超越记忆中的世界：面向演化世界的持久导航的预测性4D信念

中文摘要 AI 辅助

持久空间记忆使具身智能体能够在重复访问中导航熟悉的环境。然而，目标可能在未被观察时移动，包括在导航期间移动，使得当智能体到达时，记忆中的位置已变得不可靠。尽管在记忆检索和状态预测方面取得了进展，但考虑持续的隐藏世界演化并在有限可见性下修正信念仍然具有挑战性。我们研究演化世界导航问题，智能体从间歇性观察中推断目标位置，在检查时间预测其状态，并利用视觉证据修正信念。我们提出EvolvingNav，通过结构化的持久-重定位模型，从带时间戳的3D物体历史构建时间索引信念。该信念区分在最后观察位置的持久性与重定位到替代位置的可能性，并在已知候选集之外保留概率质量。事件驱动滤波器随时间推移传播当前信念，预测候选检查时间的目标占用情况，并整合新的RGB-D证据。负面观察根据校准的、可见性条件下的检测概率降低位置假设的权重，而证据跟踪防止重复使用相同观察。一个冻结的、零样本视觉-语言控制器使用更新后的信念选择动作并重新规划。我们进一步引入EvoWorld-Bench，一个基于人类活动轨迹的基准，包含54个场景和803,680个任务，在导航前和导航期间具有受控变化。在仿真和真实机器人实验中，EvolvingNav在导航成功率和搜索效率上优于评估的基线。配对实验显示在可学习的时间模式下的最大增益，而消融实验证明了保留不确定性和整合可见性感知证据的价值。

英文摘要

Persistent spatial memory enables embodied agents to navigate familiar environments across repeated visits. However, targets may move while unobserved, including during navigation, making remembered locations unreliable by the time an agent arrives. Despite advances in memory retrieval and state prediction, accounting for continued hidden world evolution and revising beliefs under limited visibility remain challenging. We study Evolving-World Navigation, where agents infer target locations from intermittent observations, predict their states at inspection time, and revise beliefs using visual evidence. We propose EvolvingNav, which constructs a time-indexed belief from timestamped 3D object histories through a structured persistence-relocation model. The belief distinguishes persistence at the last observed location from relocation to alternative locations and retains probability mass outside the known candidate set. An event-driven filter propagates the current belief as time elapses, forecasts target occupancy at candidate inspection times, and incorporates new RGB-D evidence. Negative observations downweight location hypotheses according to calibrated, visibility-conditioned detection probabilities, while evidence tracking prevents repeated use of the same observations. A frozen, zero-shot vision-language controller uses the updated belief to choose actions and replan. We further introduce EvoWorld-Bench, a benchmark grounded in human activity traces, comprising 54 scenes and 803,680 tasks with controlled changes before and during navigation. In simulation and real-robot experiments, EvolvingNav improves navigation success and search efficiency over the evaluated baselines. Paired experiments show the clearest gains under learnable temporal patterns, while ablations demonstrate the value of preserving uncertainty and incorporating visibility-aware evidence.

发表机构

• Zhejiang University（浙江大学）
• University of California, San Diego（加利福尼亚大学圣迭戈分校）
• Deeprobotics
• Chinese University of Hong Kong（香港中文大学）

机构由 AI 辅助整理，请以论文原文为准。