CovNav:共形预测引导的目标导向导航自适应推理
CovNav: Conformal Prediction-Guided Adaptive Inference for Object Goal Navigation
AI总结:
该研究针对目标导向导航中LLM推理的质量效率权衡问题,提出无需训练的CovNav框架,用共形预测将双过程推理转为不确定性决策,在Gibson、HM3D数据集及TurtleBot 4机器人上验证了其性能优势。
摘要:
在目标导向导航(ObjectNav)中,具身智能体需在未见过的环境中找到目标物体(例如“找到一张床”),依赖物体共现等空间常识。大型语言模型(LLM)编码了这类常识,但将其部署在机器人上会面临推理质量与效率的权衡:云端模型存在延迟和隐私风险,而小型本地LLM速度快但易出现空间判断的幻觉。混合推理LLM同时具备快速非思考模式和慢速思考模式,这引发了具身智能体的关键问题:何时值得为慢速思考付出成本?我们提出CovNav,一个无需训练的框架,通过共形预测(CP)回答该问题,将双过程(系统1/系统2)推理转化为感知不确定性的决策。与Jev等近期决策模型类似,CovNav将每个空间查询转化为结构化二元决策而非自由形式生成:快速模式下的本地LLM判断目标是否可能在观测物体附近,CP将其token概率转化为预测集,仅将模糊查询升级为慢速链式思考推理。物体对表述形式保持了校准的可处理性,并通过现成检测器支持开放集物体。在Gibson和HM3D上的实验显示,CovNav在HM3D v1和v2上的成功率分别超过最强零样本基线0.8和1.7个百分点,同时仅对12.4%的查询调用慢速推理,在仅占全时思考一小部分延迟的情况下保留了大部分增益。在TurtleBot 4上的真实机器人实验进一步验证了该方法。CovNav展示了校准后的不确定性如何决定具身智能体何时应进行慢速思考,为基于LLM的机器人提供了一种原则性的测试时自适应推理形式。
英文摘要:
In object goal navigation (ObjectNav), an embodied agent must find a target object (e.g., "find a bed") in a previously unseen environment, relying on spatial commonsense such as object co-occurrence. Large Language Models (LLMs) encode this commonsense, but deploying them on robots exposes a trade-off between reasoning quality and efficiency: cloud-based models incur latency and privacy risks, whereas small on-device LLMs are fast but prone to hallucinated spatial judgments. Hybrid reasoning LLMs offer both a fast non-thinking mode and a slow thinking mode, which raises a key question for embodied agents: when is slow thinking worth its cost? We propose CovNav, a training-free framework that answers this question with Conformal Prediction (CP), turning dual-process (System 1 / System 2) inference into an uncertainty-aware decision. Much like recent decision models such as Jev, CovNav casts each spatial query as a structured binary decision rather than free-form generation: a local LLM in fast mode judges whether the target is likely near an observed object, CP converts its token probabilities into a prediction set, and only ambiguous queries are escalated to slow chain-of-thought reasoning. The object-pair formulation keeps calibration tractable and supports open-set objects through off-the-shelf detectors. Experiments on Gibson and HM3D show that CovNav surpasses the strongest zero-shot baseline by 0.8 and 1.7 percentage points in success rate on HM3D v1 and v2, while invoking slow reasoning for only 12.4% of queries and retaining most of the gain of always-on thinking at a fraction of its latency. Real-robot experiments on a TurtleBot 4 further validate the approach. CovNav shows how calibrated uncertainty can decide when an embodied agent should think slowly, offering a principled form of adaptive test-time reasoning for LLM-based robots.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。