APEX：一种面向异步空中物体目标导航的解耦记忆探索器
APEX: A Decoupled Memory-based Explorer for Asynchronous Aerial Object Goal Navigation
把 VLM 的零样本空间语义理解与开放词表检测器解耦成异步并行的记忆-决策-定位三模块，绕开 VLM 推理延迟，这一「慢感知快决策」的异步分层范式可直接迁移到其他视觉导航与具身探索任务。
原文依据 effectively bypassing the VLM's inference latency and boosting the agent's proactivity in exploration
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论空中物体目标导航是具身智能中一个具有挑战性的前沿方向，它要求无人机（UAV）智能体仅依靠视觉感知与语言描述，自主探索、推理并识别特定目标。然而，现有方法在空中环境中的复杂空间表征记忆、可靠且可解释的动作决策，以及高效的探索与信息采集方面仍存在困难。为应对这些挑战，我们提出 APEX（空中并行探索器），一种面向复杂空中环境下高效探索与目标获取的新型分层智能体。APEX 建立在模块化的三部分架构之上：1）动态时空语义地图记忆，利用视觉语言模型（VLM）的零样本能力动态构建高分辨率的三维吸引图、探索图与障碍图，作为一种可解释的记忆机制；2）动作决策模块，通过强化学习训练，将丰富的空间理解转化为细粒度且鲁棒的控制策略；3）目标视觉定位模块，采用开放词表检测器实现确定且可泛化的目标识别。上述所有组件被集成到一个分层、异步、并行的框架中，有效绕开了 VLM 的推理延迟，并提升了智能体在探索中的主动性。大量实验表明，在具有挑战性的 UAV-ON 基准上，APEX 以 +4.2% 的成功率（SR）和 +2.8% 的 SPL 超越此前的最先进方法，证明了其卓越的效率以及分层异步设计的有效性。
英文原文摘要 1691 字符
The Aerial Object Goal Navigation, a challenging frontier in Embodied AI, requires an Unmanned Aerial Vehicle (UAV) agent to autonomously explore, reason, and identify a specific target using only visual perception and language description. However, existing methods struggle with the memorization of complex spatial representations in aerial environments, reliable and interpretable action decision-making, and inefficient exploration and information gathering. To address these challenges, we introduce **APEX** (Aerial Parallel Explorer), a novel hierarchical agent designed for efficient exploration and target acquisition in complex aerial settings. APEX is built upon a modular, three-part architecture: 1) Dynamic Spatio-Semantic Mapping Memory, which leverages the zero-shot capability of a Vision-Language Model (VLM) to dynamically construct high-resolution 3D Attraction, Exploration, and Obstacle maps, serving as an interpretable memory mechanism. 2) Action Decision Module, trained with reinforcement learning, which translates this rich spatial understanding into a fine-grained and robust control policy. 3) Target Grounding Module, which employs an open-vocabulary detector to achieve definitive and generalizable target identification. All these components are integrated into a hierarchical, asynchronous, and parallel framework, effectively bypassing the VLM's inference latency and boosting the agent's proactivity in exploration. Extensive experiments show that APEX outperforms the previous state of the art by +4.2% SR and +2.8% SPL on challenging UAV-ON benchmarks, demonstrating its superior efficiency and the effectiveness of its hierarchical asynchronous design.