CogBox - Combined Artificial Intelligence Methodologies to Achieve a Semi-realistic Agent in Serious Games

CogBox is a system created to demonstrate a theory on Artificially Intelligent Agents. This paper describes this theory, explaining how it improves upon existing AI Agents. We draw upon already well established AI concepts, such as Fuzzy Logic and the Belief, Desire, Intention model, as well as Finite State Machines and discuss their limitations. We present a novel combination of these techniques to overcome these limitations.

[1]  Hemant K. Bhargava,et al.  Simulating belief systems of autonomous agents , 1995, Decis. Support Syst..

[2]  Charles Thevathayan,et al.  BDI agents for game development , 2002, AAMAS '02.

[3]  Yifan Li,et al.  Fuzzy logic in agent-based game design , 2004, IEEE Annual Meeting of the Fuzzy Information, 2004. Processing NAFIPS '04..

[4]  Henry Hexmoor,et al.  Designing BOTs with BDI agents , 2009, 2009 International Symposium on Collaborative Technologies and Systems.

[5]  Winfried Lamersdorf,et al.  Jadex: A BDI Reasoning Engine , 2005, Multi-Agent Programming.

[6]  Michael Fisher,et al.  A Survey of Concurrent METATEM - the Language and its Applications , 1994, ICTL.

[7]  Billy Yue,et al.  The state of the art in game AI standardisation , 2006 .

[8]  Michael Wooldridge,et al.  A Common Semantic Basis for BDI Languages , 2007, PROMAS.

[9]  Jürgen Dix,et al.  Multi-Agent Programming , 2009, Springer US.

[10]  Abdennour El Rhalibi,et al.  A Hybrid Fuzzy ANN System for Agent Adaptation in a First Person Shooter , 2006, Int. J. Comput. Games Technol..

[11]  Anand S. Rao,et al.  BDI Agents: From Theory to Practice , 1995, ICMAS.

[12]  Alasdair Urquhart,et al.  Temporal Logic , 1971 .

[13]  Kevin Wong,et al.  Proceedings of the 2006 international conference on Game research and development , 2006 .

[14]  Anand S. Rao,et al.  An architecture for real-time reasoning and system control , 1992, IEEE Expert.