Unmanned aerial vehicle path planning method, device, equipment and medium

Abstract

The application provides a UAV path planning method, device, equipment and medium, which can be applied to the technical field of UAVs. The method comprises the following steps: determining a starting point, an ending point and a plurality of adjacent points related to the starting point of a UAV pre-flight from grid map data; determining the safety cost of the adjacent points based on the area type of the map area containing the adjacent points in the grid map data; detecting the navigation cost of the initial flight path passing through the starting point, the adjacent points and the ending point to determine the navigation cost related to the adjacent points; determining a target point from the plurality of adjacent points according to the comparison result between the respective adjacent point costs of the plurality of adjacent points, wherein the adjacent point cost is determined based on the safety cost and the navigation cost; and performing flight path planning according to the starting point, the target point and the ending point to obtain a target flight path.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of unmanned aerial vehicles, in particular to an unmanned aerial vehicle path planning method, device, equipment and medium. BACKGROUND

[0002] An unmanned aerial vehicle, referred to as a UAV, is a kind of unmanned aircraft using wireless remote control equipment and autonomous program control, or is completely or intermittently operated by a computer. Unmanned aerial vehicle path planning refers to finding a safe, dynamic feasible and optimal flight path from a source point to a target point for an unmanned aerial vehicle in a certain environment through a series of algorithms, controls and optimization methods.

[0003] However, the core goal of the existing path planning algorithm is to solve the shortest path problem, which needs to traverse all nodes, resulting in relatively low search efficiency and low path safety. SUMMARY

[0004] In view of the above problems, the present application provides an unmanned aerial vehicle path planning method, device, equipment and medium.

[0005] According to a first aspect of the present application, an unmanned aerial vehicle path planning method is provided, comprising: determining a starting point, an ending point and a plurality of adjacent points related to the starting point of a pre-flight of an unmanned aerial vehicle from grid map data; determining a safety cost of the adjacent points based on a region type of a map region containing the adjacent points in the grid map data; detecting a navigation cost of an initial flight path passing through the starting point, the adjacent points and the ending point to determine a navigation cost related to the adjacent points; determining a target point from the plurality of adjacent points according to a comparison result between the respective adjacent point costs of the plurality of adjacent points, the adjacent point cost being determined based on the safety cost and the navigation cost; and performing flight path planning according to the starting point, the target point and the ending point to obtain a target flight path.

[0006] Optionally, determining the safety cost of the adjacent points based on the region type of the map region containing the adjacent points in the grid map data comprises: determining a passing risk of the map region related to the adjacent points according to the region type of the map region related to the adjacent points; and determining the safety cost of the adjacent points according to the distance between the starting point and the ending point and the passing risk.

[0007] Optionally, the grid map data comprises a buffer zone, a no-fly zone and a passable zone, the no-fly zone is a region where an obstacle is located, and the buffer zone is constructed by expanding the no-fly zone based on a preset safety expansion range; wherein, the passable risk of the map region related to the adjacent point is determined according to the region type of the map region related to the adjacent point, comprising: in the case that the region type of the map region related to the adjacent point is the no-fly zone type, determining a first passable risk; in the case that the region type of the map region related to the adjacent point is the buffer zone type, determining a second passable risk, wherein the first passable risk is greater than the second passable risk; in the case that the region type of the map region related to the adjacent point is the passable zone type, determining a third passable risk, wherein the second passable risk is greater than the third passable risk.

[0008] Optionally, the navigation cost detection is performed on the initial flight path passing through the start point, the adjacent point and the end point, and the navigation cost related to the adjacent point comprises: according to a first target weight, processing the flight path consumption data of the unmanned aerial vehicle from the start point to the adjacent point by using a paid cost function to obtain a paid cost; according to a second target weight, processing the position information of the adjacent point and the end point respectively by using an evaluation function to obtain an estimated cost; and according to the paid cost and the estimated cost, obtaining the navigation cost related to the adjacent point.

[0009] Optionally, the first target weight and the second target weight are obtained based on the following operations: processing the first initial weight, the initial estimated cost and the distance between the start point and the end point by using a power function to obtain the first target weight, the first initial weight being determined based on a preset parameter adjustment threshold, and the initial estimated cost being obtained based on processing the position information of the adjacent point and the end point respectively by using the evaluation function; and processing the second initial weight, the initial estimated cost and the distance between the start point and the end point by using a power function to obtain the second target weight, the second initial weight being determined based on a preset deviation path limit.

[0010] Optionally, the target point is determined from the plurality of adjacent points according to a comparison result between the plurality of adjacent point costs corresponding to the plurality of adjacent points, comprising: determining a minimum adjacent point cost from the comparison result between the plurality of adjacent point costs; determining the adjacent point corresponding to the minimum adjacent point cost as an initial candidate point; in the case that the position difference between the initial candidate point and the end point is greater than a preset distance threshold, performing line-of-sight detection on the initial candidate point based on a straight line sampling rule to obtain a detection result; and in the case that the detection result is a passable result, determining the initial candidate point as the target point associated with the start point.

[0011] Optionally, the flight path is planned according to the starting point, the target point and the ending point to obtain a target flight path, including: determining a plurality of adjacent points corresponding to the (n-1)th target point from the grid map data; determining the nth target point corresponding to the (n-1)th target point from the plurality of adjacent points corresponding to the (n-1)th target point; until the Nth target point and the ending point satisfy a preset distance condition, determining the target flight path based on the N target points, wherein 1 n N, and n and N are integers.

[0012] The second aspect of the present application provides a UAV path planning device, including: a first determining module configured to determine a starting point, an ending point and a plurality of adjacent points related to the starting point of a UAV pre-flight from grid map data; a second determining module configured to determine a safety cost of the adjacent points based on a region type of a map region including the adjacent points in the grid map data; a third determining module configured to determine a navigation cost related to the adjacent points by performing navigation cost detection on an initial flight path passing through the starting point, the adjacent points and the ending point; a fourth determining module configured to determine a target point from the plurality of adjacent points according to a comparison result between respective adjacent point costs of the plurality of adjacent points, the adjacent point cost being determined based on the safety cost and the navigation cost; and a planning module configured to plan a flight path according to the starting point, the target point and the ending point to obtain a target flight path.

