Efficient search for robot skill learning: simulation and reality

Je G. Schneider and Roger F. Gans University of Rochester Rochester, NY 14627-0226, USA Abstract Table lookup with interpolation is used for many learning and adaptation tasks. Redundant mappings capture the important concept of \motor skill" in real, behaving systems. Few robot skill implementations have dealt with redundant mappings, in which the space to be searched to create the table has much higher dimensionality than the table. A practical method for inverting redundant mappings is important in physical systems with limited time for trials. We present the \Guided table Fill In" algorithm, which uses data already stored in the table to guide search through the space of potential table entries. The algorithm is illustrated and tested on a skill learning task using a robot with a exible link. Our experiments show that the ability to search high dimensional action spaces e ciently allows skill learners to nd new behaviors that are qualitatively di erent from what they were presented or what the system designer may have expected. Thus the use of this technique can allow researchers to seek higher dimensional action spaces for their systems rather than constraining their search space at the risk of excluding the best actions. We also present a model for the robot arm, exible link dynamics, and release mechanism of our robot. Our experiments suggest that the use of even a crude simulation model can be helpful for learning on the real robot.