Assessment of advanced behaviours for assistive robotic wheelchairs

Publication Type:
Thesis
Issue Date:
2016
Full metadata record
Research demonstrates that use of appropriate Assistive Technology (AT) is associated with increased independence and reduced need for ongoing care and support. Powered mobility devices (PMDs) such as power wheelchairs and scooters are proving to be useful pieces of assistive technology. This study focuses on developing and assessing the validity of a stand-alone sensor package and algorithms to help the assessment by an Occupational Therapists (OT) whether a person has the capacity to safely and efficiently operate a powered mobility device such as a wheelchair in their daily activities. This is accomplished by analysing data computed from a standalone sensor package fitted on a wheelchair platform. The proposed solution consists of a suite of sensors capable of inferring navigational features from the platform it is attached to (e.g. trajectories, map of surroundings, speeds, distance to doors, etc). The study aims to compare and contrast objective data derived from a PMD mounted sensor package with subjective data obtained using a standard Occupational Therapy assessment. The research work demonstrated that accurate, reliable objective data from a sensor package can be used to augment the Occupational Therapists subjective assessment. Furthermore, the task-specific parameters that may provide the most relevant user information for the assessment are automatically revealed through a machine learning approach. Machine learning automated assessment classification tests, with data attained from multiple runs of able clients simulating varying degrees of erraticness in their driving skills while they performed the assessment tasks, have indicated success rates in the order of 85%.
Please use this identifier to cite or link to this item: