Statechart-Based AI in Practice

Layered Statechart-based AI shows considerable promise by being a highly modular, reusable, and designer friendly approach to game AI. Here we demonstrate the viability of this approach by replicating the functionality of a full-featured and commercial-scale behaviour tree AI within a non-commercial game framework. As well as demonstrating that layered Statecharts are both usable and amply expressive, our experience highlights the value of several, previously unidentified design considerations, such as sensor patterns, the necessity of subsumption, and the utility of orthogonal regions. These observations point towards simplified, higher-level AI construction techniques that can reduce the complexity of AI design and further enhance reuse.

[1]  Kevin Waugh,et al.  A PATTERN CATALOG FOR COMPUTER ROLE PLAYING GAMES , 2005 .

[2]  Jörg Kienzle,et al.  Reusable components for artificial intelligence in computer games , 2012, 2012 Second International Workshop on Games and Software Engineering: Realizing User Engagement with Game Engineering Techniques (GAS).

[3]  Nicholas R. Jennings,et al.  Agent Theories, Architectures, and Languages: A Survey , 1995, ECAI Workshop on Agent Theories, Architectures, and Languages.

[4]  Jörg Kienzle,et al.  Mammoth: a massively multiplayer game research framework , 2009, FDG.

[5]  Rodney A. Brooks,et al.  A Robust Layered Control Syste For A Mobile Robot , 2022 .

[6]  Brian Schwab,et al.  Implementation Walkthrough of a Homegrown 'Abstract State Machine' Style System in a Commercial Sports Game , 2008, AIIDE.

[7]  G. Michael Youngblood,et al.  Representational complexity of reactive agents , 2010, Proceedings of the 2010 IEEE Conference on Computational Intelligence and Games.

[8]  Jeff Orkin,et al.  Three States and a Plan: The A.I. of F.E.A.R. , 2006 .

[9]  Jörg Kienzle,et al.  Toward high-level reuse of statechart-based AI in computer games , 2011, GAS '11.

[10]  Jörg Kienzle,et al.  Model-based design of computer-controlled game character behavior , 2007, MODELS'07.

[11]  Daniel Fu,et al.  Putting AI in Entertainment: An AI Authoring Tool for Simulation and Games , 2002, IEEE Intell. Syst..