Content uploaded by Judy Mathushika
Author content
All content in this area was uploaded by Judy Mathushika on Jun 01, 2022
Content may be subject to copyright.
1DOI: 10.1201/9781003299059-1
Chapter 1
Smart Farming Using
Artificial Intelligence,
the Internet of Things,
and Robotics: A
Comprehensive Review
M. J. Mathushika
University of Colombo, Colombo, Sri Lanka
R. Vinushayini
University of Colombo, Colombo, Sri Lanka
C. Gomes
University of the Witwatersrand, Johannesburg, South Africa
1.1 Introduction
Agriculture continues to remain fundamental to the global economy, with 60% of the
world’s population relying on it for survival. e Food and Agriculture Organization
(FAO) of the United Nations has stated that 5 billion hectares of land, which is 38%
of the global land surface, is currently employed in agriculture and related activities.
ough this gure seems large, each and every aspect of agricultural activities face
2 | Artificial Intelligence and Smart Agriculture Technology
numerous challenges, such as soil testing, ecient planting, controlling weeds, pesti-
cide control, disease treatment, and lack of proper irrigation (Bannerjee et al., 2018).
As such, agricultural industries are on the hunt for novel techniques to improve crop
yielding and productivity in order to feed the rising population. Smart technolo-
gies such as articial intelligence (AI), the Internet of ings (IoT), and robotics
were incorporated into agriculture a few decades ago. ey have led to a period of
revolution in agriculture and recently have been paid more attention. Although the
integration of this trio of smart technologies can maximize farming eciency, there
are some drawbacks that accompany the implementation and commercialization
of such automation technologies (Talaviya et al., 2020). is review aims to revise
the numerous desirable applications of AI, the IoT, and robotics in various stages of
agriculture and present the major challenges and future recommendations for the
successful implementation of advanced farming.
1.2 The Role of Artificial Intelligence in
Advanced Farming
Articial intelligence- based technologies support farming by increasing the e-
ciency of conventional farming and overcoming the challenges and drawbacks
faced by traditional farmers. Articial intelligence (AI) is the process where humans
produce articial machines similar to the human brain but with an ability to deal
with larger amounts of data than the human brain. AI directly falls within the com-
puter science eld, but it should surpass this boundary to contribute to agriculture
(Jha et al., 2019). Various technical devices and instruments have been developed
based on AI that have been tested on agricultural elds and optimized. ey have
been successful in developing various eld- steps of agriculture, such as soil testing,
weeding, pesticide control, the treating of diseased crops, lack of proper irrigation
to match the needs of crops, post- harvest activities such as storage management,
optimising storage parameters, etc. Farmers have attained a high output as well as
increased quality of output (Talaviya et al., 2020).
On the other hand, AI can be involved in agriculture to mitigate the environ-
mental concern raised due to unfavourable agricultural activities, such as the heavy
usage of pesticides, uncontrolled irrigation resulting in loss of water, and water being
polluted with fertilizers. e implementation of AI would help in both these ways
(Jha et al., 2019). ere have been various AI systems proposed and developed by
various scientists for various plantations in the past (Bannerjee et al., 2018).
e foremost objective of utilizing AI- based technologies is to reduce the labour
force needed to achieve the required yield. Also, questions unanswered by humans
are easily attended to by AI- based devices due to their ability to gather large amounts
of data from governmental websites up to the real- time eld data and analyse them.
ey can then provide suggestions to problems that would take a lot of time and
Smart Farming Using AI, IoT, and Robotics | 3
high- end skills if they were to be made by humans. AI requires training with the bio-
logical skills of the farmer and vice versa; hence, farmers with the required skills will
also need to be trained with these AI technologies (Talaviya et al., 2020).
1.2.1 The Fundamentals of AI Technologies
Involved in Agriculture
e foremost step in involving AI in any eld is machine learning. e data that
needs to be processed should be fed in a machine- readable manner, and the processed
solution should be delivered in a human language. As the AI- based machine
processes the fed data, it should be able to gather information from the directed
databases to meet the problem that has arisen. On occasion, real- time data would
be needed for the AI to arrive at a conclusion, where the AI should be competent
enough to read the real- time parameters. Weather prediction is an important factor
needed to make decisions about the cropping season.
Chatbots are devices that virtually assist farmers with less experience of inter-
action with technologies by engaging them in conversations. Unmanned aerial
vehicles (UAVs) are popular among governmental and institutional ocers of
farming for detecting any potential harm to the elds, such as the spreading of forest
res, pest invasions, pathogen attacks, and many more by geolocalization (Talaviya
et al., 2020).
Neuro- fuzzy logic, fuzzy logic, expert systems, and articial neural networks
(ANNs) are four methods designed to solve problems (Jha et al., 2019). ANNs
are the most common method utilized when designing AI- based technologies. An
ANN simulates the processes within a human brain in a machine. In the brain,
electric signals pass through neurons by axons and synapses. Various algorithms,
such as delta- bar- delta, Silva, and Almeida, are used. e dierence between con-
ventional computer programmes and these algorithms is that this method allows the
machine to perform an inbuilt task (Jha et al., 2019). A hardware- software interface
should be built for the user- friendly functioning of the machine by farmers and
other stakeholders. “Embedded systems” are machines into which software is fed.
1.2.2 AI in Crop or Seed Selection
High vigour, good germination, and the seedling emergence rate of seeds have always
ensured emergence even under varying agricultural conditions and have been the
key to optimising yields and ensuring uniformity in production (TeKrony & Egli,
1991). Traditionally, farmers have optimised seed choice based on experience, and
any laboratory experiments for seed- choice optimisation are laborious and prone to
error. e way that individual seed varieties react to dierent weather conditions and
disease resistance, etc., are understood by AI technical devices by analysing the pre-
vious data to a greater extent than could be accessed by a general farmer.
4 | Artificial Intelligence and Smart Agriculture Technology
SeedGerm is a phenotyping platform developed from automated seed imaging
and phenotypic analysis based on machine learning. e core algorithm of SeedGerm
has been developed with features such as background remover, feature extraction
and germination detection, and measurements of traits. e hardware design of the
SeedGerm system consists of a translucent plastic box and an overhead image sensor.
e seed imaging module of SeedGerm ensures high- throughput imaging, which
also enables the removal of background. e system also consists of environmental
sensors that sense ambient temperature and humidity. SeedGerm is capable of ger-
mination scoring and measuring morphological changes, which in turn scores seed-
ling vigour, and hence could analyse the performance of seed batches. ese traits
could be used by ocials in issuing germination certicates (Colmer et al., 2020).
A novel method named crop selection method (CSM) was proposed by Kumar et al.
(2015).
1.2.3 AI in Crop Management Practices
Sensors and embedded systems have been developed that support the growth
conditions in a growth chamber, such as light intensity, humidity, and O2 and CO2
levels. ey can control crop conditions per prevailing crop growth data in real-
time to match optimised parameters (Lakhiar et al., 2018). Trace Genomics is a
technological rm that extracts DNA from the soil samples of agricultural lands
and quanties the microbes dwelling within. e data from the soil is analysed with
machine- learning technologies. is biological data is combined with the chem-
ical parameters of the soil sample to nally recommend solutions to the farmer,
which would be evidence- based on past occurrence data the past. is would help in
selecting the best crop to suit the land or vice versa.
A continuous and accessible water supply is required for crop cultivation. Due
to the scarcity of freshwater, it is highly advised not to exploit more water resources
than is necessarily needed by the crop. Hence, AI technologies, which record real-
time data regarding soil moisture content and weather conditions, could manipu-
late the amount of water needed and automate the supply and ceasing of the water
(Talaviya et al., 2020). Kumar et al. (2014) listed a few such automated irrigation
methods using AI. Mahmood et al. (2016) listed the risks arising due to heavy pesti-
cide usage, which include eects on biodiversity threats, human health, and leaching
of excess agrochemicals into waterways, which can cause environmental issues like
eutrophication. Facchinetti et al. (2021) designed a small vehicle- like machine called
“Rover” to spray pesticide, leading to a reduction of up to 55% in the amount usu-
ally sprayed, and improving crop coverage.
1.2.4 AI in Yield Prediction
Prediction models are one of the foremost AI techniques to be readily accepted by
farmers, as yield and prot are the major targets of all forms of agriculture. Soil type,
Smart Farming Using AI, IoT, and Robotics | 5
soil nutrient content, crop information, and weather conditions are analysed before
predicting the yield. Van Klompenburg et al. (2020) has reviewed a large amount of
research regarding yield prediction models.
1.2.5 AI in Pest and Weed Management
Partel et al. (2019) describe a method for developing automated machines that
could specically detect weeds and spray them with agrochemicals, which reduces
the wastage of weedicide and reduces the exposure of the crop to the agrochemicals.
Pasqual and Manseld, SMARTSOY, and CORAC are examples of pest manage-
ment systems (Bannerjee et al., 2018).
1.2.6 AI in Storing and Marketing Products
e storage of agricultural products in suited conditions is crucial for maintaining
quality before reaching the consumer. Various sensors have been developed in storage
chambers for lengthening the post- harvest life of these products. Traditional farmers
only understand the conventional markets of their products, but the latest market
trends, decisions about the products’ price, and information about the consumption
pattern of consumers are precisely analysed by market data and can suggest the next
round of crops to the farmers (Talaviya et al., 2020).
1.3 The Role of the Internet of Things in
Advanced Farming
As we head towards more cultured and urban farming, the necessity and engage-
ment of fresh scientic developments such as IoT- based technology are becoming
increasingly vital in diverse farming systems for numerous applications. ey help
to improve a variety of farming practices in order to increase yield output while pre-
serving or minimizing the impact on the originality of the product.
1.3.1 IoT- Based Soil Sampling
Manufacturers currently present a wide range of sensors and toolkits to support
farmers in monitoring the quality of soil and provide solutions to prevent degrad-
ation. ey enable the intensive care of soil qualities such as water- holding capacity,
texture, and absorption rate, which aids in decreasing densication, salinization,
acidication, pollution, and erosion by avoiding the overconsumption of fertilizers.
e Lab- in- a- Box soil- testing toolkit made by AgroCares is considered to be a com-
prehensive laboratory in itself due to the extreme services it provides (Ayaz et al.,
2019). Any farmer, regardless of lab knowledge, can use it to analyse up to 100
6 | Artificial Intelligence and Smart Agriculture Technology
samples per day without having to visit a lab. Remote sensing is currently being
utilized to collect regular soil moisture data, which will aid in the analysis of droughts
in remote areas. e Soil Moisture and Ocean Salinity (SMOS) satellite, which gives
maps detailing the global soil moisture every one to two days, was launched in 2009
for this purpose (Crapolicchio et al., 2010).
In 2014, researchers in Spain employed SMOS L2 to evaluate the soil water
decit index (SWDI) (Pablos et al., 2018). ey used a variety of methods to get
the soil water parameters with the aim of comparing them to the SWDI calculated
from in situ data. In addition, the Moderate Resolution Imaging Spectroradiometer
(MODIS) sensor is being utilized to scan the dierent features of soil with the aim
of quantifying the danger of land degradation in Sub- Saharan Africa (Zhang et al.,
2006). Sensors and vision- based technology aid in determining the distance and
depth required for eective seed sowing. To estimate the seed ow rate, many non-
contact sensing methods are oered where the sensors are tted with LEDs that
include visible light, infrared, and laser LEDs, along with a radiation reception
element. e seed ow rate is calculated using the signal information related to the
passing seeds (Ayaz et al., 2019).
1.3.2 IoT- Based Disease and Pest Monitoring
Farmers may drastically decrease their usage of pesticides by accurately recognizing
crop pests utilizing IoT- based smart devices, including wireless sensors, drones, and
robots. Contemporary IoT- based pest management oers real- time monitoring, dis-
ease forecasting, and modelling, making it more fruitful than conventional pest con-
trol approaches (Kim et al., 2018). Cutting- edge pest and disease detection techniques
depend on image processing, with raw images collected across the farming region
using remote sensing satellites or eld sensors. Remote sensing imagery typically
covers huge areas and provides more eectiveness at a reduced cost. Field sensors,
conversely, can support more functions in data collection, such as environmental
sampling, plant condition monitoring, and pest threats, in every phase of the crop
cycle. IoT- based automatic traps may collect, count, and even describe pest varieties,
then upload the data to the cloud for detailed analysis (Ayaz et al., 2019). is IoT-
based pest monitoring system is capable of minimizing the total costs while also
assisting in the restoration of the natural climate (Oberti et al., 2016).
1.3.3 IoT- Based Fertilization
New IoT- based fertilization technologies aid in the accurate estimation of spatial
patterns of fertilizer requirements while requiring minimal labour (Lavanya et al.,
2020). e normalized dierence vegetation index (NDVI), for instance, which
is based entirely on the reection of visible and near- infrared light from vegeta-
tion, examines the status of crop nutrition utilizing satellite images and measures
crop health, vegetation vigour, and density (Benincasa et al., 2017). It also helps
Smart Farming Using AI, IoT, and Robotics | 7
to analyse soil nutrient levels. Such exact execution can considerably boost fertil-
izer eciency while also avoiding environmental side eects. Geo- mapping, GPS
accuracy, autonomous vehicles, and variable rate technology (VRT) are now con-
tributing to IoT- based smart fertilization. Besides precision fertilization, other IoT
benets include fertigation (Raut et al., 2017) and chemigation (González- Briones
et al., 2018).
1.3.4 IoT- Based Yield Monitoring
A yield monitor developed using IoT- based technologies can be mounted on any
associated harvester and connected to the FarmTRX mobile app, which demonstrates
real- time harvest data and instantly uploads it to the manufacturers’ web- based plat-
form (Ayaz et al., 2019). is app can create high- quality yield maps that the farmer
may export to other farm management tools for further analysis. Fruit growth meas-
urement can be really benecial in the precise evaluation of the quality and pro-
duction of the yield. Satellite photographs can be a useful tool for monitoring the
output of large- scale crops. is method was used to record rice crop production in
Myanmar using Sentinel- 1A interferometric pictures (Torbick et al., 2017). Colour
(RGB) depth photographs are utilized to track the various fruit stages in mango
elds (Wang et al., 2017). Similarly, several optical sensors are being used to measure
papaya shrinkage, especially during drying conditions (Udomkun et al., 2016).
1.3.5 IoT- Based Irrigation
Embracing upcoming IoT technology is predicted to change the current status of
irrigation practices. e application of IoT- based strategies, such as crop water stress
index (CWSI) based irrigation management, is projected to lead to a major enhance-
ment in crop eciency. CWSI computation necessitates the achievement of crop
canopy at various times as well as air temperature (Tekelioğlu et al., 2017). A wireless
sensor- based monitoring system has been created in which all eld sensors are linked
to assemble the measured data, which is subsequently delivered to a processing centre
where the farm data is analysed using appropriate intelligent software programs.
Various other data, such as satellite imaging and meteorological data, are also fed
into CWSI models to analyse water needs, and an exclusive irrigation index value
is created for each site. Variable rate irrigation (VRI) optimization by CropMetrics,
which functions in relation to soil variability or topography and ultimately develops
the eectiveness of water usage, is also a good example (LaRue & Fredrick, 2012).
1.3.6 IoT- Based Food Safety and Transportation
Considering the prevailing hunger crisis caused by population growth, there is a sig-
nicant opportunity to diminish food wastage and enhance food supply by merely
adopting a temperature- controlled transportation system. Executing an autonomous
8 | Artificial Intelligence and Smart Agriculture Technology
system that utilizes wireless sensors to detect and record temperatures electronically,
on the other hand, can signicantly increase food safety. is approach provides a
continuous temperature data stream. Readings can be taken regularly and on time
this way, leaving no space for interpretation; in other words, the whole procedure is
based solely on facts (Bouzembrak et al., 2019). Furthermore, the recorded data can
be kept in the cloud and retrieved from any device connected to the Internet, owing to
current technological advancements (Bharati & Mondal, 2021; Podder et al., 2021).
Notications can be delivered in real- time if the temperature exceeds predetermined
boundaries, meaning rapid action can be taken to correct the situation. In add-
ition, the IoT provides predictive maintenance by predicting when the monitoring
equipment will reach the end of its useful life, allowing it to be substituted before it
malfunctions and impacts the quality of products (Popa et al., 2019). Some of the
vital technologies utilized and their uses are enumerated in Table 1.1.
Various multipurpose technologies such as cloud computing, communication
technologies, etc., are being utilized in IoT- based farming in order to accomplish the
Table 1.1 Vital Technologies and Their Uses in Food Safety and
Transportation
Technologies Uses References
ComplianceMate Monitoring food safety and quality with
hazard analysis and critical control
points (HACCP).
Capturing temperatures in rooms and
coolers at every minute when it
integrates with Touchblock.
(Booth, 2015)
Laird Sentrius Helping in developing, customizing,
and supporting entire cold chain
systems. Handling challenging cold
chain environments.
Ensuring connectivity and consistency.
Making implementations easier, less
costly, and most effective.
(Ayaz et al., 2019)
CCP Smart Tag
(RC4)
Thorough monitoring solution for the
food service and food retail industry.
Automating the temperature of the
environment. Temperature and
other data are interpreted and
observed on a service provider cloud
platform utilizing mobile and web
applications.
(Htet Myint, 2020)
TempReporter Continuous monitoring of
temperature.
Logs readings automatically.
(Ayaz et al., 2019)
Smart Farming Using AI, IoT, and Robotics | 9
tasks mentioned above. A cloud- based system is adept at handling a broad array of
data and formats and can congure these forms for various applications (Tan, 2016).
AgJunction has developed an open cloud- based system that collects and distributes
data from various precise agriculture controllers, reducing costs and environmental
impact (Raj et al., 2021). Additionally, Akisai, Fujitsu’s agricultural sector cloud,
includes information communication technologies with the intention of elevating
the food supply in the next years (Kawakami et al., 2016).
Wi- Fi, LoRaWAN, mobile communication, Zigbee, and Bluetooth are examples
of communication technologies that can be used to apply the IoT in advanced
farming (Jawad et al., 2017). ese technologies allow the automation of the entire
agricultural cycle, making agriculture more expedient and eective. Zigbee is exten-
sively utilized for IoT implementation in agriculture among many communication
technologies due to its little power consumption, cost- eectiveness and versatility
(Farooq et al., 2019). Some of the most commonly used mobile apps and their
diverse applications in IoT- based farming are enumerated in Table 1.2.
1.4 The Role of Robotics in Advanced Farming
With technological advancements, robotics applications in digital farming have
sparked a surge in interest, transforming typical eld activities into innovative tech-
nical tasks that are highly benecial. Various types of robots capable of conducting
Table 1.2 Common Mobile Apps and Their Diverse Applications
in Farming
Mobile apps Applications
PocketLAI Irrigation
LandPKS Soil assessment
AMACA Machinery/ tools
Ecofert Fertilizer management
AgriMaps Land management
SnapCard Spraying applications
SWApp Irrigation
WeedSmart Weed management
VillageTree Pest management
WISE Irrigation
EVAPO Irrigation
BioLeaf Health monitoring
cFertigUAL Fertigation
Source: Ayaz et al. (2019); Ferguson et al. (2016)
10 | Artificial Intelligence and Smart Agriculture Technology
diverse farming operations, such as planting, eld inspection, eld data gathering,
weed control, precise spraying, and harvesting, have been developed so far, although
many are still in the prototype phase.
