A UAV collision detection platform based on data analysis

Abstract

The present invention belongs to the field of unmanned aerial vehicle collision detection, and relates to data analysis technology, which is used to solve the problem that the existing unmanned aerial vehicle collision detection technology cannot judge the collision situation in combination with the position information of the object, and cannot handle the potential collision in a complex environment. Specifically, it is a unmanned aerial vehicle collision detection platform based on data analysis, including a data acquisition module, a collision analysis module, a collision control module, a potential collision analysis module and a potential collision control module; the data acquisition module, the collision analysis module, the collision control module, the potential collision analysis module and the potential collision control module are sequentially connected for communication; the data acquisition module is used to obtain the object position information, the collision analysis module is used to classify the object collision type, the collision control module is used to perform obstacle avoidance control on the collision object, and the potential collision analysis module and the potential collision control module are used to avoid potential collisions; the present invention can effectively detect and avoid collisions, and improve the safety of unmanned aerial vehicle flight.

Description

Technical Field

[0001] The present invention belongs to the field of unmanned aerial vehicle collision detection and relates to data analysis technology, in particular to a unmanned aerial vehicle collision detection platform based on data analysis. Background Art

[0002] A drone is an aircraft managed and controlled by a control console. With the rapid development of drone technology and its deepening application in various fields, my country's drone industry has shown a trend of rapid growth, especially in the field of drone inspection. With its advantages of high efficiency, safety and flexibility, it plays an important role in the electricity, petroleum, transportation, water conservancy and other industries.

[0003] As drone applications become more widespread and flight environments become increasingly complex, the collision problem of drones during flight has become more prominent. Existing drone collision detection technologies have problems such as inaccurate detection and untimely response. They are often unable to judge the collision situation based on the relative position information of objects, and are unable to handle potential collision risks in complex environments, resulting in damage to drones and even safety accidents.

[0004] In view of the above technical problems, this application proposes a solution. Summary of the invention

[0005] The purpose of the present invention is to provide a UAV collision detection platform based on data analysis, which is used to solve the problem that the existing UAV collision detection technology cannot judge the collision situation in combination with the relative position information of the objects, and cannot handle the potential collision in complex environments;

[0006] The technical problem to be solved by the present invention is: how to provide a UAV collision detection platform based on data analysis that can judge the collision situation in combination with the relative position information of objects and handle potential collisions in complex environments.

[0007] The purpose of the present invention can be achieved through the following technical solutions:

[0008] A data analysis-based unmanned aerial vehicle collision detection platform comprises a data acquisition module, a collision analysis module, a collision control module, a potential collision analysis module and a potential collision control module; the data acquisition module, the collision analysis module, the collision control module, the potential collision analysis module and the potential collision control module are sequentially connected in communication;

[0009] The data acquisition module is used to collect the position information of objects in the environment around the drone: the spatial area with the center of the drone as the center and L1 as the radius is marked as the detection area, and the actual distance JL, pitch angle β and direction angle α of the objects in the environment relative to the drone are obtained through sensors; objects whose actual distance JL is less than the radius L1 of the detection area are marked as observation objects, and the visual image of the observation object is obtained through the visual sensor, and the observation object is identified and continuously observed based on the visual image;

[0010] The collision analysis module is used to analyze the collision situation according to the position information of the object in the detection area: the coordinates (X, Y, Z) of the observed object in the detection area in the three-dimensional coordinate system are obtained at a fixed frequency, and the coordinate changes ∆X, ∆Y, ∆Z are calculated, and the observed object is divided into a non-collision object, a collision object and a potential collision object according to the actual distance JL and the coordinate changes ∆X, ∆Y, ∆Z;

[0011] The collision control module is used to perform collision control on the collision objects: generate an obstacle avoidance priority sequence, and send the obstacle avoidance priority sequence to the control terminal of the UAV, and the operator performs obstacle avoidance operations on the collision objects in sequence according to the order of the obstacle avoidance priority sequence;

[0012] The potential collision analysis module is used to analyze the potential collision situation according to the information of the potential collision objects in the detection area: obtain the potential collision coefficient PX, determine the potential collision risk level in the detection area according to the potential collision coefficient PX, and generate a flight observation or flight optimization signal;

[0013] The potential collision control module is used to perform collision control on potential collision objects: receiving the signal sent by the potential collision analysis module, and the UAV adopts a flight observation mode or a flight optimization mode according to different signals.

