Planning for automatic product assembly using reinforcement learning

2021 ◽  
Vol 130 ◽  
pp. 103471
Author(s):  
Heng Zhang ◽  
Qingjin Peng ◽  
Jian Zhang ◽  
Peihua Gu
2013 ◽  
Vol 655-657 ◽  
pp. 1697-1701 ◽  
Author(s):  
Yuan Liang Sun ◽  
Yuan Li ◽  
Jie Zhang ◽  
Zhi Jia Xu

Assembly design and simulation plays a very important role among all stages of product design, and is the fundamental guarantee to improve the assembly performance of product. However, in current assembly design and simulation process, the detailed assembly path and the assembly position and orientation of parts are all needed to be defined through human-computer interaction. Especially when a product contains quantities of parts, there will be so many human-computer interactions to do, which can greatly increase the burden of designers. For this reason, the purpose of this paper is to study an automatic assembly method to reduce the complexity in the definition of assembly design and simulation. Firstly, we studied the intrinsic relationship between the Assembly Feature Pair (AFP) and assembly behaviors of a part, and it’s our belief that the AFP pattern of one part determines its assembly behaviors. And then we proposed an automatic product assembly method based on AFP, by which one only need to enter or specify certain parameters to achieve the assembly design and simulation of a part. Finally, a simple toolset developed based on CATIA and DELMIA using this method was introduced, and an example was given to verify the validity of this approach.


Decision ◽  
2016 ◽  
Vol 3 (2) ◽  
pp. 115-131 ◽  
Author(s):  
Helen Steingroever ◽  
Ruud Wetzels ◽  
Eric-Jan Wagenmakers

Sign in / Sign up

Export Citation Format

Share Document