No abstract

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

We present a novel sensory device that can noninvasively capture the muscle activations in the lower arm in unprecedented detail. The primary motivation for building the sensor was to have a new input channel to control modern stateof-the-art multi-degree-of-freedom prosthetic hands, but many interesting use cases have arisen such as its use as an input device in the areas of manual intelligence research, computer gaming and immersive virtual reality environments.The modular compact tactile sensor bracelet has up to 320 highly sensitive sensor elements and measures the bulgings of muscles around the full circumference of the arm. In a preliminary experiment described in this paper, we trained a linear regression model to learn the mapping between the sensor values and flexion of three fingers plus two degrees of freedom of the wrist. The results show that the measured high dimensional force pattern corresponds to targeted single-digit activity.The soft surface of the sensor and the flexible links between the single modules make the bracelet comfortable to wear and conformable to various arm and residual limb shapes.

No abstract