用代码生成让大模型输出语法正确的时序逻辑，指挥机器人按自然语言导航
LTLCodeGen: Code Generation of Syntactically Correct Temporal Logic for Robot Task Planning
- 用代码生成技术确保大模型输出的时序逻辑语法正确
- 在真实场景中通过语音指令完成机器人路径规划，成功率高
- 适合需要精确语义理解的机器人任务规划研究者
本文聚焦于从自然语言指令中规划机器人导航任务。我们提出一种模块化方法：利用大语言模型（LLM）将自然语言指令转化为线性时序逻辑（LTL）公式，其中命题由语义占据图中的物体类别定义。将LTL公式与语义占据图输入运动规划算法，生成满足指令的无碰撞路径。核心贡献是LTLCodeGen，一种通过代码生成实现自然语言到语法正确LTL的转换方法。我们在真实世界实验中验证了完整任务规划流程，人类语音指令驱动移动机器人导航。同时在仿真和真实环境中全面评估该方法，对比了端到端LLM任务规划及当前最先进的LLM-to-LTL翻译方法。
原文摘要 · Abstract (English)
This paper focuses on planning robot navigation tasks from natural language specifications. We develop a modular approach, where a large language model (LLM) translates the natural language instructions into a linear temporal logic (LTL) formula with propositions defined by object classes in a semantic occupancy map. The LTL formula and the semantic occupancy map are provided to a motion planning algorithm to generate a collision-free robot path that satisfies the natural language instructions. Our main contribution is LTLCodeGen, a method to translate natural language to syntactically correct LTL using code generation. We demonstrate the complete task planning method in real-world experiments involving human speech to provide navigation instructions to a mobile robot. We also thoroughly evaluate our approach in simulated and real-world experiments in comparison to end-to-end LLM task planning and state-of-the-art LLM-to-LTL translation methods.
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。