Professional Documents
Culture Documents
Spy Man Report 1
Spy Man Report 1
Spy Man Report 1
Chapter 1
INTRODUCTION
In this chapter, we are going to give the introduction about the Autonomous robotic
system.
1.1 Introduction
Autonomous robotic system is an outstanding innovation of a modern technology. It has
been able to provide significant support to mankind by accomplishing arduous tasks that are
apparently in feasible for human beings to perform.
The proposed embedded robotic system detects human body and metal in the
catastrophic environments which is very helpful for rescue operations and military
operations. Robots are becoming more and more intelligent as technology advances in the
areas of CPU speed, sensors, memories etc. And there is ever demanding applications even in
defence. With the rapid growth of the Internet, more and more intelligent devices or systems
have been embedded into it for service, security and entertainment, including distributed
computer systems, surveillance cameras, telescopes, manipulators and mobile robots.
Although the notion of Internet robotics or web-based robotics is relatively new and also
allows to be trained in lot less time as compared to humans. The proposed system uses
various sensors to detect alive various services are deployed for rescue operations. In order to
increase the probability of saving lives of the victim, the rescue operation needs to be faster.
But, sometimes, it is difficult for rescue personnel to enter into some parts/areas of the War
field so here robots can be used.
1.3 Objectives
This android app based military robo aims to save the life of the soldiers during wars.
This is a spy robo which very smaller in size and cannot be easily recognized by the
enemies.
This robot can be controlled wirelessly from a distant place by the soldiers using an
android application that can be installed in any android platform. In order to monitor
the opponents movement it is incorporated with a wireless camera and can take pics
of various instances at enemy sides.
1.4 Scope
The Prototype developed here would be a milestone for further research and
development in the Indian Army. It is economically feasible for implementing in large scale.
Chapter-6: Describes the Implementation. It includes a detailed description about how the
project is been implemented.
Chapter-7: Describes the Testing where the proposed system is tested in various levels
like unit test, integration test and system test and how the program is executed with the
set of test cases.
Chapter-8: Describes the Results and snapshots of the project.
Chapter-9: Describes conclusion and future work of the project.
Chapter 2
LITERATURE SURVEY
This research aim is to provide a survey for developing a robot that can detect mine, as the
robot may employ several sensors in order to help in mining. Incrementally improving
existing technologies, increasing the probability of detection, reducing the false alarm rate,
and planning use able deployment scenarios. There is no single method for efficient landmine
detection. Several technologies can be found, but their direct results cannot be generalized.
Rather than focusing on individual technologies operating in isolation, mine detection
research and development should emphasize the design from first principles and subsequent
development of an integrated, multi sensor system that would overcome the limitations of any
single sensor technology. Combining different kinds of sensors would certainly obtain better
results in landmine detection. Finally, some more attention should be given to sensor fusion
and metal detectors. All of these issues should help to discriminate useful data, which is
critical as large numbers of false alarms increase uncertainty and limit future research.
Biological Methods
Mechanical Methods
Clearing minefields by modified tanks or trucks is also a common method [12]. It does not
need sensors and is efficient on a suitable ground. Chains attached on a rotating roller are
hitting the ground in order to explode or destroy mines. Another possibility is to mount
plough in front of a tank, which dig out the mines, and moves them away, mostly without
exploding. Mine plough are slow (6.5km/h), but used in conjunction with rollers, this system
can provide a virtually 100 per cent mine clearance effectiveness [1].
developing methods that could reduce the false alarm rate and maintain or increase the
probability of detection for mine clearance. New detection concepts involve searching for
characteristics other than mine metal content. Varieties of techniques that exploit properties
of the electromagnetic spectrum are being explored. For example, Pelt et al. [3] proposed
detection method, which use a separated aperture microwave sensor and an artificial neural-
network pattern classifier to detect simulated land mines using data collected from a mine.
