Performance Evaluation of Reinforcement Learning and Graph Search-based Algorithm for Mobile Robot Path Planning

Mobile robot path planning is a vital problem in robotics that involves determining a collision-free path for a robot from a starting point to a goal point in environments populated with obstacles. In this paper, a comparative analysis of two path planning approaches for mobile robots is presented. Q-learning is used as a reinforcement learning (RL) approach, and A* as a graph search method. The performance of each technique is evaluated in Gazebo environment on a simulated Ackermann drive mobile robot that navigates through an environment containing obstacles. The generated paths are compared based on the path length, computational time, travel time, the robustness of the planning technique to changes in the environment, and path smoothness. The results show that Q-learning outperforms A* in terms of computation time. The computed paths by the Q-learning based approach are more smooth with fewer number of turns. Moreover, A* is not robust to environmental complexity because the computational time, and length of the computed path increases as the complexity of the environment increases. Hence, the acquired findings suggest that Q-learning can be a promising approach for mobile robot path planning, particularly in scenarios where path smoothness, robustness, and computational time are critical factors.