Method for determining obstacle avoidance track of unmanned vehicle and related device

Abstract

The invention provides an unmanned vehicle obstacle avoidance track determination method and a related device, and the method comprises the steps: obtaining an obstacle avoidance target three-dimensional model and a flight starting point and a flight ending point of an unmanned vehicle, and constructing a space detection grid body which comprises a plurality of target vertexes and corresponds to the obstacle avoidance target three-dimensional model; a spherical detector is arranged at each target vertex, the total collision volume of the spherical detectors from the target vertexes to the flight starting point and the flight ending point is calculated, and whether the target vertexes can serve as obstacle avoidance points is determined according to whether the total collision volume coincides with the obstacle avoidance target three-dimensional model or not. And if the collision total volume corresponding to each target vertex in the plurality of target vertexes does not coincide with the obstacle avoidance target three-dimensional model, determining the target vertex corresponding to the shortest distance of the unmanned vehicle from the flight starting point to the flight ending point through the target vertex as the target obstacle avoidance point, thereby reducing the number of the obstacle avoidance points, improving the effectiveness of the obstacle avoidance points, and improving the obstacle avoidance efficiency. And finally, the aerial photography efficiency is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of unmanned vehicle path planning, in particular to a method for determining an obstacle-avoiding path of an unmanned vehicle and related devices. BACKGROUND

[0002] Aerial modeling is a technology for quickly and widely obtaining a precise three-dimensional model of a target to be photographed by using an unmanned vehicle. When aerial photography is performed by using an unmanned vehicle, there may be a situation where an obstacle needs to be avoided. At present, the unmanned vehicle mainly relies on a visual obstacle-avoiding camera carried by itself to detect obstacles in the surrounding environment of the unmanned vehicle, so as to achieve flight obstacle avoidance. However, the visual obstacle-avoiding camera has poor obstacle-avoiding effect on high-reflective surface objects, water surfaces, branches or power lines, and the like. Therefore, a path planning algorithm can be used to plan a path of the unmanned vehicle, so as to achieve obstacle avoidance of the unmanned vehicle.

[0003] However, when the unmanned vehicle performs aerial photography, it needs to receive both a task action instruction and an obstacle avoidance instruction. Since there are many obstacle avoidance points in the current path planning algorithm, the unmanned vehicle cannot balance the number of the task action instruction and the obstacle avoidance instruction, which may eventually result in low aerial photography efficiency. SUMMARY

[0004] Therefore, the purpose of the present application is to provide a method for determining an obstacle-avoiding path of an unmanned vehicle and related devices, which can obtain a target obstacle avoidance point that can avoid obstacles and has the shortest path, reduce the number of obstacle avoidance points, improve the effectiveness of the obstacle avoidance points, and ultimately improve the aerial photography efficiency.

[0005] To achieve the above purpose, the present application has the following technical solutions:

[0006] The present application provides a method for determining an obstacle-avoiding path of an unmanned vehicle, comprising:

[0007] obtaining an obstacle avoidance target three-dimensional model and a flight start point and a flight end point of the unmanned vehicle;

[0008] constructing a space detection grid body corresponding to the obstacle avoidance target three-dimensional model, the space detection grid body comprising a plurality of micro unit grid bodies, and each micro unit grid body comprising a plurality of target vertices;

[0009] setting a spherical detector with a preset radius range at each target vertex, and calculating a collision volume from each target vertex to the flight start point and the flight end point of the spherical detector, wherein the preset radius range is an obstacle avoidance distance of the unmanned vehicle;

[0010] If the collision volume corresponding to each of the target vertices and the obstacle-avoiding target three-dimensional model has no overlapping part, a target vertex corresponding to the shortest distance of the unmanned vehicle from the flight starting point to the flight ending point through the target vertex is confirmed as a target obstacle-avoiding point.

[0011] Optionally, before the collision volumes of the spherical detector from the target vertex to the flight starting point and the flight ending point are calculated, the method further comprises:

[0012] The number of collision points of each of the spherical detector and the obstacle-avoiding target three-dimensional model is obtained, the collision points including intersection points and tangent points;

[0013] If the number of collision points of the spherical detector and the obstacle-avoiding target three-dimensional model is 0, the target vertex is confirmed as a candidate obstacle-avoiding point;

[0014] The calculation of the collision volumes of the spherical detector from the target vertex to the flight starting point and the flight ending point comprises:

[0015] The collision volumes of the spherical detector from the candidate obstacle-avoiding point to the flight starting point and the flight ending point are calculated.

[0016] Optionally, before the collision volumes of the spherical detector from the candidate obstacle-avoiding point to the flight starting point and the flight ending point are calculated, the method further comprises:

[0017] The sum of distances between each of the candidate obstacle-avoiding points and the flight starting point and the flight ending point is calculated, and the candidate obstacle-avoiding points are sorted in ascending order of the sum of distances to obtain a sorting result of the candidate obstacle-avoiding points;

[0018] The calculation of the collision volumes of the spherical detector from the candidate obstacle-avoiding point to the flight starting point and the flight ending point, if the collision volume corresponding to each of the target vertices and the obstacle-avoiding target three-dimensional model has no overlapping part, comprises:

[0019] The collision volumes of the spherical detector from the candidate obstacle-avoiding point to the flight starting point and the flight ending point are calculated in sequence according to the sorting result;

[0020] If the collision volume corresponding to each of the plurality of candidate obstacle avoidance points and the obstacle avoidance target three-dimensional model have no overlapping parts, the candidate obstacle avoidance point with the smallest sum of distances between the candidate obstacle avoidance point and the flight start point and the flight end point is determined as the target obstacle avoidance point.

[0021] Optionally, the plurality of candidate obstacle avoidance points include a first candidate obstacle avoidance point and a second candidate obstacle avoidance point.

[0022] The collision volumes of the spherical detector from the candidate obstacle avoidance points to the flight start point and the flight end point are calculated in sequence according to the sorting result; if the collision volume corresponding to each of the plurality of candidate obstacle avoidance points and the obstacle avoidance target three-dimensional model have no overlapping parts, the candidate obstacle avoidance point with the smallest sum of distances between the candidate obstacle avoidance point and the flight start point and the flight end point is determined as the target obstacle avoidance point.

[0023] The collision volume of the first candidate obstacle avoidance point is calculated according to the sorting result; if the collision volume corresponding to the first candidate obstacle avoidance point and the obstacle avoidance target three-dimensional model have overlapping parts, the collision volume of the second candidate obstacle avoidance point is calculated according to the sorting result.

[0024] If the collision volume corresponding to the second candidate obstacle avoidance point and the obstacle avoidance target three-dimensional model have no overlapping parts, the second candidate obstacle avoidance point is taken as the target obstacle avoidance point, and the step of calculating the collision volume of the candidate obstacle avoidance point according to the sorting result is ended.

[0025] Optionally, the method further includes:

[0026] The screening condition for the candidate obstacle avoidance points is obtained, and the screening condition at least includes the longitudinal height interval or the lateral position interval of the candidate obstacle avoidance points.

[0027] The plurality of candidate obstacle avoidance points are further screened according to the screening condition; if the plurality of candidate obstacle avoidance points do not meet the screening condition, the setting range of the spatial detection grid body is expanded to obtain the candidate obstacle avoidance points meeting the screening condition.

