Navigating to a specified object in an unknown environment is a fundamental yet challenging capability of embodied intelligence. However, current methods struggle to balance decision frequency with intelligence, resulting in decisions lacking foresight or discontinuous actions. In this work, we propose PIGEON: Point of Interest Guided Exploration for Object Navigation with VLM, maintaining a lightweight and semantically aligned snapshot memory during exploration as semantic input for the exploration strategy. We use a large Visual-Language Model (VLM), named PIGEON-VL, to select Points of Interest (PoI) formed during exploration and then employ a lower-level planner for action output, increasing the decision frequency. Additionally, this PoI-based decision-making enables the generation of Reinforcement Learning with Verifiable Reward (RLVR) data suitable for simulators. Experiments on classic object navigation benchmarks demonstrate that our zero-shot transfer method achieves state-of-the-art performance, while RLVR further enhances the model's semantic guidance capabilities, enabling deep reasoning during real-time navigation.

翻译：在未知环境中导航至指定物体是具身智能的一项基础但具有挑战性的能力。然而，现有方法难以在决策频率与智能水平之间取得平衡，导致决策缺乏前瞻性或动作不连贯。本研究提出PIGEON：基于视觉语言模型的兴趣点引导探索物体导航方法，通过在探索过程中维护轻量化且语义对齐的快照记忆作为探索策略的语义输入。我们采用名为PIGEON-VL的大型视觉语言模型，对探索过程中形成的兴趣点进行筛选，随后调用底层规划器输出动作，从而提升决策频率。此外，这种基于兴趣点的决策机制能够生成适用于仿真器的可验证奖励强化学习数据。在经典物体导航基准测试上的实验表明，我们的零样本迁移方法实现了最先进的性能，而可验证奖励强化学习进一步增强了模型的语义引导能力，使其能够在实时导航过程中进行深度推理。