A new system combining artificial intelligence and robotics is helping a quadriplegic man translate his thoughts into the movements of a robotic arm (including the action of grasping and releasing objects). The system operated for seven months without significant adjustments.
According to a research team at the University of California, San Francisco (UCSF), this is a much longer period compared to typical scenarios where such systems break down within a few days without recalibration, demonstrating the potential and capabilities of this technology.
The core of this brain-computer interface (BCI) system is an AI algorithm used to link specific brain signals to specific movements. Because the patient was able to express his thoughts while observing the robotic arm's movements in real time, errors could be corrected quickly, and the accuracy of the robot's actions could be improved.
"The fusion of human-AI learning is the next step in brain-computer interfaces," says Dr. Karunesh Ganguly, a neurologist at the University of California, San Francisco (UCSF). "This is exactly what is needed to implement sophisticated and lifelike functions."
This man was able to control a robotic arm using only his thoughts to open a cupboard, retrieve a cup, and place it under a beverage dispenser. This technology has the potential to be of great help to people with disabilities in performing various activities.
During the study, the research team discovered that while the shape of brain patterns related to movement does not change, their position shifts slightly over time. This is believed to be a phenomenon that occurs as the brain learns and absorbs new information.
0 Comments