[0028] Optionally, the method further includes:

[0029] The spatial detection grid body corresponding to the obstacle avoidance target three-dimensional model is constructed, taking the line between the flight start point and the flight end point as the diagonal line of the spatial detection grid body, taking the midpoint of the line between the flight start point and the flight end point as the origin of the spatial detection grid body, and taking the vertical direction of the three-dimensional space corresponding to the target three-dimensional model as the reference.

[0030] The application provides a device for determining an obstacle-avoiding flight path of an unmanned carrier, comprising:

[0031] An acquisition unit is configured to acquire an obstacle-avoiding target three-dimensional model and a flight starting point and a flight ending point of the unmanned carrier.

[0032] A construction unit is configured to construct a space detection grid body corresponding to the obstacle-avoiding target three-dimensional model, wherein the space detection grid body comprises a plurality of micro unit grid bodies, and each micro unit grid body comprises a plurality of target vertices.

[0033] A calculation unit is configured to set a spherical detector with a preset radius range at each target vertex, and calculate a collision total volume from each target vertex to the flight starting point and the flight ending point of the spherical detector, wherein the preset radius range is an obstacle-avoiding distance of the unmanned carrier.

[0034] A determination unit is configured to determine a target obstacle-avoiding point as a target vertex corresponding to a shortest distance of the unmanned carrier from the flight starting point to the flight ending point through the target vertex, if the collision total volume corresponding to each target vertex in the plurality of target vertices and the obstacle-avoiding target three-dimensional model have no overlapping parts.

[0035] The application provides a device for determining an obstacle-avoiding flight path of an unmanned carrier, comprising a processor and a memory.

[0036] The memory is configured to store instructions.

[0037] The processor is configured to execute the instructions in the memory, and execute the method in any one of the above embodiments.

[0038] The application provides a computer readable storage medium for storing a computer program, when the computer program is run on a computer device, so that the computer device executes the method in any one of the above embodiments.

[0039] The application provides a computer program product, comprising a computer program, when the computer program is run on a computer device, so that the computer device executes the method in any one of the above embodiments.

[0040] The application provides a method for determining an obstacle-avoiding flight path of an unmanned carrier. The method comprises the following steps: obtaining an obstacle-avoiding target three-dimensional model, a flight starting point and a flight ending point of the unmanned carrier, constructing a space detection grid body corresponding to the obstacle-avoiding target three-dimensional model, the space detection grid body comprising a plurality of micro-unit grid bodies, and the micro-unit grid bodies comprising a plurality of target vertices, i.e. the target vertices of the space detection grid body can be used as obstacle-avoiding points of the obstacle-avoiding flight path of the unmanned carrier. A spherical detector with a preset radius range being an obstacle-avoiding distance of the unmanned carrier can be arranged at each target vertex, the collision total volume of the spherical detector from the target vertex to the flight starting point and the flight ending point is calculated, i.e. the total volume corresponding to the moving path of the spherical detector from the target vertex to the flight starting point and the flight ending point along a straight line is calculated, and then whether the target vertex can be used as an obstacle-avoiding point is determined according to whether the collision total volume and the obstacle-avoiding target three-dimensional model have overlapping parts. If the collision total volume corresponding to each target vertex in the plurality of target vertices and the obstacle-avoiding target three-dimensional model have no overlapping parts, the target vertex corresponding to the shortest distance of the unmanned carrier from the flight starting point to the flight ending point through the target vertex is confirmed as a target obstacle-avoiding point, i.e. the target vertex with the shortest path and capable of avoiding obstacles can be selected as the target obstacle-avoiding point, so that the number of obstacle-avoiding points is reduced, the effectiveness of the obstacle-avoiding points is improved, and finally the aerial photography efficiency is improved. BRIEF DESCRIPTION OF DRAWINGS

[0041] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor based on these drawings.

[0042] Figure 1 A flowchart of a method for determining an obstacle-avoiding flight path of an unmanned carrier provided by an embodiment of the present application is shown;

[0043] Figure 2 An obstacle-avoiding target three-dimensional model and a preset flight path provided by an embodiment of the present application are shown;

[0044] Figure 3 A structure diagram of a space detection grid body provided by an embodiment of the present application is shown;

[0045] Figure 4 A calculation diagram of a collision total volume provided by an embodiment of the present application is shown;

[0046] Figure 5 An intersection diagram of a collision total volume and an obstacle-avoiding target three-dimensional model provided by an embodiment of the present application is shown;

[0047] Figure 6 A non-coincidence diagram of a collision overall volume and an obstacle avoidance target three-dimensional model is shown;

[0048] Figure 7 A spherical detector setting diagram is shown;

[0049] Figures 8-10 A cross-section diagram of a plurality of spherical detectors and an obstacle avoidance target three-dimensional model is shown;

[0050] Figure 11 A screening condition screening alternative obstacle avoidance point diagram is shown;

[0051] Figure 12 Another screening condition screening alternative obstacle avoidance point diagram is shown;

[0052] Figure 13 A setting range determination target obstacle avoidance point diagram of an expanded space detection grid body is shown;

[0053] Figure 14 An auxiliary space detection grid body diagram is shown;

[0054] Figure 15 Another flow diagram of a method for determining an obstacle avoidance path of an unmanned carrier is shown;

[0055] Figure 16 A structure diagram of a device for determining an obstacle avoidance path of an unmanned carrier is shown. DETAILED DESCRIPTION

[0056] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the specific embodiments of the present application will be described in detail below with reference to the accompanying drawings.

[0057] In the following description, many specific details are set forth in order to provide a thorough understanding of the present application, but the present application can also be implemented in other ways different from those described herein, and those skilled in the art can make similar generalizations without departing from the spirit of the present application, therefore the present application is not limited to the specific embodiments disclosed below.

[0058] The present application is described in detail in conjunction with the schematic diagram, and in the detailed description of the embodiments of the present application, the cross-sectional view of the device structure will be partially enlarged without the general proportion for the convenience of description, and the schematic diagram is only an example, which should not limit the scope of protection of the present application herein. In addition, the three-dimensional spatial dimensions of length, width and depth should be included in actual manufacture.

[0059] When the path planning algorithm is used to plan the path of the unmanned vehicle, the unmanned vehicle needs to receive both the task action instruction and the obstacle avoidance instruction. For example, when the unmanned vehicle executes a programmed task, the unmanned vehicle implements a "flight file package" to achieve the task. Each "flight file package" contains 99 waypoints, and each waypoint can be independently set. When the waypoint is used for obstacle avoidance action, the unmanned vehicle cannot execute the task action instruction. Therefore, when the number of waypoints used for obstacle avoidance in a single "flight file package" is too large, the number of waypoints used for the task is greatly reduced, and the number of "flight file packages" is greatly increased to execute the same number of task waypoints. The execution of the task requires more time to frequently switch the flight file package. In order to improve the utilization rate of the "flight file package" and reduce the frequency of replacing the flight file package during the task, the number of waypoints used for obstacle avoidance should be reduced as much as possible, and the effectiveness of the obstacle avoidance waypoint should be increased to improve the efficiency of the task and shorten the task time.

[0060] That is, because there are too many obstacle avoidance points in the current path planning algorithm, the unmanned vehicle cannot balance the number of task action instructions and obstacle avoidance instructions, which may eventually result in low aerial photography efficiency.

[0061] In addition, most of the current path planning algorithms have the defect of dimension explosion, the algorithm structure is complex, and the obstacle avoidance point calculation time is long, which also leads to low aerial photography efficiency.

