— We present a framework for the programming of manipulation behavior by means of an intrinsic reward function that encourages the building of deep control knowledge. We show how...
Several intelligent features are embedded in the Growing Competitive Linear Local Mapping Neural Network. They result in an adaptive, fast-learning, very efficient control scheme, ...
A method to learn and reproduce robot force interactions in a Human-Robot Interaction setting is proposed. The method allows a robotic manipulator to learn to perform tasks which ...
Petar Kormushev, Sylvain Calinon, Darwin G. Caldwe...
We describe a robot system that autonomously acquires skills through interaction with its environment. The robot learns to sequence the execution of a set of innate controllers to...
George Konidaris, Scott Kuindersma, Roderic A. Gru...
— In this paper, we discuss the manipulation of an object under hybrid active/passive closure. We show the orthogonality between the directions of active and passive force closur...