BDI for Intelligent Agents in Computer Games

With the emergence of complex computer games and advanced gaming hardware, possibilities for overcoming some of the deficiencies in traditional game AI are becoming feasible. These deficiencies include repetitive, predictable, and inhuman behaviour are caused by the reliance on simple reactive AI techniques. By using more sophisticated AI and agent techniques, we intend to overcome some of these problem areas. The aim of our research is to create new forms of intelligent characters (agents) that will exhibit human-like intelligence and provide more challenging and entertaining virtual opponents and team mates for computer games. We present here our prototype application that implements a BDI agent system within the 3D computer game Unreal Tournament via GameBots and JavaBots technology.

[1]  D. Hodgson Half-Life 2 , 2004 .

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

[3]  Peter Norvig,et al.  Artificial Intelligence: A Modern Approach , 1995 .

[4]  Michael Lewis,et al.  GAME ENGINES IN SCIENTIFIC RESEARCH , 2002 .

[5]  S. Stich,et al.  What is folk psychology? , 1994, Cognition.

[6]  Emma Norling,et al.  Folk psychology for human modelling: extending the BDI paradigm , 2004, Proceedings of the Third International Joint Conference on Autonomous Agents and Multiagent Systems, 2004. AAMAS 2004..

[7]  Michael E. Bratman,et al.  Intention, Plans, and Practical Reason , 1991 .

[8]  A. Pokahr,et al.  A Generic Simulation Service for Distributed Multi-Agent Systems , 2004 .

[9]  Wilfrid S. Sellars Empiricism and the philosophy of mind , 1997 .