FIRMWARE AND HARDWARE DESIGN AND IMPLEMENTATION OF LINE FOLLOWER ROBOT WITH COMPASS CALIBRATOR AND LOCALIZATION USING RFID FOR LABYRINTH NAVIGATION

• Main Author: Adnan, Muhammad
• Format: Final Project
• Language: Indonesia
• Online Access: https://digilib.itb.ac.id/gdl/view/66446
• Institution: Institut Teknologi Bandung

ABSTRACT Firmware and Hardware Design and Implementation of Line Follower Robot with Compass Calibrator and Localization using RFID for Labyrinth Navigation By Muhammad Adnan NIM: 13218019 (Bachelor????s Program in Electrical Engineering) The navigation problem in the maze is a problem that is often used as an example to test the shortest route algorithm. In this case, one wants to show that the algorithm used is able to solve the shortest-path problem. There have been many algorithms proposed to solve this problem. One of the algorithms that can be used to solve this problem is to use Q-Learning, which is a type of algorithm from Reinforcement Learning (RL). As a part of Machine Learning, RL is able to conduct learning based on trials. If in the experiment, the object conducting the experiment or called the Agent performs an action or action that does not bring the Agent closer to the goal, then the Agent will receive punishment. On the other hand, when the Agent takes a step that brings him closer to the goal, the Agent gets a reward. Thus, as the experiment is carried out by the Agent, the Agent will go towards convergence, namely knowing the best course of action that can be taken to solve a particular case. However, often the system is only in the form of a software model and not until the Hardware implementation. For that we need a system that can represent these problems on Hardware. In this implementation, the Agent representation will be done using a Line Follower robot. Line Follower robot is a type of robot that moves by following a line on the floor. The line will be read by an infrared sensor that is able to distinguish between dark and light. To make the robot walk smoother, an additional sensor input, namely a compass sensor, will be used to support movement control. During the movement, the robot needs to know its position against the testing arena or known as localization. For that, the robot is equipped with an RFID sensor. The test floor has an RFID marker inserted in each state so that when the robot enters a state, the robot can recognize its current position. Tests will be carried out to prove the performance of the Line Follower robot. The robot will be used to test the learning outcomes that have converged so that it shows the fastest way from one point to another in the testing arena. Keywords: Navigtioni, Shortest-path, Line Follower, Compass, RFID.