This paper demonstrates how OpenAI's ChatGPT can be used in a few-shot setting to convert natural language instructions into an executable robot action sequence. The paper proposes easy-to-customize input prompts for ChatGPT that meet common requirements in practical applications, such as easy integration with robot execution systems and applicability to various environments. The prompts encourage ChatGPT to output a sequence of predefined robot actions, represent the operating environment in a formalized style, and infer the updated state of the operating environment. Experiments confirmed that the proposed prompts enable ChatGPT to act according to requirements in various environments, and users can modify ChatGPT's output using natural language for safe and robust operation. The proposed prompts and source code are open-source and publicly available at https://github.com/microsoft/ChatGPT-Robot-Manipulation-Prompts

翻译：本文展示了如何利用OpenAI的ChatGPT在少样本场景下将自然语言指令转换为可执行的机器人动作序列。论文提出了易于定制的ChatGPT输入提示方案，这些提示满足实际应用中的常见需求，例如与机器人执行系统的便捷集成以及对不同环境的适用性。该提示机制引导ChatGPT输出预定义的机器人动作序列，以形式化风格描述操作环境，并推断操作环境的更新状态。实验证实，所提出的提示方案能使ChatGPT在多种环境下按照要求执行动作，且用户可通过自然语言修改ChatGPT的输出，实现安全稳健的操作。相关提示方案及源代码已开源发布，详见https://github.com/microsoft/ChatGPT-Robot-Manipulation-Prompts