[0013] The third aspect of the present application provides an electronic device, including: one or more processors; a memory configured to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors perform the above method.

[0014] The fourth aspect of the present application further provides a computer readable storage medium having a computer program or instructions stored thereon, and the computer program or instructions are executed by a processor to implement the steps of the above method.

[0015] According to the UAV path planning method, device, equipment and medium provided by the present application, the region type is divided according to the safety degree level of each map region in the grid map data, so that the safety cost of the map region where the adjacent point is located can be determined, and appropriate safety consideration is included in the selection range of the flight path. In the process of planning the target flight path, not only the navigation cost constraint of realizing the shortest path and the lowest cost is considered, but also the safety cost constraint is considered, so that the target flight path is determined based on the constraint condition that the adjacent point cost is the smallest based on the navigation cost and the safety cost, the constraint condition of the safety cost is integrated to enhance the completeness of the adjacent point cost, and the safety and the algorithm search efficiency of the overall flight path are improved. BRIEF DESCRIPTION OF DRAWINGS

[0016] The above and other objects, features and advantages of the present application will become more apparent from the following description when taken in conjunction with the accompanying drawings, in which:

[0017] Figure 1 A flowchart of a method for planning a path of a UAV according to an embodiment of the present application is shown.

[0018] Figure 2 A flowchart of determining a target flight path according to an embodiment of the present application is shown.

[0019] Figure 3 A schematic diagram of determining a target flight path according to an embodiment of the present application is shown.

[0020] Figure 4 A block diagram of a device for planning a path of a UAV according to an embodiment of the present application is shown.

[0021] Figure 5 A block diagram of an electronic device adapted to implement a method for planning a path of a UAV according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0022] Hereinafter, embodiments of the present application will be described with reference to the accompanying drawings. It is to be understood, however, that these descriptions are merely exemplary and are intended to illustrate the scope of the present application, not to limit it. In the following detailed description of the embodiments of the present application, numerous specific details are set forth in order to provide a thorough understanding of the present application. However, it will be apparent to one skilled in the art that one or more embodiments of the present application can be practiced without these specific details. In other instances, well-known structures and functions have not been described in detail in order to avoid obscuring aspects of the present application.

[0023] The terms used herein are merely used to describe specific embodiments, and are not intended to limit the present application. The terms "include" and "have" and the like used herein indicate the presence of the features, steps, operations and / or components, but do not exclude the presence or addition of one or more other features, steps, operations or components.

[0024] All terms used herein, including technical and scientific terms, have the same meanings as those generally understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein should be interpreted as having meanings consistent with the context of the present specification, and should not be interpreted in an idealized or overly formal manner.

[0025] In the case where expressions such as "at least one of A, B, and C, etc." are used, it is generally to be interpreted that the meaning of the expression is the same as that of "one or more of A, B, and C." (e.g., "a system having at least one of A, B, and C" should include but not be limited to a system having A alone, a system having B alone, a system having C alone, a system having A and B together, a system having A and C together, a system having B and C together, and / or a system having A, B, and C together, etc.).

[0026] In the process of implementing the present application, it is found that the main technical defects of the existing UAV path planning method are: (1) the core goal is to solve the shortest path problem, ignoring the safety problem. Since it needs to traverse all nodes, this leads to relatively low search efficiency and low safety; (2) the path planning method involves complex calculations every time the path node is expanded, especially in a three-dimensional space environment, which significantly increases the amount of calculation and consumes a large amount of computing resources.

[0027] Therefore, embodiments of the present application provide a UAV path planning method, device, equipment and medium. The method comprises: determining a starting point, an ending point and a plurality of adjacent points related to the starting point of a UAV pre-flight from grid map data; determining the safety cost of the adjacent points based on the region type of the map region containing the adjacent points in the grid map data; detecting the navigation cost of the initial flight path passing through the starting point, the adjacent points and the ending point to determine the navigation cost related to the adjacent points; determining a target point from the plurality of adjacent points according to the comparison result between the adjacent point costs corresponding to the plurality of adjacent points, the adjacent point cost being determined based on the safety cost and the navigation cost; and performing flight path planning according to the starting point, the target point and the ending point to obtain a target flight path.

[0028] In the technical scheme of the present application, the user information (including but not limited to user personal information, user image information, user equipment information such as location information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved are all information and data authorized by the user or authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of related data comply with relevant laws, regulations and standards, necessary security measures are taken, do not violate public order and good customs, and provide corresponding operation portal for user to choose authorization or refusal.

[0029] It should be noted that the serial numbers of the various operations in the following method are only used to represent the operations for description, and should not be regarded as representing the execution order of the various operations. Unless explicitly stated, the method does not need to be executed in the order shown.

[0030] Figure 1 A flowchart of a UAV path planning method according to an embodiment of the present application is shown.

[0031] As shown in Figure 1 , the method 100 comprises operation S110 to operation S150.

[0032] In operation S110, the starting point, the ending point and a plurality of adjacent points related to the starting point of a UAV pre-flight are determined from the grid map data.

[0033] In operation S120, a safety cost of the adjacent point is determined based on a region type of a map region including the adjacent point in the grid map data.

[0034] In operation S130, a navigation cost related to the adjacent point is determined by performing navigation cost detection on the initial flight path passing through the start point, the adjacent point, and the end point.

[0035] In operation S140, a target point is determined from the plurality of adjacent points according to a comparison result between the respective adjacent point costs of the plurality of adjacent points.

[0036] In operation S150, a target flight path is obtained by performing flight path planning according to the start point, the target point, and the end point.

[0037] Optionally, the grid map data is obtained by vectorization and rasterization processing of standard Global Positioning System (GPS) map data based on a map processing tool.

[0038] Optionally, each grid in the grid map data can be regarded as a point. The position of the start point, the position of the end point, and the positions of the plurality of adjacent points related to the start point are determined in the grid map data.

[0039] For example, the position of the start point is (0, 0), and the positions of the plurality of adjacent points related to the start point are (1, 0), (1, 1), and (0, 1) respectively.

[0040] Optionally, a first table and a second table are created as two data structures, and the start point is added to the first table as the start point.

[0041] Optionally, the region type is determined according to a safety risk of the unmanned aerial vehicle passing through the map region. For example, the region type can be a free passage region type, a no-fly region type, or a buffer region type.

[0042] Optionally, the safety cost of the adjacent point is determined by processing the region type of the map region of the adjacent point using a safety cost function.

[0043] Optionally, the greater the safety risk of the unmanned aerial vehicle passing through the map region, the greater the safety cost.

[0044] Optionally, the navigation cost related to the adjacent point is obtained by performing navigation cost detection on the initial flight path formed by the unmanned aerial vehicle flying from the start point to the adjacent point and then flying from the adjacent point to the end point using an A-star algorithm.

[0045] Optionally, the navigation cost related to the adjacent point represents a cost of fuel, distance, or the like consumed by the unmanned aerial vehicle to reach the end point based on the initial flight path.

[0046] Optionally, the adjacent point cost can be determined by weighting the safety cost and the navigation cost based on a preset weight.

[0047] Optionally, the adjacent point costs corresponding to the plurality of adjacent points are compared in size to obtain a comparison result, and the adjacent point corresponding to the minimum adjacent point cost is determined as the target point.

[0048] Optionally, the target point corresponding to the starting point is the next point passed by the UAV from the starting point.

[0049] Optionally, the target point is stored in the first table, and the remaining adjacent points are stored in the second table.

[0050] Optionally, the second table is used to record the adjacent points that have been calculated and whose child nodes have been processed, thereby preventing repeated expansion and dead loops.

[0051] For example, the adjacent points of the starting point include adjacent point 1, adjacent point 2, and adjacent point 3, the adjacent point cost of adjacent point 3 is the smallest, and therefore adjacent point 3 is determined as the target point, adjacent point 3 is stored in the first table, and adjacent point 1 and adjacent point 2 are stored in the second table.

[0052] Optionally, based on the target point of the starting point, a plurality of adjacent points of the target point are determined, and then based on the plurality of adjacent points of the target point, the next target point of the target point is determined, and the determination process is the same as the process of determining the target point of the starting point, which will not be repeated here. When a certain target point is determined as the terminal point, the iteration is stopped.

[0053] Optionally, the first table is used to record "from which previous target point each target point is obtained"; after the last target point is determined, the path is backtracked based on the first table: from the terminal point to the starting point, to obtain a target flight path composed of the starting point, the plurality of target points, and the terminal point.

[0054] Optionally, the state of the first table is checked. If the first table is empty, it means that no valid path is found, and the search process fails, and the program is terminated.

[0055] Optionally, since the area types are divided according to the safety level of each map area in the grid map data, the safety cost of the map area where the adjacent point is located can be determined, and appropriate safety considerations are included in the selection range of the flight path. In the process of planning the target flight path, not only the navigation cost constraint of realizing the shortest path and the shortest cost is considered, but also the safety cost constraint is considered, so that the target flight path is determined based on the constraint condition that the adjacent point cost is the smallest based on the navigation cost and the safety cost. The constraint condition of the safety cost is integrated to enhance the completeness of the adjacent point cost and improve the safety of the overall flight path and the search efficiency of the algorithm.

[0056] Optionally, the safety cost of the adjacent point is determined based on a region type of a map region containing the adjacent point in the grid map data, including: determining a passing risk of the map region related to the adjacent point according to the region type of the map region related to the adjacent point; and determining the safety cost of the adjacent point according to the distance between the start point and the end point and the passing risk.

[0057] Optionally, the passing risk of the map region related to the adjacent point is determined according to a map region where the adjacent point is located and a region type of the map region where the adjacent point is located.

[0058] Optionally, the region types of the map regions are divided and marked in advance in the grid map data based on a grid assignment algorithm.

[0059] For example, the region type is marked as 0, 0.5 or 1.

[0060] Optionally, in the process of path planning, the obstacle periphery is often accompanied by a flyable region, but these regions are accompanied by a certain passing risk. The passing risk represents the safety degree of the unmanned aerial vehicle flying through the region, and the greater the passing risk, the lower the safety degree.

[0061] Optionally, the region type is divided according to the flight risk, and the passing risk of the map region related to the adjacent point can be determined according to the region type of the map region related to the adjacent point.

[0062] For example, if the region type is marked as 0, the passing risk is 0, which represents that the region can be completely safely flown through; if the region type is marked as 1, the passing risk is infinite, which represents that there is an obstacle, and the passing risk of flying through the region is extremely great.

[0063] In an embodiment, the safety cost of the adjacent point i is As shown in formula (1):

[0064] (1).

[0065] wherein, represents the passing risk of the map region related to the adjacent point i, the value of is 0, 0.5 or infinite, represents the distance between the start point and the end point.

[0066] Optionally, the buffer zone, the no-fly zone and the passable zone are included in the grid map data, the no-fly zone is a position area of an obstacle, and the buffer zone is constructed by expanding the no-fly zone based on a preset safety expansion range; wherein, the passable risk of the map area related to the adjacent point is determined according to the region type of the map area related to the adjacent point, including: determining a first passable risk in the case that the region type of the map area related to the adjacent point is a no-fly zone type; determining a second passable risk in the case that the region type of the map area related to the adjacent point is a buffer zone type, wherein the first passable risk is greater than the second passable risk; determining a third passable risk in the case that the region type of the map area related to the adjacent point is a passable zone type, wherein the second passable risk is greater than the third passable risk.

