Traditional robot programming is often not feasible in small-batch production, as it is time-consuming, inefficient, and expensive. To shorten the time necessary to deploy robot tasks, we need appropriate tools to enable efficient reuse of existing robot control policies. Incremental Learning from Demonstration (iLfD) and reversible Dynamic Movement Primitives (DMP) provide a framework for efficient policy demonstration and adaptation. In this paper, we extend our previously proposed framework with improvements that provide better performance and lower the algorithm’s computational burden. Further, we analyse the learning stability and evaluate the proposed framework with a comprehensive user study. The proposed methods have been evaluated on two popular collaborative robots, Franka Emika Panda and Universal Robot UR10. ; The research leading to these results has received funding from the Horizon 2020 RIA Programme grant 820767 CoLLaboratE and from the program group P2-0076 Automation, robotics, and biocybernetics funded by the Slovenian Research Agency.
Analysis of Methods for Incremental Policy Refinement by Kinesthetic Guidance
15.04.2021
oai:zenodo.org:5586169
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
DDC: | 629 |
Incremental kinesthetic teaching of motion primitives using the motion refinement tube
British Library Online Contents | 2011
|Mini-Batched Online Incremental Learning Through Supervisory Teleoperation with Kinesthetic Coupling
Deutsches Zentrum für Luft- und Raumfahrt (DLR) | 2020
|KINESTHETIC SENSE PROVISION DEVICE AND KINESTHETIC SENSE PROVISION METHOD
Europäisches Patentamt | 2023
|