SimBionic Community Edition

Now you can add SimBionic for free! SimBionic Community Edition is a feature-limited release perfect for projects with less complex AI requirements.

• Download SimBionic Community Edition

SimBionic Publications

Stottler Henke periodically writes articles on technologies underlying our software. Here are a set of papers we've written on the SimBionic technology. Click on the title to view the PDF document.

• "A Visual Environment for Rapid Behavior Definition," by Dan Fu, Ryan Houlette, and Randy Jensen. In proceedings of the 2003 Conference on Behavior Representation in Modeling and Simulation, 2003.
• "Putting AI in Entertainment: An AI Authoring Tool for Simulation and Games," by Dan Fu and Ryan Houlette. In IEEE Intelligent Systems, July-August 2002, pp 81-84.
• "An Authoring Toolkit for Simulation Entities," by Dan Fu, Ryan Houlette, and Oscar Bascara. In the proceedings of the Industry/Interservice, Training, Simulation & Education Conference (I/ITSEC 2001).
• "Towards an AI Behavior Toolkit for Games," by Ryan Houlette, Dan Fu, and David Ross. In AAAI 2001 Spring Symposium on AI and Interactive Entertainment.

• "The Ultimate Guide to FSMs in Games," by Dan Fu and Ryan Houlette.
  Based on our experience implementing SimBionic, this article summarizes the state of the art of FSMs in video games. We cover FSM implementation styles, scripting languages, game engine integration, optimization techniques, and advanced concepts such as stack-based FSMs and polymorphism.

• "Player Modeling for Adaptive Games," by Ryan Houlette.
  This article describes an approach to automatically constructing a model of the player's behavior that can be used by the game AI to create more challenging and interesting opponents. The underlying technologies were implemented in scheduling and tutoring software built for NASA and the Air Force.

• "Constructing a Decision Tree Based on Past Experience," by Dan Fu and Ryan Houlette.
  Decision trees are becoming more popular within the game development community. They are a practical learning method that can help an AI adapt to a player. Instead of picking from a canned set of reactions to player action, the AI has the opportunity to do something much more powerful: anticipate the player's action before he acts. The article covers ID3, a classic decision tree learning algorithm that identifies the telltale features of an experience to predict its outcome. ID3 was the core learning technology behind the game Black & White. Sample source code is provided which implements ID3.