Robotic Embodiment of Human-Like Motor Skills via Sim-to-Real Reinforcement Learning
2021-12
Title
Robotic Embodiment of Human-Like Motor Skills via Sim-to-Real Reinforcement Learning
Authors
Published Date
2021-12
Publisher
Type
Thesis or Dissertation
Abstract
State of the art methods continue to face difficulties automating many tasks, particularly those which require human-like dexterity. The proposed "Internet of Skills" enables robots to learn advanced skills from a small set of expert demonstrations, bridging the gap between human and robot abilities. In this work, I train Reinforcement Learning (RL) control policies for the tasks of hand following and block pushing. I build a sim-to-real pipeline and demonstrate these policies on a Kinova Gen3 robot. Lastly, I test a prototype system that allows an expert to control the Kinova robot using only their arm movements, captured using a Vicon motion tracking system. My results show that performance of state of the art RL methods could be improved through the use of demonstrations, and I build a shared representation of human and robot action that will enable robots to learn new skills from observing expert actions.
Description
University of Minnesota M.S. thesis. 2021. Major: Computer Science. Advisor: Nikolaos Papanikolopoulos. 1 computer file (PDF); 29 pages + 1 supplementary file.
Related to
Replaces
License
Series/Report Number
Funding information
Isbn identifier
Doi identifier
Previously Published Citation
Suggested citation
Guzman, Luis. (2021). Robotic Embodiment of Human-Like Motor Skills via Sim-to-Real Reinforcement Learning. Retrieved from the University Digital Conservancy, https://hdl.handle.net/11299/226343.
Content distributed via the University Digital Conservancy may be subject to additional license and use restrictions applied by the depositor. By using these files, users agree to the Terms of Use. Materials in the UDC may contain content that is disturbing and/or harmful. For more information, please see our statement on harmful content in digital repositories.