University of Notre Dame
Browse
- No file added yet -

Autonomous, Vision-Based, Pivoting Wheelchair With Obstacle Detection Capability

Download (2.46 MB)
thesis
posted on 2004-03-25, 00:00 authored by Guillermo Del Castillo
An advanced prototype computer controlled power wheelchair or CPWNS has been developed to provide autonomy for highly disabled users, whose mix of disabilities makes it difficult or impossible to control their own power chairs in their homes. The working paradigm is 'teach and repeat' a mode of control for typical industrial holonomic robots. The industrial robot-control system stores internal joint poses that have been selected by a human operator and recalls them in sequence to execute each recurring task. Sequential pose replication for the 'nonholonomic' wheelchair, while entailing additional, computationally intensive, considerations of estimation, computer-vision observations, collision-avoidance, and control, can be equally effective. Path segments that connect wheelchair positions/orientations of interest within the home or office are first taught by pushing the chair through the path that is to be recalled later. The teaching event occurs with the estimator 'turned on'. Ultrasound sensors, which during subsequent autonomous tracking will be used to avoid obstacles, also are active during teaching. Based upon post-processed data collected during this teaching event, elaborate trajectories -- which may involve multiple direction changes, pivoting and so on, depending upon the requirements of the typically restricted spaces within which the chair must operate -- will later be called upon by the disabled rider. The postprocessor also assigns an ultrasound profile to the sequence of poses. Use of this profile during tracking obviates most of the inherent problems of using ultrasound to avoid obstacles while retaining the ability to near solid objects where required by the environment and trajectory objectives. Likewise, use of the same wall-mounted visual cues for reference/estimation during both the teaching and tracking events eliminates the need for globally accurate prior mapping of the cue locations. The vehicle has been tested extensively and successfully with disabled veterans at the Edward J. Hines, Jr. VA Hospital in Hines IL.

History

Date Created

2004-03-25

Date Modified

2018-10-30

Research Director(s)

David W. Severson

Committee Members

Michael M. Stanisic Bill Goodwine Alan P. Bowling Steven B. Skaar

Degree

  • Doctor of Philosophy

Degree Level

  • Doctoral Dissertation

Language

  • English

Alternate Identifier

etd-03252004-101438

Publisher

University of Notre Dame

Program Name

  • Aerospace and Mechanical Engineering

Usage metrics

    Dissertations

    Categories

    No categories selected

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC