Combining Gaussian Processes and Conventional Path Planning in a Learning from Demonstration Framework

Today, robots are already able to solve specific tasks in laboratory environments. Since everyday environments are more complex, the robot skills required to solve everyday tasks cannot be known in advance and thus not be programmed beforehand. Rather, the robot must be able to learn those tasks being instructed by users without any technical background. Hence, Learning from Demonstration (LfD) is one of the essential topics to bring robots out of the lab moving towards everyday robustness. The key property of an agent regarding a demonstration learned skill is its ability of generalization, that is, applying a learned skill to situations that differ from those during demonstration. In this paper, we present a method to enhance the generalization capabilities of an advanced new LfD framework by combining it with conventional path planning.