Low-altitude inspection UAV flight obstacle avoidance method and system

Abstract

The present invention relates to the technical field of unmanned aerial vehicle obstacle avoidance, and discloses a method and system for low-altitude inspection unmanned aerial vehicle flight obstacle avoidance, the method comprising: flying an inspection unmanned aerial vehicle in a flight area, using the inspection unmanned aerial vehicle to detect whether there is an obstacle to be avoided in the flight area; detecting the flight direction and flight speed of the obstacle to be avoided in the inspection unmanned aerial vehicle, and identifying whether the obstacle to be avoided is a non-free flight obstacle; querying the unmanned aerial vehicle-non-free obstacle distance between the inspection unmanned aerial vehicle and the non-free flight obstacle, calculating the unmanned aerial vehicle range of the inspection unmanned aerial vehicle and the obstacle range of the non-free flight obstacle; setting a safe distance between the inspection unmanned aerial vehicle and the non-free flight obstacle, using the inspection unmanned aerial vehicle to perform a first flight obstacle avoidance on the non-free flight obstacle; using wind direction and wind speed to generate a flight path of a free flight obstacle, and using the inspection unmanned aerial vehicle to perform a second flight obstacle avoidance on the free flight obstacle. The present invention can design a new type of unmanned aerial vehicle obstacle avoidance method to achieve flexible and autonomous obstacle avoidance.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned aerial vehicle obstacle avoidance, and in particular to a flight obstacle avoidance method and system for a low-altitude inspection unmanned aerial vehicle. Background Art

[0002] Inspection drones are deployed in field environments, mainly to inspect work sites when they are unattended, which can save commuting costs. When conducting low-altitude inspections, inspection drones may encounter obstacles such as other drones, kites, balloons, large aircraft taking off or landing, birds, etc.

[0003] At present, there have been extensive studies on obstacle avoidance for drones at home and abroad, which generally rely on three-dimensional elevation maps, binocular cameras and other high-precision equipment to achieve this. For example, the patent publication number is CN108062109A, the publication date is May 22, 2018, and the invention is named: obstacle avoidance method for drones. The application discloses a method for obstacle avoidance for drones, including: S1: installing a laser and a satellite positioning receiver on the drone; S2: during the flight of the drone, the obstacle information around the drone is collected by the laser; S3: importing the three-dimensional map library into the information processing module of the drone, converting the collected obstacle information into coordinates, and searching for the three-dimensional map of the target area in the three-dimensional map library; S4: replanning the flight route according to the three-dimensional map of the target area to achieve autonomous obstacle avoidance for the drone. The purpose of this application is to overcome the shortcomings of the existing drone obstacle avoidance technology that is difficult to accurately and autonomously avoid obstacles, and to provide a drone obstacle avoidance method that can accurately and autonomously avoid obstacles.

[0004] However, obstacle avoidance of drones involves many factors, including speed adjustment and direction adjustment when drones avoid obstacles, route planning when drones avoid obstacles, etc. The above-mentioned application for obstacle avoidance method of drones obviously does not take into account the speed adjustment and direction adjustment of inspection drones. Secondly, the above-mentioned application for obstacle avoidance method of drones is based on three-dimensional maps to realize route planning when drones avoid obstacles. This method cannot detect obstacles in front in time when affected by natural factors such as foggy weather, and it is often too late to avoid obstacles when approaching obstacles and detecting them again. Finally, the method of route planning relying solely on three-dimensional maps is not flexible enough. Similar to the principle of ground navigation, when encountering sudden obstacles, such as ground collapse, the method of driving by relying on fixed routes in three-dimensional maps is not flexible enough. Moreover, the aerial routes are different from the ground routes. Most of the drivable routes in the air are more flexible. They do not walk along fixed lanes like on the ground. Compared with the ground routes, the flexibility and randomness of controlling the routes are greater, which requires the inspection drones to have sufficient obstacle avoidance flexibility when avoiding obstacles.

[0005] Therefore, how to design a new obstacle avoidance method for UAVs to achieve flexible and autonomous obstacle avoidance is a technical problem that urgently needs to be solved in the existing technology. Summary of the invention

[0006] In order to solve the above problems, the present invention provides a low-altitude inspection UAV flight obstacle avoidance method and system, and a new type of UAV obstacle avoidance method can be designed to achieve flexible and autonomous obstacle avoidance.

[0007] In a first aspect, the present invention provides a method for avoiding obstacles in a low-altitude inspection UAV flight, comprising:

[0008] Collecting obstacles to be avoided by the inspection drone, wherein the obstacles to be avoided include non-free flight obstacles and free flight obstacles, collecting route information of the non-free flight obstacles, using the route information to identify the flight area of ​​the inspection drone, and after flying the inspection drone within the flight area, using the inspection drone to detect whether the obstacles to be avoided exist within the flight area;

[0009] When the inspection drone is used to detect the existence of the obstacle to be avoided in the flight area, the wind direction and wind speed at the obstacle to be avoided are collected, the flight direction and flight speed of the obstacle to be avoided are detected in the inspection drone, and the wind direction, wind speed, flight direction and flight speed are used to identify whether the obstacle to be avoided is the non-free flight obstacle;

[0010] When the obstacle to be avoided is identified as the non-free flight obstacle, querying the drone-non-free obstacle distance between the inspection drone and the non-free flight obstacle, and calculating the drone range of the inspection drone and the obstacle range of the non-free flight obstacle respectively;

[0011] The safety distance between the inspection drone and the non-free flight obstacle is set by using the drone range and the obstacle range, and based on the drone-non-free obstacle distance and the safety distance, the inspection drone is used to perform a first flight obstacle avoidance on the non-free flight obstacle to obtain a first flight obstacle avoidance result;

[0012] When it is identified that the obstacle to be avoided is not the non-free flight obstacle, the flight path of the free flight obstacle is generated by using the wind direction and the wind speed, and according to the flight path, the inspection drone is used to perform a second flight obstacle avoidance on the free flight obstacle to obtain a second flight obstacle avoidance result;

[0013] The first flight obstacle avoidance result and the second flight obstacle avoidance result are used as the flight obstacle avoidance result of the inspection UAV.

[0014] In a possible implementation of the first aspect, flying the inspection drone within the flight area includes:

[0015] Query whether the navigation route of the inspection drone is within the flight area;

[0016] When the navigation route of the inspection drone is not within the flight area, extracting a first target point where the navigation route of the inspection drone is not within the flight area;

[0017] According to the navigation route and the first target point, the obstacle avoidance trigger point of the inspection drone is calculated using the following formula:

[0018] a≤t≤b

[0019] x a (t)≤x(t)≤x b (t)

[0020] y a (t)≤y(t)≤y b (t)

[0021] z a (t)≤z(t)≤z b (t)

[0022]

[0023] Among them, (x a (t),y a (t),z a where (t)) represents the obstacle avoidance trigger point, L represents the length of the route from the obstacle avoidance trigger point to the first target point in the navigation route, x(t) represents the curve parameter equation of the route from the obstacle avoidance trigger point to the first target point in the navigation route on the x-axis, y(t) represents the curve parameter equation of the route from the obstacle avoidance trigger point to the first target point in the navigation route on the y-axis, z(t) represents the curve parameter equation of the route from the obstacle avoidance trigger point to the first target point in the navigation route on the z-axis, x a (t) represents the value of the obstacle avoidance trigger point on the x-axis, y a (t) represents the value of the obstacle avoidance trigger point on the y-axis, z a (t) represents the value of the obstacle avoidance trigger point on the z-axis, x b (t) represents the value of the first target point on the x-axis, y b (t) represents the value of the first target point on the y-axis, z b (t) represents the value of the first target point on the z-axis, t represents the independent variable constrained by x(t), y(t), and z(t), and a represents the independent variable constrained by x. a (t), y a (t), z a (t) is the value constrained by x. b (t), y b (t), z b(t) The value of the constraint, t0 represents the time required for the inspection UAV to complete a 180-degree turn when encountering an obstacle, and v0 represents the average flight speed of the inspection UAV;

[0024] Using the obstacle avoidance trigger point to plan the navigation route to obtain a planned route;

[0025] Calculating the route similarity between the planned route and the navigation route;

[0026] Based on the route similarity, determining a final route of the inspection drone from the planned routes;

[0027] Flying the inspection drone on the final route.

