Unmanned aerial vehicle track smoothing method, system, terminal device and storage medium

Abstract

The present invention discloses a method, system, terminal device and storage medium for smoothing the track of an unmanned aerial vehicle. The method comprises: obtaining the planned track of the unmanned aerial vehicle, detecting the track points of the planned track, and obtaining a threat distance set; determining the turning mode of each track point of the unmanned aerial vehicle according to the threat distance set, and obtaining an actual turning mode set; and obtaining a smooth track of the unmanned aerial vehicle based on the actual turning mode set and the coordinates of each track point of the unmanned aerial vehicle. The present invention takes into account the optimality and safety of the track at the same time during the track smoothing process, improves the quality of the smoothed track, and improves the efficiency of the unmanned aerial vehicle.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned aerial vehicles, and in particular to a method, system, terminal device and storage medium for smoothing the trajectory of an unmanned aerial vehicle. Background Art

[0002] As an efficient aerial survey and photography tool, drones have been widely used in surveying and mapping, power inspection, and security. When using drones to perform surveying, inspection, or security tasks, it is usually necessary to plan the mission route in advance at the ground station; at the same time, it is necessary to manually set the attributes of the waypoints, such as setting the turning waypoints as passing turns or early turns. These requirements are not user-friendly for ordinary users. At the same time, if the user chooses an inappropriate turning method, it may also bring unpredictable risks. At present, the track smoothing technology based on spline curves only achieves the smoothness of the track from a geometric perspective, without considering factors that affect the track quality, such as track safety and optimality. The resulting smooth track will be threatened by collisions with obstacles in the environment. Summary of the invention

[0003] The main purpose of the embodiments of the present invention is to provide a method, system, terminal device and storage medium for smoothing the trajectory of an unmanned aerial vehicle, aiming to take into account the optimality and safety of the trajectory during the trajectory smoothing process, improve the quality of the smoothed trajectory, and improve the efficiency of the unmanned aerial vehicle.

[0004] To achieve the above object, an embodiment of the present invention provides a method for smoothing the trajectory of an unmanned aerial vehicle, and the method for smoothing the trajectory of an unmanned aerial vehicle comprises:

[0005] Acquire the planned track of the UAV, detect the track points of the planned track, and obtain a threat distance set;

[0006] Determine the turning mode of each track point of the UAV according to the threat distance set to obtain an actual turning mode set;

[0007] Based on the actual turning pattern set and the coordinates of each track point of the UAV, a smooth track of the UAV is obtained.

[0008] Optionally, the step of detecting the track points of the planned track to obtain a threat distance set includes:

[0009] Performing collision detection on points in a preset direction of the current track point in the planned track, wherein the preset direction includes at least two directions;

[0010] If an obstacle is detected within the preset radius, the detection distance is calculated and recorded based on the current track point;

[0011] The detection distance with the largest value among the recorded detection distances is used as the threat distance of the current track point, and the threat distance is recorded;

[0012] Update the next track point of the current track point to the current track point, and return to the execution step: perform collision detection on the point position of the preset direction of the current track point in the planned track; terminate the loop until all track points of the planned track are traversed;

[0013] Based on the recorded threat distances, the threat distance set is obtained.

[0014] Optionally, the step of determining the turning mode of each track point of the UAV according to the threat distance set to obtain an actual turning mode set includes:

[0015] Based on the threat distance set, determining the number of turning modes corresponding to each track point of the UAV;

[0016] If the number of the turning patterns is one, the turning pattern is used as the actual turning pattern of the corresponding track point;

[0017] If the number of the turning patterns is greater than one, calculating the length of the first direction track segment and the length of the second direction track segment based on the track points corresponding to the turning patterns;

[0018] Based on the length of the first direction track segment and the length of the second direction track segment, obtaining an actual turning mode of the track point corresponding to the turning mode;

[0019] Based on the actual turning patterns of each track point of the UAV, the actual turning pattern set is obtained.

[0020] Optionally, the step of obtaining a smooth track of the UAV based on the actual turning pattern set and the coordinates of each track point of the UAV includes:

[0021] Based on the actual turning pattern set, the coordinates of the current track point of the drone, the coordinates of the next track point of the current track point of the drone, and the coordinates of the previous track point of the current track point of the drone, the coordinates of the center of the arc, the coordinates of the arc entry point, and the arc angle of the current track point of the drone are calculated;

[0022] Based on the arc center coordinates, arc entry point coordinates, and arc angle of the current track point of the drone, the arc cut-out point coordinates and the arc trajectory of the current track point of the drone are obtained;

[0023] Update the coordinates of the arc cut-out point of the current track point of the drone to the coordinates of the arc center of the next track point of the current track point of the drone, update the next track point of the current track point of the drone to the current track point of the drone, and return to the execution step: based on the actual turning mode set, the coordinates of the current track point of the drone, the coordinates of the next track point of the current track point of the drone, and the coordinates of the previous track point of the current track point of the drone, calculate the coordinates of the arc center, the coordinates of the arc cut-in point, and the arc angle of the current track point of the drone; until the track points of the planned track are traversed, the loop is terminated;

[0024] The smooth track is obtained based on the arc track of each track point of the UAV.

[0025] Optionally, the step of calculating the coordinates of the center of the arc, the coordinates of the arc entry point, and the arc angle of the current track point of the drone based on the actual turning mode set, the coordinates of the current track point of the drone, the coordinates of the next track point of the current track point of the drone, and the coordinates of the previous track point of the current track point of the drone includes:

[0026] Obtaining a first vector based on the actual turning pattern set, the coordinates of the current track point of the drone, and the coordinates of the arc entry point of the current track point of the drone; or

[0027] The first vector is obtained based on the actual turning pattern set, the coordinates of the current track point of the drone, and the coordinates of the previous track point of the current track point of the drone; or

[0028] Obtaining the first vector based on the actual turning pattern set, the coordinates of the current track point of the drone, and the coordinates of the next track point of the current track point of the drone;

[0029] Rotate the first vector to obtain a second vector;

[0030] Based on the second vector and the current track point of the drone, the coordinates of the center of the arc of the current track point of the drone are obtained, the next track point of the current track point of the drone is updated to the current track point of the drone, and the execution step is returned: based on the actual turning mode set, the coordinates of the current track point of the drone, and the coordinates of the arc entry point of the current track point of the drone, the first vector is obtained; or, based on the actual turning mode set, the coordinates of the current track point of the drone, and the coordinates of the previous track point of the current track point of the drone, the first vector is obtained; or, based on the actual turning mode set, the coordinates of the current track point of the drone, and the coordinates of the next track point of the current track point of the drone, the first vector is obtained; until the track points of the planned track are traversed, the loop is terminated.

[0031] Optionally, the step of rotating the first vector to obtain the second vector includes:

[0032] Determine whether the current track point corresponding to the first vector is a counterclockwise rotation point;

[0033] If the current track point corresponding to the first vector is a counterclockwise rotation point, the unit vector of the first vector is rotated counterclockwise by a preset angle to obtain the second vector;

[0034] If the current track point corresponding to the first vector is not a counterclockwise rotation point, the unit vector of the first vector is rotated clockwise by the preset angle to obtain the second vector.

[0035] Optionally, after the step of determining the number of turning modes corresponding to each track point of the drone based on the threat distance set, the step includes:

[0036] If the number of the turning patterns is greater than one, a horizontal turning angle is calculated according to the track points corresponding to the turning patterns to obtain a horizontal turning angle;

[0037] Based on the horizontal turning angle and the turning pattern, obtaining an actual turning pattern of a track point corresponding to the turning pattern;

[0038] Based on the actual turning patterns of each track point of the UAV, the actual turning pattern set is obtained.

