Modeling embodied visual behaviors
ACM Transactions on Applied Perception (TAP)
| Hi-index | 0.00 |
This dissertation explores the problem of visually guided control. The focus is not on the details of image processing, but on understanding the role that vision plays within the context of an active agent. More specifically, we focus on managing vision in multiple goal tasks. When multiple tasks are addressed simultaneously conflicts arise because of limitations on sensor and effector availability and on computational capacity. This dissertation describes principled ways of handling those conflicts using a decision theoretic approach. The test bed for this work is a graphical human that processes a rendered video stream in order to navigate through a realistically modeled urban environment. The goal of this work is to understand visually guided behavior both as it relates to the engineering of embodied mobile agents and as it relates to the science of human vision. We demonstrate an approach to managing vision for the virtual agent, and also present experimental results illustrating that the same framework can effectively model human eye movement scheduling.