Final Report 1

AGRICULTURAL ROBOT

CHAPTER 1 1.1

INTRODUCTION In India generally the traditional seed sowing methods includes the use of animal drawn

funnel and pipes driller or drilling using tractor. Earlier method requires labour and a very time and energy consuming. Whereas in tractor based drilling operators of such power units are exposed to high level of noise and vibration, which are detrimental to health and work performance. The emphasis in the development of autonomous Field Robots is currently on speed, energy efficiency, sensors for guidance, guidance accuracy and enabling technologies such as wireless communication and GPS. Many agriculture operations are automated nowadays and many automatic machineries and robots available commercially. Some of the major operations in farming which are under research and automation are seeding, weeding and spraying processes. When it comes to designing a robot for automating these operations one has to decompose its idea into two considerations which are agriculture environment in which robot/system is going to work and precision requirement in the task over traditional methods. Based on this for seeding process, considerations which are taken into account in terms of environment are: robot must be able to move in straightway properly on bumpy roads of farm field, soil moisture content may affect the soil digging function, sensors to be selected for the system must be chosen by considering farming environmental effects on their working. Apart from these three other requirements are in terms of accuracy required in the task and these are: digging depth, particular optimal distances between rows and plants for certain type of crop, rows to be sown at a time and accurate navigation in the field. Whereas the other processes like weeding, spraying and harvesting, for which functioning depends on seeding stage by knowing the exact location of crop and then making those operations on it accordingly. So the major stage of all subsequent operations is maintaining a precision in seed sowing process. When considering the physical aspects of the vehicle or robotic system, farmer’s present condition in particular area plays a major role in designing these aspects. Considering facts of farming industry of India, system to be developed must have advantage over traditional methods and tractors in terms of cost, speed, accuracy in operation for which it is designed, fuel consumption and physical energy required by human for it. Plant diseases are important factors because its affects human being as well as animals etc. that’s why as it can cause significant reduction in both quality and quantity of crops in agriculture production. Therefore, detection and classification of diseases is an important and urgent task.

Dept. of ECE, BNMIT

Page 1

2018-2019

AGRICULTURAL ROBOT

Traditionally farmers identify the diseases by naked eye observation method. Some researchers have used image processing techniques for fast and accurate detection of plant diseases and identifying the diseases in an early stage only and control them. When some diseases are not visible to naked eye but actually they are present, then it is difficult to detect it with the naked eye. And when it is visible it will be too late to detect disease and can’t help anymore. Earlier, microscope is used to detect the disease, but it become difficult as to observe each and every leaf and plant. So, the fast and effective way is a remote sensing technique. Detection and recognition of diseases in plants using machine learning is very fruitful in providing symptoms of identifying diseases at its earliest. For small scale farmers, early identification of disease is very much possible and able to control the insects by organic pesticides or by the use of minimal amount of chemical pesticides. For large scale farmers frequent monitoring and early identification of disease is not possible and it results in a severe outbreak of the disease and pest growth which cannot be controlled by organic means. In this situation farmers are forced to use the poisonous chemicals to eradicate the disease in order to retain the crop yield. This problem can be solved by automating the monitoring process by use of advanced image processing techniques and machine learning.

The proposed work aims in making the automated system easily available for the farmer’s using the device for early detection of the diseases in plants. Robotic technology is included in this system a field robot goes through the field and captures the images of the leaves and processing of the image is done using the processor that is integrated in it. After the evaluation of the diseases the result is sent to the farmer/owner of the field in the form of SMS. The steps involved in disease detection are Digital image acquisition, Image pre-processing (noise removal, Color transformation, and histogram equalization), K-means Segmentation, Feature extraction, and classification using the support vector machine algorithm which is a supervised learning algorithm. The processing that is done by using these components is divided into two phases. The first processing phase is the offline phase or Training Phase. In this phase, a set of input images of leaves (diseased and normal) were processed by image analyzer and certain features were extracted. Then these features were given as input to the classifier, and along with it, the information whether the image is that of a diseased or a normal leaf. The classifier then learns the relation among the features extracted and the possible conclusion about the presence of the disease. Thus the system is trained. India is well known for its agriculture production. Most of the population is dependent on agriculture. Farmers have variety of options to cultivate crops in the field. Still, the cultivating these crops for best harvest and top quality of production is done in a technical way.

Dept. of ECE, BNMIT

Page 2

2018-2019

AGRICULTURAL ROBOT

So the yield can be increased and quality can be improved by the use of technology. Generally, whenever there is disease to a plant, we can say that leaves are the main indicator of the disease caused to the plant. Mostly we can see the spots on the leaves of it due to disease. However when the amount of disease to the plant is large then the whole leaf gets covered by the disease spots.

1.2 MOTIVATION The central principle of this project is to explore the efficacy of agricultural applications. The focus on major application is self-governing robot navigation. This is achieved by addressing the following research objects. 1. Explore the role of features to improve the detection accuracy. 2. Development of agricultural yield and reduce the human work. 3. Develop a sensor model to be used as measurement model.

1.3 PROBLEM STATEMENT Design and development of an agricultural robot, which can be able to plough and dispense seeds in agricultural field. The control of this Agribot should be wireless and can be able to show digging and seeding operations. Fabricate the model operated by wireless control which able to show operations likes ploughing and seeding. Also design and analyses a real time system for this robot to give a solution and propose a model which can be used in real time field.

1.4 OBJECTIVE AND SCOPE Data scouting at different stage of crop growth Yield in a given field may vary in space depending on a combination of factors such as nutrient availability, soil moisture, rooting depth, pest pressure, weed density, crop maturity and others. Good agricultural practice needs an application of optimum input at appropriate time series. Continue monitoring and data collecting related to crop NDVI, Biomass, Leaf area index, crop growth rate, water stress are an important parameter for optimizing the variable input parameters in different stages of crop growth and also crop health.

Dept. of ECE, BNMIT

Page 3

2018-2019

AGRICULTURAL ROBOT

CHAPTER 2 2.1 LITERATURE SURVEY Automated agribusiness furrowing robot The paper aims on the design, development & the fabrication of the robot which can put the seeds, depth of soil, plough the land, cutting the waste plant these whole systems of robot works with battery

Design and implementation of seeding and fertilizing robot The aim of the designed system is to seeding, fertilizing and soil ph, temperature, moisture, humidity checking. The robot is controlled by remote. The designed system involves navigation of robot to the destination successfully and does the above functions. The direction of the robot is controlled via remote. The robot and the remote system are connected through internet system.

SVM classifier based grape leaf disease detection Grape constitutes one of the most widely grown fruit crops in the India. Productivity of grape decreases due to infections caused by various types of diseases on its fruit, stem and leaf. Leaf diseases are mainly caused by bacteria, fungi, virus etc.

A survey on detection and classification of cotton leaf diseases Cotton is the most important cash crop in India. It is also known as “White Gold” or “The King of fibers” among all cash crops in the country. About 80-90% of the diseases which occur on the leaves of cotton are Alternaria leaf spot, Cercosporin leaf spot, Bacterial blight and Red spot. In the current scenario most of us have come across the atomization in various fields as the advancement of technology has to a lead tremendous development in the industrial products that have made our lives a lot easier and helpful than what our ancestors faced. The advancements especially in the field of agriculture have helped evolve a new era of development and growth of different developing countries. The atomization in this field has been a trademark for the people who are completely dependent on agriculture for their survival and other needs. Around ten papers reviewed who are worked under this area.

Dept. of ECE, BNMIT

Page 4

2018-2019

AGRICULTURAL ROBOT

Agribot (International Journal of Advanced Research in Computer and Communication Engineering-2015) Ankit Singh, Abhishek Gupta et al presented an idea that Agribot is a robot designed for agricultural purposes. This Bot performs basic elementary functions like picking, harvesting, weeding, pruning, planting, grafting. It is designed to minimize the labour of farmers in addition to increasing the speed and accuracy of the work. The main feature of the robot is the ability to find the grass in the field using image processing. For this a special purpose web cam which will take photos inside the field and if the grass is found then the user will inform the robot to cut the grass in the crop field and also the user will pick the grass which has been cut by the robot. The image processing is also used for analysing the height of the plant. If the height of the crop is larger than the reference height then the cutting mechanism will be used by the robot to cut the crop. A vision-based row guidance method is presented to guide the Robot platform driven along crops planted in row.

Dept. of ECE, BNMIT

Page 5

2018-2019

AGRICULTURAL ROBOT

CHAPTER 3 3.1 DESIGN AND METHODOLOGY The assembly of the robotic system is built using high torque DC motor, communication module, relay driver circuit, Battery package, microcontroller which is shown in block diagram below. When DC motor is started, the vehicle moves along the particular columns of ploughed land for digging and sowing the seeds and its movement is controlled by remote guiding device. This system has two main sections, robot section and control section, which are intercommunicated by using communication technologies. The microcontroller is brain of this system, which gives the order of suggestions received to all the networks, and sensible factors processed by their corresponding embedded programs. Robotic mechanism runs by their internal motors and motor drivers that drive the motors in desired directions.

3.2 PROCESS OF IMPLEMENTATION

Figure 3.1 Process of Implementation

Dept. of ECE, BNMIT

Page 6

2018-2019

AGRICULTURAL ROBOT

The above fig 3.1 shows the block diagram of Agriculture robot. It explains the operation of whole agricultural automation system. The main reason behind automation of farming processes are saving the time and energy required for performing repetitive farming tasks and increasing the productivity of yield by treating every crop individually using precision farming concept. Designing of such robots is modeled based on particular approach and certain considerations of agriculture environment in which it is going to work. These considerations and different approaches are discussed in this paper. Also, prototype of an autonomous Agriculture Robot is presented which is specifically designed for seed sowing task only. It is a four wheeled vehicle. Its working is based on the precision agriculture which enables efficient seed sowing at optimal depth and at optimal distances between crops and their rows, specific for each crop type.