[0028] In a possible implementation manner of the first aspect, the step of performing route planning on the navigation route by using the obstacle avoidance trigger point to obtain a planned route includes:

[0029] Obtaining the starting point and the ending point of the navigation route;

[0030] Starting from the obstacle avoidance trigger point, searching for coordinate points around the obstacle avoidance trigger point and other coordinate points around the coordinate point;

[0031] When the searched coordinate point and the other coordinate points contain the end point, the initial route between the obstacle avoidance trigger point and the end point is generated by using the coordinate point and the other coordinate points;

[0032] In order from the end point to the obstacle avoidance trigger point, querying whether there is a first route consistent with the navigation route from the initial route;

[0033] When a first route that is consistent with the navigation route is found on the initial route, a second route other than the first route on the initial route is obtained, and a third route between the starting point and the obstacle avoidance trigger point on the navigation route is obtained;

[0034] The third route, the second route and the first route are sequentially spliced ​​to obtain the planned route.

[0035] In a possible implementation manner of the first aspect, the using the inspection drone to detect whether the obstacle to be avoided exists in the flight area includes:

[0036] Using the inspection drone to detect whether there is an object within the flight area;

[0037] When the inspection drone is used to detect the existence of an object in the flight area, the object coordinates, object direction and object speed of the object are identified;

[0038] constructing an object motion trajectory curve of the object using the object coordinates, the object direction and the object speed;

[0039] Constructing a UAV motion trajectory curve of the inspection UAV;

[0040] Determine whether it is possible to calculate the intersection point between the object motion trajectory curve and the drone motion trajectory curve;

[0041] When the intersection point between the motion trajectory curve of the object and the motion trajectory curve of the drone can be calculated, determining that the obstacle to be avoided exists in the flight area;

[0042] When the intersection point between the object motion trajectory curve and the drone motion trajectory curve cannot be calculated, it is determined that the obstacle to be avoided does not exist in the flight area.

[0043] In a possible implementation manner of the first aspect, the identifying whether the obstacle to be avoided is the non-free flight obstacle by using the wind direction, the wind speed, the flight direction, and the flight speed includes:

[0044] Querying a wind direction turning period of the wind direction and a direction turning period of the flight direction;

[0045] The correlation function between the wind speed and the flight speed is constructed using the following formula:

[0046] Y=KX+B

[0047] Wherein, Y=KX+B represents the correlation function, Y represents the flight speed, X represents the wind speed, B represents the intercept on the y-axis, and K represents the slope;

[0048] When the slope in the correlation function is greater than a preset slope and the wind direction turning period is consistent with the direction turning period, it is determined that the obstacle to be avoided is not the non-free flight obstacle;

[0049] When the slope in the correlation function is not greater than the preset slope and the wind direction turning period is inconsistent with the direction turning period, it is determined that the obstacle to be avoided is the non-free flight obstacle.

[0050] In a possible implementation manner of the first aspect, respectively calculating the drone range of the inspection drone and the obstacle range of the non-free flight obstacle includes:

[0051] Query the center coordinate point of the inspection drone;

[0052] Identifying surface coordinate points on the surface of the inspection drone;

[0053] When the distance between the first coordinate point of the central coordinate point and the surface coordinate point is the largest;

[0054] A sphere with the central coordinate point as the sphere center and the distance from the first coordinate point as the sphere radius is used as the range of the drone;

[0055] Acquiring edge coordinate points on the surface of the non-free flight obstacle in the inspection drone;

[0056] Calculating the centroid coordinate point of the non-free flight obstacle using the edge coordinate point;

[0057] When the distance between the second coordinate point between the centroid coordinate point and the edge coordinate point is the largest;

[0058] A sphere with the centroid coordinate point as the sphere center and the distance from the second coordinate point as the sphere radius is used as the obstacle range.

[0059] In a possible implementation of the first aspect, the using the drone range and the obstacle range to set a safety distance between the inspection drone and the non-free flight obstacle includes:

[0060] Obtain the maximum time it takes for the inspection drone to complete a turn;

[0061] According to the maximum duration, the range of the drone and the range of the obstacle, the safe distance between the inspection drone and the non-free flight obstacle is calculated using the following formula:

[0062] L'=t0v0+r1+r2

[0063] Among them, L' represents the safety distance, t0 represents the time required for the inspection drone to complete a 180-degree turn when encountering an obstacle, the time required for the inspection drone to complete a 180-degree turn when encountering an obstacle is the maximum time, v0 represents the average flight speed of the inspection drone, r1 represents the sphere radius corresponding to the drone range, and r2 represents the sphere radius corresponding to the obstacle range.

[0064] In a possible implementation of the first aspect, the performing a first flight obstacle avoidance on the non-free flight obstacle by using the inspection drone based on the drone-non-free obstacle distance and the safety distance to obtain a first flight obstacle avoidance result includes:

[0065] Determining whether the drone-non-free obstacle distance is less than the safety distance;

[0066] When the UAV-non-free obstacle distance is not less than the safety distance, determining whether the UAV-non-free obstacle distance is greater than the safety distance;

[0067] When the distance between the drone and the non-free obstacle is not greater than the safety distance, using the inspection drone to perform a current first flight obstacle avoidance on the non-free flight obstacle to obtain a current first flight obstacle avoidance result;

[0068] When the distance between the drone and the non-free obstacle is greater than the safety distance, calculating the obstacle avoidance speed and obstacle avoidance direction of the inspection drone when performing the first flight obstacle avoidance on the non-free flight obstacle;

[0069] According to the obstacle avoidance speed and the obstacle avoidance direction, using the inspection drone to perform complex first flight obstacle avoidance on the non-free flight obstacle to obtain a complex first flight obstacle avoidance result;

[0070] When the distance between the drone and the non-free obstacle is less than the safety distance, a simple first flight obstacle avoidance result is obtained according to a preset PID controller calculation.

[0071] In a possible implementation of the first aspect, the calculating the obstacle avoidance speed and the obstacle avoidance direction of the inspection drone when performing a first flight obstacle avoidance on the non-free flight obstacle includes:

[0072] The objective function of the inspection UAV performing the first flight obstacle avoidance on the non-free flight obstacle is constructed using the following formula;

[0073]

[0074]

[0075]

[0076]

[0077] minJx(k),u(k)=minL1(x(k))+L2(u(k))+L2(Δu(k))+L3(x(k))

[0078] Among them, minJx(k),u(k) represents the objective function, x(k) represents the flight state of the inspection drone, x(k) includes speed and direction, u(k) represents the control input value of the inspection drone, Δu(k) represents the change in the control input value of the inspection drone, L1(x(k)) represents the error parameter between the current coordinates of the inspection drone and the corresponding coordinates on the planned route, x1(k) represents the coordinates of the inspection drone on the planned route at time k, and w1 represents the objective function to be used in L1(x(k)). The weight parameter to be optimized is L2(u(k)), which is the constraint parameter to ensure that the inspection UAV flies with a smaller control input value. w2 is the weight parameter to be optimized by the objective function in L2(u(k)), which is the constraint parameter to ensure that the change of the control input value of the inspection UAV is smooth. w3 is the weight parameter to be optimized by the objective function in L2(Δu(k)), which is the constraint parameter to ensure that the inspection UAV maintains a safe distance from non-free flight obstacles. z j represents the coordinates of the jth non-free flight obstacle, x2(k) represents the corresponding coordinates on the replanned route, w4 represents the weight parameter to be optimized by the objective function in L3(x(k)), m represents the total number of non-free flight obstacles, i represents the serial number of the inspection drone, n represents the total number of inspection drones, and j represents the serial number of the non-free flight obstacle;

[0079] When the value of the objective function is minimum, obtaining the target speed and target direction in the objective function;

[0080] The target speed and the target direction are used as the obstacle avoidance speed and the obstacle avoidance direction.

