The evolution of autonomous driving has made remarkable advancements in recent years, evolving into a tangible reality. However, a human-centric large-scale adoption hinges on meeting a variety of multifaceted requirements. To ensure that the autonomous system meets the user's intent, it is essential to accurately discern and interpret user commands, especially in complex or emergency situations. To this end, we propose to leverage the reasoning capabilities of Large Language Models (LLMs) to infer system requirements from in-cabin users' commands. Through a series of experiments that include different LLM models and prompt designs, we explore the few-shot multivariate binary classification accuracy of system requirements from natural language textual commands. We confirm the general ability of LLMs to understand and reason about prompts but underline that their effectiveness is conditioned on the quality of both the LLM model and the design of appropriate sequential prompts. Code and models are public with the link \url{https://github.com/KTH-RPL/DriveCmd_LLM}.

翻译：近年来，自动驾驶技术取得了显著进步，正逐步成为现实。然而，实现以人为中心的大规模应用仍需满足多层面的复杂需求。为确保自动驾驶系统符合用户意图，必须准确识别和解读用户指令，尤其是在复杂或紧急场景中。为此，我们提出利用大型语言模型的推理能力，从座舱内用户指令中推导系统需求。通过一系列实验（涵盖不同大语言模型与提示设计），我们探索了基于自然语言文本指令的系统需求少样本多元二元分类精度。研究证实了大语言模型理解与推理提示的通用能力，但强调其有效性取决于模型质量及合理顺序提示的设计。相关代码与模型已开源，链接为\url{https://github.com/KTH-RPL/DriveCmd_LLM}。