Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Official code and checkpoint release for mobile robot foundation models: GNM, ViNT, and NoMaD.
| Date | Stars |
|---|---|
| 2026-07-31 | 1283 |
| 2026-08-02 | 1285 |
| 2026-08-06 | 1285 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# General Navigation Models: GNM, ViNT and NoMaD
**Contributors**: Dhruv Shah, Ajay Sridhar, Nitish Dashora, Catherine Glossop, Kyle Stachowicz, Arjun Bhorkar, Kevin Black, Noriaki Hirose, Sergey Levine
_Berkeley AI Research_
[Project Page](https://general-navigation-models.github.io) | [Citing](https://github.com/robodhruv/visualnav-transformer#citing) | [Pre-Trained Models](https://drive.google.com/drive/folders/1a9yWR2iooXFAqjQHetz263--4_2FFggg?usp=sharing)
---
General Navigation Models are general-purpose goal-conditioned visual navigation policies trained on diverse, cross-embodiment training data, and can control many different robots in zero-shot. They can also be efficiently fine-tuned, or adapted, to new robots and downstream tasks. Our family of models is described in the following research papers (and growing):
1. [GNM: A General Navigation Model to Drive Any Robot](https://sites.google.com/view/drive-any-robot) (_October 2022_, presented at ICRA 2023)
2. [ViNT: A Foundation Model for Visual Navigation](https://general-navigation-models.github.io/vint/index.html) (_June 2023_, presented at CoRL 2023)
3. [NoMaD: Goal Masking Diffusion Policies for Navigation and Exploration](https://general-navigation-models.github.io/nomad/index.html) (_October 2023_)
## Overview
This repository contains code for training our family of models with your own data, pre-trained model checkpoints, as well as example code to deploy it on a TurtleBot2/LoCoBot robot. The repository follows the organization from [GNM](https://github.com/PrieureDeSion/drive-any-robot).
- `./train/train.py`: training script to train or fine-tune the ViNT model on your custom data.
- `./train/vint_train/models/`: contains model files for GNM, ViNT, and some baselines.
- `./train/process_*.py`: scripts to process rosbags or other formats of robot trajectories into training data.
- `./deployment/src/record_bag.sh`: script to collect a demo trajectory as a ROS bag in the target environment on the robot. This trajectory is subsampled to generate a topological graph of the environment.
- `./deployment/src/create_topomap.sh`: script to convert a ROS bag of a demo trajectory into a topological graph that the robot can use to navigate.
- `./deployment/src/navigate.sh`: script that deploys a trained GNM/ViNT/NoMaD model on the robot to navigate to a desired goal in the generated topological graph. Please see relevant sections below for configuration settings.
- `./deployment/src/explore.sh`: script that deploys a trained NoMaD model on the robot to randomly explore its environment. Please see relevant sections below for configuration settings.
## Train
This subfolder contains code for processing datasets and training models from your own data.
### Pre-requisites
The codebase assumes access to a workstation running Ubuntu (tested on 18.04 and 20.04), Python 3.7+, and a GPU with CUDA 10+. It also assumes access to conda, but you can modify it to work with other virtual environment packages, or a native setup.
### Setup
Run the commands below inside the `vint_release/` (topmost) directory:
1. Set up the conda environment:
```bash
conda env create -f train/train_environment.yml
```
2. Source the conda environment:
```
conda activate vint_train
```
3. Install the vint_train packages:
```bash
pip install -e train/
```
4. Install the `diffusion_policy` package from this [repo](https://github.com/real-stanford/diffusion_policy):
```bash
git clone [email protected]:real-stanford/diffusion_policy.git
pip install -e diffusion_policy/
```
### Data-Wrangling
In the [papers](https://general-navigation-models.github.io), we train on a combination of publicly available and unreleased datasets. Below is a list of publicly available datasets used for training; please contact the respective authors for access to the unreleased data.
- [RECON](https://sites.google.com/view/recon-robot/dataset)
- [TartanDrive](https://github.com/Excerpt of 20,337 characters
Read on GitHub
10
6
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:869dda880e12d359, llm:description: 'Official code and checkpoint release for mobile robot foundation models: GNM, ViNT, and NoMaD.' (visual navigation / mobile robot foundation models)
matched fp:869dda880e12d359, llm:description: 'Official code and checkpoint release for mobile robot foundation models: GNM, ViNT, and NoMaD.' (visual navigation / mobile robot foundation models)
matched fp:869dda880e12d359, llm:description: 'Official code and checkpoint release for mobile robot foundation models: GNM, ViNT, and NoMaD.' (visual navigation / mobile robot foundation models)