Robot path planning algorithm with improved DDPG algorithm

This study focuses on enhancing the autonomous path planning capabilities ofintelligent mobile robots, which are complex mechatronic systems combining variousfunctionalities such as autonomous planning, behavior control, and environmentsensing. Path planning is crucial for robot mobility, enabling them to navigateautonomously. We propose an improvement to the deep deterministic policy gradient(DDPG) method by leveraging deep reinforcement learning algorithms. Throughextensive experimentation, our method demonstrates superior performance comparedto traditional DDPG, with notable reductions in training time and iterations required toreach targets. Additionally, it reduces dead zone encounters during travel andenhances convergence speed. Our findings contribute fresh insights and strategies forenhancing mobile robot path planning in unfamiliar environments. Future research willexplore further advancements, particularly in addressing dynamic obstacles andoptimizing real-world navigation efficiency.