Unmanned aerial vehicle flight route intelligent planning system based on artificial intelligence

Abstract

The invention discloses an unmanned aerial vehicle flight route intelligent planning system based on artificial intelligence, relates to the technical field of unmanned aerial vehicle route planning, and solves the technical problem that in the prior art, hovering point location setting cannot be performed during route planning, so that route planning cannot be performed according to proper point locations. Specifically, a path-finding hovering point location setting unit carries out hovering point location setting on a planned route in a path-finding planning area, determines a flight area, carries out in-area height setting according to the specification of an equipped unmanned aerial vehicle, obtains a plurality of routes in a height range matched with the specification of the unmanned aerial vehicle, marks the obtained routes as preset planned routes, and sends the preset planned routes to the path-finding hovering point location setting unit. Performing path-finding test flight on the preset planning route, and setting a preset hovering point position for the preset planning route; hovering point location analysis information is collected, a preset hovering point location setting coefficient is obtained through calculation, and the hovering point location is divided into a fixed hovering point location and a floating hovering point location through coefficient comparison.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned aerial vehicle (UAV) route planning, and in particular to an intelligent UAV flight route planning system based on artificial intelligence. Background Art

[0002] Drones are aircraft managed by a control station (including remote control or autonomous flight); they can be divided into three categories: military, civilian and consumer. Among them, military drones are mainly used for reconnaissance, surveillance, and target acquisition; civilian drones are widely used in agriculture, surveying and mapping, energy, security, rescue, logistics and other fields; consumer drones are mainly aimed at ordinary consumers and are used for aerial photography, entertainment, etc.

[0003] However, in the prior art, it is not possible to set hovering points when planning routes, so that it is impossible to plan routes according to suitable points, which reduces the accuracy of route planning, and it is not possible to perform static and dynamic risk identification on the planned routes, so that it is impossible to accurately screen and ensure the rationality of the planned routes; in addition, it is not possible to temporarily occupy alternative routes according to the screening type, which reduces the comprehensiveness of the supply of planned routes.

[0004] In view of the above technical defects, a solution is now proposed. Summary of the invention

[0005] The purpose of the present invention is to solve the above-mentioned problems and to propose an intelligent flight route planning system for unmanned aerial vehicles based on artificial intelligence.

[0006] The purpose of the present invention can be achieved through the following technical solutions:

[0007] An artificial intelligence-based UAV flight route intelligent planning system includes a route planning platform, the route planning platform is communicatively connected with a pathfinding hovering point setting unit, a pathfinding static risk identification unit, and a pathfinding dynamic risk statistics unit;

[0008] The pathfinder hovering point setting unit sets the hovering points for the planned route in the pathfinder planning area, determines the flight area, sets the altitude in the area according to the specifications of the equipped drone, obtains multiple routes within the altitude range adapted to the drone specifications, marks the obtained routes as preset planned routes, conducts pathfinder test flights on the preset planned routes, and sets preset hovering points for the preset planned routes; collects hovering point analysis information, obtains preset hovering point setting coefficients by calculation, and divides the set hovering points into fixed hovering points and floating hovering points by coefficient comparison;

[0009] The pathfinding static risk identification unit identifies static risks on the preset planned route, collects static positioning data of fixed points and static hovering data of floating points, and divides the preset planned route into static risk routes and static safe routes based on data analysis;

[0010] The pathfinding dynamic risk statistics unit performs dynamic risk statistics on the pathfinding process of the preset planned route, collects dynamic hovering occupancy information and dynamic hovering deviation information, and divides the preset planned route into dynamic risk routes and dynamic safety routes based on information analysis.

[0011] As a preferred embodiment of the present invention, the hovering point analysis information includes the maximum reciprocating span value of the crosswind force in the space formed by obstacles around the location of the preset hovering point in the preset planned route, the peak value of the shortened span of the risk distance from obstacles when the vertical flight altitude is adjusted at the location of the preset hovering point in the preset planned route, and the floating value of the numerical deviation between the passage frequency of flying objects at the location of the preset hovering point in the preset planned route and the preset frequency.

[0012] As a preferred embodiment of the present invention, if the preset hovering point setting coefficient in the preset planned route exceeds the hovering point setting coefficient threshold, the corresponding preset hovering point will be marked as a fixed hovering point; if the preset hovering point setting coefficient in the preset planned route does not exceed the hovering point setting coefficient threshold, the corresponding preset hovering point will be marked as a floating hovering point.

