LangMap: A Human-Verified Benchmark for Hierarchical Open-Vocabulary Goal Navigation
LangMap: A Human-Verified Benchmark for Hierarchical Open-Vocabulary Goal Navigation
This paper introduces LangMap, a benchmark for hierarchical open-vocabulary goal navigation enriched with human-verified semantic annotations across four levels (scene, room, region, instance). Built on HM3D, it contains over 18K tasks covering 414 object categories. The authors also propose PlaNaVid, an RGB-only baseline combining bounded diverse memory with high-level planning to achieve top-tier success rates without depth or 3D scene representations. Automated and human evaluations show improved text-to-view matching accuracy and high unique-and-correct match rates.
The authors introduce LangMap, a benchmark enriched with human-verified semantic annotations for hierarchical open-vocabulary goal navigation, and PlaNaVid, an RGB-only baseline that achieves top-tier success rates without depth or 3D scene representations.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
- paper: not_reported
- code: Reported pending Open source S6
- weights: not_reported
- dataset: not_reported
- code: not_reported
What remains unknown
Dataset licensing and commercial-use rights are not established here.
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
e introduce HieraNav, an open-vocabulary navigation task with goals at four hierarchical semantic levels: scene, room, region, and instance. We present Language as a Map (LangMap), the first goal navigation 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
Open source S3
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 a
Open source S4
ll 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 disam
Open source S5
biguation 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
Open source S6
Implications for data suppliers
RoboSignal interpretation and collection questions, not statements of buyer demand.
- Confirm the required data type and collection setting with the buyer; this source does not establish a complete collection specification.
- Validate demand and acceptance criteria with a buyer before scaling. Publication, popularity and a research result do not establish a purchase commitment.
Source：arXiv Robotics — research abstracts · arxiv.org