Application of Machine Learning for Improving the Algorithm for Capturing, Orienting and Placing an Object with 6-Axis Robot and 2d Visual Inspection Camera

Abstract

The current paper presents the implementation of machine learning to improve the algorithm for taking a part with a specific marker from a 6-axis robot, by serve it to a 2D camera for visual inspection and its correct orientation based on information received from the camera and placement on another part with a pre-marked marker direction. The aim of the present development is to increase the efficiency of automated production of electronic products. After the introduction of machine learning in the algorithm for determining distortions, injuries or other damage to the part, an improvement was achieved in the quality of the processed parts and a reduction of production waste by up to 30%, which led to an increase in system efficiency by 25%.