[0014] Furthermore, the process of obtaining the actual distance JL includes: transmitting a pulse signal to an object in the environment through a pulse radar, recording the time interval between transmitting the pulse signal and receiving the reflected pulse signal as the round-trip time t, and recording the propagation speed of the electromagnetic wave as the speed of light c, then the actual distance JL= (c*t) / 2; the pitch angle β and the azimuth angle α are obtained by collecting data through the visual sensor carried by the drone and performing trigonometric calculations.

[0015] Furthermore, the process of acquiring the coordinates (X, Y, Z) and the coordinate changes ∆X, ∆Y, ∆Z includes: taking the center of the drone as the coordinate origin O, the positive direction of the drone nose as the X axis, and the vertical ground upward as the Z axis, a three-dimensional space coordinate system O-XYZ is established, and the coordinates of the observed object in the detection area in the coordinate system O-XYZ are (X, Y, Z); obtaining the actual distance JL and the coordinates (X, Y, Z) of the observed object in the detection area at a fixed frequency, and performing a difference calculation between the coordinates (X, Y, Z) and the coordinates (X1, Y1, Z1) obtained last time, to obtain the coordinate changes ∆X, ∆Y, ∆Z on the X axis, Y axis and Z axis respectively.

[0016] Furthermore, the specific division process of the observed object includes: comparing the actual distance JL of the observed object with a preset distance threshold JLmax: if the actual distance JL is greater than or equal to the distance threshold JLmax and the coordinate changes ∆X, ∆Y, ∆Z are all greater than 0, then the observed object is marked as a non-collision object; if the actual distance JL is less than the distance threshold JLmax and the coordinate changes ∆X, ∆Y, ∆Z are all less than or equal to 0, then the observed object is marked as a collision object; if the actual distance JL is greater than or equal to the distance threshold JLmax and the coordinate changes ∆X, ∆Y, ∆Z are all less than or equal to 0, then the observed object is marked as a potential collision object.

[0017] Furthermore, the process of generating the obstacle avoidance priority sequence includes: if there is a collision object in the detection area, generating the obstacle avoidance priority sequence according to the order of the actual distance JL from the smallest to the largest.

[0018] Furthermore, the process of obtaining the potential collision coefficient PX includes: if there are potential collision objects in the detection area, marking the number of potential collision objects as a potential quantity value QS, summing and averaging the actual distances JL of all potential collision objects to obtain the potential distance value QL, and numerically calculating the potential quantity value QS and the potential distance value QL to obtain the potential collision coefficient PX.

[0019] Furthermore, the potential collision coefficient PX is compared with a preset potential collision threshold PXmax: if the potential collision coefficient PX is less than the potential collision threshold PXmax, the potential collision risk level in the detection area is judged to be low, a flight observation signal is generated and the signal is sent to the potential collision control module; if the potential collision coefficient PX is greater than or equal to the potential collision threshold PXmax, the potential collision risk level in the detection area is judged to be high, a flight optimization signal is generated and the signal is sent to the potential collision control module.

[0020] Furthermore, the specific process of the flight observation mode includes: generating an observation period of fixed duration, marking the average value of the potential collision coefficient PX of the UAV during the observation period as the average potential value, and performing a difference calculation with the average potential value of the previous observation period to obtain a potential change value QB, and judging the potential change value QB: if the potential change value QB is less than or equal to 0, it is judged that the potential collision risk is decreasing and no processing is required; if the potential change value QB is greater than 0, it is judged that the potential collision risk is increasing, and the flight observation mode of the UAV is changed to the flight optimization mode.

[0021] Furthermore, the specific process of the flight optimization mode includes: forming a potential collision set from potential collision objects in the detection area, removing the potential collision object with the smallest actual distance JL from the potential collision set, and recalculating the potential collision coefficient PX of all potential collision objects in the set; if the potential collision coefficient PX after removal still does not meet the requirements, then continue to remove the potential collision object with the smallest actual distance JL in the potential collision set, and so on, until the potential collision coefficient PX is less than the potential collision threshold PXmax, then it is judged that the removal is completed; all removed potential collision objects are marked as flight optimization objects, and the operator performs the flight path according to the flight optimization objects.

