Reinforcement learning in real-time geometry assurance
Paper in proceeding, 2018

To improve the assembly quality during production, expert systems are often used. These experts typically use a system model as a basis for identifying improvements. However, since a model uses approximate dynamics or imperfect parameters, the expert advice is bound to be biased. This paper presents a reinforcement learning agent that can identify and limit systematic errors of an expert systems used for geometry assurance. By observing the resulting assembly quality over time, and understanding how different decisions affect the quality, the agent learns when and how to override the biased advice from the expert software.

expert advice

reinforcement learning

geometry assurance

Author

Emilio Jorge

Fraunhofer-Chalmers Centre

Lucas Brynte

Fraunhofer-Chalmers Centre

Constantin Cronrath

Chalmers, Electrical Engineering, Systems and control

Oskar Wigström

Chalmers, Electrical Engineering, Systems and control

Kristofer Bengtsson

Chalmers, Electrical Engineering, Systems and control

Emil Gustavsson

Fraunhofer-Chalmers Centre

Bengt Lennartson

Chalmers, Electrical Engineering, Systems and control

Mats Jirstrand

Fraunhofer-Chalmers Centre

Procedia CIRP

22128271 (eISSN)

Vol. 72 1073-1078

51st CIRP Conference on Manufacturing Systems, CIRP CMS 2018
Stockholm, Sweden,

Smart Assembly 4.0

Swedish Foundation for Strategic Research (SSF) (RIT15-0025), 2016-05-01 -- 2021-06-30.

Subject Categories

Software Engineering

Computer Science

Computer Systems

DOI

10.1016/j.procir.2018.03.168

More information

Latest update

1/20/2023