OPTIMAL NAVIGATION PLANNING FOR MOBILE ROBOTS USING REINFORCEMENT LEARNING (RL) ALGORITHM

Abstract

The QL controller solved the path optimization problems for mobile robots. The QL algorithm
predicts the mobile robot's course by learning from prior observations of the surroundings. On the
other hand, the QL method calculates the states' Q values to offer massive deals to the Q table. The
QL algorithm had optimal navigation planning for mobile robots in a dynamic environment. The
mobile robot communicated with the control script by the robot operating system (ROS). The
mobile robot is code-programmed using Python in the ROS operating system and the QL controller
on Gazebo software. This QL controller is improved for the computation time, convergence time,
planning trajectories accuracy, and avoidance of obstacles. Therefore, the QL controller solved the
path optimization problems for mobile robots. The QL controller's efficiency was evident in its
ability to adjust to changing environments swiftly, ensuring seamless navigation without
compromising safety. By leveraging the power of machine learning and advanced algorithms, the
mobile robot could adapt its trajectory in real-time, responding to obstacles and dynamic
conditions with precision. This groundbreaking approach optimized path planning and enhanced
the overall performance of mobile robots, paving the way for a new era of intelligent and
autonomous robotic systems.