[0062] Therefore, the present application provides a method for determining an obstacle avoidance path of an unmanned vehicle. The method includes obtaining an obstacle target three-dimensional model and a flight starting point and a flight ending point of the unmanned vehicle, constructing a space detection grid body corresponding to the obstacle target three-dimensional model, the space detection grid body including a plurality of micro-unit grid bodies, and the micro-unit grid body including a plurality of target vertices. The target vertices of the space detection grid body can be used as obstacle avoidance points of the unmanned vehicle. A spherical detector with a preset radius range of the obstacle avoidance distance of the unmanned vehicle can be set at each target vertex. The collision total volume of the spherical detector from the target vertex to the flight starting point and the flight ending point is calculated, i.e. the total volume corresponding to the movement path of the spherical detector moving along a straight line from the target vertex to the flight starting point and the flight ending point is calculated. Then, whether the target vertex can be used as an obstacle avoidance point is determined according to whether the collision total volume overlaps the obstacle target three-dimensional model. If the collision total volume corresponding to each target vertex in the plurality of target vertices does not overlap the obstacle target three-dimensional model, the target vertex corresponding to the shortest distance of the unmanned vehicle from the flight starting point to the flight ending point is confirmed as the target obstacle avoidance point. That is, the target vertex with the shortest path that can avoid obstacles can be selected as the target obstacle avoidance point, thereby reducing the number of obstacle avoidance points, improving the effectiveness of the obstacle avoidance points, and ultimately improving the aerial photography efficiency.

[0063] In order to better understand the technical solutions and technical effects of the present application, specific embodiments will be described in detail below with reference to the accompanying drawings.

[0064] Reference Figure 1 As shown in FIG. 1, a flowchart of a method for determining an obstacle-avoiding flight path of an unmanned carrier provided by an embodiment of the present application is shown, and the method comprises the following steps:

[0065] S101, obtaining a three-dimensional model of an obstacle-avoiding target and a flight starting point and a flight ending point of the unmanned carrier.

[0066] In an embodiment of the present application, the three-dimensional model of the obstacle-avoiding target can be constructed and imported into a virtual three-dimensional space, so as to subsequently calculate the obstacle-avoiding flight path of the unmanned carrier according to the three-dimensional model of the obstacle-avoiding target. When the unmanned carrier is performing aerial photography, it usually flies according to a preset flight path. If the preset flight path is blocked by the obstacle-avoiding target, the obstacle-avoiding flight path needs to be recalculated. When recalculating the obstacle-avoiding flight path, the flight starting point and the flight ending point of the obstacle-avoiding flight path can be determined first, so as to calculate the obstacle-avoiding flight path according to the flight starting point and the flight ending point.

[0067] As an example, reference is made to FIG. 2, Figure 2 As shown in FIG. 2, Figure 2 The three-dimensional model of the obstacle-avoiding target and the preset flight path are shown in FIG. 2. Figure 2 As can be seen from FIG. 2, the A1-B1 section of the preset flight path is blocked by the obstacle-avoiding target, and the obstacle-avoiding flight path needs to be recalculated. At this time, the flight starting point and the flight ending point of the obstacle-avoiding flight path are A and B respectively.

[0068] S102, constructing a space detection grid body corresponding to the three-dimensional model of the obstacle-avoiding target.

[0069] In an embodiment of the present application, considering that the obstacle-avoiding flight path of the unmanned carrier between the flight starting point and the flight ending point needs to be replanned, a space detection grid body corresponding to the three-dimensional model of the obstacle-avoiding target can be constructed. Subsequently, the obstacle-avoiding points included in the obstacle-avoiding flight path can be calculated directly with the aid of the space detection grid body.

[0070] Specifically, the space detection grid body comprises a plurality of micro-unit grid bodies, and each micro-unit grid body comprises a plurality of target vertices. The connecting line between adjacent target vertices can form a micro-unit grid body. That is, a plurality of micro-unit grid bodies are stacked adjacent to each other to form a space detection grid body, and the plurality of stacked micro-unit grid bodies surround at least part of the three-dimensional model of the obstacle-avoiding target.

[0071] The size of the plurality of micro-unit grid bodies can be defined by itself, and the plurality of micro-unit grid bodies have the same and consistent properties. For example, the plurality of micro-unit grid bodies are cuboids of the same size, and the length, width and height of the cuboids can be defined by themselves.

[0072] Since the space exploration grid is a basic grid structure for subsequent calculation of obstacle avoidance points, the size of the plurality of micro-unit grid bodies, i.e., the density of the target vertices, can affect the obstacle avoidance accuracy and the calculation speed of the obstacle avoidance points. When the size of the micro-unit grid body is smaller, i.e., the density of the target vertices is higher, the obstacle avoidance path of the unmanned vehicle is shorter, but the number of target vertices that need to be screened when calculating the obstacle avoidance points is more, and the time for calculating the obstacle avoidance points is longer. Therefore, the density of the target vertices of the space exploration grid can be defined according to the actual situation, and the obstacle avoidance accuracy and the calculation speed of the obstacle avoidance points can be controlled.

[0073] When constructing the space exploration grid around the at least partial obstacle avoidance target three-dimensional model, the line between the flight starting point and the flight ending point can be taken as the diagonal line of the space exploration grid, the midpoint of the line between the flight starting point and the flight ending point can be taken as the origin of the space exploration grid, and the vertical direction of the three-dimensional space corresponding to the target three-dimensional model can be taken as the reference to construct the space exploration grid. In this way, the region of the minimum detection obstacle avoidance point can be established, the space exploration grid can be constructed in the simplest and most convenient way, and the computing resources consumed are less.

[0074] As an example, reference is made to Figure 3 , and Figure 3 , which illustrates the space exploration grid around the obstacle avoidance target three-dimensional model, and Figure 3 It can be seen from the figure that the diagonal line of the space exploration grid is the flight starting point A and the flight ending point B, the origin of the space exploration grid is the midpoint of the line between the flight starting point A and the flight ending point B, and the vertical direction of the space exploration grid is the vertical direction of the three-dimensional space corresponding to the obstacle avoidance target three-dimensional model, i.e., the vertical direction of the space exploration grid is consistent with the vertical direction of the obstacle avoidance target three-dimensional model.

[0075] S103, a spherical detector with a preset radius range is set at each target vertex, and the collision total volume of the spherical detector from the target vertex to the flight starting point and the flight ending point, respectively, is calculated.

[0076] In the embodiments of the present application, considering that the unmanned vehicle itself has a certain size and needs to fly safely for shooting at a fixed shooting distance, and also needs to avoid obstacles, a spherical detector with a preset radius range can be set at each target vertex of each micro-unit grid body after the space exploration grid corresponding to the obstacle avoidance target three-dimensional model is formed, wherein the preset radius range is the obstacle avoidance distance of the unmanned vehicle, for example, the obstacle avoidance distance can be the shooting distance of the unmanned vehicle. The collision total volume of the spherical detector from the target vertex to the flight starting point and the flight ending point, respectively, i.e., the total volume corresponding to the moving path of the unmanned vehicle from the flight starting point through the target vertex to the flight ending point, can be calculated.

[0077] Reference is made to Figure 4As shown, the target vertex can be point C, a spherical probe with a preset radius range is set from point C, and the collision total volume of the spherical probe from point C to the flight start point A and the flight end point B is calculated Figure 4 As shown, the cylinder from point C to the flight start point A shows the moving path of the spherical probe corresponding to point C to the flight start point A and the collision volume calculated when moving, and the moving distance is CA. The cylinder from point C to the flight end point B shows the moving path of the spherical probe corresponding to point C to the flight end point B and the collision volume calculated when moving, and the moving distance is CB. When calculating the collision total volume, two spherical probes can be set from point C, and the two spherical probes are moved to the flight start point A and the flight end point B respectively to calculate the collision volume from point C to the flight start point A and the collision volume from point C to the flight end point B respectively, and then the collision total volume is calculated. Figure 4 Different moving paths corresponding to different target vertices are shown, and different collision total volumes are calculated.

