Please use this identifier to cite or link to this item:
Type of publication: research article
Type of publication (PDB): Straipsnis Clarivate Analytics Web of Science / Article in Clarivate Analytics Web of Science (S1)
Field of Science: Informatika / Informatics (N009)
Author(s): Tamošiūnaitė, Minija;Nemec, Bojan;Ude, Aleš;Wörgötter, Florentin
Title: Learning to pour with a robot arm combining goal and shape learning for dynamic movement primitives
Is part of: Robotics and autonomous systems. Amsterdam : Elsevier Science, Vol. 59, iss. 11, 2011
Extent: p. 910-922
Date: 2011
Keywords: Dynamic movement primitives;Value function approximation;Reinforcement learning;PI2-method;Natural actor critic
Abstract: When describing robot motion with dynamic movement primitives (DMPs), goal (trajectory endpoint), shape and temporal scaling parameters are used. In reinforcement learning with DMPs, usually goals and temporal scaling parameters are predefined and only the weights for shaping a DMP are learned. Many tasks, however, exist where the best goal position is not a priori known, requiring to learn it. Thus, here we specifically address the question of how to simultaneously combine goal and shape parameter learning. This is a difficult problem because learning of both parameters could easily interfere in a destructive way. We apply value function approximation techniques for goal learning and direct policy search methods for shape learning. Specifically, we use “policy improvement with path integrals” and “natural actor critic” for the policy search. We solve a learning-to-pour-liquid task in simulations as well as using a Pa10 robot arm. Results for learning from scratch, learning initialized by human demonstration, as well as for modifying the tool for the learned DMPs are presented. We observe that the combination of goal and shape learning is stable and robust within large parameter regimes. Learning converges quickly even in the presence of disturbances, which makes this combined method suitable for robotic applications
Affiliation(s): Informatikos fakultetas
Vytauto Didžiojo universitetas
Appears in Collections:Universiteto mokslo publikacijos / University Research Publications

Files in This Item:
marc.xml9.64 kBXMLView/Open

MARC21 XML metadata

Show full item record
Export via OAI-PMH Interface in XML Formats
Export to Other Non-XML Formats

CORE Recommender

Citations 1

checked on Apr 24, 2021

Page view(s)

checked on May 1, 2021


checked on May 1, 2021

Google ScholarTM



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.