Sign in Subscribe
Artificial intelligence

AI-Powered Safety Framework for Human-Robot Collaborative Work Cells

Strategic Insights

— 1 min read

Researchers at Kyungpook National University in South Korea have developed a groundbreaking safety framework for human-robot collaborative work cells, leveraging artificial intelligence (AI) and digital twin technology. This innovative approach utilizes multi-domain vision sensors to monitor worker and robot positions in real-time, enabling dynamic calculation of Flexible Protective Separation Distances (FPSD) for adaptive robot velocity control and safety stops. The research has far-reaching implications for smart manufacturing, offering a flexible and efficient safety framework that enhances productivity and minimizes the risk of accidents.

Key Takeaways:

  • The safety framework, developed by Kyungpook National University researchers, integrates AI-driven 3D pose estimation and Digital Twin visualization to enhance safety and productivity in human-robot collaborative (HRC) work cells.
  • Experimental results demonstrate that FPSD significantly outperforms static Protective Separation Distance (PSD) methods, achieving collaboration times of 2.50 s (98.04%) and 5.40 s (99.08%) in gantry and collaborative robot experiments, respectively.
  • The system reduces unnecessary robot pauses with average response times of 0.021 s for deceleration and 0.032 s for stops, ensuring robust collision prevention.
  • The research was funded by the Industrial Technology Innovation Program and the Ministry of Trade, Industry, and Energy (Motie, South Korea).
  • The study highlights the potential for scalable deployment of the safety framework in smart manufacturing, offering a flexible and efficient safety framework.
  • The research was published in IEEE Access, a leading peer-reviewed scientific journal, with the article titled "AI and Digital Twin Federation-Based Flexible Safety Control for Human-Robot Collaborative Work Cell."

Statistics:

  • The FPSD method achieved collaboration times of 2.50 s (98.04%) and 5.40 s (99.08%) in gantry and collaborative robot experiments, respectively.
  • The static PSD method achieved collaboration times of 0.25 s (9.80%) and 2.50 s (45.87%) in gantry and collaborative robot experiments, respectively.
  • The system reduces unnecessary robot pauses with average response times of 0.021 s for deceleration and 0.032 s for stops.

Sources:

  • "AI and Digital Twin Federation-Based Flexible Safety Control for Human-Robot Collaborative Work Cell." IEEE Access, 2025,13():124037-124050. (IEEE Access - http://ieeexplore.ieee.org/servlet/opac?punumber=6287639).
  • NewsRx. Research from Kyungpook National University in Robotics Provides New Insights (AI and Digital Twin Federation-Based Flexible Safety Control for Human-Robot Collaborative Work Cell). Journal of Engineering. August 4, 2025; p 3690.

Read more