This paper presents a novel approach to generating behavior trees for robots using lightweight large language models (LLMs) with a maximum of 7 billion parameters. The study demonstrates that it is possible to achieve satisfying results with compact LLMs when fine-tuned on a specific dataset. The key contributions of this research include the creation of a fine-tuning dataset based on existing behavior trees using GPT-3.5 and a comprehensive comparison of multiple LLMs (namely llama2, llama-chat, and code-llama) across nine distinct tasks. To be thorough, we evaluated the generated behavior trees using static syntactical analysis, a validation system, a simulated environment, and a real robot. Furthermore, this work opens the possibility of deploying such solutions directly on the robot, enhancing its practical applicability. Findings from this study demonstrate the potential of LLMs with a limited number of parameters in generating effective and efficient robot behaviors.

翻译：本文提出了一种新颖的机器人行为树生成方法，采用参数量上限为70亿的轻量级大语言模型。研究表明，当在特定数据集上进行微调后，紧凑型大语言模型也能获得令人满意的结果。本研究的关键贡献包括：基于现有行为树并利用GPT-3.5构建微调数据集，以及针对九类不同任务对多个大语言模型（包括llama2、llama-chat和code-llama）进行综合比较。为严谨起见，我们通过静态语法分析、验证系统、仿真环境及真实机器人对生成的行为树进行了评估。此外，本工作开启了将此类解决方案直接部署于机器人终端的可能性，从而增强其实用性。研究结果表明，参数规模有限的大语言模型在生成高效能机器人行为方面具有显著潜力。