PIGEON: 通过兴趣点选择的VLM驱动物体导航
PIGEON: VLM-Driven Object Navigation via Points of Interest Selection
AI总结：
提出PIGEON框架，将物体导航建模为基于原始观测的稀疏决策问题，通过兴趣点（PoI）作为视觉决策单元，结合VLM选择关键点，实现零样本SOTA性能并迁移至主动具身问答。
摘要：
在未见过的室内环境中进行物体导航要求智能体在部分可观测条件下执行语义搜索。视觉-语言模型（VLM）为此任务提供了强大的语义-空间先验，但如何将其与机器人导航接口仍然具有挑战性：密集的VLM推理成本高昂，而将环境抽象为符号记忆通常将高层推理与支持它的原始视觉证据分离。我们提出PIGEON（基于兴趣点引导的物体导航探索），一种VLM驱动的框架，将物体导航建模为基于原始观测的稀疏决策问题。PIGEON引入兴趣点（PoI）作为稀疏视觉决策单元，将几何可执行的路点与原始自我中心观测耦合。PIGEON不是将VLM用作密集控制器或限制其进行前沿排序，而是使VLM能够选择任务关键的PoI，包括探索前沿、疑似目标物体、可穿越楼梯和楼层级摘要，而低级规划器在它们之间执行连续运动。这种PoI接口进一步使高层导航决策可验证，使我们能够开发一个RLVR流水线，无需手动思维链注释即可改进局部VLM。在Habitat ObjectNav基准上的大量实验表明，PIGEON实现了零样本最先进性能，与基础模型能力一致扩展，并且仅通过提示修改即可迁移到主动具身问答。在物理机器人上的实际部署进一步证明了其鲁棒性和效率。
英文摘要：
Object navigation in unseen indoor environments requires agents to perform semantic search under partial observability. Vision-language models (VLMs) provide strong semantic-spatial priors for this task, but how to interface them with robot navigation remains challenging: dense VLM inference is expensive, while abstracting environments into symbolic memories often separates high-level reasoning from the raw visual evidence that supports it. We propose we propose PIGEON (Point of Interest Guided Exploration for Object Navigation), a VLM-driven framework that formulates object navigation as raw-observation-grounded sparse decision problem. PIGEON introduces Points of Interest (PoIs) as sparse visual decision units that couple geometrically executable waypoints with raw egocentric observations. Rather than using VLMs as dense controllers or restricting them to frontier ranking, PIGEON enables VLMs to select among task-critical PoIs, including exploration frontiers, suspected target objects, traversable stairs, and floor-level summaries, while low-level planners execute continuous motion between them. This PoI interface further makes high-level navigation decisions verifiable, allowing us to develop an RLVR pipeline that improves local VLMs without manual Chain-of-Thought annotations. Extensive experiments on Habitat ObjectNav benchmarks show that PIGEON achieves state-of-the-art zero-shot performance, scales consistently with foundation model capacity, and transfers to Active Embodied Question Answering with only prompt modifications. Real-world deployments on physical robots further demonstrate its robustness and efficiency.
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。
