An assistive, decision-and-control architecture for force-sensitive, hand–arm systems driven by human–machine interfaces (MM4)

The video shows a 2-D drinking demonstration using the Braingate2 neural interface. The robot is controlled through a multipriority Cartesian impedance controller and its behavior is extended with collision detection and reflex reaction. Furthermore, virtual workspaces are added to ensure safety. On top of this, a decision-and-control architecture which uses sensory information available from the robotic system to evaluate the current state of task execution, is employed. During the task, the full functionality of skills currently available in a skill library of the robotic systems is used.