Electromyography data for non-invasive naturally-controlled robotic hand prostheses

TLDR

Recent advances in rehabilitation robotics suggest that hand‑amputated subjects could regain significant hand function, yet non‑invasive control of prosthetic hands remains challenging due to limited capabilities, unnatural operation, and long training times, and current literature, while promising, still falls short of real‑life requirements. This work aims to close this gap by enabling worldwide research groups to develop and test movement recognition and force control algorithms on a benchmark scientific database. The database is designed to study the relationship between surface electromyography, hand kinematics, and hand forces, ultimately supporting the development of non‑invasive, naturally controlled robotic hand prostheses. Validation shows that the data resemble real‑life conditions and that different hand tasks can be recognized using state‑of‑the‑art signal features and machine‑learning algorithms.

Abstract

Recent advances in rehabilitation robotics suggest that it may be possible for hand-amputated subjects to recover at least a significant part of the lost hand functionality. The control of robotic prosthetic hands using non-invasive techniques is still a challenge in real life: myoelectric prostheses give limited control capabilities, the control is often unnatural and must be learned through long training times. Meanwhile, scientific literature results are promising but they are still far from fulfilling real-life needs. This work aims to close this gap by allowing worldwide research groups to develop and test movement recognition and force control algorithms on a benchmark scientific database. The database is targeted at studying the relationship between surface electromyography, hand kinematics and hand forces, with the final goal of developing non-invasive, naturally controlled, robotic hand prostheses. The validation section verifies that the data are similar to data acquired in real-life conditions, and that recognition of different hand tasks by applying state-of-the-art signal features and machine-learning algorithms is possible.