AI4Forest is a virtual environment created in Unreal Engine 5 (UE5) designed for training and testing robotic navigation algorithms in a realistic forest setting. The environment includes detailed terrain generated from real-world elevation data, vegetation, rocks, and other natural features to simulate the challenges a robot might face in a forested area.
- Realistic forest environment based on Digital Elevation Model (DEM) data.
- Detailed vegetation including trees, grass, and rocks.
- Configured for robotic navigation and traversability analysis.
- Suitable for training AI models in a simulated forest setting.
Before you begin, ensure you have the following:
- A computer running a Linux distribution (Ubuntu 20.04 LTS or later is recommended).
- At least 16 GB of RAM (32 GB recommended for UE5 projects).
- A dedicated GPU with at least 6 GB of VRAM that supports Vulkan (e.g., NVIDIA GTX 1060 or equivalent).
- Git installed for cloning the repository.
- Git LFS (Large File Storage) installed for handling large files.
UE5 is not officially distributed as pre-built binaries for Linux, so you'll need to build it from source. Here's how to install UE5 on Linux:
Open your terminal and install the necessary dependencies:
sudo apt update
sudo apt install build-essential clang lld cmake python3-dev libvulkan1 libvulkan-dev vulkan-toolsFor Ubuntu 22.04 and later:
sudo apt install libxcb-xinerama0 libxcb-xinput0If you haven't already:
sudo apt install git git-lfs
git lfs install
To build Unreal Engine 5 from source, you'll need access to the UE5 repository on GitHub provided by Epic Games. Follow these steps to gain access:
- Go to the Epic Games website and create an account, or log in if you already have one.
- Log in to the Epic Games Developer Portal.
- Follow the instructions to link your GitHub account to Epic Games.
- After linking your GitHub account, you will receive an invitation to join the
EpicGamesorganization on GitHub. - Accept the invitation to gain access to the Unreal Engine repositories.
Once you have access to the repository, you can clone it by running the following command in your terminal:
git clone https://github.com/EpicGames/UnrealEngine.git ~/UnrealEngineNavigate to the UE5 directory and run the setup scripts:
cd ~/UnrealEngine
./Setup.sh
./GenerateProjectFiles.sh
make
Note: The make command will take several hours, depending on your hardware.
After the build completes, you can test the editor:
cd ~/UnrealEngine/Engine/Binaries/Linux
./UnrealEditor
or (for better performance)
./UnrealEditor -vulkanIf the editor launches, you've successfully installed UE5 on Linux.
- Clone the AI4Forest Repository
Navigate to the directory where you want to store the project and clone it using SSH:
git clone [email protected]:khalidbourr/AI4Forest.git
Note: Ensure you have SSH access set up for GitHub.
- Install Git LFS and Pull Large Files
If you haven't installed Git LFS:
sudo apt install git-lfs
git lfs install
Pull the LFS files:
git lfs pull- Verify the Project Files
Ensure that all project files, including .uasset and .umap files, are present. Running the Project
- Open Unreal Engine Editor
Launch UE5:
cd ~/UnrealEngine/Engine/Binaries/Linux
./UnrealEditoror (for better performance)
./UnrealEditor -vulkan-
Open the AI4Forest Project
In the Unreal Editor, click on "Browse" and navigate to the cloned AI4FOREST project directory. Select the AI4FOREST.uproject file and open it.
-
Wait for Asset Compilation
The first time you open the project, UE5 may need to compile shaders and load assets. This can take some time. 4. Explore the Environment
Go to File --> Open Level --> Landscape
Use the viewport to navigate around the forest environment. Play the scene by clicking on the "Play" button to test any interactive elements.
