Yingying She
Peter Grogono
ABSTRACT
We discuss a procedural planning approach that automatically and dynamically generates plans for game agents in real-time. This approach is applied to the design of an agent architecture in our current research project, Gameme, a game design application. This planning depends on offline goal design, the structure of the agent architecture, and real-time planning mechanisms. The Procedural Planning System (PPS) is capable of improving agents' control for real-time goal processing in games.
- R. P. Bonasso, D. Kortenkamp, D. P. Miller, and M. Slack. Experiences with an architecture for intelligent, reactive agents. Journal of Experimental and Theoretical Artificial Intelligence, pages 237--256, 1997.Google Scholar
- R. A. Brooks. A robust layered control system for a mobile robot. IEEE Journal of Robotics and Automation, April 1986.Google ScholarCross Ref
- J. J. Bryson. Intelligence by Design: Principles pf Modularity and Coordination for Engineering Complex Adaptive Agents. PhD thesis, Massachusetts Institutue of Technology, 2001. Google ScholarDigital Library
- A. Nareyek. Artificial Intelligence in Computer Games. Game Development, 1(10), February 2004.Google Scholar
- N. Nilsson. Teleo-reactive programs and the triple-tower architecture. Electronics Transactions in Artificial Intelligence, pages 99--110, 2001.Google Scholar
- J. Orkin. Agent architecture considerations for real-time planning in games. Artificial Intelligence and Interactive Digital Entertainment (AIIDE), 2005.Google Scholar
- Y. She and P. Grogono. Goal oriented behavior trees: A new strategy for controlling agents in games. GameOn NA, August 2008.Google Scholar
- I. Soto, M. Garijo, C. A. Iglesias, and M. Ramos. An agent architecture to fulfill real-time requirements. Agents, 2000. Google ScholarDigital Library
Index Terms
- The procedural planning system used in the agent architecture of games
Recommendations
Declarative planning in procedural agent architectures
Practical agent languages and their corresponding architectures have often relied on a static plan library with more or less direct trigger-response activation mechanisms as a source for agent behaviours for the sake of runtime efficiency. Although ...
Planning Intelligent Responses in a Natural Language System
Special issue on intelligent help systems for Unix part III: natural language dialogueIntelligent help systems cannot merely respond passively to the user's commands and queries. They need to be able to volunteer information, correct user misconceptions, and reject unethical requests when appropriate. In order to do these things, a system ...
A hybrid agent architecture for modeling autonomous agents in SAGE
IDEAL'05: Proceedings of the 6th international conference on Intelligent Data Engineering and Automated LearningThis paper highlights the Hybrid agent construction model being developed that allows the description and development of autonomous agents in SAGE (Scalable, fault Tolerant Agent Grooming Environment) – a second generation FIPA-Compliant Multi-Agent ...
Comments