[0081] In a second aspect, the present invention provides a low-altitude inspection UAV flight obstacle avoidance system, the system comprising:

[0082] An object detection module is used to collect objects to be avoided by the inspection drone, wherein the objects to be avoided include non-free flight obstacles and free flight obstacles, collect route information of the non-free flight obstacles, use the route information to identify the flight area of ​​the inspection drone, and after flying the inspection drone within the flight area, use the inspection drone to detect whether the objects to be avoided exist within the flight area;

[0083] an obstacle identification module, for collecting the wind direction and wind speed at the object to be avoided when the inspection drone is used to detect the existence of the object to be avoided in the flight area, detecting the flight direction and flight speed of the object to be avoided in the inspection drone, and identifying whether the object to be avoided is the non-free flight obstacle by using the wind direction, the wind speed, the flight direction and the flight speed;

[0084] a range calculation module, for, when the obstacle to be avoided is identified as the non-free flight obstacle, querying the drone-non-free obstacle distance between the inspection drone and the non-free flight obstacle, and respectively calculating the drone range of the inspection drone and the obstacle range of the non-free flight obstacle;

[0085] A first obstacle avoidance module, configured to set a safety distance between the inspection drone and the non-free flight obstacle by using the drone range and the obstacle range, and to perform a first flight obstacle avoidance on the non-free flight obstacle by using the inspection drone based on the drone-non-free obstacle distance and the safety distance, thereby obtaining a first flight obstacle avoidance result;

[0086] A second obstacle avoidance module is used to generate a flight path of the free flight obstacle using the wind direction and the wind speed when it is identified that the obstacle to be avoided is not the non-free flight obstacle, and perform a second flight obstacle avoidance on the free flight obstacle using the inspection drone according to the flight path to obtain a second flight obstacle avoidance result;

[0087] The result determination module is used to use the first flight obstacle avoidance result and the second flight obstacle avoidance result as the flight obstacle avoidance result of the inspection UAV.

[0088] Compared with the prior art, the technical principle and beneficial effects of this solution are:

[0089] The embodiment of the present invention flies the inspection drone within the flight area so as to correct the route of the inspection drone to a route that avoids the non-free flight obstacle before the inspection drone takes off, and searches for obstacle avoidance routes by means of a search tree, instead of the original method of using a three-dimensional map to generate routes, thereby giving the inspection drone flexibility in obstacle avoidance. Furthermore, the embodiment of the present invention detects whether the obstacle to be avoided exists within the flight area by means of the inspection drone, so as not to immediately treat the obstacle as the obstacle to be avoided when an obstacle is found, but to treat the obstacle as the obstacle to be avoided after detecting whether the navigation of the obstacle will affect the navigation of the inspection drone. Furthermore, the embodiment of the present invention identifies whether the obstacle to be avoided is the non-free flight obstacle by means of the wind direction, the wind speed, the flight direction and the flight speed, so as to detect the non-free flight obstacle. The obstacle and the free-flight obstacle plan different obstacle avoidance routes to improve the flexibility of the drone's obstacle avoidance. The embodiment of the present invention sets the safety distance between the inspection drone and the non-free-flight obstacle by using the drone range and the obstacle range, so as to automatically trigger the obstacle avoidance function of the drone when the drone and the obstacle reach the safety distance. Further, the embodiment of the present invention uses the inspection drone to perform the first flight obstacle avoidance on the non-free-flight obstacle based on the drone-non-free-obstacle distance and the safety distance, so as to automatically correct the flight speed and flight direction of the inspection drone when the inspection drone triggers the obstacle avoidance function, and avoid the obstacle in time when encountering an emergency close-range obstacle. The embodiment of the present invention uses the inspection drone to perform the second flight obstacle avoidance on the free-flight obstacle according to the flight path, so as to increase the obstacle avoidance safety distance for obstacles with unfixed flight routes. Therefore, the low-altitude inspection drone flight obstacle avoidance method and system proposed in the embodiment of the present invention can design a new drone obstacle avoidance method to achieve flexible and autonomous obstacle avoidance. BRIEF DESCRIPTION OF THE DRAWINGS

[0090] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0091] 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, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0092] Figure 1 A schematic diagram of a flow chart of a low-altitude inspection UAV flight obstacle avoidance method provided by an embodiment of the present invention;

[0093] Figure 2 A module schematic diagram of a low-altitude inspection UAV flight obstacle avoidance system provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0094] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0095] The embodiment of the present invention provides a method for avoiding obstacles in flight of a low-altitude inspection drone. The execution subject of the method includes but is not limited to at least one of the electronic devices such as a server and a terminal that can be configured to execute the method provided by the embodiment of the present invention. In other words, the method for avoiding obstacles in flight of a low-altitude inspection drone can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc. The server can be an independent server, or it can be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms.

[0096] See also Figure 1 The figure shows the process of the low-altitude inspection drone flight obstacle avoidance method provided by one embodiment of the present invention. Figure 1 The low-altitude inspection drone flight obstacle avoidance methods described in include:

[0097] S1. Collect obstacle objects to be avoided by the inspection drone, wherein the obstacle objects to be avoided include non-free flight obstacles and free flight obstacles, collect route information of the non-free flight obstacles, use the route information to identify the flight area of ​​the inspection drone, and after flying the inspection drone within the flight area, use the inspection drone to detect whether there are obstacle objects to be avoided in the flight area.

[0098] In an embodiment of the present invention, the inspection drone refers to a drone with automated flight, automatic identification, and automatic transmission and processing functions. The automated flight refers to fully automatic inspection in the inspection area, including technologies such as automatic take-off, autonomous flight, and automatic landing. The automatic identification refers to the AI ​​control system equipped in the inspection drone, which can automatically identify equipment or problems in the inspection area without human intervention. The automatic transmission and processing refers to the inspection drone collecting information on the target equipment through the onboard sensors and automatically processing it using AI technology. Furthermore, the obstacle to be avoided refers to an aerial obstacle that affects the current navigation route of the inspection drone, such as other drones, kites, balloons, large aircraft in take-off or landing status, birds, and other obstacles.

[0099] Furthermore, the non-free flight obstacles refer to obstacles that fly along a fixed navigation route, such as other drones, large aircraft in takeoff or landing, birds and other obstacles, and the free flight obstacles refer to obstacles that do not fly along a fixed navigation route, such as aerial debris such as kites and balloons.

[0100] Furthermore, the route information refers to the flight route of a large aircraft in a take-off or landing state in the non-free flight obstacle.

[0101] Furthermore, the flight area refers to an air area other than an area where the flight route corresponding to the route information is located.

[0102] Furthermore, the embodiment of the present invention flies the inspection UAV within the flight area so as to correct the route of the inspection UAV to a route that avoids the non-free flight obstacles before the inspection UAV takes off, and uses a search tree method to search for an obstacle avoidance route, replacing the original method of using a three-dimensional map to generate a route, thereby giving the inspection UAV the flexibility to avoid obstacles.

