Level Annotation and Test by Autonomous Exploration

This paper proposes the use of an autonomous exploring agent to generate and annotate the waypoint graph as an offline process during level development. The explorer incrementally generates the waypoint graph as it explores the level via the same motion model used for player movement, and then revisits the waypoints to annotate them using image-based techniques. Points where the explorer becomes stuck or falls off of the level are flagged for later investigation by a level designer.