Skip to main content

01.03.2018 | Production + Production Technology | News | Onlineartikel

Lightweight Robots Harvest Cucumbers

Not only automation-intensive industries such as the automotive industry depend on robots, but automation systems are increasingly replacing laborious manual work in agriculture as well: As part of the EU's CATCH project, the Fraunhofer IPK is developing a dual-arm robot for the automated harvesting of cucumbers.

While harvesting, the seasonal workers usually lie flat on their stomach on agricultural machines and pick the cucumbers by hand. This labour-intensive and energy-sapping type of manual harvesting is increasingly becoming uneconomical. Researchers at Fraunhofer Institute for Production Systems and Design Technology IPK are studying the potential for automating cucumber harvests as part of the EU project CATCH (Cucumber Gathering – Green Field Experiments). Project partners are the Leibniz Institute for Agricultural Engineering and Bioeconomy (ATB, Argrartechnik und Bioökonomie) in Germany and the CSIC-UPM Centre for Automation and Robotics in Spain.

The researchers are aiming to develop an inexpensive dual-arm robot system consisting of lightweight modules that could be used for automated cucumber harvesting and other agricultural applications. The robotic picker is expected to be inexpensive, efficient, reliable and capable of identifying and picking ripe cucumbers even in adverse weather conditions. Modern control methods equip the robot with tactile perception and enable it to adapt to ambient conditions. Multispectral cameras and intelligent image processing are designed to help locate the cucumbers and guide the robot’s gripper arms to the right position. A special camera system developed by the Spanish project partner CSIC-UPM ensures a high success rate of around 95 percent.

Searching in a human way

The IPK project experts have to develop three gripper prototypes: one based on vacuum technology, a set of bionic gripper jaws (Fin Ray) and a modified "cucumber hand" based on the OpenBionics robot hand. Preprogrammed behavioural patterns are designed to allow the robot to look for cucumbers with two hands like a human would: "The robot can, for example, push leaves to the side using symmetrical or asymmetrical movements, or congruent and incongruent movements. As a result, it can automatically change directions on the fly to approach and then grasp a cucumber," says Dr. Dragoljub Surdilovic, a scientist at Fraunhofer IPK. The researchers are aiming to create an intelligent control system capable of assigning tasks between the two gripper arms, monitoring cucumber picking and dealing with exceptions.

In July 2017, the Leibniz Institute for Agricultural Engineering and Bioeconomy (ATB) used various types of cucumbers to conduct initial field trials of the robot system at its test site. Since the autumn of 2017, the project partners have been conducting their tests in an ATB greenhouse. Researchers are focusing their investigations on how interference affects the efficiency and robustness of the system. Once testing has been completed, the project partners intend to commercialise the lightweight robot.

Weiterführende Themen

Die Hintergründe zu diesem Inhalt

Das könnte Sie auch interessieren

Premium Partner

in-adhesivesMKVSNeuer Inhalt

BranchenIndex Online

Die B2B-Firmensuche für Industrie und Wirtschaft: Kostenfrei in Firmenprofilen nach Lieferanten, Herstellern, Dienstleistern und Händlern recherchieren.



Künstliche Intelligenz und die Potenziale des maschinellen Lernens für die Industrie

Maschinelles Lernen ist die Schlüsseltechnologie für intelligente Systeme. Besonders erfolgreich ist in den letzten Jahren das Lernen tiefer Modelle aus großen Datenmengen – „Deep Learning“. Mit dem Internet der Dinge rollt die nächste, noch größere Datenwelle auf uns zu. Hier bietet die Künstliche Intelligenz besondere Chancen für die deutsche Industrie, wenn sie schnell genug in die Digitalisierung einsteigt.
Jetzt gratis downloaden!


Die im Laufe eines Jahres in der „adhäsion“ veröffentlichten Marktübersichten helfen Anwendern verschiedenster Branchen, sich einen gezielten Überblick über Lieferantenangebote zu verschaffen.