通过前沿评分实现基于零样本目标中心语义导航的房间介导共现
Room-Mediated Co-occurrence for Zero-Shot Object-Centric Semantic Navigation via Frontier Scoring
浏览论文内容
中文总结 AI 辅助
研究零样本目标中心语义导航，提出通过房间词汇表介导对象关系的无需训练的管道，利用CLIP-derived的RPV计算共现，经洪水填充传播投影到值图排序前沿，相比基线提升了SR和SPL，保留可解释性与灵活性。
中文摘要 AI 辅助
零样本目标导航方法越来越多地使用视觉语言先验，但潜在空间中的直接对象-对象相似性通常是空间共现的弱代理。我们提出了一种无需训练的分析性语义导航管道，通过紧凑的房间词汇表来介导对象关系。每个对象标签映射到一个基于CLIP的房间概率向量（RPV），通过RPV分布重叠计算对象-目标共现。这些分数通过测地线洪水填充传播（快速行进法）投影到值图上，并带有自适应信号衰减，用于按语义分数对前沿进行排序以进行导航。结果表明，与HM3D数据集验证分割上的图像整体基线相比，我们的目标中心方法分别将成功率（SR）和加权逆路径长度成功率（SPL）相对提高了3%和1.3%，同时保留了可解释性和开放词汇灵活性。
英文摘要
Zero-shot ObjectNav methods increasingly use vision-language priors, but direct object-object similarity in the latent space is often a weak proxy for spatial co-occurrence. We present an analytical, training-free semantic navigation pipeline that mediates object relationships through a compact room lexicon. Each object label is mapped to a CLIP-derived Room Probability Vector (RPV), and object-target co-occurrence is computed from RPV distribution overlap. These scores are projected onto a value map using geodesic flood-fill propagation (Fast Marching Method), with adaptive signal decay, and are used to rank frontiers by semantic score for navigation. Together, these components form an integrated, training-free, object-centric pipeline for open-vocabulary zero-shot navigation. Results show that our object-centric approach improves Success Rate (SR) and Success by weighted inverse Path Length (SPL) by a relative 3% and 1.3%, respectively, compared to image-holistic baselines on the HM3D dataset validation split, while preserving interpretability and open-vocabulary flexibility. Code is available at: uts-ri.github.io/RPV-SemNav.
发表机构
- Robotics Institute, Faculty of Engineering and Information Technology, University of Technology Sydney (UTS)（悉尼科技大学工程与信息技术学院机器人研究所）
机构由 AI 辅助整理，请以论文原文为准。
