Search

CN-122015839-A - Unmanned aerial vehicle path planning method and system based on environment model optimization

CN122015839ACN 122015839 ACN122015839 ACN 122015839ACN-122015839-A

Abstract

The invention relates to an unmanned aerial vehicle path planning method and system based on environment model optimization. The method comprises the steps of constructing a first geometric body based on the outline of the unmanned aerial vehicle, constructing a second geometric body based on building models around a planned route, and performing a preliminary superposition test to screen the second geometric body with superposition. And further, dividing the second geometric body with superposition into a plurality of second sub-geometric bodies, correcting the size of the second sub-geometric bodies based on the internal model section, and performing superposition test on the first geometric body and the corrected second sub-geometric bodies to determine collision risk and adjust the route. According to the invention, the invalid redundant space is removed through the segmentation and correction of the building geometry, so that the calculated amount is obviously reduced, and the real-time accurate path planning is realized.

Inventors

  • ZHANG YAO
  • JIANG HAITAO
  • LU LIFEI
  • DING KANG
  • LIU BOWEN
  • WANG JIANNAN

Assignees

  • 北京达美盛软件股份有限公司

Dates

Publication Date
20260512
Application Date
20231221

Claims (18)

  1. 1. An unmanned aerial vehicle path planning method based on environment model optimization, which is characterized by comprising the following steps: constructing a regular first geometry (100) based on the range of contours of the drone (101); constructing a regular second geometry (200) based on a three-dimensional model of surrounding buildings (201) of a planned route (300) of the drone (101); -performing a superposition test of the first geometry (100) with the second geometry (200) along the planned route (300) to screen the second geometry (200) for the presence of superposition; The method further comprises the step of dividing the second geometry (200) with the superposition situation in the horizontal and/or vertical direction to form a number of second sub-geometries (202) before calculating the superposition range; -modifying the size of the second sub-geometry (202) based on a three-dimensional model segment of the building (201) within the second sub-geometry (202); performing a superposition test on the first geometry (100) and the modified second sub-geometry (202), and calculating a superposition range; The planned route (300) is adjusted based on the overlay range.
  2. 2. The method according to claim 1, wherein said constructing a regular second geometry (200) comprises: Determining a height range of a building (201) based on a three-dimensional simulated scene and the planned route (300); Determining a three-dimensional model section of the building (201) based on the height range, the three-dimensional model section being a portion of the building (201) within the height range; the second geometry (200) is constructed on the basis of the three-dimensional model segments at the longest side of the respective coordinate axes.
  3. 3. The method of claim 1, wherein the dividing to form a number of second sub-geometries (202) comprises: Judging the distance between the vertical axis of the first geometrical body (100) and the vertical axis of the second geometrical body (200); When the distance is shortest, the second geometry (200) is divided in the vertical direction.
  4. 4. The method according to claim 1, wherein the method further comprises: Before dividing the second geometric body (200), selecting all vertexes at two ends of the second geometric body (200) to be connected, and constructing a third geometric body (203) forming a trapezoid; -performing a superposition test of the first geometry (100) and the third geometry (203).
  5. 5. The method according to claim 4, wherein the method further comprises: -in case the result of the superposition test is that the first geometry (100) is tangential, overlapping or comprised with the third geometry (203), reserving the second geometry (200) corresponding to the third geometry (203) for a subsequent partitioning step; -excluding the second geometry (200) corresponding to the third geometry (203) in case the first geometry (100) is not comprised by the third geometry (203), nor is it tangential or overlapping with the third geometry (203).
  6. 6. The method of claim 1, wherein the dividing to form a number of second sub-geometries (202) comprises: determining a dividing line at a point where a bending angle of the second geometry (200) is maximum when the first geometry (100) and the second geometry (200) are overlapped and the second geometry (200) has a bending characteristic; -dividing the second geometry (200) into at least two geometrical splits based on the dividing line.
  7. 7. The method of claim 1, wherein the modifying the size of the second sub-geometry (202) comprises: -reducing the size of the second sub-geometry (202) based on the true contour of the building (201) within the second sub-geometry (202) to exclude redundant space within the second sub-geometry (202) that does not contain a three-dimensional model section of the building (201).
  8. 8. The method of claim 1, wherein the manner of overlay testing comprises: Representing the first geometry (100) as a standard equation ax+by+cz+d=0, wherein A, B, C is the coefficients of the geometry in three directions, respectively, D is a constant; Representing the second geometry (200) as a parametric equation P (t) =p1+t (P2-P1), wherein P1, P2 are the two ends of the second geometry (200), respectively; Substituting the parameter equation into the standard equation to calculate a t value, and if the t value is within the [0,1] interval, judging that superposition exists.
  9. 9. The method according to claim 1, wherein the constructing a first geometry (100) of a rule comprises: Receiving geometrical parameters of the supplies (102) acquired by the unmanned aerial vehicle (101); Confirming the carrying mode of the unmanned aerial vehicle (101) on the materials (102); generating outline range parameters of the unmanned aerial vehicle (101) according to the geometric parameters of the materials (102) and the carrying mode; -constructing the first geometry (100) on the basis of the profile of the drone (101) at the longest edge in three dimensions.
  10. 10. The method according to claim 9, wherein the constructing the first geometry (100) of the rule further comprises: -constructing the first geometry (100) based on a maximum value of a sum of a profile range parameter and a safety range parameter of the drone (101); the safety range parameter is a parameter set for a tremble or offset phenomenon of the unmanned aerial vehicle (101) caused by wind resistance influence.
  11. 11. The method according to claim 1, wherein the constructing a first geometry (100) of a rule comprises: -constructing a first aisle model based on the distance of influence of the drone (101) from the building (201) and the planned route (300) with the drone (101) bypassing or traversing the building (201); -taking the first channel model as the first geometry (100).
  12. 12. The method of claim 1, wherein said adjusting said planned route (300) comprises: judging whether the superposition range is larger than a preset superposition range threshold; If so, re-selecting a planned route (300) for the drone (101); if not, the flying height or the flying posture of the unmanned aerial vehicle (101) is adjusted.
  13. 13. An unmanned aerial vehicle path planning system based on environmental model optimization, comprising a remote processor in communication with the unmanned aerial vehicle, wherein the processor is configured to perform the method of any of claims 1 to 12.
  14. 14. The system of claim 13, wherein the processor is configured to: in constructing the second geometry (200), only profile information of the building (201) is retrieved, and no internal structural information of the building (201) is retrieved.
  15. 15. The system of claim 13, wherein the processor is configured to: receiving codes or identifications of the supplies (102) acquired by the unmanned aerial vehicle (101); And calling the length, width and height parameters of the material (102) as geometric parameters according to the codes or the marks.
  16. 16. The system of claim 13, wherein the processor is configured to predict a dynamic situation of the drone (101) passing the second geometry (200) based on the planned route (300); -calculating a superposition of the first geometry (100) and the second geometry (200), said superposition comprising intersection, tangency and inclusion.
  17. 17. The system according to claim 13, wherein the system is further adapted to calculate the probability of passage of the planned route (300) from the range of smoke (401) of the fire (400) and its visibility; and under the condition that the dense smoke range (401) influences the unmanned aerial vehicle throwing material or obstacle avoidance judgment, excluding the influenced planned route.
  18. 18. The system of claim 13, wherein the processor is configured to: When a route comprising a channel is to be used, predicting the collision condition of the unmanned aerial vehicle (101) and the channel and the aerial ladder according to the unfolding height of the aerial ladder fire truck; In the event that there is a risk of collision and the electrical energy is insufficient to support climbing, the route is determined to be unsuitable for flight.

