An approach for monitoring the execution of human based assembly operations using machine learning

During the past years, as part of the continuous research to increase productivity in industrial sector, hybrid solutions allowing the cooperation of industrial robots with operators have been studied. Those combine characteristics from both worlds, such as high accuracy, speed and repeatability of a robot with dexterity of human to perform delicate tasks Sensing systems have been introduced safeguarding the operators, while primitive workflow monitoring systems, primarily based on operator's feedback, enhance the dynamic behaviour of the system. This paper presents an approach to automatically monitor the execution of human based assembly operations using vision sensors and machine learning techniques. A reference example based on the assembly of a water pump is showcasing the effectiveness of the proposed approach in real-life application. (C) 2019 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/) Peer-review under responsibility of the scientific committee of the 7th CIRP Global Web Conference