[0022] The present invention has the following beneficial effects:

[0023] 1. The data acquisition module collects the location information of objects in the surrounding environment of the drone at regular intervals. By combining pulse radar and visual sensors, the actual distance, pitch angle and direction angle of the object can be accurately obtained, thereby providing data support for effective and timely detection and collision avoidance;

[0024] 2. By combining the actual distance and the coordinate change, the observed objects in the complex environment are divided into collision objects, non-collision objects and potential collision objects, so that the operator can perform obstacle avoidance operations according to the collision objects, improving the efficiency of collision detection and obstacle avoidance operations;

[0025] 3. The potential analysis module calculates the potential collision coefficient, which can identify potential collision risks in advance and take corresponding measures according to the risk level;

[0026] 4. The flight mode is controlled through the potential collision control module. When the flight observation mode is adopted, the change of potential collision risk is judged according to the potential change value and the flight mode is adjusted. When the flight optimization mode is adopted, the flight optimization object is found according to the potential collision coefficient after eliminating the potential collision object, thereby helping the operator to optimize the flight path, greatly avoiding potential collisions and improving the safety of UAV flight. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0028] Figure 1 A system block diagram of the present invention as a whole;

[0029] Figure 2 Schematic diagram of a three-dimensional coordinate system in an embodiment of the present invention. DETAILED DESCRIPTION

[0030] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0031] like Figure 1 As shown, a UAV collision detection platform based on data analysis includes a data acquisition module, a collision analysis module, a collision control module, a potential collision analysis module and a potential collision control module; the data acquisition module, the collision analysis module, the collision control module, the potential collision analysis module and the potential collision control module are sequentially connected in communication;

[0032] The data acquisition module is used to collect the position information of objects in the environment around the drone: the spatial area with the center of the drone as the center and L1 as the radius is marked as the detection area, and the actual distance JL, pitch angle β and direction angle α of the objects in the environment relative to the drone are obtained through sensors; the process of obtaining the actual distance JL includes: transmitting a pulse signal to the object in the environment through a pulse radar, recording the time interval between the transmitted pulse signal and the received reflected pulse signal as the round-trip time t, and the propagation speed of the electromagnetic wave as the speed of light c, then the actual distance JL=(c*t) / 2; the pitch angle β and the direction angle α are obtained by collecting data from the visual sensor carried by the drone and performing trigonometric calculations; the object whose actual distance JL is less than the radius L1 of the detection area is marked as an observed object, the visual image of the observed object is obtained through the visual sensor, and the observed object is identified and continuously observed based on the visual image; the position information of the objects in the environment around the drone is collected regularly through the data acquisition module, and the actual distance, pitch angle and direction angle of the object can be accurately obtained by combining the pulse radar and the visual sensor, thereby providing data support for effective and timely detection and collision avoidance.

[0033] The collision analysis module is used to analyze the collision situation according to the position information of the objects in the detection area: the center of the drone is taken as the coordinate origin O, the positive direction of the drone head is the X axis, and the vertical ground upward is the Z axis. The three-dimensional space coordinate system O-XYZ is established. The coordinates of the observed object in the detection area in the coordinate system O-XYZ are (X, Y, Z), where X=JL*cosβ*cosα, Y=JL*cosβ*sinα, and Z=JL*sinβ;

[0034] For example, Figure 2 As shown, the coordinate origin O is the position of the drone, A is the position of a certain observed object, then OA is the actual distance JL, β is the pitch angle, and α is the direction angle;

[0035] The actual distance JL and coordinates (X, Y, Z) of the object in the detection area are obtained at a fixed frequency, and the difference between the coordinates (X, Y, Z) and the last acquired coordinates (X1, Y1, Z1) is calculated to obtain the change ∆X, ∆Y, ∆Z of the coordinates on the X-axis, Y-axis, and Z-axis respectively; the actual distance JL of the object is compared with the preset distance threshold JLmax:

