In this column , Colinda de Beer , Senior Business Developer Horticulture at InnovationQuarter , writes about the route to custody - gratis yield of greenhouse crop and the need for cooperation between tech developers and agriculturalist . According to De Beer , the majority of flower and vegetable growers in the Netherlands are forward - thinking ship’s company that always desire to appease ahead and need to keep innovating to maintain that pencil lead . Photo credit rating : Colinda de Beer / Innovation OriginsCollaborationBut why should a cultivator place in these kind of technical solutions and why ca n’t a tech medical specialist do it themselves ? consort to De Beer , a major reason for this is that many of the party that have that technical knowledge do not roll in the hay enough about gardening . If you , as a robot detergent builder , are think about developing a harvest robot for tomatoes , for instance , the first question is : For what kind of tomato ? Another important reason is a fiscal one . Companies that have the proficient knowledge and access to horticulture have to deal with hefty developing price . I recently heard a developer say that development up to a working image costs at least 10 million euro . This is not an amount that the average tech developer can pronto afford to ante up . quislingism is therefore essential for working on the proper problem and for bearing the fiscal risk together .
GearRover – AI in the greenhouseProduct developer , as well as entrepreneurs in nursery horticulture , are still search for a room to go about this . Is this actually working anywhere ? Yes , luckily , there are already example where technical school and agriculturalist are figure out very closely and iteratively together to figure out what is need and what is possible . A number of entrepreneurs in the decorative horticulture sphere have teamed up with a tech troupe to develop a harvesting helper . antecedently , a ordered question would have been “ Can you make a golem that can cut rose as well as people can ? ” . However , due to the finish method acting and anatomical structure of a rose crop , this would have been a very complicated task that would have cost a raft of time and money . By examining the entire process , they conjointly came to the conclusion that there would be a great heap to gain if a harvester could be aid to recognize the right ripeness stage . The develop robot ( or rather cobot in this guinea pig ) locate the rose that demand to be harvested , then the employee actually snips it off and puts it on the streetcar . The organization uses vision technology and machine learning to do this .
You could be forgive for recall that the mathematical product is not yet fetch up , devote that it does not harvest rose itself . However , the situation changes when you realize that it fill an employee up to three months to perfectly recognize the right stage for harvest . That right stage has a lot of influence on the shelf aliveness and consequently the quality of a rose . Once you make out that , you then see that it relieve oneself perfect sense to first focalize on a product that simply points towards the rose . Such a merchandise already add a lot of value and can already be sold then . Meanwhile , work is underway to add more functionality , such as a harvest prediction organization and being able to spot diseases base on images that are already collected during the golem ’s work process . To take the complete chromatography column , go to www.innovationoriginis.com .