This data consists of a set of measurements made with a separated aperture sensor operating
in the wave guide near cut-off mode. Their work has shown that neural-network pattern
classifiers can successfully detect antitank mines. This method has some drawbacks that the
level of false alarms may be made arbitrarily low and the system's complexity. Waymond et
al. [4] proposed a hybrid technique that simultaneously uses both electromagnetic and
acoustic waves in a synergistic manner to detect buried land mines. The acoustic source
causes both the mine and the surface of the earth to be displaced. The electromagnetic radar
is used to detect these displacements and, thus, the mine. The displacement of the mine is
different from the earth, because the acoustic vehicles to detect and destroy land mines.
While has an advantage of being able to destroy the mines on the spot due to the vehicle’s
mechanical structure that can withstand mine explosion. The drawbacks of this method, in
certain environments the robot perform less effectively and performance of the object
avoidance need modification to climb big obstacles A car et al. [3] have investigated some
methods in path planning techniques in robotics. The first is sensor-based coverage according
to exact cellular decomposition in terms of critical points. The robot executing the coverage
algorithm incrementally constructs this cellular decomposition while it is covering the space
with back and forth motions. The second technique, the probabilistic method, is for where
time is limited and there exists a priori information about the minefield. This method works
by minefield parameter extraction. Once the parameters are determined, the minefield layout
is fixed, allowing opportunistic robot guidance to decrease de-mining time. The drawbacks of
this method, in few instances, the system was not able to identify correctly the landmine due
to the segmentation process where the K Means clustering algorithm failed to effectively
extract the exact objects’ platforms from the image, high cost, GPR is larger and heavier, and
GPR is more power hungry Z hang et al. [3] proposed a probabilistic method for robot
landmine search, focusing on optimization search strategy determining location of mines
and/or unexploded ordnance. They first extract the characteristics of dispersion pattern of the
minefield in order to construct a probability map and then design a path for the robot
searching.
2.2 Limitations:
There are many challenges in landmines detection. The first is the changes in weather factors
led to the disappearance of the mine underground spaces. The second is the ability to stop the
effect of mines without a vision underground. The third is not only the presence of the mine
is required to be discovered, it also needs the robot to mark the location of the mine with an
accuracy of 5cm radius. There is great motivation to research new counter-mine systems.
Current anti-personnel land mines cost between $3–$25 per mine and clearance methods cost
between $300–$1000 per mine removed [3].There is work to be done in fusion of landmine
detection technology in order to enhance its performance, since every approach has good
results within limited conditions. Due to the aforementioned limitations, a multi-sensor
system based on signal and algorithm fusion should be developed. Rather than focusing on
individual technologies operating in isolation, mine detection research and development
should emphasize the design from first principles and subsequent development of an
integrated, multisensory system that would overcome the limitations of any single sensor
technology. Combining different kinds of sensors would certainly obtain better results in
landmine detection.
In order to clear up landmines, two major steps need to be done. The first step is to detect the
location of the mines. The second step is to deactivate or destroy the mines. Searching for the
location is the process that takes the most amount of time. This is because, every single inch
of the land needs to be manually and carefully probed with a mine detector [11]. There are
three kinds of mines weeping strategies ranging from a manual based mines weeping, a
mechanical equipment based mines weeping, to an advanced robot based mines weeping
[14]. The manual based technique relies on trained de-miners sweeping the ground using
metal detectors. Well-trained staff prod the ground with a thin steel spike every 2 cm at a
shallow angle of about 30 degrees [1]. The resistance of the probe and the reaction of the
surface define where to dig the ground around and carefully remove the mine. Of course, this
is a dangerous and slow task. The mine may have turned on its side and the pr odder hits the
The proposed system is controlled by human using his mobile phone. The mobile phone
allows user to fully maneuver the spyman system. The system has IR sensor, Mine detector
and also a live location sender to the user which gives the person where exactly the danger is
present.
