Authors:
Lars Carøe Sørensen
;
Jacob Pørksen Buch
;
Henrik Gordon Petersen
and
Dirk Kraft
Affiliation:
University of Southern Denmark, Denmark
Keyword(s):
Learning and Adaptive Systems, Compliant Assembly, Intelligent and Flexible Manufacturing.
Related
Ontology
Subjects/Areas/Topics:
Engineering Applications
;
Industrial Automation and Robotics
;
Industrial Engineering
;
Informatics in Control, Automation and Robotics
;
Intelligent Control Systems and Optimization
;
Machine Learning in Control Applications
;
Optimization Algorithms
;
Robotics and Automation
;
Signal Processing, Sensors, Systems Modeling and Control
Abstract:
Learning action parameters is becoming an ever more important topic in industrial assembly with tendencies
towards smaller batch sizes, more required flexibility and process uncertainties. This paper presents a statistical
online learning method capable of handling these issues. The method uses elimination of unpromising
parameter sets to reduce the elements of the discretised sample space (inspired by Action Elimination) based
on regression uncertainty. Kernel Density Estimation and Wilson Score are explored as internal representations.
Based on a dynamic simulator setup for a real world Peg-in-Hole problem, it is shown that the presented
method can drastically reduce the number of samples needed. Furthermore, it is also shown that the solution
obtained in simulation by our learning method succeeds when executed on the corresponding real world setup.