A method, system and electronic device for optimizing the escape strategy of a drone

Abstract

The present application provides an escape strategy optimization method, system and electronic device for a drone, which relates to the technical field of drones, and includes obtaining preset planning information of a drone, searching for a number of escape points according to the preset planning information; associating lifting information for the escape points, wherein the lifting information includes two different types of execution points; wherein, based on the detailed information and obstacle information of the escape point, judging whether the location of the escape point is an execution point; after the judgment is completed, determining the type of execution point to be supplemented, and supplementing the execution point for the escape point based on an association model; and when an abnormal signal of the drone is received, establishing a target escape plan for the drone based on the abnormal signal and the lifting information of the escape point, assisting the drone in escaping, and improving the survival rate and safety of the drone in abnormal situations.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned aerial vehicles, and in particular to an escape strategy optimization method, system and electronic equipment for unmanned aerial vehicles. Background Art

[0002] A drone may encounter various abnormal situations during a mission. At this time, the process of returning or descending according to its position in the mission and the different abnormal situations it faces is called escape.

[0003] When a drone escapes, the general operation is to automatically turn on obstacle avoidance and hover or descend. If an obstacle is encountered during the descent, the drone will continue to hover until the operator intervenes to manually remotely control the drone to leave, or the drone runs out of power and falls.

[0004] Therefore, it is necessary to propose an escape strategy optimization method, system and electronic equipment for UAVs. Summary of the invention

[0005] The present specification provides an escape strategy optimization method, system and electronic device for a drone, which determines an escape point and the lifting and lowering information associated with the escape point in advance, so that when an abnormal signal of the drone is received, a target escape plan of the drone is established based on the abnormal signal and the lifting and lowering information of the escape point, thereby improving the effectiveness and reliability of the escape plan.

[0006] The present application provides a method for optimizing the escape strategy of a drone using the following technical solutions, including:

[0007] Obtaining preset planning information of the drone, and searching for several escape points according to the preset planning information;

[0008] Associating lifting information with the escape point, the lifting information including two different types of execution points; judging whether the location of the escape point is an execution point based on the detailed information and obstacle information of the escape point; after the judgment is completed, determining the type of execution point to be supplemented, and supplementing the execution point for the escape point based on the association model;

[0009] When an abnormal signal of the drone is received, a target escape plan of the drone is established based on the abnormal signal and the lifting and lowering information of the escape point.

[0010] Optionally, judging whether the location of the escape point is an execution point based on the detailed information and obstacle information of the escape point includes:

[0011] Searching for detailed information of the escape point according to the type of execution point to be searched, and determining a vertical point corresponding to the escape point;

[0012] According to the escape point, the vertical point and the safety distance, a detection range corresponding to the vertical point is constructed;

[0013] In combination with the obstacle information, it is determined whether there is an obstacle within the detection range. If not, the location of the escape point is used as the execution point associated with the escape point.

[0014] Optionally, after the determination is completed, determining the type of execution point to be supplemented, and supplementing the execution point for the escape point based on the association model, includes:

[0015] Find an escape point with less than two execution points, use it as a first escape point, and determine the execution point type to be supplemented for the first escape point;

[0016] Based on the first escape point, generating a plurality of spatial areas;

[0017] In combination with a preset random strategy and the type of execution point to be supplemented, searching for a candidate execution point of the first escape point from the spatial area;

[0018] A set of all candidate execution points is obtained based on a search strategy, and a candidate execution point that is closest to the first escape point is selected as the execution point of the first escape point.

[0019] Optionally, the generating of a plurality of spatial regions based on the first escape point includes:

[0020] Defining an execution area corresponding to the first escape point based on a preset distance;

[0021] The execution area is divided according to a preset level to generate a plurality of spatial areas.

[0022] Optionally, the generating of a plurality of spatial regions based on the first escape point includes:

[0023] Based on the preset planning information, twelve-level octree partitioning is performed to obtain a number of partitioning information;

[0024] Find the nearest corner point around the first escape point;

[0025] Taking the corner point as the center and based on a preset distance, determining an execution area corresponding to the first escape point; and using the division information in the execution area as a spatial area.

[0026] Optionally, the combining of a preset random strategy and the type of execution point to be supplemented to search for a candidate execution point of the first escape point from the spatial area includes:

[0027] Determine an initial level according to a preset random strategy, and match a search strategy based on the initial level; the initial level includes one of level A, level B, and level C, wherein level A < level B < level C;

[0028] Find the spatial region corresponding to the initial level, and randomly select a spatial region therefrom as a candidate spatial region;

[0029] Determining a matching condition according to the type of the execution point to be supplemented;

[0030] In combination with the search strategy and the matching condition, a point to be tested is searched from the selected spatial area; and it is determined by the matching condition whether the point to be tested is a candidate execution point corresponding to the first escape point.

[0031] Optionally, also include:

[0032] Find the first execution point corresponding to the second escape point;

[0033] Finding a second execution point corresponding to an escape point adjacent to the second escape point; wherein the first execution point and the second execution point are of the same type;

[0034] It is determined whether the distance between the first execution point and the second execution point is less than a preset distance, and if so, the second execution point is used as a new first execution point.

[0035] The present application provides a UAV escape strategy optimization system that adopts the following technical solutions, including:

[0036] An acquisition module is used to acquire preset planning information of the drone and search for several escape points according to the preset planning information;

[0037] An associating module, used to associate lifting information with the escape point, wherein the lifting information includes two different types of execution points;

[0038] The plan generation module is used to establish a target escape plan for the drone based on the abnormal signal and the lifting and lowering information of the escape point when an abnormal signal from the drone is received.

[0039] Optionally, the association module includes:

[0040] A first association submodule is used to determine whether the location of the escape point is an execution point based on the detailed information and obstacle information of the escape point;

[0041] A second association submodule is used to determine the type of execution point to be supplemented after the judgment is completed, and to supplement the execution point for the escape point based on the association model;

[0042] Optionally, the first association submodule includes:

[0043] A vertical point determination unit, used to search for detailed information of the escape point according to the execution point type to be searched, and determine the vertical point corresponding to the escape point;

[0044] A detection range construction unit, used to construct a detection range corresponding to the vertical point according to the escape point, the vertical point and the safety distance;

[0045] The first association unit is used to determine whether there is an obstacle in the detection range in combination with the obstacle information, and if not, use the location of the escape point as an execution point for association with the escape point.

[0046] Optionally, the second association submodule includes:

[0047] An escape point search unit, used to search for an escape point with less than two execution points, use it as a first escape point, and determine a type of execution point to be supplemented for the first escape point;

[0048] A space region generating unit, configured to generate a plurality of space regions based on the first escape point;

[0049] A candidate execution point determination unit, configured to search for a candidate execution point of the first escape point from the spatial area in combination with a preset random strategy and the type of the execution point to be supplemented;

[0050] The selection unit is used to obtain a set of all candidate execution points based on a search strategy, and select a candidate execution point that is closest to the first escape point as an execution point of the first escape point.

[0051] Optionally, the space region generating unit includes:

[0052] A first limiting subunit is used to limit the execution area corresponding to the first escape point based on a preset distance;

[0053] The first division subunit is used to divide the execution area according to a preset level to generate a plurality of spatial areas.

[0054] Optionally, the space region generating unit includes:

[0055] The second partitioning subunit is used to perform twelve-level octree partitioning based on preset planning information to obtain a plurality of partitioning information;

[0056] A corner point search subunit, used to search for the nearest corner point around the first escape point;

[0057] The second limiting subunit is used to determine the execution area corresponding to the first escape point based on a preset distance with the corner point as the center; and use the division information in the execution area as the spatial area.

[0058] Optionally, the unit for determining the execution point to be selected includes:

[0059] A matching subunit, configured to determine an initial level according to a preset random strategy, and match a search strategy based on the initial level; the initial level includes one of level A, level B, and level C, wherein level A < level B < level C;

[0060] A randomly selected subunit is used to find the spatial region corresponding to the initial level, and randomly select a spatial region therefrom as a to-be-selected spatial region;

[0061] A matching condition determination subunit, used to determine a matching condition according to the type of execution point to be supplemented;

[0062] The candidate execution point search subunit is used to search for a candidate execution point from the candidate space area in combination with the search strategy and the matching condition; and determine whether the candidate execution point is the candidate execution point corresponding to the first escape point through the matching condition.

[0063] Optionally, it also includes: a point multiplexing module;

[0064] Optionally, the point multiplexing module includes:

[0065] A first execution point search submodule, used to search for a first execution point corresponding to a second escape point;

[0066] A second execution point search submodule, used to search for a second execution point corresponding to an escape point adjacent to the second escape point; wherein the first execution point and the second execution point are of the same type;

[0067] The judging submodule is used to judge whether the distance between the first execution point and the second execution point is less than a preset distance, and if so, take the second execution point as a new first execution point.

[0068] This specification also provides an electronic device, wherein the electronic device includes:

[0069] processor; and,

[0070] A memory storing computer executable instructions, which when executed cause the processor to perform any of the above methods.

[0071] The present specification also provides a computer-readable storage medium, wherein the computer-readable storage medium stores one or more programs, and when the one or more programs are executed by a processor, any of the above methods is implemented.

[0072] In the present application, by obtaining the preset planning information of the drone, several escape points are searched according to the preset planning information; the lifting information is associated with the escape point, and the lifting information includes two different types of execution points; wherein, based on the detailed information and obstacle information of the escape point, it is judged whether the location of the escape point is an execution point; after the judgment is completed, the type of execution point to be supplemented is determined, and the execution point is supplemented for the escape point based on the association model; when the abnormal signal of the drone is received, the target escape plan of the drone is established based on the abnormal signal and the lifting information of the escape point, to assist the drone in escaping, and improve the survival rate and safety of the drone in abnormal situations. BRIEF DESCRIPTION OF THE DRAWINGS

[0073] Figure 1 A schematic diagram of the principle of an escape strategy optimization method for a drone provided in an embodiment of this specification;

[0074] Figure 2 A flowchart of step S223-4 of a method for optimizing the escape strategy of a drone provided in an embodiment of this specification;

[0075] Figure 3 Another flowchart diagram of step S223-4 of a method for optimizing the escape strategy of a drone provided in an embodiment of this specification;

[0076] Figure 4 Another flowchart of step S223-4 of a method for optimizing the escape strategy of a drone provided in an embodiment of this specification;

[0077] Figure 5 A schematic diagram of a route for optimizing a method for escaping a drone provided in an embodiment of this specification;

[0078] Figure 6 A schematic diagram of the structure of an escape strategy optimization system for a drone provided in an embodiment of this specification;

[0079] Figure 7 A schematic diagram of the structure of an electronic device provided in an embodiment of this specification;

[0080] Figure 8 A schematic diagram of a computer-readable medium provided for an embodiment of this specification. DETAILED DESCRIPTION

[0081] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art can think of other obvious variations. The basic principles of the present invention defined in the following description can be applied to other embodiments, variations, improvements, equivalents, and other technical solutions that do not deviate from the spirit and scope of the present invention.

[0082] Exemplary embodiments of the present invention will now be described more fully with reference to the accompanying drawings. However, exemplary embodiments can be implemented in a variety of forms, and should not be construed as limiting the present invention to the embodiments set forth herein. On the contrary, providing these exemplary embodiments enables the present invention to be more comprehensive and complete, and is more convenient for fully conveying the inventive concept to those skilled in the art. The same reference numerals in the figures represent the same or similar elements, components or parts, and thus their repeated description will be omitted.

[0083] Under the premise of being consistent with the technical concept of the present invention, the features, structures, characteristics or other details described in a specific embodiment do not exclude that they can be combined in one or more other embodiments in a suitable manner.

[0084] In the description of specific embodiments, the features, structures, characteristics or other details described in the present invention are intended to enable those skilled in the art to fully understand the embodiments. However, it does not exclude that those skilled in the art can practice the technical solutions of the present invention without one or more of the specific features, structures, characteristics or other details.

[0085] The flowcharts shown in the accompanying drawings are only exemplary and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps can be decomposed, and some operations / steps can be combined or partially combined, so the actual execution order may change according to actual conditions.

[0086] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities may be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0087] The term "and / or" or "and / or" includes all combinations of any one or more of the associated listed items.

[0088] Figure 1 A schematic diagram of the principle of a method for optimizing the escape strategy of a drone provided in an embodiment of this specification, the method comprising:

[0089] S1 obtains preset planning information of the drone, and searches for several escape points according to the preset planning information;

[0090] S2 is the lifting information associated with the escape point, and the lifting information includes two different types of execution points; wherein, based on the detailed information and obstacle information of the escape point, it is judged whether the location of the escape point is an execution point; after the judgment is completed, the type of execution point to be supplemented is determined, and the execution point is supplemented for the escape point based on the association model;

[0091] S3: when an abnormal signal of the drone is received, a target escape plan of the drone is established based on the abnormal signal and the lifting and lowering information of the escape point.

[0092] The application of drones in military, commercial photography, agriculture, environmental monitoring, disaster relief and other fields has demonstrated its unique advantages and value. However, drones may encounter some abnormal situations during flight or inspection, which may threaten their mission execution and safety, such as:

[0093] Unstable or lost signal: Drones rely on wireless communication for remote control and data transmission. When the signal between the drone and the remote controller becomes unstable or lost, the drone may face the risk of losing control.

[0094] Low battery: The flight time of the drone is limited by the performance and capacity of the battery. In the case of severe low battery, the drone may crash due to exhaustion.

[0095] Weather changes: The drone may encounter sudden bad weather during flight, such as strong winds, heavy rain, lightning, etc. If it encounters bad weather, the drone may face the risk of unstable flight or loss of control.

[0096] Mechanical failure: The mechanical parts of the drone may fail when running for a long time or being impacted by external forces, such as motor failure, propeller damage, etc., which may cause the drone to fly unsteadily or lose control.

[0097] Encountering obstacles: When flying in a complex environment, the drone may collide with trees, buildings or other obstacles. If you do not avoid them in time, the drone may collide with the obstacles.

[0098] The above abnormal conditions can easily cause the drone to lose control or even touch nearby live equipment, resulting in damage to the equipment or the drone and causing serious accidents.

[0099] Based on this, the present invention proposes a method for generating an escape strategy of a drone, and the method comprises:

[0100] S1 obtains preset planning information of the drone, and searches for several escape points according to the preset planning information;

[0101] S11 determines preset planning information based on the flight target;

[0102] Before the drone flies, it will plan the path according to the target mission and generate preset planning information;

[0103] Among them, the path planning according to the target task can be manually planned by the user of the cruise system, or can be obtained through a provided path planning algorithm, which is not specifically limited here.

