Trustworthy AI for human-centric smart manufacturing: A survey

Human-centric smart manufacturing (HCSM) envisions a symbiotic relationship between humans and machines, leveraging human capability and Artificial Intelligence (AI)’s precision and computational power to achieve mutual enhancement. Trustworthy AI (TAI) is a promising enabler in this transition, ensuring that the integration of AI technologies within manufacturing scenarios is safe, transparent, and participatory. This paper systematically reviews TAI within the context of HCSM by adopting a progressive 3-layer framework. This framework aligns with the developmental stages of HCSM and includes basic safety (protection), advancing to explainability, accountability, and uncertainty awareness (perception), and culminating in continuous updating with human involvement (participation). The review explores the role of TAI across key stages of the product lifecycle, demonstrating how TAI can empower humans and highlighting current advancements while identifying ongoing challenges. The paper concludes by discussing future directions and offering insights for developing TAI-integrated HCSM.