[0039] Optionally, after the step of determining the number of turning modes corresponding to each track point of the drone based on the threat distance set, the step includes:

[0040] If the number of the turning modes is greater than one, the maximum offset distance is calculated according to the maximum offset distance calculation formula corresponding to the turning mode to obtain a maximum offset distance set;

[0041] Based on the maximum offset distance set and the turning pattern, obtaining an actual turning pattern of a track point corresponding to the turning pattern;

[0042] Based on the actual turning patterns of each track point of the UAV, the actual turning pattern set is obtained.

[0043] In addition, to achieve the above-mentioned purpose, the present invention also provides a track smoothing system for an unmanned aerial vehicle, the system comprising:

[0044] A detection module, used to obtain the planned track of the UAV, and detect the track points of the planned track to obtain a threat distance set;

[0045] A determination module, configured to determine a turning mode of each track point of the UAV according to the threat distance set, and obtain an actual turning mode set;

[0046] A generation module is used to obtain a smooth track of the UAV based on the actual turning pattern set and the coordinates of each track point of the UAV.

[0047] In addition, to achieve the above-mentioned purpose, the present invention also provides a terminal device, which includes: a memory, a processor, and a method for smoothing the trajectory of an unmanned aerial vehicle stored in the memory and executable on the processor. When the program for smoothing the trajectory of the unmanned aerial vehicle is executed by the processor, the steps of the method for smoothing the trajectory of the unmanned aerial vehicle as described above are implemented.

[0048] In addition, to achieve the above-mentioned purpose, the present invention also provides a computer-readable storage medium, on which a program for smoothing the trajectory of an unmanned aerial vehicle is stored. When the program for smoothing the trajectory of an unmanned aerial vehicle is executed by a processor, the steps of the method for smoothing the trajectory of an unmanned aerial vehicle as described above are implemented.

[0049] The unmanned aerial vehicle track smoothing method, system, terminal device and storage medium proposed in the embodiments of the present invention obtain the planned track of the unmanned aerial vehicle, detect the track points of the planned track, and obtain a threat distance set; determine the turning mode of each track point of the unmanned aerial vehicle according to the threat distance set to obtain an actual turning mode set; obtain the smooth track of the unmanned aerial vehicle based on the actual turning mode set and the coordinates of each track point of the unmanned aerial vehicle. The present invention improves the safety of the flight track by traversing the track points of the planned track to detect obstacles in the planned track; when an obstacle is detected, the turning mode and the smooth track are determined according to the distance between the unmanned aerial vehicle and the obstacle to avoid the obstacle, thereby improving the quality of the smoothed track and improving the efficiency of the unmanned aerial vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 It is a schematic diagram of the functional modules of the terminal device to which the track smoothing device of the UAV of the present invention belongs;

[0051] Figure 2 It is a schematic diagram of the flow chart of the first embodiment of the method for smoothing the trajectory of an unmanned aerial vehicle of the present invention;

[0052] Figure 3 A schematic diagram of the division of turning areas involved in the track smoothing method of the UAV of the present invention;

[0053] Figure 4 A schematic diagram of an inscribed turning track involved in the track smoothing method of the UAV of the present invention;

[0054] Figure 5 A schematic diagram of a turning trajectory around a point involved in the trajectory smoothing method of the UAV of the present invention;

[0055] Figure 6A schematic diagram of a pressure point turning track involved in the track smoothing method of the UAV of the present invention;

[0056] Figure 7 A schematic diagram of a point-turning track involved in the track smoothing method of the UAV of the present invention;

[0057] Figure 8 It is a flow chart of a second embodiment of the method for smoothing the trajectory of an unmanned aerial vehicle of the present invention;

[0058] Fig. 9 A schematic diagram of a track pipeline evaluation method for a UAV according to the present invention;

[0059] Fig.10 It is a schematic diagram of the variation trend of the maximum deviation distance of the track involved in the track smoothing method of the UAV of the present invention with the horizontal turning angle;

[0060] Fig.11 A schematic diagram of track smoothing involved in the track smoothing method of the UAV of the present invention;

[0061] Fig.12 The figure is a schematic diagram of the functional modules of the track smoothing system of the UAV of the present invention.

[0062] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0063] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0064] The main solution of the embodiment of the present invention is: obtaining the planned track of the UAV, and detecting the track points of the planned track to obtain a threat distance set; determining the turning mode of each track point of the UAV according to the threat distance set to obtain an actual turning mode set; based on the actual turning mode set and the coordinates of each track point of the UAV, obtaining a smooth track of the UAV.

[0065] As an efficient aerial survey and photography tool, drones have been widely used in surveying and mapping, power inspections, and security. When using drones to perform surveying, inspections, or security tasks, it is usually necessary to plan the mission route in advance at the ground station; at the same time, it is necessary to manually set the attributes of the waypoints, such as setting the turning waypoints as passing turns or turning in advance. These requirements are not user-friendly. At the same time, if the user chooses an inappropriate turning method, it may also bring about unpredictable tracks or even the risk of crashing into the mountain. Even if the ground station has functions such as high-level route detection, high-level detection also needs to first discover the improper selection of the waypoint turning method, and then have personnel redesign the waypoint turning method, and repeat high-level inspections and other steps. This route planning method is inefficient.

[0066] At present, the track smoothing technology based on spline curves only achieves the smoothness of the track from a geometric perspective, but does not consider factors that affect the track quality, such as track safety and optimality. The track obtained after this track smoothing processing will inevitably differ from the original track in spatial position, which means that the smooth track will be threatened by collision with obstacles in the environment; moreover, the relevant technology requires manual design of the arc turning method, which is inefficient.

[0067] The present invention provides a solution, which takes into account both the optimality and safety of the track during track smoothing, improves the quality of the smoothed track, and improves the efficiency of the UAV.

[0068] Specifically, refer to Figure 1 , Figure 1 Schematic diagram of the functional modules of the terminal device to which the track smoothing device of the drone of the present invention belongs. The track smoothing device of the drone can be a device independent of the terminal device, capable of image processing and network model training, which can be carried on the terminal device in the form of hardware or software. The terminal device can be a smart mobile terminal with data processing function such as a mobile phone or a tablet computer, or a fixed terminal device or server with data processing function.

[0069] In this embodiment, the terminal device to which the track smoothing device of the UAV belongs includes at least an output module 110 , a processor 120 , a memory 130 and a communication module 140 .

[0070] The memory 130 stores the operation method and the track smoothing program of the drone; the output module 110 may be a display screen, etc. The communication module 140 may include a WIFI module, a mobile communication module, a Bluetooth module, etc., and communicates with an external device or server through the communication module 140.

[0071] When the drone track smoothing program in the memory 130 is executed by the processor, the following steps are implemented:

[0072] Acquire the planned track of the UAV, detect the track points of the planned track, and obtain a threat distance set;

[0073] Determine the turning mode of each track point of the UAV according to the threat distance set to obtain an actual turning mode set;

[0074] Based on the actual turning pattern set and the coordinates of each track point of the UAV, a smooth track of the UAV is obtained.

[0075] Furthermore, when the drone track smoothing program in the memory 130 is executed by the processor, the following steps are also implemented:

[0076] Performing collision detection on points in a preset direction of the current track point in the planned track, wherein the preset direction includes at least two directions;

[0077] If an obstacle is detected within the preset radius, the detection distance is calculated and recorded based on the current track point;

[0078] The detection distance with the largest value among the recorded detection distances is used as the threat distance of the current track point, and the threat distance is recorded;

[0079] Update the next track point of the current track point to the current track point, and return to the execution step: perform collision detection on the point position of the preset direction of the current track point in the planned track; terminate the loop until all track points of the planned track are traversed;

[0080] Based on the recorded threat distances, the threat distance set is obtained.

[0081] Furthermore, when the drone track smoothing program in the memory 130 is executed by the processor, the following steps are also implemented:

[0082] Based on the threat distance set, determining the number of turning modes corresponding to each track point of the UAV;

[0083] If the number of the turning patterns is one, the turning pattern is used as the actual turning pattern of the corresponding track point;

[0084] If the number of the turning patterns is greater than one, calculating the length of the first direction track segment and the length of the second direction track segment based on the track points corresponding to the turning patterns;

[0085] Based on the length of the first direction track segment and the length of the second direction track segment, obtaining an actual turning mode of the track point corresponding to the turning mode;

[0086] Based on the actual turning patterns of each track point of the UAV, the actual turning pattern set is obtained.

[0087] Furthermore, when the drone track smoothing program in the memory 130 is executed by the processor, the following steps are also implemented:

[0088] Based on the actual turning pattern set, the coordinates of the current track point of the drone, the coordinates of the next track point of the current track point of the drone, and the coordinates of the previous track point of the current track point of the drone, the coordinates of the center of the arc, the coordinates of the arc entry point, and the arc angle of the current track point of the drone are calculated;

[0089] Based on the arc center coordinates, arc entry point coordinates, and arc angle of the current track point of the drone, the arc cut-out point coordinates and the arc trajectory of the current track point of the drone are obtained;

[0090] Update the coordinates of the arc cut-out point of the current track point of the drone to the coordinates of the arc center of the next track point of the current track point of the drone, update the next track point of the current track point of the drone to the current track point of the drone, and return to the execution step: based on the actual turning mode set, the coordinates of the current track point of the drone, the coordinates of the next track point of the current track point of the drone, and the coordinates of the previous track point of the current track point of the drone, calculate the coordinates of the arc center, the coordinates of the arc cut-in point, and the arc angle of the current track point of the drone; until the track points of the planned track are traversed, the loop is terminated;

[0091] The smooth track is obtained based on the arc track of each track point of the UAV.

[0092] Furthermore, when the drone track smoothing program in the memory 130 is executed by the processor, the following steps are also implemented:

[0093] Obtaining a first vector based on the actual turning pattern set, the coordinates of the current track point of the drone, and the coordinates of the arc entry point of the current track point of the drone; or

[0094] The first vector is obtained based on the actual turning pattern set, the coordinates of the current track point of the drone, and the coordinates of the previous track point of the current track point of the drone; or

[0095] Obtaining the first vector based on the actual turning pattern set, the coordinates of the current track point of the drone, and the coordinates of the next track point of the current track point of the drone;

[0096] Rotate the first vector to obtain a second vector;

[0097] Based on the second vector and the current track point of the drone, the coordinates of the center of the arc of the current track point of the drone are obtained, the next track point of the current track point of the drone is updated to the current track point of the drone, and the execution step is returned: based on the actual turning mode set, the coordinates of the current track point of the drone, and the coordinates of the arc entry point of the current track point of the drone, the first vector is obtained; or, based on the actual turning mode set, the coordinates of the current track point of the drone, and the coordinates of the previous track point of the current track point of the drone, the first vector is obtained; or, based on the actual turning mode set, the coordinates of the current track point of the drone, and the coordinates of the next track point of the current track point of the drone, the first vector is obtained; until the track points of the planned track are traversed, the loop is terminated.

[0098] Furthermore, when the drone track smoothing program in the memory 130 is executed by the processor, the following steps are also implemented:

[0099] Determine whether the current track point corresponding to the first vector is a counterclockwise rotation point;

[0100] If the current track point corresponding to the first vector is a counterclockwise rotation point, the unit vector of the first vector is rotated counterclockwise by a preset angle to obtain the second vector;

[0101] If the current track point corresponding to the first vector is not a counterclockwise rotation point, the unit vector of the first vector is rotated clockwise by the preset angle to obtain the second vector.

[0102] Furthermore, when the drone track smoothing program in the memory 130 is executed by the processor, the following steps are also implemented:

[0103] If the number of the turning patterns is greater than one, a horizontal turning angle is calculated according to the track points corresponding to the turning patterns to obtain a horizontal turning angle;

[0104] Based on the horizontal turning angle and the turning pattern, obtaining an actual turning pattern of a track point corresponding to the turning pattern;

[0105] Based on the actual turning patterns of each track point of the UAV, the actual turning pattern set is obtained.

[0106] Furthermore, when the drone track smoothing program in the memory 130 is executed by the processor, the following steps are also implemented:

[0107] If the number of the turning modes is greater than one, the maximum offset distance is calculated according to the maximum offset distance calculation formula corresponding to the turning mode to obtain a maximum offset distance set;

[0108] Based on the maximum offset distance set and the turning pattern, obtaining an actual turning pattern of a track point corresponding to the turning pattern;

[0109] Based on the actual turning patterns of each track point of the UAV, the actual turning pattern set is obtained.

[0110] This embodiment uses the above scheme to obtain the planned track of the drone and detect the track points of the planned track to obtain a threat distance set; determine the turning mode of each track point of the drone according to the threat distance set to obtain an actual turning mode set; and obtain the smooth track of the drone based on the actual turning mode set and the coordinates of each track point of the drone. The present invention takes into account the optimality and safety of the track at the same time during the track smoothing process, improves the quality of the smoothed track, and improves the efficiency of the drone.

[0111] Based on the above terminal device architecture but not limited to the above architecture, an embodiment of the method of the present invention is proposed.

[0112] Reference Figure 2 , Figure 2 The figure is a flow chart of a first embodiment of a method for smoothing the trajectory of an unmanned aerial vehicle according to the present invention. The method for smoothing the trajectory of an unmanned aerial vehicle comprises:

[0113] Step S101, obtaining the planned track of the UAV, and detecting the track points of the planned track to obtain a threat distance set.

[0114] The executor of the method of this embodiment can be a track smoothing device of a UAV, or it can be a track smoothing terminal device or server of a UAV. This embodiment takes the track smoothing device of a UAV as an example. The track smoothing device of the UAV can be integrated in terminal devices such as UAVs, smart phones, tablet computers, etc. with data processing functions.

[0115] In order to improve the safety of UAV flight track and reduce the possibility of smooth track being threatened by collision with obstacles in the environment, firstly, the planned track of the UAV is obtained, and each track point of the planned track is detected by track pipeline evaluation technology. The threat distances of the track points in each direction of the planned track are calculated according to the detection results. The threat distance with the largest value among the track points of the planned track is used as the track safety evaluation index of the corresponding track point. The threat distance set of the planned track is composed of the threat distance with the largest value of each track point.

[0116] Therefore, the threat distance of each track point in the planned UAV track is calculated through the track pipeline evaluation technology, so as to determine the turning mode of the UAV at the corresponding track point according to the threat distance, improve the safety of the UAV flight track, and reduce the possibility of the UAV being threatened by collision with obstacles in the environment during flight.

[0117] Step S102, determining the turning pattern of each track point of the UAV according to the threat distance set to obtain an actual turning pattern set.

[0118] In this embodiment, the turning mode of each track point of the UAV is determined according to the calculated threat distance set, and the actual turning mode set is obtained based on the turning mode of each track point of the UAV. If the track point of the UAV does not have a threat distance, the planned track of the UAV is not changed, and the corresponding track point does not have a turning mode; if the track point of the UAV has a threat distance, the turning mode of the corresponding track point of the UAV is determined according to the calculated threat distance set.

[0119] Wherein, after step S102, the following steps are included:

[0120] Step A1, divide the surrounding area of ​​each track point of the planned track of the UAV to obtain a division result; wherein each part of the division result has a corresponding turning pattern.

[0121] Since the track obtained after track smoothing processing will inevitably differ from the original track in spatial position, this means that the smooth track will be threatened by collision with obstacles in the environment. In this embodiment, according to the spatial distribution characteristics of the four turning trajectories, the area around the turning track point is divided into four parts, such as Figure 3 Shown P i Indicates the current track point, P i-1 Indicates the previous track point of the current track point, P i+1 represents the next track point of the current track point, and d represents the threat distance; wherein the above four turning trajectories include the turning trajectories corresponding to the inward turn, the point-around turn, the point-pressure turn and the point-to-point turn.

[0122] Therefore, by corresponding the threat distance in the threat distance set to the above division result, the turning mode of the corresponding track point of the UAV can be determined.

[0123] Step S103, obtaining a smooth track of the UAV based on the actual turning pattern set and the coordinates of each track point of the UAV.

[0124] Since the UAV route is usually represented by a three-dimensional track point coordinate sequence, in this embodiment, based on the actual turning pattern set, a circular arc curve segment is inserted at each turning point of the planned track to obtain the circular arc trajectory of each track point of the UAV, and then the smooth track of the UAV is obtained, so as to improve the continuity of the UAV track by smoothing the track.

[0125] Among them, the common arc turning modes include inward turning, point-around turning, point-pressing turning and point-to-point turning. The corresponding arc trajectories are as follows: Figure 4-Figure 7 As shown. Let A be the starting point, B be the turning point, C be the end point, the curve segment be an arc with a radius equal to r, T be the entry point, T' be the exit point, α be the horizontal turning angle at B, α (0≤α≤π), δd be the maximum offset distance; the dotted line represents the original track, and the solid line represents the smoothed track. This embodiment combines the principles of track safety and optimality, selects a suitable turning mode for each track point, and performs corresponding trajectory solution to achieve track smoothing.

[0126] This embodiment uses the above scheme to obtain the planned track of the drone and detect the track points of the planned track to obtain a threat distance set; determine the turning mode of each track point of the drone according to the threat distance set to obtain an actual turning mode set; and obtain the smooth track of the drone based on the actual turning mode set and the coordinates of each track point of the drone. The present invention calculates the threat distance of each track point of the planned track of the drone through the track pipeline evaluation technology to determine the turning mode of the drone at the corresponding track point according to the threat distance, select a suitable turning mode for each track point, and perform corresponding trajectory solution, thereby improving the safety of the drone's flight track and reducing the possibility of the drone being threatened by collision with obstacles in the environment during flight.

[0127] Reference Figure 8 , Figure 8 This is a flow chart of the second embodiment of the method for smoothing the trajectory of a UAV of the present invention. Figure 2 In the embodiment shown, in this embodiment, step S101: obtaining the planned track of the UAV, and detecting the track points of the planned track, and obtaining the threat distance set includes:

[0128] Step S1011, performing collision detection on points in preset directions of the current track point in the planned track, wherein the preset directions include at least two directions.

[0129] Step S1012: If an obstacle is detected within the preset radius, the detection distance is calculated and recorded based on the current track point.

[0130] Step S1013: taking the detection distance with the largest value among the recorded detection distances as the threat distance of the current track point, and recording the threat distance.

[0131] Step S1014, updating the next track point of the current track point to the current track point, and returning to execute step S1011: performing collision detection on the point position in the preset direction of the current track point in the planned track; terminating the loop until all track points of the planned track are traversed.

[0132] Step S1015: obtaining the threat distance set based on the recorded threat distances.

[0133] As an implementation method, in this embodiment, in order to evaluate the safety of each area of ​​the planned flight path of the drone, it is necessary to perform a pipeline evaluation in the horizontal direction on each flight point of the planned flight path in advance, such as Fig. 9 As shown in the figure, with a certain safety radius D as the spacing, collision detection is performed on the positions of the preset directions on both sides of each track point; where D is the safety distance set according to the performance of the drone; d is the threat distance; R is the pipeline radius of the drone; and the preset direction includes the 360-degree full direction of the track point.

[0134] Specifically, for the i-th track point P in the planned track i (current track point), perpendicular to the horizontal plane In the direction of P i The points on the left and right sides are collided, and the detection is performed from near to far in each direction, and each detection distance increases by r=R / 10. If an obstacle is detected, the current detection distance is recorded, and the detection distance with the largest value in the recorded detection distance is used as the threat distance d of the current track point in the corresponding direction, and the next track point of the current track point is updated to the current track point, and the execution of step S1011 is returned: the point in the preset direction of the current track point in the planned track is collided; if the detection distance increases to R, and the current track point has been detected in both directions, and no obstacle is detected, the next track point of the current track point is updated to the current track point, and the execution of step S1011 is returned: the point in the preset direction of the current track point in the planned track is collided; wherein R is used as the above-mentioned preset radius; the threat distance represents the distance of the environmental obstacle relative to the track point in the specified direction. The loop is terminated until the track points of the planned track of the drone are traversed, and the threat distance set is obtained based on the threat distance of each track point. Among them, when conducting track pipeline assessment, the pipeline radius R should not be less than the turning radius r, and the threat distance of the track point in the safe direction defaults to infinity.

[0135] Therefore, by traversing each track point of the planned UAV track, the threat distance set of the UAV is obtained, and the turning mode of each track point of the UAV is determined according to the threat distance set. The appropriate turning mode is selected for each track point to improve the safety of the UAV flight track and reduce the possibility of the UAV being threatened by collision with obstacles in the environment during flight.

[0136] This embodiment uses the above scheme to obtain the planned track of the drone and detect the track points of the planned track to obtain a threat distance set; determine the turning mode of each track point of the drone according to the threat distance set to obtain an actual turning mode set; and obtain the smooth track of the drone based on the actual turning mode set and the coordinates of each track point of the drone. The present invention takes the safety of the track into consideration during the track smoothing process, and by traversing each track point of the planned track of the drone and selecting a suitable turning mode for each track point, the safety of the drone's flight track is improved, and the possibility of the drone being threatened by collision with obstacles in the environment during flight is reduced.

[0137] Based on the above Figure 2 The embodiment shown is a third embodiment of the method for smoothing the track of a UAV of the present invention. In this embodiment, step S102: determining the turning mode of each track point of the UAV according to the threat distance set, and obtaining the actual turning mode set includes:

[0138] Step S1021: Based on the threat distance set, determine the number of turning patterns corresponding to each track point of the UAV.

[0139] like Figure 3 As shown, Figure 3 It represents the threat distance obtained through the track pipeline evaluation. When selecting a turning mode, the safety of each turning mode can be evaluated by judging the safety of each turning area. Specifically, the inward turn corresponds to area 1, and the safety of this area is determined by the threat distance of the track point in the inner direction; the point-around turn corresponds to area 2, and the safety of this area is determined by the threat distance of the track point in the outer direction; the pressure-point turn corresponds to area 3, and the safety of this area is determined by the threat distance of the track point in the outer direction; the point-to-point turn corresponds to area 4, and the safety of this area is determined by the threat distance of the track point in the outer direction; among them, the turning mode corresponding to the area with the maximum threat distance should be selected as the actual turning mode of the corresponding track point as much as possible.