[0067] For example, the position area of each obstacle in the grid map data is determined as the no-fly zone, the obstacle can be a building, and the no-fly zone is prohibited for the unmanned aerial vehicle to cross.

[0068] For example, the length, width and height of each obstacle in the grid map data are expanded by one grid unit in each direction, and the expanded grid unit is taken as the buffer zone between the unmanned aerial vehicle and the obstacle. After adding appropriate safety cost, the buffer zone can be flexibly adjusted as part of the flight path and is included in the selection range of the flight path.

[0069] For example, the remaining area in the grid map data is taken as the passable zone, and the passable zone is directly safe for the unmanned aerial vehicle to fly.

[0070] For example, the no-fly zone type is marked as 1, the first passable risk corresponding to the no-fly zone type is infinite; the buffer zone type is marked as 0.5, the second passable risk corresponding to the buffer zone type is 0.5; the passable zone type is marked as 0, and the third passable risk corresponding to the passable zone type is 0.

[0071] Optionally, the first passable risk is greater than the second passable risk, and the second passable risk is greater than the third passable risk.

[0072] Optionally, in the process of target path planning, the obstacle is often accompanied by a flyable area, but these areas are accompanied by a certain passable risk. The no-fly zone is a strictly prohibited flight area, and the safety cost is configured as infinite; the buffer zone is a flyable area, and the additional safety cost is calculated according to the configured passable risk , which can be flexibly adjusted as part of the flight path to form a safe flight buffer zone; the passable zone is a safe flight area, and the safety cost is configured as 0. After adding appropriate safety considerations, the flyable buffer zone can be included in the selection range of the flight path. By quantifying the passable risk of different region types, the safety cost of different regions is carefully evaluated, so that the flight safety factor can be fully considered to improve the safety of the overall flight path.

[0073] Optionally, the navigation cost detection on the initial flight path passing through the start point, the adjacent point and the end point comprises: according to a first target weight, processing flight path consumption data of the UAV from the start point to the adjacent point by using a paid cost function to obtain a paid cost; according to a second target weight, processing position information of the adjacent point and the end point respectively by using an evaluation function to obtain an estimated cost; and according to the paid cost and the estimated cost, obtaining the navigation cost related to the adjacent point.

[0074] Optionally, the flight path consumption data can be real path data from the start point to the adjacent point, such as coordinate, side length, moving direction, cumulative length, time, fuel consumption and the like.

[0075] Optionally, the paid cost represents the actual navigation cost of the UAV from the start point to the adjacent point.

[0076] Optionally, the evaluation function can be a heuristic function.

[0077] Optionally, the coordinate difference between the adjacent point and the end point is processed by using the evaluation function to obtain the estimated cost. The estimated cost represents the estimated navigation cost of the UAV from the adjacent point to the end point.

[0078] In an embodiment, the navigation cost of the adjacent point i is As shown in formula (2):

[0079] (2).

[0080] wherein, the first target weight of the adjacent point i is denoted as the paid cost function of the adjacent point i is denoted as the second target weight of the adjacent point i is denoted as the evaluation function of the adjacent point i is denoted as

[0081] In an embodiment, the adjacent point cost of the adjacent point i is As shown in formula (3):

[0082] (3).

[0083] wherein, the navigation cost of the adjacent point i is denoted as the safety cost of the adjacent point i is denoted as the weight coefficient of the safety cost is denoted as 2.

[0084] Optionally, since the safety cost of each adjacent point in the grid map data is taken into the path synthesis cost, in order to balance the influence of the paid cost, the estimated cost and the safety cost on the path search, and considering the unmanned aerial vehicle itself and the environmental conditions, the weights of various costs in the path planning are adjusted to improve the A-star algorithm, shorten the path planning length, and improve the safety of the path planning.

[0085] Optionally, the first target weight and the second target weight are obtained based on the following operations: the first initial weight, the initial estimated cost and the distance between the starting point and the ending point are processed by using a power function to obtain the first target weight, the first initial weight is determined based on a preset parameter adjustment threshold, and the initial estimated cost is obtained based on processing the position information of each of the adjacent points and the ending point by using an evaluation function; and the second initial weight, the initial estimated cost and the distance between the starting point and the ending point are processed by using a power function to obtain the second target weight, the second initial weight is determined based on a preset path deviation limit.

[0086] Optionally, if a relatively large value is taken, the efficiency of calculating the estimated cost is relatively high, and if a relatively large value is taken, the efficiency of calculating the paid cost is relatively high. The , are each set to a minimum limit, so as to avoid the phenomenon that the weight is too small, the direction is not clear during the algorithm search process, the search nodes are too many, and the search time is too long.

[0087] Optionally, the cost function of the existing A-star algorithm has certain limitations, especially in the grid map data, some nodes with a relatively low navigation cost and a relatively small proportion may be encountered. These nodes are too dependent on the actual paid cost, which causes the A-star algorithm to be not clear enough in direction during the search process, and is prone to fall into the search of a large number of invalid nodes, thereby increasing the calculation burden. In order to overcome this defect, an optimization strategy for the first initial weight and the second initial weight in the cost function of the A-star algorithm is proposed.

[0088] Optionally, the first initial weight is determined based on a preset parameter adjustment threshold, and the first initial weight is greater than 1. The first initial weight is used to adjust the proportion of the paid cost.

[0089] Optionally, the initial estimated cost is obtained based on processing the position information of each of the adjacent points and the ending point by using an evaluation function.

[0090] Optionally, the second initial weight is determined based on a preset path deviation limit, and the second initial weight is greater than 1. The second initial weight is used to adjust the proportion of the estimated cost, and to ensure that the path deviation degree is within a certain range.

[0091] ​In an embodiment, the first target weight of the adjacent point i is As shown in equation (4):

[0092] (4).

[0093] wherein, represents the first initial weight of the adjacent point i, which is also the base number of the power function in equation (4), for example, taking the value 1.2, represents the evaluation function of the adjacent point i, represents the distance between the start point and the end point.

[0094] In an embodiment, the second target weight of the adjacent point i is As shown in equation (5):

[0095] (5).