Image processing is processing of images using mathematical operations by using any form of signal processing for which the input is an image, a series of images, or a video, such as a photograph or video frame. The basic unit of image is pixels. The group of pixels will form an image. Here in proposed system for processing an image we have used MATLAB. An image is processed for disease detection in below steps: STEP 1:- Firstly image has captured by camera is in the YCbCr form then it is converted into RGB. STEP 2:- In second step RGB image is converted into HSV image. HSV is named for 3 values: Hue, Saturation and Values. This color space describes colors (hue or tint) in terms of shade (saturation or amount of gray) and their brightness value. STEP 3:- In step 3 HSV image converted into Hue image

3.3 HARDWARE DETAILS 

ARM LPC2148



Moisture sensor



DC motor



Battery



Relay circuit



Voltage regulator

Dept. of ECE, BNMIT

Page 7

2018-2019

AGRICULTURAL ROBOT

3.3.1 ARM LPC2148 General Description The LPC2141/42/44/46/48 microcontrollers are based on a 16-bit/32-bit ARM7TDMIS CPU with real-time emulation and embedded trace support, that combine microcontroller with embedded high-speed flash memory ranging from 32 kB to 512 kB. A 128-bit wide memory interface and a unique accelerator architecture enable 32-bit code execution at the maximum clock rate. For critical code size applications, the alternative 16-bit Thumb mode reduces code by more than 30 % with minimal performance penalty. Due to their tiny size and low power consumption, LPC2141/42/44/46/48 are ideal for applications where miniaturization is a key requirement, such as access control and point-ofsale. Serial communications interfaces ranging from a USB 2.0 Full-speed device, multiple UARTs, SPI, SSP to I2C-bus and on-chip SRAM of 8 kB up to 40 kB, make these devices very well suited for communication gateways and protocol converters, soft modems, voice recognition and low-end imaging, providing both large buffer size and high processing power. Various 32-bit timers, single or dual 10-bit. ADC(s), 10-bit DAC, PWM channels and 45 fast GPIO lines with up to nine edge or level sensitive external interrupt pins make these microcontrollers suitable for industrial control and medical systems.

Pin Diagram

Figure: 3.2 Pin Diagram

Dept. of ECE, BNMIT

Page 8

2018-2019

AGRICULTURAL ROBOT

Features  16-bit/32-bit ARM7TDMI-S microcontroller in a tiny LQFP64 package. 

8 kB to 40 kB of on-chip static RAM and 32 kB to 512 kB of on-chip flash memory.



128-bit wide interface/accelerator enables high-speed 60 MHz operation.



Single flash sector or full chip erase in 400 ms and programming of 256 bytes in 1 ms.



Embedded ICE RT and Embedded Trace interfaces offer real-time debugging with the on-chip Real Monitor software and high-speed tracing of instruction execution.



USB 2.0 Full-speed compliant device controller with 2 kB of endpoint RAM. In addition, the LPC2146/48 provides 8 kB of on-chip RAM accessible to USB by DMA.



One or two (LPC2141/42 vs. LPC2144/46/48) 10-bit ADCs provide a total of 6/14 analog inputs, with conversion times as low as 2.44 μs per channel.



Single 10-bit DAC provides variable analog output (LPC2142/44/46/48 only).



Two 32-bit timers/external event counters (with four capture and four compare Channels each), PWM unit (six outputs) and watchdog.



Low power Real-Time Clock (RTC) with independent power and 32 kHz clock input.



Multiple serial interfaces including two UARTs (16C550), two Fast I2C-bus (400 kbit/s), SPI and SSP with buffering and variable data length capabilities.



Vectored Interrupt Controller (VIC) with configurable priorities and vector addresses.



Upto 45 of 5 V tolerant fast general purpose I/O pins in a tiny LQFP64 package,



Upto 21 external interrupt pins available.



60 MHz maximum CPU clock available from programmable on-chip PLL with settling time of 100 μs.



On-chip integrated oscillator operates with an external crystal from 1 MHz to 25 MHz



Power saving modes include idle and Power-down.



Individual enable/disable of peripheral functions as well as peripheral clock Scaling for additional power optimization.



Processor wake-up from Power-down mode via external interrupt or BOD.



Single power supply chip with POR and BOD circuits.



CPU operating voltage range of 3.0 V to 3.6 V (3.3 V ± 10 %) with 5 V Tolerant I/O pads.

Dept. of ECE, BNMIT

Page 9

2018-2019

AGRICULTURAL ROBOT

3.3.2 DC Motors Electric motors are everywhere! Almost every mechanical movement that can see around is caused by an AC (alternating current) or DC (direct current) electric motor. Let us start by looking at the overall plan of a simple two-pole DC electric motor. A simple motor has six parts, as shown in the diagram below: 1. Armature or rotor 2. Commutator 3. Brushes 4. Axle 5. Field magnet 6. DC power supply An electric motor is all about magnets and magnetism: A motor uses magnets to Create motion. If that have ever played with magnets about the fundamental law of all magnets: Opposites attract and likes repel. So have two bar magnets with their ends marked "north" and "south," then the north end of one magnet will attract the south end of the other. On the other hand, the north end of one magnet will repel the north end of the other (and similarly, south will repel south). Inside an electric motor, these attracting and repelling forces create rotational motion. In the figure 3.3 shows two magnets in the motor the armature (or rotor) is an electromagnet, while the field magnet is a permanent magnet (the field magnet could be an electromagnet as well, but in most small motors it isn't in order to save power).To understand how an electric motor works, the key is to understand how the electromagnet works.

Figure 3.3: Working Principle of Motor

Dept. of ECE, BNMIT

Page 10

2018-2019

AGRICULTURAL ROBOT

An electromagnet is the basis of an electric motor. It’s understood how things work in the motor by imagining the following scenario. Say that created a simple electromagnet by wrapping 100 loops of wire around a nail and connecting it to a battery. The nail would become a magnet and have a north and south pole while the battery is connected. Now say that take the nail electromagnet, run an axle through the middle of it and suspend it in the middle of a horseshoe magnet as shown in the figure below. If were to attach a battery to the electromagnet so that the north end of the nail appeared as shown, the basic law of magnetism tells that what would happen: The north end of the electromagnet would be repelled from the north end of the horseshoe magnet and attracted to the south end of the horseshoe magnet. The south end of the electromagnet would be repelled in a similar way. The nail would move about half a turn and then stop in the position shown.

Figure 3.4: Electromagnet in Horse Magnet

This is half-turn of motion is simply due to the way magnets naturally attract and repel one another. The key to an electric motor is to then go one step further so that, at the moment that this half-turn of motion completes, the field of the electromagnet flips. The flip causes the electromagnet to complete another half-turn of motion.it flip the magnetic field just by changing the direction of the electrons flowing in the wire. If the field of the electromagnet were flipped at precisely the right moment at the end of each half-turn of motion, the electric motor would spin freely.

Dept. of ECE, BNMIT

Page 11

2018-2019

AGRICULTURAL ROBOT

3.3.3 Armature, Commutator and Brushes Consider the image shown below. The armature takes the place of the nail in an electric motor. The armature is an electromagnet made by coiling thin wire around two or more poles of a metal core.

Figure 3.5: Armature

The armature has an axle, and the commutator is attached to the axle. In the diagram to the right, can see three different views of the same armature: front, side and end-on. In the endon view, the winding is eliminated to make the commutator more obvious. It shows that the commutator is simply a pair of plates attached to the axle. These plates provide the two connections for the coil of the electromagnet.

Figure 3.6: Brushes and commutator Dept. of ECE, BNMIT

Page 12

2018-2019

AGRICULTURAL ROBOT

The "flipping the electric field" part of an electric motor is accomplished by two parts: the commutator and the brushes. Figure shows how the commutator and brushes work together to let current flow to the electromagnet, and also to flip the direction that the electrons are flowing at just the right moment. The contacts of the commutator are attached to the axle of the electromagnet, so they spin with the magnet. The brushes are just two pieces of springy metal or carbon that make contact with the contacts of the commutator.

Parts of Motor Put Together

Figure 3.7: Commutator Action

In the figure the armature winding has been left out so that it is easier to see the commutator in action. The key thing to notice is that as the armature passes through the horizontal position, the poles of the electromagnet flip. Because of the flip, the north pole of the electromagnet is always above the axle so it can repel the field magnet's North Pole and attract the field magnet's South Pole. If ever have the chance to take apart a small electric motor, will find that it contains the same pieces described above: two small permanent magnets, a commutator, two brushes, and an electromagnet made by winding wire around a piece of metal. Almost always, however, the rotor will have three poles rather than the two poles as shown in this article. There are two good reasons for a motor to have three poles:

Dept. of ECE, BNMIT

Page 13

2018-2019

AGRICULTURAL ROBOT

It causes the motor to have better dynamics. In a two-pole motor, if the electromagnet is at the balance point, perfectly horizontal between the two poles of the field magnet when the motor starts, imagine that the armature getting "stuck" there. That never happens in a threepole motor. Each time the commutator hits the point where it flips the field in a two-pole motor, the commutator shorts out the battery (directly connects the positive and negative terminals) for a moment. This shorting waste energy and drains the battery needlessly. A three-pole motor solves this problem as well. It is possible to have any number of poles, depending on the size of the motor and the specific application it is being used in. The motor being dissected here is a simple electric motor that would typically find in a toy:

Figure 3.8: Dissected Motor

Fig 3.8 shows a small motor, about as big around as a dime. From the outside it can see the steel can that forms the body of the motor, an axle, a nylon end cap and two battery leads. If hook of the battery leads of the motor up to a flashlight battery, the axle will spin. If it reverse the leads, it will spin in the opposite direction. Here are two other views of the same motor. (Note the two slots in the side of the steel can in the second shot -- their purpose will become more evident in a moment.

