Coordinated Control of Multiple Construction Machines Using LLM-Generated Behavior Trees with Flag-Based Synchronization
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866908859902197760 |
|---|---|
| author | Tsutsumi, Akinosuke Itsuka, Tomoya Kasahara, Yuichiro Kouno, Tomoya Akinari, Kota Yamauchi, Genki Endo, Daisuke Abe, Taro Hashimoto, Takeshi Nagatani, Keiji Kurazume, Ryo |
| author_facet | Tsutsumi, Akinosuke Itsuka, Tomoya Kasahara, Yuichiro Kouno, Tomoya Akinari, Kota Yamauchi, Genki Endo, Daisuke Abe, Taro Hashimoto, Takeshi Nagatani, Keiji Kurazume, Ryo |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_01041 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Coordinated Control of Multiple Construction Machines Using LLM-Generated Behavior Trees with Flag-Based Synchronization Tsutsumi, Akinosuke Itsuka, Tomoya Kasahara, Yuichiro Kouno, Tomoya Akinari, Kota Yamauchi, Genki Endo, Daisuke Abe, Taro Hashimoto, Takeshi Nagatani, Keiji Kurazume, Ryo Robotics 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. |
| title | Coordinated Control of Multiple Construction Machines Using LLM-Generated Behavior Trees with Flag-Based Synchronization |
| topic | Robotics |
| url | https://arxiv.org/abs/2602.01041 |