a comparative analysis of three non-invasive human-machine interfaces for the disabled

In the framework of rehabilitation robotics, a major role is played by theHuman-Machine Interface (HMI) used to gather the patient's intent from biologicalsignals, and convert them into control signals for the robotic artifact. Surprisingly,decades of research haven't yet declared what the optimal HMI is in this context;in particular, the traditional approach based upon surface electromyography (sEMG)still yields unreliable results due to the inherent variability of the signal. Toovercome this problem, the scientific community has recently been advocating thediscovery, analysis and usage of novel HMIs to supersede or augment sEMG; a comparativeanalysis of such HMIs is therefore a very desirable investigation.In this paper we compare three such HMIs employed in the detection of finger forces,namely sEMG, ultrasound imaging and pressure sensing. The comparison is performed alongfour main lines: the accuracy in the prediction, the stability over time, the wearabilityand the cost. A psychophysical experiment involving ten intact subjects engaged ina simple finger-flexion task was set up. Our results show that, at least in thisexperiment, pressure sensing and sEMG yield comparably good prediction accuraciesas opposed to ultrasound imaging; and that pressure sensing enjoys a much better stabilitythan sEMG.Given that pressure sensors are as wearable as sEMG electrodes but way cheaper, we claimthat this HMI could represent a valid alternative /augmentation to sEMG to control amulti-fingered hand prosthesis.