[0103] In one embodiment of the present invention, flying the inspection drone within the flight area includes: querying whether the navigation route of the inspection drone is within the flight area; when the navigation route of the inspection drone is not within the flight area, extracting a first target point where the navigation route of the inspection drone is not within the flight area; and calculating the obstacle avoidance trigger point of the inspection drone according to the navigation route and the first target point using the following formula:

[0104] a≤t≤b

[0105] x a (t)≤x(t)≤x b (t)

[0106] y a (t)≤y(t)≤yb (t)

[0107] z a (t)≤z(t)≤z b (t)

[0108]

[0109] Among them, (x a (t),y a (t),z a where (t)) represents the obstacle avoidance trigger point, L represents the length of the route from the obstacle avoidance trigger point to the first target point in the navigation route, x(t) represents the curve parameter equation of the route from the obstacle avoidance trigger point to the first target point in the navigation route on the x-axis, y(t) represents the curve parameter equation of the route from the obstacle avoidance trigger point to the first target point in the navigation route on the y-axis, z(t) represents the curve parameter equation of the route from the obstacle avoidance trigger point to the first target point in the navigation route on the z-axis, x a (t) represents the value of the obstacle avoidance trigger point on the x-axis, y a (t) represents the value of the obstacle avoidance trigger point on the y-axis, z a (t) represents the value of the obstacle avoidance trigger point on the z-axis, x b (t) represents the value of the first target point on the x-axis, y b (t) represents the value of the first target point on the y-axis, z b (t) represents the value of the first target point on the z-axis, t represents the independent variable constrained by x(t), y(t), and z(t), and a represents the independent variable constrained by x. a (t), y a (t), z a (t) is the value constrained by x. b (t), y b (t), z b (t) The value of the constraint, t0 represents the time required for the inspection UAV to complete a 180-degree turn when encountering an obstacle, and v0 represents the average flight speed of the inspection UAV;

[0110] The navigation route is route-planned using the obstacle avoidance trigger point to obtain a planned route; the route similarity between the planned route and the navigation route is calculated; based on the route similarity, a final route of the inspection drone is determined from the planned route; and the inspection drone is flown on the final route.

[0111] It should be noted that when the navigation route of the inspection drone is not within the flight area, it means that the navigation route of the inspection drone is within the area where the flight route corresponding to the route information is located.

[0112] Among them, the first target point refers to the boundary of the area where the flight route corresponding to the route information is located, the obstacle avoidance trigger point refers to the coordinate point on the navigation route that triggers the inspection drone to start obstacle avoidance, and the time required for the inspection drone to complete a 180-degree turn when encountering an obstacle refers to the maximum time for the inspection drone to turn when it deviates from the current navigation route and turns to other routes.

[0113] Optionally, the process of determining the final route of the inspection drone from the planned routes based on the route similarity aims to ensure that the route after obstacle avoidance has the highest similarity to the originally planned navigation route. Therefore, the process of determining the final route of the inspection drone from the planned routes based on the route similarity is to take the planned route corresponding to the largest route similarity among the route similarities as the final route.

[0114] In another embodiment of the present invention, the route planning of the navigation route using the obstacle avoidance trigger point to obtain the planned route includes: obtaining the starting point and the ending point of the navigation route; searching for coordinate points around the obstacle avoidance trigger point and other coordinate points around the coordinate point starting from the obstacle avoidance trigger point; until the ending point exists among the searched coordinate points and the other coordinate points, generating an initial route between the obstacle avoidance trigger point and the ending point using the coordinate points and the other coordinate points; querying whether there is a first route consistent with the navigation route from the initial route in order from the ending point to the end of the obstacle avoidance trigger point; when querying whether there is a first route consistent with the navigation route on the initial route, obtaining a second route on the initial route except the first route, and obtaining a third route on the navigation route between the starting point and the obstacle avoidance trigger point; and sequentially splicing the third route, the second route and the first route to obtain the planned route.

[0115] Exemplarily, the process of searching for coordinate points around the obstacle avoidance trigger point and other coordinate points around the coordinate point starting from the obstacle avoidance trigger point is, for example: when the obstacle avoidance trigger point is A, the coordinate points around the obstacle avoidance trigger point are 1, 2, 3, 4, 5, and the other coordinate points around the coordinate points 1, 2, 3, 4, 5 are 11, 12; 21, 22; 31, 32; 41, 42; 51, 52; further, other coordinate points 11, 12; 21, 22; 31, 32; 41, 42; 51, 52 continue to have other coordinate points around them, such as 111, 112, 113, etc.

[0116] The other coordinate points refer to neighbor coordinate points of the coordinate point, peripheral coordinate points of the neighbor coordinate points, further peripheral coordinate points of the peripheral coordinate points, and the like.

[0117] Optionally, the process of using the coordinate point and the other coordinate points to generate the initial route between the obstacle avoidance trigger point and the end point is obtained by the process of searching the coordinate points around the obstacle avoidance trigger point and other coordinate points around the coordinate point starting from the obstacle avoidance trigger point. The process of searching the coordinate points around the obstacle avoidance trigger point and other coordinate points around the coordinate point starting from the obstacle avoidance trigger point is essentially a search tree. For example, the root node 1, 1's child nodes 11, 12, 11's child nodes 111, 112, 113, then when 113 is the end point, the path of obstacle avoidance trigger point-1-11-113 is used as the initial route.

[0118] Optionally, the process of querying whether there is a first route consistent with the navigation route from the initial route in the order from the termination point to the obstacle avoidance trigger point refers to the first continuous route consistent with the navigation route starting from the termination point in the order from the termination point to the obstacle avoidance trigger point. If this route starts from a certain coordinate point in the middle between the termination point and the obstacle avoidance trigger point, then this route is not the first route, and the first route needs to be continuous and uninterrupted from the termination point to a certain coordinate point in the middle or the obstacle avoidance trigger point. For example, the routes in the order from the termination point to the obstacle avoidance trigger point are 5, 4, 3, 2, 1, the route from 5 and 4 is consistent with the navigation route, and the route from 2 and 1 is consistent with the navigation route. Then the route from 5 and 4 is the first route, and the route from 2 and 1 is not the first route.

[0119] The second route refers to all remaining routes on the initial route except the first route.

[0120] Furthermore, the embodiment of the present invention utilizes the inspection drone to detect whether the obstacle to be avoided exists in the flight area, so that when an obstacle is found, the obstacle is not immediately regarded as the obstacle to be avoided, but the obstacle is regarded as the obstacle to be avoided after detecting whether the navigation of the obstacle will affect the navigation of the inspection drone.

[0121] In one embodiment of the present invention, the use of the inspection drone to detect whether the object to be avoided exists in the flight area includes: using the inspection drone to detect whether there is an object in the flight area; when using the inspection drone to detect the existence of an object in the flight area, identifying the object coordinates, object direction and object speed of the object; using the object coordinates, the object direction and the object speed to construct an object motion trajectory curve of the object; constructing a drone motion trajectory curve of the inspection drone; determining whether the curve intersection between the object motion trajectory curve and the drone motion trajectory curve can be calculated; when the curve intersection between the object motion trajectory curve and the drone motion trajectory curve can be calculated, determining that the object to be avoided exists in the flight area; when the curve intersection between the object motion trajectory curve and the drone motion trajectory curve cannot be calculated, determining that the object to be avoided does not exist in the flight area.

[0122] Optionally, the process of identifying the object coordinates, object direction and object speed of the object can be achieved by using the laser ranging technology of the inspection drone.

[0123] S2. When the inspection drone is used to detect the existence of the obstacle to be avoided in the flight area, the wind direction and wind speed at the obstacle to be avoided are collected, the flight direction and flight speed of the obstacle to be avoided are detected in the inspection drone, and the wind direction, wind speed, flight direction and flight speed are used to identify whether the obstacle to be avoided is the non-free flight obstacle.

[0124] Optionally, the process of collecting the wind direction and wind speed at the obstacle to be avoided may be achieved by a wind speed and direction sensor.

[0125] Furthermore, the embodiment of the present invention utilizes the wind direction, the wind speed, the flight direction and the flight speed to identify whether the obstacle to be avoided is the non-free flight obstacle, so as to plan different obstacle avoidance routes for the non-free flight obstacle and the free flight obstacle, thereby improving the flexibility of the drone in avoiding obstacles.

[0126] In one embodiment of the present invention, the use of the wind direction, the wind speed, the flight direction and the flight speed to identify whether the obstacle to be avoided is the non-free flight obstacle includes: querying the wind direction turning period of the wind direction and the direction turning period of the flight direction; and constructing a correlation function between the wind speed and the flight speed using the following formula:

[0127] Y=KX+B

[0128] Wherein, Y=KX+B represents the correlation function, Y represents the flight speed, X represents the wind speed, B represents the intercept on the y-axis, and K represents the slope;

[0129] When the slope in the correlation function is greater than the preset slope and the wind direction turning period is consistent with the direction turning period, it is determined that the obstacle to be avoided is not the non-free flight obstacle; when the slope in the correlation function is not greater than the preset slope and the wind direction turning period is inconsistent with the direction turning period, it is determined that the obstacle to be avoided is the non-free flight obstacle.

