Compass 1: Towards Open-World and Persistent Embodied Navigation from Monocular RGB Videos

Hai Zhang, Siqi Liang, Yanjun Guo, Shoufeng Zhang, Yunhao Wang, Hangyu Du, Haoguang Mai, Hongchen Li, Jiazhi Yang, Jialong Zeng, Yu Hu, Chen Chen, Gangcheng Jiang, Zishun Zhuo, Lirui Zhao, Zhigang Li, Yu Qiao, Zhenjie Yang, Fu Zhang, Hongyang LiarXiv 2026 · arXiv

TL;DR

Compass 1 is a first-of-its-kind embodied navigation foundation model that unifies language reasoning and video generation to achieve persistent spatial awareness. By introducing a "History Representation Map" and a structured VQA supervision protocol, it enables robots to remember and backtrack through nearly two minutes of visual history, achieving a 79.4% success rate in open-world tasks—crushing the 17.8% achieved by the strongest baselines.

What Problem Does This Paper Address?

Most current embodied navigation systems are "short-sighted." They typically only process a handful of recent video frames, leading to a rapid loss of spatial context. This results in several classic failure modes:

  1. The "Goldfish" Effect: Robots forget targets they saw just a minute ago, making history backtracking (returning to a previous point) nearly impossible.
  2. Left-Right Deadlocks: In beyond-the-view exploration, models often get stuck in oscillating turning loops because they don't remember where they just looked.
  3. Fragile Generalization: Models trained in simulation often fail in the messy real world or when moved to a robot with a different camera height (e.g., moving from a tall humanoid to a short wheeled robot).

Compass 1 tackles these by aiming for persistent navigation—the ability to maintain spatial awareness over long horizons using only monocular RGB video.

Methods

The researchers introduced two primary innovations to the standard Vision-Language-Action (VLA) architecture:

1. History Representation Map (HRM)

Instead of flooding the model with every single video frame, Compass 1 uses Action-Guided Keyframe Selection to pick out critical moments. These keyframes and the robot's trajectory are rendered into a 2D visual canvas called the History Representation Map (HRM). This map is fed into the model as a native image input, allowing the backbone to "see" its own past path and landmarks without architectural changes.

The HRM encodes dense spatial topology by projecting keyframes and trajectories onto a 2D image.

2. Structured VQA Supervision

Simply providing a map isn't enough; the model must be taught to use it. The authors introduced a History Utilization protocol using three types of Visual Question Answering (VQA) tasks during training:

  • Task-Stage Grounding: "Which part of the instruction am I doing right now?"
  • Exploration Consistency: "Have I already looked to the left?"
  • Spatiotemporal Target Retrieval: "Which past keyframe showed the target, and where is it relative to me now?"

3. Unified Architecture

Compass 1 uses a unified multimodal backbone (based on Cosmos3-Edge-4B) that features two heads: an autoregressive language head for reasoning/VQA and a diffusion-based video-action head for generating smooth, continuous trajectories.

Datasets

To train a true foundation model, the team built a massive corpus of over 2,500 hours of video:

  • 500+ hours of high-quality, self-collected real-world interactions.
  • 2,000+ hours of annotated web videos (YouTube).

They developed a semi-automated pipeline to label this data, using large models to synthesize instructions and trajectories, with humans only intervening to verify "stage boundaries" and filter out noisy data.

The training data integrates self-collected trajectories with a vast amount of web-scale video.

Key Insights and Ideas

  • The Map is an Image: One of the most elegant insights is treating the navigation map as just another image input. This allows the model to leverage its pre-trained visual reasoning capabilities to understand spatial relationships without needing a custom "map-processing" module.
  • VQA as "Map Activation": The authors found that without the VQA tasks, the model tended to ignore the HRM. The VQA protocol acts as a "map activation mechanism," forcing the model to attend to historical context to answer questions correctly.
  • Height Invariance: Remarkably, training primarily on data from a 1.0m camera height allowed the model to generalize to robots as low as 0.35m (wheeled robots) and as high as 1.5m (drones). This suggests the model has learned a fundamental understanding of 3D space that transcends specific camera placements.

Key Results

Compass 1 demonstrates a "dominant" performance leap over existing SOTA models like AwareVLN and WNM-3D:

  • Overall Success Rate: 79.4% vs. the strongest baseline's 17.8%.
  • History Backtracking (HBN): In tasks requiring the robot to return to a previously seen object, Compass 1 jumped from the baseline's 0% to 58%.
  • Exploration Boost: A 250% improvement in beyond-the-view navigation tasks.
  • Zero-Shot Transfer: The model successfully navigated on four different embodiments (wheeled, quadruped, humanoid, and drone) in diverse environments ranging from quiet offices to busy, pedestrian-dense streets.
Qualitative results show Compass 1 successfully executing complex, multi-stage instructions across different robot types.

Limitations and Future Work

While Compass 1 is a major step forward, the authors note some remaining challenges:

  • Persistent Backtracking: While 58% is an "unparalleled leap," it is still lower than the success rates for simpler tasks. Occlusions during the return path can still cause the robot to lose its heading.
  • Dynamic Jitter: On platforms with high vibration, like drones or humanoids, the "out-of-distribution" visual noise can slightly degrade performance.
  • Future Directions: The team suggests that incorporating more diverse web data and refining the "anchor-and-propagate" grounding strategy could further improve the model's robustness in highly cluttered or dynamic scenes.

Summary updated

Abstract

Embodied navigation requires agents to achieve persistent spatial awareness and long-horizon execution stability in open-world environments. However, existing navigation architectures struggle to sustain both capabilities, remaining effective only over a handful of recent frames. We present Compass 1, the first embodied navigation foundation model to unify language understanding and video generation while enabling memory backtracking through nearly 2mins of visual history. Without altering the underlying architecture, we introduce History Representation, which integrates sparse visual keyframes with an explicit History Representation Map to preserve long-term spatiotemporal context. To effectively leverage this history, we further introduce History Utilization, a structured VQA supervision protocol comprising three categories: task-stage grounding, exploration consistency, and spatiotemporal target retrieval, enabling map-grounded reasoning and stable persistent long-horizon navigation. To fuel this system, we establish a complete annotation pipeline for monocular RGB videos and open-source a massive dataset featuring over 500 hours of high-quality real-world interactions and over 2,000 hours of annotated web videos. Trained mainly on the distribution of 1m height camera, Compass 1 generalizes seamlessly across diverse embodiments and scenarios, ranging from indoor environments to pedestrian-dense streets, spanning wheeled robot at 0.35m, quadruped dog at 0.5m, humanoid at 0.85m, and aerial drone at 1.5m. Compass 1achieves a dominant overall success rate of 79.4% across open-world evaluations, compared to 17.8% for the strongest baseline. It demonstrates exceptional zero-shot execution exceeding 90% on foundational tasks, a 250% boost in exploration, and an unparalleled leap from 0% to 58% in challenging persistent history backtracking.
BibTeX
@misc{zhang2026compass,
  author = {Hai Zhang and Siqi Liang and Yanjun Guo and Shoufeng Zhang and Yunhao Wang and Hangyu Du and Haoguang Mai and Hongchen Li and Jiazhi Yang and Jialong Zeng and Yu Hu and Chen Chen and Gangcheng Jiang and Zishun Zhuo and Lirui Zhao and Zhigang Li and Yu Qiao and Zhenjie Yang and Fu Zhang and Hongyang Li},
  title = {{Compass 1: Towards Open-World and Persistent Embodied Navigation from Monocular RGB Videos}},
  year = {2026},
  eprint = {2611.12087},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2611.12087},
}
Figure