Answers are grounded in this paper and cite their sources.
Effective collaboration between humans and artificial intelligence (AI) in industry 5.0 demands technological systems with human social-cognitive processes, such as trust calibration and shared mental model. This study introduces human-centric decision-making framework for configuring human-AI collaboration in smart manufacturing systems. As Industry 5.0 evolves, finding the best synergy between human intelligence and collaborative robots (cobots) becomes crucial for enhancing adaptability, safety, efficiency, and sustainability. The proposed methodology uses neutrosophic Z-numbers (NZN) to capture uncertainty with three components: truth, indeterminacy, and falsity with their associated reliabilities, and the NZN weighted arithmetic averaging (NZNWAA) operator to combine individual preferences of decision-makers. Afterward, the criteria importance through intercriteria correlation (CRITIC) method is used to objectively determine the importance of each criterion by analyzing contrast intensity and inter-criteria correlation. The ranking of alternatives is then obtained using the compromise ranking of alternatives from distance to ideal solution (CRADIS) method. This hybrid NZN-CRITIC-CRADIS approach is applied to a real-world case study of BMW manufacturing systems, assessing four human-AI collaboration strategies: full AI automation, partial cobot integration, human-led AI-assisted assembly, and hybrid multi-agent collaboration, across four critical criteria. The results of the study show that the AI-assisted assembly emerges as the most suitable solution, balancing technological capability with human-centric design. The effectiveness of the proposed approach has been further validated through a sensitivity analysis and a comparative assessment with existing decision-making techniques, where our model consistently demonstrated superior performance in handling uncertainty and maintaining objectivity. Ultimately, this study offers a reliable human-centered framework that emphasizes socially intelligent manufacturing.
No takes yet. Share an insight, caveat, or question.
Abbas et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: