This paper presents an in-depth study on human-robot teaming (HRT), focusing on state-of-the-art methodologies and real-world implementation of a collaborative robotic system designed for industrial assembly tasks. The research explores the integration of artificial intelligence-driven perception to enhance human-robot collaboration, improving efficiency and adaptability in dynamic work environments. A key aspect of this study is the real-time recognition of human actions using deep learning techniques, in particular Long Short-Term Memory (LSTM) networks, which allow the system to accurately interpret the operator’s movements and intentions. This capability is combined with object detection based on the YOLO (You Only Look Once) method, which ensures fast and accurate identification of relevant components and tools within the work area. Leveraging these artificial intelligence-based technologies, the collaborative system allows a UR5 robot to support the operator based on detected actions, thus simplifying industrial workflows. The developed system supports critical tasks such as tool changing and component positioning, reducing operator workload and increasing overall process efficiency. The intelligent perception framework ensures seamless interaction between human workers and robotic agents, minimising the risk of errors and delays in production lines. Experimental evaluations conducted in a real-world environment demonstrate the feasibility and effectiveness of the proposed approach, achieving high classification accuracy in action recognition and reliable object detection. The results highlight the potential of collaborative robotics powered by artificial intelligence to transform industrial production by optimising task execution and improving workplace ergonomics.

HUMAN-ROBOT TEAMING FOR ASSEMBLY TASKS / Neri, F., Palmieri, G., Palpacelli, M.C., Callegari, M.. - 5:(2025). (ASME 2025 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference, IDETC-CIE 2025 Hilton Anaheim, usa 2025) [10.1115/DETC2025-168752].

HUMAN-ROBOT TEAMING FOR ASSEMBLY TASKS

Neri F.
Primo
;
Palmieri G.
Secondo
;
Palpacelli M. C.
Penultimo
;
Callegari M.
Ultimo
2025-01-01

Abstract

This paper presents an in-depth study on human-robot teaming (HRT), focusing on state-of-the-art methodologies and real-world implementation of a collaborative robotic system designed for industrial assembly tasks. The research explores the integration of artificial intelligence-driven perception to enhance human-robot collaboration, improving efficiency and adaptability in dynamic work environments. A key aspect of this study is the real-time recognition of human actions using deep learning techniques, in particular Long Short-Term Memory (LSTM) networks, which allow the system to accurately interpret the operator’s movements and intentions. This capability is combined with object detection based on the YOLO (You Only Look Once) method, which ensures fast and accurate identification of relevant components and tools within the work area. Leveraging these artificial intelligence-based technologies, the collaborative system allows a UR5 robot to support the operator based on detected actions, thus simplifying industrial workflows. The developed system supports critical tasks such as tool changing and component positioning, reducing operator workload and increasing overall process efficiency. The intelligent perception framework ensures seamless interaction between human workers and robotic agents, minimising the risk of errors and delays in production lines. Experimental evaluations conducted in a real-world environment demonstrate the feasibility and effectiveness of the proposed approach, achieving high classification accuracy in action recognition and reliable object detection. The results highlight the potential of collaborative robotics powered by artificial intelligence to transform industrial production by optimising task execution and improving workplace ergonomics.
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11566/367232
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact