Chinese Journal of Intelligent Science and Technology ›› 2022, Vol. 4 ›› Issue (2): 200-211.doi: 10.11959/j.issn.2096-6652.202223

• Special Topic: Autonomous Agent Learning for Dexterous and Accurate Manipulations • Previous Articles    

Research development on automated robotic peg-in-hole assembly

De XU, Fangbo QIN   

  1. Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China
  • Online:2022-06-01 Published:2022-06-01
  • Supported by:
    The National Key Research and Development Program of China(2018AAA0103005);The National Natural Science Foundation of China(61873266);The National Natural Science Foundation of China(62103413)

Abstract:

Peg-in-hole assembly is a typical operation task in manufactory.The research of peg-in-hole assembly based on industrial robots is valuable for the application of robots in the automated assembly area.For the peg-in-hole components with high precision or complex shapes, the efficient and reliable assembly is still very challenging.The development of automated robotic peg-in-hole assembly of peg-in-hole was reviewed from the view of control.First, the process of robotic peg-in-hole assembly was introduced.Secondly, the assembly control methods based on the traditional models were described.The newly emerged intelligent assembly methods based on learning mechanism were discussed, especially the applications of imitation learning and reinforcement learning in the automated robotic assembly.The combination of the traditional methods and the artificial intelligent methods will provide new energy for the automated robotic assembly, which will be one of the important developing tendencies in future.

Key words: peg-in-hole assembly, intelligent robot, imitation learning, reinforcement learning, skill learning

CLC Number: 

No Suggested Reading articles found!