A technique for estimating three-dimensional volume-of-interest using eye gaze

WCU Author/Contributor (non-WCU co-authors, if there are any, appear on document)
Carl Cole Drawdy IV (Creator)
Institution
Western Carolina University (WCU )
Web Site: http://library.wcu.edu/
Advisor
Paul Yanik

Abstract: Assistive robotics promises to be of use to those who have limited mobility or dexterity.Moreover, those who have limited movement of limbs can bene t greatly from such assistivedevices. However, to use such devices, one would need to give commands to an assistiveagent, often in the form of speech, gesture, or text. The need for a more convenient methodof Human-Robot Interaction (HRI) is prevalent, especially for impaired users because ofsevere mobility constraints.For a socially responsive assistive device to be an e ective aid, the device generallyshould understand the intention of the user. Also, to perform a task based on gesture, theassistive device requires the user's area of attention in three-dimensional (3D) space. Gazetracking can be used as a method to determine a speci c volume of interest (VOI). However,heretofore gaze tracking has been under-utilized as a means of interaction and control in 3Dspace.The main objective of this research is to determine a practical VOI in which anindividual's eyes are focused by combining existing methods. Achieving this objective setsa foundation for further use of vergence data as a useful discriminant to generate a properdirective technique for assistive robotics.This research investigates the accuracy of the Vector Intersection (VI) model whenapplied to a usable workspace. A neural network is also applied to gaze data for use intandem with the VI model to create a Combined Model. The output of the Combined Model is a VOI that can be used to aid in a number of applications including robot pathplanning, entertainment, ubiquitous computing, and others. An alternative Search Regionmethod is investigated as well.

Additional Information

Publication
Thesis
Language: English
Date: 2015
Keywords
assistive robotics, eye tracking, neural network, three dimensional, vector intersection, vergence
Subjects
Self-help devices for people with disabilities -- Technological innovations -- Research
Visual perception -- Research
Eye tracking

Email this document to