Applying Ontologies and Knowledge Augmented Large Language Models to Industrial Automation: A Decision-Making Guidance for Achieving Human-Robot Collaboration in Industry 5.0

2025-05-24

AI Summary

Current AI technology selection—particularly large language models (LLMs), ontologies, and knowledge graphs—for Industry 5.0 human–machine collaboration and manufacturing resilience lacks systematic, lifecycle-aware decision criteria. Method: We propose the first multi-dimensional AI technology selection framework covering the entire industrial lifecycle, dynamically matching technical pathways to task complexity, cross-domain semantic requirements, and resource constraints. We further introduce a configurable Large Knowledge Language Model (LKLM) architecture that integrates ontology engineering, knowledge graph reasoning, and lightweight LLM inference to balance interpretability, task adaptability, and edge deployability. Results: Empirical evaluation demonstrates that LLMs significantly improve efficiency in flexible assembly instruction comprehension and collaborative anomaly resolution, while ontologies retain irreplaceable advantages in semantic reliability under low-compute production environments. The work delivers a practical, actionable AI technology selection roadmap for Industry 5.0.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Knowledge Representation and Reasoning: Ontologies
• Humans and AI: Learning Human Values and Preferences

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

The rapid advancement of Large Language Models (LLMs) has resulted in interest in their potential applications within manufacturing systems, particularly in the context of Industry 5.0. However, determining when to implement LLMs versus other Natural Language Processing (NLP) techniques, ontologies or knowledge graphs, remains an open question. This paper offers decision-making guidance for selecting the most suitable technique in various industrial contexts, emphasizing human-robot collaboration and resilience in manufacturing. We examine the origins and unique strengths of LLMs, ontologies, and knowledge graphs, assessing their effectiveness across different industrial scenarios based on the number of domains or disciplines required to bring a product from design to manufacture. Through this comparative framework, we explore specific use cases where LLMs could enhance robotics for human-robot collaboration, while underscoring the continued relevance of ontologies and knowledge graphs in low-dependency or resource-constrained sectors. Additionally, we address the practical challenges of deploying these technologies, such as computational cost and interpretability, providing a roadmap for manufacturers to navigate the evolving landscape of Language based AI tools in Industry 5.0. Our findings offer a foundation for informed decision-making, helping industry professionals optimize the use of Language Based models for sustainable, resilient, and human-centric manufacturing. We also propose a Large Knowledge Language Model architecture that offers the potential for transparency and configuration based on complexity of task and computing resources available.

Problem

• Guidance for choosing LLMs vs other NLP techniques in Industry 5.0
• Enhancing human-robot collaboration with ontologies and knowledge-augmented LLMs
• Addressing deployment challenges like computational cost and interpretability

Innovation

• Ontologies and knowledge augmented LLMs
• Decision-making guidance for Industry 5.0
• Large Knowledge Language Model architecture