Goal Oriented Modeling for Intelligent Software Agents
IAT '04 Proceedings of the IEEE/WIC/ACM International Conference on Intelligent Agent Technology
Artificial Intelligence for Games, Second Edition
Artificial Intelligence for Games, Second Edition
Dynamical cognitive network - an extension of fuzzy cognitive map
IEEE Transactions on Fuzzy Systems
An emotion understanding framework for intelligent agents based on episodic and semantic memories
Autonomous Agents and Multi-Agent Systems
| Hi-index | 0.00 |
As an emerging medium and industry, computer games received a lot of attention from scholars across a variety of disciplines. The realistic 3D graphics, intelligent non-player characters (NPC) and fascinating game play have made a great impact on user experience in the entertainment domain, e-Learning and other gaming related applications. In this paper, we investigate the game from another perspective - how the game can be affected by the player's real-time experience, such as emotion and gesture. A generic goal oriented software agent platform is proposed to automatically refine the animation, the NPC's personality and emotions, and the game story by learning from the player's realtime feedback from the emotion analyzing and gesture tracking modules. Fuzzy cognitive maps (FCMs) and data mining techniques are used to infer the mutual influences between the player's real world experience and the contents of the game. The adaptation of game to the player's real-time reactions will bring dynamism into the player's game experience. The proposed agent platform has been integrated with several commercial game engines including Unreal Engine 3, and Torque, etc.