Dept. of ECE, BNMIT

Page 14

2018-2019

AGRICULTURAL ROBOT

Figure 3.9: Nylon End Caps

The nylon end cap is held in place by two tabs that are part of the steel can. By bending the tabs back, it can free the end cap and remove it. Inside the end cap are the motor's brushes. These brushes transfer power from the battery to the commutator as the motor spins.

3.3.4 Other Motor Parts The axle holds the armature and the commutator. The armature is a set of electromagnets, in this case three. The armature in this motor is a set of thin metal plates stacked together, with thin copper wire coiled around each of the three poles of the armature. The two ends of each wire (one wire for each pole) are soldered onto a terminal, and then each of the three terminals is wired to one plate of the commutator. The figures below make it easy to see the armature, terminals and commutator.

Fig 3.10

Dept. of ECE, BNMIT

Page 15

2018-2019

AGRICULTURAL ROBOT

Fig 3.11

Figure 3.12 Other Motor Parts

The final piece of any DC electric motor is the field magnet. The field magnet in this motor is formed by the can itself plus two curved permanent magnets. One end of each magnet rests against a slot cut into the can, and then the retaining clip presses against the other ends of both magnets.

3.3.5 H-Bridge Take a battery; hook the positive side to one side of the DC motor. Then connect the negative side of the battery to the other motor lead. The motor spins forward. If the swap the battery leads the motor spins in reverse.

Dept. of ECE, BNMIT

Page 16

2018-2019

AGRICULTURAL ROBOT

Figure 3.13: Connections for clockwise rotation of motor

If it connects this circuit to a small hobby motor can control the motor with a processor (MCU, etc.) Applying a logical one, (+12 Volts in our example) to point A causes the motor to turn forward. Applying a logical zero, (ground) causes the motor to stop turning (to coast and stop).

Figure 3.14: Connections for Anti-Clockwise Rotation of Motor

Hook the motor up in this fashion and the circuit turns the motor in reverse when it is logical one (+12Volts) to point B. Apply a logical zero, which is usually a ground, causes the motor to stop spinning.

Dept. of ECE, BNMIT

Page 17

2018-2019

AGRICULTURAL ROBOT

NOTE: When these relay circuits are connected, remember to put a diode across the coil of the relay. This will keep the spike voltage (back EMF), coming out of the coil of the relay, from getting into the MCU and damaging it. The anode, which is the arrow side of the diode, should connect to ground. The bar, which is the Cathode side of the diode, should connect to the coil where the MCU connects to the relay. It can also pulse the motor control line, (A or B) on and off. This power the motor in short burst and gets varying degrees of torque, which usually translates into variable motor speed. But if it needs to control the motor in both forward and reverse with a processor, it will need more circuitry and H-Bridge.An Hbridge is an electronic circuit which enables a voltage to be applied across a load in either direction. These circuits are often used in robotics and other applications to allow DC motors to run forwards and backwards. H-bridges are available as integrated circuits or can be built from discrete components. Let's start with the name, H-bridge. Sometimes called a "full bridge" the H-bridge is so named because it has four switching elements at the "corners" of the H and the motor forms the cross bar. The basic bridge is shown in the figure to the right.

Figure 3.15: Basic H-Bridge

The key fact to note is that there are, in theory, four switching elements within the bridge. These four elements are often called, high side left, high side right, low side right, and low side left (when traversing in clockwise order). The "high side drivers" are the relays that control the positive voltage to the motor. This is called sourcing current. "Low side drivers" are the relays that control the negative voltage to sink current to the motor. "Sinking current" is the term for connecting the circuit to the negative side of the power supply, which is usually ground.

Dept. of ECE, BNMIT

Page 18

2018-2019

AGRICULTURAL ROBOT

Figure 3.16: Schematic Diagram of H-Bridge Using Relay

The switches are turned on in pairs, either high left and lower right, or lower left and high right, but never both switches on the same "side" of the bridge. If both switches on one side of a bridge are turned on it creates a short circuit between the battery plus and battery minus terminals. This phenomenon is called shoot through in the Switch-Mode Power Supply (SMPS) literature. If the bridge is sufficiently powerful it will absorb that load and batteries will simply drain quickly. Usually however the switches in question melt. To power the motor, turn on two switches that are diagonally opposed. In the picture to the right, imagine that the high side left and low side right switches are turned on.

Figure 3.17: Working of Basic Bridge

Then for reverse turn on the upper right and lower left circuits and power flows through the motor in reverse.

Dept. of ECE, BNMIT

Page 19

2018-2019

AGRICULTURAL ROBOT

3.3.6 Soil Moisture Sensor

Figure 3.18 Soil Moisture Sensor

FC-28 soil moisture sensor is a simple breakout for measuring the moisture in a soil and similar materials. The soil moisture sensor is pretty straight forward to use. The two large exposed pads function as probes for the sensor, together acting as a variable resistor. The more water that is in the pads will be and will results in a lower resistance, and a higher an out.

Features 

Digital output threshold adjust potentiometer



Power and digital output indicator or LED’s



Analog and digital outputs



Mounting hole for easy installation

Technical Specifications 

Operating voltage 3.3V-5V



2.PCB size:3.2cm x 1.4cm



3.Power indicators:(red) and digital switching output indicator(green) Comparator

Dept. of ECE, BNMIT

Page 20

2018-2019

AGRICULTURAL ROBOT

3.3.7 Relay Circuit A relay is an electrically operated switch. Current flowing through the coil of the relay creates a magnetic field which attracts a lever and changes the switch contacts. The coil current can be on or off so relays have two switch positions and they are double throw (changeover) switches.

SPDT ( Single Pole Dual Through) Relay

Figure 3.19 Typical SPDT Relay

Relay Construction Relays are amazingly simple devices. There are four parts in every relay: 

Electromagnet



Armature that can be attracted by electromagnet



Spring



Set of electrical contacts

Relays allow one circuit to switch a second circuit which can be completely separate from the first. For example, a low voltage battery circuit can use a relay to switch a 230V AC mains circuit. There is no electrical connection inside the relay between the two circuits; the link is magnetic and mechanical. The coil of a relay passes a relatively large current, typically 30mA for a 12V relay, but it can be as much as 100mA for relays designed to operate from lower voltages. Most ICs (chips) cannot provide this current and a transistor is usually used to amplify the small IC current to the larger value required for the relay coil.

Dept. of ECE, BNMIT

Page 21

2018-2019

AGRICULTURAL ROBOT

Relays are usually SPDT or DPDT but they can have many more sets of switch contacts, for example relays with 4 sets of changeover contacts are readily available. Most relays are designed for PCB mounting but solder wires directly to the pins providing to take care to avoid melting the plastic case of the relay. The supplier's catalogue should shows the relay's connections. The coil will be obvious and it may be connected either way round. Relay coils produce brief high voltage 'spikes' when they are switched off and this can destroy transistors and ICs in the circuit. To prevent damage, it must connect a protection diode across the relay coil. The animated picture shows a working relay with its coil and switch contacts. That can see a lever on the left being attracted by magnetism when the coil is switched on. This lever moves the switch contacts. There is one set of contacts (SPDT) in the foreground and another behind them, making the relay DPDT.

The relay's switch connections are usually labeled COM, NC and NO: 1.

COM = Common, always connect to this; it is the moving part of the switch.

2.

NC = Normally Closed, COM is connected to this when the relay coil is off.

3 NO = Normally Open, COM is connected to this when the relay coil is on

DPDT (Dual Pole Dual Through) Relay

Figure 3.20: Typical DPDT Relay

This is similar to SPDT switch but it has pair of Normally Open (NO) and Normally Closed (NC) contacts. When the relay is energized both side contacts will operate at a time. Thus, it is more use full at many applications.

Dept. of ECE, BNMIT

Page 22

2018-2019

AGRICULTURAL ROBOT

Relay Connected To Geared Motor

Figure 3.21: Relay and DC Motor Connection

As shown above initially the motor is connected to 12V supply. A DPDT relay requires 12V DC and 35mA of Current to operate. An amplifier stage is required to drive DPDT relay, since microcontroller I/O provides only 25mA of current. ULN2803 IC is used for this purpose. It accepts signal from the microcontroller and amplifies it operate DPDT relay. When microcontroller output becomes high, ULN 2803 turn on the DPDT relay. Hence Motor gets connected to Supply and starts rotating.

3.3.8 Battery

Figure 3.22 12v Battery

Dept. of ECE, BNMIT

Page 23

2018-2019

AGRICULTURAL ROBOT

The Battery (Dry Cell)

The common battery (dry cell) is a device that changes chemical energy to electrical energy. Dry cells are widely used in toys, flashlights, portable radios, cameras, hearing aids, and other devices in common use. A battery consists of an outer case made of zinc (the negative electrode), a carbon rod in the center of the cell (the positive electrode), and the space between them is filled with an electrolyte paste. In operation the electrolyte, consisting of ground carbon, Manganese dioxide, Sal ammoniac, and zinc chloride causes the electrons to flow and produce electricity. Battery is used for store the solar energy which can be further converted into electrical energy. The battery should requires following properties, 

Long life



High reliability



Low cost



High overall efficiency

Dept. of ECE, BNMIT

Page 24

2018-2019

AGRICULTURAL ROBOT

3.3.8.1 Battery specifications Table 3.1: Battery specifications.

. Dimension (Body)

150*64*92 mm

Weight

1 kg

Dimension (Battery terminals)

4.8*0.8 mm

Voltage

12V DC

Capacity

3Ah

Technology

Seal lead acid

Cycle use

14.5 to 14.9V DC

Stand by use

1.6 to 13.8V DC

Initial current

< 2.8 A

Stand by charge voltage

13.8 V

Estimated stand by time

3 hours

Dept. of ECE, BNMIT

Page 25

2018-2019

AGRICULTURAL ROBOT

3.3.9 Voltage Regulator 7805

Figure 3.23: Voltage Regulator

Features 1.

