# Nav-R2 Dual-Relation Reasoning for Generalizable Open-Vocabulary Object-Goal Navigation

arXiv: https://arxiv.org/abs/2512.02400 · HTML: https://mlsanity.com/paper/2512.02400/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 34 references that are in the map.
- First posted on arXiv 2 Dec 2025.

## Builds on (most cited first, 29 of 29)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model](https://mlsanity.com/paper/2207.07115/) (2022)
- [Video Object Segmentation using Space-Time Memory Networks](https://mlsanity.com/paper/1904.00607/) (2019)
- [Object Goal Navigation using Goal-Oriented Semantic Exploration](https://mlsanity.com/paper/2007.00643/) (2020)
- [Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigation](https://mlsanity.com/paper/1811.10092/) (2018)
- [Touchdown: Natural Language Navigation and Spatial Reasoning in Visual Street Environments](https://mlsanity.com/paper/1811.12354/) (2018)
- [VLFM: Vision-Language Frontier Maps for Zero-Shot Semantic Navigation](https://mlsanity.com/paper/2312.03275/) (2023)
- [MemoryVLA: Perceptual-Cognitive Memory in Vision-Language-Action Models for Robotic Manipulation](https://mlsanity.com/paper/2508.19236/) (2025)
- [ZSON: Zero-Shot Object-Goal Navigation using Multimodal Goal Embeddings](https://mlsanity.com/paper/2206.12403/) (2022)
- [Uni-NaVid: A Video-based Vision-Language-Action Model for Unifying Embodied Navigation Tasks](https://mlsanity.com/paper/2412.06224/) (2024)
- [Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion](https://mlsanity.com/paper/2103.07941/) (2021)
- [Video Object Segmentation with Episodic Graph Memory Networks](https://mlsanity.com/paper/2007.07020/) (2020)
- [Kernelized Memory Network for Video Object Segmentation](https://mlsanity.com/paper/2007.08270/) (2020)
- [MAST: A Memory-Augmented Self-supervised Tracker](https://mlsanity.com/paper/2002.07793/) (2020)
- [Video Object Segmentation with Adaptive Feature Bank and Uncertain-Region Refinement](https://mlsanity.com/paper/2010.07958/) (2020)
- [Learning to Learn How to Learn: Self-Adaptive Visual Navigation Using Meta-Learning](https://mlsanity.com/paper/1812.00971/) (2018)
- [NavCoT: Boosting LLM-Based Vision-and-Language Navigation via Learning Disentangled Reasoning](https://mlsanity.com/paper/2403.07376/) (2024)
- [HM3D-OVON: A Dataset and Benchmark for Open-Vocabulary Object Goal Navigation](https://mlsanity.com/paper/2409.14296/) (2024)
- [SwiftNet: Real-time Video Object Segmentation](https://mlsanity.com/paper/2102.04604/) (2021)
- [Fast Video Object Segmentation using the Global Context Module](https://mlsanity.com/paper/2001.11243/) (2020)
- [Learning Position and Target Consistency for Memory-based Video Object Segmentation](https://mlsanity.com/paper/2104.04329/) (2021)
- [Open-Nav: Exploring Zero-Shot Vision-and-Language Navigation in Continuous Environment with Open-Source LLMs](https://mlsanity.com/paper/2409.18794/) (2024)
- [VoroNav: Voronoi-based Zero-shot Object Navigation with Large Language Model](https://mlsanity.com/paper/2401.02695/) (2024)
- [Move to Understand a 3D Scene: Bridging Visual Grounding and Exploration for Efficient and Versatile Embodied Navigation](https://mlsanity.com/paper/2507.04047/) (2025)
- [Nav-R1: Reasoning and Navigation in Embodied Scenes](https://mlsanity.com/paper/2509.10884/) (2025)
- [CogNav: Cognitive Process Modeling for Object Goal Navigation with LLMs](https://mlsanity.com/paper/2412.10439/) (2024)
- [CL-CoTNav: Closed-Loop Hierarchical Chain-of-Thought for Zero-Shot Object-Goal Navigation with Vision-Language Models](https://mlsanity.com/paper/2504.09000/) (2025)
- [TDANet: Target-Directed Attention Network For Object-Goal Visual Navigation With Zero-Shot Ability](https://mlsanity.com/paper/2404.08353/) (2024)
- [Advancing Visual Large Language Model for Multi-granular Versatile Perception](https://mlsanity.com/paper/2507.16213/) (2025)

## Built on by (most cited first, 10 of 10)

- [ABot-N0: Technical Report on the VLA Foundation Model for Versatile Embodied Navigation](https://mlsanity.com/paper/2602.11598/) (2026)
- [LongFly: Long-Horizon UAV Vision-and-Language Navigation with Spatiotemporal Context Integration](https://mlsanity.com/paper/2512.22010/) (2025)
- [ABot-N1: Toward a General Visual Language Navigation Foundation Model](https://mlsanity.com/paper/2607.10383/) (2026)
- [Explore Like Humans: Autonomous Exploration with Online SG-Memo Construction for Embodied Agents](https://mlsanity.com/paper/2604.19034/) (2026)
- [MerNav: A Highly Generalizable Memory-Execute-Review Framework for Zero-Shot Object Goal Navigation](https://mlsanity.com/paper/2602.05467/) (2026)
- [AsyncShield: A Plug-and-Play Edge Adapter for Asynchronous Cloud-based VLA Navigation](https://mlsanity.com/paper/2604.24086/) (2026)
- [SpatialFly: Implicit 3D Prior-Guided Visual Reparameterization for Continuous UAV Vision-and-Language Navigation](https://mlsanity.com/paper/2603.21046/) (2026)
- [LookStep: Efficient Vision-Language Navigation with Linguistic Foresight and Event Driven Memory](https://mlsanity.com/paper/2609.02350/) (2026)
- [ABot-AgentOS: A General Robotic Agent OS with Lifelong Multi-modal Memory](https://mlsanity.com/paper/2607.10350/) (2026)
- [GG-Nav: Goal-oriented Grounding Chain-of-Thought Elicits Reasoning in Navigation Foundation Models](https://mlsanity.com/paper/2610.14541/) (2026)

## Abstract (arXiv)

Object-goal navigation in open-vocabulary settings requires agents to locate novel objects in unseen environments, yet existing approaches suffer from opaque decision-making processes and low success rate on locating unseen objects. To address these challenges, we propose Nav-R2, a framework that explicitly models two critical types of relationships, target-environment modeling and environment-action planning, through structured Chain-of-Thought (CoT) reasoning coupled with a Similarity-Aware Memory. We construct a NavR2-CoT dataset that teaches the model to perceive the environment, focus on target-related objects in the surrounding context and finally make future action plans. Our SA-Mem preserves the most target-relevant and current observation-relevant features from both temporal and semantic perspectives by compressing video frames and fusing historical observations, while introducing no additional parameters. Compared to previous methods, Nav-R2 achieves state-of-the-art performance in localizing unseen objects through a streamlined and efficient pipeline, avoiding overfitting to seen object categories while maintaining real-time inference at 2Hz. Resources will be made publicly available at hrefhttps://github.com/AMAP-EAI/Nav-R2github link.