ROBOTOR AN AUTONOMOUS VEHICLE FOR TARGET DETECTION AND SHOOTING
0 likes344 views
The document outlines the development of 'Robotor,' an autonomous robot designed for target detection and shooting using image processing techniques. It describes the robot's capabilities, including target recognition, path following, and its shooting mechanism which is triggered based on the proximity to the target. The experiments demonstrated a 95% accuracy rate in detecting static targets, though future work is indicated to enhance capabilities against moving targets.
![International Journal of Mechanical Engineering and Technology (IJMET), ISSN 0976 – 6340(Print),
ISSN 0976 – 6359(Online), Volume 5, Issue 6, June (2014), pp. 110-117 © IAEME
111
computer world especially in image processing. Apart from cameras ,gestures are also used to
control a robot.[1]
A computer can process its brain 1000 times faster than a human brain but one human life is
more important than 1000 computers. Indian military needs most advance technology to better
protect the nation. So the problem was to minimize the loss of our defense personnel by constructing
a robot as efficient as humanly Soldiers that can go to a remote area and shoot the target down.
The main objective of this project is to make an autonomous robot which is capable of going
to a remote area, recognizing a target there, follow it, and shoot target once it is within an acceptable
distance. The successful execution of the prototype will reinforce the positive contribution of the
technologies used.
2. RELATED WORK
A number of robots have been built which can follow a defined path or take pictures in
surroundings or can detect an object but there is no one which can find a target, follow it and shoot it
down from a certain distance. Most of the robots make use of sensors like infrared sensor, proximity
sensor or white line sensor to trace their path. Some make use of motion planning with complete
information in which they collect information about the premises or the environment before staring
the motion and act accordingly [2]. Some may also use a Kinect camera as a vision system [3]. At
the present time robots are not able to work in all odd circumstances they can perform only in special
circumstances that are customized for them.
3. PROPOSED METHOD
We have developed a system in which a robot autonomously goes to any remote area and
detects its target and shoot from an acceptable distance. The robot is pre-programmed and comprises
of a micro-controller with good quality webcam and has a self-made linear projectile mechanism.
The webcamcaptures the real time frame or image of the surrounding more specifically called an
arena [4]. Then the frame of an image goes as an input in the computer software called MATLAB®
and the image is being processed using Image processing techniques. Then signal has been produced
for the robot whether to move or take left, right and forward. There is also a trigger mechanism
installed in a robot which activates the linear projectile shooting mechanism. This trigger mechanism
gets activated when the robot fully detects its target and achieved its acceptable distance and linear
projectile mechanism is activated based on the Fleming thumb rule and the bullet is fired in the
direction of the target. The figure 1 shows the Work Flow of the proposed method.
Fig.1: Work flow of proposed method](https://image.slidesharecdn.com/30120140506012-160218073339/85/ROBOTOR-AN-AUTONOMOUS-VEHICLE-FOR-TARGET-DETECTION-AND-SHOOTING-2-320.jpg)
![International Journal of Mechanical Engineering and Technology (IJMET), ISSN 0976 – 6340(Print),
ISSN 0976 – 6359(Online), Volume 5, Issue 6, June (2014), pp. 110-117 © IAEME
112
The functional block diagram of the system is as below:
Fig.2: Functional Block diagram of system
3.1 Image acquisition The first step is to capture a scene through a camera. The camera should be
more reliable and it should have good specification like Pixel value and Resolution. Most frequently
used cameras are CMOS based because they are less in cost and easily available in the market.
3.2 Image preprocessingImage preprocessing commonly comprises of a series of sequential
operations including image enhancement or normalization, geometric correction, Contrast
adjustment, Histogram Equalization, removal of noise etc. It is done before applying the feature
extraction techniques. Using the above mentioned techniques, we alter the image pixel values
permanently and use this improved data for later analyses.
3.3 Image conversion Image captured by camera goes into the computer in which image processing
is done using Matlab® software. The original RBG image is converted into NTSC format through
command “rbg2ntsc”. In the NTSC format, image data consist of three components: luminance (Y),
hue (I), and saturation (Q).The first component, luminance, represents grayscale information, while
the last two components make up chrominance [1]. We take the chrominance of object which
differentiate the target from any other component which image consists.
