Region VII, Central Visayas

DIVISION OF CITY OF BOGO

CITY OF BOGO SENIOR HIGH SCHOOL
Cogon, Bogo City, Cebu

SPARK: Seed-Planting Arduino Robot for

Efficient Maize

Researchers:
Cabahug, Marie Paula C.
Olivar, Eden Agnes L.
Seno, Julius Ryan R.
Baslag, Jehiela Nirel M.
Saludo, Desiree B.
Regala, Christian N.
Becaldo, Edlyn M.
Macasil, Sam Daniel M.
Doncillo, Cluianne Mae A.
Canete, Zach Vince M.

Research Adviser:
Kent Jaspher Ytang
 RATIONALE

Numerous international studies have explored different technological approaches to

optimize seed sowing processes through robotics. For instance, Wang, Zhang, and Han

(2020) developed a vision-based robotic system for precision maize sowing, achieving

improved accuracy and efficiency. Additionally, Li, Shen, and Liu (2021) investigated the use

of a robot for autonomous seedling transplantation in rice cultivation, reducing labor costs

and increasing productivity. These studies, among others, have contributed valuable insights

into the field of agricultural robotics. However, there remains a research gap pertaining to

low-cost and easily accessible technologies for seed sowing robots specifically designed for

maize planting.

The research gap in international studies lies in the limited attention given to

affordable and accessible technologies for seed sowing robots in the context of maize

planting. Many existing studies have primarily utilized sophisticated and expensive hardware

and software components, which may not be practical or feasible in resource-constrained

environments. Consequently, there is a need for a study that addresses this gap by exploring

the feasibility of an Arduino-based solution for efficient maize seed sowing. Arduino, an

open-source microcontroller platform, offers cost-effectiveness and versatility, making it a

viable choice for resource-limited farming communities.

The proposed study stands out in its focus on an Arduino-based seed sowing robot

specifically designed for efficient maize planting. By leveraging the affordability and

versatility of Arduino, this study aims to develop a practical and accessible solution that can
be easily replicated and implemented by farmers, particularly those with limited resources.

The integration of sensors, actuators, and communication modules with Arduino will enable

precise and automated seed sowing, optimizing the planting process and ensuring optimal

seed distribution. This unique approach distinguishes the study from existing research, which

predominantly focuses on advanced and expensive technologies, and emphasizes the

significance of cost-effectiveness and ease of implementation.

The proposed study holds significant implications for agricultural automation and food

production. Firstly, by addressing the research gap in international literature, the study

contributes to the knowledge base surrounding affordable and accessible technologies for

maize seed sowing robots. This enables small-scale farmers to adopt automated solutions,

reducing labor requirements and increasing overall productivity. Secondly, the study's

emphasis on the use of Arduino as a platform underscores the potential for cost-effectiveness

and scalability, thereby empowering resource-limited farming communities to adopt modern

farming practices. Lastly, the study's significance lies in its alignment with sustainable

agricultural practices, as the automation of seed sowing processes can lead to improved

efficiency, reduced environmental impact, and increased food security.

 SPARK: Seed-Planting Arduino Robot for Maize

The main objective of this study is to build a Seed-Planting Arduino Robot for easier and

faster seed placement of corn cornel in corn fields.

Specifically, this study seeks to:

1. Determine the accuracy and precision of the Agribot in terms of its:

a. seed placement

b. navigation

2. Determine the response time of the Agribot in terms of its signal transmission from the

remote control device.

3. Evaluate the performance of the Agribot in terms of its:

a. efficiency

b. speed

c. power consumption

d. weight capacity of corn seeds

 REVIEW OF RELATED LITERATURE

This section will include the relevant studies that will provide data to support the

study’s credibility and significance and will aid in familiarizing information that is relevant

and similar to the current study.

I. Maize

II. Arduino

Arduino is an open-source hardware and software platform designed for creating any

electronic projects. It consists of a microcontroller and IDE. The IDE is use to write, upload

and run code on the Board. Arduino boards are widely used by hobbyists, students, and

professionals in various fields to bring their ideas to life and prototype electronic systems.

I. Accuracy and Precision

The significance of the accuracy and precision is for ensuring that seeds are planted in

a way that will promote healthy plant growth and yield.

a. Seed Placement

Corn seed sowing is a vital task in agriculture, and advancements in agribotics have

enabled the use of specialized robots, known as Agribots, for precise and efficient seed

placement. Precision seeding aims to distribute seeds in the soil in a way that creates the best

conditions for even emergence. It's crucial to plant seeds properly to ensure that they receive

enough moisture to germinate them from unfavorable climatic factors (Badua et al., 2020).
There were no appreciable changes in emergence uniformity at seeding depths ranging from

40 to 80 mm, however the 80 mm depth resulted in a noticeably longer emergence duration,

according to Ozmerzi et al. (2002). The stage of emergence, according to Duncan et al.