1.4.1 Robotics in Planting
Planting demands a signicant amount of time and eort because the process
requires a high level of consistency and precision and typically spans a large agri-
cultural area. For numerous crops, such as corn, wheat, sugarcane, and vegetables,
autonomous systems have been established to solve the issues of manual planting
(Mahmud et al., 2020; Shi et al., 2019). e Agribot platform was used to create an
autonomous seeding robot. An infrared (IR) sensor was employed in this develop-
ment to verify the integrity of the seed tank, as well as for row identication, and it
produced a reasonable outcome in terms of precision in the distance between seeds
(Naik et al., 2016). Robots made of galvanized iron in previous research were able
to till the soil and sow seeds (Sunitha et al., 2017). Several other robots capable
of multitasking, including planting activities, are being used in modern farming
(Chandana et al., 2020). As a result, with superior planting quality, the automated
process of planting would be much more procient and suitable for farmers in the
near future (Mahmud et al., 2020).
1.4.2 Robotics in Weed Control and Spraying
e most widely used farm duties of eld robots are weed control and precise
spraying. When compared to blanket spraying, targeted spraying using robots for
weed control has given satisfactory outcomes and decreased herbicide consumption
to as little as 5– 10% (Pinheiro & Gusmo, 2014). Various potential weed robots have
been presented and deployed during the past 10 years as the outcome of interdis-
ciplinary cooperation initiatives among several worldwide research groups; however,
they are still not fully commercialized. It has been reported that these robots are cap-
able of reducing the use of weed chemicals by 80– 90 % (Molina et al., 2011). Some
of the robots being used in this sector for various tasks are recorded in Table 1.3.
1.4.3 Robotics in Field Inspection and Data Collection
e use of automation in agricultural inspection required the development of a
system that can perform the inspection process without the use of human eyesight.
As a result, computer vision is increasingly being utilized to substitute human vision
in the examination of plants in agriculture. Computer vision is a cutting- edge image
processing technology that has shown promising results and has the potential to
replace human eyesight in specic inspection tasks (Ayaz et al., 2019). Autonomous
inspection is typically carried out by mounting a camera in a static point on a trans-
portable robot or a drone. e deterrence of diseases and the quality testing of
Smart Farming Using AI, IoT, and Robotics | 11
commodities will become more precise and eective as a result of the self- governing
strategy and its execution in the inspection procedure, ensuring future food security.
Scouting robots for data collection involves the substantial utilization of advanced
sensors for advanced farming (Patmasari et al., 2018). Listed below in Table 1.4 are
some of the robots being used for eld inspection and data collection with multiple
applications.
1.4.4 Robotics in Harvesting
Increased harvesting eciency and lower labour costs will assure sophisticated
food production yield and aordability. As a result, the implementation of autono-
mous harvesting using robots should be considered an alternate option to solving
expenses and labour unavailability. For fruit detection inside the canopy, the earliest
experiments used simple monochrome cameras (Gongal et al., 2015). Many current
advancements are being incorporated into harvesting robots, including the autono-
mous recognition of fruits from manifold images or based on the fusion of colour
and 3D features (Barnea et al., 2016), multi- template matching algorithms (Bao
et al., 2016), symmetry analysis, combined colour distance method and RGB- D
data analysis for apples (Garrido- Novell et al., 2012) and sweet- peppers (Lavanya
et al., 2020), stereo vision for the detection of apples, and the usage of convolutional
neural networks (Zhao et al., 2016) and deep learning algorithms for the recognition
of fruits and evasion of hindrance in very condensed foliage (Zujevs et al., 2015).
Table 1.3 Commonly Used Robots and Their Applications for
Weed Control and Spraying
Robots Applications References
BoniRob Weed control for row crops.
Field mapping.
(Bakken et al., 2019)
AgBot Autonomous fertilizer
application.
Weed detection and sorting.
Chemical or mechanical weed
control.
(Redhead et al., 2015)
Autonome Roboter Weed control (Shamshiri et al., 2018)
Tertill Weed cutting (Sanchez & Gallandt,
2020)
HortiBot Transporting and attaching a
variety of weed detection
and control tools.
(Fountas et al., 2020)
Kongskilde Robotti Automated and semi-
automated mechanical
weed control.
(Bogue, 2016)
12 | Artificial Intelligence and Smart Agriculture Technology
e eld examination of a self- governing robot for de- leang cucumber plants
introduced a functional model in a high- wire farming structure (Van Henten et al.,
2006). Various studies on robot arm motion planning for agricultural harvesting
operations have been done in recent years. A motion scheduling system was success-
fully implemented with a 51% success rate to synchronize the four arms of a robot for
an automated kiwi fruit picking system (Udomkun et al., 2016). Apple tree branches
were detected with 94% accuracy using the Contrast Limited Adaptive Histogram
Equalization (CLAHE) method in Ayaz et al. (2019). Many research studies are cur-
rently in progress for developing simple manipulators and multi- robot systems as well.
1.5 The Challenges and Recommendations of
Indulging Technologies in Advanced Farming
A higher quantity of food of high quality is needed in the near future due to the rapid
rise in population (Ayaz et al., 2019). Hence, both the yield and quality of agricultural
production should be increased by the application of technologies into the eld.
Table 1.4 Commonly Used Robots and Their Applications in Field
Inspection and Data Collection
Robots Applications References
TrimBot2020 Automatic bush trimming.
Rose pruning.
(Shamshiri et al., 2018)
Wall- Ye Field mapping.
Pruning.
(Fountas et al., 2020)
Ladybird Surveillance and mapping.
Classification and detection of
different vegetables.
(Bender et al., 2019)
MARS Optimizing plant- specific precision
agriculture.
(Fountas et al., 2020)
SMP S4 Bird and pest control. (Shamshiri et al., 2018)
Vine agent Health monitoring of plants. (Arguenon et al., 2006)
HV- 100 Nursery
Bot
Moving of plants and potted
trees in greenhouses.
(Shamshiri et al., 2018)
VinBot Autonomous image acquisition.
3D data collection for yield
estimation.
