Galactic Navigation System ( GNS ) by KOSASIH is licensed under Creative Commons Attribution 4.0 International

A Git repo for the Galactic Navigation System project, containing code for advanced algorithms for positioning, mapping, and collision avoidance.

This repository contains the codebase for the Galactic Navigation System (GNS), an advanced system for positioning, mapping, and collision avoidance.

Getting Started Dependencies Building Running Documentation Citation Training

These instructions will get you a copy of the project up and running on your local machine for development and testing purposes.

Ensure you have the following installed:

• Git
• CMake
• Python 3.9
• Conda

1. Clone the repository:

1 git clone --recurse-submodules https://github.com/KOSASIH/gns-interstellar.git`

2. Create a conda environment:

1 cd gns-interstellar
2 conda create -n gns python=3.9 cmake=3.22
3 conda activate gns

3. Download and install the Vulkan SDK:

1 mkdir vulkansdk
2 cd vulkansdk
3 wget https://sdk.lunarg.com/sdk/download/1.2.198.1/linux/vulkansdk-linux-x86_64-1.2.198.1.tar.gz
4 tar -xf vulkansdk-linux-x86_64-1.2.198.1.tar.gz
5 source 1.2.198.1/setup-env.sh
6 cd ../

5. Install PyTorch with CUDA 11.0+:

1 conda install pytorch=1.11 pytorch-cuda=11.7 -c pytorch -c nvidia
2 python -c "import torch; print(torch.version.cuda)"

6. Install the required Python packages:

pip install -r requirements.txt

• Vulkan SDK
• PyTorch 1.11 with CUDA 11.0+
• CMake 3.22+

Build the C++ components:

1 mkdir build
2 cd build
3 cmake ..
4 make

Run the Python scripts:

python main.py

The documentation is available in the docs folder. To generate the documentation, run:

1 cd docs
2 make html

The generated documentation will be available in the _build/html folder.

If you use this code in your research, please cite the following:

1 @article{your-paper,
2   title={Your Paper Title},
3   author={Your Name},
4   journal={Journal Name},
5   year={Year},
6   publisher={Publisher},
7   url={https://your-paper-url.com}
8 }

To train the neural network, run:

python train.py

This will train the network using the default settings. You can modify the settings in the train.py file.For more information, refer to the Training Guide