用大模型自动生成机器人装配任务的行为树，省去人工设计。
LLM-as-BT-Planner: Leveraging LLMs for Behavior Tree Generation in Robot Task Planning
- 用大模型的自然语言理解能力生成行为树，无需手动编写。
- 在仿真和真实场景中，成功率显著提升，小模型经微调后效果更好。
- 适合想快速构建可解释机器人任务规划的开发者或研究者。
机器人装配任务因周期长、部件关系复杂而难以实现。行为树（BT）因其模块化和灵活性，日益用于机器人任务规划，但手动构建耗时费力。大语言模型（LLMs）虽已用于生成动作序列，但其生成行为树的能力尚未充分探索。为此，我们提出 LLM-as-BT-Planner 框架，利用大模型生成机器人装配任务的行为树。引入四种上下文学习方法，借助大模型的语言处理与推理能力，以自然语言生成结构化的行为树，降低人工成本，同时保证规划结果的鲁棒性与可读性。此外，我们还评估了微调后的较小模型在相同任务上的表现。在仿真和真实场景中的实验表明，该框架通过上下文学习与监督微调，显著提升了大模型生成行为树的能力，有效提高了任务成功率。
原文摘要 · Abstract (English)
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.
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。