HM3D-OVON：一个用于开放词汇目标导航的数据集与基准
HM3D-OVON: A Dataset and Benchmark for Open-Vocabulary Object Goal Navigation
AI总结：
本文提出了大规模开放词汇目标导航数据集与基准HM3D-OVON，基于真实3D扫描包含379个类别超1.5万实例，支持通过自由文本定义目标进行训练评估，实验证明其训练的智能体性能更高且对噪声更鲁棒。
摘要：
我们提出了Habitat-Matterport 3D开放词汇目标导航数据集（HM3D-OVON），这是一个大规模基准，拓宽了先前目标导航（ObjectNav）基准的范围和语义范围。利用HM3DSem数据集，HM3D-OVON包含了来自真实环境照片级真实3D扫描的379个不同类别的超过1.5万个家庭物体标注实例。与将目标物体限制在预定义的6-20个类别的早期ObjectNav数据集不同，HM3D-OVON通过测试时用自由形式语言定义的开放目标集，促进了模型的训练和评估。通过这种开放词汇表述，HM3D-OVON推动了学习视觉语义导航行为的发展，该行为能够以开放词汇方式搜索由文本指定的任何物体。此外，我们在HM3D-OVON上系统评估并比较了几种不同类型的方法。我们发现，HM3D-OVON可用于训练开放词汇ObjectNav智能体，该智能体不仅实现了更高的性能，而且比最先进的ObjectNav方法对定位和驱动噪声更鲁棒。我们希望我们的基准和基线结果能推动人们对开发具身智能体的兴趣，这种智能体能在现实空间中导航，找到通过自由形式语言指定的家庭物体，朝着更灵活、更像人类的语义视觉导航迈进一步。代码和视频可在：naoki.io/ovon获取。
英文摘要：
We present the Habitat-Matterport 3D Open Vocabulary Object Goal Navigation dataset (HM3D-OVON), a large-scale benchmark that broadens the scope and semantic range of prior Object Goal Navigation (ObjectNav) benchmarks. Leveraging the HM3DSem dataset, HM3D-OVON incorporates over 15k annotated instances of household objects across 379 distinct categories, derived from photo-realistic 3D scans of real-world environments. In contrast to earlier ObjectNav datasets, which limit goal objects to a predefined set of 6-20 categories, HM3D-OVON facilitates the training and evaluation of models with an open-set of goals defined through free-form language at test-time. Through this open-vocabulary formulation, HM3D-OVON encourages progress towards learning visuo-semantic navigation behaviors that are capable of searching for any object specified by text in an open-vocabulary manner. Additionally, we systematically evaluate and compare several different types of approaches on HM3D-OVON. We find that HM3D-OVON can be used to train an open-vocabulary ObjectNav agent that achieves both higher performance and is more robust to localization and actuation noise than the state-of-the-art ObjectNav approach. We hope that our benchmark and baseline results will drive interest in developing embodied agents that can navigate real-world spaces to find household objects specified through free-form language, taking a step towards more flexible and human-like semantic visual navigation. Code and videos available at: naoki.io/ovon.
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。
