Cognition, Technology & Work

, Volume 9, Issue 4, pp 189–207

Gesture recognition for control of rehabilitation robots


  • L. Gerlich
    • School of Engineering SystemsMiddlesex University
  • B. N. Parsons
    • Becrypt LtdWyrols Court
    • School of Computing ScienceMiddlesex University
  • S. Prior
    • Product Design and EngineeringMiddlesex University
  • P. Warner
    • School of Engineering SystemsMiddlesex University
Original Article

DOI: 10.1007/s10111-007-0062-3

Cite this article as:
Gerlich, L., Parsons, B.N., White, A.S. et al. Cogn Tech Work (2007) 9: 189. doi:10.1007/s10111-007-0062-3


This paper describes the development of a control user interface for a wheelchair-mounted manipulator for use by severely disabled persons. It explains the construction of the interface using tasks to define the user interface architecture. The prototype robot used several gesture recognition systems to achieve a level of usability better than other robots used for rehabilitation at the time. The use of neural networks and other procedures is evaluated. It outlines the experiments used to evaluate the user responses and draws conclusions about the effectiveness of the whole system. It demonstrates the possibility of control using a head mouse.


User interfaceRehabilitation roboticsGesture recognitionNeural networks

Copyright information

© Springer-Verlag London Limited 2007