[0130] Among them, the wind direction turning period refers to the period when the wind direction turns from one direction to another, and the direction turning period refers to the period when the wind direction turns from one direction to another. Furthermore, the preset slope is set to 0. When the slope in the correlation function is greater than the preset slope, it indicates that the flight speed is positively correlated with the wind speed. Generally, the flight direction and flight speed of aerial debris will change with the wind direction and wind speed.

[0131] S3. When the obstacle to be avoided is identified as the non-free flight obstacle, query the drone-non-free obstacle distance between the inspection drone and the non-free flight obstacle, and calculate the drone range of the inspection drone and the obstacle range of the non-free flight obstacle respectively.

[0132] In one embodiment of the present invention, respectively calculating the drone range of the inspection drone and the obstacle range of the non-free flight obstacle includes: querying the center coordinate point of the inspection drone; identifying the surface coordinate points on the surface of the inspection drone; when the first coordinate point distance between the center coordinate point and the surface coordinate point is the largest; using the center coordinate point as the center of the sphere and the first coordinate point distance as the sphere radius as the drone range; obtaining the edge coordinate points on the surface of the non-free flight obstacle in the inspection drone; using the edge coordinate points to calculate the centroid coordinate points of the non-free flight obstacle; when the second coordinate point distance between the centroid coordinate point and the edge coordinate point is the largest; using the centroid coordinate point as the center of the sphere and the second coordinate point distance as the sphere radius as the obstacle range.

[0133] S4. Using the drone range and the obstacle range to set a safety distance between the inspection drone and the non-free flight obstacle, based on the drone-non-free obstacle distance and the safety distance, using the inspection drone to perform a first flight obstacle avoidance on the non-free flight obstacle to obtain a first flight obstacle avoidance result.

[0134] The embodiment of the present invention sets a safe distance between the inspection drone and the non-free flight obstacle by utilizing the drone range and the obstacle range, so as to automatically trigger the obstacle avoidance function of the drone when the drone and the obstacle reach a safe distance.

[0135] In one embodiment of the present invention, the method of setting the safety distance between the inspection drone and the non-free flight obstacle by using the drone range and the obstacle range includes: obtaining the maximum time for the inspection drone to complete the turn; and calculating the safety distance between the inspection drone and the non-free flight obstacle by using the following formula according to the maximum time, the drone range and the obstacle range:

[0136] L'=t0v0+r1+r2

[0137] Among them, L' represents the safety distance, t0 represents the time required for the inspection drone to complete a 180-degree turn when encountering an obstacle, the time required for the inspection drone to complete a 180-degree turn when encountering an obstacle is the maximum time, v0 represents the average flight speed of the inspection drone, r1 represents the sphere radius corresponding to the drone range, and r2 represents the sphere radius corresponding to the obstacle range.

[0138] Furthermore, the embodiment of the present invention utilizes the inspection drone to perform a first flight obstacle avoidance for the non-free flight obstacle based on the drone-non-free obstacle distance and the safety distance, so as to automatically correct the flight speed and flight direction of the inspection drone when the obstacle avoidance function is triggered, and avoid the obstacle in time when encountering an emergency close-range obstacle.

[0139] The first flight obstacle avoidance result includes a current first flight obstacle avoidance result, a complex first flight obstacle avoidance result, and a simple first flight obstacle avoidance result.

[0140] In one embodiment of the present invention, based on the UAV-non-free obstacle distance and the safety distance, using the inspection UAV to perform a first flight obstacle avoidance on the non-free flight obstacle to obtain a first flight obstacle avoidance result, including: judging whether the UAV-non-free obstacle distance is less than the safety distance; when the UAV-non-free obstacle distance is not less than the safety distance, judging whether the UAV-non-free obstacle distance is greater than the safety distance; when the UAV-non-free obstacle distance is not greater than the safety distance, using the inspection UAV to perform the current first flight obstacle avoidance on the non-free flight obstacle to obtain the current first flight obstacle avoidance result; in the When the UAV-non-free obstacle distance is greater than the safety distance, the obstacle avoidance speed and obstacle avoidance direction of the inspection UAV when performing the first flight obstacle avoidance for the non-free flight obstacle are calculated; according to the obstacle avoidance speed and the obstacle avoidance direction, the inspection UAV is used to perform complex first flight obstacle avoidance for the non-free flight obstacle, and a complex first flight obstacle avoidance result is obtained; when the UAV-non-free obstacle distance is less than the safety distance, the state adjustment gear of the inspection UAV is set according to a preset PID controller algorithm, and the inspection UAV and the state adjustment gear are used to perform simple first flight obstacle avoidance for the non-free flight obstacle, and a simple first flight obstacle avoidance result is obtained.

[0141] Optionally, the process of using the inspection drone to perform the current first flight obstacle avoidance on the non-free flight obstacle and obtaining the current first flight obstacle avoidance result refers to: automatically triggering the obstacle avoidance function of the drone when the inspection drone reaches a safe distance from the obstacle. The obstacle avoidance function includes path planning and state adjustment. The principle of setting the path planning is similar to the principle of using the obstacle avoidance trigger point to perform route planning on the navigation route and obtain the planned route, and will not be further elaborated here. Furthermore, state adjustment includes speed adjustment and direction adjustment. Since the average flight speed of the drone is used to calculate the safe distance, when the current flight speed of the inspection drone is less than or equal to the average flight speed, the inspection drone can complete the turn within the safe distance and turn to the re-planned route, and the direction adjustment process needs to be determined based on the direction of the re-planned route.

[0142] Optionally, the process of performing complex first flight obstacle avoidance on the non-free flight obstacle using the inspection drone according to the obstacle avoidance speed and the obstacle avoidance direction to obtain a complex first flight obstacle avoidance result is the process of driving the inspection drone on a re-planned route according to the obstacle avoidance speed and the obstacle avoidance direction.

[0143] Optionally, the state adjustment gear of the inspection drone is set according to a preset PID controller algorithm, and the process of using the inspection drone and the state adjustment gear to perform a simple first flight obstacle avoidance on the non-free flight obstacle means that: the distance between the inspection drone and the non-free flight obstacle is relatively close, and there is no time to perform complex data processing. Therefore, before the inspection drone flies, the PID controller algorithm is used to calculate in advance a series of speed sequences after deceleration for each or each speed gear, and then the speed is automatically reduced according to the speed sequence when encountering a close obstacle. Similarly, the correction of the direction also needs to be determined by the PID controller algorithm. It should be noted that when the direction turns 180 degrees based on the original direction, it means that the aircraft is retreating. When the aircraft is retreated to a long-distance position, the above-mentioned process of using the inspection drone to perform the current first flight obstacle avoidance on the non-free flight obstacle and obtaining the current first flight obstacle avoidance result is used to complete the process of performing a simple first flight obstacle avoidance on the non-free flight obstacle.

