More efficient processing of harvested products using robotics
After Harvest focuses on automating the harvest and transport process using advanced robotics. The goal is to improve food safety and reduce food waste by minimizing human interaction. The project involves the development of a post-harvest robot that makes the harvesting and transport process more efficient and precise.
Background Use Case 13
Advanced robotics for improved post-harvest processing
Since the start of NXTGEN, VDL ETG Projects, Bosman Van Zaal, and TU Delft have developed a prototype of a buffering and docking system for an autonomous harvesting robot. This system enables continuous processing of harvested products, even at night, and integrates seamlessly into the logistical chain. The robot is equipped with autonomous features such as path recognition and AI-driven navigation. In addition, VBTI developed a model that allows the robot to identify, grade, and sort the fruit on the stem. Through the use of deep learning, the system can automatically perform quality control and optimize the harvesting process.
"With autonomous processing, we increase food safety and reduce waste."
Public summaries Use Case 13
Autonomous path switching
Contribution to the ecosystem and the sector
Less waste and higher quality through automation
Automated processing reduces human error and minimizes product loss during the processing phase. The higher processing capacity and more consistent quality strengthen the competitive position of Dutch greenhouse horticulture in the international market. The technology enables faster and more efficient product handling, resulting in lower production costs and higher yields for growers.
Deliverables Use Case 13
Improved processing through smart technology
Development of an autonomous transport system for harvested crops
Integration of sensors for quality control during processing
Increased processing capacity through faster sorting methods
Improved food safety through precise processing
Real-time quality control using deep learning models
Added value for Human Capital
More knowledge of robot-controlled processing required
The implementation of automated processing requires new skills in robotics, data analysis, and quality management. Growers and operators will need to retrain in calibrating and maintaining robotic systems. Additional expertise in sensor calibration and processing data analysis is necessary to optimize system performance. Furthermore, the use of deep learning technology demands new insights into programming and training AI models for real-time processing.
Contact us
Want to learn more about this project? Get in touch with us via the contact form below — we’d be happy to tell you more.