Long-Term Upper-Limb Prosthesis Myocontrol via High-Density sEMG and Incremental Learning
This work addresses long-term usability and accuracy issues in prosthetic control for amputees, though it is incremental in combining existing high-density sensing with incremental learning methods.
The paper tackled the problem of long-term myoelectric prosthesis control by integrating high-density sEMG with incremental learning to manage distribution shifts, achieving accurate control of 7 motions over several months with 7 subjects, including one with limb absence, and releasing the DELTA dataset.
Noninvasive human-machine interfaces such as surface electromyography (sEMG) have long been employed for controlling robotic prostheses. However, classical controllers are limited to few degrees of freedom (DoF). More recently, machine learning methods have been proposed to learn personalized controllers from user data. While promising, they often suffer from distribution shift during long-term usage, requiring costly model re-training. Moreover, most prosthetic sEMG sensors have low spatial density, which limits accuracy and the number of controllable motions. In this work, we address both challenges by introducing a novel myoelectric prosthetic system integrating a high density-sEMG (HD-sEMG) setup and incremental learning methods to accurately control 7 motions of the Hannes prosthesis. First, we present a newly designed, compact HD-sEMG interface equipped with 64 dry electrodes positioned over the forearm. Then, we introduce an efficient incremental learning system enabling model adaptation on a stream of data. We thoroughly analyze multiple learning algorithms across 7 subjects, including one with limb absence, and 6 sessions held in different days covering an extended period of several months. The size and time span of the collected data represent a relevant contribution for studying long-term myocontrol performance. Therefore, we release the DELTA dataset together with our experimental code.