[0078] S104, if the collision total volume corresponding to each target vertex in the plurality of target vertices does not overlap with the obstacle avoidance target three-dimensional model, the target vertex corresponding to the shortest distance of the unmanned vehicle from the flight start point to the flight end point through the target vertex is determined as the target obstacle avoidance point.

[0079] In the embodiments of the present application, considering that the space detection grid body includes a plurality of target vertices, the corresponding collision total volume of each target vertex can be calculated, and it can be determined whether the collision total volume corresponding to any target vertex overlaps with the obstacle avoidance target three-dimensional model. If there is an overlapping part, it means that if the target vertex is an obstacle avoidance point, the unmanned vehicle cannot still avoid obstacles. If there is no overlapping part, it means that if the target vertex is an obstacle avoidance point, the unmanned vehicle can avoid obstacles. Therefore, if the collision total volume corresponding to each target vertex in the plurality of target vertices does not overlap with the obstacle avoidance target three-dimensional model, the plurality of target vertices corresponding to the non-overlapping parts can be determined as the obstacle avoidance points.

[0080] Reference Figure 5 As shown, the collision total volume corresponding to point C overlaps with the obstacle avoidance target three-dimensional model, that is, the collision total volume corresponding to point C intersects with the obstacle avoidance target three-dimensional model, which means that if the moving path of the unmanned vehicle is from the flight start point A to the flight end point B through point C, the unmanned vehicle cannot avoid the obstacle avoidance target three-dimensional model, and point C cannot be determined as an obstacle avoidance point.

[0081] Reference Figure 6As shown, the C point corresponds to no overlapping part between the collision volume and the obstacle avoidance target three-dimensional model, i.e., the C point corresponds to complete separation between the collision volume and the obstacle avoidance target three-dimensional model, which represents that the moving path of the unmanned carrier can avoid the obstacle avoidance target three-dimensional model if the unmanned carrier moves from the flight starting point A to the flight ending point B through the C point, and the C point is determined as the obstacle avoidance point.

[0082] Considering the energy consumption of the unmanned carrier during obstacle avoidance and the aerial photography task, the target vertex corresponding to the shortest distance from the flight starting point to the flight ending point of the unmanned carrier can be determined as the target obstacle avoidance point, i.e., the target vertex with the shortest moving path is selected from the multiple target vertices corresponding to no overlapping part as the target obstacle avoidance point, thereby meeting the actual short distance obstacle avoidance requirement.

[0083] Therefore, the method for determining the obstacle avoidance path of the unmanned carrier provided in the embodiments of the present application can construct a space detection grid body corresponding to the obstacle avoidance target three-dimensional model, and the target vertex of the space detection grid body can be used as the obstacle avoidance point of the obstacle avoidance path of the unmanned carrier. A spherical detector with a preset radius range as the obstacle avoidance distance of the unmanned carrier is set at each target vertex, and the collision volume of the spherical detector from the target vertex to the flight starting point and the flight ending point is calculated, i.e., the total volume corresponding to the moving path of the spherical detector from the target vertex to the flight starting point and the flight ending point along a straight line is calculated, and then whether the target vertex can be used as the obstacle avoidance point is determined according to whether the collision volume overlaps with the obstacle avoidance target three-dimensional model. If there is no overlapping part between the collision volume corresponding to each target vertex of the multiple target vertices and the obstacle avoidance target three-dimensional model, the target vertex corresponding to the shortest distance from the flight starting point to the flight ending point of the unmanned carrier is determined as the target obstacle avoidance point, i.e., the target vertex with the shortest path that can avoid the obstacle can be selected as the target obstacle avoidance point, thereby reducing the number of obstacle avoidance points, improving the effectiveness of the obstacle avoidance points, and finally improving the aerial photography efficiency. When the method provided in the embodiments of the present application is used for local obstacle avoidance, the number of local obstacle avoidance points is reduced to one, and when multiple similar local paths form a total path, the number of total obstacle avoidance points can be greatly reduced to reduce the number of obstacle avoidance instructions as much as possible to provide more space for the unmanned carrier to execute task instructions.

[0084] In the embodiments of the present application, considering that calculating the collision volume corresponding to multiple target vertices consumes a large amount of computing resources and a long calculation time, the target vertices with a low probability of being determined as obstacle avoidance points can be deleted first to avoid the calculation consumption of calculating the collision volume of the target vertices with a low probability of being determined as obstacle avoidance points.

[0085] Specifically, after setting the spherical probe at each target vertex, since the preset radius range of the spherical probe is the obstacle avoidance distance, the number of collision points of each spherical probe and the obstacle avoidance target three-dimensional model can be determined first, wherein the collision points include intersection points and tangent points. That is, whether each spherical probe and the obstacle avoidance target three-dimensional model at different target vertex positions intersect, are tangent to each other, or are not in contact is obtained. When intersecting, the number of collision points of each spherical probe and the obstacle avoidance target three-dimensional model is greater than 1, when tangent, the number of collision points of each spherical probe and the obstacle avoidance target three-dimensional model is equal to 1, and when not in contact, the number of collision points of each spherical probe and the obstacle avoidance target three-dimensional model is 0.

[0086] In order to determine the subsequent target vertex as an obstacle avoidance point, the number of collision points of each spherical probe and the obstacle avoidance target three-dimensional model can be used to screen the target vertex. Since the number of collision points of each spherical probe and the obstacle avoidance target three-dimensional model is 0, it means that the spherical probe and the obstacle avoidance target three-dimensional model are not in contact, thereby achieving the purpose of obstacle avoidance. That is, when the number of collision points of the spherical probe and the obstacle avoidance target three-dimensional model corresponding to the target vertex is 0, the target vertex is confirmed as a candidate obstacle avoidance point.

[0087] As an example, referring to FIG. 1, a spherical probe with a preset radius range is set at a target vertex, and the number of collision points of each spherical probe and the obstacle avoidance target three-dimensional model is obtained. As shown in FIG. 2, when the number of collision points of each spherical probe and the obstacle avoidance target three-dimensional model is equal to 0, the target vertex corresponding to the spherical probe is determined as a candidate obstacle avoidance point, and the coordinates of the target vertex are recorded. As shown in FIG. 3, when the number of collision points of each spherical probe and the obstacle avoidance target three-dimensional model is equal to 1, the target vertex corresponding to the spherical probe is deleted and does not participate in the subsequent process of calculating the total collision volume. As shown in FIG. 4, when the number of collision points of each spherical probe and the obstacle avoidance target three-dimensional model is greater than 1, for example, 2, the target vertex corresponding to the spherical probe is deleted and does not participate in the subsequent process of calculating the total collision volume. Figure 7 Figures 8-10 As an example, referring to FIG. 1, a spherical probe with a preset radius range is set at a target vertex, and the number of collision points of each spherical probe and the obstacle avoidance target three-dimensional model is obtained. As shown in FIG. 2, when the number of collision points of each spherical probe and the obstacle avoidance target three-dimensional model is equal to 0, the target vertex corresponding to the spherical probe is determined as a candidate obstacle avoidance point, and the coordinates of the target vertex are recorded. As shown in FIG. 3, when the number of collision points of each spherical probe and the obstacle avoidance target three-dimensional model is equal to 1, the target vertex corresponding to the spherical probe is deleted and does not participate in the subsequent process of calculating the total collision volume. As shown in FIG. 4, when the number of collision points of each spherical probe and the obstacle avoidance target three-dimensional model is greater than 1, for example, 2, the target vertex corresponding to the spherical probe is deleted and does not participate in the subsequent process of calculating the total collision volume. Figure 8 Figure 9 Figure 10

[0088] After screening a plurality of candidate obstacle avoidance points, only the total collision volume corresponding to the candidate obstacle avoidance points can be calculated, that is, only the total collision volume of the spherical probe from the candidate obstacle avoidance points to the flight starting point and the flight ending point is calculated, thereby reducing the consumption of computing resources and speeding up the determination speed of the target obstacle avoidance point.