The system has a disk shaped rotater present on which camera is mounted. This camera takes
in video and stores it in a memory card. There is gun trigger where an actual gun can also be
placed in order to shoot a person which is directly controlled by the user from the app. The
video now has to be converted to frames and then it is uploaded to machine learning model
and the model then predicts the outcome as it is human with a weapon, classify images of
weapons and also help soldiers to know what exact danger is present. This is done using a
deep learning model called web vision to classify images.
Chapter 3
SYSTEM REQUIREMENTSSPECIFICATION
A software requirements specification (SRS) is the official statement of what the
system developers should implement.It should include both the user requirements for a
system and a detailed specification of the system requirements.A requirement specification
for a software system is a complete description of the behaviour of a system to be
developed. It includes a set of use cases that describes all the interactions the users will
have with the software. In addition to the use cases the SRS will also have non-
functiona1requirements. Non-functional requirements are requirements which impose
constraints on the design or implementation(such as performance engineering requirements,
quality standards or design constraints).
Dependencies:
The system detects bomb and sends the location details to the mobile
application which is developed using Arduino IDE and Android studio.
Motion Sensor
LASER
Metal Detector
HC05
Arduino IDE
Android studio
Anaconda
3.2.3.2 Input: power supply to the Autonomous robotic system and directions in which the
robot should move like front, back, right, left.
3.2.3.3Processing:
Monitors and co-ordinate values continuously to determine the object detected in a war
field and determines the readings of the location in which bomb or human is
detected.
Chapter 4
GANTT CHART
A Gantt chart is a type of bar chart, developed by Henry Gantt that illustrates a project
schedule. Gantt charts illustrate the start and finish of the terminal elements and summary
elements of the project. Terminal elements and summary elements comprise the work
breakdown structure of the project.
The following is the Gantt chart of the project “Autonomous robotic system”
6 Presentation on work
progress
7 Testing
ACTIVITY/ AU SE OC NO DE JA FE MA AP MA
MONTH G P T V C N B R R Y
SYNOPSIS
PRESENTATION
ON IDEA
SRS
DESIGN
IMPLEMENTATION
TESTING
REPORT
The Gantt chart of Table 4.2 shows our project schedule. The project work started in August
when the project synopsis was submitted. The presentation on the idea was done during
August. Requirement collection was done in September and design work in January.
Implementation was started in October and was continued till March.
Chapter 5
SYSTEM DESIGN
System overview provides a top-level view of the entire software product. It highlights the major
Dept. of CSE, MITE, Moodabidri Page13
SYPMAN
components without taking account the inner details of the implementation. It describes the
functionality of the product and context and design of the software product. The application will
be developed in a way which provides the user to interact with the system and simplifies the tasks
by providing a smooth user interface and user experience with easily readable and understandable
buttons. There are button with labels on for navigation purposes. The proposed solution takes
advantage of the rich features offered in android smart phones. This project makes it easier for
soldiers and thus keeping them safe, ensures safety and monitors the whereabouts of physically
harmful things and weapon carrying people.
The architectural design gives the description about how the overall system is designed. It is
specified by identifying the components defining the control and data flow between them.
The arrows indicate the connection and the rectangular boxes represent the functional units.
The Figure 5.1 shows the Architectural Design Diagram of this project.
This section describes the conceptual design of Spyman System as shown in (Figure 5.1).
summarizes who uses our application or system and what they can do with it.
User Current
Position
Bluetooth Connection
Image Recognition
Open Mobile
App
Connect to
Spyman
Human Controller
Direct it to location
you want
Brief Description
There is human that operates the system. The mobile device is used to control the direction in
which the spyman moves. There is a small camera mounted on top of the spyman that records
video and it gets recorded in the memory and also it has a metal detector for detecting mines. This
will make the soldier understand threats that may have been planted by enemies what a soldier
may not have seen with his naked eyes since they are below the earth surface. The recorded video
is brought back along with spyman which can be used to study human with bombs and other geo-
locations.
