Myoelectric Control of Artificial Limbs-Is There a Need to Change Focus?

The basic concept of myoelectric control and the state of the art in both industry and academia is discussed. Myoelectric control has a great potential for improving the quality of life of persons with limb deficiency. The pattern classification approach for myoelectric control is based on the assumption that there exist distinguishable and repeatable signal patterns among different types of muscular activations. A pattern classification myoelectric controller usually consists of three main steps, segmentation, feature extraction, and classification. The main problem with the pattern classification for myoelectric control is that it inherently leads to a control scheme that is substantially different from the natural control. Academic research has focused on refining classification accuracy, creating a gap between he academia and the industry state of the art. This gap could be filled by addressing the specific needs of intuitive myoelectric control and system robustness.