[0013] As a preferred embodiment of the present invention, the static positioning data of fixed points and the static hovering data of floating points are respectively the frequency of increase in the deviation value between the real-time hovering position and the preset hovering position when the drone hovers at a fixed hovering point in the preset planned route, and the sum of the corresponding spans of the increase in the hovering times of a single hovering point and the increase in the continuous hovering times of adjacent hovering points when the drone hovers at a floating hovering point in the preset planned route.

[0014] As a preferred embodiment of the present invention, if the static positioning data of the fixed point exceeds the frequency threshold of the deviation value increase, or the static hovering data of the floating point exceeds the sum threshold of the number of spans, the current preset planned route is marked as a static risk route; if the static positioning data of the fixed point does not exceed the frequency threshold of the deviation value increase, and the static hovering data of the floating point does not exceed the sum threshold of the number of spans, the current preset planned route is marked as a static safe route.

[0015] As a preferred embodiment of the present invention, the dynamic hovering occupancy information and the dynamic hovering deviation information are respectively the peak value of the area ratio of the occupied area of ​​the hovering point position corresponding to the hovering moment in the preset planned route to the area occupied by the drone hovering, and the corresponding numerical ratio of the on-time frequency of the drone hovering moment when the hovering point position is occupied and the distance deviation hovering frequency of the actual hovering moment.

[0016] As a preferred embodiment of the present invention, if the dynamic hovering occupancy information exceeds the area ratio peak threshold, or the dynamic hovering deviation information does not exceed the frequency value ratio threshold, the corresponding preset planned route will be marked as a dynamic risk route; if the dynamic hovering occupancy information does not exceed the area ratio peak threshold, and the dynamic hovering deviation information exceeds the frequency value ratio threshold, the corresponding preset planned route will be marked as a dynamic safe route.

[0017] As a preferred embodiment of the present invention, after the route planning platform receives various types of static risk routes and static safety routes, dynamic risk routes and dynamic safety routes, it screens the preset planned routes and retains the safe routes to obtain the planned routes; and sends the planned routes to each drone control terminal.

[0018] Compared with the prior art, the present invention has the following beneficial effects:

[0019] 1. In the present invention, hovering points are set for the planned route in the pathfinding planning area, and the pathfinding route is acquired by planning the flight area. The acquired route is subjected to pathfinding flight to ensure the feasibility of the route, and hovering points are set in the acquired route during the flight, so that it is possible to effectively infer whether the external influence of the current flight route is normal based on the hovering points, thereby improving the accuracy of flight route planning and ensuring the availability of the route;

[0020] Static risk identification is performed on the preset planned route. Through the pathfinding process of the preset planned route, it is inferred whether the static risk identification of the preset planned route is qualified, so as to screen the planned route to ensure the flight safety performance of the planned route and the flight efficiency of the UAV.

[0021] 2. In the present invention, dynamic risk statistics are performed on the pathfinding process of the preset planned route, and the dynamic risk identification analysis of the preset planned route during the pathfinding process is used to infer whether the current preset planned route is suitable as the UAV flight route, thereby improving the dynamic safety performance of the UAV flight, avoiding the increase of the dynamic impact of the route caused by external interference, and preventing the route from being safely flown. The flight risk of the UAV planned route is effectively reduced through route planning screening;

[0022] The alternative routes are set according to the real-time pathfinding process, and the occupancy analysis is performed based on the type classification of the preset planned routes during the pathfinding process. This facilitates the effective flight of alternative routes when abnormalities occur on the planned routes, ensures the efficiency of UAV flight, and improves the comprehensiveness of flight supply of the planned routes. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to facilitate understanding by those skilled in the art, the present invention is further described below with reference to the accompanying drawings.

[0024] Figure 1 This is a principle block diagram of Embodiment 1 of the present invention;

[0025] Figure 2 This is a principle block diagram of the second embodiment of the present invention. DETAILED DESCRIPTION

[0026] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not 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.