[0104] In order to improve the flight safety and mission execution efficiency of drones, the actual situation near the original route needs to be surveyed before the drone performs the target mission. Specifically, before the drone performs the mission, it obtains the location and shape information of obstacles around the original route. Obstacles include: terrain, buildings, trees, wires, and other objects that may affect flight.

[0105] Based on the position and shape information of the obstacle, a point cloud coordinate system is constructed, and the obstacle is spatially located in the form of points to form an obstacle point cloud as obstacle information. The obstacle information includes several obstacle points. Each obstacle point contains its position information in three-dimensional space, and multiple obstacle points together describe the shape and position of an obstacle.

[0106] In one embodiment of the present specification, the preset planning information includes an original route, obstacle information, and original points on the original route.

[0107] The original route is the route pre-planned by the drone before it performs a mission.

[0108] Original points are pre-added points used to mark specific location information. Original points include at least one of important waypoints and other waypoints. Among them, important waypoints are used to mark important points on the original route, such as mission points, transition points, turning points, etc. Other waypoints are other waypoints on the route.

[0109] S12 extracts the original point from the preset planning information; generates an escape point according to the original point and the preset interval;

[0110] S12-1 extracts the original route segment between two adjacent original points;

[0111] S12-2 adding an interval point on the original route segment based on the relationship between the Euclidean distance d between the two original points and the preset interval;

[0112] Specifically, if the Euclidean distance d between the two original points is less than or equal to the preset interval, no interval point is added to the original route segment;

[0113] If the Euclidean distance d between two original points is greater than the preset interval, an interval point is added to the original route segment for each interval of the preset length; Number of interval points Ceil is rounded up; floor is rounded down.

[0114] That is to say, the original route segment is divided into a plurality of first route segments by the interval points; the lengths of the first path segments are equal and are all preset lengths; that is, the interval points on the original route segment are equidistantly arranged.

[0115] Traverse all the original route segments on the original route, perform the above operations, and increase the interval points.

[0116] S12-3 summarizes all original points and all interval points to obtain a set of escape points.

[0117] The escape point includes one or more of a waypoint, a turning point and a separation point.

[0118] S2 is the associated lifting information of the escape point;

[0119] When a drone encounters an abnormality during flight, the general operation is: first stop, and then continue to follow the original route to a nearby escape point. Since the escape point is located on the original route, there is basically no possibility that a malfunction occurs on the way to the escape point and the escape point cannot be reached.

[0120] After the drone reaches the escape point, it decides whether to take off and return or land on the ground based on the lift information. Therefore, it is necessary to determine the lift information corresponding to the escape point in advance to ensure that the drone can "escape" smoothly when encountering an abnormality at any position during the flight mission.

[0121] The lifting information includes two different types of execution points; the execution point types include return execution points and landing execution points. In other words, the lifting information includes return execution points and landing execution points, that is, each escape point is associated with a return execution point and a landing execution point.

[0122] S21, based on the detailed information and obstacle information of the escape point, determining whether the location of the escape point is an execution point;

[0123] S211 searches for detailed information of the escape point according to the type of execution point to be searched, and determines a vertical point corresponding to the escape point;

[0124] When the execution point to be searched is the return execution point, the detailed information of the escape point includes the location of the escape point, the safety height h up and the first safety distance r up . According to the location of the escape point and the safety height h up Determine the vertical point corresponding to the return execution point. At this time, the vertical point refers to the vertical rise of the drone from the escape point to the safe height h up The position reached at the time.

[0125] When the execution point to be searched is the landing execution point, the detailed information of the escape point includes the location of the escape point and the second safety distance r down The vertical point corresponding to the landing execution point is determined according to the location of the escape point. At this time, the vertical point refers to the position reached by the drone when it descends vertically from the escape point to the ground.

[0126] S212 constructs a detection range corresponding to the vertical point according to the escape point, the vertical point and the safety distance;

[0127] S213 determines whether there is an obstacle in the detection range in combination with the obstacle information, and if not, uses the location of the escape point as an execution point associated with the escape point.

[0128] Determine whether there is an obstacle point within the range to be measured. If yes, it is determined that there is an obstacle within the range to be measured; if not, it is determined that there is no obstacle within the range to be measured.

[0129] The safety altitude is a manually set parameter, which is set according to the specific scenario. At the safety altitude, the drone can fly freely without any collision.

[0130] Safety distance: When the drone is flying, there must be no radius of obstacles around the drone. The safety height is set according to the specific scenario.

[0131] In one embodiment of the present specification, the safety distance includes a first safety distance r up and the second safety distance r down .

[0132] In the process of verifying whether the location of the escape point itself can be used as an execution point, if there is no obstacle in the vertical ascending direction of the escape point, the location of the escape point is the return execution point, and the escape point and the return execution point coincide. If there is no obstacle in the vertical descending direction of the escape point, the location of the escape point is the landing execution point, and the escape point and the landing execution point coincide.

[0133] It is easy to understand that if there is no obstacle in the vertical ascending direction of the escape point, and there is no obstacle in the vertical descending direction of the escape point, the escape point, the corresponding return execution point, and the corresponding landing execution point coincide with each other.

[0134] In one embodiment of the present specification, when determining whether the location of the escape point is a return execution point, the steps specifically include:

[0135] S211-A When the execution point to be searched is the return execution point, according to the location of the escape point and the safety height h up Determine the first vertical point;

[0136] S212-A is based on the first vertical point, escape point and first safety distance r up , construct the first range to be tested;

[0137] According to the first vertical point and the first safety distance r up , determine the upper reference point; where the upper reference point is the first safety distance r vertically upward from the first vertical point up The position reached at the time.

[0138] According to the escape point and the first safe distance r up , determine the lower reference point; where the lower reference point is the first safe distance r vertically downward from the escape point up The position reached at the time.

[0139] That is, the upper reference point, the first vertical point, the escape point and the lower reference point are coaxially arranged, and from top to bottom they are the upper reference point, the first vertical point, the escape point and the lower reference point.

[0140] The straight line where the upper reference point and the lower reference point are located is the central axis, the upper reference point is the center of the upper bottom surface, and the lower reference point is the center of the lower bottom surface. The first safety distance r up As the radius, a cylindrical space is constructed as the first measurement range.

[0141] S213-A determines whether there is an obstacle within the first detection range, and based on the determination result, determines whether the location of the escape point is a return execution point:

[0142] If there is an obstacle point within the first test range, it is determined that the location of the escape point cannot be used as the return execution point of the escape point:

[0143] If there is no obstacle point within the first test range, it means that: in the vertical path from the escape point to the upper safe height, any point can be guaranteed to have no obstacles within the first safe distance.

[0144] Therefore, if there is no obstacle within the first detection range, it is determined that the return operation can be performed at the escape point, and the location of the escape point is used as the return execution point associated with the escape point.

[0145] In another embodiment of the present specification, when determining whether the location of the escape point is a landing execution point, the steps specifically include:

[0146] S211-B determines the second vertical point according to the position of the escape point;

[0147] S212-B is based on the escape point, the second vertical point and the second safety distance r down , construct the second range to be tested;

[0148] According to the escape point and the second safety distance r down , determine the upper reference point; where the upper reference point is the second safety distance r vertically upward from the escape point down The position reached at the time.

[0149] That is, the upper reference point, the escape point and the second vertical point are coaxially arranged, and from top to bottom they are the upper reference point, the escape point and the second vertical point.

