Documentation

Topic	Link
Getting Started	Getting Started
Using the Simulator	Using the Simulator
Using Vehicles	Using Vehicles
Using Walkers	Using Walkers
Sensors	Sensors
Setupping sensors	Setupping sensor
Creating own levels	Creating own levels
Building from source on Linux	Building on Linux
Building from source on Windows	Building on Windows
Installing on Linux	Installing on Linux
Installing on Windows	Installing on Windows

AGRARSENSE Simulator

AGRARSENSE simulator has been developed from the ground up to support the development, training, and validation of autonomous driving and safety systems for forestry. It serves as a versatile tool, primarily designed for two key functions: real-time simulation and data collection.

The simulator is built on Unreal Engine 5 and the simulator includes several sensors such as RGB camera, Depth Camera, Radar and Lidar to name a few. See sensors documentation for more information about the sensors. The simulator also includes high quality forest assets, maps and vehicles.

The simulator uses MIT licenced ROSIntegration plugin to communicate data in and out of the simulator. When ROS is active, the simulator sends all sensor data into their own ROS topics where it can be accessed through variety of tools and programming languages. The simulator also supports ROS2 via ROS1 <--> ROS2 bridge.

AGRARSENSE Project

AGRARSENSE is a large 3-year KDT Joint Undertaking consortium project aiming to develop microelectronics, photonics, electronic packaging for agricultural use and forestry. The project will also develop related ICT and data management to realise large scale field demonstrators for real industrial needs.

See more at:

Agrarsense website

The simulator is developed by FrostBit Software Lab which is one of the research, development and innovation groups at Lapland University of Applied Sciences.

FrostBit Software Lab website

FrostBit AGRARSENSE portfolio page

Lapland UAS website

System Recommendation

Intel i7 / Intel i9 9th or newer / AMD Ryzen 7 / AMD Ryzen 9
16+ GB RAM or more
NVIDIA RTX 3070/3080 or newer / AMD RX 6700 XT or newer
150+ GB disk space for source version
Ubuntu 20.04 / Windows 10 / Windows 11

Note 1. The simulator, including ROS might work on Ubuntu 18.04 but this has not been tested.

Note 2. The simulator (Unreal project) should work on Ubuntu 22.04, however Ubuntu 22.04 doesn't support ROS noetic which is required for the ROS to work.

Repositories

Simulator repository - Contains the full simulator source code with all the assets.

"Art" repository - Contains all 2D and 3D assets made/used in the simulator.

Custom ROS messages repository - Contains custom ROS1 and ROS2 message types.

Project Structure

AGRARSENSE Simulator project structure is as follows:

├── AGRARSENSE [root]
    └── Data (Created when simulator is launched)
        ├── All data saved from the Simulator
    └── Docs
        ├── All documentation files
    └── Examples
        └── ExamplesJsonFiles
        └── ROS1
        └── ROS2
    └── Utils
        ├── Build scripts for Agrarsense unreal project
    └── Unreal
        └── Agrarsense [Unreal project files]
            └── Content
                ├── All blueprints, models and other assets
            └── Plugins
                ├── Plugins C++ source
            └── Source
                ├── Agrarsense simulator C++ source

Modifying AGRARSENSE Source

When modifying Blueprints or Widget Blueprints in Unreal Editor, simply click compile and save in the Unreal Editor as in with any Unreal project.

When modifying AGRARSENSE C++ source or plugins C++ source, you must close the Unreal Editor, re-compile C++ and then open the Unreal Editor again or else changes will not take effect. Unreal Engine does support compiling C++ in Unreal Editor through Live Coding but your experience may vary.

To compile and open the Unreal Editor open terminal in Agrarsense ROOT/Unreal/Agrarsense location and type:

# Windows
OpenProject.bat
 
# Linux
./LinuxOpenProject.sh

To just compile C++ source and plugins

# Windows
Compile.bat
 
# Linux
./LinuxCompile.sh

Compiling in Visual Studio

# Windows only

Open Agrarsense.sln with Visual Studio, right click Agrarsense in the Solution Explorer and click Build.

## Licenses

Lapland UAS (FrostBit Software Lab) AGRARSENSE specific code is distributed under MIT License.

Lapland UAS (FrostBit Software Lab) AGRARSENSE specific assets such as models and textures are distributed under CC0 License.

AGRARSENSE Dependency and Integration licenses

Unreal Engine 5 follows its own license terms.

AGRARSENSE dependencies & plugins:

ROSIntegration which is Unreal Engine Plugin to enable ROS Support. MIT open source license.
Parts of the sensor code is adapted from MIT-licenced CARLA Simulator.

Table of Contents