(Shamshiri et al., 2018)
Mantis Field data collection. (Stein et al., 2016)
GRAPE Plant detection.
Health monitoring.
Manipulation of small objects.
(Roure et al., 2017)
Smart Farming Using AI, IoT, and Robotics | 13
Even though 2% of the farming population performs better in terms of quan-
tity and quality as they have access to modern technology, the rest of the population
struggles to gain a better yield. is is clear to see because developed countries, such
as Australia and most countries in Europe, have already been using new technology
and equipment over the past ve decades and have reached an exponentially higher
yield. us, it is clear that modern equipment and technology help in obtaining
higher yields, as well as making farms environmentally safe and benecial (Zha,
2020). In light of this scenario, future agriculture is predicted to develop into a high-
tech industry, with networked systems beneting from articial intelligence and big
data capabilities. From sowing to production forecasts, the resulting systems will
converge into a single unit where farm machinery and management will be linked.
Agriculture may usher in a new era of superfusion by using sophisticated technology
such as agricultural robotics, big data, and cloud- computing articial intelligence.
e major challenge of introducing technology into advanced farming is the lack
of proper knowledge of farmers who practice them in the eld. Hence, the major
recommendation would be to simultaneously educate farmers about the insights
of technological devices and produce a proper information base from individual
farming lands in order to optimize the devices in the future. Fear of technological
devices and automation technologies replacing the needed labour force had created
a reluctance towards these technologies among farmers in agriculture. ere is a
high chance that utilization of these technologies will be avoided as eld manage-
ment and disease management practices, which were historically performed by
experienced farmers, are now given by machines. Hence, it is practically observed
that young farmers who have more hands- on experiences with the technologies are
readily accepting the technologies into their elds than the old farmers. Hence, they
should be slowly admitted and introduced to them (Jha et al., 2019).
e creation of autonomous machines such as tractors is not accepted due
to safety considerations. Hence, more precise sensors and controlling technolo-
gies should be developed in the future. Also, to employ autonomous agricultural
machinery in the eld, IoT technologies must be combined to ensure agricultural
machinery safety (Kim et al., 2020).
Both cultivation and domestication of species are included in agriculture (Harris
et al., 2014). As only cultivation is looked upon by many farmers now, the domesti-
cation purpose has been greatly left to scientists and agro- technical ocers. Hence,
the implementation of AI into the eld of domestication would make it easier for
farmers to use their knowledge about wild varieties and test them for domestication.
AI development and involvement have only been limited to areas of agriculture
where prot- gain is the major target; however, the minor elds of agriculture such as
horticulture, mixed crop- livestock farming, and arboriculture should also be given
enough attention to improvise as well as optimize the services provided by those
elds.
IoT devices are employed in open surroundings in most agricultural areas, with
the exception of greenhouses, where they are directly exposed to hostile conditions.
14 | Artificial Intelligence and Smart Agriculture Technology
Safety devices are required in IoT hardware because environmental variables such
as rain, high temperature, humidity, and strong wind may aect their performance
(Farooq et al., 2020).
Hacking gathered host properties, farm information, and agricultural data,
as well as network and communication interruptions, should be avoided in IoT-
based agriculture. Since the IoT employs a distributed network of sensor nodes, a
single security protocol is insucient, and it is necessary to plan for data loss (Paul
et al., 2020).
e major challenge for sensor development and agricultural robotic technology
is the required spatial and resolution data being unable to be measured as they vary
extremely and hence pose diculties in measuring them. e goal of new analytical
methods is to extract new knowledge by combining data and fusing disparate infor-
mation layers. Network applications must be trustworthy and scalable in order to
manage these complex systems.
e main diculties to be disentangled for the generalization of robotics
structures are increasing the speed and accuracy of robots for agricultural applications.
e progress in the research related to the eld is hindered by the lack of substan-
tial budget allocations and funding. Improving sensing (fruit detection), acting
(manipulator movement, fruit attachment, detaching, and collecting), and growing
systems (leave pruning and plant reshaping) are some of the features that could be
vehemently suggested to improve the eciency.
It should be noted that the development of a cost- eective and ecient agri-
culture robot necessitates a multidisciplinary approach involving deep learning and
intelligent systems, computer science, dynamic control, crop management, sensors
and instrumentation, horticultural engineering, software design, mechatronics, and
system integration (Rahmadian & Widyartono, 2020). According to an IDTechEx
report, by 2023, more types of robots could be seen in the market with the rolling
out of robots used in weeding, vegetable and fruit harvesting, strawberry picking,
and apple picking.
AI, IoT, and robotics in agriculture are expected to solve a number of challenges
and enable higher quality and productivity. However, there is a need for a technology
that integrates and applies these technologies to all aspects of farm management.
erefore, research and development in this particular area should be encouraged,
and the governments should be ready to invest in the research sector of agriculture
for the well- being of their people.
1.6 Conclusion
Machine learning has enabled deep learning into automated technologies to be
directed for use in agriculture. Machines communicate with dierent databases
and produce solutions to timely problems faced by farmers. Adopting smart tech-
nologies, AI, the IoT, and robotics for various applications in advanced farming can
Smart Farming Using AI, IoT, and Robotics | 15
be highly benecial to farmers. ese technologies have reduced the involvement
of labour in the processes, thus reducing the number of human- made mistakes as
well as optimizing the processes, which have resulted in high eciency of produc-
tion as well as high yield. However, future research and development is needed to
overcome the shortcomings associated with these smart technologies in advanced
farming.
References
Arguenon, V., Bergues- Lagarde, A., Rosenberger, C., Bro, P., & Smari, W. (2006). Multi-
agent based prototyping of agriculture robots. International Symposium on Collaborative
Technologies and Systems (CTS’06). https:// doi.org/ 10.1109/ cts.2006.57
Ayaz, M., Ammad- Uddin, M., Sharif, Z., Mansour, A., & Aggoune, E. (2019). Internet- of-
things (IoT)- based smart agriculture: Toward making the elds talk. IEEE Access, 7,
129551– 129583. https:// doi.org/ 10.1109/ access.2019.2932609
Bakken, M., Moore, R., & From, P. (2019). End- to- end learning for autonomous crop
row- following. IFAC- Papersonline, 52(30), 102– 107. https:// doi.org/ 10.1016/ j.
ifacol.2019.12.505
Bannerjee, G., Sarkar, U., Das, S, & Ghosh, I. (2018). Articial intelligence in agricul-
ture: A literature survey. International Journal of Scientic Research in Computer Science
Applications and Management Studies, 7(3), pp. 1– 6.