[0089] ​​​​In the embodiments of the present application, considering that the selected spatial range is constructed with the flight starting point and the flight ending point as the diagonal line when constructing the spatial exploration grid, the target vertex is screened to obtain the candidate obstacle avoidance point, and at this time, in order to further reduce the calculation time and calculation resources of the subsequent calculation of the collision volume, the candidate obstacle avoidance point can be further screened to delete the candidate obstacle avoidance point that does not meet the screening condition.

[0090] Specifically, the screening condition for the candidate obstacle avoidance point can be obtained, and the screening condition at least includes the longitudinal height interval or the lateral position interval of the candidate obstacle avoidance point. The plurality of candidate obstacle avoidance points are further screened according to the screening condition. If there is a candidate obstacle avoidance point that meets the screening condition, the step of calculating the obstacle avoidance volume corresponding to the candidate obstacle avoidance point can be entered. If the plurality of candidate obstacle avoidance points do not meet the screening condition, the setting range of the spatial exploration grid is expanded to obtain the candidate obstacle avoidance point that meets the screening condition.

[0091] As an example, referring to FIG. 1, Figure 11 The candidate obstacle avoidance point is C point, the screening condition can be that the longitudinal height of C point is between the flight starting point A and the flight ending point B, and the lateral position of C point is between the flight starting point A and the flight ending point B. At this time, C point meets the screening condition, and the setting range of the spatial exploration grid can also meet the demand of screening the candidate obstacle avoidance point, so it is not necessary to adjust the setting range of the spatial exploration grid.

[0092] As another example, referring to FIG. 2, Figure 12 The candidate obstacle avoidance point is C point, the screening condition can be that the longitudinal height of C point is higher than the longitudinal height of the flight starting point A and the flight ending point B, and the lateral position of C point is not limited. At this time, C point located in the setting range of the current spatial exploration grid does not meet the screening condition, and the setting range of the spatial exploration grid cannot meet the demand of screening the candidate obstacle avoidance point, so it is necessary to adjust the setting range of the spatial exploration grid. The setting range of the spatial exploration grid can be expanded according to a preset proportion with the original point of the spatial exploration grid as the axis point, so that C point in the spatial exploration grid can meet the screening condition, as shown in FIG. 3. Figure 12 It can be seen that after the setting range of the spatial exploration grid is expanded, there is a C point that meets the screening condition in the spatial exploration grid.

[0093] In the embodiments of the present application, in order to quickly and orderly determine the target obstacle avoidance point from multiple candidate obstacle avoidance points, the sum of distances between each candidate obstacle avoidance point and the flight start point and the flight end point can be calculated, the multiple candidate obstacle avoidance points are sorted in ascending order of the sum of distances, and the sorting result of the multiple candidate obstacle avoidance points is obtained. The collision volume of the spherical detector from the candidate obstacle avoidance point to the flight start point and the flight end point is calculated in sequence according to the sorting result. If the collision volume corresponding to each candidate obstacle avoidance point in the multiple candidate obstacle avoidance points and the obstacle avoidance target three-dimensional model have no overlapping parts, the candidate obstacle avoidance point with the smallest sum of distances between the candidate obstacle avoidance point and the flight start point and the flight end point is determined as the target obstacle avoidance point. That is, by calculating the collision volume corresponding to the candidate obstacle avoidance point in ascending order of the sum of distances between each candidate obstacle avoidance point and the flight start point and the flight end point, the target obstacle avoidance point can be determined in order and efficiently.

[0094] In the embodiments of the present application, considering that the number of candidate obstacle avoidance points is large, the collision volume of the corresponding candidate obstacle avoidance point can be calculated in ascending order of the sum of distances between each candidate obstacle avoidance point and the flight start point and the flight end point. When the collision volume and the obstacle avoidance target three-dimensional model have no overlapping parts, the candidate obstacle avoidance point is directly determined as the target obstacle avoidance point, without the need to calculate the collision volume corresponding to the candidate obstacle avoidance point with a larger sum of distances, thereby greatly reducing the calculation time and consumed calculation resources for determining the target obstacle avoidance point.

[0095] Specifically, the multiple candidate obstacle avoidance points include a first candidate obstacle avoidance point and a second candidate obstacle avoidance point, and the sum of distances between the first candidate obstacle avoidance point and the flight start point and the flight end point is smaller than the sum of distances between the second candidate obstacle avoidance point and the flight start point and the flight end point. Therefore, the sorting is performed in ascending order of the sum of distances, and the order of the first candidate obstacle avoidance point in the sorting result is before the order of the second candidate obstacle avoidance point. The collision volume of the first candidate obstacle avoidance point is calculated according to the sorting result. If the collision volume corresponding to the first candidate obstacle avoidance point and the obstacle avoidance target three-dimensional model have no overlapping parts, the first candidate obstacle avoidance point is taken as the target obstacle avoidance point, and the step of calculating the collision volume of the second candidate obstacle avoidance point according to the sorting result is ended. If the collision volume corresponding to the first candidate obstacle avoidance point and the obstacle avoidance target three-dimensional model have overlapping parts, the collision volume of the second candidate obstacle avoidance point is continued to be calculated according to the sorting result. If the collision volume corresponding to the second candidate obstacle avoidance point and the obstacle avoidance target three-dimensional model have no overlapping parts, the second candidate obstacle avoidance point is taken as the target obstacle avoidance point, and the step of calculating the collision volume of other candidate obstacle avoidance points according to the sorting result is ended. That is, the collision volume corresponding to the candidate obstacle avoidance point is calculated from the shortest distance according to the ascending order of the sum of distances, and whether the candidate obstacle avoidance point is the target obstacle avoidance point is determined. When the candidate obstacle avoidance point is determined as the target obstacle avoidance point, the calculation cycle can be directly interrupted, and the calculation speed is greatly improved.

[0096] As an example, refer to Figure 4 As shown in FIG. 10, the alternative obstacle avoidance point is point C, the distances CA and CB between the coordinates of all the screened point C and the flight starting point A and the flight ending point B are calculated, the values of all CA+CB are calculated, and the coordinates of the CA+CB corresponding to the point C are sorted in ascending order of the values, and the coordinates of the CA+CB corresponding to the point C are placed in the set Z in the order. The first Z point coordinate stored in the set Z is selected, that is, the coordinate of the point C corresponding to the minimum value of CA+CB, and two spherical detectors are released at the point C. The two spherical detectors move in a straight line from the point C to the flight starting point A and the flight ending point B, respectively, and perform collision detection with the obstacle avoidance target three-dimensional model to calculate the collision volume. Figure 4 The value of CA+CB on the left side is smaller than that on the right side, so the collision volume corresponding to the left side point C can be calculated first. When the collision volume corresponding to the left side point C and the obstacle avoidance target three-dimensional model have overlapping parts, the collision volume corresponding to the right side point C is calculated. When the collision volume corresponding to the left side point C and the obstacle avoidance target three-dimensional model have no overlapping parts, the left side point C is directly determined as the target obstacle avoidance point, and the collision volume corresponding to the right side point C does not need to be calculated.

