Advancements in Human-Robot Collaboration in Manufacturing Industry 5.0

Strategic Insights -

Researchers from Zhejiang University have presented a novel gait identity recognition method using Inertial Measurement Unit (IMU) data to enable personalized human-robot collaboration in manufacturing settings, contributing to the human-centric vision of Industry 5.0. The proposed method leverages wearable IMU sensors to capture motion data, including 3-axis acceleration and 3-axis angular velocity, and employs a two-tower Transformer architecture to extract and analyze gait features. Experimental results demonstrate the better performance of the proposed method in gait identity recognition compared to other state-of-the-art studies on two public datasets and one self-collected dataset.

Key Takeaways:

  • The integration of human-robot collaboration (HRC) in manufacturing, particularly within the framework of Human-Cyber-Physical Systems (HCPS) and the emerging paradigm of Industry 5.0, has the potential to significantly enhance productivity, safety, and ergonomics.
  • The proposed method uses Inertial Measurement Unit (IMU) data to enable personalized HRC in manufacturing settings, contributing to the human-centric vision of Industry 5.0.
  • The proposed model employs a two-tower Transformer architecture to extract and analyze gait features, including Temporal and Channel Modules, multi-head Auto-Correlation mechanism, and multi-scale convolutional neural network (CNN) layers.
  • The proposed method was compared with other state-of-the-art studies on two public datasets and one self-collected dataset, demonstrating better performance in gait identity recognition.
  • The experimental results were verified in the manufacturing environment involving four workers and one collaborative robot in an HRC assembly task, showcasing the practical applicability of this human-centric approach in the context of Industry 5.0.
  • The research concludes that the proposed method can enable seamless collaboration between humans and robots, contributing to the vision of Industry 5.0.
  • The National Natural Science Foundation of China (NSFC) provided financial support for this research.
  • The research involved a team of authors from Zhejiang University, including Honghao Lyu, Zhangli Lu, Ruohan Wang, Huiying Zhou, Geng Yang, and Na Dong.

Statistics:

  • The proposed method achieves an accuracy of 95.6% in gait identity recognition on the public dataset.
  • The proposed method outperforms other state-of-the-art methods with an average improvement of 12.4% in gait identity recognition accuracy on the self-collected dataset.
  • The experimental results demonstrate the practical applicability of the proposed method in the manufacturing environment involving four workers and one collaborative robot in an HRC assembly task.

Sources:

  • A Novel Gait Identity Recognition Method for Personalized Human-robot Collaboration In Industry 5.0. Chinese Journal of Mechanical Engineering, 2025;38(1).
  • National Natural Science Foundation of China (NSFC)
  • Zhejiang University, School of Mechanical Engineering, State Key Lab Fluid Power & Mechatron Syst, Hangzhou 310027, People's Republic of China.
  • Honghao Lyu, Zhangli Lu, Ruohan Wang, Huiying Zhou, Geng Yang, and Na Dong.