Optimized path planning of drones for efficient logistics using turning point with evolutionary techniques

Mobile robots/drones are an important consideration in today's society because several basic and hazardous activities of humans are replaced with robots. Moreover, developing an efficient strategy for a mobile robot to secure navigation is the major issue for autonomous robots. Recently, path planning is a major consideration and research on the topic of autonomous robots in the domain of logistics. Finding the safest and shortest path for mobile robots is the focus. The safe path is determined with the turning point algorithm from the moving robot's starting position to the destination position without obstacles. The efficient path for the static and dynamic environment of the safe path is determined using reinforcement learning. Evolutionary particle swarm optimization (EPSO) has been used to enhance the path planning approach for mobile robots to make this path planning robust and efficient. The proposed evolutionary-based path planning approach for mobile robots satisfies three objectives, such as safe path, efficient path length, and also suitable for static and dynamic environments. Finally, the simulation results prove that the proposed method performs better in finding the safest and shortest path for the mobile robot in the static and dynamic environment and is useful for mobile robot robust tracking. The proposed TP-HL-EPSO secured the average cumulative reward of 167. (c) 2022 SPIE and IS&T