EvoMemNav: 用于零样本具身导航的高效自进化细粒度记忆
EvoMemNav: Efficient Self-Evolving Fine-Grained Memory for Zero-Shot Embodied Navigation
AI总结：
提出EvoMemNav框架，通过构建视觉-语义记忆图并采用预算驱动的粗到细策略，结合反射驱动写回机制，实现零样本具身导航中高效、自进化的细粒度记忆，提升多实例区分和停止验证性能。
摘要：
构建记忆对于零样本具身导航中的长时程规划至关重要。以检测器为中心的场景图通常将观测压缩为稀疏节点，丢弃细粒度视觉证据并积累噪声，而基于3D重建的方法计算成本高昂。我们提出EvoMemNav，一种用于零样本具身导航的高效、自进化、细粒度记忆框架。EvoMemNav构建视觉-语义记忆图（VSMGraph），将原始视图作为一等记忆，并通过轻量级语义线索和拓扑关系将其组织成房间-视图-对象层次结构，保留用于消歧和停止验证的细粒度细节。为了扩展到不断增长的记忆，我们引入预算驱动的粗到细策略：粗阶段将搜索空间压缩到有希望的区域，细阶段仅调用VLM进行目标验证和决策。除了静态记忆，EvoMemNav在每个子任务后执行反射驱动的写回，更新附加到图上的先验知识，编码累积的环境知识以优化未来决策而无需重新训练。在GOAT-Bench和HM3D上，针对物体、文本描述和图像目标模态的实验显示，SR/SPL持续提升，具有更好的多实例区分能力、更少的过早停止和更强的零样本泛化能力。
英文摘要：
Building memory is essential for long-horizon planning in zero-shot embodied navigation. Detector-centric scene graphs often compress observations into sparse nodes, discarding fine-grained visual evidence and accumulating noise, while 3D reconstruction-based methods remain computationally prohibitive. We present EvoMemNav, an efficient, self-evolving, fine-grained memory framework for zero-shot embodied navigation. EvoMemNav constructs a Visual-Semantic Memory Graph (VSMGraph) that keeps raw views as first-class memory and organizes them with lightweight semantic cues and topological relations into a room-view-object hierarchy, preserving fine-grained details for disambiguation and Stop verification. To scale to growing memory, we introduce a budgeted coarse-to-fine policy: a coarse stage compresses the search space into promising regions, and a fine stage invokes a VLM only for targeted verification and decision. Beyond static memories, EvoMemNav performs reflection-driven write-back after each subtask, updating graph-attached priors that encode accumulated environmental knowledge to refine future decisions without retraining. Experiments on GOAT-Bench and HM3D across object, text-description, and image-goal modalities show consistent gains in SR/SPL, with better multi-instance disambiguation, fewer premature stops, and stronger zero-shot generalization.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