(2007), is when a seedling first rises above the earth's surface.

The diverse soil conditions (such as soil texture and tillage practices) call for different

levels of downward force, and excessive application of this force can have detrimental effects

on the depth and sprouting of corn plants. (Hanna, 2009) found that an excessive load can

result in compacting the area where seeds are placed. Insufficient load could, however, result

in insufficient seeding depth (Karayel and Arauskis 2011). Poor root development and

irregular plant emergence may be caused by compacted soil surrounding the seed and

insufficient moisture at a shallow planting depth (Gratton et al. 2003).

b. Navigation

The ability of the robot to move around a field and sow seeds in a predetermined pattern

is called navigation. There are a number of different navigation techniques that can be used

by seed sowing robots, including GPS navigation, inertial navigation, and odometry.

Meyer (2003) and Filliat (2003) discuss the different sensors and map-based

navigation systems that robots can use to build internal representations of their environment

and position themselves within it. The allothetic and idiothetic sensors that these robots can

use to generate internal representations of their surroundings, as well as the maps in which

these representations can be instantiated.

 Based on both studies by Santhi (2017) and Dutta (2019), robots use sensors and vision

systems to navigate and sow seeds in a grid pattern. A robot that uses ultrasonic sensors can

detect obstacles and navigate while sowing seed (Godse 2021). Overall, seed sowing robots

use a combination of sensors and vision systems to navigate and sow seeds with precision,

reducing the need for human labor in agriculture.

II. Response Time

In a seed sowing robot, response time refers to the time it takes for the robot to react to

a change in its environment. This could be anything from a shift in soil conditions to a shift in

seed spacing. A quick response time is critical for the robot to spread seeds accurately and

effectively.

A seed sowing robot's response time can be affected by a variety of circumstances.

These include the sort of sensors employed, the processing capability of the robot's computer,

and the actuator design .Based on a study by Umarkar (2016), ultrasonic sensors are used to

detect obstacles and navigate the robot in the field. Santhi (2017) also used a vision system

for navigation and localization.

The response time also refers to the time it takes for the robot to receive a command

from the remote controller and execute the corresponding action. For most agricultural

robots, the response time can range from milliseconds to a few seconds. However, it's

important to note that this is a general estimate, and the actual response time can be
influenced by various factors such as the communication range, signal strength, and

processing speed of the robot's control system. Godse (2021) and Amie (2009) describe seed

sowing robots that are controlled by a remote device. The remote control allows the operator

to navigate the robot to the desired location and control the seeding and fertilizing process.

In accordance with Obialor (2022), a remote-controlled seed sowing machine can

cover 1000 square meters in 5 minutes with a control range of 10m and an efficiency of 95

percent. Srinivasan (2016) reports that their autonomous seed planting robot navigates using

inputs from a magnetometer, indicating that it can receive signals from a remote control

device. The use of a microcontroller to control the distance between seeds, could potentially

affect the response time of the robot (Amie 2009).

An Arduino Uno is used for controlling the robotic activities, which can be considered

a type of remote control device (Godse 2021). Overall, the response time of a seed sowing

robot is an important factor to consider when choosing a robot for your farm. A fast response

time will help to ensure that the robot can sow seeds accurately and efficiently, which can

lead to increased yields and profits.

III. Performance Evaluation

A. Efficiency

Using mechatronics and related fields, Kumar et al. (2022) claim to have created low-

cost machinery that might partially automate the seed planting process. The technology was

effective at reducing the time and effort required for seed sowing. Dutta et al., (2019) created
and manufactured an autonomous seed-planting robot named Agribot that eliminates the need

for labor throughout the irrigation and seed-planting procedures. According to the study,

using Agribot helped cut down on the time and effort needed for spreading seeds.

The design and development of an automatic seed sowing agribot were given in a

survey by (Kale et al., 2018). The goal was to create a technique that reduces the amount of

time and labor needed for seed sowing. According to the study, using an automatic seed

sowing agribot helped cut down on the time and labor needed for seed sowing. Abdulrhaman

et al., (2017) created a seed-planting robot that was effective and highly accurate. According

to the study, using a seed-sowing robot helped cut down on the time and labor needed to plant

seeds.

