The École Polytechnique Fédérale de Lausanne (EPFL) has developed a super-small thought-reading chip, opening new opportunities for individuals with limited mobility.
The world is currently witnessing a race in the development of brain-machine interfaces (BMIs). While Elon Musk’s Neuralink chip has garnered the most attention, a much smaller and thinner chip has emerged, which is performing exceptionally well, as reported by New Atlas on August 30. The new research has been published in the IEEE Journal of Solid-State Circuits.
The super-small MiBMI chip next to a pair of tweezers and a crocodile clip. (Photo: EPFL/Lundi13-CC-BY-SA 4.0).
The new chip, developed by a research team at École Polytechnique Fédérale de Lausanne (EPFL), represents a significant advancement in brain-machine interface (BMI) technology. BMIs are devices capable of reading brain activity and converting it into real-world outputs, such as text on a screen.
The new device, called the micro brain-machine interface (MiBMI), is notable for its tiny size, consisting of two thin chips with a total area of just 8 mm². In contrast, Elon Musk’s Neuralink chip is bulkier, measuring around 23 x 8 mm.
MiBMI also consumes very little energy, is said to be minimally invasive, and features a fully integrated system with real-time data processing capabilities. This differs from Neuralink, which requires the implantation of 64 electrodes in the brain and processes information through an external device application.
“MiBMI allows for the conversion of complex neural activity into readable text with high accuracy and low power consumption. This advancement brings us closer to practical implantable solutions that could significantly enhance communication capabilities for individuals with severe mobility impairments,” said Mahsa Shoaran, head of EPFL’s Integrated Neuroscience Technology Laboratory.
Like other BMIs, the new chip monitors electrical activity in the brain. Equipped with datasets from previous brain research, it converts this activity into output. In this case, MiBMI can read brain signals generated when a person imagines writing letters and outputs those signals as text.
Unlike the Neuralink chip, which was implanted in a patient earlier this year, the new MiBMI chip has not yet been tested on humans. However, experts have provided it with real-time neural recordings obtained from previous brain interface trials. As a result, MiBMI achieved an accuracy rate of 91% in converting neural activity into actual text.
The MiBMI chip offers a communication solution for individuals who cannot speak, such as those with amyotrophic lateral sclerosis (ALS) or other severe mobility disabilities. The team of experts is exploring additional applications beyond text processing.
“We are collaborating with other research groups to test the system in various contexts, such as speech decoding and motion control. Our goal is to develop a flexible BMI that can be tailored to accommodate multiple neurological disorders, providing further solutions for patients,” Shoaran added.
