idw – Informationsdienst Wissenschaft
Nachrichten, Termine, Experten
Nachrichten, Termine, Experten
Researchers from the Technical University of Munich (TUM) are developing a harvesting robot for asparagus. They programmed a prototype that detects and localizes ripe green asparagus, moving at a commercially attractive speed. Further testing is planned to develop the harvest ability of the robot.
Asparagus is one of the most labor-intensive crops on the market. Especially the harvest is very demanding for precision – the terrain is uneven, and the stalks are thin and of varying length. These challenges inhibit automation, leading to currently available harvesting robots being too slow and inefficient.
Researchers at TUM have developed a robot prototype that can maneuver quickly across an asparagus field and identify and locate ripe green asparagus.
Robot identifies and localizes asparagus
Several pictures from mounted cameras must be processed to identify the asparagus spears correctly. These pictures feed the robotic actuator which can harvest the asparagus. The robot must consider that it is moving and that the relative position of the asparagus to the robot changes in the time between the localization and harvesting process.
The presented prototype successfully completes these first few steps of the process; with the mounted cameras and the algorithms, the robot can identify and localize the asparagus spears, all while moving at a speed that is commercially attractive. “We see big opportunities for asparagus harvesting robotics worldwide,” says Timo Oksanen, Professor for Agrimechatronics at TUM.
Commercially competitive speed
Prior to designing this prototype, the researchers calculated that the robot should move at a speed of at least 0.33 meters per second to be commercially attractive. The presented prototype can move at up to 0.8 meters per second in uneven and up to 1 meter per second in even terrain. With this speed and simultaneous identification and localization of the asparagus stalks, the prototype exceeds current market standards.
In the next step, the detection algorithms will be improved in further tests. “When we have further optimized the detection, we will work on the harvesting algorithm and robotic feature.” says Andreas Neubauer, who has developed the robot.
Andreas Neubauer
Technical University of Munich
Professorship of Agrimechatronics
andreas.neubauer@tum.de
Andreas Neubauer, Peter Buckel, Timo Oksanen, Novel Dataset of RGB-D Images for Robotic Harvesting of Green Asparagus, IFAC-PapersOnLine, Volume 59, Issue 23, 2025, ISSN 2405-8963, https://doi.org/10.1016/j.ifacol.2025.11.822
https://The Professorhip of Agrimechatronics is part of the TUM School of Engineering and Design and the TUM School of Life Sciences.
https://www.ed.tum.de/en/ed/home-1/ (TUM School of Engineering and Design)
https://www.ls.tum.de/en/ls/home/ (TUM School of Life Sciences)
https://The Professorship is also part of the Munich Institute for Robotics and Machine Intelligence (MIRMI) and the World Agricultural Systems Center - Hans Eisenmann-Forum (HEF).
Criteria of this press release:
Journalists, Scientists and scholars, all interested persons
Environment / ecology, Nutrition / healthcare / nursing, Zoology / agricultural and forest sciences
transregional, national
Research results, Scientific Publications
English
You can combine search terms with and, or and/or not, e.g. Philo not logy.
You can use brackets to separate combinations from each other, e.g. (Philo not logy) or (Psycho and logy).
Coherent groups of words will be located as complete phrases if you put them into quotation marks, e.g. “Federal Republic of Germany”.
You can also use the advanced search without entering search terms. It will then follow the criteria you have selected (e.g. country or subject area).
If you have not selected any criteria in a given category, the entire category will be searched (e.g. all subject areas or all countries).