Bao, G., Cai, S., Qi, L., Xun, Y., Zhang, L., & Yang, Q. (2016). Multi- template matching
algorithm for cucumber recognition in natural environment. Computers and Electronics
in Agriculture, 127, 754– 762. https:// doi.org/ 10.1016/ j.compag.2016.08.001
Barnea, E., Mairon, R., & Ben- Shahar, O. (2016). Colour- agnostic shape- based 3D fruit
detection for crop harvesting robots. Biosystems Engineering, 146, 57– 70. https:// doi.
org/ 10.1016/ j.biosystemseng.2016.01.013
Bender, A., Whelan, B., & Sukkarieh, S. (2019). A high- resolution, multimodal data set for
agricultural robotics: A ladybird ‘s- eye view of Brassica. Journal of Field Robotics, 37(1),
73– 96. https:// doi.org/ 10.1002/ rob.21877
Benincasa, P., Antognelli, S., Brunetti, L., Fabbri, C., Natale, A., & Sartoretti, V. (2017).
Reliability of NDVI derived by high resolution satellite and UAV compared to in- eld
methods for the evaluation of early crop n status and grain yield in wheat. Experimental
Agriculture, 54(4), 604– 622. https:// doi.org/ 10.1017/ s0014479717000278
Bharati, S., & Mondal, M. R. H. (2021). 12 applications and challenges of AI-driven
IoHT for combating pandemics: A review. Computational Intelligence for Managing
Pandemics, 5, 213.
Bogue, R. (2016). Robots poised to revolutionise agriculture. Industrial Robot: An
International Journal, 43(5), 450– 456. https:// doi.org/ 10.1108/ ir- 05- 2016- 0142
Booth, D. (2015). Building capacity: Internet of ings builds capacity for automatic tem-
perature logging. Journal of Environmental Health, 77(10), 34– 37. Retrieved June 10,
2021, from www.jstor.org/ stable/ 26330268
Bouzembrak, Y., Klüche, M., Gavai, A., & Marvin, H. (2019). Internet of ings in food
safety: Literature review and a bibliometric analysis. Trends in Food Science & Technology,
94, 54– 64. https:// doi.org/ 10.1016/ j.tifs.2019.11.002
16 | Artificial Intelligence and Smart Agriculture Technology
Chandana, R., Nisha, M., Pavithra, B., Sumana, S., & Nagashree, R. (2020). A multipurpose
agricultural robot for automatic ploughing, seeding and plant health monitoring.
International Journal of Engineering Research & Technology, 8(1).
Colmer, J., O’Neill, C., Wells, R., Bostrom, A., Reynolds, D., & Websdale, D. (2020).
SeedGerm: A cost- eective phenotyping platform for automated seed imaging and
machine- learning based phenotypic analysis of crop seed germination. New Phytologist,
228(2), 778– 793. https:// doi.org/ 10.1111/ nph.16736
Crapolicchio, R., Ferrazzoli, P., Meloni, M., Pinori, S., & Rahmoune, R. (2010). Soil
Moisture and Ocean Salinity (SMOS) mission: System overview and contribution to
vicarious calibration monitoring. European Journal of Remote Sensing, 37– 50. https://
doi.org/ 10.5721/ itjrs20104214
Facchinetti, D., Santoro, S., Galli, L. E., Fontana, G., Fedeli, L., Parisi, S., & Pessina, D.
(2021). Reduction of pesticide use in fresh- cut salad production through articial intel-
ligence. Applied Sciences, 11(5), 1992. https:// doi.org/ 10.3390/ app11051992
Farooq, M. S., Riaz, S., Abid, A., Abid, K., & Naeem, M. A. (2019). A survey on the role of
IoT in agriculture for the implementation of smart farming. IEEE Access, 7, 156237–
156271. https:// doi.org/ 10.1109/ ACCESS.2019.2949703
Farooq, M. S., Riaz, S., Abid, A., Umer, T., & Zikria, Y. B. (2020). Role of IoT trechnology
in agriculture: A systematic literature review. Electronics, 9(2), 319. https:// doi.org/
10.3390/ electronics9020319
Ferguson, J., Chechetto, R., O’Donnell, C., Fritz, B., Homann, W., & Coleman, C. (2016).
Assessing a novel smartphone application – SnapCard, compared to ve imaging
systems to quantify droplet deposition on articial collectors. Computers and Electronics
in Agriculture, 128, 193– 198. https:// doi.org/ 10.1016/ j.compag.2016.08.022
Food and Agriculture Organization of the United Nations. (2021). From: www.fao.org/ sus-
tainability/ news/ detail/ en/ c/ 1274219/ .
Fountas, S., Mylonas, N., Malounas, I., Rodias, E., Hellmann Santos, C., & Pekkeriet, E.
(2020). Agricultural robotics for eld operations. Sensors, 20(9), 2672. https:// doi.org/
10.3390/ s20092672
Garrido- Novell, C., Pérez- Marin, D., Amigo, J., Fernández- Novales, J., Guerrero, J., &
Garrido- Varo, A. (2012). Grading and color evolution of apples using RGB and
hyperspectral imaging vision cameras. Journal of Food Engineering, 113(2), 281– 288.
https:// doi.org/ 10.1016/ j.jfoodeng.2012.05.038
Gongal, A., Amatya, S., Karkee, M., Zhang, Q., & Lewis, K. (2015). Sensors and systems for
fruit detection and localization: A review. Computers and Electronics in Agriculture, 116,
8– 19. https:// doi.org/ 10.1016/ j.compag.2015.05.021
González- Briones, A., Castellanos- Garzón, J., Mezquita Martín, Y., Prieto, J., & Corchado,
J. (2018). A framework for knowledge discovery from wireless sensor networks in
rural environments: A crop irrigation systems case study. Wireless Communications and
Mobile Computing, 2018, 1– 14. https:// doi.org/ 10.1155/ 2018/ 6089280
Harris, D., & Fuller, D. (2014). Agriculture: Denition and overview. Encyclopedia of Global
Archaeology, 104– 113.
