Deep reinforcement learning with enhanced PPO for safe mobile robot navigation

Collision-free motion is essential for mobile robots. Most approaches to collision-free and efficient navigation with wheeled robots require parameter tuning by experts to obtain good navigation behaviour. This study investigates the application of deep reinforcement learning to train a mobile robot for autonomous navigation in a complex environment. The robot utilises LiDAR sensor data and a deep neural network to generate control signals guiding it toward a specified target while avoiding obstacles. We employ two reinforcement learning algorithms in the Gazebo simulation environment: deep deterministic policy gradient and proximal policy optimisation. The study introduces an enhanced neural network structure in the proximal policy optimisation algorithm to boost performance, accompanied by a well-designed reward function to improve algorithm efficacy. Experimental results conducted in both obstacle and obstacle-free environments underscore the effectiveness of the proposed approach. This research significantly contributes to the advancement of autonomous robotics in complex environments through the application of deep reinforcement learning.