[0096] wherein, represents the second initial weight of the adjacent point i, which is also the base number of the power function in equation (5), for example, taking the value 1.0, represents the evaluation function of the adjacent point i, represents the distance between the start point and the end point.

[0097] Optionally, the first initial weight and the second initial weight are optimized to dynamically adjust according to the initial estimated cost calculated by different adjacent points, so that the calculation of the flight cost avoids relying on the paid cost, and the first target weight and the second target weight are adjusted, which improves the definiteness of the direction in the search process of the algorithm, and the change of the weight improves the rationality of the algorithm operation and the path search efficiency.

[0098] Optionally, through the efficient weight self-adaptive adjustment optimization algorithm, the optimal path can be found in fewer search points, which not only reduces the consumption of computing resources, but also makes the entire path planning process more concise and efficient. In terms of flight distance, the improved algorithm can calculate a shorter flight path through the weight optimization search strategy and path selection logic. Not only does it mean that the aircraft or unmanned system can reach the destination faster and reduce energy consumption, but it also improves the efficiency and flexibility of task execution. For scenarios that need to frequently perform short-range flight tasks, this optimization in distance is particularly important, which can greatly improve the economic efficiency and sustainability of overall operation.

[0099] Optionally, the target point is determined from the plurality of adjacent points according to a comparison result between the respective adjacent point costs of the plurality of adjacent points, including: determining a minimum adjacent point cost from the comparison result between the plurality of adjacent point costs; determining an initial candidate point corresponding to the minimum adjacent point cost; in a case where a position difference between the initial candidate point and the end point is greater than a preset distance threshold, performing line-of-sight detection on the initial candidate point based on a straight line sampling rule to obtain a detection result; and in a case where the detection result is a passable result, determining the initial candidate point as the target point associated with the start point.

[0100] Optionally, the plurality of adjacent points are traversed, the adjacent point cost of each adjacent point is calculated, the plurality of adjacent point costs are compared to obtain a comparison result, and a minimum adjacent point cost is determined.

[0101] Optionally, the adjacent point corresponding to the minimum adjacent point cost is determined as the initial candidate point. The preset distance threshold is a distance threshold set considering a position error, and the position difference between the initial candidate point and the end point being greater than the preset distance threshold represents that the initial candidate point and the end point are not the same point.

[0102] Optionally, the initial candidate point is subjected to line-of-sight detection based on a straight line sampling rule: a straight line is drawn from the initial candidate point, and each grid is checked, and it is immediately checked whether the grid is blocked at each step; a non-passable detection result is obtained when an obstacle is encountered, or a passable detection result is obtained when the last grid is unobstructed.

[0103] Optionally, the passable result represents that there is a passable space around the initial candidate point, and in a case where the detection result is the passable result, the initial candidate point is determined as the target point associated with the start point.

[0104] Optionally, the non-passable result represents that there is no passable space around the initial candidate point, and in a case where the detection result is the non-passable result, an adjacent point at a second-to-last position in a sequence of the adjacent points sorted from large to small according to the adjacent point cost is determined, the adjacent point is subjected to line-of-sight detection, and the above process is repeated until the target point is determined.

[0105] Optionally, a flight path is planned according to the start point, the target point, and the end point to obtain a target flight path, including: determining a plurality of adjacent points corresponding to the (n-1)th target point from the grid map data; determining an nth target point corresponding to the (n-1)th target point from the plurality of adjacent points corresponding to the (n-1)th target point; and repeating the above process until the (N)th target point and the end point satisfy a preset distance condition, and determining the target flight path based on the N target points, wherein 1 n N, and n and N are integers.

[0106] Optionally, the first target point is determined according to the respective adjacent point cost of each of the plurality of adjacent points of the start point; the second target point is determined according to the respective adjacent point cost of each of the plurality of adjacent points of the first target point, and the plurality of adjacent points are sequentially determined until the Nth target point and the end point satisfy the preset distance condition, and the search of the target point is stopped.

[0107] Optionally, the Nth target point and the end point satisfying the preset distance condition means that the Nth target point and the end point are the same point.

[0108] Optionally, each target point is stored in the first table, and the adjacent point of the non-target point is stored in the second table, and in the case that the Nth target point and the end point satisfy the preset distance condition, the path is backtracked based on the first table: from the end point to the start point, to obtain the target flight path composed of the start point, the plurality of target points and the end point.

[0109] Figure 2 A flowchart for determining a target flight path according to an embodiment of the present application is shown.

[0110] As shown in Figure 2 , the process includes operations S201-S212.

[0111] In operation S201, the algorithm is initialized, and the first table and the second table are created.

[0112] In operation S202, it is determined whether the first table is empty. If yes, operation S212 is entered, otherwise operation S203 is entered.

[0113] In operation S203, the respective adjacent point cost of each of the plurality of adjacent points is calculated.

[0114] In operation S204, the initial candidate point is determined.

[0115] In operation S205, it is determined whether the initial candidate point is the end point. If yes, operation S206 is entered, otherwise operation S207 is entered.

[0116] In operation S206, the previous node is searched.

[0117] In operation S207, it is determined whether there is a feasible space for line-of-sight detection. If yes, operation S208 is entered, otherwise operation S204 is entered.

[0118] In operation S208, a search is performed around the target point.

[0119] In operation S209, it is determined whether there is a feasible space for the adjacent point of the target point. If yes, operation S210 is entered, otherwise operation S208 is entered.

[0120] In operation S210, the visibility of the adjacent point is detected.

[0121] In operation S211, the target flight path is generated.

[0122] In operation S212, the process ends.

[0123] Optionally, the adjacent points are sorted according to the adjacent point cost from large to small to obtain an adjacent point sequence, and the previous node is an adjacent point located at a position before the initial candidate point.

[0124] Figure 3 A schematic diagram of determining a target flight path according to an embodiment of the present application is shown.

