Drag

WeedElec – Robotic Agriculture

WeedElec – Robotic Agriculture

WeedElec – Robotic Agriculture

WeedElec – Robotic Agriculture

WeedElec – Robotic Agriculture

WeedElec – Robotic Agriculture

Scroll to explore

WeedElec: Localised weeding robot using high-voltage electrical process

The WeedElec project offers an alternative to overall chemical weed control. It combines aerial weed detection by drone with an ECOROBOTIX delta-arm robot equipped with a high-voltage electric weeding tool. At a time when agro-ecology has become a daily reality for many farmers, WeedElec is providing an innovative, high-performance and eco-responsible solution thanks to precision farming.

©Ecorobotix

The project : Substitution of chemical weeding by high-voltage weeding

WeedElec’s objective is to remove the following major scientific obstacles in particular :

Weed detection and identification using hyper-spectral and colour imagery and associated chemometrics and deep learning techniques.
Combining aerial detection and on-board robot detection to decide whether or not to eliminate weeds.
An in-depth study of the behaviour of weeds exposed to a high-voltage electrical discharge, examining the coupling between the electrical discharge and the complex impedance of weeds with their phenology.

We will also look at the environmental and safety effects associated with the use of electrical discharges on weeds. This study will help us to develop an integrated strategy for safe weed control.

The WeedElec solution: weed detection

Weed detection is a key aspect of WeedElec.
The available resources can be classified into three categories according to the type of information used :

Spatial position of seedlings:
The aim is to detect the seedlings by using the fixed distance that separates them during planting and then to improve their detection around their pre-positioning using algorithms that discriminate between the soil and the vegetation.
Most often, colour or near-infrared image segmentation techniques are used.
Once the seedling is located, everything that will be detected around it is then classified as a weed. This method is very effective in centimetric planting (laser guidance) and at a very early stage of vegetation. However, this technique, which does not allow weeds to be individualized on the row, will only be used as a first approach in WeedElec.

Taxonomic identification by deep learning:
Image recognition algorithms are capable of identifying one plant among thousands of others with high recognition rates. The latest results in this field show recognition rates in excess of 85%(http://www.lifeclef.org/). Access to these techniques has become widely available in recent years, notably through the Pl@ntNet mobile application(www.plantnet-project.org; Joly & al., 2016). This approach, which mobilises large quantities of data, requires computing power that is difficult to mobilise on an on-board electronic solution. Knowledge distillation (Hinton & all, 2015), transfer learning (Carranza-Rojas & all, 2017) and domain adaptation (Tzeng & all, 2017) techniques will be used to overcome this problem.

Spectral information:
The technique of hyper-spectral imaging (one to several hundred bands, combined with chemo-metric treatments such as PLS-DA, has shown its ability to achieve effective discrimination (Hadoux & all, 2014) between weeds and crop plants. WeedElec will rely mainly on this technique to detect weeds by drone and proxy detection.

Weed destruction

The principle of electric weeding was studied by Diprose (1984). This showed that the energy required to destroy a plant is proportional to its size and more important for outdoor plants than for those under glass. Irstea during the PATCHWORK and D3E projects (1995-2000) had already developed a specific technique for localized high-voltage electrical destruction of weeds.
However the characteristics of complex electrical impedance vary according to the species. It leads to different behaviours when they are subjected to high voltage. WeedElec aims to study these characteristics to generate the optimal high voltage signal from a lethal efficiency and energy consumption point of view.

The purpose of WeedElec

Ultimately, WeedElec’s overall aim is to assemble all these solutions on a robot to produce a viable prototype solution that can be sold to industry as a whole or in independent modules.

The role of TERIA

TERIA is involved in a number of eco-responsible projects across a wide range of applications. Respecting and improving the environment is an integral part of the company’s DNA. Our team of experts works daily with its partners to develop efficient, environmentally-friendly solutions.