Indoor route planning and mapping for autonomous mobile robot

This thesis covers SLAM (Simultaneous Localization and Mapping) and navigation studies performed on the TurtleBot3 robot. The aim of the thesis is to to improve autonomous driving capabilities and enable them to act effectively in a complex environment. TurtleBot3 is a compact and mobile robot platform. This platform is equipped with a series of sensors and motion control units operating under the umbrella of ROS (Robot Operating System). These sensors include LIDAR (Light Detection and Ranging) sensor, IMU (Inertial Measurement Unit) and odometry. These sensors allow the robot to It helps it perceive its environment, track its location, and move. Autonomous driving refers to the TurtleBot3 robot's ability to steer itself without human intervention. Thanks to SLAM and navigation capabilities TurtleBot3 can realize autonomous driving. Using map and location information, the robot detects obstacles, adapts to environmental conditions and moves safely towards the target. Path planning algorithms such as the A* algorithm help achieve autonomous driving successfully by ensuring TurtleBot3 reaches the destination safely and quickly. Path planning is the process of determining a path that a robot or vehicle must follow to reach its destination from a specific starting point. Path planning consists of a set of algorithms and strategies used to ensure that robots or vehicles overcome obstacles and reach their destination safely and effectively. Path planning algorithms help find the shortest or most appropriate path in the given environment. Algorithm like A* is the popular method often used in path planning. The A* algorithm considers the distance to the destination as well as the shortest path using the estimated cost function. In this way, the TurtleBot3 robot operates more efficiently. It can move faster and reach the target faster. Path planning algorithms enable the TurtleBot3 robot to find the optimal path in the given environment. In this thesis, algorithms such as DWA (Dynamic Window Approach) and A* are used in road planning. DWA is a path planning and control method that helps an autonomous robot instantly create a safe and effective action plan, taking into account environmental conditions and speed control. The A* algorithm, on the other hand, is an improved version of the Dijkstra algorithm and can produce faster results. The A* algorithm considers the distance to the destination as well as the shortest path using the estimated cost function. In this way, the TurtleBot3 robot can move more efficiently and reach the target faster. Within the scope of this thesis, various experimental studies were carried out to improve the SLAM, navigation and autonomous driving capabilities of the TurtleBot3 robot. In these studies, different scenarios were tested using the Gazebo simulation environment and the A* algorithm was also evaluated in this simulation environment.