Statechart-Based AI in Practice


  • Christopher Dragert McGill University
  • Jorg Kienzle McGill University
  • Clark Verbrugge McGill University



Statecharts, Game AI, AI Representation


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.




How to Cite

Dragert, C., Kienzle, J., & Verbrugge, C. (2021). Statechart-Based AI in Practice. Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, 8(1), 136-141.