Coordinated Control of Multiple Construction Machines Using LLM-Generated Behavior Trees with Flag-Based Synchronization

TL;DR

This paper introduces an LLM-based method for automatically generating Behavior Trees with flag-based synchronization to coordinate multiple construction machines, improving scalability and reducing manual design effort.

Contribution

It presents a novel workflow using LLMs to generate synchronized Behavior Trees with a global blackboard for multi-machine construction automation.

Findings

Achieved up to 93% success rate in simulation scenarios

Demonstrated successful real-world cooperation between excavator and dump truck

Showed potential to reduce manual Behavior Tree design in construction automation

Abstract

Earthwork operations face increasing demand, while workforce aging creates a growing need for automation. ROS2-TMS for Construction, a Cyber-Physical System framework for construction machinery automation, has been proposed; however, its reliance on manually designed Behavior Trees (BTs) limits scalability in cooperative operations. Recent advances in Large Language Models (LLMs) offer new opportunities for automated task planning, yet most existing studies remain limited to simple robotic systems. This paper proposes an LLM-based workflow for automatic generation of BTs toward coordinated operation of construction machines. The method introduces synchronization flags managed through a Global Blackboard, enabling multiple BTs to share execution states and represent inter-machine dependencies. The workflow consists of Action Sequence generation and BTs generation using LLMs. Simulation experiments on 30 construction instruction scenarios achieved up to 93\% success rate in coordinated multi-machine tasks. Real-world experiments using an excavator and a dump truck further demonstrate successful cooperative execution, indicating the potential to reduce manual BTs design effort in construction automation. These results highlight the feasibility of applying LLM-driven task planning to practical earthwork automation.