用大模型自动生成多台施工机械协同行为树，提升自动化效率。
Coordinated Control of Multiple Construction Machines Using LLM-Generated Behavior Trees with Flag-Based Synchronization
- 通过大模型生成行为树，并用全局黑板同步状态标志实现多机协调。
- 30个场景仿真中多机协同任务成功率达93%。
- 适合想减少人工设计复杂逻辑的施工自动化研究者。
土方作业需求持续增长，而劳动力老龄化促使自动化迫切发展。已有面向施工机械自动化的ROS2-TMS框架依赖人工设计的行为树（BTs），在多机协作中难以扩展。大型语言模型（LLMs）为自动任务规划带来新可能，但现有研究多局限于简单机器人系统。本文提出基于LLM的流程，实现施工机械协同操作的行为树自动生成。方法引入由全局黑板管理的同步标志，使多个行为树可共享执行状态并表达机器间依赖关系。流程包括使用LLM生成动作序列和行为树两步。在30个施工指令场景的仿真中，多机协同任务最高成功率达93%。真实世界实验使用挖掘机与自卸卡车也成功完成协作任务，表明该方法可显著降低人工设计行为树的工作量。结果验证了大模型驱动的任务规划在实际土方自动化中的可行性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。