B. Speed

The time it takes a seed sowing robot to plant a field is referred to as its speed. The

number of seeds planted every hour can be used to calculate this. Seed sowing robots can

significantly reduce the amount of time it takes to plant a field.

In accordance with Kumar (2020), a smart seed sowing robot that can sow seeds

automatically reduces the total cost and human effort required for sowing. Naseer (2021)

introduces a solar-powered 4-wheel drive autonomous seed sowing robot that can plant seeds

while cultivating the soil in multi-terrain surfaces, increasing the efficiency of seeding by

exact measurement and distance. Belgali (2021) introduces auto seed sowing agriculture

robot that can move in different directions and sow seeds at a particular distance with a
specific delay, reducing the time and labor requirements for the process of planting the seed.

Therefore, the speed of seed sowing robot is an important factor as it can help to reduce the

amount of time.

C. Power Consumption

The power consumption of seed sowing robots can also affects their operating time. In

a study by Agetano (2018), found that their robot’s power supply was enough to give power

to the components of the robot for 4 hours and maintained its pace. Swetha (2015) and

Premalatha (2019) both used solar-powered DC motors to drive their robots, which reduced

the working cost and increased the productivity of the machine.

The main power supply in this study is a battery which contains an electrochemical cells

which are mainly used to generate power to the electronic devices. It mainly transform

chemical energy into an electrical energy. There are two major categories on a battery which

is called the primary and secondary, the primary are non-rechargeable and disposable while

the secondary is chargeable and reusable. In this study the battery will be used is secondary

where it can be chargeable (Rafath, 2020). All System is powered by a 4 rechargeable lithium

ion battery consisting 1200mAh with maximum voltage of 3.7 that can be total of 12 volts.

This 12 voltage is enough to power all DC motors and the Arduino board (Sowjanya, 2017).

D. Weight Capacity of Corn Seeds

An Arduino-based seed sowing robot was just recently unveiled by Vidushini et al.

(2021) as a brand-new approach to seed sowing in agriculture. This robot is capable of

efficiently and effectively sowing seeds without wasting any of them. The hopper, which is
situated in the middle of the base frame, is one of this robot's distinguishing characteristics.

To prevent seeds from being wasted during sowing, the hopper is shaped semi-circularly. It is

appropriate for mid- to large-scale agriculture operations because it can carry 1 to 1.5

kilogram of seeds.

The seed-sowing robot developed by Vidushini et al. (2021) combines the advantages

of robotics in agriculture. The robot can also produce real-time data, giving farmers important

information they may use to make wise decisions. The development of the Arduino based

seed sowing robot is a significant advancement in precision agriculture as it can support

sustainable agriculture by reducing waste and ensuring efficient use of resources. The robot

can accurately sow seeds at a specific depth, spacing, and precise timing, increasing

productivity and reducing human errors.

 METHODOLOGY

This section encompasses the research flow of the proposal of the SPARK: Seed-Planting

Arduino Robot for Efficient Maize and the procedures that will be taken to collect data and

conduct analysis related to the research.

I. Research Variable

Considering the factors that impact the effectiveness of planting, the researchers will

gather and analyze quantitative data acquired from the prototype design seeds using the seed

planting robot. The data will be compared to other common seed sowing systems available on

the market. The analysis will include critical performance metrics such as seed placement

accuracy, planting speed, seed spacing consistency, and overall productivity. This

comparative analysis will provide useful insights into the efficiency of the intended seed

planting robot, allowing for a better knowledge of its advantages and prospective

enhancements in comparison to existing market options.

II. Scope and Limitations of the Study

However, the implementation of the Seed-Planting Arduino Robot does come with certain

limitations. Soil variability poses challenges as different soil types, textures, and conditions

can impact the Agribot's ability to achieve precise seed placement and consistent germination

rates. Moreover, the Agribot's seed compatibility may be limited to specific sizes or types,

necessitating manual intervention for certain crop varieties. Additionally, adverse weather

conditions can hinder the Agribot's functionality, affecting its efficiency and productivity.

Furthermore, maintenance requirements, including periodic repairs and associated costs, as

well as the initial investment required for the Agribot, may pose financial challenges for

farmers, especially those with limited resources. Considering these limitations is crucial for

realistic expectations and effective decision-making in adopting and optimizing the Arduino-

based seed sowing Agribot in agricultural practices.

