Graduation Semester and Year

Fall 2024

Language

English

Document Type

Dissertation

Degree Name

Doctor of Philosophy in Computer Science

Department

Computer Science and Engineering

First Advisor

Fillia Makedon

Second Advisor

Nicholas Gans

Third Advisor

Ming Li

Fourth Advisor

Leonidas Fegaras

Fifth Advisor

William Beksi

Abstract

People who are blind and vision impaired often require assistance in performing various tasks. With new technologies emerging in the recent years, vision impaired people either require assistance in accessing those technologies or in using those technologies to perform different tasks in real life. Previous works have focused on assisting vision impaired people in different scenarios such as navigation, accessing smartphone interfaces etc. With the recent developments in robotics, a new research has emerged where new systems can be developed for vision impaired people to interact with robots to perform various human robot interactive tasks. But with developing new and individual technologies for assisting vision impaired people in each and every task will either become a burden for them to use it or become infeasible for them to acquire those technologies. Also, many of the previous works have developed systems that might place a hardware load or computational load on the user while using them to perform tasks. There is a need for developing an unified system that can assist vision impaired people in performing different tasks by accessing the system.

This dissertation research focuses on developing an unified cross-modal interactive system that can be used by people who are vision impaired for assistance in both human navigation tasks and human robot interactive tasks in indoor environments. In terms of human navigation, this work focuses on assisting vision impaired people in avoiding collision with moving people during navigation in indoor environments. In terms of human robot interaction, this work focuses on two tasks:

• Identifying objects and their locations in indoor environment based on user requests

• Robotic collision avoidance even when vision impaired people are moving around in the environment

The user can use different modalities such as speech, and human pose hand signs to send request or data to the system, for assistance in human navigation tasks and human robot interaction tasks. The system will be implemented such that certain components can be interchangeably used for both human navigation tasks and human robot interactive tasks thus making it an integrated system.

Keywords

Human Robot Interaction, Vision Impaired Navigation, Collision Avoidance, Pose Classification, Depth Estimation, Robotics, SLAM

Disciplines

Artificial Intelligence and Robotics | Graphics and Human Computer Interfaces

License

Creative Commons Attribution 4.0 International License
This work is licensed under a Creative Commons Attribution 4.0 International License.

Share

COinS
 
 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.