Hierarchical Control Framework for Path Planning of Mobile Robots in Dynamic Environments Through Global Guidance and Reinforcement Learning

This article focuses on achieving efficient and safe navigation for robots in dynamic and unpredictable environments. We propose a hierarchical path planning framework that integrates global path planning with local dynamic obstacle avoidance. This framework aims to quickly plan a collision-free, shortest, and safest path for the robot while adapting the navigation path according to uncertainties in the operating environment. Global path planning is conducted using the improved gray wolf optimization algorithm (IGWO), trajectory tracking is achieved through a pure pursuit control algorithm, and a dynamic switching mechanism based on deep reinforcement learning (DRL) significantly enhances the navigation performance of the robotic system. The effectiveness of this approach has been verified through simulations and experiments. Simulation results indicate that in global path planning, the IGWO algorithm achieves faster convergence compared to algorithms, such as GWO-MP and GWO-CS. The planned path lengths are reduced by approximately 4.01% and 2.27%, respectively, and the fitness values are decreased by 4.78% and 1.9%, demonstrating superior path planning performance. For local dynamic obstacle avoidance, both single-robot and multirobot systems successfully avoided obstacles in multiple experiments. Finally, physical experiments conducted in various complex scenarios show that both single-robot and multirobot systems can effectively execute global planning and respond to unexpected obstacles. These results further demonstrate the method’s wide applicability and robust performance across diverse complex environments.

I. Introduction

With technological advancements, mobile robots are increasingly deployed in complex scenarios, such as resource exploration [1], goods delivery [2], and medical rescue operations [3], demonstrating remarkable flexibility and efficiency [4]. However, ensuring that robots can navigate various obstacles safely and efficiently while following optimal paths and adapting to dynamic environmental changes remains a significant challenge in automation and robotics [5]. To address this challenge, it is crucial to develop efficient obstacle avoidance path planning algorithms that enable collision-free navigation from a specified starting point to a target location. Currently, obstacle avoidance path planning generally falls into two main categories: 1) offline planning for static obstacles in fully known environments and 2) online planning for dynamic obstacles in partially known environments [6].