An Affordances based approach to assisted teleoperation

The introduction of teleoperated robots in scenarios in which human manipulation dexterity does not have to be limited by the teleoperation system is one of the greatest challenges in the field of telecontrol. In this paper we propose an approach for capturing and transferring human manupulative skills to a robotic manipulator that is able to supervise the teleoperation process by means of a proactive support that introduces elastic motion constraints around specific motion primitives. By exploiting not only information about motion, but also the relationships between the manipulator and the objects, in the form of affordances, the system is capable of assisting the human operator in order to improve the teleoperation task performances. We test the algorithm with a Microsoft Kinect RGBD sensor that allows human body pose tracking and the semi-humanoid Baxter Robot by Rethink Robotics as teleoperated platform.