A Robot Programming by Demonstration Method for Precise Manipulation in 3C Assembly
Zhilong Zhao, Haopeng Hu, Xiansheng Yang, Yunjiang Lou
- Year
- 2019
- Citations
- 2
Abstract
Industrial robots have been widely used in various production line but not in the 3C assembly line which is characterized by highly frequent change-over and still relies on labor heavily. To deal with this challenge, the Programming by Demonstration (PbD) method, which provides a simple and intuitive way for workers to transfer skills to the robot, will greatly reduces professional knowledge requirements for robot users. However, some practical factors in 3C assembly line, such as the mechanical diversities between the human body and the robot, make it difficult to apply PbD methods. Motivated by that, with a subtly designed demonstration data extraction platform and a posture mapping strategy, this article proposes a PbD method that transforms human assembly skill to the robot for 3C assembly tasks. Further more, by an iterative optimization method, the demonstration path is simplified to boost the assembly efficiency which counts for much in practice. A simulation and a 3C assembly experiment has demonstrated the effectiveness of the proposed method.
Keywords
Related papers
Statistical Learning Theory
Yuhai Wu, Vladimir Vapnik
1999
Artificial intelligence: a modern approach
1995
Applied Nonlinear Control
Jean-Jacques Slotine, Weiping Li
1991
A new optimizer using particle swarm theory
R.C. Eberhart, James Kennedy
2002