Programming Everyday Task by Demonstration using Primitive Skills for a Manipulator

Pham Ngoc Hung, Takashi Yoshimi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This manuscript presents a method to program everyday manipulation tasks for a robot by human demonstration using primitive skills. The hand movement in the demonstrated task is recorded then segmented into sub-actions. Each sub-action is mapped to primitives skills of the robot. We proposed a list of necessary skills for a manipulator which are common to use in many everyday tasks. In order to adapt with the change of object's location, we applied Dynamic Movement Primitives model for regenerating movement which follows the demonstrated trajectory. In experiment, we considered the task 'dispensing water' from a water thermos pot performed by a robot arm to verify the proposed method.

Original languageEnglish
Title of host publication2017 IEEE 7th Annual International Conference on CYBER Technology in Automation, Control, and Intelligent Systems, CYBER 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages321-325
Number of pages5
ISBN (Print)9781538604892
DOIs
Publication statusPublished - 2018 Aug 24
Event7th IEEE Annual International Conference on CYBER Technology in Automation, Control, and Intelligent Systems, CYBER 2017 - Honolulu, United States
Duration: 2017 Jul 312017 Aug 4

Publication series

Name2017 IEEE 7th Annual International Conference on CYBER Technology in Automation, Control, and Intelligent Systems, CYBER 2017

Other

Other7th IEEE Annual International Conference on CYBER Technology in Automation, Control, and Intelligent Systems, CYBER 2017
Country/TerritoryUnited States
CityHonolulu
Period17/7/3117/8/4

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Control and Optimization

Fingerprint

Dive into the research topics of 'Programming Everyday Task by Demonstration using Primitive Skills for a Manipulator'. Together they form a unique fingerprint.

Cite this