AgroIntelliAGROINTELLI has been working with SoilCare study sites to test and demonstrate various soil-improving technologies.  Integrating these technologies into agricultural operations, especially through automation and the use of sensors, can improve both soil health and profitability.


Site-specific rotavator control and crop residue detection for Robotti

Robotti is AgroIntelli’s autonomous field robot with a 3-point hitch that is capable of performing seeding, mechanical weeding, spraying, harrowing, and rotavating operations. Using a soil texture map, the Robotti can alter the speed on the PTO, increase/decrease Robotti’s speed, and raise and lower the rotavator based on actual field conditions, creating the ideal seedbed. The PTO speed and Robotti speed will help create right-sized aggregates, while the depth will control how much residue is incorporated into the soil. The more residue, the deeper the rotavator will need to work to ensure that the residue is mixed with the soil.


Soil-improving benefits

Robotti typically weighs less than half of a similarly advanced tractor. The low weight reduces the risk of soil compaction and structural damage to the soil, which can result in higher crop yields per hectare. Tillage can damage the soil, breaking the soil into very small aggregates, increasing wind and water erosion. The site-specific rotovator control for Robotti can blend the soil based on the soil type, resulting in the same aggregate sizes over the entire field. The rotavator speed, the speed of the Robotti and the depth of the tillage can be adjusted.

Rotavator and crop residue detection

To be able to perform site-specific rotavating, it is necessary to know how much crop residue is on the soil. Crop residue can protect the soil from erosion and ‘reduce surface runoff, sediment loss, and associated nutrient losses’ 

Study sites in the SoilCare project took photos of crop residues to help crop residues detection.  A total of 313 images were analysed for 6 SoilCare project partners.  Instructions were sent to the participating partners about how to take the pictures. A blue metal square measuring 1 x 1 m was sent to the participating partners to create a defined area that would be a consistent area to find the crop residue.

When taking a picture, the person would place the blue square frame on the soil with the colour card and take a picture. To avoid shadows and noise in the data, the person was instructed to take the pictures facing the sun.  After the images, were received, they were cropped.


Cropped images of crop residue.

An algorithm using semantic segmentation was created to recognize the crop residue. The semantic segmentation was used to classify the residue and background in order to estimate the residue cover. The algorithm’s accuracy was 75% and 82% accurate, using an error range of +/- 10.

crop residue image

LiDar soil surface scans

Soil surface measurements play an important role in the performance assessment of tillage operations and are relevant in both academic and industrial settings. Manual soil surface measurements are time-consuming and laborious, which often limits the amount of data collected. An experiment was conducted to compare two approaches for measuring and analysing the cross-sectional area and geometry of a furrow after a trailing shoe sweep. The compared approaches in this study were a manual pinboard and a Light Detection and Ranging (LiDAR) sensor. The experiments were conducted in coarse sand and loamy sand soil bins exposed to three levels of irrigation. Using the LiDAR, a system for generating 3D scans of the soil surface was obtained and a mean furrow geometry was introduced to study the geometrical variations along the furrows. A comparison of the cross-sectional area measurements by the pinboard and the LiDAR showed up to 41% difference between the two methods. The relation between irrigation and the resulting furrow area of a trailing shoe sweep was investigated using the LiDAR measurements. The furrow cross-sectional area increased by 11% and 34% under 20 mm and 40 mm irrigation compared to non-irrigated in the coarse sand experiment. In the loamy sand, the cross-sectional area increased by 17% and 15% by irrigation of 20 mm and 40 mm compared to non-irrigated measured using the LiDAR.

Tillage Intensity Impact

Soil structure and structural stability are key parameters in sustainable soil management and optimum cropping practices. This study aimed to improve the knowledge of potential precision tillage practices by characterizing the effect of varied tillage intensities on structural properties of a clay loam soil. An experiment with seedbed preparation was conducted using a power take-off-driven rotovator equipped to measure torque and angular velocity and with operational speed (OS) and rotational speed (RS) as main factors. Effects of soil coverage prior to tillage and wheeling directly after tillage were measured at one combination of OS and RS. Highly significant correlations were observed between soil dispersibility and energy input, specific surface area of aggregates, fractions of small (<4 mm) and medium (8–16 mm) aggregates, and geometric mean diameter. Slow OS combined with fast RS showed significantly greater air permeability than all other treatments. The results suggest that there is a potential for controlling soil structure in seedbed preparation by minimizing compaction from traffic and adapting site-specific control of rotavation intensity.

Plough depth control

The hypothesis for the plough section control was that an automatic ploughing depth control system, installed on an existing mouldboard plough, can dynamically adjust and maintain prescribed operation depths, independent of communication with the tractor. It is possible to reduce energy consumption without compromising the purpose of ploughing by utilising spatial data together with a modelling methodology to prepare a site-specific operational ploughing depth map.

In 2018, AgroIntelli performed plough depth control trials at the Danish Study Site in sandy loamy soils. The experiment had 2 factors – residue amounts and ploughing depths.  The results were that both vertical and horizontal distributions of incorporated residue depended on ploughing depth. The residue amounts >12 t ha-1 were incorporated significantly deeper than targeted depths as well as unevenly within soil profiles. The site-specific distribution of plant materials and soil properties have to be considered to obtain a constant ploughing, hence, incorporation depth.

As a result of the trials, in 2019, a mechanical design was created to alter the plough in the easiest way possible in order to add the extra feature of being able to control the plough depth based on site-specific plough depth maps. The target group for this technology is farmers who are interested in achieving an even distribution of residue incorporation.  


Navigation optimization for soil tillage

This technology is a navigation platform for the control of the field robot.  The platform provides several possibilities for ensuring the soil is tilled in a sustainable way.  Two primary functionalities in the navigation platform have been tested: a) Plough section control and b) Site-specific working areas.

Plough section control system

Plough section control


The plough is able to lift each section as the plough exits the main field into the headlands. This reduces the size of the triangles in the headlands. In the area of the triangles, the soil is ploughed twice, once when entered/exiting the mainland and once when ploughing the headlands. When the soil is ploughed twice, the soil is mixed and the plant/weed material is brought onto the surface of the soil. This increases the weed pressure in these areas, decreases the plant residue blended into the soil, and decreases the effects of the ploughing.

Soil-improving benefits

The use of this plough section control system minimizes weeds and improves the soil incorporation in the headlands. In particular, the plough section control reduces the negative impacts when ploughing with larger implements, reducing the environmental impact (less herbicides are needed in these areas) and increasing the effectiveness of the ploughing.

Site-specific working areas

working areas1 working areas2


Navigation platform showing defined working areas and performed working areas for mechanical weeding


Crop residues and weed population are the primary reason to manage soil cultivation. However, the uneven distribution in the field is very seldom considered in soil cultivation in normal farm practice. The navigation platform includes functionality that provides the opportunity to define working areas within a field and a single route for the robot, so the mechanical weed control for instance is only performed when needed. The input for planning the route on the navigation platform, with working areas, will be vision-based and is under development in other projects.

Soil-improving benefits

Targeting of mechanical weed control only to areas of the field where it is needed reduces soil disturbance.


For more information about Agrointelli's technologies please contact Ole Green This email address is being protected from spambots. You need JavaScript enabled to view it.



AGROINTELLI has produced a report that illustrates the importance of using technology to assess field readiness, manage in-field traffic, implement site-specific controlled as well as sensor-controlled seedbed preparation, seeding and weeding. The use of this technology can result in reduced operational costs and minimise soil threats and negative environmental impacts.