[0144] In another embodiment of the present invention, the calculating the obstacle avoidance speed and obstacle avoidance direction of the inspection drone when performing the first flight obstacle avoidance on the non-free flight obstacle includes: constructing the objective function of the inspection drone when performing the first flight obstacle avoidance on the non-free flight obstacle using the following formula;

[0145]

[0146]

[0147]

[0148]

[0149] minJx(k),u(k)=minL1(x(k))+L2(u(k))+L2(Δu(k))+L3(x(k))

[0150] Among them, minJx(k),u(k) represents the objective function, x(k) represents the flight state of the inspection drone, x(k) includes speed and direction, u(k) represents the control input value of the inspection drone, Δu(k) represents the change in the control input value of the inspection drone, L1(x(k)) represents the error parameter between the current coordinates of the inspection drone and the corresponding coordinates on the planned route, x1(k) represents the coordinates of the inspection drone on the planned route at time k, and w1 represents the objective function to be used in L1(x(k)). The weight parameter to be optimized is L2(u(k)), which is the constraint parameter to ensure that the inspection UAV flies with a smaller control input value. w2 is the weight parameter to be optimized by the objective function in L2(u(k)), which is the constraint parameter to ensure that the change of the control input value of the inspection UAV is smooth. w3 is the weight parameter to be optimized by the objective function in L2(Δu(k)), which is the constraint parameter to ensure that the inspection UAV maintains a safe distance from non-free flight obstacles. z j represents the coordinates of the jth non-free flight obstacle, x2(k) represents the corresponding coordinates on the replanned route, w4 represents the weight parameter to be optimized by the objective function in L3(x(k)), m represents the total number of non-free flight obstacles, i represents the serial number of the inspection drone, n represents the total number of inspection drones, and j represents the serial number of the non-free flight obstacle;

[0151] When the value of the objective function is minimum, a target speed and a target direction in the objective function are obtained; and the target speed and the target direction are used as the obstacle avoidance speed and the obstacle avoidance direction.

[0152] S5. When it is identified that the obstacle to be avoided is not the non-free flight obstacle, the flight path of the free flight obstacle is generated using the wind direction and the wind speed, and according to the flight path, the inspection drone is used to perform a second flight obstacle avoidance on the free flight obstacle to obtain a second flight obstacle avoidance result.

[0153] The embodiment of the present invention uses the inspection drone to perform a second flight obstacle avoidance on the free-flight obstacle according to the flight path, so as to increase the obstacle avoidance safety distance for obstacles with unfixed flight paths.

[0154] Optionally, the process of performing a second flight obstacle avoidance on the free flight obstacle using the inspection drone according to the flight path to obtain a second flight obstacle avoidance result includes a process of setting a safety distance and performing obstacle avoidance based on the safety distance. When setting the safety distance, the safety distance is increased on the basis of the safety distance between the inspection drone and the non-free flight obstacle. The basis for increasing the safety distance needs to be determined based on the distance at which the free flight obstacle will change the original predicted trajectory due to an emergency in historical data. Furthermore, the process of performing obstacle avoidance based on the safety distance is similar to the principle of performing a first flight obstacle avoidance on the non-free flight obstacle based on the drone-non-free obstacle distance and the safety distance to obtain the first flight obstacle avoidance result, and will not be further elaborated here.

[0155] S6. Use the first flight obstacle avoidance result and the second flight obstacle avoidance result as the flight obstacle avoidance result of the inspection UAV.

[0156] It can be seen that the embodiment of the present invention flies the inspection drone in the flight area to correct the route of the inspection drone to a route that avoids the non-free flight obstacle before the inspection drone takes off, and uses a search tree method to search for obstacle avoidance routes, instead of the original method of using a three-dimensional map to generate routes, giving the inspection drone the flexibility to avoid obstacles. Furthermore, the embodiment of the present invention uses the inspection drone to detect whether the obstacle to be avoided exists in the flight area, so that when an obstacle is found, the obstacle is not immediately regarded as the obstacle to be avoided, but is regarded as the obstacle to be avoided after detecting whether the navigation of the obstacle will affect the navigation of the inspection drone. Furthermore, the embodiment of the present invention uses the wind direction, the wind speed, the flight direction and the flight speed to identify whether the obstacle to be avoided is the non-free flight obstacle, so as to target the non-free flight obstacle. Different obstacle avoidance routes are planned for the flight obstacle and the free flight obstacle, so as to improve the flexibility of the obstacle avoidance of the drone. The embodiment of the present invention sets the safety distance between the inspection drone and the non-free flight obstacle by using the drone range and the obstacle range, so as to automatically trigger the obstacle avoidance function of the drone when the drone and the obstacle reach the safety distance. Further, the embodiment of the present invention uses the inspection drone to perform the first flight obstacle avoidance on the non-free flight obstacle based on the drone-non-free obstacle distance and the safety distance, so as to automatically correct the flight speed and flight direction of the inspection drone when the obstacle avoidance function is triggered by the inspection drone, and avoid the obstacle in time when encountering an emergency close-range obstacle. The embodiment of the present invention uses the inspection drone to perform the second flight obstacle avoidance on the free flight obstacle according to the flight path, so as to increase the obstacle avoidance safety distance for obstacles with unfixed flight routes. Therefore, the low-altitude inspection drone flight obstacle avoidance method and system proposed in the embodiment of the present invention can design a new drone obstacle avoidance method to achieve flexible and autonomous obstacle avoidance.

[0157] like Figure 2 Shown is a functional module diagram of the low-altitude inspection UAV flight obstacle avoidance system of the present invention.

[0158] The low-altitude inspection drone flight obstacle avoidance system 200 of the present invention can be installed in an electronic device. According to the functions to be implemented, the low-altitude inspection drone flight obstacle avoidance system can include an object detection module 201, an obstacle recognition module 202, a range calculation module 203, a first obstacle avoidance module 204, a second obstacle avoidance module 205 and a result determination module 206. The module of the present invention can also be referred to as a unit, which refers to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, which are stored in the memory of the electronic device.

[0159] In the embodiment of the present invention, the functions of each module / unit are as follows:

[0160] The object detection module 201 is used to collect objects to be avoided by the inspection drone, wherein the objects to be avoided include non-free flight obstacles and free flight obstacles, collect route information of the non-free flight obstacles, use the route information to identify the flight area of ​​the inspection drone, and after flying the inspection drone in the flight area, use the inspection drone to detect whether the objects to be avoided exist in the flight area;

[0161] The obstacle identification module 202 is used to collect the wind direction and wind speed at the object to be avoided when the inspection drone is used to detect the existence of the object to be avoided in the flight area, detect the flight direction and flight speed of the object to be avoided in the inspection drone, and use the wind direction, wind speed, flight direction and flight speed to identify whether the object to be avoided is the non-free flight obstacle;

[0162] The range calculation module 203 is used to query the drone-non-free obstacle distance between the inspection drone and the non-free flight obstacle when the obstacle to be avoided is identified as the non-free flight obstacle, and calculate the drone range of the inspection drone and the obstacle range of the non-free flight obstacle respectively;

[0163] The first obstacle avoidance module 204 is used to set a safety distance between the inspection drone and the non-free flight obstacle by using the drone range and the obstacle range, and based on the drone-non-free obstacle distance and the safety distance, use the inspection drone to perform a first flight obstacle avoidance on the non-free flight obstacle to obtain a first flight obstacle avoidance result;

[0164] The second obstacle avoidance module 205 is used to generate a flight path of the free flight obstacle using the wind direction and the wind speed when it is identified that the obstacle to be avoided is not the non-free flight obstacle, and perform a second flight obstacle avoidance on the free flight obstacle using the inspection drone according to the flight path to obtain a second flight obstacle avoidance result;

[0165] The result determination module 206 is used to use the first flight obstacle avoidance result and the second flight obstacle avoidance result as the flight obstacle avoidance result of the inspection UAV.

[0166] In detail, each module in the low-altitude inspection drone flight obstacle avoidance system 200 in the embodiment of the present invention is used in the same manner as described above. Figure 1 The low-altitude inspection UAV flight obstacle avoidance method described in the invention has the same technical means and can produce the same technical effects, so I will not go into details here.

[0167] In addition, each functional module in each embodiment of the present invention may be integrated into one processing unit, each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0168] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0169] Therefore, no matter from which point of view, the embodiments should be regarded as illustrative and non-restrictive, and the scope of the present invention is limited by the appended claims rather than the above description, so it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present invention. Any attached figure mark in the claims should not be regarded as limiting the claims involved.

