Unmanned aerial vehicle collision risk assessment method based on BP neural network

Abstract

The invention belongs to the technical field of unmanned aerial vehicle control, and particularly relates to an unmanned aerial vehicle collision risk assessment method based on a BP neural network. The method comprises: determining an unmanned aerial vehicle speed range; determining the safe distance of the unmanned aerial vehicle; determining motor performance of the unmanned aerial vehicle; determining an unmanned aerial vehicle azimuth evaluation function; determining an unmanned aerial vehicle speed evaluation function; establishing an unmanned aerial vehicle BP neural network model; performing BP neural network learning of the unmanned aerial vehicle; adjusting an adaptive learning rate; adjusting the additional momentum term; and carrying out assessment of collision risk. Accordingto the invention, in order to prevent the problem that a network falls into local minimum and cannot converge to a required error range in an iterative learning process, a BP neural network model ofthe unmanned aerial vehicle is established, an adaptive learning rate algorithm is introduced, the learning rate of each node is optimized to the maximum extent, the convergence rate of the network isfurther improved, and the evaluation of the collision risk degree of the unmanned aerial vehicle is realized are solved.

Description

technical field [0001] The invention belongs to the technical field of unmanned aerial vehicle control, and in particular relates to a method for evaluating the collision risk of an unmanned aerial vehicle based on a BP neural network. Background technique [0002] With the advancement of science and technology and the needs of human development, more and more attention is focused on undeveloped space resources, and drones will be an important carrier for the development of this resource. In recent decades, both countries and enterprises have invested a lot of manpower and material resources in the research of drones, so drone technology has developed very rapidly and has been applied in various industries. In the civilian field, drones have begun to be used in many fields such as power inspections, aerial images, event reports, material transportation, traffic patrols, security monitoring, coastal private collection, emergency monitoring, wildlife observation, and emergency...

AI Technical Summary

Problems solved by technology

If the UAV cannot avoid obstacles in time, it will cause the UAV to be collided and destroyed. In extreme cases, it may cause harm to pedestrians or other objects on the ground, resulting in unnecessary loss of personnel and property

Images