[0150] The straight line between the above reference point and the second vertical point is the central axis, the above reference point is the center of the upper base, the second vertical point is the center of the lower base, and the second safety distance r is the center of the lower base. down With θ as the radius, a cylindrical space is constructed as the second measurement range.

[0151] S213-B determines whether there is an obstacle within the second detection range, and based on the determination result, determines whether the location of the escape point is a landing execution point:

[0152] If there is an obstacle point within the second test range, it is determined that the location of the escape point cannot be used as the landing execution point of the escape point:

[0153] If there is no obstacle point within the second test range, it means that: in the vertical path from the escape point to the road surface below, it can be guaranteed that there is no obstacle within the second safety distance at any point.

[0154] Therefore, if there is no obstacle within the second detection range, it is determined that the landing operation can be performed at the escape point, and the location of the escape point is used as the landing execution point associated with the escape point.

[0155] In the embodiments of the present specification, the escape point can also be marked to determine whether the escape point coincides with a specific execution point (return execution point and / or landing execution point), and the specific marking method will not be repeated here.

[0156] As mentioned above, the present invention performs step S21 twice on the escape point to determine whether the location of the escape point can be used as a return execution point and / or a landing execution point, and then the following four situations can be obtained:

[0157] (1) Some escape points can be used as both return execution points and landing execution points; that is, the escape point coincides with the corresponding return execution point and the corresponding landing execution point;

[0158] (2) Some escape points can only be used as return execution points, but not as landing execution points; that is, the escape point only coincides with the corresponding return execution point;

[0159] (3) Some escape points can only be used as landing execution points, but not as return execution points; that is, the escape point only coincides with the corresponding landing execution point;

[0160] (4) The location of some escape points can neither be used as return execution points nor as landing execution points, that is, the escape points do not coincide with the corresponding execution points (return execution points and landing execution points).

[0161] When the locations of some escape points cannot be directly used as return execution points and / or landing execution points, it is necessary to further match the return execution points and / or landing execution points for the corresponding escape points, so that each escape point is associated with a return execution point and a landing execution point, so as to increase the escape probability of the drone.

[0162] S22, after the judgment is completed, determining the type of execution point to be supplemented, and supplementing the execution point for the escape point based on the association model;

[0163] If the location of the escape point can be used as a return execution point and a landing execution point, the lift information of the escape point is already complete, and there is no need to supplement the execution point. Therefore, according to the current execution point association of the first escape point, the type of execution point to be supplemented is determined, and then the execution point is supplemented.

[0164] S221 searches for an escape point with less than two execution points, takes the escape point as a first escape point, and determines the execution point type to be supplemented for the first escape point;

[0165] In one embodiment of the present specification, the first escape point includes: an escape point associated with only one execution point and / or an escape point associated with 0 execution point.

[0166] Determine the position coordinates (x, y, z) of the first escape point p;

[0167] If the location of the first escape point can only be used as a return execution point, a landing execution point needs to be added for the first escape point, that is, the execution point type to be added for the first escape point is a landing execution point;

[0168] If the location of the first escape point can only be used as a landing execution point, a return execution point needs to be added for the first escape point, that is, the execution point type to be added for the first escape point is a return execution point;

[0169] If the location of the first escape point cannot be used as a return execution point and a landing execution point, it is necessary to add a return execution point and a landing execution point for the first escape point. That is to say, the execution point types to be added for the first escape point are the return execution point and the landing execution point. At this time, two operations of adding execution points are required.

[0170] S222 generates a plurality of spatial regions based on the first escape point;

[0171] In outdoor scenarios, especially in the overall environment of a power station, the entire power station covers several hundred meters, but the operation of supplementing associated execution points only involves the area around the escape point. Therefore, by determining the execution area corresponding to the first escape point, unnecessary environments can be eliminated to increase computing efficiency, so that the entire process can be completed in a very short time.

[0172] In one embodiment of the present specification, a spatial region is generated based on steps S222 - 1 to S222 - 2 ;

[0173] S222-1 defines an execution area corresponding to the first escape point based on a preset distance;

[0174] In order to find the execution point within the preset distance i around the first escape point p0(x,y,z), first cut out the space of [x-2i,x+2i] on the x-axis, [y-2i,y+2i] on the y-axis, and [z-2i,z+2i] on the z-axis in the complete point cloud space to obtain the execution range, which contains the corresponding obstacle point information. The execution range is centered on the first escape point p0(x,y,z) and is a orig is a cube with a side length of orig =4i.

[0175] S222-2 divides the execution area according to a preset level to generate a plurality of spatial areas.

[0176] Default level T max ∈N, and T≥0. The level corresponding to the execution area is 0. In one embodiment of the present specification, the preset level is preferably 7. The preset distance i is preferably 10 meters, and the side length a orig Preferably 40 meters.

[0177] In one embodiment of the present specification, recursive partitioning is performed starting from the execution region.

[0178] In the first division, the execution area is equally divided into eight smaller spatial areas. Specifically, the eight spatial areas are arranged in a 2×2×2 cubic grid. In each subsequent division, each spatial area obtained in the previous division is equally divided into eight smaller spatial areas; the above process is repeated until the preset level is reached. In the next division of the spatial area, the spatial area includes 8 non-overlapping sub-space areas, and the number of spatial areas corresponding to the current level T is 8. T The spatial region n of level T is represented by Q (T,n) , where T∈N and 0≤T≤T max ; n∈N, and 1≤n≤8. The numbering order of the 8 area ranges in the same level is not limited here. The spatial shape of the space area is a cube.

[0179] Each level corresponds to a different division accuracy; the division accuracy corresponding to the current level includes: the side length of the area range corresponding to the current level. In other words, the division accuracy corresponding to the current level T is a T for

[0180] To facilitate finding the execution point, a T ≤Preset accuracy. Preferably, the preset accuracy is 0.32 meters.

[0181] When searching for execution points, first of all, it is necessary to ensure that there are no obstacles within the preset safety distance around the drone. In the application scenario of this manual, the preset safety distance is 2 meters. Since the accuracy of all the lowest area ranges is within 0.32 meters, which is much larger than the preset safety distance, the current division accuracy is sufficient for searching the return (landing) execution point.

[0182] It is easy to understand that if the corresponding point cloud area (a orig If the safety distance requirement is greater than 100%, a higher preset level should be set to make the deepest level division accuracy a T Meet the preset accuracy requirements.

[0183] In another embodiment of the present specification, a seven-level octree is used to divide the region range.

[0184] Detect obstacle points in the execution range and associate the spatial region with the obstacle points within the spatial region.

[0185] In another embodiment of the present specification, a spatial region is generated based on steps S222-3 to S222-5;

[0186] S222-3 performing twelve-level octree partitioning based on the preset planning information to obtain a plurality of partitioning information;

[0187] The division information is saved in the form of a file. Step S222-3 may be completed in advance, and once completed, it can be used when subsequently determining the lifting information of multiple escape points.

[0188] S222-4 searching for the nearest corner point around the first escape point;

[0189] When it is necessary to determine the candidate execution point of the first escape point p0;

[0190] Build an octree around the first escape point p0, and directly take the corner point p on the last leaf node that is closest to the first escape point p0. ′ ;

[0191] S222-5 determines the execution area corresponding to the first escape point based on the preset distance and the corner point as the center; and uses the division information in the execution area as the spatial area.

[0192] Specifically, p ′ The octree structure in the cube with a center and a side length of 4i is directly extracted from the previously saved file.