Output Current up to 1A.

2.

Output Voltages of 5, 6, 8, 9, 10, 12, 15, 18, 24V.

3.

Thermal Overload Protection.

4.

Short Circuit Protection.

5.

Output Transistor Safe Operating Area Protection.

Description The LM78XX/LM78XXA series of three-terminal positive regulators are available in the TO-220/D-PAK package and with several fixed output voltages, making them useful in a Wide range of applications. Each type employs internal current limiting, thermal shutdown and safe operating area protection, making it essentially indestructible. If adequate heat sinking is provided, they can deliver over 1A output Current. Although designed primarily as fixed voltage regulators, these devices can be used with external components to obtain adjustable voltages and currents.

Dept. of ECE, BNMIT

Page 26

2018-2019

AGRICULTURAL ROBOT

Internal Block Diagram

Figure 3.24: Block Diagram of 7805

3.3.10 Liquid Crystal Display This is the first interfacing example for the Parallel Port. it will start with something simple. This example doesn't use the Bi-directional feature found on newer ports, thus it should work with most, if not all Parallel Ports. It however doesn't show the use of the Status Port as an input for a 16 Character x 2 Line LCD Module to the Parallel Port. These LCD Modules are very common these days, and are quite simple to work with, as all the logic required running them is on board.

LCD Background Frequently, an 8051 program must interact with the outside world using input and output devices that communicate directly with a human being. One of the most common devices attached to an 8051 is an LCD display. Some of the most common LCDs connected to the 8051 are 16x2 and 20x2 displays. This means 16 characters per line by 2 lines and 20 characters per line by 2 lines, respectively. Fortunately, a very popular standard exists which allows us to communicate with the vast majority of LCDs regardless of their manufacturer. The standard is referred to as HD44780U, which refers to the controller chip which receives data from an external source (in this case, the 8051) and communicates directly with the LCD.

Dept. of ECE, BNMIT

Page 27

2018-2019

AGRICULTURAL ROBOT

Figure 3.25 16*2 LCD Display

Figure 3.26: Internal Connection of LCD

The three control lines are referred to as EN, RS, and RW. The EN line is called "Enable." This control line is used to tell the LCD that are sending it data. To send data to the LCD, the program should make sure this line is low (0) and then set the other two control lines and/or put data on the data bus. When the other lines are completely ready, bring EN high (1) and wait for the minimum amount of time required by the LCD datasheet (this varies from LCD to LCD), and end by bringing it low (0) again. The RS line is the "Register Select" line. When RS is low (0), the data is to be treated as a command or special instruction (such as clear screen, position cursor, etc.). When RS is high (1), the data being sent is text data which should be displayed on the screen. For example, to display the letter "T" on the screen would set RS high. Dept. of ECE, BNMIT

Page 28

2018-2019

AGRICULTURAL ROBOT

The RW line is the "Read/Write" control line. When RW is low (0), the information on the data bus is being written to the LCD. When RW is high (1), the program is effectively querying (or reading) the LCD. Only one instruction ("Get LCD status") is a read command. All others are write commands--so RW will almost always be low .Finally, the data bus consists of 4 or 8 lines (depending on the mode of operation selected by the user). In the case of an 8bit data bus, the lines are referred to as DB0, DB1, DB2, DB3, DB4, DB5, DB6, and DB7.

3.4 SOFTWARE DETAILS 

Keil microvision3



Embedded c



Matlab



SVM Algorithm

Dept. of ECE, BNMIT

Page 29

2018-2019

AGRICULTURAL ROBOT

3.4.1 Keil microvision3 The µVision3 IDE is a Windows-based software development platform that combines a robust editor, project manager, and make facility. µVision3 integrates all tools including the C compiler, macro assembler, linker/locator, and HEX file generator. The µVision3 IDE offers numerous features and advantages that help you quickly and successfully develop embedded applications. They are easy to use and are guaranteed to help you achieve your design goals.

Features 1) The µVision3 Simulator is the only debugger that completely simulates all on-chip peripherals. 2) Simulation capabilities may be expanded using the Advanced Simulation Interface (AGSI). 3) µVision3 incorporates project manager, editor, and debugger in a single environment. 4) The µVision3 Device Database automatically configures the development tools for the target microcontroller. 5) The µVision3 IDE integrates additional third-party tools like VCS, CASE, and FLASH/Device Programming. 6) The ULINK USB-JTAG Adapter supports both Debugging and Flash programming with configurable algorithm files. 7) Identical Target Debugger and Simulator User Interface. 8) The Code Coverage feature of the µVision3 Simulator provides statistical analysis of your program's execution.

Benefits 1) Write and test application code before production hardware is available. Investigate different hardware configurations to optimize the hardware design. 2) Sophisticated systems can be accurately simulated by adding your own peripheral drivers. 3) Safety-critical systems can be thoroughly tested and validated. Execution analysis reports can be viewed and printed for certification requirements. 4) Accelerates application development. While editing, you may configure debugger features. While debugging, you may make source code modifications.

Dept. of ECE, BNMIT

Page 30

2018-2019

AGRICULTURAL ROBOT

3.4.2 Embedded C When designing software for a smaller embedded system with the 8051, it is very common place to develop the entire product using assembly code. With many projects, this is a feasible approach since the amount of code that must be generated is typically less than 8 kilobytes and is relatively simple in nature. If a hardware engineer is tasked with designing both the hardware and the software, he or she will frequently be tempted to write the software in assembly language. The trouble with projects done with assembly code can is that they can be difficult to read and maintain, especially if they are not well commented. Additionally, the amount of code reusable from a typical assembly language project is usually very low. Use of a higher-level language like C can directly address these issues. A program written in C is easier to read than an assembly program. Since a C program possesses greater structure, it is easier to understand and maintain. Because of its modularity, a C program can better lend itself to reuse of code from project to project. The division of code into functions will force better structure of the software and lead to functions that can be taken from one project and used in another, thus reducing overall development time. A high order language such as C allows a developer to write code, which resembles a human’s thought process more closely than does the equivalent assembly code. [25]The developer can focus more time on designing the algorithms of the system rather than having to concentrate on their individual implementation. This will greatly reduce development time and lower debugging time since the code is more understandable.

By using a language like C, the programmer does not have to be intimately familiar with the architecture of the processor. This means that someone new to a given processor can get a project up and running quicker, since the internals and organization of the target processor do not have to be learned. Additionally, code developed in C will be more portable to other systems than code developed in assembly. Many target processors have C compilers available, which support ANSI C.

Dept. of ECE, BNMIT

Page 31

2018-2019

AGRICULTURAL ROBOT

3.4.3 MATLAB The tutorial are independent of the rest of the document. The primarily objective is to help you learn quickly the first steps. The emphasis here is “learning by doing”. Therefore, the best way to learn is by trying it yourself. Working through the examples will give you a feel for the way that Matlab operates. In this introduction we will describe how Matlab handles simple numerical expressions and mathematical formulas. The name Matlab stands for Matrix Laboratory. Matlab was written originally to provide easy access to matrix software developed by the LINPACK (linear system package) and EISPACK (Eigen system package) projects. Matlab is a high-performance language for technical computing. It integrates computation, visualization, and programming environment. Furthermore, Matlab is a modern programming language environment: it has sophisticated data structures, contains built-in editing and debugging tools, and supports object-oriented programming. These factors make Matlab an excellent tool for teaching and research. Matlab has many advantages compared to conventional computer languages (e.g., C, FORTRAN) for solving technical problems. Matlab is an interactive system whose basic data element is an array that does not require dimensioning. The software package has been commercially available since 1984 and is now considered as a standard tool at most universities and industries worldwide. It has powerful built-in routines that enable a very wide variety of computations. It also has easy to use graphics commands that make the visualization of results immediately available. Specific applications are collected in packages referred to as toolbox. There are toolboxes for signal processing, symbolic computation, control theory, simulation, Optimization, and several other fields of applied science and engineering

3.4.4 Support vector machine SVM is a non-linear classifier, and is a newer trend in machine learning algorithm. SVM is popularly used in many pattern recognition problems including texture classification. SVM is designed to work with only two classes. This is done by maximizing the margin from the hyper plane. The samples closest to the margin that were selected to determine the hyper plane is known as support vectors.

Dept. of ECE, BNMIT

Page 32

2018-2019

AGRICULTURAL ROBOT

Multiclass classification is applicable and basically built up by various two class SVMs to solve the problem, either by using one-versus-all or one. Another feature is the kernel function that projects the non-linearly separable data from low-Dimensional space to a space of higher dimension so that they may become separable in the higher dimensional space too. The first step in the proposed approach is to capture the sample from the digital camera and extract the features. The sample is captured from the digital camera and the features are then stored in the database. Preprocessing images is used to removing low-frequency background noise. Normalizing the intensity of the individual particles of images. It enhance the visual appearance of images. Improve the manipulation of datasets. It is the technique of enhancing data images prior to computational processing. The caution is enhancement techniques can emphasize image artifacts, or even lead to a loss of information if not correctly used. The steps involved in preprocessing are to get an input image and then the image has to be enhanced. Then the RGB image is converted to a gray scale image to get a clear identification of pests on leaves. Noise removal function can be performed by using filtering techniques. Mean filtering: The 3x3 subregion is scanned over the entire image. At each position the center pixel is replaced by the average value. Median filtering: The 3x3 sub-region is scanned over the entire image. At each position the center pixel is replaced by the median value.

