VersendenDrucken

Brain-controlled Robotics

We investigate various methods to control the DLR Light-Weight-Robot III with five-finger-hand via brain interfaces.  The LWR's various soft-robotics control schemes are embedded in a human-friendly state-based control architecture which enables the development of complex interaction scenarios. The LWR-III is equipped with the modular DLR-HIT five-finger hand for grasping and holding objects. Similar to the robot, this hand is equipped with joint torque sensors for impedance control which makes it robust against uncertainties in the environment such as the position of objects to be grasped.

We use EMG for controlling the grasp force of the hand as well as the position of the arm in a user-intuitive manner.  To this end, an adaptive system learns the correspondence between the human hand position and orientation and the muscular activity measured at the skin surface.  To this end we can control to move the arm and grasp an object in teleoperation/telemanipulation.  Such control schemes are also applicable in rehabilitation and orthoses environments.

We are furthermore investigating the control of the DLR-LWR-III with five-finger-hand through human cortical implants.  Further information will appear here as soon as the first publications on this joint work are out.

Other interfaces, including invasive communication with the human peripheral nervous system as well as surface EEG control are within the realm of our research spectrum.