Advanced methods for image processing and robotisation allow companies in the agro-food sector to make huge savings on labour-intensive and time-consuming manual work.
While robots are common practice in the automotive industry, the agro-food sector still uses lots of manual labour. An important reason for this is that food products come in a wide variety: No two apples are exactly the same. This makes it difficult for robots to perform sensory analyses of the products in order to replace the manual labour in agro-food processes. Wageningen Food & Biobased Research has substantial experience in developing methods for image processing and controlling robots in agro-food processes.
Pick and place of vine tomatoes
With its knowledge of vision guided robotics, Wageningen Food & Biobased Research developed an extensive portfolio. Within the EU project PicknPack, for example, we worked with Wageningen Greenhouse Horticulture to develop a fully automated solution for picking vine tomatoes from harvesting crates and placing them in their packaging. Based on camera images, we analyse the vines and determine the 3D location and orientation for grasping by the robot.
Wageningen Food & Biobased Research also developed a technology for determining the cutting points of roses for the automated cutting of rose slips. This is based on a 3D reconstruction of the rose branches. Based on the cutting points we steer the robot to make the cuttings.
Sorting tomato seedlings
A third example is the sorting of tomato seedlings. Using multiple cameras, we make a 3D analysis of the structure of the plant, which enables us to determine its quality based on which the plants can be sorted automatically.