3.5. Summary We are planning an effort to overcome some problems in agriculture. The rapid growth in the industries is influencing the labours that are situating in the villages to migrate to the cities. This creating the labour problem in agriculture. The wages for the labour is also more. As the prices of commodities such as food grains, fuels, cloths and other essentials of daily life is increasing rapidly the labours demand for the more wages from the owners. By using this robot in the field of agriculture we can help the farmers in the initial stage of agriculture i.e. during the seeding and fertilizing. This robot can be a better substitute for the human who performs the seeding and fertilizing. This robot is very useful for the farmers who are interested to do agriculture activity but facing the labor problem.

Dept. of ECE, BNMIT

Page 33

2018-2019

AGRICULTURAL ROBOT

CHAPTER-4 4.1 FLOW CHART

Figure 4.1 Flow Diagram

Dept. of ECE, BNMIT

Page 34

2018-2019

AGRICULTURAL ROBOT

When the system is ON, Initialization of LCD takes place and also light movements of robot can observed because of H-BRIDGE (IC L2932). The control switch can be either switched ON/OFF depending on the mode the user wants (automatic/manual). If the switch is ON automatic mode is selected, the further process is done automatically and if switch is OFF then the manual mode is selected. The command (for the work to be done) is given to the Robot through the Wi-Fi module incorporated in the system. The Robot then starts operating based on the command given i.e., seeding, ploughing and levelling of the soil. The system checks for level of moisture content in the soil. If the moisture level is equal to or more than optimal soil moisture level than the pump is OFF and if it falls below the optimal moisture level than the pump is turned on to maintain the soil hydration level. The system also checks if the crop is infected by any kinds of microbes or if any diseases are found. If a disease is found, then the Robot sprinkles the suitable pesticide on it.

Dept. of ECE, BNMIT

Page 35

2018-2019

AGRICULTURAL ROBOT

CHAPTER 5 5.1 WHAT IS A GSM MODEM? (GPRS MODEM? OR 3G MODEM?) A GSM modem is a specialized type of modem which accepts a SIM card, and operates over a subscription to a mobile operator, just like a mobile phone. From the mobile operator perspective, a GSM modem looks just like a mobile phone. When a GSM modem is connected to a computer, this allows the computer to use the GSM modem to communicate over the mobile network. While these GSM modems are most frequently used to provide mobile internet connectivity, many of them can also be used for sending and receiving SMS and MMS messages. A GSM modem can be a dedicated modem device with a serial, USB or Bluetooth connection, or it can be a mobile phone that provides GSM modem capabilities.For the purpose of this document, the term GSM modem is used as a generic term to refer to any modem that supports one or more of the protocols in the GSM evolutionary family, including the 2.5G technologies GPRS and EDGE, as well as the 3G technologies WCDMA, UMTS, HSDPA and HSUPA. A GSM modem exposes an interface that allows applications such as now SMS to send and receive messages over the modem interface. The mobile operator charges for this message sending and receiving as if it was performed directly on a mobile phone. To perform these tasks, a GSM modem must support an “extended AT command set” for sending/receiving SMS messages, as defined in the ETSI GSM 07.05 and 3GPP TS 27.005 specifications.

History of GSM During the early 1980s, analog cellular telephone systems were experiencing rapid growth in Europe, particularly in Scandinavia and the United Kingdom, but also in France and Germany. Each country developed its own system, which was incompatible with everyone else's in equipment and operation. This was an undesirable situation, because not only was the mobile equipment limited to operation within national boundaries, which in a unified Europe were increasingly unimportant, but there was also a very limited market for each type of equipment, so economies of scale and the subsequent savings could not be realized. Dept. of ECE, BNMIT

Page 36

2018-2019

AGRICULTURAL ROBOT

The Europeans realized this early on, and in 1982 the Conference of European Posts and Telegraphs (CEPT) formed a study group called the Groupe Spécial Mobile (GSM) to study and develop a pan-European public land mobile system. The proposed system had to meet certain criteria: 1. Good subjective speech quality 2. Low terminal and service cost 3. Support for international roaming 4. Ability to support handheld terminals 5. Support for range of new services and facilities 6. Spectral efficiency 7. ISDN compatibility

In 1989, GSM responsibility was transferred to the European Telecommunication Standards Institute (ETSI), and phase I of the GSM specifications were published in 1990. Commercial service was started in mid-1991, and by 1993 there were 36 GSM networks in 22 countries. Although standardized in Europe, GSM is not only a European standard. Over 200 GSM networks (including DCS1800 and PCS1900) are operational in 110 countries around the world. In the beginning of 1994, there were 1.3 million subscribers worldwide, which had grown to more than 55 million by October 1997. With North America making a delayed entry into the GSM field with a derivative of GSM called PCS1900, GSM systems exist on every continent, and the acronym GSM now aptly stands for Global System for Mobile communications. The developers of GSM chose an unproven (at the time) digital system, as opposed to the then-standard analog cellular systems like AMPS in the United States and TACS in the United Kingdom. They had faith that advancements in compression algorithms and digital signal processors would allow the fulfillment of the original criteria and the continual improvement of the system in terms of quality and cost. The over 8000 pages of GSM recommendations try to allow flexibility and competitive innovation among suppliers, but provide enough standardization to guarantee proper interworking between the components of the system. This is done by providing functional and interface descriptions for each of the functional entities defined in the system.

Dept. of ECE, BNMIT

Page 37

2018-2019

AGRICULTURAL ROBOT

Services provided by GSM From the beginning, the planners of GSM wanted ISDN compatibility in terms of the services offered and the control signaling used. However, radio transmission limitations, in terms of bandwidth and cost, do not allow the standard ISDN B-channel bit rate of 64 kbps to be practically achieved. Using the ITU-T definitions, telecommunication services can be divided into bearer services, teleservices, and supplementary services. The most basic teleservice supported by GSM is telephony. As with all other communications, speech is digitally encoded and transmitted through the GSM network as a digital stream. There is also an emergency service, where the nearest emergency-service provider is notified by dialing three digits (similar to 911). Other data services include Group 3 facsimile, as described in ITU-T recommendation T.30, which is supported by use of an appropriate fax adaptor. A unique feature of GSM, not found in older analog systems, is the Short Message Service (SMS). SMS is a bidirectional service for short alphanumeric (up to 160 bytes) messages. Messages are transported in a store-andforward fashion. For point-to-point SMS, a message can be sent to another subscriber to the service, and an acknowledgement of receipt is provided to the sender. SMS can also be used in a cell-broadcast mode, for sending messages such as traffic updates or news updates. Messages can also be stored in the SIM card for later retrieval. Supplementary services are provided on top of teleservices or bearer services. In the current specifications, they include several forms of call forward (such as call forwarding when the mobile subscriber is unreachable by the network), and call barring of outgoing or incoming calls, for example when roaming in another country. Many additional supplementary services will be provided, such as caller identification, call waiting, multi-party conversations.

5.2 ZIGBEE In 21st century, wireless sensor networks are becoming necessary and seen as in dispensible in various medical and telecommunication equipments, smart energy resources, home automation products etc., which require monitoring and control. Zigbee is a wireless technology, which communicates on the principle of IEEE 802.15.4 standard. IEEE 802.15.4 is a standard that states the details for the lower layers of the communication.

Dept. of ECE, BNMIT

Page 38

2018-2019

AGRICULTURAL ROBOT

This standard focuses on the low-cost and low power communication. Because of Zigbee’s low cost, low power consumption and ability to connect in a mesh network, it is becoming more optimum solution for monitoring and control applications. Ability to connect in mesh network allows Zigbee to provide more range compared to other wireless technologies such as “INFRARED”, “BLUETOOTH” etc. In addition, it also provides high reliability of the data reproduced at receiver. It also consumes less power in communicating data between its transmitter and receiver, which means longer life with smaller batteries. The primary reason for low power consumption in Zigbee devices is that they work on very small duty cycle that helps them to have a longer life span. Variation in duty cycle depends upon the application usage, for example, some applications need data more frequently like in health centers compared to others such as home automation systems.

5.2.1 Types of Zigbee Devices Zigbee Coordinator This acts as the building block of the Zigbee communication. Zigbee coordinator forms the root of the various topologies like mesh, star, tree topology network etc. and communicates from one device to other. There is only one Zigbee coordinator in the whole Zigbee environment

Fig 5.1 Zigbee coordinator

5.2.2 Full Function Device Full function devices support all IEEE 802.15.4 functions and features that are defined by the standard. They can also function as a Zigbee coordinator. More memory and computing power availability helps them to work as router also, which helps in transmitting data to longer distances through different networks.

