Generative manufacturing systems using diffusion models and ChatGPT

2024-05-02

arXiv.org

AI Summary

To address the slow decision-making speed, limited flexibility, and weak human–machine collaboration in manufacturing systems, this paper proposes a Generative Manufacturing System (GMS) that introduces a novel “training–sampling” decision paradigm. Departing from conventional explicit modeling, GMS constructs an implicit representation of the “anticipated future” by jointly leveraging diffusion models and ChatGPT, enabling interactive, iterative, and globally coordinated human–machine decision-making. Decisions are triggered and refined through natural-language human–machine dialogue, supporting generative, diverse, and feedback-driven co-creation. Experimental results demonstrate that GMS reduces decision latency from seconds to milliseconds, significantly improves solution quality, diversity, and alignment with human preferences, and substantially enhances system resilience and adaptability to uncertainty.

Technology Category

• Humans and AI: Planning and Decision Support for Human-Machine Teams
• Natural Language Processing: Generation
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

In this study, we introduce Generative Manufacturing Systems (GMS) as a novel approach to effectively manage and coordinate autonomous manufacturing assets, thereby enhancing their responsiveness and flexibility to address a wide array of production objectives and human preferences. Deviating from traditional explicit modeling, GMS employs generative AI, including diffusion models and ChatGPT, for implicit learning from envisioned futures, marking a shift from a model-optimum to a training-sampling decision-making. Through the integration of generative AI, GMS enables complex decision-making through interactive dialogue with humans, allowing manufacturing assets to generate multiple high-quality global decisions that can be iteratively refined based on human feedback. Empirical findings showcase GMS's substantial improvement in system resilience and responsiveness to uncertainties, with decision times reduced from seconds to milliseconds. The study underscores the inherent creativity and diversity in the generated solutions, facilitating human-centric decision-making through seamless and continuous human-machine interactions.

Problem

• Manufacturing Systems
• Decision Speed
• Human-Robot Collaboration

Innovation

• Generative Manufacturing System (GMS)
• Artificial Intelligence (AI) Integration
• Human-Machine Collaborative Decision-Making