Towards a Reference Software Architecture for Human-AI Teaming in Smart Manufacturing

TL;DR

This paper proposes a reference software architecture for human-AI teaming in smart manufacturing, focusing on knowledge graphs, scene analysis, and relational machine learning to enhance context-aware support and ethical validation.

Contribution

It introduces a novel reference architecture leveraging knowledge graphs and relational machine learning tailored for scalable, context-specific human-AI collaboration in manufacturing.

Findings

Identified key challenges in human-AI teaming for manufacturing.

Developed a preliminary reference architecture based on knowledge graphs.

Plans for empirical validation with industry partners.

Abstract

With the proliferation of AI-enabled software systems in smart manufacturing, the role of such systems moves away from a reactive to a proactive role that provides context-specific support to manufacturing operators. In the frame of the EU funded Teaming.AI project, we identified the monitoring of teaming aspects in human-AI collaboration, the runtime monitoring and validation of ethical policies, and the support for experimentation with data and machine learning algorithms as the most relevant challenges for human-AI teaming in smart manufacturing. Based on these challenges, we developed a reference software architecture based on knowledge graphs, tracking and scene analysis, and components for relational machine learning with a particular focus on its scalability. Our approach uses knowledge graphs to capture product- and process specific knowledge in the manufacturing process and to utilize it for relational machine learning. This allows for context-specific recommendations for actions in the manufacturing process for the optimization of product quality and the prevention of physical harm. The empirical validation of this software architecture will be conducted in cooperation with three large-scale companies in the automotive, energy systems, and precision machining domain. In this paper we discuss the identified challenges for such a reference software architecture, present its preliminary status, and sketch our further research vision in this project.