At this stage, the research is a proof-of-concept study, based on experiments combining neuroengineering and robotics using three amputees and seven healthy subjects, at the Ecole Polytechnique Fédérale de Lausanne. The combined scienctific field of neuroprosthetics covers both neuroscience and biomedical engineering, and it is concerned with developing neural prostheses. There are similarities with brain–computer interface technologies (which connects the brain to a computer), although in the case of neuroprosthetics this is about linking a device that is intended to replace some form of missing biological functionality.
An earlier example of neuroprostheses is where devices have been used that use electrodes to interface with the nervous system and aim to restore function that has been lost due to spinal cord injury, restoring some motor, sensory, and autonomic functions by stimulating various parts of the nervous system.
With the new research, scientists have successfully tested new neuroprosthetic technology that combines robotic control with users’ voluntary control. This research opens up avenues in the new interdisciplinary field of shared control for neuroprosthetic technologies.
Concepts from neuroengineering allow the user to decipher intended finger movement from muscular activity being triggered from on the amputee’s stump. This provides individual finger control of the prosthetic hand. Concepts from robotics enables the robotic hand to take hold of objects and maintain contact with them for robust grasping. A specially developed algorithm is required to interpret the user’s intention, and this has been improved through machine learning.
Further detail about the research, and with the device functioning, is shown in the following video:
According to lead researcher Aude Billard, the new prosthetic devices are more advanced then any previous types. He uses an example to explain this: “When you hold an object in your hand, and it starts to slip, you only have a couple of milliseconds to react. The robotic hand has the ability to react within 400 milliseconds. Equipped with pressure sensors all along the fingers, it can react and stabilize the object before the brain can actually perceive that the object is slipping.”
The research findings have been published in the journal Nature Machine Intelligence. The research paper is: “Shared human–robot proportional control of a dexterous myoelectric prosthesis.”
