Interesting piece of research.
It appears that dexterous hand control for prosthetic arms is definitely on the move. With 79% average accuracy for amputees they are not exactly targeting commercial success (no one ever did, actually) but they are definitely going in a good direction.
This type of research - giving percentage figures for accuracy rates - is interesting as it makes me ask a number of follow up questions:
- How do we measure success, generally, when going about ADL / activities of daily living?
- What is an average accuracy rate for a body powered arm? Given that this morning was basically spent eating several courses of a really extended breakfast, I did not drop anything except one tiny part of an eggshell (when making fried eggs), but also, my left hand feels strained and exerted, any type of value attribution would have to take into account a range of factors. Increased functionality of a prosthetic hand could alleviate a lot of problems even at the cost of more errors - but how that would be adequately quantified, I do not know.
Online Myoelectric Control of a Dexterous Hand Prosthesis by Transradial Amputees
Cipriani, C.; Antfolk, C.; Controzzi, M.; Lundborg, G.; Rosen, B.; Carrozza, M. C.; Sebelius, F.;
The BioRobotics Institute (former ARTS and CRIM Labs), Scuola Superiore Sant'Anna, Pontedera, Italy
This paper appears in: Neural Systems and Rehabilitation Engineering, IEEE Transactions on
Issue Date: June 2011
Volume: 19 Issue:3
On page(s): 260 - 270
Digital Object Identifier: 10.1109/TNSRE.2011.2108667
A real-time pattern recognition algorithm based on k-nearest neighbors and lazy learning was used to classify, voluntary electromyography (EMG) signals and to simultaneously control movements of a dexterous artificial hand. EMG signals were superficially recorded by eight pairs of electrodes from the stumps of five transradial amputees and forearms of five able-bodied participants and used online to control a robot hand. Seven finger movements (not involving the wrist) were investigated in this study. The first objective was to understand whether and to which extent it is possible to control continuously and in real-time, the finger postures of a prosthetic hand, using superficial EMG, and a practical classifier, also taking advantage of the direct visual feedback of the moving hand. The second objective was to calculate statistical differences in the performance between participants and groups, thereby assessing the general applicability of the proposed method. The average accuracy of the classifier was 79% for amputees and 89% for able-bodied participants. Statistical analysis of the data revealed a difference in control accuracy based on the aetiology of amputation, type of prostheses regularly used and also between able-bodied participants and amputees. These results are encouraging for the development of noninvasive EMG interfaces for the control of dexterous prostheses.