Adhly Hasbi Fadhlillah
Fakultas Ilmu Komputer, Universitas Brawijaya

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

Implementasi Robot Lengan Pemindah dan Penghitung Jumlah Barang menggunakan Metode Deteksi Objek Histogram of Oriented Gradient (HOG) dan K-Nearest Neighbor (K-NN) Adhly Hasbi Fadhlillah; Rizal Maulana; Eko Setiawan
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 6 No 6 (2022): Juni 2022
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

All production sectors currently have warehouses that are used as storage of objects. The occurrence of errors in the process of moving objects from one location to another very often occurs which causes objects to get damaged and disrupt activities in the warehouse. To overcome errors that often occur, the creation of a robotic arm that is capable of moving objects is accompanied by the ability to know the number of objects that have been moved. Input for processing in the system will later be obtained from the inframerah sensor and camera. The inframerah sensor is used to detect the availability of an empty final place. The camera functions as a tool used to obtain digital images of objects. The image will be selected using HSV to get the color of the object, which will then be carried out feature extraction using the Histogram of Graident (HOG). The features obtained will be distinguished using K-Nearest Neighbor (K-NN) in order to obtain the final result in the form of the shape and color of the object. In the next step, the object will be moved by the hand robot to its final place by means of reverse kinematics. Inverse kinematics is a way to get the values ​​of each joint from the robot hand by changing the location coordinates. When the robot successfully moves the object, it will automatically add value to the LCD screen. The results of the tests that were run 10 times on the system as a whole got a value of 90% on a successful object movement, a perfect score on the calculation of items that had moved and a calculation time of 9811 microseconds.