Multi-robot collaborative manufacturing driven by digital twins: Advancements, challenges, and future directions

Multi-robot systems envisioned for future factories will promote advancements and capabilities of handling complex tasks and realising optimal robotic operations. However, existing multi-robot systems face challenges such as integration complexity, difficult coordination and control, low scalability, and flexibility, and thus are far from realising adaptive and efficient multi-robot collaborative manufacturing (MRCM). Digital twin technology improves visualisation, consistency, and spatial-temporal collaboration in MRCM through real-time interaction and iterative optimisation in physical and virtual spaces. Despite these improvements, barriers such as undeveloped modelling capabilities, indeterminate collaborative strategies, and limited applicability impede widespread integration of MRCM. In response to these needs, this study provides a comprehensive review of the foundational concepts, systematic architecture, and enabling technologies of digital twin-driven MRCM, serving as a prospective vision for future work in collaborative intelligent manufacturing. With the development of sensors and computational capabilities, robot intelligence is evolving towards multi-robot collaboration, including perceptual, cognitive, and behavioural collaboration. Digital twins play a critical supporting role in multi-robot collaboration, and the architecture, methodologies, and applications are elaborated across diverse stages of MRCM processes. This paper also identifies current challenges and future research directions. It encourages academic and industrial stakeholders to integrate state-of-the-art AI technologies more thoroughly into multi-robot digital twin systems for enhanced efficiency and reliability in production.