Utilizing Gaze Behavior for Inferring Task Transitions Using Abstract Hidden Markov Models

We demonstrate an improved method for utilizing observed gaze behavior and show that it is useful in inferring hand movement intent during goal directed tasks. The task dynamics and the relationship between hand and gaze behavior are learned using an Abstract Hidden Markov Model (AHMM). We show that...

Full description

Saved in:

Bibliographic Details
Published in:	Inteligencia artificial 2016, Vol.19 (58), p.1-16
Main Author:	Pinpin, Kenneth
Format:	Article
Language:	eng
Subjects:	AHM Gaze Modeling Gaze Tracking Probabilistic Graphical Model Task Transitions Prediction
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	We demonstrate an improved method for utilizing observed gaze behavior and show that it is useful in inferring hand movement intent during goal directed tasks. The task dynamics and the relationship between hand and gaze behavior are learned using an Abstract Hidden Markov Model (AHMM). We show that the predicted hand movement transitions occur consistently earlier in AHMM models with gaze than those models that do not include gaze observations.
ISSN:	1988-3064 1137-3601 1988-3064