Robotics: Science and Systems VII

Learning to Control a Low-Cost Manipulator using Data-Efficient Reinforcement Learning

Marc Deisenroth, Carl Rasmussen, Dieter Fox


Over the last years, there has been substantial progress in robust manipulation in unstructured environments. The long-term goal of our work is to get away from precise, but very expensive robotic systems and to develop affordable, potentially imprecise, self-adaptive manipulator systems that can interactively perform tasks such as playing with children. In this paper, we demonstrate how a low-cost off-the-shelf robotic system can learn closed-loop policies for a stacking task in only a handful of trials-from scratch. Our manipulator is inaccurate and provides no pose feedback. For learning a controller in the work space of a Kinect-style depth camera, we use a model-based reinforcement learning technique. Our learning method is data efficient, reduces model bias, and deals with several noise sources in a principled way during long-term planning. We present a way of incorporating state-space constraints into the learning process and analyze the learning gain by exploiting the sequential structure of the stacking task.



    AUTHOR    = {Marc Deisenroth AND Carl Rasmussen AND Dieter Fox}, 
    TITLE     = {Learning to Control a Low-Cost Manipulator using Data-Efficient Reinforcement Learning}, 
    BOOKTITLE = {Proceedings of Robotics: Science and Systems}, 
    YEAR      = {2011}, 
    ADDRESS   = {Los Angeles, CA, USA}, 
    MONTH     = {June},
    DOI       = {10.15607/RSS.2011.VII.008}