Implementation of Convolutional Neural Network (CNN) Algorithm for Autonomous Robot

Abstract

In Indonesia, the development of autonomous robots has emerged intensively since the last coronavirus pandemic, especially the autonomous UV disinfection (A-UV) robot. A-UV disinfection robot has the purpose of purifying germs and pathogens in critical areas, such as the hospital. As the minuscule creature can be difficult to control, the anticipation of letting no human have contact with it is one of the other purposes of the A-UV disinfection robot. However, the systematic development of the autonomous robot is the priority, where the robot can offer a collision-free obstacle, and target-lock when arriving at the designated location. In this study, two main contributions are proposed to develop the autonomous robot: 1) Convolutional Neural Network (CNN) algorithm to learn the potential surrounding the lock area from the dataset to ensure collision-free during the operation. 2) Original design to ensure the compactness of the autonomous robot with almost omnidirectional UV light. We design the surrounding area with “BOX” as the obstacle and “SIGN STOP” as the target in our CNN dataset. The performance is validated to have 97% and 99% for training and validation performance and 0.3% for loss. The robot prototype was also developed and tested inside a workspace with a size of 2.1 x 3 m. The robot prototype successfully performed the required tasks.