Title: A hybrid human-machine interface for hands-free control of an intelligent wheelchair

Authors: Lai Wei, Huosheng Hu

Addresses: School of Computer Science and Electronic Engineering, University of Essex, Wivenhoe Park, Colchester CO4 3SQ, UK. ' School of Computer Science and Electronic Engineering, University of Essex, Wivenhoe Park, Colchester CO4 3SQ, UK

Abstract: This paper presents a novel hybrid human-machine interface (HMI) designed for hands-free control of electric powered wheelchairs. Both forehead electromyography (EMG) signals and colour face image information are deployed to identify winking and jaw clenching movements of human face. Five winking and jaw clenching movement patterns are selected and classified, mapping into six control commands to drive an electric powered wheelchair in an indoor environment. Six subjects participated in the experiments and the experimental results show that the proposed control scheme have potential applicability to accommodate various individual cases and achieve good performance.

Keywords: human-machine interface; HMI; face detection; eye detection; electromyography; EMG signals; SVM; electric wheelchairs; computer vision; boosting; multi-modality; support vector machines; hands-free control; intelligent wheelchairs; colour face images; winking; jaw clenching; disabled support.

DOI: 10.1504/IJMA.2011.040040

International Journal of Mechatronics and Automation, 2011 Vol.1 No.2, pp.97 - 111

Available online: 12 May 2011 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article