# OpenBelief-Nav: Evidence-Preserving Object Memory for Open-Vocabulary Language-Guided Navigation

arXiv: https://arxiv.org/abs/2608.13923 · HTML: https://mlsanity.com/paper/2608.13923/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 24 references that are in the map.
- First posted on arXiv 14 Aug 2026.

## Builds on (most cited first, 21 of 21)

- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [SAM 3: Segment Anything with Concepts](https://mlsanity.com/paper/2511.16719/) (2025)
- [The Replica Dataset: A Digital Replica of Indoor Spaces](https://mlsanity.com/paper/1906.05797/) (2019)
- [Evidential Deep Learning to Quantify Classification Uncertainty](https://mlsanity.com/paper/1806.01768/) (2018)
- [Visual Language Maps for Robot Navigation](https://mlsanity.com/paper/2210.05714/) (2022)
- [ConceptGraphs: Open-Vocabulary 3D Scene Graphs for Perception and Planning](https://mlsanity.com/paper/2309.16650/) (2023)
- [ConceptFusion: Open-set Multimodal 3D Mapping](https://mlsanity.com/paper/2302.07241/) (2023)
- [Habitat 3.0: A Co-Habitat for Humans, Avatars and Robots](https://mlsanity.com/paper/2310.13724/) (2023)
- [Robot Operating System 2: Design, Architecture, and Uses In The Wild](https://mlsanity.com/paper/2211.07752/) (2022)
- [Hierarchical Open-Vocabulary 3D Scene Graphs for Language-Grounded Robot Navigation](https://mlsanity.com/paper/2403.17846/) (2024)
- [Habitat-Matterport 3D Semantics Dataset](https://mlsanity.com/paper/2210.05633/) (2022)
- [The Marathon 2: A Navigation System](https://mlsanity.com/paper/2003.00368/) (2020)
- [Dynamic Open-Vocabulary 3D Scene Graphs for Long-term Language-Guided Mobile Manipulation](https://mlsanity.com/paper/2410.11989/) (2024)
- [MobileCLIP2: Improving Multi-Modal Reinforced Training](https://mlsanity.com/paper/2508.20691/) (2025)
- [FSR-VLN: Fast and Slow Reasoning for Vision-Language Navigation with Hierarchical Multi-modal Scene Graph](https://mlsanity.com/paper/2509.13733/) (2025)
- [OpenIN: Open-Vocabulary Instance-Oriented Navigation in Dynamic Domestic Environments](https://mlsanity.com/paper/2501.04279/) (2025)
- [DualMap: Online Open-Vocabulary Semantic Mapping for Natural Language Navigation in Dynamic Changing Scenes](https://mlsanity.com/paper/2506.01950/) (2025)
- [SysNav: Multi-Level Systematic Cooperation Enables Real-World, Cross-Embodiment Object Navigation](https://mlsanity.com/paper/2603.06914/) (2026)
- [OGScene3D: Incremental Open-Vocabulary 3D Gaussian Scene Graph Mapping for Scene Understanding](https://mlsanity.com/paper/2603.16301/) (2026)
- [Think While You Map: Asynchronous Vision-Language Agents for Incremental 3D Scene Graphs](https://mlsanity.com/paper/2606.31471/) (2026)

## Abstract (arXiv)

Open-vocabulary 3D scene graphs provide compact semantic memory for language-guided navigation, but mapped objects are often exposed through a single fused feature or committed semantic label. Such commitment can remove minority yet task-relevant hypotheses from the task-time interface. We present OpenBelief-Nav, an evidence-preserving object memory that retains observation-level phrases, reliability cues, and frame-mask provenance while maintaining separate aggregate geometric and visual representations. Semantically related phrases are consolidated into a vocabulary-independent object belief from which task-specific readouts perform fixed-vocabulary projection or free-form retrieval. On five ScanNet200 and eight Replica scenes, full-belief projection achieves mIoU scores of 0.2742 and 0.2912, compared with 0.2393 and 0.2701 for a matched early-commit readout. Across 78 HM3D-YCB navigation trials, consensus and early-commit retrieval each achieve 60/78 successes, compared with 58/78 for belief-weighted retrieval and 55/78 for DualMap. Across 20 Unitree G1 runs organized as 10 matched evaluation cases, a correction policy permitting at most two verified candidate attempts improves target-confirmation success from 6/10 to 8/10 relative to top-1-only execution. Code will be released upon acceptance at https://openbelief-nav.github.io/.