III. Research Procedure

Fig. 1 Schematic Diagram for the Procedure of the Device.

a. Collection of Materials

Following the schematic flowchart of the procedures for the proposed product, the

researchers will first assess, identify, and collect the required components. The researchers

will compare the prices of various materials sold by various businesses in order to select the

most cost-effective component.  A seed discharge tube, wheels, dc motors, battery and seed

metering will be utilized for the proposed device.

b. Software Development and Hardware Integration

i. Construction of the Proposed Device

Once the specified materials have been completely gathered, the researchers will then

proceed with constructing the device based on the proposed research design. As seen in

Figure 2, the seed metering device is attached on the frame with the seed container.

Fig. 2 Prototype design

(a) Schematic diagram of the seed-metering device's structure

1. Seed inlet

2. Fixed 4. 5. Core 7. Seed pick-up

disc Pressure disc disc module assembly

3. Seed spacer 6. Limit guide plate 8. Moving disc

9. Shaft

(b) Physical view of the seed-metering device

ii. Construction and Configuration of the Program

Following the construction of the device, the researchers will proceed with

programming the device and connecting its wires to its respective parts and sensors.

Illustrated in Figure 3, the diagram showcases the combination of the sensors and

microcontrollers that will be utilized for the device. Following the connection of its

components, the researchers will then program the Arduino board using the IDE Software to

write and upload the program.

 Fig.3 Schematic Flow Chart of the Agribot

c. Trial Run

Following the completion of the hardware and software construction of the

suggested seed sowing agribot will begin with the user turning on the power switch, after

which the program will commence. The device would then be launched and placed in a

cornfield. The device would regularly begin planting, and once completed, the agribot would

be remotely shut off.

The proposed device will next be compared to a standardized seed sower and a

commercial seed sower over the same time period and in the same location by the

researchers. Following the initial testing of the proposed device, the device would be

subjected to additional tests (in terms of response time and flexibility) for the final

performance evaluation.

d. Observation and Performance Evaluation

The researchers will assess the performance of the prototype using the

aforementioned performance indicators provided in this paper's theoretical framework. The

researcher will compare the prototype to two other devices (standardized seed sower and

commercialized seed sower) to determine its performance in the relevant variables.

Furthermore, to completely analyze its accuracy and precision, the researchers will conduct a
series of tests over the duration of one month to determine a dependable and concrete

performance ratio in examining its capabilities in contrast to the other devices stated.

i. Data analysis

To test and ascertain the effectiveness of the Agribot conducted by the City of Bogo

Senior High School STEM students, Table 1 shows the data set of variables.

Trial Sowing Speed Seed Time period Seed Sowing

Distribution Accuracy (%)

Table 1

Expected Outputs and Potential Impact

Upon the completion and implementation of the seed planting robot, the researchers

hypothesized the prototype's success in its capability in performing its tasks (i.e. accurately

and precisely planting the corn seeds accordingly). The seed planter along with the

programmed Arduino R3 board will accurately sow the maize seeds in the plowed field
automatically. Moreover, the robot’s response time will positively concur with the robot’s

accuracy and precision.

Fig.4 View of an agricultural robot on a plowed field

Shown in Figure 4, the seed planting robot should be used in a plowed field. Its cost

effectiveness will help increase yield and reduce labor dependency. Implementing a Maize

Seed Sowing Robot can improve the seeding process in agriculture and provide a feasible

solution for farmers. Furthermore, the Department of Agriculture and those associated with it

will benefit from the information gathered and the methods utilized in fabricating a cost

effective Agribot for an efficient maize seed planting.

REFERENCE:

Kumar, P., & Ashok, G. (2020). Design and fabrication of smart seed sowing robot. Materials

Today: Proceedings. doi: 10.1016/j.matpr.2020.07.432

Dutta, S., Shanker, U., Katiyar, S., Singh, V., Nayab Zafar, M., & Mohanta, J. C. (2019).

Development and Fabrication of an Autonomous Seed Sowing Robot. IOP

Conference Series: Materials Science and Engineering, 691, 012023.

doi:10.1088/1757-899x/691/1/012023

Kumar, Y. N., Haswanth, C., Kiran, M. H., Rao, M. K., Raj, R., Saramekala, G. K., &

Chakrobarty, P. A. (2019). Automated Seed Sowing Agribot. 2019 IEEE 1st

International Conference on Energy, Systems, and Information Processing (ICESIP).

doi:10.1109/icesip46348.2019.8938

Jayakrishna, P. V. S., Reddy, M. S., Sai, N. J., Susheel, N., & Peeyush, K. P. (2018).