[0125] As shown in Figure 3 , the size of the local grid map is determined according to the grid map data: 5x5. The local grid map includes a starting point A(0, 0), an ending point B(4, 4), a no-fly zone (2, 2), a buffer zone (1, 2), (2, 1), (2, 3), (3, 2), and a passable zone: other positions. According to a related algorithm (without safety cost), only the shortest path is considered, and the target flight path is determined to be path 1: from the starting point (0, 0) -> (1, 0) -> (2, 0) -> (3, 1) -> (4, 2) -> the ending point (4, 4). Path 1 avoids the obstacles, but passes through the buffer zone, the total path length is shorter, but it is close to the obstacles, and the flight safety is poor. According to the method of the present application (considering safety cost), the target point with small safety cost is selected each time, and the target flight path is determined to be path 2: (0, 0) -> (0, 1) -> (1, 1) -> (1, 3) -> (2, 4) -> (4, 4). Path 2 is slightly longer, but completely avoids the buffer zone, and is safer.

[0126] Optionally, the algorithm without considering safety cost will prefer the shortest path, and is easy to be close to the obstacles; the algorithm considering safety cost will punish the nodes close to the obstacles during calculation, so that the flight path is safer.

[0127] Based on the above unmanned aerial vehicle path planning method, the present application further provides an unmanned aerial vehicle path planning device. The device will be described in detail below. Figure 4

[0128] Figure 4 A structure block diagram of the unmanned aerial vehicle path planning device according to an embodiment of the present application is shown.

[0129] As shown in Figure 4 , the unmanned aerial vehicle path planning device 400 of this embodiment includes a first determination module 410, a second determination module 420, a third determination module 430, a fourth determination module 440, and a planning module 450.

[0130] ​The first determining module 410 is configured to determine a start point, an end point and a plurality of adjacent points related to the start point of the flight of the UAV from the grid map data. In an embodiment, the first determining module 410 can be configured to perform the operation S110 described above, and details are not repeated here.

[0131] The second determining module 420 is configured to determine a safety cost of the adjacent point based on a region type of a map region including the adjacent point in the grid map data. In an embodiment, the second determining module 420 can be configured to perform the operation S120 described above, and details are not repeated here.

[0132] The third determining module 430 is configured to determine a navigation cost related to the adjacent point by performing navigation cost detection on an initial flight path passing through the start point, the adjacent point and the end point. In an embodiment, the third determining module 430 can be configured to perform the operation S130 described above, and details are not repeated here.

[0133] The fourth determining module 440 is configured to determine a target point from the plurality of adjacent points according to a comparison result between a plurality of adjacent point costs respectively corresponding to the plurality of adjacent points, the adjacent point cost being determined based on the safety cost and the navigation cost. In an embodiment, the fourth determining module 440 can be configured to perform the operation S140 described above, and details are not repeated here.

[0134] The planning module 450 is configured to perform flight path planning according to the start point, the target point and the end point to obtain a target flight path. In an embodiment, the planning module 450 can be configured to perform the operation S150 described above, and details are not repeated here.

[0135] Optionally, the second determining module 420 includes a first determining sub-module and a second determining sub-module.

[0136] The first determining sub-module is configured to determine a passing risk of the map region related to the adjacent point according to the region type of the map region related to the adjacent point.

[0137] The second determining sub-module is configured to determine the safety cost of the adjacent point according to the distance between the start point and the end point and the passing risk.

[0138] Optionally, the first determining sub-module includes a first determining unit, a second determining unit and a third determining unit.

[0139] The first determining unit is configured to determine a first passing risk in a case where the region type of the map region related to the adjacent point is a no-fly zone type.

[0140] The second determining unit is configured to determine a second passing risk in a case where the region type of the map region related to the adjacent point is a buffer zone type, and the first passing risk is greater than the second passing risk.

[0141] The third determining unit is configured to determine a third passing risk when the region type of the map region related to the adjacent point is the passing region type, wherein the second passing risk is greater than the third passing risk.

[0142] Optionally, the third determining module 430 comprises a third determining submodule, a fourth determining submodule and a fifth determining submodule.

[0143] The third determining submodule is configured to obtain a paid cost by processing the flight path consumption data of the UAV from the starting point to the adjacent point by using the paid cost function according to the first target weight.

[0144] The fourth determining submodule is configured to obtain an estimated cost by processing the position information of the adjacent point and the terminal point respectively by using the estimated cost function according to the second target weight.

[0145] The fifth determining submodule is configured to obtain the navigation cost related to the adjacent point according to the paid cost and the estimated cost.

[0146] Optionally, the fourth determining module 440 comprises a sixth determining submodule, a seventh determining submodule, an eighth determining submodule and a ninth determining submodule.

[0147] The sixth determining submodule is configured to determine the minimum adjacent point cost from the comparison result between the plurality of adjacent point costs.

[0148] The seventh determining submodule is configured to determine the adjacent point corresponding to the minimum adjacent point cost as the initial candidate point.

[0149] The eighth determining submodule is configured to perform line-of-sight detection on the initial candidate point based on the line-of-sight sampling rule to obtain a detection result when the position difference between the initial candidate point and the terminal point is greater than the preset distance threshold.

[0150] The ninth determining submodule is configured to determine the initial candidate point as the target point associated with the starting point when the detection result is the passable result.

[0151] Optionally, the planning module 450 comprises a first planning submodule, a second planning submodule and a third planning submodule.

[0152] The first planning submodule is configured to determine the plurality of adjacent points corresponding to the (n-1)th target point from the grid map data.

[0153] The second planning submodule is configured to determine the nth target point corresponding to the (n-1)th target point from the plurality of adjacent points corresponding to the (n-1)th target point.

[0154] The third planning submodule is configured to determine the target flight path based on the N target points until the Nth target point and the terminal point satisfy the preset distance condition, wherein 1 n N, and n and N are integers.

