Expert system to interpret hand tremor and provide joystick position signals for powered wheelchairs with ultrasonic sensor systems

Abstract

PurposeThe purpose of this paper is to investigate how to make powered‐wheelchair driving easier using simple expert systems to interpret joystick and ultrasonic sensor data. The expert systems interpret shaky joystick movement and identify potentially hazardous situations and then recommend safe courses of action.Design/methodology/approachThe way that a human user interacts with a powered‐wheelchair is investigated. Some simple expert systems are presented that interpret hand tremor and provide joystick position signals for an ultrasonic sensor system. Results are presented from a series of timed tasks completed by users using a joystick to control a powered‐wheelchair. Effect on the efficiency of driving a powered‐wheelchair is measured using the times to drive through progressively more complicated courses. Drivers completed tests both with and without sensors and the most recently published systems are used to compare results.FindingsThe new expert systems consistently out‐performed the most recently published systems. A minor secondary result was that in simple environments, wheelchair drivers tended to perform better without any sensor system to assist them but in more complicated environments then they performed better with the sensor systems.Research limitations/implicationsThe time taken for a powered‐wheelchair to move from one place to another partly depends on how a human user interacts with the powered‐wheelchair. Wheelchair driving relies heavily on visual feedback and the experience of the drivers. Although attempts were made to remove variation in skill levels by using sets of data associated with each driver and then using paired statistical tests on those sets, some variation must still be present.Practical implicationsThe paper presents new systems that could allow more people to use powered‐wheelchairs and also suggests that the amount of sensor support should be varied depending on circumstances.Originality/valueThe new systems described in the paper consistently performed driving tasks more quickly than the most recently published systems.

Non-Model-Based Control of a Wheeled Vehicle Pulling Two Trailers to Provide Early Powered Mobility and Driving Experiences

“…The train is to be equipped with a Langner Scanning Collision Avoidance Device (langner-SCAD) [1] at the front of the train locomotive to detect local obstacles and stop the train. For further reading, obstacle avoidance for powered wheelchairs is described in [29]- [32].…”

Fast Transformations to Provide Simple Geometric Models of Moving Objects

“…The method is being successfully used with sensors [15,16] mobile robots [17,18,19,20,21] and wheelchairs [22,23].…”

Sensor-based ambient intelligence for optimal energy efficiency

“…That was to addresses two of the most critical problems in energy management in industrial production technologies: how to efficiently and promptly acquire and provide information online for optimising energy consumption; and how to effectively use such knowledge to support decision making. The research was inspired by the need for industry to have effective sensor systems (Sanders, 2008(Sanders, , 2009c(Sanders, , d, 2010Sanders et al, 2012b) for energy efficiency (Sanders et al, 2007(Sanders et al, , 2011c.…”