BrainCo demonstrates brain-controlled robot AI platform
BrainCo has spent over a decade developing its brain control interface and medical rehabilitation technology. | Source: BrainCo BrainCo, a brain-computer interface, or BCI, developer this week showcased a platform that allows users to direct a robot through neural signals. At the 2026 World Artificial Intelligence Conference, a person wearing a lightweight EEG headset and BrainCo’s BCI thought about grabbing a cap, and a robotic arm reached out and performed the action. The technology work
Get smart on it
A brain-computer interface company demonstrated a platform that allows users to control a robot through brain signals picked up by an EEG headset. The system decodes neural signals through AI algorithms and converts them into robot commands in under 200 milliseconds, enabling the robotic arm to perform precise tasks like grasping objects. The company also introduced a data collection solution that captures EEG data alongside human hand movements and robot execution to create high-quality training data for teaching robots complex physical tasks, addressing a persistent challenge in robot development. This work combines brain-computer interfaces with artificial intelligence to enable a new form of human-machine collaboration.
Related news
Photos: First look at J&J’s Ottava surgical robot
Johnson & Johnson’s Ottava surgical robot has four robotic arms that come out from underneath the operating table. Photo credit: Johnson & Johnson Johnson & Johnson MedTech unveiled its long-awaited Ottava surgical robot after winning FDA de novo authorization. It’s the world’s first table-integrated, soft-tissue robotics system. The robot-in-table design is meant to save space in the operating room, with J&J saying its novel architecture takes up 30-50% less space tha
Generalist’s GEN-1 foundation model now supports a range of robot end effectors
Generalist’s latest embodied foundation model, GEN-1, now supports a broad range of robot end effectors. The company said GEN-1 is compatible with five-fingered hands to specialized tools with new modes of actuation and everything in between. By training GEN-1 to work with these new hands, Generalist said it is demonstrating that a single base AI model can learn sensorimotor policies on robots that transfer across radically different ways of interacting with the physical world. Below, the
