The assisted assembly of customized products supported by collaborative robots combined with mixed reality devices is the current trend in the Industry 4.0 concept. This article introduces an experimental work cell with the implementation of the assisted assembly process for customized cam switches as a case study. The research is aimed to design a methodology for this complex task with full digitalization and transformation data to digital twin models from all vision systems. Recognition of position and orientation of assembled parts during manual assembly are marked and checked by convolutional neural network (CNN) model. Training of CNN was based on a new approach using virtual training samples with single shot detection and instance segmentation. The trained CNN model was transferred to an embedded artificial processing unit with a high-resolution camera sensor. The embedded device redistributes data with parts detected position and orientation into mixed reality devices and collaborative robot. This approach to assisted assembly using mixed reality, collaborative robot, vision systems, and CNN models can significantly decrease assembly and training time in real production.

The paper deals with the optimization of production processes and the setting of criteria for reducing production costs. Any company is not just a leap in production, but a lean has to be gradually transferred to all its activities. This created the concept of a lean company first. The skill of an enterprise is to perform only the activities that are needed, to do them right for the first time, to make them faster than others and to spend less resources at the same time. The company's business is that the company does exactly what the customer wants, with a minimum number of activities that do not add value to the product or service. The Lean Production System focuses mainly on eliminating waste in every activity of the manufacturing enterprise.