A Temporal Planning Framework for Multi-Agent Systems via LLM-Aided Knowledge Base Management
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910845998465024 |
|---|---|
| author | Saccon, Enrico Tikna, Ahmet De Martini, Davide Lamon, Edoardo Palopoli, Luigi Roveri, Marco |
| author_facet | Saccon, Enrico Tikna, Ahmet De Martini, Davide Lamon, Edoardo Palopoli, Luigi Roveri, Marco |
| contents | This paper presents a novel framework, called PLANTOR (PLanning with Natural language for Task-Oriented Robots), that integrates Large Language Models (LLMs) with Prolog-based knowledge management and planning for multi-robot tasks. The system employs a two-phase generation of a robot-oriented knowledge base, ensuring reusability and compositional reasoning, as well as a three-step planning procedure that handles temporal dependencies, resource constraints, and parallel task execution via mixed-integer linear programming. The final plan is converted into a Behaviour Tree for direct use in ROS2. We tested the framework in multi-robot assembly tasks within a block world and an arch-building scenario. Results demonstrate that LLMs can produce accurate knowledge bases with modest human feedback, while Prolog guarantees formal correctness and explainability. This approach underscores the potential of LLM integration for advanced robotics tasks requiring flexible, scalable, and human-understandable planning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_19135 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Temporal Planning Framework for Multi-Agent Systems via LLM-Aided Knowledge Base Management Saccon, Enrico Tikna, Ahmet De Martini, Davide Lamon, Edoardo Palopoli, Luigi Roveri, Marco Artificial Intelligence Human-Computer Interaction Robotics This paper presents a novel framework, called PLANTOR (PLanning with Natural language for Task-Oriented Robots), that integrates Large Language Models (LLMs) with Prolog-based knowledge management and planning for multi-robot tasks. The system employs a two-phase generation of a robot-oriented knowledge base, ensuring reusability and compositional reasoning, as well as a three-step planning procedure that handles temporal dependencies, resource constraints, and parallel task execution via mixed-integer linear programming. The final plan is converted into a Behaviour Tree for direct use in ROS2. We tested the framework in multi-robot assembly tasks within a block world and an arch-building scenario. Results demonstrate that LLMs can produce accurate knowledge bases with modest human feedback, while Prolog guarantees formal correctness and explainability. This approach underscores the potential of LLM integration for advanced robotics tasks requiring flexible, scalable, and human-understandable planning. |
| title | A Temporal Planning Framework for Multi-Agent Systems via LLM-Aided Knowledge Base Management |
| topic | Artificial Intelligence Human-Computer Interaction Robotics |
| url | https://arxiv.org/abs/2502.19135 |