arXiv cs.AI· Mingjian Gao, Zhaocheng Li, Haoyang Huang, Wenqiao Zhang, Yingjie Niu, Hao Zhou, Chao Li, Juncheng Li, Siliang Tang, Yueting Zhuang·· 9 天前AI 评分34
EvolvingNav：面向演化世界持续导航的预测式 4D 信念
Beyond the Remembered World: Predictive 4D Belief for Persistent Navigation in Evolving Worlds
AI 导读
针对目标在未被观察时可能移动、导致记忆位置失效的问题，研究者提出 EvolvingNav，通过时间索引的 3D 物体历史构建持久-迁移结构化信念，并用事件驱动滤波器在时间推移中传播信念、预测检查时刻的目标占据情况并融合新的 RGB-D 证据。
正文 · 原文
Abstract: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.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2609.39166 [cs.AI] |
| (or arXiv:2609.39166v3 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2609.39166 arXiv-issued DOI via DataCite |
Submission history
From: Mingjian Gao [view email]
[v1]
Wed, 30 Sep 2026 07:26:36 UTC (23,565 KB)
[v2]
Thu, 1 Oct 2026 12:48:26 UTC (23,580 KB)
[v3]
Thu, 8 Oct 2026 00:42:08 UTC (23,580 KB)
来源：arXiv cs.AI · arxiv.org