[0027] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0028] Embodiment 1

[0029] See also Figure 1 As shown, an AI-based UAV flight route intelligent planning system includes a route planning platform, which is communicatively connected to a pathfinding hovering point setting unit, a pathfinding static risk identification unit, and a pathfinding dynamic risk statistics unit, wherein the pathfinding hovering point setting unit, the pathfinding static risk identification unit, and the pathfinding dynamic risk statistics unit cooperate with each other during operation to perform real-time pathfinding on the UAV flight route planning, and monitor each point of the route according to the UAV hovering technology, and construct a complete UAV planned flight route according to the data connection of each point;

[0030] The route planning platform generates a pathfinding hovering point setting signal and sends the pathfinding hovering point setting signal to the pathfinding hovering point setting unit. After receiving the pathfinding hovering point setting signal, the pathfinding hovering point setting unit sets the hovering points for the planned route in the pathfinding planning area, acquires the pathfinding route by planning the flight area, performs pathfinding flight on the acquired route to ensure the feasibility of the route, and sets the hovering points in the acquired route during the flight, so as to be able to effectively infer whether the external influence on the current flight route is normal based on the point hovering, thereby improving the accuracy of flight route planning and ensuring the availability of the route;

[0031] Determine the flight area, set the altitude within the area according to the specifications of the equipped drone, obtain multiple routes within the altitude range adapted to the drone specifications, mark the obtained routes as preset planned routes, conduct pathfinding test flights on the preset planned routes, and set preset hovering points for the preset planned routes, where the setting standard for the preset hovering points is a space area with more than one drone flying;

[0032] After determining the preset hovering point, the preset hovering point is screened to obtain the maximum reciprocating span value of the crosswind force in the space formed by the obstacles around the location of the preset hovering point in the preset planned route, and the maximum reciprocating span value of the crosswind force in the space formed by the obstacles around the location of the preset hovering point in the preset planned route is marked as HFK;

[0033] Obtaining a peak value of the shortened span of the obstacle risk distance when the vertical flight height is adjusted at the location of the preset hovering point in the preset planned route, and marking the peak value of the shortened span of the obstacle risk distance when the vertical flight height is adjusted at the location of the preset hovering point in the preset planned route as SDF;

[0034] Obtain a floating value of a numerical deviation between a flying object's passing frequency at a preset hovering point in a preset planned route and a preset frequency, and mark the floating value of a numerical deviation between a flying object's passing frequency at a preset hovering point in a preset planned route and a preset frequency as SZF;

[0035] The above collected information is uniformly marked as hovering point analysis information, and substituted into the formula to obtain the preset hovering point setting coefficient in the preset planned route, where the formula is: Wherein, wt1, wt2 and wt3 are preset proportional coefficients respectively, and wt1, wt2 and wt3 are all positive integers greater than 1, and β is an error correction factor, and its value is 1.1;

[0036] Compare the preset hovering point setting coefficient in the preset planned route with the hovering point setting coefficient threshold:

[0037] If the preset hovering point setting coefficient in the preset planned route exceeds the hovering point setting coefficient threshold, it is inferred that the risk probability of the corresponding preset hovering point is high, and the corresponding preset hovering point is marked as a fixed hovering point;

[0038] If the preset hovering point setting coefficient in the preset planned route does not exceed the hovering point setting coefficient threshold, it is inferred that the risk probability of the corresponding preset hovering point is small, and the corresponding preset hovering point is marked as a floating hovering point;

[0039] The fixed hovering points and the floating hovering points are sent to the route planning platform together. After the route planning platform receives the fixed hovering points and the floating hovering points, the UAV in the pathfinding flight hovers over the fixed hovering points in sequence and selectively hovers over the floating hovering points. That is, if the environment at the location of the floating hovering point is abnormal during flight, the floating hovering point will be hovered. The environmental abnormality is such as reduced visibility and reduced infrared ranging accuracy.

[0040] At the same time, a pathfinding static risk identification signal is generated and sent to a pathfinding static risk identification unit. After receiving the pathfinding static risk identification signal, the pathfinding static risk identification unit performs static risk identification on the preset planned route, and infers whether the static risk identification of the preset planned route is qualified through the pathfinding process of the preset planned route, thereby screening the planned route to ensure the flight safety performance of the planned route and the flight efficiency of the UAV;

[0041] The frequency of increasing the deviation value between the real-time hovering position and the preset hovering position when the drone hovers at a fixed hovering point in the preset planned route is obtained, and the frequency of increasing the deviation value between the real-time hovering position and the preset hovering position when the drone hovers at a fixed hovering point in the preset planned route is marked as fixed point static positioning data;

