Learning parameterized motor skills on a humanoid robot

Bruno Castro da Silva, Gianluca Baldassarre, George Dimitri Konidaris, Andrew G. BartoICRA 2014 · OpenReview

Abstract

We demonstrate a sample-efficient method for constructing reusable parameterized skills that can solve families of related motor tasks. Our method uses learned policies to analyze the policy space topology and learn a set of regression models which, given a novel task, appropriately parameterizes an underlying low-level controller. By identifying the disjoint charts that compose the policy manifold, the method can separately model the qualitatively different sub-skills required for solving distinct classes of tasks. Such sub-skills are useful because they can be treated as new discrete, specialized actions by higher-level planning processes. We also propose a method for reusing seemingly unsuccessful policies as additional, valid training samples for synthesizing the skill, thus accelerating learning. We evaluate our method on a humanoid iCub robot tasked with learning to accurately throw plastic balls at parameterized target locations.
BibTeX
@inproceedings{silva2014learning,
  author = {Bruno Castro da Silva and Gianluca Baldassarre and George Dimitri Konidaris and Andrew G. Barto},
  title = {{Learning parameterized motor skills on a humanoid robot}},
  booktitle = {IEEE International Conference on Robotics and Automation},
  year = {2014},
  url = {https://openreview.net/forum?id=JXIt6jefiB},
}

Loading related content...

Figure