<p>Pada penelitian ini, akan diterapkan konsep <em>fuzzy logic </em>sebagai kendali cerdas pada robot line follower. Aturan pada <em>fuzzy logic</em> menggunakan metode <em>mamdani</em>. Sebagai input kendali digunakan 2 nilai hasil pembacaan sensor garis yang merupakan data biner 6-bit, yaitu pembacaan pada saat sampling ke-(<em>k</em>)<em> </em>dan pembacaan pada saat sampling ke-(<em>k-1</em>). Hasil pembacaan sensor diberi bobot dengan range nilai dari 0 s/d 255 yang merupakan semesta pembicaraan dari fuzzy set input ini. Setiap fuzzy set input menggunakan 5 <em>membershif function, </em>dan <em>rule base </em>yang digunakan sebanyak 25. Pada fuzzy set output digunakan 5 <em>membership function </em>dengan semesta pembicaraan adalah -127 s/d +127. output fuzzy merupakan bilangan crips tunggal yang didapat dengan menggunakan metode COG (<em>Center of Gravity</em>). Nilai crips output ini digunakan sebagai nilai deviasi untuk mengatur nilai PWM pada motor penggerak roda kiri dan kanan dari robot line follower. Pengujian fungsi kendali menggunakan metode matematis dan simulasi berbasis Simulink. Dari hasil yang didapat menjelaskan bahwa robot dapat bergerak sesuai dengan desain rule base yang digunakan.</p><p> </p><p> </p><p><strong><em>Abstract</em></strong></p><p><strong><em> </em></strong><em>In this research, the fuzzy logic concept will be applied as intelligent control on line-follower robot. The rules on fuzzy logic use the Mamdani method. As control inputs, used 2 values of line sensor readings are in the form of 6-bit binary data. the input is the sensor reading at the time of the kth sampling and the reading at the k-sampling moment. The sensor readings are weighted with a range of values from 0 s / d 255 which is the universe of speech from the fuzzy set of these inputs. Each fuzzy set of inputs uses 5 membership function, and the base rule used is 25. In fuzzy set output used 5 membership functions with the universe of talk is -127 s / d +127. the fuzzy output is a single crips number obtained by using the COG (Center of Gravity) method. This output crips value is used as the deviation value to set the PWM value on the left and right wheel drive motor of the line follower robot. Tests of control functions using mathematical methods and Simulink based simulations. From the results obtained to explain that the robot can move in accordance with the design of the base rule used</em></p><p> </p>
In this research the master-slave method implemented on an embedded system using 3 processor applied to the mobile robot, to know the speed of program execution of robot. As a comparison is also used a robot with an embedded system based on single processor. From the experimental results, by applying the slave master method obtained the execution time of 546,5 μs and the number of iteration 1079, while for single processor-based system obtained execution time average 67828 μs and the amount of iteration average 147 times. Where the number of iterations is obtained by running the robot for 10 s. From this experiment, it can be concluded that there is a performance increase of 7.3% when compared to embedded systems based on single processor.
The texture feature description becomes a tremendous challenge in the field of computer vision and pattern recognition. The high-quality feature descriptor attributes some of which are unique, due to a large number of texture classes, robust against illumination variations, and low dimensional representations. A number of image feature extraction methods had been proposed, which can be divided into two categories: holistic and local image feature extraction. The holistic feature extraction method is very sensitive to changes in geometric shapes and some variations of illumination and noise. The local image feature extraction methods can effectively overcome those weaknesses. In this study, the texture features of an RGB image are built using the Local Weighting Pattern (LWP). By using the gray-level dynamic range modification technique, Fuzzy Membership Function (MF) is applied to LWP texture images to build Fuzzy-based LWP image (FLWP). From the resulting image is then used to generate a feature descriptor in the form of labels.
In robot fire extinguisher not only extinguish the fire but search for space contained by fire. When a robot searches for a fire inside the room, the robot goes through the process and tries to know the surroundings in order to know the position of the robot and to know what action to take, on positioning not only knowing where the robot is but also knowing the direction of the robot. This study aims to build intelligent control based Fuzzy Logic (Logic Samar) to determine the position of robots are located when inside the arena or the environment. Fuzzy Logic Testing using Mathlab Software (software). The sensor data as a reference environment is built on Random (random). Once data is built, data is then processed using Fuzzy Logic. The result will be robot position. From that position it will be known where the robot and what decisions to take.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.