Date of Award

1-1-2016

Document Type

Masters Thesis

Degree Name

M.S.

Organizational Unit

Daniel Felix Ritchie School of Engineering and Computer Science, Electrical and Computer Engineering

First Advisor

Mohammad Mahoor, Ph.D.

Second Advisor

Timothy Sweeny

Third Advisor

Kimon Valavanis

Fourth Advisor

Matthew Rutherford

Keywords

Assistive technologies, Robotics, Socially assistive robotics, Social robots

Abstract

There has been tremendous progress in the field of robotics in the past decade and especially developing humanoid robots with social abilities that can assist human at a socio-emotional level. The objective of this thesis is to develop and study a perceptive and expressive animal-like robot equipped with artificial intelligence in assisting the elderly people with depression. We investigated how social robots can become companions of elderly individuals with depression and improve their mood and increase their happiness and well-being. The robotic platform built in this thesis is a bear-like robot called the eBear. The eBear can show facial expression and head gesture, can understand user's emotion using audio-video sensory inputs and machine learning, can speak and show relatively accurate visual speech, and make dialog with users. the eBear can respond to their questions by querying the Internet, and even encourage them to physically be more active and even perform simple physical exercises. Besides building the robot, the eBear was used in running a pilot study in which seven elderly people with mild to severe depression interacted with the eBear for about 45 minutes three times a week over one month. The results of the study show that interacting with the eBear can increase happiness and mood of these human users as measured by Face Scale, and Geriatric Depression Scale (GDS) score systems. In addition, using Almere Model, it was concluded that the acceptance of the social agent increased over the study period. Videos of the users interaction with the eBear was analyzed and eye gaze, and facial expressions were manually annotated to better understand the behavior changes of users with the eBear. Results of these analyses as well as the exit surveys completed by the users at the end of the study demonstrate that a social robot such as the eBear can be an effective companion for the elderly people and can be a new approach for depression treatment.

Publication Statement

Copyright is held by the author. User is responsible for all copyright compliance.

Rights Holder

Amirhossein Kargarbideh

Provenance

Received from ProQuest

File Format

application/pdf

Language

en

File Size

146 p.

Discipline

Engineering, Robotics



Included in

Robotics Commons

Share

COinS