Master-Slave Parallel Vector-Evaluated Genetic Algorithm for Unmanned Aerial Vehicle's path planning

The demand of Unmanned Aerial Vehicle (UAV) to monitor natural disasters extends its use to multiple civil missions. While the use of remotely control UAV reduces the human casualties' rates in hazardous environments, it is reported that most of UAV accidents are caused by human factor errors. In order to automate UAVs, several approaches to path planning for UAVs, mainly based on Genetic Algorithm (GA), have been proposed. However, none of the proposed paradigms optimally solve the path planning problem with contrasting objectives. We are proposing a Master-Slave Parallel Vector-Evaluated Genetic Algorithm (MSPVEGA) to solve the path planning problem. MSPVEGA takes advantage of the advanced computational capabilities to process multiple GAs concurrently. In our present experimental set-up, the MSPVEGA gives optimal results for UAV.