[0036] If the actual distance JL is greater than or equal to the distance threshold JLmax and the coordinate changes ∆X, ∆Y, and ∆Z are all greater than 0, the observed object is marked as a non-collision object;

[0037] If the actual distance JL is less than the distance threshold JLmax and the coordinate changes ∆X, ∆Y, and ∆Z are all less than or equal to 0, the observed object is marked as a collision object;

[0038] If the actual distance JL is greater than or equal to the distance threshold JLmax and the coordinate changes ∆X, ∆Y, and ∆Z are all less than or equal to 0, the observed object is marked as a potential collision object; by combining the actual distance and the coordinate change, the observed objects in the complex environment are divided into collision objects, non-collision objects, and potential collision objects, so that the operator can perform obstacle avoidance operations according to the collision objects, thereby improving the efficiency of collision detection and obstacle avoidance operations.

[0039] The collision control module is used to perform collision control on the collision object: if there is a collision object in the detection area, an obstacle avoidance priority sequence is generated for the collision object in the order of the actual distance JL from small to large, and the obstacle avoidance priority sequence is sent to the control terminal of the UAV, and the operator performs obstacle avoidance operations on the collision object in the order of the obstacle avoidance priority sequence; for example, the obstacle avoidance operations include adjusting the flight altitude, changing the flight direction, and adjusting the flight speed;

[0040] The potential collision analysis module is used to analyze the potential collision situation according to the information of the potential collision objects in the detection area: if there are potential collision objects in the detection area, the number of potential collision objects is marked as the potential number value QS, and the actual distances JL of all potential collision objects are summed and averaged to obtain the potential distance value QL; the potential number value QS and the potential distance value QL are numerically calculated by the formula PX=k1*QS-k2*QL to obtain the potential collision coefficient PX, where k1 and k2 are both proportional coefficients; the potential collision coefficient PX is compared with the preset potential collision threshold value PXmax:

[0041] If the potential collision coefficient PX is less than the potential collision threshold PXmax, the potential collision risk level in the detection area is judged to be low, a flight observation signal is generated and sent to the potential collision control module;

[0042] If the potential collision coefficient PX is greater than or equal to the potential collision threshold PXmax, the potential collision risk level in the detection area is judged to be high, and a flight optimization signal is generated and sent to the potential collision control module; the potential collision coefficient is calculated by the potential analysis module, so that the potential collision risk can be identified in advance and corresponding measures can be taken according to the risk level.

[0043] The potential collision control module is used to perform collision control on potential collision objects: if the potential collision control module receives a flight observation signal, the UAV adopts a flight observation mode: an observation period of fixed duration is generated, the average value of the potential collision coefficient PX of the UAV in the observation period is marked as the average potential value, and the difference between the potential value and the average potential value of the previous observation period is calculated to obtain a potential change value QB, and the potential change value QB is judged: if the potential change value QB is less than or equal to 0, it is judged that the potential collision risk is decreasing and no processing is required; if the potential change value QB is greater than 0, it is judged that the potential collision risk is increasing, and the flight observation mode of the UAV is changed to a flight optimization mode;

[0044] If the potential collision control module receives the flight optimization signal, the UAV will adopt the flight optimization mode: the potential collision objects in the detection area constitute a potential collision set, the potential collision object with the smallest actual distance JL is removed from the potential collision set, and the potential collision coefficient PX of all potential collision objects in the set is recalculated. If the potential collision coefficient PX after removal still does not meet the requirements, the potential collision object with the smallest actual distance JL in the potential collision set will continue to be removed, and so on, until the potential collision coefficient PX is less than the potential collision threshold PXmax, then it is judged that the removal is completed; all removed potential collision objects are marked as flight optimization objects, and the operator optimizes the flight path according to the flight optimization objects; the flight mode is controlled by the potential collision control module, and when the flight observation mode is adopted, the change of potential collision risk is judged according to the potential change value and the flight mode is adjusted. When the flight optimization mode is adopted, the flight optimization object is found according to the potential collision coefficient after the potential collision object is removed, thereby helping the operator to optimize the flight path, greatly avoiding potential collisions and improving the safety of UAV flight.

