Development of a Learning-Based Intention Detection Framework for Power-Assisted Manual Wheelchair Users

Abstract

Pushrim-activated power-assisted wheels (PAPAWs) are assistive technologies that provide on-demand assistance to wheelchair users. PAPAWs operate based on a collaborative control scheme. Therefore, they rely on accurate interpretation of the user’s intent to provide effective propulsion assistance. This paper presents a learning-based approach to predict wheelchair users’ intention when performing a variety of wheelchair activities. We obtained kinematic and kinetic data from manual wheelchair users when performing standard wheelchair activities such as turns and ascents. Our measurements revealed variability in physical capabilities and propulsion habits of different users, therefore, highlighting the need for the development of personalized intention inference models. We used Gaussian Mixture models to label different phases of user-pushrim interactions based on individual user’s wheeling behaviour. Supervised classifiers were trained with each user’s data and these models were used to predict the user’s intentions during different propulsion activities. We found random forest classifiers had high accuracy (>92%) in predicting different states of individual-specific wheelchair propulsion and user intent for 2 participants. This proposed framework is computationally efficient and can be used for real-time prediction of wheelchair users’ intention. The outcome of this clustering-classification pipeline provides relevant information for designing user-specific and adaptive PAPAW controllers.