LangMap：一个用于分层开放词汇目标导航的人工验证基准
LangMap: A Human-Verified Benchmark for Hierarchical Open-Vocabulary Goal Navigation
AI总结：
针对现有基准在分层语义目标导航中的不足，提出LangMap基准，通过人工验证的语义标注和对比注释协议，支持场景、房间、区域和实例四个层级的目标导航任务，并引入PlaNaVid基线方法。
摘要：
语言条件目标导航（LGN）要求智能体在没有逐步指导的情况下定位用户指定的目标。然而，现有基准主要关注类别级目标或依赖视觉语言模型（VLM）生成的实例描述，这些描述通常包含歧义和语义错误，限制了系统性和可靠的评估。我们提出了HieraNav，一个开放词汇的LGN任务，目标在四个分层语义层级上指定：场景、房间、区域和实例。为此，我们提出了Language as a Map（LangMap），据我们所知，这是第一个具有人工验证语义标注的真实世界3D室内导航基准，支持所有四个目标层级的任务。LangMap提供了区域标签以及覆盖414个对象类别的区分性区域和实例描述，通过比较同一场景区域和实例的严格对比注释协议生成，包含超过18K个任务。每个目标都配有简洁和详细的描述，支持跨指令风格的评估。定量和定性分析验证了我们的注释质量；值得注意的是，我们的实例描述在文本到视图匹配上比GOAT-Bench注释高出23个百分点。我们进一步引入了PlaNaVid，一个强大的仅RGB基线，它将有界多样记忆（BDM）与高级规划相结合，以激发用于多目标导航的反应策略。PlaNaVid在没有深度、3D场景表示或对象掩码的情况下实现了顶级成功率。进一步分析表明，记忆和更丰富的上下文提升了性能，而长尾类别、小物体、远距离目标和多目标完成仍然是开放的挑战。该基准可在https://bo-miao.github.io/LangMap获取。
英文摘要：
Language-conditioned goal navigation (LGN) requires embodied agents to locate user-specified targets without step-by-step guidance. However, existing benchmarks largely focus on category-level goals or rely on instance descriptions generated by vision-language models, which often contain ambiguities and semantic errors, limiting systematic and reliable evaluation. We introduce HieraNav, an open-vocabulary LGN task with goals at four hierarchical semantic levels: scene, room, region, and instance. We present Language as a Map (LangMap), the first LGN benchmark to enrich real-world indoor 3D scans with human-verified semantic annotations supporting tasks across all four goal levels. Built on HM3D using a contrastive annotation protocol that compares same-scene regions and instances, LangMap provides region labels and discriminative region and instance descriptions covering 414 object categories and contains over 18K tasks. Each target has concise and detailed descriptions, enabling evaluation across instruction styles. Automated and human evaluations validate our annotation quality: our descriptions improve text-to-view matching accuracy over GOAT-Bench's by 23 points on all shared annotated instances, and an independent human audit yields 92.5% unique-and-correct matches. We also propose PlaNaVid, an RGB-only baseline that combines Bounded Diverse Memory with high-level planning to prime a reactive policy for multi-goal navigation, achieving top-tier success rates without depth, 3D scene representations, or object masks. Further analyses reveal that exploration and hierarchical disambiguation failures become more prominent at finer goal levels, while long-tail categories, small objects, distant targets, timely stopping, and multi-goal completion remain challenging. Benchmark and code: https://bo-miao.github.io/LangMap
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。
