用大模型替代机器人规划中的关键模块，发现其效率与成功率不如传统系统。
A Systematic Study of Large Language Models for Task and Motion Planning With PDDLStream
- 设计16种大模型集成方案，替换任务与运动规划中的核心组件
- 零样本测试中成功率低于工程化系统，规划耗时更长
- 直接调用大模型比推理型方案更快，几何信息反而增加错误
尽管已知大语言模型（LLMs）能解决部分规划问题，但其在机器人领域的实际能力仍不清晰。将大模型的语义知识与任务与运动规划（TAMP）的形式化推理结合是一条有前景的方向，但如何整合存在众多选择。我们构建了16种利用大模型替代TAMP关键组件的算法。在三个领域上进行的13750次零样本实验表明，基于大模型的规划器成功率较低、规划时间更长。提供几何细节反而比纯PDDL描述导致更多任务规划错误；（更快的）直接大模型变体在多数情况下优于（更慢的）推理型变体。代码与结果已公开于https://github.com/jorge-a-mendez/llm-pddlstream。
原文摘要 · Abstract (English)
While we know that large language models (LLMs) can solve some planning problems, we do not understand the extent of these capabilities for robotics. One promising direction is to integrate the semantic knowledge of LLMs with the formal reasoning of task and motion planning (TAMP). However, designing such systems is complicated by the myriad of choices for how to integrate LLMs within TAMP. We develop 16 algorithms that use LLMs to substitute key TAMP components. Our zero-shot experiments across 13750 evaluations and three domains reveal that LLM-based planners exhibit lower success rates and higher planning times than engineered systems. Providing geometric details increases the number of task-planning errors compared to pure PDDL descriptions, and (faster) direct LLM variants outperform (slower) reasoning variants in most cases. Code and results are available at https://github.com/jorge-a-mendez/llm-pddlstream.
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。