Agentic AI autonomously configures smart digital twins in manufacturing
Agentic AI-enabled Semantic Commissioning of a Cognitive Digital Twin for Reconfigurable Manufacturing
RoboticsMultiagent Systems
Summary
Setting up digital twins—virtual copies of machines—for manufacturing is usually slow and manual. The authors developed an AI system that reads technical documents and connects live machine data automatically to create smart digital twins faster. Tested on a robotic machining cell, their method cut setup time from weeks to just a couple of hours with high accuracy. This approach lets factories adjust machines more quickly without needing experts to write lots of custom code.
What this means in practice
- •For manufacturing automation teams: Automatically deploy and debug digital twins to speed up machine reconfiguration processes in smart factories.
- •For industrial robotics engineers: Enable autonomous linking of real-time sensor data with machine specifications for efficient robotic cell monitoring and control.
Authors
Yangyang Liu, Xun Xu, Jan Polzer
Abstract
Rapid bespoke commissioning of the Cognitive Digital Twin (CDT) is a major challenge in reconfigurable manufacturing. Traditional digital twin (DT) construction methods primarily focus on geometric reconstruction, often neglecting the deep semantic integration and functional interoperability necessary for autonomous reasoning. This paper proposes an agent-based, AI-driven workflow to automate end-to-end CDT debugging. The system utilises LangGraph as a multi-agent orchestration engine to achieve dual-path synthesis: the semantic path extracts technical specifications from unstructured documents using Retrieval Augmented Generation (RAG), while the functional path autonomously discovers and binds to real-time industrial telemetry data using Model Context Protocol (MCP). Experimental validation in a robotic machining cell demonstrates that the system achieves a mean average accuracy (mAP) of 97.2% in perception and reduces the deployment cycle from several weeks to an average of 2 hours, marking a paradigm shift from manual scripting to autonomous orchestration.