Autonomous Behaviour for Animated Characters: towards Artificial Acting

Artificial actors must respond to and interact with their surroundings. A multi-agent system for allowing this is presented.

The presented project aims at providing animated characters with a capability of independent planning their motion. To interact with the virtual environment, animated creatures must be capable of solving problems lying at the intersection of such domains as inverse kinematics, collision detection and avoidance and simulation of the body dynamics. With heterogeneity and multi-layering as the main design principles, the presented solution integrates various animation techniques and contains a society of complex interrelated animation components called actions. They execute on various levels of abstraction and vary in the level of built-in intelligence. In this collaborative environment the intelligence is distributed among multiple agents. As both reactive and proactive modes of operation are present, and the communication between actions is crucial, the overall structure may be considered as a multiagent system. Capabilities of the proposed system will be demonstrated on a number of examples, including catching objects in motion, some balancing problems and communication in a sign language.

Register to tell a friend about this lecture.

Comments

If you would like to comment about this lecture, please register here.

©2003-2006 Niminim Limited. Created by

Any ad revenue is entirely reinvested into the Lecture List's operating fund