Research
BrainCo, a brain-computer interface (BCI) developer, showcased a platform that allows users to direct a robot through neural signals at the 2026 World Artificial Intelligence Conference. The technology enables a person wearing a lightweight EEG headset to control a robotic arm by simply thinking about an action, such as grabbing a cap, which the robot then performs.
The system operates in three steps: an EEG headset picks up brain signals, AI algorithms decode those signals to identify motor intent, and that intent is converted into commands for the robot, with the entire process taking under 200 milliseconds. “A decade of BCI research has given us the ability to decode what a person intends to do and translate that into machine action,” said Nyx He, partner and senior vice president of BrainCo. “By integrating brain-computer interfaces, AI, and embodied AI, we believe it will define the next chapter of human-machine collaboration.”
A decade of BCI research has given us the ability to decode what a person intends to do and translate that into machine action.
During the demonstration in Shanghai, the mind-controlled robotic arm completed precision tasks such as grasping a cup or picking up an apple. BrainCo designed its platform to work with a wide range of commercially available robots, from humanoids to robotic arms and legged robots, without requiring proprietary hardware. The Somerville, Mass.-based company described its framework as “neuro-embodied-AI,” where BCI decodes intent, the AI layer refines that intent into actionable steps, and the robot’s own systems handle physical execution. At WAIC, BrainCo also debuted its Embodied AI Data Collection Solution, aiming to help close the robot training data gap.
Source: The Robot Report