Dept. of ECE, BNMIT

Page 39

2018-2019

AGRICULTURAL ROBOT

Figure 5.2: Full function device

5.2.3 Reduced Function Device Reduced function devices just talk to the Zigbee coordinators or Full function devices. They cannot perform the functions of a router or coordinator

Figure 5.3: Reduced function device

5.2.4 Zigbee Network Network Setup: The Zigbee coordinator does Zigbee network initialization. As soon as the network is powered up, the coordinator starts the network initialization sequence. After that, the coordinator starts a search for the full function devices and reduced function devices to establish a network. Joining Network as a New Device Whenever a new device either Full Function Device (FFD) or Reduced Function Device (RFD) wants to join a network, it sends a request to all other parent capability devices such as FFDs that it wants to join the network. Dept. of ECE, BNMIT

Page 40

2018-2019

AGRICULTURAL ROBOT

Then all the parent devices send a packet which gives the information about their address and number of devices already connected to it. The child device that can be either FFD or RFD collects all the data and then selects one of the devices as a parent device, which is best suited for it. Then that parent device is responsible to provide the child device a unique ID. Joining Previous Network Zigbee devices save the information in a table whenever they are connected to a network. This table stores the information, which helps the device to reconnect to the same network again. So next time whenever they are switched on, they first look into that table about the previous information and try to connect to the old network. If the table is blank then they try to connect into a network as a new device.

Mechanism for Data Transfer Whenever a device wants to send a data packet, it has to check for channel. If the channel is idle, device can send a packet else it has to wait. If the receiver is FFD then transmitters can send the packet any time because its transceiver always remains ON. However if the receiver is RFD then there are chances that its transceiver is OFF to save power. So to avoid data loss all RFDs send a packet to their corresponding parent device as soon as there transceiver comes to ON position to get the data packet which was send to them when they were in sleeping mode .Zigbee Network Topology Zigbee network topology can be divided into three types

Star Topology Star topology consists of one Zigbee coordinator and one or more RFDs or FFDs. All end point devices directly communicate to coordinator. If the end point devices want to talk to each other they have to send the information to coordinator first and then coordinator sends that information to appropriate receiver.

Dept. of ECE, BNMIT

Page 41

2018-2019

AGRICULTURAL ROBOT

Figure 5.3 star topology

5.2.5 Zigbee Specifications: 1. 802.11 b or g or n protocol 2. Wi-Fi 2.4 GHz, support WPA or WPA2 3. Super small module size (11.5mm x 11.5mm) 4. Deep sleep power <10uA 5. Power down leakage current < 5uA 6. Integrated low power 32-bit MCU 7. Wake up and transmit packets in < 2ms 8. Standby power consumption of < 1.0mW (DTIM3)

5.3 LEAF DISEASE MODULE MATLAB The tutorial are independent of the rest of the document. The primarily objective is to help you learn quickly the first steps. The emphasis here is “learning by doing”. Therefore, the best way to learn is by trying it yourself. Working through the examples will give you a feel for the way that MATLAB operates. In this introduction we will describe how MATLAB handles simple numerical expressions and mathematical formulas.

Dept. of ECE, BNMIT

Page 42

2018-2019

AGRICULTURAL ROBOT

The name MATLAB stands for Matrix Laboratory. MATLAB was written originally to provide easy access to matrix software developed by the LINPACK (linear system package) and EISPACK (Eigen system package) projects.

MATLAB is a high-performance language for technical computing. It integrates computation,

visualization, and programming environment. Furthermore, MATLAB is a

modern programming language environment:

it has sophisticated data structures, contains

built-in editing and debugging tools, and supports object-oriented programming. These factors make MATLAB an excellent tool for teaching and research. MATLAB has many advantages compared to conventional computer languages (e.g., C, FORTRAN) for solving technical problems. MATLAB is an interactive system whose basic data element is an array that does not require dimensioning. The software package has been commercially available since 1984 and is now considered as a standard tool at most universities and industries worldwide.

It has powerful built-in routines that enable a very wide variety of computations. It also has easy to use graphics commands that make the visualization of results immediately available. Specific applications are collected in packages referred to as toolbox. There are toolboxes for signal processing, symbolic computation, control theory, simulation, optimization, and several other fields of applied science and engineering.

5.3.1 Starting MATLAB After logging into your account, you can enter MATLAB by double-clicking on the MATLAB shortcut icon (MATLAB 8.1.2) on your Windows desktop. When you start MATLAB, a special window called the MATLAB desktop appears. The desktop is a window that contains other windows. The major tools within or accessible from the desktop are: • The Command History • The Workspace • The Current Directory • The Help Browser • The Start button

Dept. of ECE, BNMIT

Page 43

2018-2019

AGRICULTURAL ROBOT

Figure 5.4: The graphical interface to the MATLAB workspace

When MATLAB is started for the first time, the screen looks like the one that shown in the Figure 5.4 This illustration also shows the default configuration of the MATLAB desktop. You can customize the arrangement of tools and documents to suite our needs.

Now, we are interested in doing some simple calculations. We will assume that you have sufficient understanding of your computer under which MATLAB is being run. You are now faced with the MATLAB desktop on your computer, which contains the prompt (>>) in the Command Window. Usually, there are 2 types of prompt: >> for full version EDU> for educational version

Note: To simplify the notation, we will use this prompt, >>, as a standard prompt sign, though our MATLAB version is for educational purpose.

Dept. of ECE, BNMIT

Page 44

2018-2019

AGRICULTURAL ROBOT

Using MATLAB as a calculator As an example of a simple interactive calculation, just type the expression you want to evaluate. Let’s start at the very beginning. For example, let’s suppose you want to calculate the expression, 1 + 2 × 3. You type it at the prompt command (>>) as follows, >>1+2*3 Ans =7

You will have noticed that i f you do not specify an output variable, MATLAB uses a default variable, short for answer, to store the results of the current calculation. Note that the variable is created (overwritten, if it is already existed). To avoid this, you may assign a value to a variable or output argument name. For example, >>x=1+2*3 x =7 Will result in x being given the value1+2×3=7. This variable name can always be used to refer to the results of the previous computations. Therefore, computing4xwill result in >>4*x Ans=28.0000

5.4 RUST DISEASE Pucciniamelanocephala is a fungal that causes rust disease. This fungal is now found in almost everywhere in all types of plants grown. The spread of rust disease has had economic impact. The symptoms start from small, elongated yellowish spots on both leaf surfaces. This spots increase in length, turn brown to orange-brown or red-brown in color. Lesions ranges are from 2-10 mm in length but these lesions can reach 30 mm. The lesions are no more than 1-3 mm in width. Infections of rust disease are usually most numerous toward the leaf tip and less toward the base. High rust disease severities can cause death of young leaves. Rust with high severity has caused reductions in stalk mass and numbers, thereby reducing plant growth. Rust pathogen incites new infections on living host tissue. Prevention of rust disease have been observed over the years, suggesting the existence of fungal variants. Spores of rust disease are well-suited to dissemination by air currents. It is well-adapted for atmospheric transport and it has been hypothesized that rust disease in the America came from the continent of Africa via high altitude trans-Atlantic winds. On local scale rust spores are develop in the direction of prevailing winds. Environmental factors that most influential in rust development are leaf wetness and atmospheric temperature.

Dept. of ECE, BNMIT

Page 45

2018-2019

AGRICULTURAL ROBOT

5.5 SHAPE FEATURE EXTRACTION Feature extractions used in this paper are solidity, extent, minor axis length and eccentricity. These features taken Shape feature extraction used in this paper are solidity, extent, minor axis length and eccentricity Shape. These features taken from research [3] in order to extract shape feature in diseased region. Eccentricity is used to recognize whether the rust shape is a circle or line segment. Eccentricity is the ratio of the distance between the foci of the ellipse and its major axis length. An ellipse whose eccentricity is 0 can recognized as a circle, while an ellipse whose eccentricity is 1 can recognized as a line segment. Minor axis length is used to measure length of axis of the diseased region. Minor axis length is the length of the minor axis of the ellipse that has the same normalized second central moments as the region. Extent is used to measure area of diseased region that is divided by the area of the bounding box. Extent is computed as the area divided by area of the bounding box. Solidity is used to measure area of diseased region divided by pixels in the convex hull. Solidity is the proportion of the pixels in the Convex hull that are also in the region. It is computed by dividing the area by convex area.

5.6 TEXTURE FEATURE EXTRACTION Gray Level Co-occurrence Matrix (GLCM) extract second order statistical texture features. Texture feature extraction used in this research is contrast, correlation, energy and homogeneity. These features taken from research [3] to extract texture feature in leaf diseased region. Contrast of the pixel and its neighbors is calculated over all of the image pixels. Contrast is used to measure contrast between neighborhood pixel.

Correlation is a measure of correlation of a pixel with its neighbors over all of the image.

Energy is a sum of G (grey level co-occurrence matrix elements.

Dept. of ECE, BNMIT

Page 46

2018-2019

AGRICULTURAL ROBOT

Homogeneity computes similarity of G to the diagonal matrix.

All of the four features described in this section represent texture of the images of diseased region in comparison with the normal one.

Color Feature Extraction Color is a distinctive feature for image representation that is invariant with respect to scaling, translation and rotation of an image. Mean, skewness and kurtosis are used to represent color as features. To do this, we transform RGB to LAB.

Mean used to represent average value of each color channel.

Skewness and kurtosis used to measure the distribution of each color channel. Skewness can be described as:

skewness is a measure of symmetry. If a distribution or data is symmetric, it looks the same to the left and right of the center point. Kurtosis can represent whether the data are peaked or flat relative to a normal distribution [12]. Kurtosis can be described as follows:

Combination of mean, skewness and kurtosis is used to represent color feature of normal and diseased image of leaf.

Dept. of ECE, BNMIT

Page 47

2018-2019

AGRICULTURAL ROBOT

5.7 SUPPORT VECTOR MACHINE Training sample in support vector machine is separable by a hyperplane. This hyperplane is computed according to the decision function f(x) = sign (w.x) + b, where w is a weight vector and b is a threshold cut-off. To maximize the margin, w € f and b have to be minimized to:

Additional slack variables should be added to prevent over fitting.