Autonomous Seed Sowing Agricultural Robot. 2018 International Conference on

Advances in Computing, Communications, and Informatics (ICACCI).

doi:10.1109/icacci.2018.8554622

Ghotbi, B., Gonzalez, F., Kovecses, J., & Angeles, J. (2014). Effect of normal force

dispersion on the mobility of wheeled robots operating on soft soil. 2014 IEEE

International Conference on Robotics and Automation (ICRA).

https://doi.org/10.1109/icra.2014.6907835
Besseron, G., Grand, Ch., Amar, F. B., Plumet, F., & Bidaud, Ph. (2005). Locomotion modes

of a hybrid wheel-legged robot. Climbing and Walking Robots, 825–833.

https://doi.org/10.1007/3-540-29461-9_80

Oda, T., Yoshikawa, H., Shibata, N., Nonaka, K., & Sekiguchi, K. (2019). Model Predictive

Allocation Control for leg-wheel mobile robot on loose soil considering wheel

dynamics. Linköping Electronic Conference Proceedings.

https://doi.org/10.3384/ecp18148240

Komatsu, S., Kakiuchi, Y., Nozawa, S., Kojio, Y., Sugai, F., Okada, K., & Inaba, M. (2017).

Tool force adaptation in soil-digging task for humanoid robot. 2017 IEEE-RAS 17th

International Conference on Humanoid Robotics (Humanoids).

https://doi.org/10.1109/humanoids.2017.8246901

Mazzolai, B., Mondini, A., Del Dottore, E., Margheri, L., Carpi, F., Suzumori, K., Cianchetti,

M., Speck, T., Smoukov, S. K., Burgert, I., Keplinger, T., Siqueira, G. D., Vanneste,

F., Goury, O., Duriez, C., Nanayakkara, T., Vanderborght, B., Brancart, J., Terryn,

S., … Lendlein, A. (2022). Roadmap on soft robotics: Multifunctionality,

adaptability and growth without borders. Multifunctional Materials, 5(3), 032001.

https://doi.org/10.1088/2399-7532/ac4c95

Srinivasan, N., Prabhu, P., Smruthi, S. S., Sivaraman, N. V., Gladwin, S. J., Rajavel, R., &

Natarajan, A. R. (2016). Design of an autonomous seed planting robot. 2016 IEEE

Region 10 Humanitarian Technology Conference (R10-HTC). doi:10.1109/r10-

htc.2016.7906789

AMIE, S. C. M., & Mohanraj, T. (2009). Automation and Emerging Technology

Development of 2d Seed Sowing Robo. Journal of Agricultural Science, 1(1).

doi:10.5539/jas. V1n1p33
Godse, Dr. D. (2021). Seed sowing robot. International Journal for Research in Applied

Science and Engineering Technology, 9(9), 781–786.

https://doi.org/10.22214/ijraset.2021.38042

Thirumaran, V. (2019). Automation in seed sowing by using Smart Agri-Robot. International

Journal for Research in Applied Science and Engineering Technology, 7(4), 1721–

1724. https://doi.org/10.22214/ijraset.2019.4312

Soza, E., Botta, G., Tourn, M., & Hidalgo, R. (2004). Sowing efficiency of two seeding

machines with different metering devices and distribution systems: A comparison

using soybean, glycine max (L) merr. Spanish Journal of Agricultural Research,

2(3), 315. https://doi.org/10.5424/sjar/2004023-86

Naik, N. S., Shete, Virendra. V., & Danve, Shruti. R. (2016). Precision Agriculture robot

for seeding function. 2016 International Conference on Inventive Computation

Technologies (ICICT). https://doi.org/10.1109/inventive.2016.7824880

CUNHA, J. P., & SOARES FILHO, R. (2016). Broadcast Distribution Uniformity of

fertilizer with centrifugal spreaders used in variable rate application. Engenharia

Agrícola, 36(5), 928–937. https://doi.org/10.1590/1809-4430-eng.agric.v36n5p928-

937/2016

Bechar, A., & Vigneault, C. (2017). Agricultural Robots for Field Operations. part 2:

Operations and systems. Biosystems Engineering, 153, 110–128.

https://doi.org/10.1016/j.biosystemseng.2016.11.004

Cogels, O. G. (1983). An irrigation system uniformity function relating the effective

uniformity of water application to the scale of influence of the plant root zones.

