The Collaborative Kitting (CoKitting) approach in manufacturing combines human dexterity and robot repeatability to simplify assembly tasks, improving efficiency and safety. The proposed methodology aligns with the Industry 5.0 (I5.0) perspective, aiming at optimizing the collaborative task by proposing guidelines for both quantitative safety definition and reactive control algorithms. The first aspect is pursued by a review of the applicable norms and the development of advanced vision algorithms and AI-based strategies for the continuous human pose monitoring and behavioural models prediction with the objective of realising a real-time risk assessment. The second aspect anticipates interactions and minimises risks by introducing novel collision avoidance algorithms which re-plan in real time trajectories that avoid contact between the robot and any obstacles present in the work area, whether fixed or mobile, by considering the evaluated safety index.
Dynamic Safety Evaluation and Risk Mitigation Strategies for Collaborative Kitting / Lettera, G; Bajrami, A; Costa, D; Callegari, M. - ELETTRONICO. - 165:(2024), pp. 286-293. (Intervento presentato al convegno 9th European Conference on Mechanism Science, EuCoMeS 2024 tenutosi a Padua, Italy nel 18 - 20 September 2024) [10.1007/978-3-031-67295-8_32].
Dynamic Safety Evaluation and Risk Mitigation Strategies for Collaborative Kitting
Lettera, G
Primo
;Bajrami, ASecondo
;Costa, D;Callegari, M
Ultimo
2024-01-01
Abstract
The Collaborative Kitting (CoKitting) approach in manufacturing combines human dexterity and robot repeatability to simplify assembly tasks, improving efficiency and safety. The proposed methodology aligns with the Industry 5.0 (I5.0) perspective, aiming at optimizing the collaborative task by proposing guidelines for both quantitative safety definition and reactive control algorithms. The first aspect is pursued by a review of the applicable norms and the development of advanced vision algorithms and AI-based strategies for the continuous human pose monitoring and behavioural models prediction with the objective of realising a real-time risk assessment. The second aspect anticipates interactions and minimises risks by introducing novel collision avoidance algorithms which re-plan in real time trajectories that avoid contact between the robot and any obstacles present in the work area, whether fixed or mobile, by considering the evaluated safety index.File | Dimensione | Formato | |
---|---|---|---|
Dynamic_Safety_Evaluation_and_Risk_Mitigation_Strategies_for_Collaborative_Kitting___V1.pdf
embargo fino al 10/08/2025
Tipologia:
Documento in post-print (versione successiva alla peer review e accettata per la pubblicazione)
Licenza d'uso:
Tutti i diritti riservati
Dimensione
4.9 MB
Formato
Adobe PDF
|
4.9 MB | Adobe PDF | Visualizza/Apri Richiedi una copia |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.