The Application of AI to Automatically Generated Animation

Abstract

Abstract. Modern animation packages provide partial automation of action between key frames. However the creation of scenes involving many interacting characters still requires most of the work to be hand-done by animators and any automatic behavior in the animation sequence tends to be hard-wired and lacking autonomy. This paper describes our "FreeWill" prototype which addresses these limitations by proposing and implementing an extendable cognitive architecture designed to accommodate goals, actions and knowledge, thus endowing animated characters with some degree of autonomous intelligent behavior.

Layering and heterogeneity as design principles for animated embedded agents

“…The proposed, new framework is called FreeWill+ [10] and it is an evolution of its predecessor system, FreeWill [32]. It provides general means for co-operation of various (heterogeneous) agents.…”

Interacting Agents in a Network for in silico Modeling of Nature-Inspired Smart Systems

“…In reactive animation, Efroni et al [29], Harel [41], Szarowicz et al [98], Szarowicz et al [99], WavesWorld [105], the system has to react to various kinds of events, signals and conditions that are often distributed and concurrent. Also they can be time critical exhibiting both digital and analog (or hybrid) behaviour.…”

Modelling and simulation of realistic pedestrian behaviours

“…Pedestrian simulation can also be used to automatically generate a pedestrian crowd [94], [111], [120], with realistic navigation behaviours in animation systems or in interactive digital medias such as massively online multi-player games. Realistic pedestrian simulation is important in this case to generate a pedestrian crowd that look natural and realistic.…”