Indoor Location and Collision Feedback for a Powered Wheelchair System Using Machine Learning

Abstract

In 2015 a powered wheelchair system that can detect and avoid objects was enhanced with a Raspberry Pi to extend the number of inputs the system could use to infer information about its environment. Wheelchair users are not always able to use simple controls such as joystick to drive, they may have to control the wheelchair using tongue, head or feet. This can make it much more difficult to learn how to drive and therefore is important to know how a user is progressing. The research described in this paper employs machine learning to uses wireless access points and predict its location, and with prolonged use will learn routes between rooms and buildings. The system uses location and accelerometer data to present information about driving patterns and collisions behaviour, to inform the wheelchair user and carer of issues while driving the wheelchair.

Intelligent Control of the Steering for a Powered Wheelchair Using a Microcomputer

“…Many researchers investigated navigation and steering [18][19][20][21][22] and obstacles avoidance [23] has been considered using local sensors [24], but they have barely moved out of the laboratory to assist disabled wheelchair users. A new architecture is described here that uses sensors to effectively assist with driving.…”

Intelligent System to Analyze Data About Powered Wheelchair Drivers

“…Considerable research was conducted to study the steering and navigation of powered wheelchairs [5][6][7][8][9][10][11][12][13][14][15][16][17]. The systems used were often local, and slight work has been made to improve mobility using more global approaches.…”

Use of the Analytical Hierarchy Process to Determine the Steering Direction for a Powered Wheelchair

“…Intelligent mixing of the two routes generates a new route. The desired route is modified depending on sensor readings [1][2][3][4][5][6][7][8][9][10][11] to help disabled drivers.…”