Embodying the JACK Agent Architecture

Emma Norling
University of Melbourne

Friday, 31st August 2001
0930 - 1100

SEECS lecture theatre 2
University of Melbourne Computer Science Department
SEECS Building
221 Bouverie Street, Carlton.

Abstract:

Agent-based models of human operators rarely include explicit representations of the timing and accuracy of perception and action, although their accuracy is sometimes implicitly modelled by including random noise for observations and actions. In many situations though, the timing and accuracy of the person's perception and action significantly influence their overall performance on a task. Recently many cognitive architectures have been extended to include perceptual/motor capabilities, making them embodied, and they have since been successfully used to test and compare interface designs. This presentation describes the implementation of a similar perceptual/motor system that uses and extends the JACK agent language. The resulting embodied architecture has been used to compare GUIs representing telephones, but has been designed to interact with any mouse-driven Java interface. The results clearly indicate the impact of poor design on performance, with the agent taking longer to perform the task on the more poorly designed telephone.

Biosketch:

Emma Norling is a PhD student at the University of Melbourne. She is looking at using agents to model human operators in software simulations, and what aspects of human performance are important to include in the agent models in order to achieve realistic simulations. She recently spent three months studying at Pennsylvania State University with Frank Ritter, a researcher in Cognitive Science. During this time she was looking at implementing models of perception and action using the JACK agent language.