LLM-Drone: Aerial Additive Manufacturing with Drones Planned Using Large Language Models

2025-03-21

AI Summary

This work addresses the low precision and poor adaptability of aerial additive manufacturing (AAM) in constrained environments—such as high-altitude or remote locations. We propose the first unmanned aerial vehicle (UAV)-based closed-loop construction framework integrating large language models (LLMs). Methodologically, the LLM is embedded within a perception–planning–execution loop to enable semantic instruction interpretation, online semantic-geometric co-modeling, vision-based SLAM-assisted localization, dynamic path re-planning, and closed-loop extrusion control—achieving autonomous fault tolerance without handcrafted heuristic rules. The core contribution is the first integration of LLMs into AAM, enabling end-to-end text-driven construction. Experimental results demonstrate a 90% structural construction accuracy, significantly enhancing robustness, flexibility, and autonomy in complex operational scenarios.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Planning, Routing, and Scheduling: Planning with Language Models
• Humans and AI: Human-in-the-loop Machine Learning

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information

Abstract

Additive manufacturing (AM) has transformed the production landscape by enabling the precision creation of complex geometries. However, AM faces limitations when applied to challenging environments, such as elevated surfaces and remote locations. Aerial additive manufacturing, facilitated by drones, presents a solution to these challenges. However, despite advances in methods for the planning, control, and localization of drones, the accuracy of these methods is insufficient to run traditional feedforward extrusion-based additive manufacturing processes (such as Fused Deposition Manufacturing). Recently, the emergence of LLMs has revolutionized various fields by introducing advanced semantic reasoning and real-time planning capabilities. This paper proposes the integration of LLMs with aerial additive manufacturing to assist with the planning and execution of construction tasks, granting greater flexibility and enabling a feed-back based design and construction system. Using the semantic understanding and adaptability of LLMs, we can overcome the limitations of drone based systems by dynamically generating and adapting building plans on site, ensuring efficient and accurate construction even in constrained environments. Our system is able to design and build structures given only a semantic prompt and has shown success in understanding the spatial environment despite tight planning constraints. Our method's feedback system enables replanning using the LLM if the manufacturing process encounters unforeseen errors, without requiring complicated heuristics or evaluation functions. Combining the semantic planning with automatic error correction, our system achieved a 90% build accuracy, converting simple text prompts to build structures.

Problem

• Enabling precise aerial additive manufacturing in challenging environments
• Overcoming drone accuracy limitations for extrusion-based AM processes
• Dynamically adapting construction plans using LLM semantic reasoning

Innovation

• LLMs for aerial additive manufacturing planning
• Dynamic building plan generation and adaptation
• Feedback system for automatic error correction