[0193] This specification provides two methods for dividing the spatial region, which are performed according to the actual situation in operation. If the accuracy of the result is required to be higher, the spatial region is generated based on steps S222-1 to S222-2; if the time requirement is higher, the spatial region is generated based on steps S222-3 to S222-5.

[0194] S223 combines a preset random strategy and the type of the execution point to be supplemented, searching for a candidate execution point for the first escape point in the spatial area;

[0195] S223-1 Determine the initial level T according to the preset random strategy ω , based on the initial level T ω Matching search strategy;

[0196] The initial level includes one of level A, level B, and level C, wherein level A<level B<level C;

[0197] Among them, T ω ∈N, and 0≤T ω ≤T max In one embodiment of the present specification, Tω \in{A,B,C}. That is, the initial level T ω It can be one of A, B, or C.

[0198] That is, the probability that the initial level is A according to the preset random strategy is 35%; the probability that the initial level is B according to the preset random strategy is 35%; the probability that the initial level is C according to the preset random strategy is 30%.

[0199] When the initial level is level A, the first search strategy is matched.

[0200] When the initial level is level B, the second search strategy is matched.

[0201] When the initial level is level C, the third search strategy is matched.

[0202] S223-2 Find the initial level T ω Corresponding spatial regions, randomly select a spatial region from them as the candidate spatial region;

[0203] S223-3 determining a matching condition according to the type of execution point to be supplemented;

[0204] In one embodiment of the present specification, the matching condition includes: there is no obstacle point in the test range of the test point.

[0205] Specifically, if the execution point type to be supplemented is a return execution point, the matching condition includes: there is no obstacle point in the third test range of the test point. up Determine the third vertical point; according to the third vertical point, the point to be measured and the first safety distance r up , construct a third range to be tested; the construction process of the third range to be tested is similar to the construction process of the first range to be tested, and will not be repeated here.

[0206] If the execution point type to be supplemented is a landing execution point, the matching condition includes: there is no obstacle point in the fourth test range of the test point. The fourth vertical point is determined according to the position of the escape point; the fourth vertical point is determined according to the test point, the fourth vertical point and the second safety distance r down , construct a fourth range to be tested; the construction process of the fourth range to be tested is similar to the construction process of the aforementioned second range to be tested, and will not be repeated here.

[0207] S223-4 searches for a point to be tested in the selected spatial area in combination with the search strategy; and determines whether the point to be tested is a selected execution point corresponding to the first escape point through the matching condition.

[0208] S223-4-1 When the initial level is level A, select a candidate execution point in combination with the first search strategy;

[0209] like Figure 2 As shown, in one embodiment of the present specification, level A is 4; the division accuracy corresponding to level 4 is 2.5 meters.

[0210] (1-1) taking the adjacent spatial region and the neighboring spatial region of the selected spatial region as the spatial region to be tested; executing step (1-2);

[0211] The adjacent space region has a face overlap with the space region to be selected. The adjacent space region includes: the space regions above, below, to the left, to the right, in front of, and behind the space region to be selected.

[0212] The neighboring spatial regions overlap with the corners of the spatial region to be selected. The neighboring spatial regions include: the spatial regions of the front upper left, front upper right, front lower left, front lower right, rear upper left, rear upper right, rear lower left, and rear lower right of the spatial region to be selected.

[0213] The adjacent spatial region has the same division accuracy as the spatial region to be selected. The neighboring spatial region has the same division accuracy as the spatial region to be selected.

[0214] (1-2) Randomly select a point P to be tested from the selected space area α , execute steps (1-3);

[0215] That is to say, when there is a non-empty spatial region in the spatial region to be tested, further operations are required.

[0216] (1-3) Determine whether the spatial area to be measured meets the range condition; if so, execute step (1-4); otherwise, execute step (1-5);

[0217] The range condition includes: there are no obstacles in all the spatial regions to be tested. If there are no obstacles in the spatial region, it means that the spatial region is empty; if there are obstacles in the spatial region, it means that the spatial region is a non-empty spatial region.

[0218] (1-4) Determine whether the point to be tested is a candidate execution point according to the matching conditions. After the determination is completed, end the search.

[0219] Specifically, if the space to be tested meets the range condition, it means that there is no non-empty space to be tested around the space to be selected, that is, there is no obstacle point in the 2.5-meter space around the space to be selected. α Whether it is a candidate execution point, after the judgment is completed, the search ends.

[0220] That is to say, if there is no obstacle point in the test range of the test point, the test point will be used as the selected execution point and the search will be terminated; if there is an obstacle point in the test range of the test point, the test point will not be used as the selected execution point this time, that is, the test point will be discarded and the search will be terminated.

[0221] (1-5) Based on the splitting conditions and all the test space areas with obstacle points, determine the new test space area; combined with the test point P α , determine whether the new space area to be tested meets the distance condition;

[0222] In one embodiment of the present specification, a spatial region to be tested with an obstacle point is searched, and a sub-space region of the spatial region to be tested with an obstacle point is used as a set of first spatial regions, where there must be at least one non-empty spatial region. All first spatial regions are aggregated as new spatial regions to be tested; that is, the spatial region to be tested with an obstacle point corresponds to a level of 4; and the new spatial region to be tested corresponds to a level of 5.

[0223] The distance conditions include: the shortest distance between the space area to be measured and the point to be measured ≥ the preset safety distance.

[0224] If the space area to be tested meets the distance condition, that is, the shortest distance between the boundary of the space area to be tested and the point to be tested ≥ the preset safety distance, it means that although there are obstacles around the space area to be tested, the point to be tested P α The distance to the obstacle point is ≥ the preset safety distance. At this time, execute steps (1-4) and determine the test point P according to the matching conditions. α Whether it is a candidate execution point, after the judgment is completed, the search ends.

[0225] If the space area to be measured does not meet the distance condition, determine whether the new space area to be measured corresponds to the preset level. If not, loop through steps (1-5) until the new space area to be measured corresponds to the preset level.

[0226] If the new space area to be tested corresponds to the preset level, then search for the point P to be tested in the new space area to be tested. α The nearest obstacle point is determined to determine whether the nearest obstacle point meets the distance condition; if so, execute steps (1-4) to determine the measured point P according to the matching condition. α Is it a candidate execution point? After the judgment is completed, the search ends; if not, the test point P is discarded. α , and end this search.

[0227] Specifically, if the spatial area to be tested does not meet the distance condition, and the new spatial area to be tested at this time does not have a corresponding preset level, then based on the splitting condition and the spatial area to be tested with obstacle points, the subspace area of ​​the spatial area to be tested with obstacle points is used as the new spatial area to be tested, and the corresponding level of the new spatial area to be tested is 6.

[0228] Determine whether the new space area to be tested meets the distance condition; if the space area to be tested meets the distance condition, determine the test point P according to the matching condition α Whether it is a candidate execution point, after the judgment is completed, the search is terminated; if the space area to be tested does not meet the distance condition, and the new space area to be tested at this time does not correspond to the preset level, then based on the splitting condition and the space area to be tested with obstacles, a new space area to be tested is determined; the level corresponding to the new space area to be tested is 7.

