WeedElec: a robotic research platform for individual weed detection and selective electrical weeding

Florent Abdelghafour (1) , Florian Rançon (1) , Shiyu Liu (1) , Julien Champ (2) , Vincent de Rudnicki (1) , Christophe Guizard (1) , Hervé Goëau (3, 4) , Claude Doussan (5) , Alexis Joly (2) , Pierre Bonnet (3, 4) , Gilles Rabatel (1)

1 UMR ITAP - Information – Technologies – Analyse Environnementale – Procédés Agricoles
2 ZENITH - Scientific Data Management
3 UMR AMAP - Botanique et Modélisation de l'Architecture des Plantes et des Végétations
4 Cirad-BIOS - Département Systèmes Biologiques
5 EMMAH - Environnement Méditerranéen et Modélisation des Agro-Hydrosystèmes

The project ‘WeedElec’ aims at developing a robotic intra-row weeding solution based on a high-voltage selective electrocution. It performs the following tasks: weed detection and location, positioning of the weeding probe according to location results and electrical destruction of weeds. The detection is achieved using an RGB camera associated with the deep-learning solution of the ‘Pl@ntNet’ team. Discrimination results between crops and weeds attained 76% accuracy for maize and 62% for beans (field trials). Mortality rates weeds ranged from 75% (Polygonaceae) to 13% (Brassicaceae) for plants less than one month old (laboratory conditions). Survivors were nevertheless impacted with a severe limitation of their growth.

Mots clés: robotic; selective weeding; electrical weeding; deep learning; robotic

Domaines: Sciences de l'ingénieur [physics]

Florent Abdelghafour, Florian Rançon, Shiyu Liu, Julien Champ, Vincent de Rudnicki, et al.. WeedElec: a robotic research platform for individual weed detection and selective electrical weeding. EPCA 2021 - 13th European Conference on Precision Agriculture, Jul 2021, Budapest, Hungary. pp.695-702, ⟨10.3920/978-90-8686-916-9_83⟩. ⟨hal-03325689⟩