LLM-as-BT-Planner: Leveraging LLMs for Behavior Tree Generation in Robot Task Planning
Ao, Jicong Wu, Fan Wu, Yansong Swiki, Abdalla Haddadin, Sami
Ao, Jicong
Wu, Fan
Wu, Yansong
Swiki, Abdalla
Haddadin, Sami
Supervisor
Department
Robotics
Embargo End Date
Type
Conference proceeding
Date
2025
License
Language
English
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
Robotic assembly tasks remain an open challenge due to their long horizon nature and complex part relations. Behavior trees (BTs) are increasingly used in robot task planning for their modularity and flexibility, but creating them manually can be effort-intensive. Large language models (LLMs) have recently been applied to robotic task planning for generating action sequences, yet their ability to generate BTs has not been fully investigated. To this end, we propose LLM-as-BT-Planner, a novel framework that leverages LLMs for BT generation in robotic assembly task planning. Four in-context learning methods are introduced to utilize the natural language processing and inference capabilities of LLMs for producing task plans in BT format, reducing manual effort while ensuring robustness and comprehensibility. Additionally, we evaluate the performance of fine-tuned smaller LLMs on the same tasks. Experiments in both simulated and real-world settings demonstrate that our framework enhances LLMs' ability to generate BTs, improving success rate through in-context learning and supervised fine-tuning.
Citation
J. Ao, F. Wu, Y. Wu, A. Swiki and S. Haddadin, "LLM-as-BT-Planner: Leveraging LLMs for Behavior Tree Generation in Robot Task Planning," 2025 IEEE International Conference on Robotics and Automation (ICRA), Atlanta, GA, USA, 2025, pp. 1233-1239, doi: 10.1109/ICRA55743.2025.11128454.
Source
International Conference on Robotics and Automation (ICRA)
Conference
2025 IEEE International Conference on Robotics and Automation (ICRA)
Keywords
Robotic Assembly, Learning Systems, Large Language Models, Training Data, Manuals, Robustness, Natural Language Processing, Human in the Loop, Planning, Robots
Subjects
Source
2025 IEEE International Conference on Robotics and Automation (ICRA)
Publisher
IEEE