ROBOTIC ARM FOR OBJECT SORTING BASED ON COLOR ASRA ANJUM 1, Y. ARUNA SUHASINI DEVI 2 1 Asra Anjum, M.Tech Student, Dept Of ECE, CMR College Of Engg And Tech, Kandlakoya, Medchal, Telangana, India. 2 Y. Aruna Suhasini Devi, Associate Professor, Dept Of ECE, CMR College Of Engg And Tech, Kandlakoya, Medchal, Telangana, India. Abstract-- Usually sorting of objects is carried out manually using human labor. Recognizing a particular object and placing it in the required position is a tiring work especially in the field of industry where in one has to sort a bulk of objects in quick time and also the weight is greater than what a human can carry. This is when automation plays a major role. This paper presents an efficient method that reduces the cost taking these factors into consideration. Raspberry pi isused,which is an open sourced Linux based board which is interfaced with camera module. Initially the images of objects are captured using camera that are required to be sorted. Open CV is used for detecting the colour of the objects. The basic firmware for the Raspberry Pi is written in PHP/Python language. The system uses DC motor for the movement of conveyer belt and servomotor for robotic arm gripper to pick the objects of respective color from the fixed location at particular direction. Keywords: Raspberry pi 3, conveyor belt, servo motor, dc motor, gripper motor, camera, open CV. I. INTRODUCTION The proposed system has automatic object sorting and implementing material handling(pick and place) technique for selected items using robot system. It synchronizes the movementof robotic arm to pick the objects moving on a conveyor belt. It aims in classifying the colored(red, green, blue) which are coming on the conveyor by picking and placing the objects in its respective pre-programmed location. Thereby eliminating the monotonous work done by human,achieving accuracy and speed in the work. The proposed system makes use of advanced Raspberry Pi processor and also USB camera to sense the selected objects moving on the conveyer belt. The objects are sensed using an IR sensor. When the object appears near to its vicinity then the system captures an image with the help of a camera and is fed as input signal to the Raspberry Pi processor for further implementation. The Raspberry Pi processor checks the captured image from the predefined data base of the object. When the object detected matches with the selected color then it activates the robotic arm motors using interfacing circuits for necessary action. The basic firmware for the Raspberry Pi is written in Python language. The proposed system uses DC motor for the movement of conveyer belt and servomotor for robotic arm gripper to pick the objects of respective color and place it in a particular direction. II. LITERATURE SURVEY Traditionally, the object sorting process was done manually. However, this method has some disadvantages such as increase in the cost of the product, slow performance, and inaccuracy due to the human mistake. Existing sorting methods use set of inductive, capacitive and optical sensors to differentiate color. Photodiode based color sensors are attached with this robot system for detecting the color of the particular object. They measure
color, based on RGB color model. A large percentage of the visible spectrum can be created using these three colors but the disadvantages of this kind of system is sensor sensitivity range or effect of environmental conditions. In some existing systems of sorting, objects are placed on conveyor belt and according to movement of belt, objects get sorted. But the disadvantage of this type of system is objects which are already present on belt are not considered in sorting process. edge detecting techniques are widely used for sorting fruits in large scale. The robotic arms are widely used in the industry, but most of them are used in a PTP (Point To Point) trajectory, where the movements of the robotic arms are learned previously. The use of sensors in various techniques also helps in sorting the objects based on the parameters like height, color, shape, size etc. This is implemented in the microcontrollers, arduino boards with the help of Mat lab software. III. EXISTING SYSTEM IV. PROPOSED SYSTEM Color is the most common feature to distinguish between objects by sorting, recognizing and tracking. Generally robot is mounted with a camera or the camera is mounted in the workspace to detect the object. This technology can be used in material handling in logistics and packaging industry where the objects moving through a conveyer belt can be separated using a color detecting robot. Another system separates the objects from a set, based on their color. The detection of the particular color is done by light intensity to frequency converter method, which consists of the robot with its arm supervised by a microcontroller based system which controls DC and servo motors. A mechatronics color sorting system is based on application of image processing. It aims in classifying the objects by color, size, which are placed on the conveyor belt by picking and placing the objects in the desired place, thereby eradicating the repetitious work done by human, achieving accuracy and speed in the work. Color sorting systems in segregating crayons, uses visual color matching or color sorting techniques. For example, the crayon manufacturer guarantees that the green crayon in each color-assorted box will look identical in every box. In mineral sorting, the MSort scans bulk material in free fall by means of a color line camera. The respective data is evaluated by free programmable sorting software of an industrial computer by color, brightness into good product and rejected parts. Fruit grading and multi scale This paper presents a system which uses low cost and open source software for achieving the goal of sorting the objects. Raspberry pi 3 is used with Linux operating system, USB camera and open CV for sorting. The latest version of Raspberry pi 3 is used which is a low cost, portable, multipurpose and tiny computer. The Fig.1 shows Raspberry pi 3 interfaced with web camera, dc motor, servo motor. A 5V and 2A power supply is applied to the Raspberry pi. Raspberry Pi 3 has 4 USB ports which can be used for connecting a webcam and it has 40 GPIO pins which are connected to the DC motor, servo motor ADC, IR sensor. H bridge is used to drive the gripper motor as it is available at low cost and can be used to run the motor. PWM is used for controlling the speed of the motors. Web camera: A webcam is a video camera that feeds its image in real time to a computer or computer network. Unlike an IP camera (which uses a direct connection using Ethernet or Wi-Fi), a webcam is generally connected by a USB cable, FireWire cable, or similar cable.their most popular use is the establishment of video links, permitting computers to act as videophones or videoconference stations. The common use as a video camera for the World Wide Web gave the webcam its name. Other popular uses include security surveillance, computer vision, video broadcasting, and for recording social videos.
