Deep Learning architecture to assist with steering a powered wheelchair

Malik Haddad, David Sanders

Research output: Contribution to journalArticlepeer-review

332 Downloads (Pure)

Abstract

This paper describes a novel Deep Learning architecture to assist with steering a powered wheelchair. A rule-based approach is utilized to train and test a Long Short Term Memory (LSTM) Neural Network. It is the first time a LSTM has been used for steering a powered wheelchair. A disabled driver uses a joystick to provide desired speed and direction, and the Neural Network provides a safe direction for the wheelchair. Results from the Neural Network are mixed with desired speed and direction to avoid obstacles. Inputs originate from a joystick and from three ultrasonic transducers attached to the chair. The resultant course is a blend of desired directions and directions that steer the chair to avoid collision. A rule-based approach is used to create a training and test set for the Neural Network system and applies deep learning to predict a safe route for a wheelchair. The user can over-ride the new system if necessary.
Original languageEnglish
Article number9225000
Pages (from-to)2987-2994
Number of pages7
JournalIEEE Transactions on Neural Systems and Rehabilitation Engineering
Volume28
Issue number12
Early online date15 Oct 2020
DOIs
Publication statusPublished - 1 Dec 2020

Keywords

  • Deep Learning
  • Wheelchair
  • Neural Network
  • Rule-based
  • Disabled
  • Steer
  • RCUK
  • EPSRC
  • EP/S005927/1

Fingerprint

Dive into the research topics of 'Deep Learning architecture to assist with steering a powered wheelchair'. Together they form a unique fingerprint.

Cite this