Abstract
Rapid advances in digital twin (DT) provide an unprecedented opportunity to derive data-enabled intelligence for smart manufacturing. However, traditional DT is more concerned about real-time data streaming, dashboard visualization, and predictive analytics, but focuses less on multiagent intelligence. This limitation hampers the development of agentic intelligence for decentralized decision-making in complex manufacturing environments. Therefore, this article presents a cognitive digital twin (CDT) approach for multiobjective production scheduling through decentralized, collaborative multiagent learning. First, we propose to construct models of heterogeneous agents (e.g., machines, jobs, automated guided vehicles, and automated storage and retrieval systems) that interact with physical and digital twins. Second, multiobjective optimization is embedded in CDT to align production schedules with diverse and often conflicting objectives such as throughput, task transition efficiency, and workload balance. Third, we develop a multiagent learning approach to enable decentralized decision-making in response to unexpected disruptions and dynamic demands. Each agent operates independently and collaboratively with cognitive capabilities, including perception, learning, and reasoning, to optimize the individual agentic objective while contributing to overarching system-wide goals. Finally, the proposed CDT is evaluated and validated with experimental studies in a learning factory environment. Experimental results demonstrate that CDT improves operational performance in terms of task allocation, resource utilization, and system resilience compared to traditional centralized approaches. This initial study of CDT highlights the potential to bring multiagent cognitive intelligence into next-generation smart manufacturing.
