Unmanned aerial vehicle path planning method based on Monte Carlo tree search

Abstract

The invention discloses an unmanned aerial vehicle path planning method based on Monte Carlo tree search. The unmanned aerial vehicle path planning method is high in algorithm efficiency, good in performance and capable of better adapting to a dynamic environment. The method comprises the following steps of: (10) establishing a Monte Carlo tree, initializing a root node, and initializing the position of an unmanned aerial vehicle; (20) setting the total number of times of Monte Carlo tree search algorithm training according to experimental data; (30) performing search algorithm training on the Monte Carlo tree within the set total number of times of training, so as to make the parameters of the Monte Carlo tree iterated according to specific steps and the unmanned aerial vehicle perform corresponding actions; and (40) when the number of times of training is equal to the total number of times of training, finishing training to obtain a trained Monte Carlo tree, according to the tree structure of the trained Monte Carlo tree, continuously selecting downwards a child node with the maximum UCT value from the root node by using a UCT algorithm until reaching a leaf node, and enabling the unmanned aerial vehicle to execute a corresponding action according to the selected node, so as to obtain an optimal unmanned aerial vehicle path.

Description

technical field [0001] The invention belongs to the technical field of UAV path planning, and in particular relates to a UAV path planning method based on Monte Carlo tree search. Background technique [0002] In recent years, drones have proven to be one of the most challenging and promising technologies in aviation. Due to their high mobility and low cost, UAVs have been widely used in the field of communication over the past few decades. At the same time, the UAV path planning task is becoming one of the key technologies of UAVs and has been extensively studied by scholars around the world. The main goal of UAV path planning is to design an optimal flight path pointing to the target, that is, to meet the given target conditions while meeting the performance requirements of the UAV. [0003] UAV-assisted wireless communication can provide wireless connectivity to devices without communication infrastructure coverage, such as areas where infrastructure cannot be covered d...

AI Technical Summary

Problems solved by technology

The user's task demand in each time slot will affect the migration throughput of the system, and the user's movement will affect the state of the communication channel and the energy consumption of the UAV.

Traditional reinforcement learning methods, such as Q-learning, will cost a lot of time and space when dealing with a large number of state-action pairs, which will reduce the efficiency of UAV path planning and cannot be directly applied to dynamic environments.

Images