# NavA3: Understanding Any Instruction, Navigating Anywhere, Finding Anything

arXiv: https://arxiv.org/abs/2508.04598 · HTML: https://mlsanity.com/paper/2508.04598/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Aug 2025.

## Built on by (most cited first, 14 of 14)

- [Multimodal Spatial Reasoning in the Large Model Era: A Survey and Benchmarks](https://mlsanity.com/paper/2510.25760/) (2025)
- [Is your VLM Sky-Ready? A Comprehensive Spatial Intelligence Benchmark for UAV Navigation](https://mlsanity.com/paper/2511.13269/) (2025)
- [VLingNav: Embodied Navigation with Adaptive Reasoning and Visual-Assisted Linguistic Memory](https://mlsanity.com/paper/2601.08665/) (2026)
- [Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation](https://mlsanity.com/paper/2604.18486/) (2026)
- [FutureNav: Unified World-Action Modeling for Vision-and-Language Navigation](https://mlsanity.com/paper/2606.30367/) (2026)
- [Lifelong Embodied Navigation Learning](https://mlsanity.com/paper/2603.06073/) (2026)
- [Structured Observation Language for Efficient and Generalizable Vision-Language Navigation](https://mlsanity.com/paper/2603.27577/) (2026)
- [Uni-LaViRA: Language-Vision-Robot Actions Translation for Unified Embodied Navigation](https://mlsanity.com/paper/2605.27582/) (2026)
- [HyPerNav: Hybrid Perception for Object-Oriented Navigation in Unknown Environment](https://mlsanity.com/paper/2510.22917/) (2025)
- [SEF-MAP: Subspace-Decomposed Expert Fusion for Robust Multimodal HD Map Prediction](https://mlsanity.com/paper/2602.21589/) (2026)
- [All-day Multi-scenes Lifelong Vision-and-Language Navigation with Tucker Adaptation](https://mlsanity.com/paper/2603.14276/) (2026)
- [Weather-Conditioned Branch Routing for Robust LiDAR-Radar 3D Object Detection](https://mlsanity.com/paper/2604.05405/) (2026)
- [Learning to Navigate Socially Through Proactive Risk Perception](https://mlsanity.com/paper/2510.07871/) (2025)
- [VCN-Bench: A Video-Contextualized Navigation Benchmark for Spatial Reasoning over Prior Visual Experience](https://mlsanity.com/paper/2609.34687/) (2026)

## Abstract (arXiv)

Embodied navigation is a fundamental capability of embodied intelligence, enabling robots to move and interact within physical environments. However, existing navigation tasks primarily focus on predefined object navigation or instruction following, which significantly differs from human needs in real-world scenarios involving complex, open-ended scenes. To bridge this gap, we introduce a challenging long-horizon navigation task that requires understanding high-level human instructions and performing spatial-aware object navigation in real-world environments. Existing embodied navigation methods struggle with such tasks due to their limitations in comprehending high-level human instructions and localizing objects with an open vocabulary. In this paper, we propose NavA3, a hierarchical framework divided into two stages: global and local policies. In the global policy, we leverage the reasoning capabilities of Reasoning-VLM to parse high-level human instructions and integrate them with global 3D scene views. This allows us to reason and navigate to regions most likely to contain the goal object. In the local policy, we have collected a dataset of 1.0 million samples of spatial-aware object affordances to train the NaviAfford model (PointingVLM), which provides robust open-vocabulary object localization and spatial awareness for precise goal identification and navigation in complex environments. Extensive experiments demonstrate that NavA3 achieves SOTA results in navigation performance and can successfully complete longhorizon navigation tasks across different robot embodiments in real-world settings, paving the way for universal embodied navigation. The dataset and code will be made available. Project website: https://NavigationA3.github.io/.