[0140] On the premise of ensuring the safety of the turning track, the optimality of the track should also be ensured, that is, the smoothed track should be as close to the original track as possible. In this embodiment, the concept of maximum offset distance δd is introduced as an indicator to evaluate the degree of track restoration. It represents the farthest distance between the corresponding track points of the smoothed track and the original track. The smaller δd is, the closer the smoothed track and the original track are to each other, and the better the track is.

[0141] The maximum offset distance in each turning mode is Figure 4-Figure 7 The calculation method is as follows:

[0142]

[0143] δd A =r

[0144] δd F =(1-cosα)r

[0145] δd T =(1-cosα)r

[0146] Among them, the subscripts I, A, F, and T correspond to inward turning, point-around turning, point-pressing turning, and point-to-point turning, respectively. From the above formulas, it can be seen that the maximum offset distances of the four arc turning modes have different trends with the change of the horizontal turning angle, such as Fig.10 shown.

[0147] Therefore, when selecting the optimal turning mode (actual turning mode), environmental threats act as a "hard constraint", which restricts the UAV to move within a safe turning area and ensures the safety of the track; while track optimality acts as a "soft requirement", which improves the quality of the track under the premise of track safety.

[0148] Since the threat distances of the track points of the planned UAV track may be located in multiple areas, and multiple areas correspond to multiple turning modes, when determining the turning mode of each UAV track point according to the threat distance set, it is necessary to first determine the number of turning modes corresponding to each UAV track point.

[0149] Step S1022: If the number of the turning patterns is one, the turning pattern is used as the actual turning pattern of the corresponding track point.

[0150] Step S1023: If the number of the turning patterns is greater than one, the length of the first direction track segment and the length of the second direction track segment are calculated based on the track points corresponding to the turning patterns.

[0151] Step S1024: obtaining the actual turning pattern of the track point corresponding to the turning pattern based on the length of the first direction track segment and the length of the second direction track segment.

[0152] Step S1025, obtaining the actual turning pattern set based on the actual turning patterns of each track point of the UAV.

[0153] If the number of turning patterns is one, the turning pattern is used as the actual turning pattern of the corresponding track point; if the number of turning patterns is greater than one, the first direction track segment length and the second direction track segment length are calculated based on the track point corresponding to the turning pattern; based on the first direction track segment length and the second direction track segment length, the actual turning pattern of the track point corresponding to the turning pattern is obtained; based on the actual turning pattern of each track point of the UAV, an actual turning pattern set is obtained.

[0154] For example, the turning modes of the track points determined by the threat distance are pressure point turning and point-to-point turning. Since the principles of pressure point turning and point-to-point turning are similar, Fig.10 It can be seen that for the same turning point, the maximum offset distances of the two turning modes are equal. When the turning areas corresponding to the two modes have the same safety or threat level, the track segment |P i-1 P i | and |P i P i+1 | to choose between the two modes. i-1 P i| is shorter, the pressure point turn is selected as the actual turning mode of the corresponding track point; otherwise, the point turn is used as the actual turning mode of the corresponding track point. This is to insert the arc track segment into the longer track segment, which is beneficial to the maneuverability and response of the drone when turning; among them, |P i-1 P i | as the length of the first direction track segment, and |P i P i+1 | is used as the length of the second direction track segment. Then, according to the actual turning patterns of each track point of the UAV, an actual turning pattern set is obtained.

[0155] It should be noted that, after step S1021, the following steps are also included:

[0156] Step B1, if the number of the turning patterns is greater than one, then the horizontal turning angle is calculated according to the track points corresponding to the turning patterns to obtain the horizontal turning angle.

[0157] Step B2, based on the horizontal turning angle and the turning pattern, obtaining the actual turning pattern of the track point corresponding to the turning pattern.

[0158] Step B3, obtaining the actual turning pattern set based on the actual turning patterns of each track point of the UAV.

[0159] If the number of turning patterns is greater than one, the horizontal turning angle is calculated according to the track points corresponding to the turning pattern to obtain the horizontal turning angle; based on the horizontal turning angle and the turning pattern, the actual turning pattern of the track points corresponding to the turning pattern is obtained; based on the actual turning patterns of each track point of the UAV, the actual turning pattern set is obtained.

[0160] For example, if the turning mode of the track point determined according to the threat distance is an inward turn or a point-around turn, the horizontal turning angle of the track point corresponding to the turning mode is further obtained; if the horizontal turning angle is not greater than 120°, the inward turn is used as the actual turning mode of the corresponding track point; if the horizontal turning angle is greater than 120°, the point-around turn is used as the actual turning mode of the corresponding track point. Then, based on the actual turning mode of each track point of the UAV, the actual turning mode set is obtained.

[0161] It should be noted that, after step S1021, the following steps are also included:

[0162] Step C1: if the number of the turning patterns is greater than one, a maximum offset distance is calculated according to a maximum offset distance calculation formula corresponding to the turning pattern to obtain a maximum offset distance set.

[0163] Step C2, based on the maximum offset distance set and the turning pattern, obtaining the actual turning pattern of the track point corresponding to the turning pattern.

[0164] Step C3, obtaining the actual turning pattern set based on the actual turning patterns of each track point of the UAV.

[0165] If the number of turning modes is greater than one, the maximum offset distance is calculated according to the maximum offset distance calculation formula corresponding to the turning mode to obtain a maximum offset distance set; based on the maximum offset distance set and the turning mode, the actual turning mode of the track point corresponding to the turning mode is obtained; based on the actual turning mode of each track point of the UAV, the actual turning mode set is obtained.

[0166] For example, if the turning mode of the track point determined according to the threat distance is greater than one, the maximum offset distance δd is further calculated according to the maximum offset distance calculation formula corresponding to the turning mode to obtain the maximum offset distance set; the smaller δd is, the closer the smooth track and the original track are, and the better the track is. Therefore, based on the maximum offset distance set and the turning mode, the turning mode corresponding to the maximum offset distance in the maximum offset distance set is obtained as the actual turning mode of the corresponding track point; based on the actual turning mode of each track point of the UAV, the actual turning mode set is obtained.

[0167] Therefore, under the premise of ensuring the safety of the track, the smoothed track is made as close to the optimal original track as possible. An arc turning strategy is designed, which comprehensively considers the safety and optimality of the track and realizes track smoothing based on arc turning.

[0168] Based on the above ideas, the turning mode selection strategy designed in this embodiment is shown in Table 1.

[0169] Table 1 Turning strategy table

[0170]

[0171] This embodiment uses the above scheme to obtain the planned track of the UAV and detect the track points of the planned track to obtain a threat distance set; determine the turning mode of each track point of the UAV according to the threat distance set to obtain an actual turning mode set; and obtain the smooth track of the UAV based on the actual turning mode set and the coordinates of each track point of the UAV. The track smoothing method proposed in the present invention can automatically select a track smoothing method based on multiple constraint considerations without manual intervention, greatly improving the efficiency of mission route planning. In the process of track smoothing, the optimality and safety of the track are taken into account at the same time, improving the quality of the smoothed track, and improving the efficiency of the UAV.

[0172] Based on the above Figure 2 The embodiment shown is a fourth embodiment of the method for smoothing the track of a drone of the present invention. In this embodiment, step S103: based on the actual turning pattern set and the coordinates of each track point of the drone, obtaining the smooth track of the drone includes:

[0173] Step S1031, based on the actual turning pattern set, the coordinates of the current track point of the drone, the coordinates of the next track point of the current track point of the drone, and the coordinates of the previous track point of the current track point of the drone, calculate the coordinates of the center of the arc, the coordinates of the arc entry point, and the arc angle of the current track point of the drone.

[0174] Step S1032, based on the arc center coordinates, arc entry point coordinates, and arc angle of the current track point of the drone, obtain the arc exit point coordinates of the current track point of the drone and the arc trajectory of the current track point of the drone.

[0175] In this embodiment, according to the actual turning mode set, the coordinates of the current track point B of the drone, the coordinates of the next track point C of the current track point of the drone, and the coordinates of the previous track point A of the current track point of the drone, the calculation formula of the arc center coordinates, the calculation formula of the arc entry point coordinates, and the calculation formula of the arc angle of the current track point of the drone are determined; based on the calculation formula of the arc center coordinates, the calculation formula of the arc entry point coordinates, and the calculation formula of the arc angle of the current track point, the arc center coordinates, the arc entry point coordinates, and the arc angle of the current track point of the drone are calculated. Based on the arc center coordinates, arc entry point coordinates, and arc angle of the current track point of the drone, the arc cut-out point coordinates of the current track point of the drone and the arc trajectory of the current track point of the drone are obtained.

[0176] It should be noted that step S1031 includes:

[0177] Step D1, obtaining a first vector based on the actual turning pattern set, the coordinates of the current track point of the UAV, and the coordinates of the arc entry point of the current track point of the UAV; or

[0178] Step D2, obtaining the first vector based on the actual turning pattern set, the coordinates of the current track point of the drone, and the coordinates of the previous track point of the current track point of the drone; or

[0179] Step D3, obtaining the first vector based on the actual turning pattern set, the coordinates of the current track point of the drone, and the coordinates of the next track point of the current track point of the drone.

[0180] Step D4, rotating the first vector to obtain a second vector.

[0181] Step D5, based on the second vector and the current track point of the drone, obtain the coordinates of the center of the arc of the current track point of the drone, update the next track point of the current track point of the drone to the current track point of the drone, and return to execute step D1: based on the actual turning mode set, the coordinates of the current track point of the drone, and the coordinates of the arc entry point of the current track point of the drone, obtain the first vector; or, return to execute step D2: based on the actual turning mode set, the coordinates of the current track point of the drone, and the coordinates of the previous track point of the current track point of the drone, obtain the first vector; or, return to execute step D3: based on the actual turning mode set, the coordinates of the current track point of the drone, and the coordinates of the next track point of the current track point of the drone, obtain the first vector; until the track points of the planned track are traversed, the loop is terminated.

[0182] Specifically, in this embodiment, based on the coordinates of the arc entry point of the current track point of the drone and the coordinates of the track point of the drone, the first vector is determined according to the actual turning mode of the current track point; based on the position of the current track point of the drone, the first vector is rotated to obtain the second vector; based on the second vector and the coordinates of the current track point of the drone, the coordinates of the center of the arc of the current track point of the drone are obtained, the next track point of the current track point of the drone is updated to the current track point of the drone, and the step D1 is returned to execute: based on the actual turning mode set, the coordinates of the current track point of the drone, and the coordinates of the arc entry point of the current track point of the drone, the first vector is obtained; or, the step D2 is returned to execute: based on the actual turning mode set, the coordinates of the current track point of the drone, and the coordinates of the previous track point of the current track point of the drone, the first vector is obtained; or, the step D3 is returned to execute: based on the actual turning mode set, the coordinates of the current track point of the drone, and the coordinates of the next track point of the current track point of the drone, the first vector is obtained; until the track points of the planned track are traversed, the loop is terminated.

[0183] Wherein, step D4 comprises:

[0184] Step E1, determining whether the current track point corresponding to the first vector is a counterclockwise rotation point.

[0185] Step E2: If the current track point corresponding to the first vector is a counterclockwise rotation point, the unit vector of the first vector is rotated counterclockwise by a preset angle to obtain the second vector.

[0186] Step E3: If the current track point corresponding to the first vector is not a counterclockwise rotation point, the unit vector of the first vector is rotated clockwise by the preset angle to obtain the second vector.

[0187] In this embodiment, based on the position of the current track point of the drone, when rotating the first vector, it is first determined whether the current track point corresponding to the first vector is a counterclockwise rotation point; if the current track point corresponding to the first vector is a counterclockwise rotation point, the unit vector of the first vector is rotated counterclockwise by a preset angle to obtain a second vector; if the current track point corresponding to the first vector is not a counterclockwise rotation point, the unit vector of the first vector is rotated clockwise by a preset angle to obtain a second vector; wherein, whether the track point is a counterclockwise rotation point is set according to the experience of ground personnel, and the range of the above preset angle is 0°-arc angle.

[0188] For example: The first method: If the current track point of the drone is determined to be an inward turn according to the actual turning mode set:

[0189] a) Find the arc entry point T

[0190] First, calculate the length of line segment BT:

[0191]

[0192] Then, calculate the entry point T coordinate:

[0193]

[0194] b) Find the center of the arc O

[0195] First, if B is a counterclockwise rotation point, then the vector The unit vector e TB Rotate 90 degrees counterclockwise to get the vector The unit vector e TO , otherwise the vector e TB Rotate 90 degrees clockwise to get e TO Among them, As the first vector, e TO As the second vector, then, calculate the coordinates of the arc center O:

[0196]

[0197] c) Find the arc angle

[0198] The arc angle of the inset turn is equal to the horizontal turning angle:

[0199] θ a =α

[0200] The second method: If the current track point of the drone is determined to be a point-to-point turn according to the actual turning mode set:

[0201] a) Find the arc entry point T

[0202] First, calculate the vector With vector The angle ∠ABT is:

[0203]

[0204] If B is the counterclockwise rotation point, then according to ∠ABT, the vector The unit vector e BA Counterclockwise to get vector The unit vector e BT , otherwise the vector e BA Rotate clockwise to get vector e BT Among them, As the first vector, e BT As the second vector, then, calculate the T coordinate of the entry point:

[0205]

[0206] b) Find the center of the arc O

[0207] The center O of the arc of the point-to-point turn is the track point B, as shown in the formula:

[0208] O=B

[0209] c) Find the arc angle

[0210] Similar to the track entry point T, the coordinates of the track exit point T' can be calculated, and then the arc angle can be obtained

[0211] θ a =2π-∠ABT-∠CBT′-∠ABC

[0212] The third method: If the current track point of the drone is determined to be a pressure-point turn according to the actual turning mode set:

[0213] a) Find the arc entry point T

[0214] The arc entry point T of the pressure point turn is the track point B:

[0215] T=B

[0216] b) Find the center of the arc O

[0217] If B is a counterclockwise rotation point, then the vector The unit vector e BA Rotate 90 degrees clockwise to get the vector The unit vector e BO , otherwise the vector e BA Rotate 90 degrees counterclockwise to get vector e BO Among them, As the first vector, e BO As the second vector, the coordinate of the arc center O is then calculated:

[0218]

[0219] c) Find the arc angle

[0220] First, calculate the vector With vector The angle ∠COT′:

[0221]

[0222] If B is the counterclockwise rotation point, then according to ∠COT′, the vector The unit vector e OC Rotate clockwise to get vector The unit vector e OT′ , otherwise the vector e OC Rotate counterclockwise to get vector e OT′ , then we can get the coordinates of the arc intersection point T':

[0223]

[0224] Finally judge the arc The advantages and disadvantages of calculating the arc angle θ a :

[0225]

[0226] Among them, if major arc means: if the arc is a major arc; if minor arc means: if the arc is a minor arc.