DC Motor: A dc motor uses electrical energy to produce mechanical energy, very generally through the interaction of magnetic fields and current-containing conductors. The reverse process,producing electrical energy from mechanical energy, is carried out by an alternator, source or dynamo. Many types of electric motors can be run as sources, and vice verse. The input of a DC motor is current/voltage and its output is torque (speed). Conveyor Belt: The belt conveyor is an endless belt moving over two end pulleys at fixed positions and used for transporting material horizontally or at an incline up or down. Servo Motor: A servomotor is a rotary actuator that allows for precise control of angular position. It consists of a motor coupled to a sensor for position feedback, through a reduction gearbox. It also requires a relatively sophisticated controller, often a dedicated module designed specifically for use with servomotors. Servomotors are used in applications such as robotics, CNC machinery or automated manufacturing. Working: The block diagram consists of Raspberry pi, servomotor, dc motor, ADC controller, IR sensor, and color sensor. Initially IR sensor detects the presence of the object and camera captures the image of the object and stores it in raspberry pi SD card. Raspberry then checks the intensity of color and stores it in python script. Color sensor is used to detect the color of the object by its intensity. The ADC voltage values are measured for each color and accordingly the object placed on the conveyor belt is sorted. Now the predefined and present values of objects are compared and accordingly the objects are sorted and placed in their respective positions with the help of a gripper motor. V. FLOW CHART Fig.1 Block diagram of object sorting based on color
VI. ALGORITHM STEP 1: Initialize the RPi3 STEP 2: Initialize the DC motor STEP 3: The object is placed on the moving conveyor belt and the presence of the object is detected by IR sensor. STEP 4: Camera captures the image of the object and sends it to raspberry pi. In raspberry pi the RGB pixel values are stored and intensity is checked to classify the color of the object(i.e., Red, Green, Blue) the capability to segregate large and heavy objects and sort them effectively. VIII. FUTURE SCOPE In future applications we can sort the object with differences shapes and weights. IX. EXPERIMENTAL RESULTS EXAMPLE: The image data is 2 dimensional array of pixels and each pixel is triple of 3 values, the relative intensity of RGB is in the range of 0-255. (x,y,1) determines red pixel if it is greater than 50 in 0-255 range of 8 bit image. If color intensity is greater than 30 then the object is determined to be blue and if color intensity is greater than 40 then the object is determined to be green. STEP 5: Predefined ADC voltage values for RGB are now compared with the ADC voltage values of object and intensity of RGB in image to get accurate color of the object. The robot then picks and places the object at its position. STEP 7: Stop the entire process when picking and placing of all the objects are done. VII. CONCLUSION The automated system outlined above provides cost effective, low time consuming and technically simple approach for sorting of objects. The proposed system uses Raspberry pi 3 which makes the model easy to use and more efficient. Generally, sensing the color of the object is a big challenge as there is a chance of high uncertainty due to the external lighting conditions and other noise. Further approaches to this system can be made to increase Fig.2 Object sorting kit Fig.3 The red object is sensed and placed Fig.4 The Green object is sensed and placed Fig.5 The Blue object is sensed and placed
X. ACKNOWLEDGEMENT Guide Details: We would like to thank all the authors of different research papers referred during writing this paper. It was very knowledge gaining and helpful for the further research to be done in future. REFERENCES: 1) Szabo R.; Lie I. "Automated colored object sorting application for robotic arms Electronics and Telecommunications (ISETC) 2012 10th International Symposium on vol. no. pp.95 98 15-16 Nov. 2012. 2) Aji Joy, Object sorting robotic arm based on color sensing, International Journal of Advanced Research in Electrical, Electronics and Instrumentation Engineering, Vol.3,Issue 3, March 2014. 3) Viren Pereira, Vandyk Amsdem Fernandes and Junieta Sequeira, Low cost object sorting robotic arm using raspberry pi, 2014 IEEE global humanitarian technology conference, Sept 27, 2014. 4) N. P. Papanikolopoulos, P. K. Khosla, and T. Kanade, Visual tracking of a moving target by a camera mounted on a robot: A combination of vision and control, IEEE Trans. Robot. Automczt. vol. 9, no. I, pp. 14-35, 1993. AUTHOR(S) PROFILE: Y. Aruna Suhasini Devi, completed BE in ECE, M.Tech in Digital Systems & Computer Electronics. Presently working as Associate Professor in the Department of Electronics and Communication, CMR College of Engineering & Technology, Hyderabad. Life Member of ISTE and Fellow Member of IETE. Research interestsare in the area of Image Processing and Microcontrollers. Co- Guide Details: K. Jyothi Presently working as Assistant Professor in the Department of Electronics and Communication, CMR College of Engineering & Technology, Hyderabad. Asra anjum is pursuing the M.Tech in Embedded systems from CMR Institute of Engg & Tech, Hyderabad.