A method for adjusting the safety distance of an unmanned aerial vehicle

By analyzing video streams and positioning data in real time, using object detection models and LSTM models for obstacle detection and prediction, dynamically adjusting the safe distance of the drone, solving the problems of insufficient response time and complex environment when manually operating the drone to avoid obstacles, and improving flight safety and flexibility.

CN119472740BActive Publication Date: 2025-03-25RISING SUN & BLUE SKY (WUHAN) TECH CO LTD
3 Cites 0 Cited by

Patent Information

Application Number
CN202510037972.6
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2025-01-10
Publication Date
2025-03-25
Estimated Expiration
2045-01-10

AI Technical Summary

Technical Problem

When manually operating the drone to avoid obstacles, you may encounter problems such as insufficient reaction time, visual blind spots and complex environment, which will lead to failure to avoid obstacles and increase the risk of operational errors.

Method used

By obtaining video and positioning data of the drone's flight mission route, using the target detection model and LSTM model for real-time obstacle detection and prediction, calculating the directional angle and relative speed between the drone and the obstacle, and dynamically adjusting the safe distance to adapt to the current flight environment and conditions.

Benefits of technology

It realizes that the drone can dynamically adjust the safe distance while maintaining safe flight, reduce the risk of collision caused by human negligence or errors, and improves the reliability of operation and the practicality of the drone.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The present invention relates to the field of unmanned aerial vehicles, and more specifically, to a method for adjusting the safety distance of unmanned aerial vehicles, the method comprising: obtaining unmanned aerial vehicle flight video and positioning data, constructing an obstacle set and training a target detection model, obtaining the position coordinates of historical obstacles, predicting the obstacle position using an LSTM model, and calculating the prediction accuracy; inputting a real-time frame image into a target detection model to obtain the position coordinates of the obstacle, and predicting the position information at the next moment, calculating the direction angle and trajectory overlap probability between the unmanned aerial vehicle and the obstacle; calculating the relative speed according to the speed vector and direction angle of the unmanned aerial vehicle and the obstacle at the current moment respectively; and dynamically adjusting the safety distance of the unmanned aerial vehicle according to the relative speed between the unmanned aerial vehicle and the obstacle, the trajectory overlap probability, and the prediction accuracy. By dynamically adjusting the safety distance, the unmanned aerial vehicle can improve the reliability of operation and the practicality of the unmanned aerial vehicle while maintaining safe flight.
Need to check novelty before this filing date? Find Prior Art