Method for predicting flight path of unmanned aerial vehicle through flight mode recognition

• Main Authors: SHI ZHUOYONG, JIA YETAO, ZHANG QINYANG, ZHANG ANLI, CHEN KUIFENG
• Format: Patent
• Language: Chinese; English
• Published: 01.03.2024
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS; SIGNALLING; TRAFFIC CONTROL SYSTEMS

The invention provides an unmanned aerial vehicle flight path prediction method based on flight mode recognition, and the method comprises the steps: building a flight path prediction system of an unmanned aerial vehicle for different flight states, constructing the motion features of the unmanned aerial vehicle through a principal component analysis method, and recognizing the flight state of the unmanned aerial vehicle through an improved support vector machine model. And according to different flight states, respectively establishing prediction models to predict the flight path of the unmanned aerial vehicle. According to the invention, the improved support vector machine model based on the binary tree is adopted to identify different flight states of the unmanned aerial vehicle; and a BP neural network is adopted to establish flight path prediction models in different flight states. The method not only considers the historical flight path of the unmanned aerial vehicle, but also considers the current flig