Fusing Hand and Body Skeletons for Human Action Recognition in Assembly

TL;DR

This paper introduces a method that combines coarse body skeletons with detailed hand skeletons using CNNs and transformers to improve human action recognition in assembly tasks for collaborative robots.

Contribution

It proposes a novel fusion approach of body and hand skeletons with attention mechanisms, enhancing recognition accuracy for assembly actions.

Findings

Improved action recognition accuracy in assembly scenarios.

Transformers effectively fuse information from body and hand skeletons.

Demonstrated effectiveness of the approach in real-world tasks.

Abstract

As collaborative robots (cobots) continue to gain popularity in industrial manufacturing, effective human-robot collaboration becomes crucial. Cobots should be able to recognize human actions to assist with assembly tasks and act autonomously. To achieve this, skeleton-based approaches are often used due to their ability to generalize across various people and environments. Although body skeleton approaches are widely used for action recognition, they may not be accurate enough for assembly actions where the worker's fingers and hands play a significant role. To address this limitation, we propose a method in which less detailed body skeletons are combined with highly detailed hand skeletons. We investigate CNNs and transformers, the latter of which are particularly adept at extracting and combining important information from both skeleton types using attention. This paper demonstrates the effectiveness of our proposed approach in enhancing action recognition in assembly scenarios.