Citation: Kiti´c, G.; Krklješ, D.; Pani´c,
M.; Petes, C.; Birgermajer, S.;
Crnojevi´c, V. Agrobot Lala—An
Autonomous Robotic System for
Real-Time, In-Field Soil Sampling,
and Analysis of Nitrates. Sensors
2022, 22, 4207. https://doi.org/
10.3390/s22114207
Academic Editor: Sigfredo Fuentes
Received: 20 April 2022
Accepted: 24 May 2022
Published: 31 May 2022
Publisher’s Note: MDPI stays neutral
with regard to jurisdictional claims in
published maps and institutional affil-
iations.
Copyright: © 2022 by the authors.
Licensee MDPI, Basel, Switzerland.
This article is an open access article
distributed under the terms and
conditions of the Creative Commons
Attribution (CC BY) license (https://
creativecommons.org/licenses/by/
4.0/).
Article
Agrobot Lala—An Autonomous Robotic System for Real-Time,
In-Field Soil Sampling, and Analysis of Nitrates
Goran Kiti´c *, Damir Krklješ , Marko Pani´c , Csaba Petes, Slobodan Birgermajer and Vladimir Crnojevi´c
BioSense Institute—Research Institute for Information Technologies in Biosystems, University of Novi Sad,
Dr. Zorana Ðin
¯
di´ca 1a, 21000 Novi Sad, Serbia; dkrkljes@biosense.rs (D.K.); panic@biosense.rs (M.P.);
chaba@biosense.rs (C.P.); b.sloba@biosense.rs (S.B.); crnojevic@biosense.rs (V.C.)
* Correspondence: gkitic@biosense.rs or office@biosense.rs
Abstract:
This paper presents an autonomous robotic system, an unmanned ground vehicle (UGV),
for in-field soil sampling and analysis of nitrates. Compared to standard methods of soil analysis it
has several advantages: each sample is individually analyzed compared to average sample analysis
in standard methods; each sample is georeferenced, providing a map for precision base fertilizing;
the process is fully autonomous; samples are analyzed in real-time, approximately 30 min per sample;
and lightweight for less soil compaction. The robotic system has several modules: commercial robotic
platform, anchoring module, sampling module, sample preparation module, sample analysis module,
and communication module. The system is augmented with an in-house developed cloud-based
platform. This platform uses satellite images, and an artificial intelligence (AI) proprietary algorithm
to divide the target field into representative zones for sampling, thus, reducing and optimizing the
number and locations of the samples. Based on this, a task is created for the robot to automatically
sample at those locations. The user is provided with an in-house developed smartphone app enabling
overview and monitoring of the task, changing the positions, removing and adding of the sampling
points. The results of the measurements are uploaded to the cloud for further analysis and the
creation of prescription maps for variable rate base fertilization.
Keywords: UGV; precision agriculture; artificial intelligence; soil nutrient analysis; soil sampling
1. Introduction
With the continuous growth of the world population, the demand for food and culti-
vated land increases continuously. The prediction of the Food and Agriculture Organization
of United Nations (FAO) indicates the presence of constant growth of the population with
the rate of 79 million people per year, increasing food demand [
1
]. Since the cultivated land
resources are limited, and acquiring new ones is correlated with degradation of ecosystems,
reduction of forests, climate changes, and risks of new pandemic breakouts, as well as
degradation of soil properties due to inappropriate cultivation and treatment, there is an
urgent need to improve soil treatment, to increase yield in a sustainable manner. The
best approach that will enable farming to become more efficient in a sustainable way
and reduce the production costs at the same time, is to provide an efficient supply of
nutrients and water [
2
]. Standard and classical methods of soil analysis usually involve
taking 1–20 samples per 5 hectares from around 30 cm depth. They are usually mixed and
analyzed for an average value of nutrients [
3
]. A laboratory analysis then takes 10–15 days
to obtain the results. The most common soil sampling methods used are hand sampling,
hydraulic probes, electric probes, and auger probes [
4
]. Hand sampling is easy to use and
economic, but it is time-consuming, labor-intensive, and could be inconsistent with the
sampling depths. Hydraulic probes are fast and have a consistent depth, but are composed
of numerous components (engine, hydraulics tank, pump, and lines), vendor locked, and
pricy in the range from USD 4000 to 8000 on average. Electric probes demand low mainte-
nance, with no fuel costs, and are more suited for dusty conditions. They do have a slower
Sensors 2022, 22, 4207. https://doi.org/10.3390/s22114207 https://www.mdpi.com/journal/sensors
