Approach for Unsupervised Interaction Clustering in Human-Robot Co-Work using Spatio-Temporal Graph Convolutional Networks

Aaron Heuermann^1,2*Zied Ghrairi¹Anton Zitnikov²Abdullah Al Noman¹Klaus-Dieter Thoben¹

• ¹Bremen Institute for Production and Logistics (BIBA), University of Bremen, Bremen, Germany
• ²University of Bremen, Bremen, Bremen, Germany

This paper presents an approach to cluster interaction forms in industrial human-robot co-work using Spatio-Temporal Graph Convolutional Networks (STGCN). Increasingly, humans will work with robots, whereas previously, humans worked side by side, hand in hand, or alone. More frequent robotic and human-robot co-working applications and the requirement to increase flexibility affect the variety and variability of interactions between humans and robots, which can be observed at the production workplaces. This paper investigates the variety and variability of human-robot interactions in industrial co-work scenarios where full automation is impractical. To address the challenges of interaction modeling and clustering, we present an approach that utilizes Spatio-Temporal Graph Convolutional Networks (STGCN) for interaction clustering. Data were collected from 12 realistic human-robot co-work scenarios using a high-accuracy tracking system. The approach identified 10 distinct interaction forms, revealing more granular interaction patterns than established taxonomies. These results support continuous, data-driven analysis of human-robot behavior and contribute to the development of more flexible, human-centered systems aligned with Industry 5.0.