[0097] In the embodiments of the present application, if the collision volumes corresponding to all the alternative obstacle avoidance points are calculated according to the sorting results, and all the collision volumes corresponding to the alternative obstacle avoidance points have overlapping parts with the obstacle avoidance target three-dimensional model, it means that the setting range of the spatial detection grid body may be too small, and the setting range of the spatial detection grid body can be expanded to determine the target obstacle avoidance point. That is, the space for finding the obstacle avoidance point is quantized by the micro-unit grid body, and the space can be infinitely extended. If the required obstacle avoidance point cannot be found in one cycle, the setting range of the spatial detection grid body can be extended to increase the success probability of the large screening.

[0098] As an example, refer to Figure 13 As shown in FIG. 10, if the collision volumes corresponding to all the alternative obstacle avoidance points are calculated according to the sorting results, and all the collision volumes corresponding to the alternative obstacle avoidance points have overlapping parts with the obstacle avoidance target three-dimensional model, the original point of the spatial detection grid body can be taken as the axis point, and the setting range of the spatial detection grid body can be expanded according to a preset proportion. The steps of repeatedly determining the target obstacle avoidance point from the multiple target vertices included in the spatial detection grid body with the expanded setting range are continued, that is, the steps of S103 to S104 are continued.

[0099] In practical applications, if the total collision volume corresponding to all the candidate obstacle avoidance points is calculated according to the sorting result, and the total collision volume corresponding to all the candidate obstacle avoidance points all have overlapping parts with the obstacle avoidance target three-dimensional model, it can also be determined whether the current time exceeds the limit calculation time. If the limit calculation time is exceeded, the process of determining the target obstacle avoidance point is directly exited to avoid excessive consumption of computing resources and to wait for a long time to determine the obstacle avoidance track. If the current time does not exceed the limit calculation time, the setting range of the spatial detection grid body can be expanded, and the process of determining the target obstacle avoidance point is continued.

[0100] In the embodiments of the present application, in addition to the obstacle avoidance target three-dimensional model being a target that needs to be avoided by the unmanned carrier, other targets that need to be avoided cannot be identified by the obstacle avoidance target three-dimensional model, such as highly reflective objects, water surfaces, tree branches, or power lines, etc. At this time, auxiliary spatial detection grid bodies can be used to identify these targets that need to be avoided. The intersection operation of the auxiliary spatial detection grid body and the spatial detection grid body is performed, and the overlapping vertex cannot be determined as the target obstacle avoidance point, that is, the target vertex overlapping the spatial detection grid body and the auxiliary spatial detection grid body cannot be determined as the target obstacle avoidance point. The "auxiliary spatial detection grid body" can be used to improve the target vertex screening speed, thereby further shortening the determination time of the target obstacle avoidance point.

[0101] Reference is made to Figure 14 as shown, Figure 14 The middle red frame is an auxiliary spatial detection grid body. The auxiliary spatial detection grid body on the left is used to assist in marking the power line between the building eaves. The auxiliary spatial detection grid body on the right is used to mark the dangerous obstacle tree. Figure 14 The middle blue frame is a spatial detection grid body.

[0102] As an example, reference is made to Figure 15As shown, the method for determining an obstacle-avoiding flight path of an unmanned carrier provided in the embodiments of the present application can be displayed in the form of a flowchart. The obstacle-avoiding target three-dimensional model is imported into a virtual three-dimensional space and an obstacle-avoiding distance is set. When a line connecting the flight starting point and the flight ending point collides with the obstacle-avoiding target, a space detection grid body is constructed to find a target obstacle-avoiding point. A spherical detector with a preset radius range of the obstacle-avoiding distance is set at all target vertices of the space detection grid body. The number of collision points between the spherical detector and the obstacle-avoiding target three-dimensional model is judged. The target vertices with a collision point number of 0 are selected as candidate obstacle-avoiding points, and the coordinates of these candidate obstacle-avoiding points are recorded. The candidate obstacle-avoiding points are selected according to the selection condition. If the candidate obstacle-avoiding points do not meet the selection condition, the setting range of the space detection grid body is expanded. If the candidate obstacle-avoiding points meet the selection condition or there is no selection condition, the sum of distances between the multiple candidate obstacle-avoiding points and the flight starting point and the flight ending point is calculated. The candidate obstacle-avoiding points are sorted in ascending order of the sum of distances, and a sorting result is obtained. The coordinates of the candidate obstacle-avoiding points are put into a set Z according to the sorting result. The candidate obstacle-avoiding point with the smallest sum of distances is selected according to the sorting result to set a spherical detector. The total collision volume corresponding to the candidate obstacle-avoiding point is calculated. It is judged whether the total collision volume has overlapping parts with the obstacle-avoiding target three-dimensional model, or the number of collision points between the total collision volume and the obstacle-avoiding target three-dimensional model. If there is no overlapping part or the number of collision points is 0, the candidate obstacle-avoiding point is the nearest target obstacle-avoiding point to the flight starting point and the flight ending point. If there is an overlapping part or the number of collision points is greater than 0, it is judged whether the set Z is an empty set. If the set Z is not an empty set, the coordinates of the candidate obstacle-avoiding point corresponding to the smallest sum of distances in the set Z are deleted. If the set Z is an empty set, it is continuously judged whether the current time exceeds a limited calculation time. If the current time exceeds the limited calculation time, the operation is ended. If the current time does not exceed the limited calculation time, the setting range of the space detection grid body is expanded. The target vertices are reselected according to the selection condition.

[0103] Based on the method for determining an obstacle-avoiding flight path of an unmanned carrier provided in the above embodiments, the embodiments of the present application further provide a device for determining an obstacle-avoiding flight path of an unmanned carrier. Reference can be made to the above description of the method for determining an obstacle-avoiding flight path of an unmanned carrier. Figure 16 As shown, it is a structural schematic diagram of a device for determining an obstacle-avoiding flight path of an unmanned carrier provided in the embodiments of the present application. The device 200 for determining an obstacle-avoiding flight path of an unmanned carrier provided in the embodiments of the present application comprises:

[0104] The acquisition unit 210 is configured to acquire an obstacle-avoiding target three-dimensional model and a flight starting point and a flight ending point of an unmanned carrier.

[0105] The construction unit 220 is configured to construct a space detection grid body corresponding to the obstacle-avoiding target three-dimensional model. The space detection grid body comprises multiple micro-unit grid bodies, and the micro-unit grid body comprises multiple target vertices.

[0106] The computing unit 230 is configured to set a spherical detector with a preset radius range at each target vertex, and calculate collision volumes of the spherical detector from the target vertex to the flight start point and the flight end point, respectively, wherein the preset radius range is an obstacle avoidance distance of the UAV.

[0107] The determining unit 240 is configured to determine a target obstacle avoidance point corresponding to a target vertex with a shortest distance from the flight start point to the flight end point through the target vertex.

