Learning hand movements from markerless demonstrations for humanoid tasks

We present a framework for generating trajectories of the hand movement during manipulation actions from demonstrations so the robot can perform similar actions in new situations. Our contribution is threefold: 1) we extract and transform hand movement trajectories using a state-of-the-art markerless full hand model tracker from Kinect sensor data; 2) we develop a new bio-inspired trajectory segmentation method that automatically segments complex movements into action units, and 3) we develop a generative method to learn task specific control using Dynamic Movement Primitives (DMPs). Experiments conducted both on synthetic data and real data using the Baxter research robot platform validate our approach.