Large language models (LLMs) pre-trained on vast internet-scale data have showcased remarkable capabilities across diverse domains. Recently, there has been escalating interest in deploying LLMs for robotics, aiming to harness the power of foundation models in real-world settings. However, this approach faces significant challenges, particularly in grounding these models in the physical world and in generating dynamic robot motions. To address these issues, we introduce a novel paradigm in which we use few-shot prompts collected from the physical environment, enabling the LLM to autoregressively generate low-level control commands for robots without task-specific fine-tuning. Experiments across various robots and environments validate that our method can effectively prompt a robot to walk. We thus illustrate how LLMs can proficiently function as low-level feedback controllers for dynamic motion control even in high-dimensional robotic systems. The project website and source code can be found at: https://prompt2walk.github.io/ .

翻译：大型语言模型（LLMs）在海量互联网规模数据上预训练后，已在不同领域展现出卓越能力。近年来，将LLMs应用于机器人领域的研究兴趣日益增长，旨在利用基础模型在现实世界中的强大功能。然而，这种方法面临重大挑战，尤其是在物理世界中落地这些模型以及生成动态机器人运动方面。为解决这些问题，我们提出了一种新范式，利用从物理环境中采集的少样本提示，使LLMs能够无需任务特定微调即可自回归生成机器人的低级控制指令。在多种机器人和环境中的实验验证了我们的方法可有效提示机器人行走。我们由此证明，即使在高维机器人系统中，LLMs也能作为动态运动控制的低级反馈控制器发挥出色作用。项目网站和源代码详见：https://prompt2walk.github.io/。