A Sequence diagram shows parallel vertical lines (lifelines), different processes or objects that
live simultaneously, and as horizontal arrows, the messages exchanged between them, in the
order in which they occur. This allows the specification of simple run-time scenarios in a
Graphical manner. Figure 5.3 Shows the Sequence Diagram.
Activity Diagram shows the sequence of steps that make up complex process. It shows the flow
of control, similar to sequence but focuses on operations rather than on objects. The components
Start
Mobile Application
Mobile Controls
(Movements)
No
Validate detection Items Detected
Displayed on
App
Yes
Video Capturing
To Predict
Mobile Bluetooth DC
App MOTOR
Module
Arduino Board
IR Metal
Camera
SENSOR
Detector
Prediction
Model
The Figure 5.5 shows the data flow between each component in the system. Initially the
android app is connected to Bluetooth module. After the connection is set up, now a person
can navigate the Spyman to different location how he wants. After he has done that, the
detector if it detects anything a message is sent to app. The camera mounted on the top takes
a video which is further processed to identify what is there and give a clear image.
Chapter 6
IMPLEMENTATION
The implementation phase of the software development is concerned with translating design
specification into source code. The user tests developed system and changes are made
Dept. of CSE, MITE, Moodabidri Page19
SYPMAN
according to their needs. Our system has been successfully implemented. Before
implementation, several tests have been conducted to ensure that no errors are encountered
during operation. The implementation phase ends with evaluation of the system after placing
it into operation for a period of time. Implementation is the third phase of system process. In
order to achieve the objectives and the expected performance the system has been developed
in a highly interactive and user friendly manner.
This Project makes use of many modules like arduino module, Bluetooth
module, Driving Motor, Sensor module and Machine Learning module to detect
and predict the outcomes.
The function is made to maneuver the spyman using the mobile app.
Code snippet
void RIGHT()
{digitalWrite(2,HIGH);
digitalWrite(3,LOW);
digitalWrite(4,LOW);
digitalWrite(5,HIGH);
}
void LEFT()
{digitalWrite(2,LOW);
digitalWrite(3,HIGH);
digitalWrite(4,HIGH);
digitalWrite(5,LOW);
void GUN_FIRE()
{
digitalWrite(12,HIGH);
delay(80);
digitalWrite(12,LOW);
delay(80);
digitalWrite(12,HIGH);
delay(80);
digitalWrite(12,LOW);
delay(80);
digitalWrite(12,HIGH);
delay(80);
digitalWrite(12,LOW);
delay(80);
}
delay(2000);//while(MetalState == 0);
testing may lead to errors. Nothing is completed without the testing, as it is vital kinds of data.
While testing, errors are noted and corrections are made. So general testing demonstrates that the
system is working according to the specifications, and that it meets the performance requirement.
System testing is done to check whether the system works accurately and efficiently before live
operation commences. A small error can conceivably explode into much larger problem.
Effective testing early in the process translates directly into long term cost savings from a reduced
number of errors. Testing is the systematic search for details in all project deliverable. It is the
process of examining an output of a process under consideration, comparing the results against a
set of predetermined expectations and dealing with variances.
Testing is vital for the success of the system. System testing makes a logical assumption that if all
parts of the system are correct, the goal will be successfully achieved. Testing involves operation
of systems or application under controlled conditions and evaluating the results. The controlled
conditions include both normal and abnormal conditions. At first, the different units are
individually tested and the system as a whole is tested.
Tests are frequently grouped by where they are added in the software development process,
or by the level of specificity of test. The main level during the development process are unit
testing, integration testing, and the system testing that are distinguished by the test target
without implying a specific, process model.
A pessimistic approach of running the software with the intent of finding errors.
Testing can be performed in various levels like unit test, integration test and system test.
Chapter 8
Thus able to do protect them from such instances. Also it can be used in any other
circumstance where humans can’t reach. This can be life saving in such situations.