[0229] Determine whether the new space area to be tested meets the distance condition; if the space area to be tested meets the distance condition, determine the test point P according to the matching condition α Is it a candidate execution point? After the judgment is completed, the search ends. If the space area to be tested does not meet the distance condition, since the new space area to be tested at this time already corresponds to the preset level, the new space area to be tested is searched for the point P to be tested. α The nearest obstacle point is calculated to find the distance between the obstacle point and the point to be measured P. α The shortest distance is determined to determine whether the shortest distance is greater than or equal to the preset safety distance; if so, the point to be measured P is determined according to the matching conditions. α Is it a candidate execution point? After the judgment is completed, the search ends; if not, the test point P is discarded. α , and end this search.

[0230] S223-4-2 When the initial level is level B, select a candidate execution point in combination with the second search strategy;

[0231] like Figure 3 As shown, in one embodiment of the present specification, level B is 5; the division accuracy corresponding to level 5 is 1.25 meters.

[0232] (2-1) taking the adjacent spatial region and the neighboring spatial region of the selected spatial region as the spatial region to be tested; executing step (2-2);

[0233] The adjacent spatial region has the same division accuracy as the spatial region to be selected. The neighboring spatial region has the same division accuracy as the spatial region to be selected.

[0234] (2-2) Randomly select a point P to be tested from the selected space area β , execute steps (2-3);

[0235] (2-3) Determine whether the spatial area to be measured meets the range condition; if the spatial area to be measured meets the range condition, execute step (2-4); otherwise, execute step (2-7).

[0236] If the space area to be tested meets the range condition, it means that there are no obstacle points in the space area to be tested. In one embodiment of the present specification, the division accuracy of the 5th level is 1.25 meters, which is less than the preset safety distance. Therefore, although there is no non-empty space area to be tested around the space area to be tested, it cannot guarantee that the points in the space area to be tested meet the safety distance requirements. Therefore, it is necessary to process one layer outward.

[0237] (2-4) Determine a new spatial area to be tested based on the diffusion condition and all the spatial areas to be tested; determine whether the spatial area to be tested meets the range condition; if the spatial area to be tested meets the range condition, execute step (2-5); otherwise, execute step (2-6).

[0238] Based on the diffusion conditions and the space area to be tested, a new space area to be tested is determined, including:

[0239] Determining coverage based on a set of spatial regions to be measured;

[0240] The adjacent spatial regions and neighboring spatial regions of the spatial region to be measured are extracted, and the spatial regions outside the coverage range are taken as new spatial regions to be measured.

[0241] (2-5) Determine whether the point to be tested is a candidate execution point according to the matching condition. After the determination is completed, end the search.

[0242] Specifically, the point to be tested P is determined according to the matching conditions. β Is it a candidate execution point? If so, the test point P β As the candidate execution point, end this search; otherwise, discard the test point P β , end this search.

[0243] If the space area to be measured meets the range condition, it means that there are no obstacles in the new space area to be measured.

[0244] (2-6) Based on the splitting conditions and all the test space areas with obstacle points, determine the new test space area; combined with the test point P β , determine whether the new space area to be tested meets the distance condition;

[0245] In one embodiment of the present specification, a spatial region to be tested in which an obstacle point exists is searched, and a subspace region of the spatial region to be tested in which the obstacle point exists is used as a new spatial region to be tested; that is, the spatial region to be tested in which the obstacle point exists has a corresponding level of 5; and the new spatial region to be tested has a corresponding level of 6.

[0246] The distance conditions include: the shortest distance to the point to be measured ≥ the preset safety distance.

[0247] If the space area to be tested meets the distance condition, that is, the shortest distance between the boundary of the space area to be tested and the point to be tested ≥ the preset safety distance, it means that although there are obstacles around the space area to be tested, the point to be tested P β The distance to the obstacle point is ≥ the preset safety distance; at this time, execute step (2-5).

[0248] If the space area to be measured does not meet the distance condition, determine whether the new space area to be measured corresponds to the preset level. If not, execute (2-6) repeatedly until the new space area to be measured corresponds to the preset level. If the new space area to be measured corresponds to the preset level, then if the space area to be measured does not meet the distance condition, discard the point P to be measured. β , end this search.

[0249] (2-7) Combined with the points to be measured, determine whether the new spatial areas to be measured meet the distance conditions;

[0250] If yes, execute step (2-5); if no, execute step (2-6).

[0251] S223-4-3 When the initial level is C, select a candidate execution point in combination with the third search strategy;

[0252] like Figure 4 As shown, in one embodiment of the present specification, level C is 6; the division accuracy corresponding to level 6 is 0.625 meters.

[0253] (3-1) constructing a spatial region to be tested based on the spatial region to be selected;

[0254] The spatial region to be measured includes a first spatial region, a second spatial region and a third spatial region.

[0255] Specifically, the adjacent spatial region and the neighboring spatial region of the to-be-selected spatial region are taken as the first spatial region;

[0256] determining a second spatial region based on the diffusion condition and the first spatial region to be measured;

[0257] determining a third spatial region based on the diffusion condition and the second spatial region to be measured;

[0258] The division accuracy of each spatial area to be measured is the same.

[0259] (3-2) Determine whether the spatial area to be tested meets the range condition; if the spatial area to be tested meets the range condition, execute step (3-3), otherwise, end this search.

[0260] (3-3) Randomly select a point P to be tested from the selected space area γ , execute steps (3-4);

[0261] (3-4) determining a new spatial region to be measured based on the diffusion condition and the third spatial region, and executing step (3-5);

[0262] Based on the diffusion conditions and the third space region, a new space region to be tested is determined, including:

[0263] Determining a coverage range based on a set of third spatial regions;

[0264] The adjacent spatial regions and the neighboring spatial regions of the third spatial region are extracted, and the spatial regions outside the coverage range are taken as new spatial regions to be measured.

[0265] (3-5) Combine the points to be measured and determine whether the new spatial area to be measured meets the distance condition; if so, execute step (2-6); if not, discard the point to be measured P β , end this search.

[0266] (3-6) Determine whether the point to be tested is a candidate execution point according to the matching conditions. After the determination is completed, end the search.

[0267] S224 obtains a set of all candidate execution points based on the search strategy, and selects a candidate execution point that is closest to the first escape point as the execution point of the first escape point.

[0268] In the embodiment of the present specification, after the current search is completed, it is determined whether the execution times of step S223 reaches the preset search times. If so, the search is stopped; if not, it is determined whether the total number of execution points to be selected reaches the preset search number; if so, the search is stopped; if not, S223-S224 are continued.

[0269] As an example, the predetermined number of searches is 4000. The preset number of searches is 100.

[0270] After stopping the search, the candidate execution point closest to the escape point is selected as the execution point of the escape point.

[0271] In the present specification, if the escape point lacks an associated return execution point, the associated return execution point is determined by step S22. If the escape point lacks an associated landing execution point, the associated return execution point is determined by step S22. If the escape point lacks an associated return execution point and a landing execution point, in one embodiment of the present specification, step S22 is executed twice, wherein step S22 is executed once to determine the return execution point associated with the escape point, and step S22 is executed once to determine the landing execution point. In another embodiment of the present specification, steps S223-S224 are executed twice, wherein steps S223-S224 are executed once to determine the return execution point associated with the escape point, and steps S223-S224 are executed once to determine the landing execution point. There is no limitation on the order in which the return execution point and the landing execution point are determined.

[0272] In order to improve the layout of execution points, reduce the amount of calculation of escape plans, and improve decision-making efficiency, in one embodiment of this specification, the execution points may also be merged; specifically:

[0273] Find the first execution point corresponding to the second escape point;

[0274] Find the second execution point corresponding to the escape point adjacent to the second escape point; wherein the first execution point and the second execution point are of the same type, that is, both are return execution points, or both are landing execution points;

[0275] It is determined whether the distance between the first execution point and the second execution point is less than a preset distance. If so, the second execution point is used as a new first execution point.

