Transfer Learning-enabled Action Recognition for Human-robot Collaborative Assembly

Abstract Human-robot collaboration (HRC) is critical to today’s tendency towards high-flexible assembly in manufacturing. Human action recognition, as one of the core prerequisites for HRC, enables industrial robots understand human intentions and execute planning adaptively. However, existing deep learning-based recognition methods rely heavily on a huge amount annotation data, which may not be effective or realistic practice. Therefore, transfer learning-enabled approach proposed this research facilitate robot reactive control HRC assembly. Meanwhile, decision-making mechanism robotic introduced well. Lastly, evaluated an aircraft bracket scenario reveal its significance.