In robotics, the use of Large Language Models (LLMs) is becoming prevalent, especially for understanding human commands. In particular, LLMs are utilized as domain-agnostic task planners for high-level human commands. LLMs are capable of Chain-of-Thought (CoT) reasoning, and this allows LLMs to be task planners. However, we need to consider that modern robots still struggle to perform complex actions, and the domains where robots can be deployed are limited in practice. This leads us to pose a question: If small LMs can be trained to reason in chains within a single domain, would even small LMs be good task planners for the robots? To train smaller LMs to reason in chains, we build `COmmand-STeps datasets' (COST) consisting of high-level commands along with corresponding actionable low-level steps, via LLMs. We release not only our datasets but also the prompt templates used to generate them, to allow anyone to build datasets for their domain. We compare GPT3.5 and GPT4 with the finetuned GPT2 for task domains, in tabletop and kitchen environments, and the result shows that GPT2-medium is comparable to GPT3.5 for task planning in a specific domain. Our dataset, code, and more output samples can be found in https://github.com/Gawon-Choi/small-LMs-Task-Planning

翻译：在机器人学中，大型语言模型（LLMs）的应用日益广泛，尤其体现在理解人类指令方面。具体而言，LLMs 被用作处理高层级人类指令的跨领域任务规划器。LLMs 具备思维链（Chain-of-Thought, CoT）推理能力，这使其能够胜任任务规划任务。然而，我们需要认识到，现代机器人执行复杂动作仍存在困难，且机器人的实际部署领域也较为有限。这引出一个问题：如果小型语言模型（LMs）能在单一领域内通过训练实现链式推理，那么即使是小型LMs，是否能成为优秀的机器人任务规划器？为训练小型LMs进行链式推理，我们通过LLMs构建了由高层指令及其对应可执行低层步骤组成的“COmmand-STeps数据集”（COST）。我们不仅发布了数据集，还提供了用于生成数据的提示模板，以便用户为其特定领域构建数据集。我们在桌面环境和厨房环境中，对比了GPT3.5、GPT4与微调后的GPT2在任务规划上的表现。结果表明，在特定领域内，GPT2-medium 的任务规划能力可与GPT3.5相媲美。我们的数据集、代码及更多输出样例可在 https://github.com/Gawon-Choi/small-LMs-Task-Planning 获取。