volume 15; Issue No. 1; Year 2015; Int. J. Imag. Robot.
ISSN 2231–525X; Copyright © 2015 by IJIR (CESER PUBLICATIONS)
www.ceser.in/ceserp
www.ceserp.com/cp-jour
www.ceserpublications.com