A joint project of the Graduate School, Peabody College, and the Jean & Alexander Heard Library

Title page for ETD etd-03242017-160746


Type of Document Master's Thesis
Author Li, Mingqi
Author's Email Address mingqi.li@vanderbilt.edu
URN etd-03242017-160746
Title Skill Transfer between Humans and Robots Based on Dynamic Movement Primitives and Sparse Autoencoder
Degree Master of Science
Department Electrical Engineering
Advisory Committee
Advisor Name Title
Richard Alan Peters Committee Chair
Kazuhiko Kawamura Committee Member
Keywords
  • Dynamic Movement Primitives
  • Skill Transfer
  • Robot kinematics
  • Sparse Autoencoder
Date of Defense 2017-03-24
Availability unrestricted
Abstract
With the development of robotic industry, subhuman robots are paid more attention. In order to meet people’s requirements, robots need to grasp human’s behaviors and service human beings. Skill transfer is the core for this procedure. In this thesis, we supply a process to transfer behaviors from humans to robots or from robots to robots. The technical contributions of this procedure include: (1) two approaches to capture human’s behavior trajectories; (2) building model to solve robotic kinematics problems; (3) applying Dynamic Movement Primitives (DMP) to achieve targets of reproducing trajectory; (4) combining DMP with Sparse Autoencoder to increase efficient of procedure. As the result, trajectories are transferred successfully from human to robot and from robot to robot. Meanwhile, performances of inverse kinematics and DMP are proved.
Files
  Filename       Size       Approximate Download Time (Hours:Minutes:Seconds) 
 
 28.8 Modem   56K Modem   ISDN (64 Kb)   ISDN (128 Kb)   Higher-speed Access 
  LiMingqi.pdf 3.38 Mb 00:15:37 00:08:02 00:07:02 00:03:31 00:00:18

Browse All Available ETDs by ( Author | Department )

If you have more questions or technical problems, please Contact LITS.