Progress in the Application of Deep Reinforcement Learning in Path Planning and Control of Mobile Robots

Abstract

This study reviews the progress in the application of deep reinforcement learning in the field of path planning and control for mobile robots. Traditional methods exhibit poor adaptability in complex and dynamic environments, struggling to handle static and dynamic obstacles as well as environmental uncertainties. Deep reinforcement learning enables robots to autonomously interact with the environment and learn optimal strategies, significantly enhancing the performance of path planning and control. The article provides a detailed analysis of the limitations of traditional methods, such as high computational complexity, susceptibility to local optima, and lack of adaptability. It also introduces the advantages of deep reinforcement learning algorithms (e.g., DDPG, SAC) and their improved variants (e.g., APF-DDPG, AM-LSTM-SAC). These algorithms demonstrate excellent experimental results in various environments through multi-algorithm fusion strategies. The paper further discusses the setup of simulation environments, experimental configurations, and result analysis, summarizing existing achievements and shortcomings while providing an outlook on future research directions. This work offers valuable insights for the further development of mobile robot technology."