Supporting sketch-based retrieval from a library of reusable behaviours

Building the behaviour for non-player characters in a game is a complex collaborative task among AI designers and programmers. In this paper we present a visual authoring tool for game designers that supports behaviour reuse. We describe a visual editor, capable of storing, indexing, retrieving and reusing behaviours previously designed by AI programmers. One of the most notable features of our editor is its capability for sketch-based retrieval: searching in a repository for behaviours that are similar to the one the user is drawing, and making suggestions about how to complete it. As this process relies on graph behaviour comparison, in this paper, we describe different algorithms for graph comparison, and demonstrate, through empirical evaluation in a particular test domain, that we can provide structure-based similarity for graphs that preserves behaviour similarity and can be computed at reasonable cost.

► We present a visual authoring tool, eCo, which supports behaviour reuse.
► We use structural similarity to find state machines that behave similarly.
► We have successfully experimented our approach on a large repository of FSMs.
► Our approach can be applied to other graph-based representations like BTs.
► To be able to handle retrieval with big graphs we use a heuristic approach.