Htet Myint, K. (2020). SMS security on Android using RC4 algorithm. Intelligent System and
Computing. https:// doi.org/ 10.5772/ intechopen.90119
IDTechEx Ltd. (2017, March 6). Agricultural Robots and Drones 2017– 2027: Technologies,
Markets, Players. IDTechEx. www.idtechex.com/ en/ research- report/ agricultural-
robots- and- drones- 2017- 2027- technologies- markets- players/ 525
Smart Farming Using AI, IoT, and Robotics | 17
Jawad, H. M., Nordin, R., Gharghan, S. K., Jawad, A. M., & Ismail, M. (2017). Energy-
ecient wireless sensor networks for precision agriculture: A review. Sensors, 17(8),
1781. https:// doi.org/ 10.3390/ s17081 781.
Jha, K., Doshi, A., Patel, P., & Shah, M. (2019). A comprehensive review on automation
in agriculture using articial intelligence. Articial Intelligence in Agriculture, 2, 1– 12.
https:// doi.org/ 10.1016/ j.aiia.2019.05.004
Kawakami, Y., Furuta, T., Nakagawa, H., Kitamura, T., Kurosawa, K., & Kogami, K. (2016).
Rice cultivation support system equipped with water- level sensor system. IFAC-
PapersOnLine, 49(16), 143– 148. https:// doi.org/ 10.1016/ j.ifacol.2016.10.027
Kim, S., Lee, M., & Shin, C. (2018). IoT- based strawberry disease prediction system for
smart farming. Sensors, 18(11), 4051. https:// doi.org/ 10.3390/ s18114051
Kim, W., Lee, W., & Kim, Y. (2020). A review of the applications of the Internet of ings
(IoT) for agricultural automation. Journal of Biosystems Engineering, 45(4), 385– 400.
https:// doi.org/ 10.1007/ s42853- 020- 00078- 3
Kumar, R., Singh, M., Kumar, P., & Singh, J. (2015). Crop selection method to maximize
crop yield rate using machine learning technique. 2015 International Conference on
Smart Technologies and Management for Computing, Communication, Controls, Energy
And Materials (ICSTM). https:// doi.org/ 10.1109/ icstm.2015.7225403
Lakhiar, I., Jianmin, G., Syed, T., Chandio, F., Buttar, N., & Qureshi, W. (2018). Monitoring
and control systems in agriculture using intelligent sensor techniques: A Review of
the aeroponic system. Journal of Sensors, 2018, 1– 18. https:// doi.org/ 10.1155/ 2018/
8672769
LaRue, J., & Fredrick, C. (2012). Decision process for the application of variable rate irri-
gation. 2012 Dallas, Texas, July 29 – August 1, 2012. https:// doi.org/ 10.13031/
2013.42154
Lavanya, G., Rani, C., & Ganeshkumar, P. (2020). An automated low cost IoT based fer-
tilizer intimation system for smart agriculture. Sustainable Computing: Informatics and
Systems, 28, 100300. https:// doi.org/ 10.1016/ j.suscom.2019.01.002
Mahmood, I., Imadi, S., Shazadi, K., Gul, A., & Hakeem, K. (2016). Eects of pesticides
on environment. Plant, Soil and Microbes, 253– 269. https:// doi.org/ 10.1007/ 978- 3-
319- 27455- 3_ 13
Mahmud, A., Saiful, M., Abidin, Z., Shukri, M., Abiodun, A., & Sahib, H. (2020) Robotics
and automation in agriculture: present and future applications. Applications of Modelling
and Simulation, 4, 130– 140.
Molina, I., Morillo, C., García- Meléndez, E., Guadalupe, R., & Roman, M. (2011).
Characterizing olive grove canopies by means of ground- based hemispherical pho-
tography and spaceborne RADAR data. Sensors, 11(8), 7476– 7501. https:// doi.org/
10.3390/ s100807476
Naik, N., Shete, V., & Danve, S. (2016). Precision agriculture robot for seeding function.
2016 International Conference on Inventive Computation Technologies (ICICT). https://
doi.org/ 10.1109/ inventive.2016.7824880
Oberti, R., Marchi, M., Tirelli, P., Calcante, A., Iriti, M., & Tona, E. (2016). Selective
spraying of grapevines for disease control using a modular agricultural robot. Biosystems
Engineering, 146, 203– 215. https:// doi.org/ 10.1016/ j.biosystemseng.2015.12.004
Pablos, M., González- Zamora, Á, Sánchez, N., & Martínez- Fernández, J. (2018). Assessment
of SMADI and SWDI agricultural drought indices using remotely sensed root zone
soil moisture. Proceedings of e International Association Of Hydrological Sciences, 380,
55– 66. https:// doi.org/ 10.5194/ piahs- 380- 55- 2018
18 | Artificial Intelligence and Smart Agriculture Technology
Partel, V., Charan Kakarla, S., & Ampatzidis, Y. (2019). Development and evaluation of
a low- cost and smart technology for precision weed management utilizing articial
intelligence. Computers and Electronics In Agriculture, 157, 339– 350. https:// doi.org/
10.1016/ j.compag.2018.12.048
Patmasari, R., Wijayanto, I., Deanto, R., Gautama, Y., & Vidyaningtyas, H. (2018). Design
and realization of automatic packet reporting system (APRS) for sending telemetry
data in nano satellite communication system. Journal of Measurements, Electronics,
Communications, and Systems, 4(1), 1. https:// doi.org/ 10.25124/ jmecs.v4i1.1692
Paul, P., Marroquin, R. S., Aithal, P. S., Sinha, R. R., & Aremu, B. (2020). Agro inform-
atics vis- à- vis Internet of ings (IoT) integration & potentialities— An analysis. SSRN
Electronic Journal. https:// doi.org/ 10.2139/ ssrn.3724421
Pinheiro, F., & Gusmão dos Anjos, W. (2014). Optical sensors applied in agricultural crops.
Optical Sensors – New Developments and Practical Applications. https:// doi.org/ 10.5772/
57145
Podder, P., Mondal, M., Bharati, S., & Paul, P. K. (2021). Review on the security threats of
Internet of ings. arXiv:2101.05614
Popa, A., Hnatiuc, M., Paun, M., Geman, O., Hemanth, D., & Dorcea, D. (2019). An intel-
ligent IoT- based food quality monitoring approach using low- cost sensors. Symmetry,
11(3), 374. https:// doi.org/ 10.3390/ sym11030374
Rahmadian, R., & Widyartono, M. (2020). Autonomous robotic in agriculture: A review.