[0170] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0171] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A low-altitude inspection drone flight obstacle avoidance method, characterized in that: The method comprises: Collecting obstacles to be avoided by the inspection drone, wherein the obstacles to be avoided include non-free flight obstacles and free flight obstacles, collecting route information of the non-free flight obstacles, using the route information to identify the flight area of ​​the inspection drone, and after flying the inspection drone within the flight area, using the inspection drone to detect whether the obstacles to be avoided exist within the flight area; When the inspection drone is used to detect the existence of the obstacle to be avoided in the flight area, the wind direction and wind speed at the obstacle to be avoided are collected, the flight direction and flight speed of the obstacle to be avoided are detected in the inspection drone, and the wind direction, wind speed, flight direction and flight speed are used to identify whether the obstacle to be avoided is the non-free flight obstacle, wherein the use of the wind direction, wind speed, flight direction and flight speed to identify whether the obstacle to be avoided is the non-free flight obstacle includes: Querying a wind direction turning period of the wind direction and a direction turning period of the flight direction; The correlation function between the wind speed and the flight speed is constructed using the following formula: Y=KX+B Wherein, Y=KX+B represents the correlation function, Y represents the flight speed, X represents the wind speed, B represents the intercept on the y-axis, and K represents the slope; When the slope in the correlation function is greater than a preset slope and the wind direction turning period is consistent with the direction turning period, it is determined that the obstacle to be avoided is not the non-free flight obstacle; When the slope in the correlation function is not greater than the preset slope and the wind direction turning period is inconsistent with the direction turning period, determining that the obstacle to be avoided is the non-free flight obstacle; When the obstacle to be avoided is identified as the non-free flight obstacle, querying the drone-non-free obstacle distance between the inspection drone and the non-free flight obstacle, and calculating the drone range of the inspection drone and the obstacle range of the non-free flight obstacle respectively; The safety distance between the inspection drone and the non-free flight obstacle is set by using the drone range and the obstacle range, and based on the drone-non-free obstacle distance and the safety distance, the inspection drone is used to perform a first flight obstacle avoidance on the non-free flight obstacle to obtain a first flight obstacle avoidance result, wherein the first flight obstacle avoidance result is obtained by using the inspection drone to perform a first flight obstacle avoidance on the non-free flight obstacle based on the drone-non-free obstacle distance and the safety distance, including: Determining whether the drone-non-free obstacle distance is less than the safety distance; When the UAV-non-free obstacle distance is not less than the safety distance, determining whether the UAV-non-free obstacle distance is greater than the safety distance; When the distance between the drone and the non-free obstacle is not greater than the safety distance, using the inspection drone to perform a current first flight obstacle avoidance on the non-free flight obstacle to obtain a current first flight obstacle avoidance result; When the distance between the drone and the non-free obstacle is greater than the safety distance, calculating the obstacle avoidance speed and obstacle avoidance direction of the inspection drone when performing the first flight obstacle avoidance on the non-free flight obstacle; According to the obstacle avoidance speed and the obstacle avoidance direction, using the inspection drone to perform complex first flight obstacle avoidance on the non-free flight obstacle to obtain a complex first flight obstacle avoidance result; When the UAV-non-free obstacle distance is less than the safety distance, a simple first flight obstacle avoidance result is obtained according to a preset PID controller calculation; The calculating the obstacle avoidance speed and obstacle avoidance direction of the inspection drone when performing the first flight obstacle avoidance on the non-free flight obstacle includes: The objective function of the inspection UAV performing the first flight obstacle avoidance on the non-free flight obstacle is constructed using the following formula; minJ(x(k), u(k))=min{L1(x(k))+L2(u(k))+L2(Δu(k))+L3(x(k))} Among them, minJ(x(k), u(k)) represents the objective function, x(k) represents the flight state of the inspection drone, x(k) includes speed and direction, u(k) represents the control input value of the inspection drone, Δu(k) represents the change in the control input value of the inspection drone, L1(x(k)) represents the error parameter between the current coordinates of the inspection drone and the corresponding coordinates on the planned route, x1(k) represents the corresponding coordinates of the inspection drone on the planned route at time k, and w1 represents the target to be used in L1(x(k)). function optimization, L2(u(k)) represents the constraint parameter to ensure that the inspection UAV flies with a smaller control input value, W2 represents the weight parameter to be optimized by the objective function in L2(u(k)), L2(Δu(k)) represents the constraint parameter to ensure the smooth change of the control input value of the inspection UAV, W3 represents the weight parameter to be optimized by the objective function in L2(Δu(k)), L3(x(k)) represents the constraint parameter to ensure that the inspection UAV maintains a safe distance from non-free flight obstacles, z j represents the coordinates of the jth non-free flight obstacle, x2(k) represents the corresponding coordinates on the replanned route, w4 represents the weight parameter to be optimized by the objective function in L3(x(k)), m represents the total number of non-free flight obstacles, i represents the serial number of the inspection drone, n represents the total number of inspection drones, and j represents the serial number of the non-free flight obstacle; When the value of the objective function is minimum, obtaining the target speed and target direction in the objective function; Using the target speed and the target direction as the obstacle avoidance speed and the obstacle avoidance direction; When it is identified that the obstacle to be avoided is not the non-free flight obstacle, the flight path of the free flight obstacle is generated by using the wind direction and the wind speed, and according to the flight path, the inspection drone is used to perform a second flight obstacle avoidance on the free flight obstacle to obtain a second flight obstacle avoidance result; The first flight obstacle avoidance result and the second flight obstacle avoidance result are used as the flight obstacle avoidance result of the inspection UAV.

2. The method according to claim 1, characterized in that Flying the inspection drone within the flight area includes: Query whether the navigation route of the inspection drone is within the flight area; When the navigation route of the inspection drone is not within the flight area, extracting a first target point where the navigation route of the inspection drone is not within the flight area; According to the navigation route and the first target point, the obstacle avoidance trigger point of the inspection drone is calculated using the following formula: a≤t≤b x a (t)≤x(t)≤x b (t) y a (t)≤y(t)≤y b (t) z a (t)≤z(t)≤z b (t) Among them, (x a (t), y a (t), z a where (t)) represents the obstacle avoidance trigger point, L represents the length of the route from the obstacle avoidance trigger point to the first target point in the navigation route, x(t) represents the curve parameter equation of the route from the obstacle avoidance trigger point to the first target point in the navigation route on the x-axis, y(t) represents the curve parameter equation of the route from the obstacle avoidance trigger point to the first target point in the navigation route on the y-axis, z(t) represents the curve parameter equation of the route from the obstacle avoidance trigger point to the first target point in the navigation route on the z-axis, x a (t) represents the value of the obstacle avoidance trigger point on the x-axis, y a (t) represents the value of the obstacle avoidance trigger point on the y-axis, z a (t) represents the value of the obstacle avoidance trigger point on the z-axis, x b (t) represents the value of the first target point on the x-axis, y b (t) represents the value of the first target point on the y-axis, z b (t) represents the value of the first target point on the z-axis, t represents the independent variable constrained by x(t), y(t), and z(t), and a represents the independent variable constrained by x. a (t), y a (t), z a (t) is the value constrained by x. b (t), y b (t), z b (t) The value of the constraint, t0 represents the time required for the inspection UAV to complete a 180-degree turn when encountering an obstacle, and v0 represents the average flight speed of the inspection UAV; Using the obstacle avoidance trigger point to plan the navigation route to obtain a planned route; Calculating the route similarity between the planned route and the navigation route; Based on the route similarity, determining a final route of the inspection drone from the planned routes; Flying the inspection drone on the final route.

3. The method according to claim 2, characterized in that The step of planning the navigation route by using the obstacle avoidance trigger point to obtain a planned route includes: Obtaining the starting point and the ending point of the navigation route; Starting from the obstacle avoidance trigger point, searching for coordinate points around the obstacle avoidance trigger point and other coordinate points around the coordinate point; When the searched coordinate point and the other coordinate points contain the end point, the initial route between the obstacle avoidance trigger point and the end point is generated by using the coordinate point and the other coordinate points; In order from the end point to the obstacle avoidance trigger point, querying whether there is a first route consistent with the navigation route from the initial route; When a first route that is consistent with the navigation route is found on the initial route, a second route other than the first route on the initial route is obtained, and a third route between the starting point and the obstacle avoidance trigger point on the navigation route is obtained; The third route, the second route and the first route are sequentially spliced ​​to obtain the planned route.

