CN-122018531-A - Unmanned aerial vehicle automatic obstacle avoidance system

CN122018531ACN 122018531 ACN122018531 ACN 122018531ACN-122018531-A

Abstract

The invention discloses an automatic obstacle avoidance system of an unmanned aerial vehicle, and belongs to the technical field of unmanned aerial vehicle control. The system includes a power system, a radar scanning system, and a camera imaging system. The power system comprises a vertical power unit, a horizontal power unit and an adjusting power unit, and is used for providing flight power for the unmanned aerial vehicle. The radar scanning system scans the airspace in front of a preset flight path of the unmanned aerial vehicle, performs weighted average on multiple radar scanning data to obtain airspace information T, and filters impurity information through screening. And the camera imaging system shoots a real-time scene of an airspace in front of the preset flight path, and determines airspace information F. And establishing three-dimensional coordinates by taking the unmanned aerial vehicle as a coordinate origin, respectively converting the airspace information T and F into coordinate information, and determining real-time airspace information by judging the matching degree. The system further includes an image processing center and a mode switching system that is switchable between a manual mode and an automatic pilot mode, the control system automatically changing the flight path when a predetermined flight path condition difference is detected. The invention can improve the flight safety and the automation degree of the unmanned aerial vehicle.

Inventors

DOU ZHAOQI
LI YIHENG
SHI HONG
XU MENG
DAI CHANGQI

Assignees

零重力南京航空科技有限公司

Dates

Publication Date: 20260512
Application Date: 20260119

Claims (10)

1. An unmanned aerial vehicle automatic obstacle avoidance system, comprising: The power system comprises a vertical power unit, a horizontal power unit and an adjusting power unit, and is used for providing flight power for the unmanned aerial vehicle; The radar scanning system is used for scanning an airspace in front of a preset flight path of the unmanned aerial vehicle to obtain radar scanning data T of the airspace, and carrying out weighted average on the radar scanning data T generated for many times to obtain airspace information T of the preset flight path; the camera imaging system is used for shooting real-time scenes of airspace in front of a preset flight path of the unmanned aerial vehicle and determining airspace information F of the preset flight path according to the real-time scenes; And establishing three-dimensional coordinates by taking the unmanned aerial vehicle as a coordinate origin, respectively converting the airspace information T and the airspace information F into first coordinate information and second coordinate information, judging the matching degree between the first coordinate information and the second coordinate information, and determining the real-time airspace information of the preset flight path according to the matching degree.
2. The unmanned aerial vehicle automatic obstacle avoidance system of claim 1, wherein the radar scan data t is screened to filter out impurity information, and wherein: The nth scanning of the radar scanning system generates radar scanning data T n , the (n+1) th scanning of the radar scanning system generates radar scanning data T n+1 , the sharing information of the radar scanning data T n+1 is T n+1 -A1+B1, matching is conducted on airspace information T n and sharing information T n+1 -A, a matching value is obtained, and real airspace information T n of an airspace is judged according to the matching value.
3. The automatic obstacle avoidance system of claim 2 wherein the airspace information T n is matched with the three-dimensional coordinates, the moving unmanned aerial vehicle is taken as a coordinate origin to obtain three-dimensional coordinate information Q1 of airspace information T n , the airspace information T n is a dynamic straight line in the three-dimensional coordinates, and the dynamic straight line is related to a preset flight path of the unmanned aerial vehicle in K.
4. The automatic obstacle avoidance system of claim 2, wherein A is airspace information newly added to the unmanned aerial vehicle on a preset flight path from the nth scan to the n+1th scan, and the time from the nth scan to the n+1th scan is t1.
5. The unmanned aerial vehicle automatic obstacle avoidance system of claim 1, wherein the camera imaging system performs imaging synchronously when the radar scanning system scans, matches the spatial information F n generated by each imaging with the three-dimensional coordinates to obtain three-dimensional coordinate information Q2 of spatial information F n , compares the three-dimensional coordinate information Q2 of spatial information F n with the three-dimensional coordinate information Q1 of spatial information T n to obtain a matching value P, sets an error between Q1 and Q2 not to exceed Y, judges that the spatial information F n is consistent with the spatial information T n if P < Y, judges that the spatial information F n is inconsistent with the spatial information T n if P > Y, and judges the accuracy of the spatial information F n and the spatial information T n .
6. The unmanned aerial vehicle automatic obstacle avoidance system according to claim 5, further comprising an image processing center that transmits the acquired airspace information F n to the image processing center, wherein the image processing center determines that the authenticity of airspace information F n is excellent, and when the authenticity of airspace information F n is determined to be poor and P < Y, the authenticity of airspace information T n is determined to be poor, and then the airspace information T n and airspace information F n are re-acquired, and when the authenticity of airspace information F n is determined to be poor and P > Y, the authenticity of airspace information T n is determined to be excellent, and then the airspace information F n is re-acquired, and when the authenticity of airspace information F n is determined to be excellent and P < Y, the authenticity of airspace information T n is determined to be excellent, the airspace information T n and airspace information F n can be used directly, and when the authenticity of airspace information F n is determined to be excellent and P > Y, the authenticity of airspace information T n is determined to be poor, and then the airspace information T n is re-acquired.
7. The unmanned aerial vehicle automatic obstacle avoidance system of claim 1, wherein the airspace information comprises mobile information, weather information, and obstacle information.
8. The unmanned aerial vehicle automatic obstacle avoidance system of claim 1, further comprising a mode switching system for switching a flight mode of the unmanned aerial vehicle, the flight mode comprising a manual mode and an autopilot mode, the control system being turned off when the flight mode is the manual mode.
9. The automatic obstacle avoidance system of claim 8 wherein when said flight mode is autopilot, a control system is enabled, said control system controlling the powertrain to change a predetermined flight path of the unmanned aerial vehicle when airspace information acquired by said radar scanning system and camera imaging system reveals a predetermined flight path condition difference.
10. An electronic device, the electronic device comprising: at least one processor, and A memory communicatively coupled to the at least one processor, wherein, The memory stores a computer program executable by the at least one processor to enable the at least one processor to execute the flight control system of any one of claims 1-8 for use in an electric unmanned aerial vehicle.