[0042] The sum of the increase span of the number of hovering times at a single hovering point and the corresponding span of the increase span of the number of consecutive hovering times at adjacent hovering points when the drone hovers at a floating hovering point in the preset planned route is obtained, and the sum of the increase span of the number of hovering times at a single hovering point and the corresponding span of the increase span of the number of consecutive hovering times at adjacent hovering points when the drone hovers at a floating hovering point in the preset planned route is marked as floating point static hovering data;

[0043] And the static positioning data of the fixed point and the static hovering data of the floating point are compared with the frequency threshold of the deviation value increase and the sum threshold of the number of spans respectively:

[0044] If the frequency of increase in the deviation value between the real-time hovering position and the preset hovering position when the drone hovers at a fixed hovering point in the preset planned route exceeds the threshold of the frequency of increase in the deviation value, or the sum of the spans corresponding to the increase in the number of hovering times at a single hovering point and the span of the increase in the number of consecutive hovering times at adjacent hovering points when the drone hovers at a floating hovering point in the preset planned route exceeds the threshold of the sum of the spans, it is inferred that the static risk of drone pathfinding in the preset planned route is abnormal, and the current preset planned route is marked as a static risk route;

[0045] If the frequency of increase in the deviation value between the real-time hovering position and the preset hovering position when the drone hovers at a fixed hovering point in the preset planned route does not exceed the threshold value for the frequency increase in the deviation value, and the sum of the corresponding spans of the increase in the number of hovering times at a single hovering point and the increase in the number of consecutive hovering times at adjacent hovering points when the drone hovers at a floating hovering point in the preset planned route does not exceed the threshold value for the sum of the spans, then it is inferred that the static risk of drone pathfinding in the preset planned route is normal, and the current preset planned route is marked as a static safe route; in this application, pathfinding risk identification is performed on the premise that the drone is in a qualified state to perform data collection and analysis, excluding the influence of the drone's own state;

[0046] The static risk route and the static safe route are sent to the route planning platform, and a pathfinding dynamic risk statistical signal is generated and sent to the pathfinding dynamic risk statistical unit. After receiving the pathfinding dynamic risk statistical signal, the pathfinding dynamic risk statistical unit performs dynamic risk statistics on the pathfinding process of the preset planned route, and infers whether the current preset planned route is suitable as the UAV flight route based on the dynamic risk identification analysis of the preset planned route during the pathfinding process, thereby improving the dynamic safety performance of the UAV flight, avoiding the increase of the dynamic impact of the route caused by external interference, and making it impossible to safely fly the route. The flight risk of the UAV planned route is effectively reduced through route planning screening;

[0047] The peak value of the area ratio of the area occupied by the hovering point position corresponding to the hovering time in the preset planned route to the area occupied by the drone hovering is obtained, and at the same time, the corresponding numerical ratio of the on-time frequency of the drone hovering time and the distance deviation hovering frequency at the actual hovering time when the hovering point position is occupied is obtained, and the peak value of the area ratio of the area occupied by the hovering point position corresponding to the hovering time in the preset planned route to the area occupied by the drone hovering, and the corresponding numerical ratio of the on-time frequency of the drone hovering time and the distance deviation hovering frequency at the actual hovering time when the hovering point position is occupied are marked as dynamic hovering occupancy information and dynamic hovering deviation information, and are compared with the area ratio peak threshold and frequency value ratio threshold respectively:

[0048] If the peak value of the area ratio of the occupied area of ​​the hovering point position corresponding to the hovering time in the preset planned route to the area occupied by the drone hovering exceeds the area ratio peak threshold, or the corresponding numerical ratio of the distance deviation of the drone hovering time and the actual hovering time when the hovering point position is occupied does not exceed the frequency value ratio threshold, it is inferred that the hovering dynamic pathfinding risk of the preset planned route is high, and the corresponding preset planned route is marked as a dynamic risk route;

[0049] If the peak value of the area ratio of the area occupied by the hovering point position corresponding to the hovering time in the preset planned route to the area occupied by the drone hovering does not exceed the area ratio peak threshold, and the hovering frequency corresponding to the distance deviation between the on-time frequency of the drone hovering time and the actual hovering time when the hovering point position is occupied exceeds the frequency value ratio threshold, it is inferred that the hovering dynamic path exploration risk of the preset planned route is low, and the corresponding preset planned route is marked as a dynamic safe route;

