Among the currently available grasp-type selection techniques for hand prostheses, there is a distinct lack of intuitive, robust, low-latency solutions. In this paper we investigate the use of a portable, forearm-mounted, video-based technique for the prediction of hand-grasp preshaping for arbitrary objects. The purpose of this system is to automatically select the grasp-type for the user of the prosthesis, potentially increasing ease-of-use and functionality. This system can be used to supplement and improve existing control strategies, such as surface electromyography (sEMG) pattern recognition, for prosthetic and orthotic devices. We designed and created a suitable dataset consisting of RGB-D video data for 2212 grasp examples split evenly across 7 classes; 6 grasps commonly used in activities of daily living, and an additional no-grasp category. We processed and analyzed the dataset using several state-of-the-art deep learning architectures. Our selected model shows promising results for realistic, intuitive, real-world use, reaching per-frame accuracies on video sequences of up to 95.90% on the validation set. Such a system could be integrated into the palm of a hand prosthesis, allowing an automatic prediction of the grasp-type without requiring any special movements or aiming by the user.

The past decade has seen an increasing number of motor control studies using functional magnetic resonance imaging to explore the underlying neural mechanisms. To enable advanced experimental paradigms under well-controlled and reproducible conditions, a number of fMRI-compatible haptic interfaces have been developed for such studies. These devices typically rely on actuation principles and transmissions with non-linear behavior and large output impedance. Fiberoptic force sensors are a common and well-established means of measuring interaction forces with subjects or to reduce the inherent dynamics of the haptic interface through force feedback. The elastic probes for such sensors are typically fabricated by expensive methods such as electro-erosion of non-ferromagnetic metals or injection moulding of polymers, or are realized by milling of polymers, resulting in bulky structures. In this paper we propose a compact and integrated elastic probe for fiberoptics-based force sensing, developed using low-cost off-the-shelf 3D printing technology. Characterization of the sensor probe shows high linearity, repeatability and temporal stability, as well as high reproducibility in terms of the manufacturing process. The realized sensor is integrated into a linear grasper to evaluate its performance in force-feedback applications, underlining the potential of this technology for use in fMRI-compatible haptic interfaces.