Description

Unmanned aerial vehicle automatic obstacle avoidance system Technical Field The invention relates to the technical field of unmanned aerial vehicle obstacle avoidance, in particular to an automatic unmanned aerial vehicle obstacle avoidance system. Background Along with the rapid development of unmanned aerial vehicle technology, unmanned aerial vehicle has obtained wide application in fields such as taking photo by plane, logistics distribution, agricultural plant protection, security protection control. However, the autonomous flight and obstacle avoidance capabilities of unmanned aerial vehicles in complex environments are still a key technical problem restricting further popularization and application. The existing unmanned aerial vehicle obstacle avoidance system mainly relies on a single sensor to detect obstacles, and the problems of insufficient detection precision, poor reliability and the like exist in a complex flight environment. At present, the unmanned aerial vehicle obstacle avoidance technology mainly adopts two modes of radar detection or visual identification. Chinese patent CN111399535A discloses an unmanned aerial vehicle obstacle avoidance method, which comprises obtaining detection data of radar and vision data of a camera, determining that an obstacle exists in an airspace within a predetermined range on an unmanned aerial vehicle route according to the detection data and the vision data, and performing an emergency pause and a corresponding obstacle avoidance mode [ CN111399535A ] on the unmanned aerial vehicle. Chinese patent CN119200625A discloses a dynamic planning method for an unmanned aerial vehicle inspection path in a three-dimensional scene, by scanning depth information of a flight area in real time, obtaining a ranging value in front of an unmanned aerial vehicle and a depth actual measurement value below the unmanned aerial vehicle, judging collision risk according to the ranging value and the depth actual measurement value, and performing automatic obstacle avoidance [ CN119200625A ]. Chinese patent CN103984357B discloses an unmanned aerial vehicle automatic obstacle avoidance flight system based on panoramic stereoscopic imaging equipment, which adopts catadioptric panoramic stereoscopic imaging equipment to collect omnidirectional stereoscopic scenes, and performs obstacle point detection and effective flight path judgment according to geographic coordinate information provided by a navigation module [ CN103984357B ]. In addition, there are some technical solutions that attempt to improve obstacle avoidance performance by adopting a multi-sensor fusion manner. Chinese patent CN108334103B discloses a multi-distance obstacle avoidance method for an unmanned aerial vehicle, by acquiring obstacle information on multiple distance levels in a flight airspace of the unmanned aerial vehicle, and applying multiple obstacle avoidance mechanisms in parallel, predictive avoidance of large-scale obstacles and mobility obstacles in a medium distance range on a flight path is achieved [ CN108334103B ]. Chinese patent CN108227738B discloses an unmanned aerial vehicle obstacle avoidance method, which uses millimeter wave radar to detect an obstacle, then analyzes the type of the obstacle in combination with a video image captured by a front camera, and comprehensively analyzes the shape and distance information of the obstacle to construct a grid map for path planning [ CN108227738B ]. However, the prior art still has the following problems that firstly, a special remote controller is combined with a scheme of an unmanned aerial vehicle, the remote controller has a simple display function, the processing capacity of a control system is limited, and high-difficulty flight control cannot be supported, secondly, the existing unmanned aerial vehicle automatic driving control system can only fly along a preset flight path, and lacks flexible path adjustment capacity, and most importantly, the acquired airspace information is inaccurate due to simple radar early warning, is easily influenced by environmental interference and equipment errors, and cannot effectively avoid obstacle. These problems seriously affect the flight safety and reliability of unmanned aerial vehicles in complex environments, and limit the further development and application of unmanned aerial vehicle autonomous flight techniques. Disclosure of Invention (One) solving the technical problems In order to solve the problems that a scheme of combining a special remote controller with an unmanned aerial vehicle in the prior art has a simple remote controller display function, a limited processing capacity of a control system and can not support high-difficulty flight control, and the existing unmanned aerial vehicle automatic driving control system can only fly along a preset flight path, and simply relies on radar early warning to cause inaccurate acquired airspace information and can not perform effective obstacle avoidanc