[0276] Multiple escape points may correspond to one return execution point, and / or, multiple escape points may correspond to one landing execution point.

[0277] like Figure 5 As shown, the blue solid line represents the original route of the drone. There are several blue circles on the original route. The blue circles represent escape points, among which the blue solid circles represent the original points on the entire route, and the blue hollow circles represent the divided interval points. The blue circle with an upward arrow indicates that the escape point coincides with the corresponding return execution point, and the return operation can be performed at the location of the escape point; the blue circle with a downward arrow indicates that the escape point coincides with the corresponding landing execution point, and the landing operation can be performed at the location of the escape point. It is easy to understand that the blue circle with both an upward arrow and a downward arrow indicates that the escape point coincides with both the return execution point and the landing execution point, that is, the return or landing operation can be performed at the location of the escape point.

[0278] A green solid circle indicates a supplementary execution point, which does not coincide with the escape point. A green circle with an upward arrow indicates a supplementary return execution point, at which the drone can perform a return operation; a green circle with a downward arrow indicates a supplementary landing execution point, at which the drone can perform a landing operation; a green circle with both an upward and downward arrow indicates that the supplementary return execution point coincides with the supplementary landing execution point, at which the drone can perform a return or landing operation.

[0279] Each escape point must involve an up arrow and a down arrow, thereby ensuring that each escape point corresponds to a return execution point and a landing execution point.

[0280] The escape point and the supplementary execution point are connected by a green dotted line, which not only indicates the association between the escape point and the supplementary execution point, but also indicates the escape route from the escape point to the supplementary execution point. If a supplementary execution point is associated with multiple blue circles, it means that multiple escape points correspond to one execution point.

[0281] By merging similar execution points, the total number of execution points can be reduced, making the entire execution point network more streamlined and efficient. This can not only reduce maintenance costs, but also improve the utilization rate of execution points.

[0282] S3: when an abnormal signal of the drone is received, a target escape plan of the drone is established based on the abnormal signal and the lifting and lowering information of the escape point.

[0283] In one embodiment of the present specification, basic information and abnormality type of the drone are obtained according to the abnormal signal of the drone; the basic information of the drone includes: the current location of the drone and the remaining power of the drone;

[0284] Search for the closest escape point to the current location of the drone as the target escape point;

[0285] Determine the escape plan of the drone based on the type of abnormality of the drone and the remaining power of the drone;

[0286] Specifically, the abnormal types include: unstable signal, insufficient power, weather changes, and mechanical failure.

[0287] If the abnormal type of the drone is low battery, weather change and mechanical failure, a target escape plan is constructed based on the current position of the drone, the target escape point and the landing execution point corresponding to the target escape point.

[0288] Specifically, in the preset planning information, the route from the current position of the drone to the target escape point is extracted as the first escape line segment, and the route from the target escape point to the landing execution point is taken as the second escape line segment. The first escape line segment and the second escape line segment are merged in sequence to determine the escape path as the target escape plan. This ensures that the drone can safely and quickly reach the target escape point and land in abnormal situations, thereby minimizing losses and risks.

[0289] If the abnormal type of the drone is unstable signal, a first escape path is constructed based on the current position of the drone, the target escape point, and the return execution point corresponding to the target escape point;

[0290] Specifically, in the preset planning information, the route from the current position of the drone to the target escape point is extracted as the first escape segment; the route from the starting position and the target escape point is extracted as the second escape segment; the route from the target escape point to the return execution point is used as the third escape segment; the first escape segment, the third escape segment and the second escape segment are merged in sequence to determine the first escape path.

[0291] Evaluate the required power according to the length of the first escape path; determine the required power and the remaining power of the drone;

[0292] If the remaining power of the drone is greater than or equal to the required power, the first escape path will be used as the target escape plan.

[0293] If the remaining power of the drone is less than the required power, it means that the remaining power of the drone is not enough to support the drone to return to the nest. At this time, based on the current position of the drone, the target escape point, and the landing execution point corresponding to the target escape point, a target escape plan is constructed. Of course, the farthest target landing execution point that the drone can reach can also be determined based on the remaining power of the drone, so that the staff can pick up the drone in time.

[0294] The present invention obtains the planning information of the drone in advance and searches for escape points based on the information, so that the drone can respond quickly when encountering an emergency. This pre-planning method greatly reduces the time for the drone to perform real-time calculation and analysis in an emergency, thereby improving the success rate of escape.

[0295] When the number of execution points associated with an escape point is insufficient, the system can supplement the execution points based on the association model, ensuring that each escape point has sufficient execution point options, further improving the flexibility and success rate of escape.

[0296] In addition, when receiving abnormal signals from drones, the system can combine the lifting and lowering information of the escape point to formulate a target escape plan for the drone. This comprehensive consideration makes the escape plan more in line with the actual situation and improves the effectiveness and safety of the escape.

[0297] Figure 6 A schematic diagram of the structure of an escape strategy optimization system for a drone provided in an embodiment of this specification, the system comprising:

[0298] The acquisition module 601 is used to acquire the preset planning information of the drone and search for a number of escape points according to the preset planning information;

[0299] An association module 602 is used to associate lifting information with the escape point, wherein the lifting information includes two different types of execution points;

[0300] The plan generation module 603 is used to establish a target escape plan for the drone based on the abnormal signal and the lifting and lowering information of the escape point when an abnormal signal from the drone is received.

[0301] Optionally, the association module 602 includes:

[0302] A first association submodule is used to determine whether the location of the escape point is an execution point based on the detailed information and obstacle information of the escape point;

[0303] A second association submodule is used to determine the type of execution point to be supplemented after the judgment is completed, and to supplement the execution point for the escape point based on the association model;

[0304] Optionally, the first association submodule includes:

[0305] A vertical point determination unit, used to search for detailed information of the escape point according to the execution point type to be searched, and determine the vertical point corresponding to the escape point;

[0306] A detection range construction unit, used to construct a detection range corresponding to the vertical point according to the escape point, the vertical point and the safety distance;

[0307] The first association unit is used to determine whether there is an obstacle in the detection range in combination with the obstacle information, and if not, use the location of the escape point as an execution point for association with the escape point.

[0308] Optionally, the second association submodule includes:

[0309] An escape point search unit, used to search for an escape point with less than two execution points, use it as a first escape point, and determine a type of execution point to be supplemented for the first escape point;

[0310] A space region generating unit, configured to generate a plurality of space regions based on the first escape point;

[0311] A candidate execution point determination unit, configured to search for a candidate execution point of the first escape point from the spatial area in combination with a preset random strategy and the type of the execution point to be supplemented;

[0312] The selection unit is used to obtain a set of all candidate execution points based on a search strategy, and select a candidate execution point that is closest to the first escape point as an execution point of the first escape point.

[0313] Optionally, the space region generating unit includes:

[0314] A first limiting subunit is used to limit the execution area corresponding to the first escape point based on a preset distance;

[0315] The first division subunit is used to divide the execution area according to a preset level to generate a plurality of spatial areas.

[0316] Optionally, the space region generating unit includes:

[0317] The second partitioning subunit is used to perform twelve-level octree partitioning based on preset planning information to obtain a plurality of partitioning information;

[0318] A corner point search subunit, used to search for the nearest corner point around the first escape point;

[0319] The second limiting subunit is used to determine the execution area corresponding to the first escape point based on a preset distance with the corner point as the center; and use the division information in the execution area as the spatial area.