[0050] And send the dynamic risk route and the dynamic safety route together to the route planning platform;

[0051] After receiving the types of static risk routes and static safety routes, dynamic risk routes and dynamic safety routes, the route planning platform will screen the preset planned routes and retain the safe routes to obtain the planned routes; and send the planned routes to each drone control terminal;

[0052] Embodiment 2

[0053] See also Figure 2 As shown, the route planning platform is communicatively connected with an alternative route analysis and setting unit; after completing the pathfinding and obtaining the planned route, the route planning platform generates an alternative route analysis and setting signal and sends the alternative route analysis and setting signal to the alternative route analysis and setting unit. After receiving the alternative route analysis and setting signal, the alternative route analysis and setting unit sets the alternative route according to the real-time pathfinding process, and performs occupancy analysis in combination with the type classification of the preset planned route in the pathfinding process, so as to facilitate the effective flight of the alternative route when an abnormality occurs in the planned route, thereby ensuring the efficiency of the UAV flight and improving the comprehensiveness of the flight supply of the planned route;

[0054] The distance ratio of the precise flight control section in the static risk route of the route adjacent to the height threshold of the current planned route is obtained, and at the same time, the cumulative flight time of the route trajectory without interference flight distance exceeding the set threshold in the dynamic risk route of the route adjacent to the height threshold of the current planned route is obtained, and the distance ratio of the precise flight control section in the static risk route of the route adjacent to the height threshold of the current planned route and the cumulative flight time of the route trajectory without interference flight distance exceeding the set threshold in the dynamic risk route of the route adjacent to the height threshold of the current planned route are marked as static occupancy information and dynamic occupancy information, respectively, and compared with the section distance ratio threshold and the cumulative flight time threshold respectively: Among them, the collection period of static occupancy information and dynamic occupancy information are both the occasional occupancy process of the current route during the operation stage of the drone. If the real-time planned route flight is abnormal and the altitude needs to be adjusted, the route is adjusted; the adjacent altitude threshold is represented by the adjacent route, and the altitude is the flight altitude manually set in combination with the characteristics of the drone;

[0055] If the distance ratio of the precise flight control section in the static risk route of the route adjacent to the altitude threshold of the current planned route exceeds the section distance ratio threshold, or the cumulative flight time of the route trajectory interference-free flight distance exceeding the set threshold in the dynamic risk route of the route adjacent to the altitude threshold of the current planned route exceeds the cumulative flight time threshold, it is inferred that the route occupancy risk of the route adjacent to the altitude threshold of the current planned route is low, and the corresponding route is marked as a temporary alternative route;

[0056] If the distance ratio of the precise flight control section in the static risk route of the route adjacent to the altitude threshold of the current planned route does not exceed the section distance ratio threshold, and the cumulative flight time of the route trajectory without interference in the dynamic risk route of the route adjacent to the altitude threshold of the current planned route exceeds the set threshold does not exceed the cumulative flight time threshold, it is inferred that the route occupancy risk of the route adjacent to the altitude threshold of the current planned route is high, and the corresponding route is marked as a non-alternative route;

[0057] Sending the temporary alternative route and the non-alternative route together to the route planning platform, which will prepare for the temporary route change after receiving them;

[0058] The above formulas are obtained by collecting a large amount of data and performing software simulation, and a formula close to the actual value is selected. The coefficients in the formula are set by technicians in this field according to actual conditions;

[0059] When the present invention is in use, the pathfinder hovering point setting unit sets the hovering points of the planned route in the pathfinder planning area; collects hovering point analysis information, obtains the preset hovering point setting coefficients by calculation, and divides the set hovering points into fixed hovering points and floating hovering points by coefficient comparison; the pathfinder static risk identification unit performs static risk identification on the preset planned route, collects static positioning data of fixed points and static hovering data of floating points, and divides the preset planned route into static risk routes and static safe routes according to data analysis; the pathfinder dynamic risk statistics unit performs dynamic risk statistics on the pathfinder process of the preset planned route, collects dynamic hovering occupancy information and dynamic hovering deviation information, and divides the preset planned route into dynamic risk routes and dynamic safe routes according to information analysis.

