ABSTRACT The use of large language models (LLMs) to drive robots poses significant challenges, especially in the accurate interpretation of commands and the generation of executable programs for the robot actuators. To address these issues, this study introduces a novel robot control strategy that enables users to provide commands directly in natural language. In this strategy, LLMs automatically generate the robot's control program guided by a specific prompt, eliminating the need for task‐specific fine‐tuning. This study examines the consistency of command meanings during the translation of natural language commands into LLM‐compatible textual inputs and analyzes the motion trajectories of the McNamee wheeled robot upon receiving these commands. Experimental results demonstrate that LLMs correctly interpret and transform commands with an accuracy of up to 0.92 and generate executable control programs with a success rate exceeding 0.80
Wang et al. (Mon,) studied this question.