OmniNav: A Unified Framework for Prospective Exploration and Visual-Language Navigation

🔥 Latest News!!

• February 12, 2026: We release the slow-fast collaboration system inference checkpoint for OVON benchmark.
• December 30, 2025: We release the slow-fast collaboration system inference code for OVON benchmark.
• December 11, 2025: We release the training code as well as the fast system (vision-only) inference code for the R2R, RxR, and OVON benchmarks.

Quickstart

🧰 Installation

Clone the repo:

git clone https://github.com/amap-cvlab/OmniNav.git

Install Training dependencies:

# Ensure torch >= 2.6.0
cd train_code
pip install -r requirements.txt

Install habitat-sim and habitat-lab for inference

r2r&rxr and ovon have different version dependencies.
● habitat-sim
r2r&rxr: git clone https://github.com/facebookresearch/habitat-sim.git && cd habitat-sim && git checkout v0.1.7 
Ovon: git clone https://github.com/facebookresearch/habitat-sim.git && cd habitat-sim && git checkout v0.2.3
pip install -r requirements.txt
python setup.py install --headless
● habitat-lab
r2r&rxr: git clone https://github.com/facebookresearch/habitat-lab && cd habitat-lab && git checkout v0.1.7
ovon: git clone https://github.com/chongchong2025/habitat-lab && cd habitat-lab && git checkout v0.2.3_waypoint
python -m pip install -r habitat-baselines/habitat_baselines/rl/requirements.txt
python -m pip install -r habitat-baselines/habitat_baselines/rl/ddppo/requirements.txt
pip install -e .
cd habitat-baselines
pip install -e .

🎁 Model

Models	Download Link
Visual-only for r2r, rx2 & ovon	ModelScope
Slow-fast collaboration system for ovon	ModelScope

⚡ Inference

● r2r & rxr

● visual_only
cd infer_r2r_rxr
bash eval_r2r.sh
bash eval_rxr.sh

● ovon

● visual_only
cd infer_ovon
bash eval_ovon.sh

● frontier based slow-fast 
cd infer_ovon_slowfast
bash eval_ovon_slowfast

⚡ Training

cd train_code
bash run_train_demo.sh

🏛️ Citation

If you find this repository useful, please consider giving a star ⭐ and citation

@article{xue2025omninav,
  title={OmniNav: A Unified Framework for Prospective Exploration and Visual-Language Navigation},
  author={Xue, Xinda and Hu, Junjun and Luo, Minghua and Shichao, Xie and Chen, Jintao and Xie, Zixun and Kuichen, Quan and Wei, Guo and Xu, Mu and Chu, Zedong},
  journal={arXiv preprint arXiv:2509.25687},
  year={2025}
}

Acknowledgments

Thanks to NaVid, MTU3D, and OVON for open-sourcing the construction of training data and the closed-loop inference code. Their contributions have significantly enriched the open-source community.