Industry 6.0: New Generation of Industry driven by Generative AI and Swarm of Heterogeneous Robots

TL;DR

The paper proposes Industry 6.0, a fully autonomous production paradigm driven by generative AI and a swarm of heterogeneous robots that execute product design and manufacturing from natural language input. It presents a four-stage architecture—blueprint generation, part production, logistics via a flying conveyor, and autonomous assembly—integrating SDF-based CAD generation, 3D printing, drone transport, and LangGraph-enabled robot coordination. Empirical results show strong performance of top LLMs in blueprinting and code generation, and a user study reports substantial speedups over expert human teams (119.10 minutes vs 528.64 minutes, a 4.4x improvement) with dramatic gains in the design phase (0.50 minutes vs 23.5 minutes). The work demonstrates a significant step toward fully autonomous manufacturing, with potential paths toward on-demand personalized production and market-aware autonomous optimization.

Abstract

This paper presents the concept of Industry 6.0, introducing the world's first fully automated production system that autonomously handles the entire product design and manufacturing process based on user-provided natural language descriptions. By leveraging generative AI, the system automates critical aspects of production, including product blueprint design, component manufacturing, logistics, and assembly. A heterogeneous swarm of robots, each equipped with individual AI through integration with Large Language Models (LLMs), orchestrates the production process. The robotic system includes manipulator arms, delivery drones, and 3D printers capable of generating assembly blueprints. The system was evaluated using commercial and open-source LLMs, functioning through APIs and local deployment. A user study demonstrated that the system reduces the average production time to 119.10 minutes, significantly outperforming a team of expert human developers, who averaged 528.64 minutes (an improvement factor of 4.4). Furthermore, in the product blueprinting stage, the system surpassed human CAD operators by an unprecedented factor of 47, completing the task in 0.5 minutes compared to 23.5 minutes. This breakthrough represents a major leap towards fully autonomous manufacturing.

Figures (6)

• Figure 1: Implementation of Industry 6.0 concept.
• Figure 2: Industry 6.0 architecture, including stages of code generating, printing, delivering, and assembling required parts performed in the human-out-of-the-loop model.
• Figure 3: CAD model design by generative AI.
• Figure 4: Transfer of the 3D printing surface from the printer to the drone. In (a), the Universal Robot UR10 grasps the printing surface, takes it out from the 3D printer (b), transfers (c), and places it on the drone (d).
• Figure 5: LangGraph-inspired assembly pipeline of the parts delivered by drones.