You are here

UCF Digital Collections ยป ETD Collection

Modeling and Compensation for Efficient Human Robot Interaction

Download pdf | Full Screen View

Date Issued:
2016
Abstract/Description:
The purpose of this research is to first: identify the important human factors to performance when operating an assistive robotic manipulator, second: develop a predictive model that will be able to determine a user's performance based on their known human factors, and third: develop compensators based on the determined important human factors that will help improve user performance and satisfaction. An extensive literature search led to the selection of ten potential human factors to be analyzed including reaction time, spatial abilities (orientation and visualization), working memory, visual perception, dexterity (gross and fine), depth perception, and visual acuity of both eyes (classified as strongest and weakest). 93 participants were recruited to perform six different pick-and-place and retrieval tasks using an assistive robotic device. During this time, a participants Time-on-Task, Number-of-Moves, and Number-of-Moves per minute were recorded. From this it was determined that all the human factors except visual perception were considered important to at least one aspect of a user's performance. Predictive models were then developed using random forest, linear models, and polynomial models. To compensate for deficiencies in certain human factors, the GUI was redesigned based on a heuristic analysis and user feedback. Multimodal feedback as well as adjustments in the sensitivity of the input device and reduction in the robot's speed of movement were also implemented. From a user study using 15 participants it was found that certain compensation did improve satisfaction of the users, particularly the multimodal feedback and sensitivity adjustment. The reduction of speed was met with mixed reviews from the participants.
Title: Modeling and Compensation for Efficient Human Robot Interaction.
57 views
25 downloads
Name(s): Paperno, Nicholas, Author
Behal, Aman, Committee Chair
Haralambous, Michael, Committee Member
Boloni, Ladislau, Committee Member
University of Central Florida, Degree Grantor
Type of Resource: text
Date Issued: 2016
Publisher: University of Central Florida
Language(s): English
Abstract/Description: The purpose of this research is to first: identify the important human factors to performance when operating an assistive robotic manipulator, second: develop a predictive model that will be able to determine a user's performance based on their known human factors, and third: develop compensators based on the determined important human factors that will help improve user performance and satisfaction. An extensive literature search led to the selection of ten potential human factors to be analyzed including reaction time, spatial abilities (orientation and visualization), working memory, visual perception, dexterity (gross and fine), depth perception, and visual acuity of both eyes (classified as strongest and weakest). 93 participants were recruited to perform six different pick-and-place and retrieval tasks using an assistive robotic device. During this time, a participants Time-on-Task, Number-of-Moves, and Number-of-Moves per minute were recorded. From this it was determined that all the human factors except visual perception were considered important to at least one aspect of a user's performance. Predictive models were then developed using random forest, linear models, and polynomial models. To compensate for deficiencies in certain human factors, the GUI was redesigned based on a heuristic analysis and user feedback. Multimodal feedback as well as adjustments in the sensitivity of the input device and reduction in the robot's speed of movement were also implemented. From a user study using 15 participants it was found that certain compensation did improve satisfaction of the users, particularly the multimodal feedback and sensitivity adjustment. The reduction of speed was met with mixed reviews from the participants.
Identifier: CFE0006370 (IID), ucf:51504 (fedora)
Note(s): 2016-08-01
Ph.D.
Engineering and Computer Science, Electrical Engineering and Computer Engineering
Doctoral
This record was generated from author submitted information.
Subject(s): human-robot interaction -- assistive robotics
Persistent Link to This Record: http://purl.flvc.org/ucf/fd/CFE0006370
Restrictions on Access: campus 2019-08-15
Host Institution: UCF

In Collections