Description

Unmanned aerial vehicle path planning method and system based on environment model optimization The original basis of the divisional application is a patent application with the application number 202311773020.8, the application date 2023, 12 months and 21 days and the invention name of a collision risk prediction system and method of an unmanned aerial vehicle. Technical Field The invention relates to the technical field of unmanned aerial vehicle risk judgment, in particular to an unmanned aerial vehicle path planning method and system based on environment model optimization. Background Unmanned aerial vehicle clusters are widely used for cruising in industrial plants. Especially in the initial stage of fire occurrence, the advantage of the fast action of unmanned aerial vehicle makes the fire more can be eliminated fast, or effectively delays spread speed and spread scope of fire. In the process of extinguishing a fire, a large number of unmanned aerial vehicles need to transport or deliver fire-fighting materials. The unmanned aerial vehicle carries the mode of supplies including two kinds first, carry liquid material through self storage device, for example carry fire extinguishing liquid, fire extinguishing bomb, broken window bullet etc.. Second, large solid materials, such as carrying sand, sandbags, sand, etc., are hoisted by the grasping assembly. Unmanned aerial vehicle carries fire control supplies and changes self flight width and weight. Under the condition of carrying fire-fighting materials, in order to quickly reach a fire point, the unmanned aerial vehicle needs to judge whether the original flight route is available again under the condition of changing the flight width of the unmanned aerial vehicle, and re-plan the flight route according to the current flight width. In the prior art, since the algorithm for calculating the collision risk in real time according to the flight width of the unmanned aerial vehicle is complex, large in calculation amount and more in time consumption, collision risk prediction information cannot be provided for the unmanned aerial vehicle in real time, a wider flight route of a flight area is planned for the unmanned aerial vehicle generally, so that the unmanned aerial vehicle can fly safely whether fly alone or fly with objects. However, the defects of the arrangement include that the unmanned aerial vehicle needs to bypass a far route to reach a fire point in an emergency, the flying height is reduced under the condition of heavy load, the spatial distribution of the same height in an industrial factory is changed, the flying inertia of the unmanned aerial vehicle is large, and the unmanned aerial vehicle is not easy to avoid obstacles in time. Currently, the patent application with the publication number of CN113867391A discloses a digital twinning-based unmanned aerial vehicle low-altitude security early warning and monitoring method, related data related to unmanned aerial vehicle operation are collected and preprocessed, the related data comprise unmanned aerial vehicle operation track and operation performance basic data, unmanned aerial vehicle operation geographic environment data, unmanned aerial vehicle operation weather environment live and space position information data, unmanned aerial vehicle operation limiting area data and the like, the unmanned aerial vehicle low-altitude security risk is evaluated by combining a pre-trained neural network model, so that unmanned aerial vehicle operation integrated monitoring is achieved, early warning of operation risk is completed, and maneuver avoidance measures are timely taken. However, the data calculation amount in the operation of the patent is huge, the chip carried by the unmanned aerial vehicle cannot perform self-operation, and the processor cannot perform real-time rapid operation, so that the patent is difficult to apply to real-time risk prediction in emergency, and particularly cannot meet the requirement on calculation speed. The collision risk prediction method for the unmanned aerial vehicle, which is capable of predicting the collision risk and changing the planned route in real time based on the hardware of the unmanned aerial vehicle, is a requirement in the use of the unmanned aerial vehicle at present, and particularly is a use requirement of the unmanned aerial vehicle in an emergency. Furthermore, since the applicant has studied numerous documents and patents on the one hand, and since the applicant has made the present invention, the text is not to be limited to all details and matters of detail, but this is by no means the present invention does not feature these prior art features, but rather the present invention has features of all prior art, and the applicant has remained in the background art to which this invention pertains. Disclosure of Invention When unmanned aerial vehicle is used to carry the thing, especially when being used to in the emergency and carry the thing, u