Graduation Semester and Year

Spring 2025

Language

English

Document Type

Thesis

Degree Name

Master of Science in Computer Science

Department

Computer Science and Engineering

First Advisor

Dr Nicholas R. Gans

Second Advisor

Dr Manfred Huber

Third Advisor

Dr Chris Dale McMurrough

Abstract

This paper presents our preliminary study on enabling individuals with visual impairments to safely operate mobile robots and vehicles. To achieve this, we developed a teleoperation with accessibility at its core. The system incorporates features that enhance usability and situational awareness, including assistive control based on artificial potential fields to prevent collisions and ensure smooth navigation. It also provides multimodal feedback through (a) haptic vibrations on the gamepad controller, which convey the proximity of nearby objects detected by the robot’s laser sensor, and (b) color-coded overlays that differentiate paths, obstacles, and people through semantic segmentation performed by a deep neural network on the robot’s camera feed. To evaluate its effectiveness, we partnered with the Austin Lighthouse to conduct experiments in which legally blind participants used the system to successfully guide the robot through a testing area with obstacles

Keywords

Robotics, visually impaired, teleoperated, virtual fixtures

Disciplines

Robotics

Available for download on Tuesday, November 11, 2025

Included in

Robotics Commons

Share

COinS