[0155] Optionally, any of the first determining module 410, the second determining module 420, the third determining module 430, the fourth determining module 440 and the planning module 450 can be combined in one module, or any of them can be split into multiple modules. Alternatively, at least part of the function of one or more of these modules can be combined with at least part of the function of other modules, and implemented in one module. Optionally, at least one of the first determining module 410, the second determining module 420, the third determining module 430, the fourth determining module 440 and the planning module 450 can be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on chip, a system on substrate, a system on package, an application specific integrated circuit (ASIC), or any other reasonable way of integrating or packaging a circuit, etc. hardware or firmware, or in any one of software, hardware and firmware three kinds of implementation or in any appropriate combination of several of them. Alternatively, at least one of the first determining module 410, the second determining module 420, the third determining module 430, the fourth determining module 440 and the planning module 450 can be at least partially implemented as a computer program module, which can perform corresponding functions when running.

[0156] Figure 5 A block diagram of an electronic device suitable for implementing the UAV path planning method according to an embodiment of the present application is shown.

[0157] Figure 5 The electronic device shown is only an example and should not bring any limitation to the function and use range of the embodiments of the present application.

[0158] As Figure 5 shown, the computer electronic device 500 according to an embodiment of the present application includes a processor 501, which can perform various appropriate actions and processes according to programs stored in a ROM 502 (read only memory) or loaded from a storage portion 508 to a RAM 503 (random access memory). The processor 501 may, for example, include a general purpose microprocessor (such as a CPU), an instruction set processor and / or a related chipset, and / or a special purpose microprocessor (such as an application specific integrated circuit (ASIC)), etc. The processor 501 can also include an on-board memory for cache use. The processor 501 can include a single processing unit or multiple processing units for performing different actions of the method processes according to embodiments of the present application.

[0159] In the RAM 503, various programs and data required by the electronic device 500 to operate are stored. The processor 501, the ROM 502 and the RAM 503 are connected to each other via the bus 504. The processor 501 performs various operations of the method flow according to the embodiments of the present application by executing the programs in the ROM 502 and / or the RAM 503. It should be noted that the programs can also be stored in one or more memories other than the ROM 502 and the RAM 503. The processor 501 can also perform various operations of the method flow according to the embodiments of the present application by executing the programs stored in the one or more memories.

[0160] Optionally, the electronic device 500 can further include an input / output (I / O) interface 505, which is also connected to the bus 504. The electronic device 500 can further include one or more of the following components connected to the input / output (I / O) interface 505: an input portion 506 including a keyboard, a mouse, etc.; an output portion 507 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage portion 508 including a hard disk, etc.; and a communication portion 509 including a network interface card such as a LAN card, a modem, etc. The communication portion 509 performs communication processing via a network such as the Internet. A drive 510 is also connected to the input / output (I / O) interface 505 as necessary. A removable medium 511 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc. is attached to the drive 510 as necessary, so that a computer program read therefrom is installed in the storage portion 508 as necessary.

[0161] Optionally, the method flow according to the embodiments of the present application can be implemented as a computer software program. For example, the embodiments of the present application include a computer program product comprising a computer program carried on a computer-readable storage medium, the computer program containing program codes for executing the method shown in the flow chart. In such embodiments, the computer program can be downloaded and installed from a network by the communication portion 509, and / or installed from the removable medium 511. When the computer program is executed by the processor 501, the above-described functions defined in the system according to the embodiments of the present application are performed. Optionally, the system, device, apparatus, module, unit, etc. described above can be implemented by computer program modules.

[0162] The present application also provides a computer-readable storage medium, which can be included in the device / apparatus / system described in the above embodiments; or can exist separately without being assembled into the device / apparatus / system. The above computer-readable storage medium carries one or more programs, which when executed, implement the UAV path planning method according to the embodiments of the present application.

[0163] Optionally, the computer readable storage medium can be a non-transitory computer readable storage medium. For example, it can include, but is not limited to, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), portable compact disc read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing. In this application, the computer readable storage medium can be any tangible medium that contains or stores a program for use by or in connection with an instruction execution system, apparatus, or device.

[0164] For example, optionally, the computer readable storage medium can include one or more memories such as the ROM 502 and / or the RAM 503 described above and / or one or more memories other than the ROM 502 and the RAM 503.

[0165] Embodiments of the present application also include a computer program product, which comprises a computer program for executing the method provided by the embodiments of the present application, and the program codes contained in the computer program are used for making the electronic device implement the UAV path planning method provided by the embodiments of the present application when the computer program product is run on the electronic device.

[0166] When the computer program is executed by the processor 501, the above-mentioned functions defined in the system / apparatus of the embodiments of the present application are executed. Optionally, the system, apparatus, module, unit and the like described above can be implemented by the computer program modules.

[0167] In one embodiment, the computer program can rely on tangible storage media such as optical storage media, magnetic storage media and the like. In another embodiment, the computer program can also be transmitted, distributed and downloaded in the form of a signal on a network medium, and be downloaded and installed through the communication part 509, and / or be installed from the detachable medium 511. The program codes contained in the computer program can be transmitted by any appropriate network medium, including but not limited to wireless, wired, or any suitable combination of the foregoing.

[0168] Alternatively, program code to carry out operations provided in embodiments of the application can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C++ or the like, and / or conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computing device, partly on the user's computing device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device or entirely on the remote computing device or server. In the latter scenario, the remote computing device can be connected to the user's computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computing device such as through the Internet using an Internet Service Provider.

[0169] The computer program instructions can also be loaded onto a computer or other programmable information processing apparatus to cause a series of operations to be performed on the computer or other programmable information processing apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable information processing apparatus implement the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0170] Embodiments of the present application have been described. However, these embodiments are merely meant to be illustrative of the present application and should not be construed as limiting the scope of the present application. Although each of the embodiments has been described above, it should be noted that measures in each of the embodiments can be advantageously used in combination. Various substitutions and modifications are possible within the scope of the present application without departing from the spirit and scope of the present application.