[0060] 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. An intelligent flight route planning system for unmanned aerial vehicles based on artificial intelligence, characterized in that: It includes a route planning platform, which is communicatively connected with a pathfinder hovering point setting unit, a pathfinder static risk identification unit, and a pathfinder dynamic risk statistics unit; The pathfinder hovering point setting unit sets the hovering points for the planned route in the pathfinder planning area, determines the flight area, sets the altitude in the area according to the specifications of the equipped drone, obtains multiple routes within the altitude range adapted to the drone specifications, marks the obtained routes as preset planned routes, conducts pathfinder test flights on the preset planned routes, and sets preset hovering points for the preset planned routes; collects hovering point analysis information, obtains preset hovering point setting coefficients by calculation, and divides the set hovering points into fixed hovering points and floating hovering points by coefficient comparison; The pathfinding static risk identification unit identifies static risks on the preset planned route, collects static positioning data of fixed points and static hovering data of floating points, and divides the preset planned route into static risk routes and static safe routes based on data analysis; The pathfinding dynamic risk statistics unit performs dynamic risk statistics on the pathfinding process of the preset planned route, collects dynamic hovering occupancy information and dynamic hovering deviation information, and divides the preset planned route into dynamic risk routes and dynamic safety routes based on information analysis.

2. The UAV flight route intelligent planning system based on artificial intelligence according to claim 1 is characterized in that: The hovering point analysis information includes the maximum reciprocating span value of the crosswind force in the space formed by obstacles around the preset hovering point in the preset planned route, the peak value of the shortened span of the risk distance from obstacles when the vertical flight altitude is adjusted at the preset hovering point in the preset planned route, and the floating value of the numerical deviation between the passage frequency of flying objects at the preset hovering point in the preset planned route and the preset frequency.

3. The UAV flight route intelligent planning system based on artificial intelligence according to claim 2 is characterized in that: If the preset hovering point setting coefficient in the preset planned route exceeds the hovering point setting coefficient threshold, the corresponding preset hovering point will be marked as a fixed hovering point; if the preset hovering point setting coefficient in the preset planned route does not exceed the hovering point setting coefficient threshold, the corresponding preset hovering point will be marked as a floating hovering point.

4. The UAV flight route intelligent planning system based on artificial intelligence according to claim 1 is characterized in that: The static positioning data of fixed points and the static hovering data of floating points are respectively the frequency of increase in the deviation value between the real-time hovering position and the preset hovering position when the UAV hovers at a fixed hovering point in the preset planned route, and the sum of the corresponding spans of the increase in the number of hovering times at a single hovering point and the increase in the number of consecutive hovering times at adjacent hovering points when the UAV hovers at a floating hovering point in the preset planned route.

5. The UAV flight route intelligent planning system based on artificial intelligence according to claim 4 is characterized in that: If the static positioning data of the fixed point exceeds the frequency threshold of the deviation value increase, or the static hovering data of the floating point exceeds the sum threshold of the number of spans, the current preset planned route is marked as a static risk route; If the static positioning data of the fixed point does not exceed the frequency threshold of the deviation value increase, and the static hovering data of the floating point does not exceed the sum of the number of spans, the current preset planned route is marked as a static safe route.

6. The UAV flight route intelligent planning system based on artificial intelligence according to claim 1 is characterized in that: The dynamic hovering occupancy information and dynamic hovering deviation information are respectively the peak value of the ratio of the occupied area of ​​the hovering point position corresponding to the hovering time in the preset planned route to the occupied area of ​​the drone hovering, and the corresponding numerical ratio of the on-time frequency of the drone hovering time when the hovering point position is occupied and the distance deviation hovering frequency of the actual hovering time.

7. The UAV flight route intelligent planning system based on artificial intelligence according to claim 6 is characterized in that: If the dynamic hovering occupancy information exceeds the area ratio peak threshold, or the dynamic hovering deviation information does not exceed the frequency value ratio threshold, the corresponding preset planned route is marked as a dynamic risk route; If the dynamic hovering occupancy information does not exceed the area ratio peak threshold, and the dynamic hovering deviation information exceeds the frequency value ratio threshold, the corresponding preset planned route is marked as a dynamic safe route.

8. The UAV flight route intelligent planning system based on artificial intelligence according to claim 7 is characterized in that: After receiving the types of static risk routes and static safety routes, dynamic risk routes and dynamic safety routes, the route planning platform will screen the preset planned routes and retain the safe routes to obtain the planned routes; And send the planned routes to each drone control terminal.

Images