Large language models (LLMs) exhibit advanced reasoning skills, enabling robots to comprehend natural language instructions and strategically plan high-level actions through proper grounding. However, LLM hallucination may result in robots confidently executing plans that are misaligned with user goals or, in extreme cases, unsafe. Additionally, inherent ambiguity in natural language instructions can induce task uncertainty, particularly in situations where multiple valid options exist. To address this issue, LLMs must identify such uncertainty and proactively seek clarification. This paper explores the concept of introspective planning as a systematic method for guiding LLMs in forming uncertainty--aware plans for robotic task execution without the need for fine-tuning. We investigate uncertainty quantification in task-level robot planning and demonstrate that introspection significantly improves both success rates and safety compared to state-of-the-art LLM-based planning approaches. Furthermore, we assess the effectiveness of introspective planning in conjunction with conformal prediction, revealing that this combination yields tighter confidence bounds, thereby maintaining statistical success guarantees with fewer superfluous user clarification queries.

翻译：大型语言模型展现出高级推理能力，使机器人能够理解自然语言指令，并通过适当的接地机制制定高层动作策略。然而，语言模型的幻觉现象可能导致机器人自信地执行与用户目标不一致甚至存在安全风险的规划方案。此外，自然语言指令中固有的歧义性会引发任务不确定性，尤其当存在多个有效选项时。为解决该问题，语言模型需识别此类不确定性并主动寻求澄清。本文探索内省规划这一系统化方法，引导语言模型在无需微调的前提下，形成具有不确定性意识的机器人任务执行规划。我们研究了任务级机器人规划中的不确定性量化问题，实验表明，与现有最先进的基于语言模型的规划方法相比，内省规划能显著提升成功率和安全性。此外，我们评估了内省规划与保形预测的联合效果，发现这种组合能获得更紧密的置信区间，从而在减少冗余用户澄清查询次数的同时维持统计成功保证。