Irrigation Science, 4(4), 289–299. https://doi.org/10.1007/bf00389651

Ascough, G., & Kiker, G. (2002). The effect of irrigation uniformity on irrigation water

requirements. Water SA, 28(2). https://doi.org/10.4314/wsa.v28i2.4890

Santhi, P. V., Kapileswar, N., Chenchela, V. K. R., & Prasad, C. H. V. S. (2017). Sensor and

vision based autonomous AGRIBOT for sowing seeds. 2017 International

Conference on Energy, Communication, Data Analytics and Soft Computing

(ICECDS). doi:10.1109/icecds.2017.8389873

Özmerzi, A., Karayel, D., & Topakci, M. (2002). PM—Power Machinery. Biosystems

Engineering, 82(2), 227–230. doi:10.1006/bioe.2002.0057

Corrêa, R. D. G., Furlani, C. E. A., Zerbato, C., Oliveira, D. T. de, Noronha, R. H. de F., &

Warikoda, N. K. (2019). Sowing operation direction and population densities in corn

growing. Revista Brasileira de Engenharia Agrícola e Ambiental, 23(3), 183–187.

doi:10.1590/1807-1929/agriambi.v23n3p183-187

Agetano, J. C. Q., Pamplona, N. A. T., Hernia, G. L., Obnial, I. C. C., & Zhuo, E. R. (2018).

Amaize. Proceedings of the 6th International Conference on Information

Technology: IoT and Smart City - ICIT 2018. doi:10.1145/3301551.3301554

Poncet, A. M., Fulton, J. P., McDonald, T. P., Knappenberger, T., Shaw, J. N., & Bridges, R.

W. (2018). Effect of Heterogeneous Field Conditions on Corn Seeding Depth

Accuracy and Uniformity. Applied Engineering in Agriculture, 34(5), 819–830.

doi:10.13031/aea.12238

Sowjanya, K. D., Sindhu, R., Parijatham, M., Srikanth, K., & Bhargav, P. (2017).

Multipurpose autonomous agricultural robot. 2017 International Conference of

Electronics, Communication and Aerospace Technology (ICECA).

https://doi.org/10.1109/iceca.2017.8212756
Rafath, F., Rana, S., Ahmed, S. Z., Juveria, Begum, R., & Sultana, N. (2020). Obstacle

detecting multifunctional AGRIBOT driven by solar power. 2020 4th International

Belgali, P., Jadhav, S., Shirgure, S., & Shirgure, K. (2021). Auto seed sowing agriculture

robot. Journal of Communication Engineering and Its Innovations, 7(2).

https://doi.org/10.46610/jocei.2021.v07i02.003

Dutta, S., Shanker, U., Katiyar, S., Singh, V., Zafar, Mohd. N., & Mohanta, J. C. (1970,

January 1). Development and fabrication of an autonomous seed sowing robot:

Semantic scholar. IOP Conference Series: Materials Science and Engineering.

https://semanticscholar.org/paper/67ea8cb348679c82cf9507e4ed7d8d4be8b31ed9

Godse, D. A. (1970, January 1). Seed sowing robot: Semantic scholar. International Journal

for Research in Applied Science and Engineering Technology.

https://semanticscholar.org/paper/b1470c14d86eb21e41ee675f9a19fae69a7b6cc7

Kumar, P., & Ashok, G. (2021). Design and fabrication of smart seed sowing robot.

Materials Today: Proceedings, 39, 354–358.

https://doi.org/10.1016/j.matpr.2020.07.432

Naseer, F., Rasool, A., Qammar, M. Z., & Shahood, R. (2021). Solar powered 4-wheel drive

autonomous seed sowing robot for rough terrain. Intelligent Environments 2021.

https://doi.org/10.3233/aise210104

Santhi, P. V., Kapileswar, N., Chenchela, V. K., & Prasad, C. H. (2017). Sensor and vision

based autonomous AGRIBOT for sowing seeds. 2017 International Conference on

Energy, Communication, Data Analytics and Soft Computing (ICECDS).

https://doi.org/10.1109/icecds.2017.8389873
 Conceptual Framework

SPARK: Seed Planting

Arduino Robot for
Efficient Maize

Automation

Soil Conditions
Optimal Moisture levels
Data Analysis Sensor Data Autonomous
Planting and Collection Navigation
Locations Environmental
data

Crop Growth Real-time Seed-

Computer
and Health Monitoring Planting
Vision
Data Mechanism

Data Analysis
and Insights

Optimized
Resource
Allocation

Decision Support Sustainability

and Efficiency