SVM was chosen as the binary classifier because it can classify accurately even when limit samples were available [6]. There are different kernel function in SVM classifier. Table 1 shows different types of kernel in SVM. They are linear, quadratic, polynomial, and radial basis function. Table 5.1 Different Kernel in SVM

SVMs (Support Vector Machines) are a useful technique for data classification. Classification task usually involves separating data into training and testing sets. Each instance in the training set contains one \target value" (i.e. the class labels) and several attributes" (i.e. the features or observed variables). The goal of SVM is to produce a model (based on the training data) which predicts the target values of the test data given only the test data attributes. A Support Vector Machine (SVM) is a discriminative classifier formally defined by a separating hyperplane. In other words, given labeled training data (supervised learning), the algorithm outputs an optimal hyperplane which categorizes new examples. Let’s consider the following simple problem:

Dept. of ECE, BNMIT

Page 48

2018-2019

AGRICULTURAL ROBOT

We are given a set of n points (vectors) : x1, x2, x3, ….. xn such that xi is a vector of length m, and each belong to one of two classes we label them by “+1” and “-1”. So our training set is

(10)

We want to find a separating hyperplane that separates these points into the two classes. “The positives” (class “+1”) and “The negatives” (class “-1”). Let’s introduce the notation used to define formally a hyperplane:

Where, β is known as the weight vector andβo as the bias. For a linearly separable set of 2Dpoints which belong to one of two classes, find a separating straight line. In Figure you can see that there exist multiple lines that offer a solution to the problem.

Figure 5.5. Green color hyperplane separating two classes of red squares and blue circles.

A line is bad if it passes too close to the points because it will be noise sensitive and it will not generalize correctly. Therefore, our goal should be to find the line passing as far as possible from all points. Dept. of ECE, BNMIT

Page 49

2018-2019

AGRICULTURAL ROBOT

Then, the operation of the SVM algorithm is based on finding the hyperplane that gives the largest minimum distance to the training examples. Twice, this distance receives the important name of margin within SVM’s theory. Therefore, the optimal separating hyper plane maximizes the margin of the training data which is depicted well in the Figure 4.5.The optimal hyper plane can be represented in an infinite number of different ways by scaling of β and βo. As a matter of convention, among all the possible representations of the hyperplane, the one chosen is

(12)

Where

symbolizes the training examples closest to the hyperplane. In general, the

training examples that are closest to the hyperplane are called support vectors. This representation is known as the canonical hyperplane.

Figure 5.6 Finding an optimal hyperplane.

The data usually contain noises, which result in overlapping samples in pattern space, and there may produce some outliers in the training data set. So we need to remove these outliers from the training data set so that a better decision boundary can be easily formed. We here apply smoothening method to remove those points that do not agree with the majority of their k nearest neighbors.

Dept. of ECE, BNMIT

Page 50

2018-2019

AGRICULTURAL ROBOT

In particular, by comparing with the 1-NN and k-NN classifiers, it can be found that the SVM classifier can not only save the storage space but also reduce the classification time under the case of no sacrificing the classification accuracy.

5.8. HISTOGRAM STRETCHING IS USED TO ENHANCE THE CONTRAST Contrast is the difference between maximum and minimum pixel intensity. An important class of point operations is based upon the manipulation of an image histogram or a region histogram. The most important examples are described below.

Frequently, an image is scanned in such a way that the resulting brightness values do not make full use of the available dynamic range. This can be easily observed in the histogram of the brightness values shown in Figure 5.1. By stretching the histogram over the available dynamic range we attempt to correct this situation. If the image is intended to go from brightness 0 to brightness 2B-1, then one generally maps the 0% value (or minimum as defined) to the value 0 and the 100% value (or maximum) to the value 2B-1. The appropriate transformation is given by:

(13)

This formula, however, can be somewhat sensitive to outliers and a less sensitive and more general version is given by:

(14)

Dept. of ECE, BNMIT

Page 51

2018-2019

AGRICULTURAL ROBOT

Figure 5.7 The stretched histogram of the image.

In this second version one might choose the 1% and 99% values for plow% and phigh%, respectively, instead of the 0% and 100% values represented by eq. . . . It is also possible to apply the contrast-stretching operation on a regional basis using the histogram from a region to determine the appropriate limits for the algorithm. Note that in eqs. And it is possible to suppress the term 2B-1 and simply normalize the brightness range to 0 <= b[m,n] <= 1. This means representing the final pixel brightnesses as reals instead of integers but modern computer speeds and RAM capacities make this quite feasible.

5.8.1. Contrast stretching Consider Figure 5.7 The histogram of the image is shown in Figure 3.8Now we calculate contrast from this image. Contrast = 225.Now we will increase the contrast of the image. Increasing the contrast of the image: The formula for stretching the histogram of the image to increase the contrast is

(15)

Dept. of ECE, BNMIT

Page 52

2018-2019

AGRICULTURAL ROBOT

Figure 5.8 Image used for contrast stretching.

Figure 5.9. Histogram of the image.

The formula requires finding the minimum and maximum pixel intensity multiply by levels of gray. In our case the image is 8bpp, so levels of gray are 256. The minimum value is 0 and the maximum value is 225. So the formula in our case is

(15) Where f(x,y) denotes the value of each pixel intensity. For each f(x,y) in an image, we will calculate this formula. After doing this, we will be able to enhance our contrast. The image in Figure 5 will appear after applying histogram stretching.

Dept. of ECE, BNMIT

Page 53

2018-2019

AGRICULTURAL ROBOT

Figure 5.10. Image after applying histogram stretching.

The stretched histogram of this image has been shown in Figure 1. Note the shape and symmetry of histogram. The histogram is now stretched or in other means expands. Have a look at it. In this case the contrast of the image can be calculated as Contrast = 240 Hence we can say that the contrast of the image is increased. Note: this method of increasing contrast does not work always, but it fails on some cases.

5.9 SOBEL EDGE DETECTION Edge detection is more popular for identifying discontinuities in gray level than detecting isolated points and thin lines .The edge is the boundary between two regions with relatively distinct gray level properties. It is assumed here that the transition between two regions can be properties. The transition between two regions can be determined based on the gray level discontinuities .The Sobel operator performs a 2-D spatial gradient measurement on an image and so emphasizes regions of high spatial frequency that correspond to edges. In the input grayscale image, approximate gradient magnitude is also identified at each point by the edge detector. The operator consists of a pair of 3x3 convolution kernels which is rotated by 90 degree [10]. The convolution masks of the Sobel detector are given in Figure 5.11

Dept. of ECE, BNMIT

Page 54

2018-2019

AGRICULTURAL ROBOT

Figure 5.11. Sobel mask.

Input: A Sample Image. Output: Detected Edges. Step 1: Accept the input image. Step 2: Apply mask Gx,Gy to the input image. Step 3: Apply Sobel edge detection algorithm and the gradient. Step 4: Masks manipulation of Gx,Gy separately on the input image. Step 5: Results combined to find the absolute magnitude of the gradient. Step 6: The absolute magnitude is the output edges.

5.10. PROPOSED ALGORITHM FLOW

Main steps are data collection which contain normal and diseased images, image preprocessing, and feature extraction and classification Real data of sugarcane images are collected from sugarcane field’s survey in Malang. Observation is conducted by capturing photos of sugarcane leaf on a paper. There are 200 data of normal sugarcane leaves and 200 data of sugarcane leaves with rust disease. Figure 4.6.1 & 4.7 are data that we collected from field survey. Figure 3 shows normal sugarcane leaf. Figure 4.9 shows sugarcane leaf with rust disease. Dept. of ECE, BNMIT

Page 55

2018-2019

AGRICULTURAL ROBOT

After collecting the image data, these images are pre-processed. Firstly, leaf area that represents rust disease are selected. After that, these images are resized to 100 x 100 pixels to reduce computational time. The contrast of these images are enhanced to a maximum value. Figure 4.7 shows

image results after pre-processed. Original images are shown in Figure

4.6.1 and 4.7, results after preprocessed with process described above shown in Figure 4.7.

Figure 5.12 Rust Disease in a Leaf

Figure 5.13. Result of Image Pre-processing

Dept. of ECE, BNMIT

Page 56

2018-2019

AGRICULTURAL ROBOT

Figure 5.14. Binary Image

Table 5.2 Feature Extraction Shape

Texture

Color

Solidity

Contrast

Mean

Extent

Correlation

Skewness

Minor axis length

Energy

Kurtosis

Eccentricity

Homogeneity

To extract shape feature, the color image is processed to be a binary using Otsu thresholding. Figure 6 shows the results of binary image from normal sugarcane leaf with Otsu thresholding. Combination of color, shape and texture feature of an image are used in feature extraction. To extract color feature, we transform image from RGB to LAB color. Table 2 shows feature extraction used in this research. We use shape, texture and color feature extraction to identify rust disease in sugarcane. SVM is used to classify normal and diseased images. All features from these images are extracted and classified into normal and rust disease. After that, accuracy is calculated from several combination of features.

Dept. of ECE, BNMIT

Page 57

2018-2019

AGRICULTURAL ROBOT

Figure 5.15.Diseased leaf and Normal Leaf

On the other hand, color feature results in 87% accuracy because leaf with rust disease has different color from normal leaf. Figure 4.7.3 shows the differences between rust disease and normal leaf of sugarcane. Normal leaf has no lesion on its surface. Leaf with rust disease has lesion on its surface so it is different in texture. The differences are also on its color, normal sugarcane leaf is green on all its surface but leaf with rust disease have yellow until brown lession on its surface. Texture has the highest accuracy in single feature testing, 96.5 %, because normal and rust disease have different texture that can be analyzed from energy, contrast, correlation and homogeneity. When group of features are used, combination of color and texture feature has the highest accuracy of 97.5%, because diseased image have different value of energy, contrast, correlation and homogeneity from normal leaf image. When shape and texture are combined, it yields 96% accuracy. Color and shape yields 86.5% accuracy. It is because shape cannot represent the pattern of sugarcane rust disease well. A combination of shape, texture and color results 97.5 % accuracy. Combination of color and texture has the same accuracy, so we evaluate it again with different SVM kernel. In our previous work, we use linear kernel. Table 4 shows classification accuracy with different SVM kernel described in previous section where C is a color feature, S is a shape feature, and T is a texture feature.

