Obstacle Avoidance Robot

Abstract

The goal of this project is to use a variety of autonomous navigation algorithms to avoid obstacles, allowing a robot to move and work in an unstructured, unknown environment. The investigation and study of the platform at the Mechatronics Laboratory, on which the navigation algorithm is implemented, is the first step. ROS has been utilized in relation to the software platform. An open-source framework for controlling the actions, tasks, and operations of robots is known as the Robot Operating System. Because the ROS-compatible TurtleBot3 (Burger) has been utilized. The evaluation of the various algorithms that are appropriate and pertinent to our objective, environment, and purpose is the second step. The navigation, which is typically divided into global motion planning and local motion control, can be implemented using a variety of methods. When autonomous mobile robots work in an environment, previous maps frequently contain inaccuracies or are incomplete. They require a safe course that avoids collision. As a result, the robot is able to move toward the open area while avoiding the obstacles thanks to the sensor that is mounted on it. This paper discusses three distinct Obstacle Avoidance algorithms for fully autonomous navigation in an unstructured environment. All of the algorithms are tested on the TurtleBot3 robot, where only LiDAR was used as a sensor to identify obstacles. The complexity of the algorithms grows as the evolution and the various possible situations in which the robot will have to move are considered. The main advantage of the third algorithm, "Autonomous Navigation," is that it can perform curved trajectories with precise path selection. Combining angular and linear velocity (980 different motions), the LiDAR scans 180 degrees in front of the robot to determine the correct direction. The automatic creation of the map is the final step. The official ROS environment software, RViz, will be used to analyze and compare this map to the one created using RViz. The tool can be used to record sensor data, debug problematic behaviors, visualize the robot's state and the performance of the algorithms, and more. This reactive approach to obstacle avoidance can be improved by driving robots successfully into challenging locations. In order to conclude this study, we will present the experimental results on TurtleBot3 to support the findings and make a case for the benefits and drawbacks