用大模型把自然语言中的约束自动转为可执行规划代码
CaStL: Constraints as Specifications through LLM Translation for Long-Horizon Task and Motion Planning
- 分阶段提取自然语言中的目标、动作顺序、互斥等约束
- 在三个PDDL领域中提升复杂场景下的规划成功率
- 适合需要从口语描述生成机器人任务计划的研究者
大语言模型（LLMs）在长时序任务与运动规划（TAMP）中表现出色，能将清晰的自然语言问题转化为形式化规范，如规划领域定义语言（PDDL）。然而，现实问题往往模糊且包含多种复杂约束。本文提出约束即规范通过大模型翻译（CaStL）框架，分多阶段从自然语言中识别目标条件、动作顺序和动作阻塞等约束，并将其转换为PDDL与Python脚本，由定制化的PDDL求解器求解。在三个PDDL领域上的测试表明，该方法显著提升了复杂场景下基于自然语言规范的约束处理能力与规划成功率。
原文摘要 · Abstract (English)
Large Language Models (LLMs) have demonstrated remarkable ability in long-horizon Task and Motion Planning (TAMP) by translating clear and straightforward natural language problems into formal specifications such as the Planning Domain Definition Language (PDDL). However, real-world problems are often ambiguous and involve many complex constraints. In this paper, we introduce Constraints as Specifications through LLMs (CaStL), a framework that identifies constraints such as goal conditions, action ordering, and action blocking from natural language in multiple stages. CaStL translates these constraints into PDDL and Python scripts, which are solved using an custom PDDL solver. Tested across three PDDL domains, CaStL significantly improves constraint handling and planning success rates from natural language specification in complex scenarios.
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。