Department of Electrical Engineering and Information Technologies, Polytechnic and Basic Sciences School, University of Naples "Federico II", 80125 Naples, Italy.
School of Engineering, Design and Built Environment, Western Sydney University, Penrith, NSW 2747, Australia.
Sensors (Basel). 2021 Oct 15;21(20):6863. doi: 10.3390/s21206863.
As a definition, Human-Machine Interface (HMI) enables a person to interact with a device. Starting from elementary equipment, the recent development of novel techniques and unobtrusive devices for biosignals monitoring paved the way for a new class of HMIs, which take such biosignals as inputs to control various applications. The current survey aims to review the large literature of the last two decades regarding biosignal-based HMIs for assistance and rehabilitation to outline state-of-the-art and identify emerging technologies and potential future research trends. PubMed and other databases were surveyed by using specific keywords. The found studies were further screened in three levels (title, abstract, full-text), and eventually, 144 journal papers and 37 conference papers were included. Four macrocategories were considered to classify the different biosignals used for HMI control: biopotential, muscle mechanical motion, body motion, and their combinations (hybrid systems). The HMIs were also classified according to their target application by considering six categories: prosthetic control, robotic control, virtual reality control, gesture recognition, communication, and smart environment control. An ever-growing number of publications has been observed over the last years. Most of the studies (about 67%) pertain to the assistive field, while 20% relate to rehabilitation and 13% to assistance and rehabilitation. A moderate increase can be observed in studies focusing on robotic control, prosthetic control, and gesture recognition in the last decade. In contrast, studies on the other targets experienced only a small increase. Biopotentials are no longer the leading control signals, and the use of muscle mechanical motion signals has experienced a considerable rise, especially in prosthetic control. Hybrid technologies are promising, as they could lead to higher performances. However, they also increase HMIs' complexity, so their usefulness should be carefully evaluated for the specific application.
作为定义,人机接口 (HMI) 使人类能够与设备交互。从基本设备开始,最近用于生物信号监测的新型技术和非侵入性设备的发展为新型 HMI 铺平了道路,这些 HMI 将生物信号作为输入来控制各种应用。本综述旨在回顾过去二十年关于用于辅助和康复的基于生物信号的 HMI 的大量文献,以概述最新技术并确定新兴技术和潜在的未来研究趋势。通过使用特定的关键词在 PubMed 和其他数据库中进行了调查。发现的研究在三个层次(标题、摘要、全文)中进行了进一步筛选,最终包括 144 篇期刊论文和 37 篇会议论文。为了对用于 HMI 控制的不同生物信号进行分类,考虑了四个大类:生物电位、肌肉机械运动、身体运动及其组合(混合系统)。还根据目标应用对 HMI 进行了分类,考虑了六个类别:假肢控制、机器人控制、虚拟现实控制、手势识别、通信和智能环境控制。近年来,观察到发表的出版物数量呈不断增长的趋势。过去几年,大多数研究(约 67%)属于辅助领域,而 20%与康复相关,13%与辅助和康复相关。在过去十年中,可以观察到专注于机器人控制、假肢控制和手势识别的研究有所增加。相比之下,其他目标的研究仅略有增加。生物电位不再是主要的控制信号,肌肉机械运动信号的使用有了相当大的增加,特别是在假肢控制中。混合技术很有前途,因为它们可以带来更高的性能。然而,它们也增加了 HMI 的复杂性,因此应根据特定应用仔细评估其有用性。