Affordances and level-of-detail AI for virtual humans

Abstract

Anyone who aims at developing a virtual reality application featuring a large artificial world inhabited by intelligent virtual humans will face two problems—the problem with simulation speed, and the problem with adding new components to the simulation both during the development and after the release. We have developed a framework that copes with these issues. The solution is based on augmentation of the level-of-detail AI technique and theories of affordances and practical reasoning. Contrary to existing approaches, our solution is theoretically well-founded, robust and deals with both these issues at once. In this paper, we present the key concepts of our framework and evaluate a test scenario.