MIT researchers developed a framework that lets a user correct a robot's behavior during deployment using simple interactions, such as by pointing to an item, tracing a trajectory, or nudging the ...

Google DeepMind has unveiled two AI models, Gemini Robotics and Gemini Robotics-ER, designed to enhance robot control. Gemini Robotics features “vision-language-action” (VLA) capabilities, enabling it ...

In Apple's promotional video, the prototype robot responds to user gestures and vocal commands, demonstrating attentiveness. Waving, pointing, and pushing tell the robot to bring the light closer ...