2020 ird International Conference on Vocational Education and Electrical Engineering
(ICVEE). https:// doi.org/ 10.1109/ icvee50212.2020.9243253
Raj, M., Gupta, S., Chamola, V., Elhence, A., Garg, T., Atiquzzaman, M., & Niyato,
D. (2021). A survey on the role of Internet of ings for adopting and promoting
Agriculture 4.0. Journal of Network and Computer Applications, 187, 103107. https://
doi.org/ 10.1016/ j.jnca.2021.103107
Raut, R., Varma, H., Mulla, C., & Pawar, V. (2017). Soil monitoring, fertigation, and irri-
gation system using IoT for agricultural application. Intelligent Communication and
Computational Technologies, 67– 73. https:// doi.org/ 10.1007/ 978- 981- 10- 5523- 2_ 7
Redhead, F., Snow, S., Vyas, D., Bawden, O., Russell, R., Perez, T., & Brereton, M. (2015).
Bringing the farmer perspective to agricultural robots. Proceedings Of e 33rd Annual
ACM Conference Extended Abstracts on Human Factors in Computing Systems. https://
doi.org/ 10.1145/ 2702613.2732894
Roure, F., Moreno, G., Soler, M., Faconti, D., Serrano, D., & Astol, P. (2017). GRAPE:
Ground Robot for vineyArd Monitoring and ProtEction. ROBOT 2017: ird Iberian
Robotics Conference, 249– 260. https:// doi.org/ 10.1007/ 978- 3- 319- 70833- 1_ 21
Sanchez, J., & Gallandt, E. (2020). Functionality and ecacy of Franklin Robotics’
Tertill™ robotic weeder. Weed Technology, 35(1), 166– 170. https:// doi.org/ 10.1017/
wet.2020.94
Shamshiri, R., Weltzien, C., Hameed, I., Yule, I., Grift, T., Balasundram, S., Pitonakova,
L., Ahmad, D., & Chowdhary, G. (2018). Research and development in agricultural
robotics: A perspective of digital farming. International Journal of Agricultural and
Biological Engineering, 11(4), 1– 11. https:// doi.org/ 10.25165/ j.ijabe.20181104.4278
Shi, Y., Xin (Rex), S., Wang, X., Hu, Z., Newman, D., & Ding, W. (2019). Numerical
simulation and eld tests of minimum- tillage planter with straw smashing and strip
lying based on EDEM software. Computers and Electronics in Agriculture, 166, 105021.
https:// doi.org/ 10.1016/ j.compag.2019.105021
Smart Farming Using AI, IoT, and Robotics | 19
Stein, M., Bargoti, S., & Underwood, J. (2016). Image based mango fruit detection, localisa-
tion and yield estimation using multiple view geometry. Sensors, 16(11), 1915. https://
doi.org/ 10.3390/ s16111915
Sunitha, K., Suraj, G., Sowrya, C., Sriram, G., Shreyas, D., & Srinivas, T. (2017). Agricultural
robot designed for seeding mechanism. IOP Conference Series: Materials Science and
Engineering, 197, 012043. https:// doi.org/ 10.1088/ 1757- 899x/ 197/ 1/ 012043
Talaviya, T., Shah, D., Patel, N., Yagnik, H., & Shah, M. (2020). Implementation of articial
intelligence in agriculture for optimisation of irrigation and application of pesticides
and herbicides. Articial Intelligence in Agriculture, 4, 58– 73. https:// doi.org/ 10.1016/
j.aiia.2020.04.002
Tan, L. (2016). Cloud- based decision support and automation for precision agricul-
ture in orchards. IFAC- PapersOnLine, 49(16), 330– 335. https:// doi.org/ 10.1016/
j.ifacol.2016.10.061
Tekelioğlu, B., Büyüktaş, D., Baştuğ, R., Karaca, C., Aydinşakir, K., & Dinç, N. (2017).
Use of crop water stress index for irrigation scheduling of soybean in Mediterranean
conditions. Journal of Experimental Agriculture International, 18(6), 1– 8. https:// doi.
org/ 10.9734/ jeai/ 2017/ 37058
TeKrony, D., & Egli, D. (1991). Relationship of seed vigour to crop yield: A review. Crop
Science 31: 816– 822
Torbick, N., Chowdhury, D., Salas, W., & Qi, J. (2017). Monitoring rice agriculture across
Myanmar using time series Sentinel- 1 assisted by Landsat- 8 and PALSAR- 2. Remote
Sensing, 9(2), 119. https:// doi.org/ 10.3390/ rs9020119
Udomkun, P., Nagle, M., Argyropoulos, D., Mahayothee, B., & Müller, J. (2016). Multi- sensor
approach to improve optical monitoring of papaya shrinkage during drying. Journal of
Food Engineering, 189, 82– 89. https:// doi.org/ 10.1016/ j.jfoodeng.2016.05.014
Van Henten, E., Van Tuijl, B., Hoogakker, G., Van Der Weerd, M., Hemming, J., Kornet, J.,
& Bontsema, J. (2006). An autonomous robot for de- leang cucumber plants grown
in a high- wire cultivation system. Biosystems Engineering, 94(3), 317– 323. https:// doi.
org/ 10.1016/ j.biosystemseng.2006.03.005
Van Klompenburg, T., Kassahun, A., & Catal, C. (2020). Crop yield prediction using machine
learning: A systematic literature review. Computers and Electronics in Agriculture, 177,
105709. https:// doi.org/ 10.1016/ j.compag.2020.105709
Wang, Z., Walsh, K., & Verma, B. (2017). On- tree mango fruit size estimation using RGB- D
images. Sensors, 17(12), 2738. https:// doi.org/ 10.3390/ s17122738
Zha, J. (2020). Articial intelligence in agriculture. Journal of Physics: Conference Series, 1693,
012058. https:// doi.org/ 10.1088/ 1742- 6596/ 1693/ 1/ 012058
Zhang, X., Friedl, M., & Schaaf, C. (2006). Global vegetation phenology from moderate
resolution imaging spectroradiometer (MODIS): Evaluation of global patterns and
comparison with in situ measurements. Journal of Geophysical Research: Biogeosciences,
111(G4). https:// doi.org/ 10.1029/ 2006jg000217
Zhao, Y., Gong, L., Huang, Y., & Liu, C. (2016). A review of key techniques of vision- based
control for harvesting robot. Computers and Electronics in Agriculture, 127, 311– 323.
https:// doi.org/ 10.1016/ j.compag.2016.06.022
Zujevs, A., Osadcuks, V., & Ahrendt, P. (2015). Trends in robotic sensor technologies for
fruit harvesting: 2010– 2015. Procedia Computer Science, 77, 227– 233. https:// doi.org/
10.1016/ j.procs.2015.12.378
