Honors College Thesis
 

Sensorless Localization for Robots and Wheelchairs

Public Deposited

Downloadable Content

Download PDF
https://ir.library.oregonstate.edu/concern/honors_college_theses/n296x673z

Descriptions

Attribute NameValues
Creator
Abstract
  • Despite an increase in the number of people who rely on manual wheelchairs, there are still substantial economic barriers to affordable and accessible localization systems. As a result, there is a pressing need to build a versatile yet low cost localization system for manual wheelchairs. Such systems allow users to self-navigate their environment, and foster greater self-sufficiency. Existing solutions rely on external sensors to assist with localization; creating a sensor-free system will result in a much cheaper, and more accessible, solution. This thesis investigates the application of a modified Monte Carlo Localization technique to successfully localize within a simulated indoor environment. By counting predicted locations within a 1-meter radius from the original location, we evaluate the efficacy of our algorithm and optimize its parameters. We find that our sensorless approach, given environments with realistic levels of noise, is able to successfully localize. Moreover, the localization algorithm can operate on a small number of particles, and performs with greater accuracy with knowledge of the starting position.
  • Keywords: Monte Carlo Localization, Wheelchair, Robot Operating System, Python
Resource Type
Date Issued
Degree Level
Degree Name
Degree Field
Degree Grantor
Commencement Year
Advisor
Committee Member
Academic Affiliation
Non-Academic Affiliation
Rights Statement
Publisher
Peer Reviewed
Language

Relationships

Parents:

This work has no parents.

In Collection:

Items

Thumbnail Title Date Uploaded Visibility Actions
file details SubramanianAshwin2024.pdf 2024-03-12 Public Download