3.4 Target detection Now we extract the boundary of detecting object so that computer understands
that target particularly. We evaluate the center of the target and center of the frame. Now let
Euclidean distance, D is the distance of the center of the frame from the center of the object.
ܦ ൌ ඥሾሺݔ െ ܽሻଶ ሺݕ െ ܾሻଶሿ (1)
Where x and y are the spatial coordinate of the center of the target and a and b are the spatial
coordinate of the center of the frame.](https://image.slidesharecdn.com/30120140506012-160218073339/85/ROBOTOR-AN-AUTONOMOUS-VEHICLE-FOR-TARGET-DETECTION-AND-SHOOTING-3-320.jpg)
![International Journal of Mechanical Engineering and Technology (IJMET), ISSN 0976 – 6340(Print),
ISSN 0976 – 6359(Online), Volume 5, Issue 6, June (2014), pp. 110-117 © IAEME
116
Table 2: Observation table
The varying the distance of the Robotor from the target we can know the range for which it
can detect and shoot the object successfully. The use of our vision system and the technique of object
detection using NTSC format of the image to control the Robotor obtained satisfactory results. The
robot could detect and shot the target many times. In case of changing the distance from using above
steps, we got good results except when the distance was 120cm. In that case it failed once to hit the
target.
6. CONCLUSION
This paper has presented an autonomous moving robot has been implemented which is
capable to detect a certain object, approaches towards its target and shoot it down. The result shows
that the accuracy to find the target is 95 % which demonstrate its accuracy and efficiency. The main
constraint of this approach is that it can shoot only static object but no one is always static in nature.
So our future work is to make an autonomous system which could predict the direction of moving
targets using object tracking.
7. ACKNOWLEDGEMENT
We would like to thank Ms. Twisha for supervising all activities and for lending her full
cooperation, despite her busy schedule, in successful implementation of this system.
REFERENCE
[1] Harish Kumar Kaura, VipulHonrao, SayaliPatil, Pravish Shetty,” Gesture Controlled Robot
using Image Processing”, (IJARAI) International Journal of Advanced Research in Artificial
Intelligence, Vol. 2, No. 5, 2013
[2] Qing Li, Wei Zhang, Yixin Yin, Zhiliang Wang, and Guangjun Liu. An improved genetic
algorithm of optimum path planning for mobile robots. In Intelligent Systems Design and
Applications, 2006. ISDA'06. Sixth International Conference on, volume 2, pages 637{642.
IEEE, 2006.
Distance from
Robotor
30cm 60cm 90 cm 120cm
Number of Trials 5 5 5 5
Successful
Performance
5 5 5 4
Unsuccessful
Performance
0 0 0 1
Success Rate (%) 100 100 100 80
Distance from
Robotor
30cm 60cm 90 cm 120cm
Number of Trials 5 5 5 5
Successful
Performance
5 5 5 4
Unsuccessful
Performance
0 0 0 1
Success Rate (%) 100 100 100 80](https://image.slidesharecdn.com/30120140506012-160218073339/85/ROBOTOR-AN-AUTONOMOUS-VEHICLE-FOR-TARGET-DETECTION-AND-SHOOTING-7-320.jpg)
![International Journal of Mechanical Engineering and Technology (IJMET), ISSN 0976 – 6340(Print),
ISSN 0976 – 6359(Online), Volume 5, Issue 6, June (2014), pp. 110-117 © IAEME
117
[3] Gesture Controlled Robot using Kinect http://www.e-yantra.org/home/projects-wiki/item/180-
gesture-controlled-robot-using-firebirdv-and-kinect.
[4] ShahedShojaeipour, Sallehuddin Mohamed Haris, ElhamGholami and Ali Shojaeipour,”
Webcam-based Mobile Robot Path Planning using Voronoi Diagrams and Image Processing”,
Proceedings of the 9th WSEAS International Conference on Applications of Electrical
Engineering.
[5] Saifuldeenabed Jebur, Prabhat Kumar Sinha and Ishan Om Bhargava, “Advancement and
Stimulation of Five Degree of Freedom Robot Lever Arm”, International Journal of
Mechanical Engineering & Technology (IJMET), Volume 5, Issue 3, 2014, pp. 20 - 30,
ISSN Print: 0976 – 6340, ISSN Online: 0976 – 6359.
[6] Hameedah Sahib Hasan and Dr. P.Ramesh Babu, “Analysis and Control of Mobile Robot for
Pipe Line Inspection”, International Journal of Mechanical Engineering & Technology
(IJMET), Volume 4, Issue 5, 2013, pp. 1 - 9, ISSN Print: 0976 – 6340, ISSN Online:
0976 – 6359.
[7] Sarthak Pareek, “Embedded Based Robotic Vehicle Protection using Stisim Software”,
International Journal of Electronics and Communication Engineering & Technology
(IJECET), Volume 5, Issue 4, 2014, pp. 36 - 42, ISSN Print: 0976- 6464, ISSN Online:
0976 –6472.
[8] Sreekanth Reddy Kallem, “Artificial Intelligence in the Movement of Mobile Agent
(Robotic)”, International Journal of Computer Engineering & Technology (IJCET), Volume 4,
Issue 6, 2013, pp. 394 - 402, ISSN Print: 0976 – 6367, ISSN Online: 0976 – 6375.
[9] Srushti H. Bhatt, N. Ravi Prakash and S. B. Jadeja, “Modelling of Robotic Manipulator Arm”,
International Journal of Mechanical Engineering & Technology (IJMET), Volume 4, Issue 3,
2013, pp. 125 - 129, ISSN Print: 0976 – 6340, ISSN Online: 0976 – 6359.](https://image.slidesharecdn.com/30120140506012-160218073339/85/ROBOTOR-AN-AUTONOMOUS-VEHICLE-FOR-TARGET-DETECTION-AND-SHOOTING-8-320.jpg)
ROBOTOR AN AUTONOMOUS VEHICLE FOR TARGET DETECTION AND SHOOTING
- 1. International Journal of Mechanical Engineering and Technology (IJMET), ISSN 0976 – 6340(Print), ISSN 0976 – 6359(Online), Volume 5, Issue 6, June (2014), pp. 110-117 © IAEME 110 ROBOTOR AN AUTONOMOUS VEHICLE FOR TARGET DETECTION AND SHOOTING Vivek Pal, Amit Kr. Gautam, Deepak Singh, Akshay (Cluster Innovation Centre, University of Delhi, India) ABSTRACT Humans have evolved to better survive and have evolved their invention. In today’s age, a large number of robots are placed in many areas replacing manpower in severe or dangerous workplaces. Moreover, the most important thing is to take care of this technology for developing robots progresses. This paper proposes an autonomous moving system which automatically finds its target from a scene, lock it and approach towards its target and hits through a shooting mechanism. The main objective is to provide reliable, cost effective and accurate technique to destroy an unusual threat in the environment using image processing. Keywords: Capacitor Bank, Coil Gun, Image Processing, Microcontroller, Trigger Mechanism. 1. INTRODUCTION The robotic industry is one of such invention that will evolve parallel to us because somewhere we view them as our descendants. Every day we see new products in the market with new innovation, better efficiency and accuracy. The trend of robotics has affected every phase of our life. The information that the robot process or generate can be sent in a wired fashion or though wireless communication. To process the data a processing unit is required, generally a microprocessor perform this task. The data can be an image or video as well. Then image processing comes into the picture. A robot must have a vision system to capture the images or videos in the vicinity. Then they can be sent to the microprocessor for processing and some information can be extracted out of them. The eye for a Robot is its sensors to understand the circumstances. There are several types of sensors like IR proximity sensor or sharp IR which can be used depends on their requirements, instead of those, Cameras are now being widely used due to the remarkable improvement in INTERNATIONAL JOURNAL OF MECHANICAL ENGINEERING AND TECHNOLOGY (IJMET) ISSN 0976 – 6340 (Print) ISSN 0976 – 6359 (Online) Volume 5, Issue 6, June (2014), pp. 110-117 © IAEME: www.iaeme.com/IJMET.asp Journal Impact Factor (2014): 7.5377 (Calculated by GISI) www.jifactor.com IJMET © I A E M E
- 2. International Journal of Mechanical Engineering and Technology (IJMET), ISSN 0976 – 6340(Print), ISSN 0976 – 6359(Online), Volume 5, Issue 6, June (2014), pp. 110-117 © IAEME 111 computer world especially in image processing. Apart from cameras ,gestures are also used to control a robot.[1] A computer can process its brain 1000 times faster than a human brain but one human life is more important than 1000 computers. Indian military needs most advance technology to better protect the nation. So the problem was to minimize the loss of our defense personnel by constructing a robot as efficient as humanly Soldiers that can go to a remote area and shoot the target down. The main objective of this project is to make an autonomous robot which is capable of going to a remote area, recognizing a target there, follow it, and shoot target once it is within an acceptable distance. The successful execution of the prototype will reinforce the positive contribution of the technologies used. 2. RELATED WORK A number of robots have been built which can follow a defined path or take pictures in surroundings or can detect an object but there is no one which can find a target, follow it and shoot it down from a certain distance. Most of the robots make use of sensors like infrared sensor, proximity sensor or white line sensor to trace their path. Some make use of motion planning with complete information in which they collect information about the premises or the environment before staring the motion and act accordingly [2]. Some may also use a Kinect camera as a vision system [3]. At the present time robots are not able to work in all odd circumstances they can perform only in special circumstances that are customized for them. 3. PROPOSED METHOD We have developed a system in which a robot autonomously goes to any remote area and detects its target and shoot from an acceptable distance. The robot is pre-programmed and comprises of a micro-controller with good quality webcam and has a self-made linear projectile mechanism. The webcamcaptures the real time frame or image of the surrounding more specifically called an arena [4]. Then the frame of an image goes as an input in the computer software called MATLAB® and the image is being processed using Image processing techniques. Then signal has been produced for the robot whether to move or take left, right and forward. There is also a trigger mechanism installed in a robot which activates the linear projectile shooting mechanism. This trigger mechanism gets activated when the robot fully detects its target and achieved its acceptable distance and linear projectile mechanism is activated based on the Fleming thumb rule and the bullet is fired in the direction of the target. The figure 1 shows the Work Flow of the proposed method. Fig.1: Work flow of proposed method
- 3. International Journal of Mechanical Engineering and Technology (IJMET), ISSN 0976 – 6340(Print), ISSN 0976 – 6359(Online), Volume 5, Issue 6, June (2014), pp. 110-117 © IAEME 112 The functional block diagram of the system is as below: Fig.2: Functional Block diagram of system 3.1 Image acquisition The first step is to capture a scene through a camera. The camera should be more reliable and it should have good specification like Pixel value and Resolution. Most frequently used cameras are CMOS based because they are less in cost and easily available in the market. 3.2 Image preprocessingImage preprocessing commonly comprises of a series of sequential operations including image enhancement or normalization, geometric correction, Contrast adjustment, Histogram Equalization, removal of noise etc. It is done before applying the feature extraction techniques. Using the above mentioned techniques, we alter the image pixel values permanently and use this improved data for later analyses. 3.3 Image conversion Image captured by camera goes into the computer in which image processing is done using Matlab® software. The original RBG image is converted into NTSC format through command “rbg2ntsc”. In the NTSC format, image data consist of three components: luminance (Y), hue (I), and saturation (Q).The first component, luminance, represents grayscale information, while the last two components make up chrominance [1]. We take the chrominance of object which differentiate the target from any other component which image consists. 3.4 Target detection Now we extract the boundary of detecting object so that computer understands that target particularly. We evaluate the center of the target and center of the frame. Now let Euclidean distance, D is the distance of the center of the frame from the center of the object. ܦ ൌ ඥሾሺݔ െ ܽሻଶ ሺݕ െ ܾሻଶሿ (1) Where x and y are the spatial coordinate of the center of the target and a and b are the spatial coordinate of the center of the frame.
- 4. International Journal of Mechanical Engineering and Technology (IJMET), ISSN 0976 – 6340(Print), ISSN 0976 – 6359(Online), Volume 5, Issue 6, June (2014), pp. 110-117 © IAEME 113 Our goal is to minimize the distance D. Microcontroller gives the instruction based on how much the spatial coordinates differ from center of the target to the center of the frame. Table no. explains the detail of instruction given by the microcontroller. Table 1 Instructions given by microcontroller Where, P=Number of pixels used to outline the target. D = Distance between the center of frame and the center of object. Relative x-coordinate = x-a 4. HARDWARE DESCRIPTION Fig.3: Hardware model of Robotor The robot is self-assembled consist of metallic chassis having 4 geared DC (Direct Current) motors of 50 RPM, 1 servo motor has operated speed 1.18 Sec per 60 degrees at 4.8 volts at no load, 4 plastic wheels are attached to the motor, one CMOS based camera is mounted in the front of the robot. The Camera is connected to the computer. A microcontroller ATmega328 is connected to the computer.it operates at 5 V DC supply having 32 KB flash memory and 16 MHZ clock frequency. Computer is connected to the micro-controller by the USB cable connector. The computer sends the signal command to micro-controller in which direction it has to be moved. The shooting mechanism comprises of Coil gun, Capacitor bank and Trigger mechanism. Figure 5 shows the block of shooting mechanism. P D Relative x coordinate Move <300 >35 <0 LEFT <300 >35 >0 RIGHT <300 <35 - FORWARD >300 <35 - STOP+ trigger on
- 5. International Journal of Mechanical Engineering and Technology (IJMET), ISSN 0976 – 6340(Print), ISSN 0976 – 6359(Online), Volume 5, Issue 6, June (2014), pp. 110-117 © IAEME 114 Fig.4: Working principle of shooting mechanism 4.1 Trigger and shooting mechanismThe trigger mechanism is activated once the robot takes its position after image detection is complete. The mechanism is designed using a servo motor with an alligator clip attached to its axle and another fixed alligator clip. The two alligator clips are placed at an angle of 90 degrees not touching each other. When the servo rotates along with first clip it touches the second clip and the circuit is complete and hence the coil gun gets activated the target is shot down. Fig.5: Triggered mechanism 4.2 Coil gun The gun is charged projectile accelerator which makes use of magnetic effect of electric current to accelerate a ferromagnetic substance used as bullet. The coil gun has been made by winding copper wires around a non-ferromagnetic barrel. After the image detection is complete, the trigger mechanism is activated using servos and the coil gun turns on. If the gun is loaded, the bullet is fired in the direction of the object and the target is shot down. Fig.6: Coil tube
- 6. International Journal of Mechanical Engineering and Technology (IJMET), ISSN 0976 – 6340(Print), ISSN 0976 – 6359(Online), Volume 5, Issue 6, June (2014), pp. 110-117 © IAEME 115 4.3Capacitor bank: A capacitor bank consisting of 330V capacitors, 220mF charge were interconnected in parallel. The capacitor bank stores charge for the coil gun. The charge when discharged across the copper coil make it magnetized and then its acts as coil gun. It also enhances the ripple current capacity. Fig. 7: Capacitor are connected in parallel 5. EXPERIMENT AND RESULTS In this section the detailed experiments which are done by Robotorare explained. Conversion of image from RGB to NTSC format is shown in figure 8. Fig.8: Image conversion from RGB to NTSC The experimental procedure is as follows: 1. Set the Robotor at a distance of 30 cm from the target facing any direction. 2. Start autonomous action. 3. If the robot goes near the target and shoot it. Repeat the same procedure from the beginning. 4. After five trials, set the robot at a distance of 60 cm from the steps and restart. 5. Repeat above procedure with 90 cm and 120 cm also.
- 7. International Journal of Mechanical Engineering and Technology (IJMET), ISSN 0976 – 6340(Print), ISSN 0976 – 6359(Online), Volume 5, Issue 6, June (2014), pp. 110-117 © IAEME 116 Table 2: Observation table The varying the distance of the Robotor from the target we can know the range for which it can detect and shoot the object successfully. The use of our vision system and the technique of object detection using NTSC format of the image to control the Robotor obtained satisfactory results. The robot could detect and shot the target many times. In case of changing the distance from using above steps, we got good results except when the distance was 120cm. In that case it failed once to hit the target. 6. CONCLUSION This paper has presented an autonomous moving robot has been implemented which is capable to detect a certain object, approaches towards its target and shoot it down. The result shows that the accuracy to find the target is 95 % which demonstrate its accuracy and efficiency. The main constraint of this approach is that it can shoot only static object but no one is always static in nature. So our future work is to make an autonomous system which could predict the direction of moving targets using object tracking. 7. ACKNOWLEDGEMENT We would like to thank Ms. Twisha for supervising all activities and for lending her full cooperation, despite her busy schedule, in successful implementation of this system. REFERENCE [1] Harish Kumar Kaura, VipulHonrao, SayaliPatil, Pravish Shetty,” Gesture Controlled Robot using Image Processing”, (IJARAI) International Journal of Advanced Research in Artificial Intelligence, Vol. 2, No. 5, 2013 [2] Qing Li, Wei Zhang, Yixin Yin, Zhiliang Wang, and Guangjun Liu. An improved genetic algorithm of optimum path planning for mobile robots. In Intelligent Systems Design and Applications, 2006. ISDA'06. Sixth International Conference on, volume 2, pages 637{642. IEEE, 2006. Distance from Robotor 30cm 60cm 90 cm 120cm Number of Trials 5 5 5 5 Successful Performance 5 5 5 4 Unsuccessful Performance 0 0 0 1 Success Rate (%) 100 100 100 80 Distance from Robotor 30cm 60cm 90 cm 120cm Number of Trials 5 5 5 5 Successful Performance 5 5 5 4 Unsuccessful Performance 0 0 0 1 Success Rate (%) 100 100 100 80
- 8. International Journal of Mechanical Engineering and Technology (IJMET), ISSN 0976 – 6340(Print), ISSN 0976 – 6359(Online), Volume 5, Issue 6, June (2014), pp. 110-117 © IAEME 117 [3] Gesture Controlled Robot using Kinect http://www.e-yantra.org/home/projects-wiki/item/180- gesture-controlled-robot-using-firebirdv-and-kinect. [4] ShahedShojaeipour, Sallehuddin Mohamed Haris, ElhamGholami and Ali Shojaeipour,” Webcam-based Mobile Robot Path Planning using Voronoi Diagrams and Image Processing”, Proceedings of the 9th WSEAS International Conference on Applications of Electrical Engineering. [5] Saifuldeenabed Jebur, Prabhat Kumar Sinha and Ishan Om Bhargava, “Advancement and Stimulation of Five Degree of Freedom Robot Lever Arm”, International Journal of Mechanical Engineering & Technology (IJMET), Volume 5, Issue 3, 2014, pp. 20 - 30, ISSN Print: 0976 – 6340, ISSN Online: 0976 – 6359. [6] Hameedah Sahib Hasan and Dr. P.Ramesh Babu, “Analysis and Control of Mobile Robot for Pipe Line Inspection”, International Journal of Mechanical Engineering & Technology (IJMET), Volume 4, Issue 5, 2013, pp. 1 - 9, ISSN Print: 0976 – 6340, ISSN Online: 0976 – 6359. [7] Sarthak Pareek, “Embedded Based Robotic Vehicle Protection using Stisim Software”, International Journal of Electronics and Communication Engineering & Technology (IJECET), Volume 5, Issue 4, 2014, pp. 36 - 42, ISSN Print: 0976- 6464, ISSN Online: 0976 –6472. [8] Sreekanth Reddy Kallem, “Artificial Intelligence in the Movement of Mobile Agent (Robotic)”, International Journal of Computer Engineering & Technology (IJCET), Volume 4, Issue 6, 2013, pp. 394 - 402, ISSN Print: 0976 – 6367, ISSN Online: 0976 – 6375. [9] Srushti H. Bhatt, N. Ravi Prakash and S. B. Jadeja, “Modelling of Robotic Manipulator Arm”, International Journal of Mechanical Engineering & Technology (IJMET), Volume 4, Issue 3, 2013, pp. 125 - 129, ISSN Print: 0976 – 6340, ISSN Online: 0976 – 6359.