With Industry 4.0, the number of robotic systems working with operators in manufacturing has occurred a further growth. In this context, it is fundamental to guarantee the well-being of operators sharing a workspace with industrial robots, aiming to lead the robot to fully adapt to humans, reducing risky and/or harmful situations for the operators. For this purpose, monitoring systems are exploited to study the most suitable deep learning methodologies to obtain information from the movements of the individual operator performing a specific task. Action segmentation can be fundamental to establish a new, safe way of communication among operators and robots.
Deep Learning methodologies for action recognition in manufacturing
Laura Romeo
2022
Abstract
With Industry 4.0, the number of robotic systems working with operators in manufacturing has occurred a further growth. In this context, it is fundamental to guarantee the well-being of operators sharing a workspace with industrial robots, aiming to lead the robot to fully adapt to humans, reducing risky and/or harmful situations for the operators. For this purpose, monitoring systems are exploited to study the most suitable deep learning methodologies to obtain information from the movements of the individual operator performing a specific task. Action segmentation can be fundamental to establish a new, safe way of communication among operators and robots.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.