Agriculture

Digital Orchard

OnePlanet is developing technology for autonomous pruning robots, essential due to labor shortages in the fruit sector.

Autonomous management of fruit orchards

Robotization of fruit growing focuses primarily on labor-intensive tasks such as fruit picking, tree pruning or blossom thinning. It can be particularly challenging to work in an orchard because of the complexity of the environment, where the fruit is often hidden behind leaves and not immediately visible. The latest orchards are being designed and planted to be suitable for future robotization. Within the “Digital Orchard” research program, OnePlanet uses LiDAR technology to create a three-dimensional digital copy of fruit trees in an orchard. Researchers make scans of all individual trees, down to the level of branches. That produces accurate 3-D models that form the basis for a digital twin of the orchard. The models can be used to train robots to work in the orchard. By digitally tracking the growth of the trees, the robotic systems will soon know, for example, exactly which branches to prune for the best harvest, and when.

LiDAR scanners and stereo cameras.

OnePlanet uses LiDAR technology to map tree structures. The photonic technology LiDAR is also known from self-driving cars. LiDAR can use laser light to measure the distance to a given object and form a 3D image via scans. This allows a pruning robot in fruit farming to position itself properly and handle pruning shears correctly. These 3D reconstructions form the basis for recognizing structures and abnormalities (fruit, leaf, blossom, branches, insects) and for teaching tasks (picking, pruning, thinning, spraying) to future robotic systems.

Digital twin of the orchard

The data and images are combined with knowledge of plant models and form the basis for building a digital orchard (a digital twin). They can also be used for educational purposes in VR applications, where the user can practice and learn tasks in a 3D virtual environment. Future robotic tasks OnePlanet is working on include autonomous pruning of fruit trees (apple and red currant bushes) and better recognition of diseases and insect pests in pears.

Application-oriented research with robotics

In addition to technical feasibility, the future acceptance and implementation of robots in future cultivation systems require careful choices regarding practical applicability, safety and ultimate cost. By seeking appropriate partnerships, OnePlanet seeks to ensure these practical conditions in its research and development activities.

1

insects analyzed with hyperspectral camera

1

GB of raw data collected in orchards (2024)

1

3D scans of apple trees in Randwijk

3500

meter driven with sensor setup

Interested in a
collaboration?

Creativity connects! We love working together and are happy to connect with companies, students, teachers, professionals and organisations. Let’s explore how we can increase our impact together.