Skip to main content
Kent Academic Repository

Feature determination from powered wheelchair user joystick input characteristics for adapting driving assistance

Gillham, Michael, Pepper, Matthew G., Kelly, Stephen W., Howells, Gareth (2017) Feature determination from powered wheelchair user joystick input characteristics for adapting driving assistance. Wellcome Open Research, 2 . Article Number 93. ISSN 2398-502X. (doi:10.12688/wellcomeopenres.12280.3) (KAR id:65459)

Abstract

Background: Many powered wheelchair users find their medical condition and

their ability to drive the wheelchair will change over time. In order to maintain

their independent mobility, the powered chair will require adjustment over time

to suit the user's needs, thus regular input from healthcare professionals is

required. These limited resources can result in the user having to wait weeks

for appointments, resulting in the user losing independent mobility,

consequently affecting their quality of life and that of their family and carers. In

order to provide an adaptive assistive driving system, a range of features need

to be identified which are suitable for initial system setup and can automatically

provide data for re-calibration over the long term.

Methods: A questionnaire was designed to collect information from powered

wheelchair users with regard to their symptoms and how they changed over

time. Another group of volunteer participants were asked to drive a test platform

and complete a course which represented manoeuvring in a very confined

space as quickly as possible. Two of those participants were also monitored

over a longer period in their normal home daily environment. Features, thought

to be suitable, were examined using pattern recognition classifiers to determine

their suitability for identifying the changing user input over time.

Results: The results are not designed to provide absolute insight into the

individual user behaviour, as no ground truth of their ability has been

determined, they do nevertheless demonstrate the utility of the measured

features to provide evidence of the users’ changing ability over time whilst

driving a powered wheelchair.

Conclusions: Determining the driving features and adjustable elements

provides the initial step towards developing an adaptable assistive technology

for the user when the ground truths of the individual and their machine have

been learned by a smart pattern recognition system

Item Type: Article
DOI/Identification number: 10.12688/wellcomeopenres.12280.3
Divisions: Divisions > Division of Computing, Engineering and Mathematical Sciences > School of Engineering and Digital Arts
Depositing User: Michael Gillham
Date Deposited: 14 Dec 2017 16:17 UTC
Last Modified: 10 Oct 2023 15:37 UTC
Resource URI: https://kar.kent.ac.uk/id/eprint/65459 (The current URI for this page, for reference purposes)

University of Kent Author Information

Gillham, Michael.

Creator's ORCID:
CReDIT Contributor Roles:

Pepper, Matthew G..

Creator's ORCID:
CReDIT Contributor Roles:

Kelly, Stephen W..

Creator's ORCID:
CReDIT Contributor Roles:

Howells, Gareth.

Creator's ORCID: https://orcid.org/0000-0001-5590-0880
CReDIT Contributor Roles:
  • Depositors only (login required):

Total unique views for this document in KAR since July 2020. For more details click on the image.