Human-machine interfaces to control prosthetic devices still suffer from scarce dexterity\nand low reliability; for this reason, the community of assistive robotics is exploring novel solutions to\nthe problem of myocontrol. In this work, we present experimental results pointing in the direction\nthat one such method, namely Tactile Myography (TMG), can improve the situation. In particular,\nwe use a shape-conformable high-resolution tactile bracelet wrapped around the forearm/residual\nlimb to discriminate several wrist and finger activations performed by able-bodied subjects and\na trans-radial amputee. Several combinations of features/classifiers were tested to discriminate\namong the activations. The balanced accuracy obtained by the best classifier/feature combination\nwas on average 89.15% (able-bodied subjects) and 88.72% (amputated subject); when considering\nwrist activations only, the results were on average 98.44% for the able-bodied subjects and 98.72%\nfor the amputee. The results obtained from the amputee were comparable to those obtained by the\nable-bodied subjects. This suggests that TMG is a viable technique for myoprosthetic control, either\nas a replacement of or as a companion to traditional surface electromyography.
Loading....