Artificial life for computer graphics
Communications of the ACM
Fast Synthetic Vision, Memory, and Learning Models for Virtual Humans
CA '99 Proceedings of the Computer Animation
Hi-index | 0.00 |
This paper presents a neural design which is able to provide the necessary reactive navigation and attention skills for 3D embodied agents (virtual humanoids or characters). Based on Grossberg's neural model of conditioning [6], as recently implemented by Chang and Gaudiando [7], and according to the Adaptative Resonance Theory (ART) and the neuroscientific concepts associated, the neural design introduced has been divided in two main phases. Firstly, an environmentcategorization phase, where an on-line pattern recognition and categorization of the current agent sensory input data is carried out by a self organizing neural network, which will finally provide the agent's short term memory layer(STM). Secondly, and based on the classical conditioning paradigm, the model will associate the interesting STM states, from the navigation or attention points of view, to finally simulate these necessary skills for 3D characters or humanoids. Finally, we will show some experimental navigational results, through the integration of the model presented in 3D virtual environments.