Past Project : Map Learning

Map Learning

About Map Learning

In this project, our objective is to develop new ability-based algorithms for computer-controlled non-player characters (NPCs), or "smart monsters," in interactive 3D games.

Our system exploits predefined perceptual abilities of the NPCs to allow them to identify, and (possibly, fail to) recognize landmarks to build perceptual navigation maps of their environment. The map built by an NPC will reflect the perceptual and cognitive abilities of the NPC, thus allowing for more varied, interesting behaviors of NPCs in games.


Map Learning

Marc Schraffenberger (M.S. Computer Science 2006)
Jean-Yves Hervé

M. Schraffenberger and Jean-Yves Hervé, "Agent Abilities in a Landmark-based Mapping Model," in Proceedings IEEE Int'l Conf. On Systems, Man, and Cybernetics, Taipei, Taiwan, October 2006.

Marc Schraffenberger, "A Landmark-based Mapping Model for Non-Player Characters with Abilities in Computer Games," M.S. Thesis, Department of Computer Science and Statistics, University of RHode Island, Kingston, RI, 2006.