Indoor Path Planning Technology Based On UAV System

With the rapid development of the flight control technology,the unmanned aerial vehicle(UAV)system is valued by more and more people in recent years.A large number of companies from different countries begin to develop their own unmanned aerial system(UAS)with high performance and reliability.Simultaneously,the universities and some research institutions put more focus on the intelligence and multitasking of the UAV system,which include the environment sensing,path planning,etc.This paper proposes a new flight control system which aims to verify the feasibility of the path planning algorithm in indoor environments with the help of the UAV.The major contents include path planning,image processing,embedded software development,robot operating system(ROS)and flight control.The entire UAV system consists of three modules,that is the embedded UAV flight platform,the image processing system with single camera and the ground monitoring system for sending commands.In the indoor environment,an industry camera is installed on the ceiling to capture the image of the aircraft.Then we can obtain the basic information of the aircraft using the image processing algorithm.Simultaneously,according to the commands from the ground station,we start the path planning process to implement the intelligent control of the aircraft.The main contributions and results of the paper can be summarized as follows:Firstly,four main algorithms for path planning are proposed in this paper.In the first algorithm,we establish a fuzzy control model between the flying point and the probabilistic risks,which has great advantage for the situation with dynamic obstacles.The A star algorithm create a cost system to optimize the path points.And the rapidly-exploring random tree(RRT)algorithm,as the third method,proposes the map searching structure which helps the UAV flying towards the destination.The last algorithm carries out a potential energy theory to simulate the planning process.We also evaluate the stability and efficiency of those algorithm through the contrast experiment,Secondly,we establish the entire software system of the UAV flight platform.Two threads are built in the image processing system,including the image thread which aims to obtain the real-time position using Open CV and the serial thread which is used to transmit the data frame to the ground station.The ground monitoring system designs the command control node for sending message to the aircraft and the position analyzing node to extract the key information from the data frame.Once the command is sent,the UAV system will follow the basic instruction and move to the aim point.Finally,we design and implement the basic hardware s ystem for the project.We design the PID control strategy to adjust the movement of the aircraft.Then,we show the whole procedure for the UAV path planning,which have obtained the predictive effect.