Scenario generation for emergency rescue training games

Procedural methods have long been used for generation of art assets, but procedural generation of scenarios has lagged behind. In particular, training games for emergency rescue workers would benefit from procedural scenario generation guided by pedagogical goals. In such a game, users could select what skills they wish to train for, and the system would generate a unique level containing the elements necessary to train those skills. In this paper, we present a system that uses HTN planning to generate collapsed structure training scenarios that are both internally consistent and allow the user to train for the desired goals. Categories and Subject Descriptors I.2.1 [Artificial Intelligence]: Applications and Expert Systems Games I.2.4 [Artificial Intelligence]: Knowledge Representation Formalisms and Methods – Representations (procedural and rulebased) K.8 [Personal Computing]: Games General Terms Algorithms, Design Keywords Procedural Level Generation, Serious Games, Qualitative R...

• Type: Conference
• Year: 2009
• Where: FDG
• Authors: Kenneth Hullett, Michael Mateas
• Keywords: FDG 2009, Procedural Generation, Procedural Level Generation, Procedural Scenario Generation