发表机构
University of Pennsylvania; Texas A&M University（宾夕法尼亚大学; 德克萨斯A&M大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对自然语言中欠指定任务的情境不确定性，提出CLUE框架，利用LLM假设与在线语言地图闭环交互，在真实机器人上实现接近oracle且远超无反馈规划器的成功率。
AI 中文摘要
基础模型使机器人能够解释自然语言并推理环境情境，但大多数语言条件化策略假设目标已被良好指定，且任务相关信息通过先验地图预先提供。在陌生环境中执行欠指定任务会带来高度的情境不确定性：机器人必须联合推断什么构成任务成功、什么构成相关信息，以及这些信息存在于何处（或是否存在）。我们通过CLUE（闭环情境不确定性解决）框架来解决这些局限性，该框架用于在自然语言中主动解决欠指定任务的情境不确定性。CLUE使用由LLM派生的策略来假设任务相关概念和潜在计划，然后利用在线构建的语言嵌入地图将这些假设落地为行动。该策略通过闭环环境交互顺序评估假设，并在收集新信息时完善其计划。我们在Boston Dynamics Spot上部署了CLUE，涵盖三个真实室内和室外环境，共15个任务，这些任务需要对象消歧、功能推断和遮挡推理。CLUE的成功率在7个百分点以内接近oracle策略，并且比没有闭环反馈的LLM启用规划器高出4倍。支持实验表明，仅构建然后查询语言增强地图不足以解决复杂的情境规划任务；这些方法的成功率约为CLUE的三分之一，同时需要超过10倍的VLM令牌。我们在此https URL提供额外信息。
英文摘要
Foundation models provide robots with the ability to interpret natural language and reason about environmental context, yet most language-conditioned policies assume that goals are well-specified and that task-relevant information is provided upfront via a prior map. Operating in unfamiliar environments with underspecified tasks entails high contextual uncertainty: the robot must jointly infer what constitutes task success, what constitutes relevant information, and where (or whether) that information exists. We address these limitations via CLUE (Closed-Loop contextual Uncertainty rEsolution), a framework for actively resolving contextual uncertainty given underspecified tasks in natural language. CLUE uses an LLM-derived policy to hypothesize task-relevant concepts and potential plans. It then uses a language-embedded map, which is constructed online, to ground these hypotheses into actions. The policy sequentially evaluates hypotheses via closed-loop environment interaction and refines its plans as it gathers new information. We deploy CLUE on a Boston Dynamics Spot across three real indoor and outdoor environments spanning 15 tasks that require object disambiguation, functional inference, and occlusion reasoning. CLUE achieves a success rate within 7 percentage points of an oracle policy and outperforms an LLM-enabled planner without closed-loop feedback by a 4x margin. Supporting experiments demonstrate that simply building and then querying a language-enriched map is insufficient to resolve complex contextual planning tasks; these approaches achieve roughly one third the success rate of CLUE while requiring over 10x more VLM tokens. We provide additional information at https://zacravichandran.github.io/CLUE.
CommentsAccepted to the International Symposium of Robotics Research (ISRR) 2026
