A Multimodal Manufacturing Safety Chatbot: Knowledge Base Design, Benchmark Development, and Evaluation of Multiple RAG Approaches

TL;DR

This paper presents a multimodal safety chatbot for manufacturing, grounded in regulatory data, evaluated with a new benchmark, and systematically optimized for accuracy, latency, and cost in Industry 5.0 settings.

Contribution

It introduces an open-source safety chatbot, a validated benchmark for AI safety instruction, and a methodology for designing and evaluating AI safety training systems.

Findings

Top configuration achieved 86.66% accuracy

Latency of 10.04 seconds for safety instructions

Cost of $0.005 per query

Abstract

Ensuring worker safety remains a critical challenge in modern manufacturing environments. Industry 5.0 reorients the prevailing manufacturing paradigm toward more human-centric operations. Using a design science research methodology, we identify three essential requirements for next-generation safety training systems: high accuracy, low latency, and low cost. We introduce a multimodal chatbot powered by large language models that meets these design requirements. The chatbot uses retrieval-augmented generation to ground its responses in curated regulatory and technical documentation. To evaluate our solution, we developed a domain-specific benchmark of expert-validated question and answer pairs for three representative machines: a Bridgeport manual mill, a Haas TL-1 CNC lathe, and a Universal Robots UR5e collaborative robot. We tested 24 RAG configurations using a full-factorial design and assessed them with automated evaluations of correctness, latency, and cost. Our top 2 configurations were then evaluated by ten industry experts and academic researchers. Our results show that retrieval strategy and model configuration have a significant impact on performance. The top configuration, selected for chatbot deployment, achieved an accuracy of 86.66%, an average cost of $0.005 per query, and an average end-to-end latency of 10.04 seconds. This latency is practical for delivering a complete safety instruction and is measured from query submission to full instruction delivery rather than generation onset. Overall, our work provides three contributions: an open-source, domain-grounded safety training chatbot; a validated benchmark for evaluating AI-assisted safety instruction; and a systematic methodology for designing and assessing AI-enabled instructional and immersive safety training systems for Industry 5.0 environments.