Human-robot cooperative assembly key information extraction based on GCN

In order to tackle the challenge of inadequate comprehension by cooperative robots during assembly tasks, we present an innovative algorithm that leverages Graph Convolutional Neural Networks. The primary objective of this algorithm is to extract essential information relevant to assembly tasks from assembly process cards. To achieve this, we also implement an Optical Character Recognition algorithm, which effectively identifies textual information contained within the cards cells. By incorporating the Graph Convolutional Neural Network, we can then capture the underlying topological relationships among the key information elements. This comprehensive approach not only facilitates the prediction of key cell locations but also help robots to autonomously comprehend assembly tasks through an automated data mining process.