Plant Soil Environ., 2025, 71(11):782-792 | DOI: 10.17221/335/2025-PSE

A comparative applied analysis of six robotic-assisted weeding systems in sugar beetsOriginal Paper

Sonja I. Kimmel ORCID...¹, Matthias Schumacher ORCID...¹, Michael Spaeth ORCID...¹, Markus Sökefeld¹, Oyebanji O. Alagbo ORCID...², Alicia Allmendinger ORCID...¹, Dionisio Andujar ORCID...³, Therese W. Berge ORCID...⁴, Reiner Braun ORCID...⁵, Sergiu Cioca Parasca ORCID...⁶, Jessica Emminghaus¹, Ioannis Glykos ORCID...⁷, Pavel Hamouz ORCID...⁸, Adam Hruška ORCID...⁸, Michael Merkle ORCID...¹, Georg Naruhn ORCID...¹, Gerassimos G. Peteinatos ORCID...⁷, Bahadir Sin ORCID...⁹, Roland Gerhards ORCID...¹

¹ Weed Science Department, Faculty of Agricultural Science, University of Hohenheim, Stuttgart, Germany

² Department of Crop Production and Protection, Faculty of Agriculture, Obafemi Awolowo University, Ile-Ife, Nigeria

³ CSIC – Centre for Automation and Robotics, Madrid, Spain

⁴ Department of Invertebrate Pests and Weeds in Forestry, Agriculture and Horticulture, Norwegian Institute of Bioeconomy Research (NIBIO), Ås, Norway

⁵ Reutlingen University, Herman Hollerith Centre (HHZ), Reutlingen, Germany

⁶ USAMV – University of Agricultural Sciences and Veterinary Medicine, Cluj-Napoca, Romania

⁷ Department of Natural Resources and Agricultural Engineering, Agricultural University of Athens, Greece; Soil and Water Resources Institute, Hellenic Agricultural Organisation – DIMITRA, Athens, Greece

⁸ CULSP, Czech University of Life Sciences Prague, Prague, Czech Republic

⁹ Sakarya University of Applied Science, Sakarya, Turkey

Effective weed management is crucial in the critical period of sugar beet production, but often lacks sustainability and environmental protection. Recent advancements in sensor-based weed control systems have rendered the latter a realistic prospect, which demands detailed analyses, especially under suboptimal field conditions. The present study analysed six robotic-assisted weed control systems (RAWS) in three experiments on sugar beets in 2024, conducted under dry soil and high weed pressure. The experiments included sensor-based inter-row and intra-row hoeing, spot- and band-spraying and were compared to a broadcast herbicide treatment and an untreated control. Weed control efficacy (WCE) in the intra- and inter-row areas, as well as weed species composition and crop plant damage, were assessed after treatment. The data show that intra-row WCE of two hoeing robots (Farming GT® and Robovator®) equipped with selective intra-row blades achieved up to 80%, which was higher than the broadcast herbicide control with 67% WCE. In the inter-row area, Farming GT® robotic hoeing and ARA® spot-spraying resulted in more than 90% WCE, which was equal to the broadcast herbicide application. Weed species composition was not affected by the different RAWS. Crop plants were affected by all hoeing treatments with maximum non-lethal burial rates of 33%. The highest lethal uprooting of crop plants occurred after Farming GT® robotic hoeing, at 5.5% overall. The results demonstrate the great potential of robotic weeding to replace broadcast herbicide applications.

Keywords: weeding robots; plant detection; sensor technologies; artificial intelligence; precision farming

Received: July 28, 2025; Revised: October 6, 2025; Accepted: October 13, 2025; Prepublished online: November 26, 2025; Published: November 28, 2025  Show citation