[0045] A UAV collision detection platform based on data analysis, when working, obtains the actual distance, pitch angle and direction angle of the observed objects in the UAV's surrounding environment through sensors, establishes a three-dimensional space coordinate system, calculates the object coordinates, and divides the observed objects into collision objects, non-collision objects and potential collision objects according to the actual distance and the coordinate change before and after acquisition, controls collisions by generating an obstacle avoidance priority sequence, determines the potential collision risk level by calculating the potential collision coefficient, adopts a flight observation mode or a flight optimization mode according to the potential collision risk level, and controls potential collisions.

[0046] The above contents are merely examples and explanations of the structure of the present invention. The technicians in this technical field may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the structure of the invention or exceed the scope defined by the claims, they should all fall within the protection scope of the present invention.

[0047] The above formulas are obtained by collecting a large amount of data for software simulation and selecting a formula close to the real value. The coefficients in the formula are set by technicians in this field according to the actual situation; for example: formula PX=k1*QS-k2*QL; technicians in this field collect multiple groups of sample data and set corresponding potential collision coefficients for each group of sample data; substitute the set potential collision coefficients and the collected sample data into the formula, any two formulas constitute a set of binary linear equations, screen the calculated coefficients and take the average, and obtain the values ​​of k1 and k2 as 3.17 and 2.25 respectively;

[0048] The size of the coefficient is to quantify each parameter to obtain a specific value for subsequent comparison. The size of the coefficient depends on the amount of sample data and the preliminary setting of the corresponding potential collision coefficient for each set of sample data by technical personnel in this field; as long as it does not affect the proportional relationship between the parameter and the quantified value, such as the potential collision coefficient is proportional to the value of the potential quantity.

[0049] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0050] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A UAV collision detection platform based on data analysis, characterized in that: It includes a data acquisition module, a collision analysis module, a collision control module, a potential collision analysis module and a potential collision control module; the data acquisition module, the collision analysis module, the collision control module, the potential collision analysis module and the potential collision control module are sequentially connected in communication; The data acquisition module is used to collect the position information of objects in the environment around the drone: the spatial area with the center of the drone as the center and L1 as the radius is marked as the detection area, and the actual distance JL, pitch angle β and direction angle α of the objects in the environment relative to the drone are obtained through sensors; objects whose actual distance JL is less than the radius L1 of the detection area are marked as observation objects, and the visual image of the observation object is obtained through the visual sensor, and the observation object is identified and continuously observed based on the visual image; The collision analysis module is used to analyze the collision situation according to the position information of the object in the detection area: the coordinates (X, Y, Z) of the observed object in the detection area in the three-dimensional coordinate system are obtained at a fixed frequency, and the coordinate changes ∆X, ∆Y, ∆Z are calculated, and the observed object is divided into a non-collision object, a collision object and a potential collision object according to the actual distance JL and the coordinate changes ∆X, ∆Y, ∆Z; The collision control module is used to perform collision control on the collision objects: generate an obstacle avoidance priority sequence, and send the obstacle avoidance priority sequence to the control terminal of the UAV, and the operator performs obstacle avoidance operations on the collision objects in sequence according to the order of the obstacle avoidance priority sequence; The potential collision analysis module is used to analyze the potential collision situation according to the information of the potential collision objects in the detection area: obtain the potential collision coefficient PX, determine the potential collision risk level in the detection area according to the potential collision coefficient PX, and generate a flight observation or flight optimization signal; The potential collision control module is used to perform collision control on potential collision objects: receiving the signal sent by the potential collision analysis module, and the UAV adopts a flight observation mode or a flight optimization mode according to different signals.

2. The UAV collision detection platform based on data analysis according to claim 1 is characterized in that: The process of obtaining the actual distance JL includes: transmitting a pulse signal to objects in the environment through a pulse radar, recording the time interval between transmitting the pulse signal and receiving the reflected pulse signal as the round-trip time t, and recording the propagation speed of the electromagnetic wave as the speed of light c, then the actual distance JL = (c*t) / 2; the pitch angle β and the azimuth angle α are obtained by collecting data through the visual sensor carried by the drone and performing trigonometric calculations.