[0227] The fourth method: If the current track point of the drone is determined to be a point-to-point turn according to the actual turning mode set:

[0228] a) Find the center of the arc O

[0229] If B is a counterclockwise rotation point, then the vector The unit vector e BC Rotate 90 degrees counterclockwise to get the vector The unit vector e BO , otherwise the vector e BC Rotate 90 degrees clockwise to get vector e BO′ Among them, As the first vector, e BO 、e BO′ As the second vector, we can then get the coordinates of the arc center O:

[0230]

[0231] b) Find the arc entry point T

[0232] First, calculate the vector With vector The angle ∠AOT is:

[0233]

[0234] If B is the counterclockwise rotation point, then according to ∠AOT, the vector The unit vector e OA Rotate counterclockwise to get the vector The unit vector e OT , otherwise the vector e OA Rotate clockwise to get vector e OT , then we can get the coordinates of the arc entry point T:

[0235]

[0236] c) Find the arc angle

[0237] Finally judge the arc The advantages and disadvantages of calculating the arc angle

[0238]

[0239] Among them, if major arc means: if the arc is a major arc; if minor arc means: if the arc is a minor arc.

[0240] Furthermore, in this embodiment, the coordinates of the current track point and its two previous and next track points, the turning radius, the turning mode, the coordinates of the arc center O, the coordinates of the arc entry point T, and the arc angle are known. By adding the vector At a certain angle Rotation To obtain the coordinates of the arc cut-out point of the current track point.

[0241] Step S1033, update the coordinates of the arc cut-out point of the current track point of the UAV to the coordinates of the arc center of the next track point of the current track point of the UAV, update the next track point of the current track point of the UAV to the current track point of the UAV, and return to execute step S1031: based on the actual turning mode set, the coordinates of the current track point of the UAV, the coordinates of the next track point of the current track point of the UAV, and the coordinates of the previous track point of the current track point of the UAV, calculate the coordinates of the arc center of the current track point of the UAV, the coordinates of the arc cut-in point, and the arc angle; until the track points of the planned track are traversed, the loop is terminated.

[0242] Step S1034, obtaining the smooth track based on the arc track of each track point of the UAV.

[0243] In this embodiment, the coordinates of the arc cut-out point of the current track point of the drone are updated to the coordinates of the arc center of the next track point of the current track point of the drone, and the next track point of the current track point of the drone is updated to the current track point of the drone, and the execution returns to step S1031: based on the actual turning mode set, the coordinates of the current track point of the drone, the coordinates of the next track point of the current track point of the drone, and the coordinates of the previous track point of the current track point of the drone, the arc center coordinates, arc cut-in point coordinates, and arc angle of the current track point of the drone are calculated; until the track points of the planned track are traversed, the loop is terminated. Finally, based on the arc trajectory of each track point of the drone, a smooth track is obtained, such as Fig.11 As shown, Fig.11 It is the result of a certain track after smoothing, where the dotted line is the original planned track, the solid line is the smoothed track, and numbers 1 to 4 correspond to inward turns, point-around turns, pressure-point turns, and point-to-point turns, respectively.

[0244] Therefore, the coordinates of the arc cut-out point of the current track point are used as the coordinates of the arc center of the next track point of the current track point, so as to ensure the continuity and integrity of the smooth track and improve the quality of the smooth track.

[0245] This embodiment uses the above scheme to obtain the planned track of the drone and detect the track points of the planned track to obtain a threat distance set; determine the turning mode of each track point of the drone according to the threat distance set to obtain an actual turning mode set; and obtain the smooth track of the drone based on the actual turning mode set and the coordinates of each track point of the drone. Under the premise of ensuring the safety of the track, the present invention makes the smoothed track as close as possible to the optimal original track, greatly improving the efficiency of mission route planning, and using the coordinates of the arc cut-out point of the current track point as the coordinates of the arc center of the next track point of the current track point, thereby ensuring the continuity and integrity of the smooth track and improving the quality of the smooth track.

[0246] Reference Fig.12 , Fig.12 The following is a functional module diagram of the track smoothing system of the UAV of the present invention. The track smoothing system of the UAV includes:

[0247] The detection module 10 is used to obtain the planned track of the UAV and detect the track points of the planned track to obtain a threat distance set;

[0248] A determination module 20, configured to determine a turning mode of each track point of the UAV according to the threat distance set, and obtain an actual turning mode set;

[0249] The generating module 30 is used to obtain the smooth track of the UAV based on the actual turning pattern set and the coordinates of each track point of the UAV.

[0250] The principle and implementation process of achieving track smoothing of the UAV in this embodiment can be referred to the above embodiments and will not be described in detail here.

[0251] In addition, an embodiment of the present invention also proposes a terminal device, which includes a memory, a processor, and a drone track smoothing program stored in the memory and runable on the processor. When the drone track smoothing program is executed by the processor, the steps of the drone track smoothing method as described above are implemented.

[0252] Since all the technical solutions of all the aforementioned embodiments are adopted when the track smoothing program of the UAV is executed by the processor, it has at least all the beneficial effects brought by all the technical solutions of all the aforementioned embodiments, which will not be described one by one here.

[0253] In addition, an embodiment of the present invention also proposes a computer-readable storage medium, on which a drone track smoothing program is stored. When the drone track smoothing program is executed by a processor, the steps of the drone track smoothing method as described above are implemented.

[0254] Since all the technical solutions of all the aforementioned embodiments are adopted when the track smoothing program of the UAV is executed by the processor, it has at least all the beneficial effects brought by all the technical solutions of all the aforementioned embodiments, which will not be described one by one here.

[0255] Compared with the prior art, the present invention provides a method, system, terminal device and storage medium for smoothing the track of a drone, which obtains the planned track of the drone and detects the track points of the planned track to obtain a threat distance set; determines the turning mode of each track point of the drone according to the threat distance set to obtain an actual turning mode set; and obtains the smooth track of the drone based on the actual turning mode set and the coordinates of each track point of the drone. The present invention takes into account the optimality and safety of the track at the same time during the track smoothing process, improves the quality of the smoothed track, and improves the efficiency of the drone.

[0256] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or method including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or method. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or method including the element.

[0257] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0258] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as above, and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, a controlled terminal, or a network device, etc.) to execute the method of each embodiment of the present invention.

[0259] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for smoothing the trajectory of an unmanned aerial vehicle, characterized in that: The method comprises the following steps: Acquire the planned track of the UAV, detect the track points of the planned track, and obtain a threat distance set; Determine the turning mode of each track point of the UAV according to the threat distance set to obtain an actual turning mode set; Based on the actual turning pattern set and the coordinates of each track point of the UAV, a smooth track of the UAV is obtained; The step of determining the turning mode of each track point of the UAV according to the threat distance set to obtain the actual turning mode set comprises: Based on the threat distance set, determining the number of turning modes corresponding to each track point of the UAV; If the number of the turning patterns is one, the turning pattern is used as the actual turning pattern of the corresponding track point; If the number of the turning patterns is greater than one, calculating the length of the first direction track segment and the length of the second direction track segment based on the track points corresponding to the turning patterns; Based on the length of the first direction track segment and the length of the second direction track segment, obtaining an actual turning mode of the track point corresponding to the turning mode; Based on the actual turning patterns of each track point of the UAV, the actual turning pattern set is obtained; The step of determining the turning mode of each track point of the UAV according to the threat distance set to obtain an actual turning mode set also includes: Divide the surrounding area of ​​each track point of the planned track of the UAV to obtain a division result; wherein each part of the division result has a corresponding turning mode, and the turning mode includes an inward turn, a point-around turn, a point-pressure turn, and a point-to-point turn; The threat distance set is matched with the division result, the turning mode of each track point of the UAV is determined, and an actual turning mode set is obtained.