[0108] Optionally, before the computing unit 230 calculates the collision volumes of the spherical detector from the target vertex to the flight start point and the flight end point, respectively, the device further comprises an alternative obstacle avoidance point determining unit.

[0109] The alternative obstacle avoidance point determining unit is configured to:

[0110] If the number of collision points of the spherical detector and the obstacle avoidance target three-dimensional model is 0, the target vertex is determined as an alternative obstacle avoidance point.

[0111] The computing unit 230 is configured to:

[0112] Calculate the collision volumes of the spherical detector from the alternative obstacle avoidance point to the flight start point and the flight end point, respectively.

[0113] Optionally, before the computing unit 230 calculates the collision volumes of the spherical detector from the alternative obstacle avoidance point to the flight start point and the flight end point, respectively, the device further comprises a sorting unit.

[0114] The sorting unit is configured to:

[0115] Calculate a sum of distances between each alternative obstacle avoidance point and the flight start point and the flight end point, and sort the plurality of alternative obstacle avoidance points in ascending order of the sum of distances to obtain a sorting result of the plurality of alternative obstacle avoidance points.

[0116] The computing unit 230 is configured to:

[0117] According to the sorting result, calculate the collision volumes of the spherical detector from the alternative obstacle avoidance point to the flight start point and the flight end point, respectively.

[0118] If the collision volume corresponding to each of the plurality of candidate obstacle avoidance points and the obstacle avoidance target three-dimensional model have no overlapping parts, the candidate obstacle avoidance point with the smallest sum of distances between the flight start point and the flight end point and the candidate obstacle avoidance point is determined as the target obstacle avoidance point.

[0119] Optionally, the plurality of candidate obstacle avoidance points include a first candidate obstacle avoidance point and a second candidate obstacle avoidance point.

[0120] The computing unit 230 is configured to:

[0121] The collision volume of the first candidate obstacle avoidance point is calculated according to the sorting result, and if the obstacle avoidance volume corresponding to the first candidate obstacle avoidance point and the obstacle avoidance target three-dimensional model have overlapping parts, the collision volume of the second candidate obstacle avoidance point is calculated according to the sorting result.

[0122] The determining unit 240 is configured to:

[0123] If the obstacle avoidance volume corresponding to the second candidate obstacle avoidance point and the obstacle avoidance target three-dimensional model have no overlapping parts, the second candidate obstacle avoidance point is taken as the target obstacle avoidance point, and the step of calculating the collision volume of the candidate obstacle avoidance point according to the sorting result is ended.

[0124] Optionally, the device further includes a screening unit, which is configured to:

[0125] Obtain a screening condition for the candidate obstacle avoidance points, and the screening condition at least includes a longitudinal height interval or a lateral position interval of the candidate obstacle avoidance points.

[0126] Continue to screen the plurality of candidate obstacle avoidance points according to the screening condition, and if the plurality of candidate obstacle avoidance points do not meet the screening condition, the setting range of the space detection grid body is expanded to obtain a candidate obstacle avoidance point meeting the screening condition.

[0127] Optionally, the constructing unit 220 is configured to:

[0128] The line between the flight start point and the flight end point is taken as the diagonal line of the space detection grid body, the midpoint of the line between the flight start point and the flight end point is taken as the origin of the space detection grid body, and the vertical direction of the three-dimensional space corresponding to the target three-dimensional model is taken as the reference to construct the space detection grid body.

[0129] Based on the method for determining an obstacle avoidance path of an unmanned carrier provided in the above embodiments, the embodiments of the present application further provide a device for determining an obstacle avoidance path of an unmanned carrier, which comprises:

[0130] The processor and the memory can be connected through a bus or other means. In some embodiments of the present application, the processor and the memory can be connected through a bus or other means.

[0131] The memory can include read-only memory and random access memory, and provide instructions and data to the processor. A portion of the memory can also include NVRAM. The memory stores operating systems and operating instructions, executable modules or data structures, or subsets thereof, or expanded sets thereof, wherein the operating instructions can include various operating instructions for implementing various operations. The operating system can include various system programs for implementing various basic services and processing hardware-based tasks.

[0132] The processor controls the operation of the terminal device, and the processor can also be referred to as a CPU.

[0133] The method disclosed in the embodiments of the present application can be applied to a processor or implemented by the processor. The processor can be an integrated circuit chip with a processing capability. In the implementation process, each step of the above method can be completed by integrated logic circuits or instructions in the form of software in the processor. The processor mentioned above can be a general processor, DSP, ASIC, FPGA or other programmable logic device, discrete gate or transistor logic device, discrete hardware component. The disclosed methods, steps and logic block diagrams in the embodiments of the present application can be implemented or executed. The general processor can be a microprocessor or the processor can also be any conventional processor. The steps of the method disclosed in combination with the embodiments of the present application can be directly embodied as a hardware coding processor for execution, or a combination of hardware and software modules in the coding processor for execution. The software module can be located in a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, or other mature storage media in the art. The storage medium is located in the memory, and the processor reads the information in the memory and combines the hardware to complete the steps of the above method.

[0134] The embodiments of the present application also provide a computer readable storage medium for storing program codes, the program codes being used to execute any one of the embodiments of the method of the foregoing embodiments.

[0135] In the context of this application, a machine-readable medium can be a tangible medium that can contain or store program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. Machine-readable storage medium can include, but are not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the machine-readable storage medium can include, but are not limited to, an electrical connection based on one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0136] Note that the computer-readable medium described above in the application can be a computer-readable signal medium or a computer-readable storage medium or any combination thereof. The computer-readable storage medium may, for example, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus or device, or any combination of the above. More specific examples of the computer-readable storage medium can include, but are not limited to, an electrical connection based on one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In this application, the computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus or device. In this application, the computer-readable signal medium can include a data signal carried in a baseband or as a part of a carrier wave, which carries computer-readable program code. Such a propagated data signal can take many forms, including but not limited to an electromagnetic signal, an optical signal or any suitable combination of the above. The computer-readable signal medium can also be any computer-readable medium other than the computer-readable storage medium, which can send, propagate or transmit programs for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to a wire, an optical fiber, an RF (radio frequency) or the like, or any suitable combination of the above.

[0137] The terms "first", "second", "third", "fourth", "one", "another", "another", "one", "the other", "one", "another", "one" and "the" are intended to represent one or more elements. The words "including", "including" and "including" are inclusive and mean that in addition to the listed elements, other elements can also be included.

[0138] It should be noted that those of ordinary skill in the art can understand that all or part of the processes in the above method embodiments can be completed by a computer program instructing related hardware. The program can be stored in a computer readable storage medium. When the program is executed, it can include the processes of the above method embodiments. The storage medium can be a magnetic disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM).

[0139] Computer program code for carrying out operations of the present application can be written in one or more programming languages or combinations thereof, including object-oriented programming languages such as Java, Smalltalk, C++, and conventional procedural programming languages such as "C" language or similar programming languages. Program code can be executed entirely on a user computer, partially on a user computer, as a separate software package, partially on a user computer and partially on a remote computer, or entirely on a remote computer or server. In the case of remote computers, remote computers can be connected to user computers through any kind of network, including local area network (LAN) or wide area network (WAN), or can be connected to external computers (for example, using Internet service providers to connect through the Internet).

[0140] The embodiments of the present application also provide a computer program product, which, when running on a computer device, causes the computer device to execute any one of the methods of the preceding embodiments.

