Autonomous navigation of ROS2 based Turtlebot3 in static and dynamic environments using intelligent approach

Abstract This study offers a unique strategy for autonomous navigation for the TurtleBot3 robot by applying advanced reinforcement learning algorithms in both static and dynamic environments. With the use of TD3 (twin-delayed deep deterministic), DDPG (Deep Deterministic Policy Gradient), and DQN (Deep Q-Network), real-time object detection, tracking, and navigation can now be done seamlessly by the proposed TD3 algorithms. Additional techniques have been integrated to this project to enhance its mobility performance: ROS 2 (Robot Operating System 2) and LiDAR (Light Detection and Ranging)-based perception. Performance comparison among the above-mentioned algorithms shows that TD3 is the most efficient and robust when exposed to diverse environments. The work further addresses significant gaps in dynamic obstacle navigation and maze resolution, significantly changing the game for robotics applications such as those found in surveillance, human–robot interaction, and inspection. The outcome significantly boosts TurtleBot3's performance and capabilities across various scenarios.