AbstractState of the art upper limb prostheses offer up to six active DoFs (degrees of freedom) and are controlled using different grip patterns. This low number of DoFs combined with a machine-human-interface which does not provide control over all DoFs separately result in a lack of usability for the patient. The aim of this novel upper limb prosthesis is both offering simplified control possibilities for changing grip patterns depending on the patients’ priorities and the improvement of grasp capability. Design development followed the design process requirements given by the European Medical Device Directive 93/42 ECC and was structured into the topics mechanics, software and drive technology. First user needs were identified by literature research and by patient feedback. Consequently, concepts were evaluated against technical and usability requirements. A first evaluation prototype with one active DoF per finger was manufactured. In a second step a test setup with two active DoF per finger was designed. The prototype is connected to an Android based smartphone application. Two main grip patterns can be preselected in the software application and afterwards changed and used by the EMG signal. Three different control algorithms can be selected: “all-day”, “fine” and “tired muscle”. Further parameters can be adjusted to customize the prosthesis to the patients’ needs. First patient feedback certified the prosthesis an improved level of handling compared to the existing devices. Using the two DoF test setup, the possibilities of finger control with a neural network are evaluated at the moment. In a first user feedback test, the smartphone based software application increased the device usability, e.g. the change within preselected grip patterns and the “tired muscle” algorithm. Although the overall software application was positively rated, the handling of the prosthesis itself needs to be proven within a patient study to be performed next. The capability of the neural network to control the hand has also to be proven in a next step.
Automated objective dystonia identification using smartphone-quality gait videos acquired in clinic