A groundbreaking brain-computer interface (BCI) has allowed a paralyzed man to control a robotic arm using only his imagination, defying previous limitations of short-lived BCI functionality. The AI-enhanced device worked reliably for seven months, adapting to natural shifts in brain activity and maintaining accuracy over time.
Researchers at the University of California, San Francisco (UCSF), led by neurologist Karunesh Ganguly, developed a novel BCI system that can learn from daily changes in brain activity. The study’s participant, who had been paralyzed by a stroke years earlier, successfully grasped, moved, and manipulated real-world objects using the device.
The key to success lay in adapting the AI model to account for the small changes in brain activity as the participant repeated movements or imagined actions. This allowed the system to refine its performance over time, achieving lifelike function.
Ganguly’s team achieved this by studying how patterns of brain activity in animals represent specific movements and applied that knowledge to human subjects. The study participant was able to control a robotic arm with remarkable precision, performing tasks such as picking up blocks, turning them, and moving them to new locations.
The breakthrough has significant implications for people with paralysis, offering hope for restoring movement and independence. Ganguly is now refining the AI models to make the robotic arm move faster and more smoothly, planning to test the BCI in a home environment.
“This blending of learning between humans and AI is the next phase for these brain-computer interfaces,” said Ganguly. “I’m very confident that we’ve learned how to build the system now, and that we can make this work.”
Source: https://neurosciencenews.com/ai-robot-arm-bci-neurotech-28471