4. The method according to claim 1, characterized in that: The method of using the inspection drone to detect whether the obstacle to be avoided exists in the flight area includes: Using the inspection drone to detect whether there is an object within the flight area; When the inspection drone is used to detect the existence of an object in the flight area, the object coordinates, object direction and object speed of the object are identified; constructing an object motion trajectory curve of the object using the object coordinates, the object direction and the object speed; Constructing a UAV motion trajectory curve of the inspection UAV; Determine whether it is possible to calculate the intersection point between the object motion trajectory curve and the drone motion trajectory curve; When the intersection point between the motion trajectory curve of the object and the motion trajectory curve of the drone can be calculated, determining that the obstacle to be avoided exists in the flight area; When the intersection point between the object motion trajectory curve and the drone motion trajectory curve cannot be calculated, it is determined that the obstacle to be avoided does not exist in the flight area.

5. The method according to claim 1, characterized in that The respectively calculating the drone range of the inspection drone and the obstacle range of the non-free flight obstacle includes: Query the center coordinate point of the inspection drone; Identifying surface coordinate points on the surface of the inspection drone; When the distance between the first coordinate point of the central coordinate point and the surface coordinate point is the largest; A sphere with the central coordinate point as the sphere center and the distance from the first coordinate point as the sphere radius is used as the range of the drone; Acquiring edge coordinate points on the surface of the non-free flight obstacle in the inspection drone; Calculating the centroid coordinate point of the non-free flight obstacle using the edge coordinate point; When the distance between the second coordinate point between the centroid coordinate point and the edge coordinate point is the largest; A sphere with the centroid coordinate point as the sphere center and the distance from the second coordinate point as the sphere radius is used as the obstacle range.

6. The method according to claim 1, characterized in that The step of using the drone range and the obstacle range to set a safe distance between the inspection drone and the non-free flight obstacle includes: Obtain the maximum time it takes for the inspection drone to complete a turn; According to the maximum duration, the range of the drone and the range of the obstacle, the safe distance between the inspection drone and the non-free flight obstacle is calculated using the following formula: L'=t0v0+r1+r2 Among them, L' represents the safety distance, t0 represents the time required for the inspection drone to complete a 180-degree turn when encountering an obstacle, the time required for the inspection drone to complete a 180-degree turn when encountering an obstacle is the maximum time, v0 represents the average flight speed of the inspection drone, r1 represents the sphere radius corresponding to the drone range, and r2 represents the sphere radius corresponding to the obstacle range.

7. A low-altitude inspection drone flight obstacle avoidance system, characterized in that: The system comprises: An object detection module is used to collect objects to be avoided by the inspection drone, wherein the objects to be avoided include non-free flight obstacles and free flight obstacles, collect route information of the non-free flight obstacles, use the route information to identify the flight area of ​​the inspection drone, and after flying the inspection drone within the flight area, use the inspection drone to detect whether the objects to be avoided exist within the flight area; The obstacle identification module is used to collect the wind direction and wind speed at the obstacle to be avoided when the inspection drone is used to detect the existence of the obstacle to be avoided in the flight area, detect the flight direction and flight speed of the obstacle to be avoided in the inspection drone, and use the wind direction, wind speed, flight direction and flight speed to identify whether the obstacle to be avoided is the non-free flight obstacle, wherein the use of the wind direction, wind speed, flight direction and flight speed to identify whether the obstacle to be avoided is the non-free flight obstacle includes: Querying a wind direction turning period of the wind direction and a direction turning period of the flight direction; The correlation function between the wind speed and the flight speed is constructed using the following formula: Y=KX+B Wherein, Y=KX+B represents the correlation function, Y represents the flight speed, X represents the wind speed, B represents the intercept on the y-axis, and K represents the slope; When the slope in the correlation function is greater than a preset slope and the wind direction turning period is consistent with the direction turning period, it is determined that the obstacle to be avoided is not the non-free flight obstacle; When the slope in the correlation function is not greater than the preset slope and the wind direction turning period is inconsistent with the direction turning period, determining that the obstacle to be avoided is the non-free flight obstacle; a range calculation module, for, when the obstacle to be avoided is identified as the non-free flight obstacle, querying the drone-non-free obstacle distance between the inspection drone and the non-free flight obstacle, and respectively calculating the drone range of the inspection drone and the obstacle range of the non-free flight obstacle; The first obstacle avoidance module is used to set a safety distance between the inspection drone and the non-free flight obstacle by using the drone range and the obstacle range, and to perform a first flight obstacle avoidance on the non-free flight obstacle by using the inspection drone based on the drone-non-free obstacle distance and the safety distance, to obtain a first flight obstacle avoidance result, wherein the first flight obstacle avoidance result is obtained by using the inspection drone based on the drone-non-free obstacle distance and the safety distance, including: Determining whether the drone-non-free obstacle distance is less than the safety distance; When the UAV-non-free obstacle distance is not less than the safety distance, determining whether the UAV-non-free obstacle distance is greater than the safety distance; When the distance between the drone and the non-free obstacle is not greater than the safety distance, using the inspection drone to perform a current first flight obstacle avoidance on the non-free flight obstacle to obtain a current first flight obstacle avoidance result; When the distance between the drone and the non-free obstacle is greater than the safety distance, calculating the obstacle avoidance speed and obstacle avoidance direction of the inspection drone when performing the first flight obstacle avoidance on the non-free flight obstacle; According to the obstacle avoidance speed and the obstacle avoidance direction, using the inspection drone to perform complex first flight obstacle avoidance on the non-free flight obstacle to obtain a complex first flight obstacle avoidance result; When the UAV-non-free obstacle distance is less than the safety distance, a simple first flight obstacle avoidance result is obtained according to a preset PID controller calculation; The calculating the obstacle avoidance speed and obstacle avoidance direction of the inspection drone when performing the first flight obstacle avoidance on the non-free flight obstacle includes: The objective function of the inspection UAV performing the first flight obstacle avoidance on the non-free flight obstacle is constructed using the following formula; minJ(x(k), u(k))=min{L1(x(k))+L2(u(k))+L2(Δu(k))+L3(x(k))} Among them, minJ(x(k), u(k)) represents the objective function, x(k) represents the flight state of the inspection drone, x(k) includes speed and direction, u(k) represents the control input value of the inspection drone, Δu(k) represents the change in the control input value of the inspection drone, L1(x(k)) represents the error parameter between the current coordinates of the inspection drone and the corresponding coordinates on the planned route, x1(k) represents the corresponding coordinates of the inspection drone on the planned route at time k, and w1 represents the target to be used in L1(x(k)). function optimization, L2(u(k)) represents the constraint parameter to ensure that the inspection UAV flies with a smaller control input value, w2 represents the weight parameter to be optimized by the objective function in L2(u(k)), L2(Δu(k)) represents the constraint parameter to ensure the smooth change of the control input value of the inspection UAV, w3 represents the weight parameter to be optimized by the objective function in L2(Δu(k)), L3(x(k)) represents the constraint parameter to ensure that the inspection UAV maintains a safe distance from non-free flight obstacles, z j represents the coordinates of the jth non-free flight obstacle, x2(k) represents the corresponding coordinates on the replanned route, w4 represents the weight parameter to be optimized by the objective function in L3(x(k)), m represents the total number of non-free flight obstacles, i represents the serial number of the inspection drone, n represents the total number of inspection drones, and j represents the serial number of the non-free flight obstacle; When the value of the objective function is minimum, obtaining the target speed and target direction in the objective function; Using the target speed and the target direction as the obstacle avoidance speed and the obstacle avoidance direction; A second obstacle avoidance module is used to generate a flight path of the free flight obstacle using the wind direction and the wind speed when it is identified that the obstacle to be avoided is not the non-free flight obstacle, and perform a second flight obstacle avoidance on the free flight obstacle using the inspection drone according to the flight path to obtain a second flight obstacle avoidance result; The result determination module is used to use the first flight obstacle avoidance result and the second flight obstacle avoidance result as the flight obstacle avoidance result of the inspection UAV.

Images