HuggingFace Daily Papers（社区热门论文）· HuggingFace Daily Papers（社区热门论文）·· 6 天前AI 评分36
EvolvingNav：面向动态变化世界的预测式 4D 信念持久导航
AI 导读
针对目标在未被观察时移动、导致记忆位置失效的问题，研究者提出 EvolvingNav，通过带时间戳的 3D 物体历史构建时间索引信念，用结构化持久-迁移模型区分目标停留与迁移，并以事件驱动滤波器随时间传播信念、预测候选检查时刻的目标占据情况。该方法同时引入基于人类活动轨迹的 EvoWorld-Bench，含 54 个场景、803,680 个任务，在仿真与真机实验中提升了导航成功率和搜索效率。
正文
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:2609.39166v2 [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)
来源：HuggingFace Daily Papers（社区热门论文） · arxiv.org