Brain waves give movement to robotic exoskeleton
European researchers are testing a mind-controlled robotic exoskeleton that could enable fully paralysed people to walk again.
The €2.75m Mindwalker project uses an easily fitted electrode cap placed on the patient’s head to read brain signals related to movement that can be turned into commands for operating the exoskeleton.
The robotic suit itself, which is attached to the patient’s legs, is designed to mimic more closely the way people walk than other exeskeletons that require an additional walking frame or sticks to support the user.
‘Mindwalker was proposed as a very ambitious project intended to investigate promising approaches to exploit brain signals for the purpose of controlling advanced orthosis, and to design and implement a prototype system demonstrating the potential of related technologies,’ said project coordinator Michel Ilzkovitz of the Space Applications Services in Belgium.
He added that the technology developed for Mindwalker could also have applications in stroke victim rehabilitation and in assisting astronauts rebuild muscle mass after prolonged periods in space.
Once tests with able-bodied trial users are complete, the system will undergo clinical evaluation with five to 10 volunteers suffering from spinal cord injuries, which will help identify any problems and improve performance.
The researchers have developed a brain-neural-computer interface (BNCI) that converts electroencephalography (EEG) signals from the brain, or electromyography (EMG) signals from shoulder muscles, into electronic commands to control the exoskeleton.
To collect the signals, they used technology developed by Berlin-based eemagine Medical Imaging Solutions that consists of a cap covered in electrodes that amplifies and optimises signals before sending them to the neural network.
This contrasts with most other BNCI systems that either require electrodes to be placed directly into brain tissue, or take a long time to fit and use special gels to reduce the electrical resistance at the interface between the skin and the electrodes.
‘The “dry” EEG cap can be placed by the subject on their head by themselves in less than a minute, just like a swimming cap,’ said Ilzkovitz.
The BNCI signals also have to be filtered and processed before they can be used to control the exoskeleton. To achieve this, the Mindwalker researchers fed the signals into a ‘Dynamic recurrent neural network’, a processing technique capable of learning and exploiting the dynamic character of the BNCI signals.
‘This is appealing for kinematic control and allows a much more natural and fluid way of controlling an exoskeleton,’ said Ilzkovitz.
The exoskeleton itself can support a 100kg adult and is powerful enough to recover balance from instability created by the user’s torso movements during walking or a gentle push from the back or side.
It is relatively light, weighing less than 30kg without batteries, and uses springs fitted inside the joints that are capable of absorbing and recovering some of the energy otherwise dissipated during walking, in order to make it more energy efficient.
Unlike most exoskeletons that are designed to be balanced when stationary – a property that makes them heavy, slow and require additional support when moving – the Mindwalker uses a controlled loss of balance.
‘This approach is called “Limit-cycle walking” and has been implemented using model predictive control to predict the behaviour of the user and exoskeleton and for controlling the exoskeleton during the walk,’ said Ilzkovitz.
Space Applications Services also developed a virtual-reality training platform to allow new users to safely become accustomed to using the system before testing it out in a clinical setting.
Mindwalker was coordinated by Space Applications Services NV and received research funding under the European Union’s Seventh Framework Programme (FP7).