HECTOR SLAM BASED NAVIGATION WITH INTEGRATED OBJECT DETECTION

The main aim of this study is to develop an approach that detects and classifies objects in indoor areas by applying Hector Simultaneous Localization and Mapping (SLAM) and "You Only Look Once" (YOLO) algorithms to an autonomous, custom-made mobile robot. The approach is based on the Robot Operating System (ROS) and computer vision. The mobile robot's motion, path, and communication are controlled by the ROS navigation package. This paper provides a detailed description of the approach implemented to create a new map with objects, as well as information about the hardware and software configuration of the mobile robot. The object identification process and map creation are performed using a low-budget Laser Imaging Detection and Ranging (LIDAR) sensor and non-encoder DC motors. The results show that the proposed technique can detect objects with an accuracy of 97.8% and 94.86% for the x and y cartesian axes, respectively..