Search Results for Maysam Hameed Qasim

Abstract

Autonomous mobile robots (AMRs) are becoming increasingly important in different domains such as healthcare, warehouse automation and household duties, but still encounter problems when it comes to moving around unfamiliar and dynamic environments. This study proposes an advanced robotic navigation system which combines the Soft Actor-Critic (SAC) approach and Vector Field Histogram (VFH) for path planning and avoidance obstacles in completely unknown environments. This system leverages the strengths of deep reinforcement learning and real-time obstacle detection to achieve robust and efficient navigation in certain scenarios. The SAC strategy optimizes robot navigation using policy networks and Q-networks, while the VFH method addresses obstacle avoidance by sensor data processing and dynamically adjusting the robot’s angular velocity to avoid collision. For testing and implementing this system, Gazebo simulation and Robot Operating System (ROS) are used. Experimental results demonstrated that the proposed method outperformed the standard technique and achieved a high success rate in path planning and obstacles avoidance.