Dept. of ECE, BNMIT

Page 58

2018-2019

AGRICULTURAL ROBOT

Table 5.3 Classification of accuracy with different SVM kernel

SVM

C

S

T

C+T

C+S

S+T

All

Kernel

(%)

(%)

(%)

(%)

(%)

(%)

(%)

87

51

96,5

97,5

86,5

96

97,5

92,5

49

95,5

96

90

90

93,5

88,5

47

97

98,5

88

93,5

93,5

92,5

62

95,5

92

88

88,5

84,5

Linear

Quadratic

Polynomial

RBF

Dept. of ECE, BNMIT

Page 59

2018-2019

AGRICULTURAL ROBOT

CHAPTER 6

RESULT & DISCUSSION

The agricultural robot will be using a chassis as a base to connect and assemble everything on it will be consisting of four motors. Two of which are toy motors and the other being gear motors. The robot is capable of doing four separate functions. 1. Digging 2. Hopper 3. Leveler 4. Disease Detection These will be working in different modes. Programming of different modes will be done separately the different modes.

The results can be seen from accuracy that is calculated from several combination of features. Table 3 shows classification accuracy. When single feature is used, shape feature has the lowest accuracy of 51% because rust in sugarcane has various shape of lesion so it is difficult to analyze it by solidity, extent, minor axis length and eccentricity of image. But, normal and diseased images have different shape. Healthy leaf has no lesion and rust diseased leaf has lesion, so system can recognize the pattern. Table 6.1 Classification Accuracy

Features

Accuracy

SHAPE

51 %

COLOR

87 %

TEXTURE

96, 5 %

COLOR + TEXTURE

97, 5 %

COLOR + SHAPE

86, 5 %

SHAPE + TEXTURE

96 %

COLOR + SHAPE + TEXTURE

97, 5 %

Dept. of ECE, BNMIT

Page 60

2018-2019

AGRICULTURAL ROBOT

6.1 POWER SUPPLY When power supply is given to robot system, LCD will display AGRIBOT, by using smart phone through Wi-Fi can initiate the systems

Figure 6.1: Power supply board

6.2 MODE 1: DIGGING Here obtained a new technology for sowing the seeds in a particular order. The seeds are placed with some specific gap between them and which is different for every crop. So in order to overcome the problem, robot which will itself dig the soil and place the seeds.Table 4.2 explains placement of seeding.

Table 6.2: The placement of seeding

Placement of seed(distance

Farm land

between two seed) Corn

7.2cm

Expected(6-8 cm) Wheat

9 cm

Expected(8-10 cm) Jowar

10cm

Expected(10-12 cm) Soya bean

5.3 cm

Expected(5-6 cm)

Dept. of ECE, BNMIT

Page 61

2018-2019

AGRICULTURAL ROBOT

6.3 MODE 2: HOPPER Hopper is used to carry seeds and to drop the seed at a particular hole that is being dig by Agribot.

Figure 6.2. Hopper

6.4 MODE 3: LEVELER

Leveler is placed at front of the robot. This will help to make an uneven surface to a flat shape. This will work simply by making Front actuators come down. When robot starts moving forward, the even surface has up’s and down’s leveler will make all the area to flat surface. This is very compatible for leveling gardens, small areas, closing gaps, etc.

Figure 6.3: Leveler

Dept. of ECE, BNMIT

Page 62

2018-2019

AGRICULTURAL ROBOT

6.5 MODE 4: SPRINKLER

Fig 6.4: Micro submersible pump

This is lightweight, small size, high efficiency, low consumption and low noise water pump .It has been used widely; in household include cooking, cleaning, bathing, space heating and water flowers, etc.

6.5.1 FEATURES 1. High quality Hall Effect sensor 2. Compact, easy to install

6.5.2 SPECIFICATION 1. Working voltage: DC 10-13V 2. No load current: 250ma 3. Temperature range:-30~0°C 4. Suction lift: 100mm 5. Spit out: 500mm 6. Flow rate range: 1.31±0.26L/Min

Dept. of ECE, BNMIT

Page 63

2018-2019

AGRICULTURAL ROBOT

6.5.3: DATA SHEET FOR MOISTURE LEVEL REQUIRED Table 6.3 explains the data sheet of moisture level required in the soil for different crops. The data sheet of moisture level

Table 6.3: data sheet for moisture level

Crops

Humidity (%)

Moisture level

Corn

65

33

Yellow corn

65

15.3

Soybean

65

12.6

Wheat

65

13.8

Barley

65

19

Jute

65

13.7

Paddy

65

24

6.6 ADVANTAGES 1. Time and manual power is reduced. 2. Used in various fields like agriculture, medicine, mining, and space research. 3. The machines could easily work around trees, rocks, ponds and other obstacles. 4. The robot will be able to expose in different weather conditions

6.6.1 DIS ADVANTAGES 1. Robot cannot work more effectively on unequal surface of the field. 2. It is necessary to set seeding space for particular seed. 3. As it works with battery supply, recharging of battery is time consumable. 4. A periodic human presence in the field is likely to be necessary.

Dept. of ECE, BNMIT

Page 64

2018-2019

AGRICULTURAL ROBOT

6.6.2 FUTURE SCOPE 1. Automated disease prediction 2. Intimation to farmer 3. Water sprinkling based on moisture levels 4. Pesticides sprinkling automation 5. The robot can be designed with chain roller instead of normal wheel.

6.7 Outlook of Agribot

Dept. of ECE, BNMIT

Page 65

2018-2019

AGRICULTURAL ROBOT

CONCLUSION Agricultural Automation Robot using ARM proposed shows an initial outcome that most of these systems that which work autonomously are more flexible than traditional systems. The benefits of reduction in labor costs and restrictions on the number of daily working hours significantly improved. Thus, it has made possible to automate the most significant working routines. The project presents a low cost, low power & simple system for device control. This system will have high application in farming, gardening and AgriUniversity. The chassis handles the complete weight of solar panel, battery and the hardware mounted on Agribot which is able to perform each and every operation skillfully and successfully. This project proposes a leaf image pattern classification to identify disease in leaf with a combination of texture and color feature extraction. Initially the farmers sends a digital image of the diseased leaf of a plant and these images are read in MATLAB and processed automatically based on SVM and the results were shown. The results of this project are to find appropriate features that can identify leaf disease of certain commonly caused disease to plants. Firstly, normal and diseased images are collected and pre-processed. Then, features of shape, color and texture are extracted from these images. After that, these images are classified by support vector machine classifier. A combination of several features is used to evaluate the appropriate features to find distinctive features for identification of leaf disease. When a single feature is used, shape feature has the lowest accuracy and texture feature has the highest accuracy. A combination of texture and color feature extraction results highest classification accuracy. A combination of texture and color feature extraction with polynomial kernel results in good classification accuracy. Based on the classified type of disease a text message was sent to the user in the project. With fully-automated farms in the future, robots can perform all the tasks like mowing, fertilizing, monitoring of pests and diseases, harvesting, tilling, etc. This also enables the farmers to just supervise the robots without the need to operate them. The project can be enhanced to any other kinds of crop. Hence, it can be applicable to the real time agricultural field.

Dept. of ECE, BNMIT

Page 66

2018-2019

AGRICULTURAL ROBOT

REFERENCE [1]D. Ramesh and H. P. Girishkumar, “Agriculture Seed Sowing Equipment: A Review”International Journal of Science, Engineering and Technology Research, 2014, volume 3, Issue 7, Pp-1987-19992 [2] Laukik P. Rut, Smit B. Jaiswal and Nitin Y. Mohite, “Design, development, and fabrication of agricultural pesticides with weeder”, International Journal of Applied Research and Studies, 2013, volume 2, Issue 11, Pp-1-8 [3]Sridhar H.S “Development of Single Wheel Multi-Use Mutually Operated Weed Remover”, International Journal of Modern Engineering Research, 2013, Vol. 3, Issue.6, Pp-3836-3840 [4] Tim Mueller-Sim, Merritt Jenkins, Justin Abel, and George Kantor, “The Robotanist: A Ground-Based Agricultural Robot for High-Throughput Crop Phenotyping,”2017 IEEE International Conference on Robotics and Automation (ICRA) Singapore, May 29 - June 3, 2017.

[5] SajjadYaghoubi et al., "Autonomous Robots for Agricultural Tasks and Farm Assignment and Future Trends in Agro Robots," International Journal of Mechanical & Mechatronics Engineering IJMME-IJENS, vol.13, no. 03, pp. 1-6, June 2013. [6] M. priyadarshini, Mrs. L. Sheela, “Command based self-guided digging and seed sowing rover”,International Conference on Engineering Trends and Science & Humanities, ISSN: 2348 – 8379, ICETSH-2015. [7] AkhilaGollakota, M. B. shriniva, “Agribot - a multipurpose agricultural robot,” India conference (INDICON) 2011 Annual IEEE 978-1-4577-1110- 7, 1-4, IEEE 2011

Dept. of ECE, BNMIT

Page 67

2018-2019

AGRICULTURAL ROBOT

Dept. of ECE, BNMIT

Page 68

2018-2019