[0141] Each embodiment in the specification is described in a progressive manner, and the same or similar parts between each embodiment can be referred to each other. Each embodiment focuses on the difference from other embodiments. In particular, for the device embodiment, since it is basically similar to the method embodiment, it is described more simply, and the relevant part can be referred to the part of the method embodiment.

[0142] The above description is only the preferred embodiment of the present application, although the present application has been disclosed as above with the preferred embodiment, however, not to limit the present application. Any skilled person in the art, without departing from the scope of the technical scheme of the present application, can utilize the above disclosed methods and technical contents to make many possible changes and modifications to the technical scheme of the present application, or modify as equivalent embodiments of equivalent changes. Therefore, any simple modification, equivalent change and modification made to the above embodiments according to the technical essence of the present application, without departing from the content of the technical scheme of the present application, still belongs to the scope of protection of the technical scheme of the present application.

Claims

1. A method for determining the obstacle avoidance trajectory of an unmanned vehicle, characterized in that, The method comprises the following steps: obtaining a three-dimensional model of an obstacle avoidance target and a flight starting point and a flight ending point of an unmanned carrier; constructing a space exploration grid corresponding to the three-dimensional model of the obstacle avoidance target, the space exploration grid comprising a plurality of micro-unit grid bodies, and each micro-unit grid body comprising a plurality of target vertices; setting a spherical detector with a preset radius range at each target vertex, and calculating collision volumes of the spherical detector from the target vertex to the flight starting point and the flight ending point, respectively, the preset radius range being an obstacle avoidance distance of the unmanned carrier; if the collision volume corresponding to each target vertex among a plurality of target vertices and the three-dimensional model of the obstacle avoidance target have no overlapping parts, a target vertex corresponding to a shortest distance of the unmanned carrier from the flight starting point to the flight ending point through the target vertex is determined as a target obstacle avoidance point.

2. The method of claim 1, wherein, Before the collision volumes of the spherical detector from the target vertex to the flight starting point and the flight ending point are calculated, the method further comprises the following steps: obtaining a number of collision points of each spherical detector and the three-dimensional model of the obstacle avoidance target, the collision points comprising intersection points and tangent points; if the number of collision points of the spherical detector and the three-dimensional model of the obstacle avoidance target is 0, the target vertex is determined as a candidate obstacle avoidance point; the calculation of the collision volumes of the spherical detector from the target vertex to the flight starting point and the flight ending point comprises the following steps: calculating collision volumes of the spherical detector from the candidate obstacle avoidance point to the flight starting point and the flight ending point, respectively.

3. The method of claim 2, wherein, Before the collision volumes of the spherical detector from the candidate obstacle avoidance point to the flight starting point and the flight ending point are calculated, the method further comprises the following steps: calculating a sum of distances between each candidate obstacle avoidance point and the flight starting point and the flight ending point, sorting a plurality of candidate obstacle avoidance points in ascending order of the sum of distances to obtain a sorting result of the plurality of candidate obstacle avoidance points; the calculation of the collision volumes of the spherical detector from the candidate obstacle avoidance point to the flight starting point and the flight ending point, if the collision volume corresponding to each target vertex among a plurality of target vertices and the three-dimensional model of the obstacle avoidance target have no overlapping parts, a target vertex corresponding to a shortest distance of the unmanned carrier from the flight starting point to the flight ending point through the target vertex is determined as a target obstacle avoidance point, comprises the following steps: calculating the collision volumes of the spherical detector from the candidate obstacle avoidance point to the flight starting point and the flight ending point, respectively, in sequence according to the sorting result; if the collision volume corresponding to each candidate obstacle avoidance point among a plurality of candidate obstacle avoidance points and the three-dimensional model of the obstacle avoidance target have no overlapping parts, a candidate obstacle avoidance point with a minimum sum of distances between the candidate obstacle avoidance point and the flight starting point and the flight ending point is determined as a target obstacle avoidance point.

4. The method of claim 3, wherein, The plurality of candidate obstacle avoidance points comprise a first candidate obstacle avoidance point and a second candidate obstacle avoidance point. The collision volume of the spherical detector from each of the candidate obstacle avoidance points to the flight start point and the flight end point is calculated in sequence according to the sorting result; If the collision volume corresponding to each of the candidate obstacle avoidance points and the obstacle avoidance target three-dimensional model have no overlapping parts, the candidate obstacle avoidance point with the smallest sum of distances between the candidate obstacle avoidance point and the flight start point and the flight end point is determined as the target obstacle avoidance point, including: The collision volume of the first candidate obstacle avoidance point is calculated according to the sorting result, and if the collision volume corresponding to the first candidate obstacle avoidance point and the obstacle avoidance target three-dimensional model have overlapping parts, the collision volume of the second candidate obstacle avoidance point is calculated according to the sorting result; If the collision volume corresponding to the second candidate obstacle avoidance point and the obstacle avoidance target three-dimensional model have no overlapping parts, the second candidate obstacle avoidance point is taken as the target obstacle avoidance point, and the step of calculating the collision volume of the candidate obstacle avoidance point according to the sorting result is ended.

5. The method of claim 2, wherein, The method further includes: Obtaining a screening condition for the candidate obstacle avoidance points, the screening condition at least including a longitudinal height interval or a lateral position interval of the candidate obstacle avoidance points; According to the screening condition, the plurality of candidate obstacle avoidance points are continuously screened, and if the plurality of candidate obstacle avoidance points do not meet the screening condition, the setting range of the space detection grid body is expanded to obtain a candidate obstacle avoidance point meeting the screening condition.

6. The method of claim 1, wherein, The method further includes: The space detection grid body corresponding to the obstacle avoidance target three-dimensional model is constructed by taking the line segment between the flight start point and the flight end point as the diagonal line of the space detection grid body, taking the midpoint of the line segment between the flight start point and the flight end point as the origin of the space detection grid body, and taking the vertical direction of the three-dimensional space corresponding to the target three-dimensional model as the reference.

7. An apparatus for determining an obstacle-avoiding path of an unmanned carrier, characterized in that, The method further includes: An obtaining unit is configured to obtain an obstacle avoidance target three-dimensional model and a flight start point and a flight end point of an unmanned carrier; A constructing unit is configured to construct a space detection grid body corresponding to the obstacle avoidance target three-dimensional model, the space detection grid body including a plurality of micro unit grid bodies, and each micro unit grid body including a plurality of target vertices; A calculating unit is configured to set a spherical detector with a preset radius range at each target vertex, and calculate the collision volume of the spherical detector from each target vertex to the flight start point and the flight end point, the preset radius range being an obstacle avoidance distance of the unmanned carrier; A determining unit is configured to, if the collision volume corresponding to each target vertex and the obstacle avoidance target three-dimensional model have no overlapping parts, confirm the target vertex corresponding to the shortest distance of the unmanned carrier from the flight start point to the flight end point through the target vertex to the flight end point as a target obstacle avoidance point.

8. An unmanned vehicle obstacle avoidance path determination device, characterized by, The device includes a processor and a memory; The memory is configured to store instructions; The processor is configured to execute the instructions in the memory to execute the method in any one of claims 1-6. The device includes a processor and a memory; The memory is configured to store instructions; The processor is configured to execute the instructions in the memory to execute the method in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer readable storage medium is configured to store a computer program, and when the computer program is executed on the computer device, the computer device is caused to perform the method in any one of claims 1-6.

10. A computer program product comprising a computer program, characterized in that, The computer program is configured to cause the computer device to perform the method in any one of claims 1-6 when the computer program is executed on the computer device.

Images