#193193rd of 206 in ML frameworks and librariesFor science, health and research, robotics
internnav
Toolbox for training and evaluating embodied navigation models in Habitat and Isaac Sim
- Stars
- 1.2k
- License
- MIT
- Last commit
- Mar 2026
- Last release
- Feb 2026
- Language
- Jupyter Notebook
816 on 21 Apr 20261,176 on 10 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
InternNav is a PyTorch toolbox for vision-language navigation (VLN-CE, VLN-PE) and visual navigation with point, image or trajectory goals. It runs training and evaluation against Habitat and Isaac Sim, and ships a model zoo of 10+ baselines, including the InternVLA-N1 dual-system navigation model, plus the InternData-N1 dataset. Real-world deployment code for Unitree Go2 is included.
Who it is for: Robotics researchers training and benchmarking vision-language navigation models
Strengths
- Covers VLN-CE, VLN-PE and visual navigation benchmarks with published result tables
- Model zoo includes Seq2Seq, CMA, RDP, NavDP and InternVLA-N1 checkpoints on Hugging Face
- Supports both Habitat and Isaac Sim, with distributed VLN-PE evaluation since v0.2.0
- Training code for InternVLA-N1 and real-world Go2 deployment code are released
Weaknesses
- InternData-N1 dataset is CC BY-NC-SA 4.0, so non-commercial only
- StreamVLN support is listed as coming soon
- Needs Habitat or Isaac Sim setup; no Docker or compose files provided
- README defers installation and hardware requirements to external docs
What it needs
- Needs PyTorch, Habitat, Isaac Sim, InternUtopia
- Models: InternVLA-N1, NavDP, Seq2Seq, CMA, RDP
What changed
From the release notes. No flag means the note does not say so, not that the upgrade is safe.
Also in ML frameworks and libraries
See all 206| Rank | Project | Score |
|---|---|---|
| 1 | transformersPython library defining open models for text, vision, audio and multimodal tasks | 94 out of 100 |
| 2 | ultralyticsPython library and CLI for training and running YOLO vision models | 94 out of 100 |
| 3 | pytorchPython tensor library with GPU support and tape-based autograd | 93 out of 100 |
| #4 | pytorch-image-modelsPyTorch library of image models, pretrained weights and training scripts | 93 out of 100 |
| #5 | supervisionPython toolkit for loading, annotating and counting computer vision detections | 92 out of 100 |