ECAI 2004 Conference Paper

Avatars That Learn How To Behave

Adam Szarowicz, Paolo Remagnino

It is possible to model avatars that learn to simulate object manipulations and interactions between individuals. Many applications may benefit from this technique including safety, ergonomics, film animation and many others. Current techniques "control" avatars manually, scripting what they can do by imposing constraints on their physical and cognitive model. In this paper we show how avatars in a controlled environment can learn behaviours as composits of simple actions. The avatar learning process is described in detail for a generic behaviour and tested in simple experiments. Local and global metrics are introduced to optimise the selection of a set of actions from the learnt pool. The performance for the learnt tasks is qualitatively compared with a human performance.

Keywords: learnt behaviours, animation, learning metric, lifelike characters

Citation: Adam Szarowicz, Paolo Remagnino: Avatars That Learn How To Behave. In R.López de Mántaras and L.Saitta (eds.): ECAI2004, Proceedings of the 16th European Conference on Artificial Intelligence, IOS Press, Amsterdam, 2004, pp.554-558.

ECAI-2004 is organised by the European Coordinating Committee for Artificial Intelligence (ECCAI) and hosted by the Universitat Politècnica de València on behalf of Asociación Española de Inteligencia Artificial (AEPIA) and Associació Catalana d'Intel-ligència Artificial (ACIA).