This work presents a comprehensive framework for smart automotive manufacturing through the integration of artificial intelligence (AI), Industrial Internet of Things (IIoT), collaborative robotics (cobots), and 3D digital production simulation. The study introduces agentic AI-driven, self-healing production systems capable of real-time monitoring, predictive decision-making, and autonomous corrective actions. By leveraging distributed IoT sensor networks, machine learning-based analytics, and digital twin environments, the proposed architecture enables early fault detection, adaptive process control, and continuous system optimization.

A practical implementation demonstrates the effectiveness of an IoT-enabled monitoring system in a high-volume manufacturing environment, achieving significant improvements including substantial reductions in unplanned downtime and scrap rates, alongside notable increases in overall equipment effectiveness (OEE), throughput, and process stability. The integration of AI-guided cobots further enhances precision, reduces operator workload, and improves operational efficiency, while 3D simulation tools enable risk-free validation and optimization of production systems.

The findings highlight the transition from traditional Industry 4.0 automation toward Industry 5.0 paradigms, emphasizing human–machine collaboration, resilience, and sustainability. This research demonstrates how intelligent, data-driven manufacturing ecosystems can significantly enhance production efficiency, quality performance, and system reliability, providing a scalable pathway toward next-generation autonomous and self-optimizing manufacturing systems.