Enhancing sustainability of human-robot collaboration in industry 5.0: Context- and interaction-aware human motion prediction for proactive robot control

Abstract

Industry 5.0 (I5.0) marks a shift towards human-centric, sustainable, and resilient production systems, with Human-Robot Collaboration (HRC) contributing to these goals. Achieving sustainability of HRC, encompassing economic, environmental, and social dimensions, remains challenging to ensure safety, efficiency, and adaptability. Human Motion Prediction (HMP) can address these challenges by enabling robots to anticipate human actions and respond proactively. However, existing HMP studies often neglect to incorporate contextual and interaction-based information. The practical applicability of HMP in industrial settings requires further demonstration. Therefore, this study aims to apply context- and interaction-aware HMP to enhance sustainability of HRC in I5.0. A motion capture system collects human motion data, while a camera tracks object position as contextual information. Human-Object Interaction (HOI) is identified for HMP. A transformer model is applied for HMP based on integrated context and interaction data. Additionally, the applicability of HMP in industrial settings is demonstrated by a power transformer assembly. Two additional cases are applied for validation. Results show that object recognition achieved 98 % accuracy. The identified interaction periods are effective in enhancing HMP performance. HMP with context and interaction data achieves an Average Displacement Error (ADE) of 0.07 m and a Final Displacement Error (FDE) of 0.10 m. The demonstration results suggest that the HMP enabled proactive robot control, contributing to safer, more efficient, and adaptive production. The findings of this research contribute to enhancing the sustainability of HRC in I5.0, with potential benefits for environmental efficiency, worker safety, and productivity in industrial settings.