2. The method for smoothing the trajectory of an unmanned aerial vehicle according to claim 1, characterized in that: The step of detecting the track points of the planned track to obtain a threat distance set comprises: Performing collision detection on points in a preset direction of the current track point in the planned track, wherein the preset direction includes at least two directions; If an obstacle is detected within the preset radius, the detection distance is calculated and recorded based on the current track point; The detection distance with the largest value among the recorded detection distances is used as the threat distance of the current track point, and the threat distance is recorded; Update the next track point of the current track point to the current track point, and return to the execution step: perform collision detection on the point position of the preset direction of the current track point in the planned track; terminate the loop until all track points of the planned track are traversed; Based on the recorded threat distances, the threat distance set is obtained.

3. The method for smoothing the trajectory of an unmanned aerial vehicle according to claim 1, characterized in that: The step of obtaining a smooth track of the UAV based on the actual turning pattern set and the coordinates of each track point of the UAV comprises: Based on the actual turning pattern set, the coordinates of the current track point of the drone, the coordinates of the next track point of the current track point of the drone, and the coordinates of the previous track point of the current track point of the drone, the coordinates of the center of the arc, the coordinates of the arc entry point, and the arc angle of the current track point of the drone are calculated; Based on the arc center coordinates, arc entry point coordinates, and arc angle of the current track point of the drone, the arc cut-out point coordinates and the arc trajectory of the current track point of the drone are obtained; Update the coordinates of the arc cut-out point of the current track point of the drone to the coordinates of the arc center of the next track point of the current track point of the drone, update the next track point of the current track point of the drone to the current track point of the drone, and return to the execution step: based on the actual turning mode set, the coordinates of the current track point of the drone, the coordinates of the next track point of the current track point of the drone, and the coordinates of the previous track point of the current track point of the drone, calculate the coordinates of the arc center, the coordinates of the arc cut-in point, and the arc angle of the current track point of the drone; until the track points of the planned track are traversed, the loop is terminated; The smooth track is obtained based on the arc track of each track point of the UAV.

4. The method for smoothing the trajectory of an unmanned aerial vehicle according to claim 3, characterized in that: The step of calculating the coordinates of the center of the arc, the coordinates of the arc entry point, and the arc angle of the current track point of the drone based on the actual turning pattern set, the coordinates of the current track point of the drone, the coordinates of the next track point of the current track point of the drone, and the coordinates of the previous track point of the current track point of the drone includes: Obtaining a first vector based on the actual turning pattern set, the coordinates of the current track point of the drone, and the coordinates of the arc entry point of the current track point of the drone; or The first vector is obtained based on the actual turning pattern set, the coordinates of the current track point of the drone, and the coordinates of the previous track point of the current track point of the drone; or Obtaining the first vector based on the actual turning pattern set, the coordinates of the current track point of the drone, and the coordinates of the next track point of the current track point of the drone; Rotate the first vector to obtain a second vector; Based on the second vector and the current track point of the drone, the coordinates of the center of the arc of the current track point of the drone are obtained, the next track point of the current track point of the drone is updated to the current track point of the drone, and the execution step is returned: based on the actual turning mode set, the coordinates of the current track point of the drone, and the coordinates of the arc entry point of the current track point of the drone, the first vector is obtained; or, based on the actual turning mode set, the coordinates of the current track point of the drone, and the coordinates of the previous track point of the current track point of the drone, the first vector is obtained; or, based on the actual turning mode set, the coordinates of the current track point of the drone, and the coordinates of the next track point of the current track point of the drone, the first vector is obtained; until the track points of the planned track are traversed, the loop is terminated.

5. The method for smoothing the trajectory of an unmanned aerial vehicle according to claim 4, characterized in that: The step of rotating the first vector to obtain the second vector comprises: Determine whether the current track point corresponding to the first vector is a counterclockwise rotation point; If the current track point corresponding to the first vector is a counterclockwise rotation point, the unit vector of the first vector is rotated counterclockwise by a preset angle to obtain the second vector; If the current track point corresponding to the first vector is not a counterclockwise rotation point, the unit vector of the first vector is rotated clockwise by the preset angle to obtain the second vector.

6. The method for smoothing the trajectory of an unmanned aerial vehicle according to claim 1, characterized in that: The step of determining the number of turning modes corresponding to each track point of the UAV based on the threat distance set includes: If the number of the turning patterns is greater than one, a horizontal turning angle is calculated according to the track points corresponding to the turning patterns to obtain a horizontal turning angle; Based on the horizontal turning angle and the turning pattern, obtaining an actual turning pattern of a track point corresponding to the turning pattern; Based on the actual turning patterns of each track point of the UAV, the actual turning pattern set is obtained.

7. The method for smoothing the trajectory of an unmanned aerial vehicle according to claim 1, characterized in that: The step of determining the number of turning modes corresponding to each track point of the UAV based on the threat distance set includes: If the number of the turning modes is greater than one, the maximum offset distance is calculated according to the maximum offset distance calculation formula corresponding to the turning mode to obtain a maximum offset distance set; Based on the maximum offset distance set and the turning pattern, obtaining an actual turning pattern of a track point corresponding to the turning pattern; Based on the actual turning patterns of each track point of the UAV, the actual turning pattern set is obtained.

8. A track smoothing system for an unmanned aerial vehicle, characterized in that: include: A detection module, used to obtain the planned track of the UAV, and detect the track points of the planned track to obtain a threat distance set; A determination module, configured to determine a turning mode of each track point of the UAV according to the threat distance set, and obtain an actual turning mode set; A generating module, configured to obtain a smooth track of the UAV based on the actual turning pattern set and the coordinates of each track point of the UAV; The determination module is further used to determine the number of turning modes corresponding to each track point of the UAV based on the threat distance set and the turning strategy table; If the number of the turning patterns is one, the turning pattern is used as the actual turning pattern of the corresponding track point; If the number of the turning patterns is greater than one, calculating the length of the first direction track segment and the length of the second direction track segment based on the track points corresponding to the turning patterns; Based on the length of the first direction track segment and the length of the second direction track segment, obtaining an actual turning mode of the track point corresponding to the turning mode; Based on the actual turning patterns of each track point of the UAV, the actual turning pattern set is obtained; The determination module is further used to divide the surrounding area of ​​each track point of the planned track of the drone to obtain a division result; wherein each part of the division result has a corresponding turning mode, and the turning mode includes an inward turn, a point-around turn, a point-pressure turn, and a point-to-point turn; The threat distance set is matched with the division result, the turning mode of each track point of the UAV is determined, and an actual turning mode set is obtained.

9. A terminal device, characterized in that: The terminal device includes a memory, a processor, and a method for smoothing the trajectory of a UAV stored in the memory and executable on the processor. When the program for smoothing the trajectory of a UAV is executed by the processor, the steps of the method for smoothing the trajectory of a UAV as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a program for smoothing the trajectory of an unmanned aerial vehicle. When the program for smoothing the trajectory of an unmanned aerial vehicle is executed by a processor, the steps of the method for smoothing the trajectory of an unmanned aerial vehicle as described in any one of claims 1 to 7 are implemented.

Images