[0320] Optionally, the unit for determining the execution point to be selected includes:

[0321] A matching subunit, configured to determine an initial level according to a preset random strategy, and match a search strategy based on the initial level; the initial level includes one of level A, level B, and level C, wherein level A < level B < level C;

[0322] A randomly selected subunit is used to find the spatial region corresponding to the initial level, and randomly select a spatial region therefrom as a to-be-selected spatial region;

[0323] A matching condition determination subunit, used to determine a matching condition according to the type of execution point to be supplemented;

[0324] The candidate execution point search subunit is used to search for a candidate execution point from the candidate space area in combination with the search strategy and the matching condition; and determine whether the candidate execution point is the candidate execution point corresponding to the first escape point through the matching condition.

[0325] Optionally, it also includes: a point multiplexing module;

[0326] Optionally, the point multiplexing module includes:

[0327] A first execution point search submodule, used to search for a first execution point corresponding to a second escape point;

[0328] A second execution point search submodule, used to search for a second execution point corresponding to an escape point adjacent to the second escape point; wherein the first execution point and the second execution point are of the same type;

[0329] The judging submodule is used to judge whether the distance between the first execution point and the second execution point is less than a preset distance, and if so, take the second execution point as a new first execution point.

[0330] The functions of the system of the embodiment of the present invention have been described in the above method embodiment, so for details not fully described in this embodiment, please refer to the relevant description in the above embodiment, and no further description will be given here.

[0331] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, devices or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0332] The present invention is described with reference to flowcharts and / or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram and the combination of processes and / or blocks in the flowchart and / or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the process in the flowchart. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0333] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0334] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0335] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A method for optimizing the escape strategy of a drone, characterized in that: Acquire preset planning information of the drone, and search for a number of escape points according to the preset planning information; wherein, extract the original point position from the preset planning information, and generate the escape point according to the original point position and the preset interval; The method associates lifting information with the escape point, including: judging whether the location of the escape point is a return execution point and whether the location of the escape point is a landing execution point based on the detailed information and obstacle information of the escape point; after the judgment is completed, determining the type of execution point to be supplemented, supplementing the execution point for the escape point based on the association model, wherein, searching for an escape point with less than two execution points, taking it as the first escape point, and determining the type of execution point to be supplemented for the first escape point; generating a plurality of spatial regions based on the first escape point; determining the initial level according to a preset random strategy; searching for the initial level The spatial area corresponding to the level is selected, and a spatial area is randomly selected as the selected spatial area; a point to be tested is searched from the selected spatial area; whether the point to be tested is the selected execution point of the first escape point is determined by matching conditions, and the matching conditions include: there is no obstacle point in the test range of the point to be tested; a set of all the selected execution points is obtained based on the search strategy, and the selected execution point closest to the first escape point is selected as the execution point of the first escape point; the lifting information includes two different types of execution points; the escape point is associated with one of the return execution points and one of the landing execution points; When an abnormal signal of the drone is received, a target escape plan of the drone is established based on the abnormal signal and the lifting and lowering information of the escape point.

2. The method for optimizing the escape strategy of a drone as claimed in claim 1, characterized in that: The determining, based on the detailed information and obstacle information of the escape point, whether the location of the escape point is an execution point includes: Searching for detailed information of the escape point according to the type of execution point to be searched, and determining a vertical point corresponding to the escape point; According to the escape point, the vertical point and the safety distance, a detection range corresponding to the vertical point is constructed; In combination with the obstacle information, it is determined whether there is an obstacle within the detection range. If not, the location of the escape point is used as the execution point associated with the escape point.

3. The method for optimizing the escape strategy of a drone as claimed in claim 1, characterized in that: Based on the first escape point, a plurality of spatial regions are generated, including: Defining an execution area corresponding to the first escape point based on a preset distance; The execution area is divided according to a preset level to generate a plurality of spatial areas.

4. The method for optimizing the escape strategy of a drone as claimed in claim 1, characterized in that: Based on the first escape point, a plurality of spatial regions are generated, including: Based on the preset planning information, twelve-level octree partitioning is performed to obtain a number of partitioning information; Find the nearest corner point around the first escape point; Taking the corner point as the center and based on a preset distance, determining an execution area corresponding to the first escape point; and using the division information in the execution area as a spatial area.

5. The method for optimizing the escape strategy of a drone as claimed in claim 1, characterized in that: Combining a preset random strategy and the type of execution point to be supplemented, searching for a candidate execution point of the first escape point from the spatial area includes: Determine an initial level according to a preset random strategy, and match a search strategy based on the initial level; the initial level includes one of level A, level B, and level C, wherein level A < level B < level C; Find the spatial region corresponding to the initial level, and randomly select a spatial region therefrom as a candidate spatial region; Determining a matching condition according to the type of the execution point to be supplemented; In combination with the search strategy and the matching condition, a point to be tested is searched from the selected spatial area; and it is determined by the matching condition whether the point to be tested is a candidate execution point corresponding to the first escape point.

6. The method for optimizing the escape strategy of a drone as claimed in claim 1, characterized in that: Also includes: Find the first execution point corresponding to the second escape point; Finding a second execution point corresponding to an escape point adjacent to the second escape point; wherein the first execution point and the second execution point are of the same type; It is determined whether the distance between the first execution point and the second execution point is less than a preset distance, and if so, the second execution point is used as a new first execution point.

7. An escape strategy optimization system for a drone, characterized in that: include: An acquisition module is used to acquire preset planning information of the drone, and search for a number of escape points according to the preset planning information; wherein, the original point position is extracted from the preset planning information, and the escape point is generated according to the original point position and the preset interval; The association module is used to associate the lifting information with the escape point, including: judging whether the location of the escape point is a return execution point based on the detailed information and obstacle information of the escape point, judging whether the location of the escape point is a landing execution point; after the judgment is completed, determining the type of execution point to be supplemented, supplementing the execution point for the escape point based on the association model, wherein, searching for an escape point with less than two execution points, taking it as the first escape point, and determining the type of execution point to be supplemented for the first escape point; generating a plurality of spatial areas based on the first escape point; determining the initial level according to a preset random strategy; searching for the execution points of the first escape point; and determining the execution points of the first escape point. The spatial area corresponding to the initial level is randomly selected as the to-be-selected spatial area; the to-be-tested point is searched from the to-be-selected spatial area; whether the to-be-tested point is the to-be-selected execution point of the first escape point is determined by matching conditions, wherein the matching conditions include: there is no obstacle point in the to-be-tested range of the to-be-tested point; a set of all to-be-selected execution points is obtained based on the search strategy, and the to-be-selected execution point closest to the first escape point is selected as the execution point of the first escape point; the lifting information includes two different types of execution points; the escape point is associated with one of the return execution points and one of the landing execution points; The plan generation module is used to establish a target escape plan for the drone based on the abnormal signal and the lifting and lowering information of the escape point when an abnormal signal from the drone is received.

8. An electronic device, wherein: The electronic device includes: A processor; and a memory storing computer executable instructions, which when executed cause the processor to perform the method according to any one of claims 1-6.

9. A computer-readable storage medium, wherein: The computer-readable storage medium stores one or more programs, and when the one or more programs are executed by a processor, the method of any one of claims 1 to 6 is implemented.

Images