KG-MAS: Knowledge Graph-Enhanced Multi-Agent Infrastructure for coupling physical and digital robotic environments

TL;DR

This work tackles the challenge of coupling heterogeneous physical and digital robotic environments in Cyber-Physical Systems for Industry 4.0. It proposes KG-MAS, a knowledge graph–driven, multi-agent infrastructure in which a centralized KG acts as a dynamic world model that agents query and update, enabling semantic, autonomous coordination. A model-driven workflow automatically generates agents from semantic descriptions and aligns them through a RAMI 4.0–inspired layered KG, validated in a warehouse scenario with a simulated RX150 arm and a Turtlebot. The study demonstrates scalable, adaptable integration that abstracts transport-layer specifics, supports real-time state management, and sets a path for future enhancements like formal coordination protocols and collision-aware KG representations.

Abstract

The seamless integration of physical and digital environments in Cyber-Physical Systems(CPS), particularly within Industry 4.0, presents significant challenges stemming from system heterogeneity and complexity. Traditional approaches often rely on rigid, data-centric solutions like co-simulation frameworks or brittle point-to-point middleware bridges, which lack the semantic richness and flexibility required for intelligent, autonomous coordination. This report introduces the Knowledge Graph-Enhanced Multi-Agent Infrastructure(KG-MAS), as resolution in addressing such limitations. KG-MAS leverages a centralized Knowledge Graph (KG) as a dynamic, shared world model, providing a common semantic foundation for a Multi-Agent System(MAS). Autonomous agents, representing both physical and digital components, query this KG for decision-making and update it with real-time state information. The infrastructure features a model-driven architecture which facilitates the automatic generation of agents from semantic descriptions, thereby simplifying system extension and maintenance. By abstracting away underlying communication protocols and providing a unified, intelligent coordination mechanism, KG-MAS offers a robust, scalable, and flexible solution for coupling heterogeneous physical and digital robotic environments.

Figures (6)

• Figure 1: Modularized Knowledge Graph in Smart Manufacturing
• Figure 2: The Architecture of the proposed infrastructure
• Figure 3: Revised layered approach of the RAMI 4.0
• Figure 4: Agent generation process
• Figure 5: Motivating Scenario