Claims

1. A method for unmanned aerial vehicle (UAV) path planning, characterized in that, The method includes: The starting point, ending point, and multiple adjacent points related to the starting point are determined from the raster map data for the UAV's pre-flight. Based on the region type of the map area containing the adjacent points in the raster map data, the security cost of the adjacent points is determined as follows: Based on the region type of the map region associated with the adjacent point, the passage risk of the map region associated with the adjacent point is determined. The raster map data includes a buffer zone, a no-fly zone, and a passage zone. The buffer zone is constructed by expanding the no-fly zone based on a preset safety extension range. The no-fly zone is the area where the obstacle is located, and the buffer zone is the flyable area. Based on the distance between the starting point and the ending point and the passage risk, the safety cost of the adjacent points is determined, and the safety cost of the adjacent points satisfies the following formula: = , This indicates the access risk of the map area related to adjacent points. Indicates the distance between the starting point and the ending point; The initial flight path passing through the starting point, the adjacent points, and the endpoint is subjected to flight cost detection to determine the flight cost associated with the adjacent points. The flight cost includes the estimated cost obtained by processing the position information of the adjacent points and the endpoint using an evaluation function based on a second target weight. The second target weight is obtained by processing the second initial weight, the initial estimated cost, and the distance between the starting point and the endpoint using a power function. The second initial weight is determined based on a preset deviation path limit. A target point is determined from the plurality of neighboring points based on the comparison results between the neighboring point costs corresponding to each of the plurality of neighboring points, wherein the neighboring point costs are determined based on the security cost and the navigation cost; Based on the starting point, the target point, and the ending point, a flight path is planned to obtain the target flight path.

2. The method according to claim 1, characterized in that, in, The step of determining the access risk of a map region related to a neighboring point based on the region type of the map region related to the neighboring point includes: If the map area associated with the adjacent point is a no-fly zone, a first passage risk is determined. If the region type of the map area associated with the adjacent point is a buffer type, a second passage risk is determined, wherein the first passage risk is greater than the second passage risk; If the area type of the map region associated with the adjacent point is a passable area, a third passable risk is determined, wherein the second passable risk is greater than the third passable risk.

3. The method according to claim 1, characterized in that, The step of detecting the flight cost of the initial flight path passing through the starting point, the adjacent points, and the ending point, and determining the flight cost associated with the adjacent points, includes: Based on the first objective weight, the paid cost function is used to process the flight path consumption data of the UAV from the starting point to the adjacent point to obtain the paid cost. Based on the paid cost and the estimated cost, the navigation cost associated with the adjacent point is obtained.

4. The method according to claim 3, characterized in that, The first target weight is obtained based on the following operation: The first target weight is obtained by using a power function to process the first initial weight, the initial estimated cost, and the distance between the starting point and the ending point. The first initial weight is determined based on a preset parameter tuning threshold, and the initial estimated cost is obtained by processing the position information of the adjacent points and the ending point based on the evaluation function.

5. The method according to claim 1, characterized in that, The step of determining the target point from the plurality of neighboring points based on the comparison results between the costs of the neighboring points corresponding to each of the plurality of neighboring points includes: Determine the minimum adjacent point cost from the comparison results of the costs of multiple adjacent points; Determine the adjacent point corresponding to the minimum adjacent point cost as the initial candidate point; When the position gap between the initial candidate point and the end point is greater than a preset distance threshold, perform line-of-sight detection on the initial candidate point based on the line sampling rule to obtain a detection result; When the detection result is a passable result, determine the initial candidate point as the target point associated with the starting point.

6. The method according to claim 1, characterized in that, The flight path planning according to the starting point, the target point, and the end point to obtain a target flight path includes: Determine multiple adjacent points corresponding to the (n - 1)-th target point from the grid map data; Determine the n-th target point corresponding to the (n - 1)-th target point from the multiple adjacent points corresponding to the (n - 1)-th target point; Until the N-th target point and the end point meet the preset distance condition, determine the target flight path based on the N target points, where 1 < n ≤ N, and both n and N are integers.

7. A path planning device for unmanned aerial vehicles (UAVs), characterized in that, The device includes: A first determination module, configured to determine the starting point, the end point, and multiple adjacent points related to the starting point for the pre-flight of the drone from the grid map data; A second determination module, configured to determine the safety cost of the adjacent points based on the area type of the map area including the adjacent points in the grid map data. The second determination module includes a first determination sub-module and a second determination sub-module; The first determination sub-module is configured to determine the通行风险 (should be 'passing risk' in English) of the map area related to the adjacent point according to the area type of the map area related to the adjacent point. The grid map data includes a buffer zone, a no-fly zone, and a passing zone. The buffer zone is constructed by expanding the no-fly zone based on a preset safety expansion range. The no-fly zone is the area where obstacles are located, and the buffer zone is a flyable area; The second determining submodule is used to determine the safety cost of the adjacent points based on the distance between the starting point and the ending point and the passage risk. The safety cost of the adjacent points satisfies the following formula: = , This indicates the access risk of the map area related to adjacent points. Indicates the distance between the starting point and the ending point; A third determination module, configured to perform navigation cost detection on the initial flight path passing through the starting point, the adjacent point, and the end point, and determine the navigation cost related to the adjacent point. The navigation cost includes an estimated cost obtained by processing the position information of the adjacent point and the end point respectively using an evaluation function according to a second target weight. The second target weight is obtained by processing a second initial weight, an initial estimated cost, and the distance between the starting point and the end point using a power function. The second initial weight is determined based on a preset deviation path limit; A fourth determination module, configured to determine the target point from the multiple adjacent points according to the comparison results of the adjacent point costs corresponding to the multiple adjacent points respectively. The adjacent point cost is determined based on the safety cost and the navigation cost; A planning module, configured to perform flight path planning according to the starting point, the target point, and the end point to obtain a target flight path.

8. An electronic device, including: One or more processors; A memory, configured to store one or more computer programs, Characterized in that the one or more processors call the one or more computer programs to implement the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is invoked by the processor, it implements the steps of the method according to any one of claims 1 to 6.

Images