3. The UAV collision detection platform based on data analysis according to claim 2 is characterized in that: The process of acquiring the coordinates (X, Y, Z) and the coordinate changes ∆X, ∆Y, ∆Z includes: taking the center of the drone as the coordinate origin O, the positive direction of the drone nose as the X axis, and the vertical ground upward as the Z axis, a three-dimensional space coordinate system O-XYZ is established, and the coordinates of the observed object in the detection area in the coordinate system O-XYZ are (X, Y, Z); the actual distance JL and the coordinates (X, Y, Z) of the observed object in the detection area are obtained at a fixed frequency, and the coordinates (X, Y, Z) are calculated by difference between the coordinates (X1, Y1, Z1) obtained last time, to obtain the coordinate changes ∆X, ∆Y, ∆Z on the X axis, Y axis and Z axis respectively.

4. The UAV collision detection platform based on data analysis according to claim 3 is characterized in that: The specific division process of the observed object includes: comparing the actual distance JL of the observed object with the preset distance threshold JLmax: if the actual distance JL is greater than or equal to the distance threshold JLmax and the coordinate changes ∆X, ∆Y, ∆Z are all greater than 0, then the observed object is marked as a non-collision object; if the actual distance JL is less than the distance threshold JLmax and the coordinate changes ∆X, ∆Y, ∆Z are all less than or equal to 0, then the observed object is marked as a collision object; if the actual distance JL is greater than or equal to the distance threshold JLmax and the coordinate changes ∆X, ∆Y, ∆Z are all less than or equal to 0, then the observed object is marked as a potential collision object.

5. The UAV collision detection platform based on data analysis according to claim 4 is characterized in that: The process of generating the obstacle avoidance priority sequence includes: if there is a collision object in the detection area, the collision object is generated into an obstacle avoidance priority sequence in the order of the actual distance JL from small to large.

6. The UAV collision detection platform based on data analysis according to claim 5 is characterized in that: The process of obtaining the potential collision coefficient PX includes: if there are potential collision objects in the detection area, the number of potential collision objects is marked as the potential number value QS, the actual distances JL of all potential collision objects are summed and averaged to obtain the potential distance value QL, and the potential number value QS and the potential distance value QL are numerically calculated to obtain the potential collision coefficient PX.

7. The UAV collision detection platform based on data analysis according to claim 6 is characterized in that: The potential collision coefficient PX is compared with the preset potential collision threshold PXmax: if the potential collision coefficient PX is less than the potential collision threshold PXmax, the potential collision risk level in the detection area is judged to be low, a flight observation signal is generated and the signal is sent to the potential collision control module; if the potential collision coefficient PX is greater than or equal to the potential collision threshold PXmax, the potential collision risk level in the detection area is judged to be high, a flight optimization signal is generated and the signal is sent to the potential collision control module.

8. The UAV collision detection platform based on data analysis according to claim 7 is characterized in that: The specific process of the flight observation mode includes: generating an observation period of fixed duration, marking the average value of the potential collision coefficient PX of the drone during the observation period as the average potential value, and performing a difference calculation with the average potential value of the previous observation period to obtain a potential change value QB, and judging the potential change value QB: if the potential change value QB is less than or equal to 0, it is judged that the potential collision risk is decreasing and no processing is required; if the potential change value QB is greater than 0, it is judged that the potential collision risk is increasing, and the flight observation mode of the drone is changed to the flight optimization mode.

9. The UAV collision detection platform based on data analysis according to claim 8, characterized in that: The specific process of the flight optimization mode includes: forming a potential collision set from potential collision objects in the detection area, removing the potential collision object with the smallest actual distance JL from the potential collision set, and recalculating the potential collision coefficient PX of all potential collision objects in the set; if the potential collision coefficient PX after removal still does not meet the requirements, continue to remove the potential collision object with the smallest actual distance JL in the potential collision set, and so on, until the potential collision coefficient PX is less than the potential collision threshold PXmax, then it is judged that the removal is completed; all removed potential collision objects are marked as flight optimization objects, and the operator optimizes the flight path according to the flight optimization objects.

Images