A ROS-based hybrid algorithm for the UAV path planning problem

PurposeIt is possible with classical path planning algorithms to plan a path in a static environment if the instant position of the vehicle is known and the target and obstacle positions are constant. In a dynamic case, these methods used for the static environment are insufficient. The purpose of this study is to find a new method that can provide a solution to the four-rotor unmanned aerial vehicle (UAV) path planning problem in static and dynamic environments. Design/methodology/approachAs a solution to the problem within the scope of this study, there is a new hybrid method in which the global A* algorithm and local the VFH+ algorithm are combined. FindingsThe performance of the designed algorithm was tested in different environments using the Gazebo model of a real quadrotor and the robot operating system (ROS), which is the widely used platform for robotic applications. Navigation stacks developed for mobile robots on the ROS platform were also used for the UAV, and performance benchmarks were carried out. From the proposed hybrid algorithm, remarkable results were obtained in terms of both planning and implementation time compared to ROS navigation stacks. Originality/valueThis study proposes a new hybrid approach to the path planning problem for UAVs operating in both static and dynamic environments.

Automated summary

The purpose of this study is to find a new method that can solve the path planning problem for four-rotor unmanned aerial vehicles (UAVs) in both static and dynamic environments. By combining the global A* algorithm and the local VFH+ algorithm, a new hybrid method is proposed and tested using a real quadrotor model and the robot operating system (ROS) platform. The results show significant improvements in both planning and implementation time compared to ROS navigation stacks.