Survivors of a severe brain or spinal cord injury are often left with a lifelong disability that impacts their lives negatively. A common problem faced by them is permanent paralysis due to the damage caused to their nervous system. The most severe form of paralysis is tetraplegia, as people suffering from it have lost control of both their arms and legs. Researchers have been working for years to build devices that tetraplegic patients can control using their thoughts and perform certain activities independently. Different institutions and organizations have been working on building seamless mind-controlled robots to perform various tasks.
Previous Efforts
MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) and Boston University had a breakthrough in 2017 in their efforts to develop mind-controlled robots. They created novel machine learning (ML) algorithms for their system that could analyze brain waves in 10 to 30 milliseconds. Researchers from ETH Zurich in 2020 tried a different approach to assist disabled persons who cannot speak. They used deep learning models to convert fMRI scan data to particular words in a fixed vocabulary to understand a person’s thoughts by converting them to coherent text.
Researchers from the Institute of Electrical And Electronics Engineers (IEEE) have recently developed a system called BrainGate that allows tetraplegic persons to perform web browsing and operate mobile applications on tablets. It is basically the same as other Brain-Computer Interfaces (BCI), except it is wireless. This opens up new possibilities for potential applications.
Mind-Controlled Robotic Arm
Prof Aude Billard, the head of EPFL’s Learning Algorithms and Systems Laboratory, and Prof José del R. Millán, the former head of EPFL’s Brain-Machine Interface Laboratory, carried out a project to develop a robotic assistance system for a person suffering from motor disabilities.
According to Professor Billard, such robot assistance systems are meant for people who have suffered permanent neurological damage and lost their motor functions due to spinal cord injury. It would help them recover some of the lost dexterity and perform simple tasks.
The two research groups developed a computer program that made it possible to control a robot just by using thoughts; no voice control or touch is necessary. The system receives input from a person’s brain through a head cap equipped with electrodes for performing electroencephalogram (EEG) scans of the user’s brain signals. To use this robot arm, all the person has to do is look at it. The robot will automatically understand if it has done something wrong as our brains will emit a signal that tells the robot, “Not like that.”
The system uses a combination of inverse reinforcement learning (IRL) techniques and brain-computer interfaces (BCI) that decode error-related potentials (ErrP), which allows the system to have a reward function depending on the user’s ErrP. In other words, through a hit-and-trial method, the robot figures out the user’s needs by interpreting their brain signals. According to the lead author, Iason Batzianoulis, what was particularly difficult from a technical viewpoint was “‘translating’ a patient’s brain signals into actions performed by the robot.” They did that by using machine learning to link each brain signal to specific tasks.
It is noteworthy to mention that the first breakthrough in this field was in 2019 by researchers from Carnegie Mellon University, collaborating with the University of Minnesota. This new study by EPFL researchers represents a significant advancement in building such devices for providing day-to-day assistance to tetraplegic patients and others with limited upper body motor functions. This team of researchers has already set their sights on the next project: “A Mind-Controlled Wheelchair.”
Future is Mind-Controlled
Even though this technology will immediately help people with motor disabilities, it will not be limited to only clinical applications. Neuralink is developing “brain chips” called LINK that, when implanted in the motor cortex region of our brains, can cure conditions from disability to depression. However, according to Elon Musk, the potential of LINK is in the realm of science fiction. He believes that one day it will allow us to store our memories and replay them, among other outrageous things. Let’s hope at least some of these claims become true in the near future!
