In the heart of the Netherlands, a quiet revolution is taking place in the world of pointed pepper production. Gearbox, a leading agritech company, has developed a sophisticated sorting robot for sweet pointed peppers, in collaboration with Frestia, a member of the Harvest House cooperative. This project, part of the NPPL-R program, aims to integrate this innovative technology into Frestia’s production environment, optimizing business operations and addressing critical labor challenges.
Sorting and packaging pointed peppers is a labor-intensive process, traditionally relying heavily on human labor for quality control and flexible packaging formats. “Individually assessing and sorting pointed peppers according to different quality requirements and packaging formats makes the process very labor-intensive,” says Simone Keijzer of Gearbox. The development of this sorting robot was sparked by the success of a similar project for snack peppers, raising the question: could the same innovation be applied to pointed peppers?
Frestia, a year-round grower of snack peppers, sweet pointed peppers, and mini truss tomatoes, has been grappling with the labor-intensive nature of pepper sorting. “Because this is a labor-intensive process and it’s becoming increasingly difficult to find good workers, we started looking for ways to automate this manual work about five years ago,” says Patrick Franken of Frestia. The migrant labor issue has further intensified the need for automation, making robotization not just a solution but an absolute necessity.
The sorting robot developed by Gearbox is a marvel of modern technology. It features four lines, each consisting of two robots, working in tandem to sort peppers based on quality and weight. The process begins with emptying the crates and singulating the peppers. Using vision technology and artificial intelligence (AI), the system determines the weight and quality of each pepper, which is then used to control the robots. The first robots in the line remove Class 2 peppers, make certain weight selections, and place the peppers onto a patented sorting disk. The second set of robots assembles the correct weight combinations, collaborating with each other to produce sets of 2, 3, 4, or 5 peppers based on weight and quality.
The system has undergone extensive testing at Gearbox’s development site, and it’s now time for practical trials. Long-duration stress tests are being conducted to simulate real-world use and eliminate any remaining faults. The robot’s capacity is 12,000 pieces per hour, and these tests are crucial to ensure the machine can run for twenty hours straight without overheating or malfunctioning. “The machine must integrate 100% reliably into our production process—we have no time for ‘adventures,’” Franken emphasizes.
A crucial phase has now begun to objectively demonstrate the sorting robot’s performance. Neutral technicians are involved to validate the process, ensuring that the machine can meet the stringent requirements of Frestia’s production environment. “It’s great for us that the grower’s cooperative and the grower can get extra support from Wageningen University & Research (WUR) during this crucial phase,” Keijzer adds.
Defining and implementing quality guidelines is a critical aspect of this project. WUR researcher Menno Sytsma works on various robotics projects to implement technical solutions in fresh produce production. “From a technical perspective, a lot is possible in terms of 0s and 1s, but you need guidelines—such as for quality—that must be translated into a well-functioning robot,” Sytsma explains. The challenge lies in translating human quality assessments into precise, consistent machine operations. “Humans don’t always see the smallest details, and that’s taken into account. We expect the robot to detect details more consistently,” Sytsma says.
Through the NPPL-R program, WUR can independently and transparently assess the status of this technology. Analyses of the business case, product quality assessment, and technical support can help improve customer acceptance of these technologies. “We weren’t involved in the sorting robot’s development, but the parties appreciate having an independent party involved,” says Sytsma. WUR will independently validate the sorting robot’s performance in terms of product quality compared to the current manual process, ensuring that the technology meets the high standards set by Frestia and Harvest House.
The project also involves technical support for a quality control tool. “We’re checking whether we can clearly define the quality requirements for both parties, which are essential for a well-functioning sorting robot,” Sytsma explains. The grower emphasizes that interpreting quality correctly is key for setting the machine parameters. Sytsma adds: “We also want to connect machine data—which we don’t yet have—to the business management system to ensure proper integration into business and work processes. There may be bottlenecks here that we’ll need to solve.”
Franken believes that robotization is not only a solution but an urgent necessity