# EA-Nav: Learning Safe Visual Navigation Policies with Embodiment Awareness

arXiv: https://arxiv.org/abs/2607.19880 · HTML: https://mlsanity.com/paper/2607.19880/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 44 references that are in the map.
- First posted on arXiv 22 Jul 2026.

## Builds on (most cited first, 23 of 23)

- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders](https://mlsanity.com/paper/2301.00808/) (2023)
- [Depth Anything 3: Recovering the Visual Space from Any Views](https://mlsanity.com/paper/2511.10647/) (2025)
- [NoMaD: Goal Masked Diffusion Policies for Navigation and Exploration](https://mlsanity.com/paper/2310.07896/) (2023)
- [MegaSaM: Accurate, Fast, and Robust Structure and Motion from Casual Dynamic Videos](https://mlsanity.com/paper/2412.04463/) (2024)
- [ViPE: Video Pose Engine for 3D Geometric Perception](https://mlsanity.com/paper/2508.10934/) (2025)
- [Rapid Exploration for Open-World Navigation with Latent Goal Models](https://mlsanity.com/paper/2104.05859/) (2021)
- [GRUtopia: Dream General Robots in a City at Scale](https://mlsanity.com/paper/2407.10943/) (2024)
- [Deep Visual MPC-Policy Learning for Navigation](https://mlsanity.com/paper/1903.02749/) (2019)
- [TartanDrive: A Large-Scale Dataset for Learning Off-Road Dynamics Models](https://mlsanity.com/paper/2205.01791/) (2022)
- [NavDP: Learning Sim-to-Real Navigation Diffusion Policy with Privileged Information Guidance](https://mlsanity.com/paper/2505.08712/) (2025)
- [WMNav: Integrating Vision-Language Models into World Models for Object Goal Navigation](https://mlsanity.com/paper/2503.02247/) (2025)
- [Rethinking the Embodied Gap in Vision-and-Language Navigation: A Holistic Study of Physical and Visual Disparities](https://mlsanity.com/paper/2507.13019/) (2025)
- [ExAug: Robot-Conditioned Navigation Policies via Geometric Experience Augmentation](https://mlsanity.com/paper/2210.07450/) (2022)
- [Learning to Drive Anywhere with Model-Based Reannotation](https://mlsanity.com/paper/2505.05592/) (2025)
- [GND: Global Navigation Dataset with Multi-Modal Perception and Multi-Category Traversability in Outdoor Campus Environments](https://mlsanity.com/paper/2409.14262/) (2024)
- [CE-Nav: Flow-Guided Reinforcement Refinement for Cross-Embodiment Local Navigation](https://mlsanity.com/paper/2509.23203/) (2025)
- [SysNav: Multi-Level Systematic Cooperation Enables Real-World, Cross-Embodiment Object Navigation](https://mlsanity.com/paper/2603.06914/) (2026)
- [Mobile Robot Oriented Large-Scale Indoor Dataset for Dynamic Scene Understanding](https://mlsanity.com/paper/2406.19791/) (2024)
- [WildOS: Open-Vocabulary Object Search in the Wild](https://mlsanity.com/paper/2602.19308/) (2026)
- [i2Nav-Robot: A Large-Scale Indoor-Outdoor Robot Dataset for Multi-Sensor Fusion Navigation](https://mlsanity.com/paper/2508.11485/) (2025)
- [DIV-Nav: Open-Vocabulary Spatial Relationships for Multi-Object Navigation](https://mlsanity.com/paper/2510.16518/) (2025)
- [CeRLP: A Cross-embodiment Robot Local Planning Framework for Visual Navigation](https://mlsanity.com/paper/2603.19602/) (2026)

## Abstract (arXiv)

Cross-embodiment navigation is a key challenge in embodied intelligence. Due to differences in embodiment, the same visual observation may imply different actions for different agents, making prediction ambiguous when relying solely on vision. Existing studies mainly rely on reinforcement learning, which requires large-scale interaction and careful reward design, making it difficult to support scalable pretraining and real-world adaptation. In contrast, imitation-learning-based approaches remain limited. To address these challenges, we propose an imitation-learning-based embodiment-aware navigation framework with a modular multi-stage design. In pretraining, we construct a cross-embodiment navigation dataset from Internet videos and introduce embodiment geometry as conditional tokens to reduce action ambiguity under the same observation. In fine-tuning, we design a multimodal information injection mechanism based on a decoupled architecture. Specifically, we design a trajectory augmentation strategy to generate high-risk samples, which are used to train spatial perception and risk-aware correction separately, thereby explicitly incorporating embodiment geometry for safe navigation. Experimental results show that the proposed method effectively improves navigation performance across different embodiment settings, demonstrating the effectiveness of incorporating embodiment geometry into embodied navigation.