Documentation

Topic	Link
Getting Started	Getting Started
Using the Simulator	Using the Simulator
Using Vehicles	Using Vehicles
Using Walkers	Using Walkers
Sensors	Sensors
Creating own maps	Creating own maps
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.

This project has received funding from the KDT Joint Undertaking (JU) under Grant Agreement No. 101095835. The JU receives support from the European Union’s Horizon 2020 research and innovation programme and Sweden, Czechia, Finland, Ireland, Italy, Latvia, Netherlands, Poland, Spain, Norway, Türkiye. AGRARSENSE project has also received funding from the Swiss State Secretariat for Education, Research and Innovation (SERI). The AIFor project, which is related to the AGRARSENSE project, aims to develop these new methods and a virtual environment for autonomous forest machine AI training. The AIFor-project is implemented by Lapland UAS and it’s co-financed by Business Finland.

AGRARSENSE Website

FrostBit Website

Lapland UAS Website

System Recommendation

9th gen Intel i5/i7/i9 or newer / 2nd gen AMD Ryzen 5/7/9 or newer
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

Using the Simulator

See Using the Simulator

Installing pre-packaged version of the simulator

Topic	Link
Installing on Linux	Installing on Linux
Installing on Windows	Installing on Windows

Building simulator from Source

Topic	Link
Building from source on Linux	Building on Linux
Building from source on Windows	Building on Windows

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 are adapted from MIT-licenced CARLA Simulator.

Table of Contents