Position prediction method and device of unmanned aerial vehicle, equipment and storage medium

Abstract

The invention provides a position prediction method and device of an unmanned aerial vehicle, equipment and a storage medium. The method comprises the following steps: acquiring a first position and a first waypoint of the unmanned aerial vehicle at a first moment; wherein the first waypoint is a waypoint at which the first flight direction is adjusted to be a second flight direction after the unmanned aerial vehicle passes through the first position, and the first flight direction and the second flight direction are different flight directions; predicting a second position of the unmanned aerial vehicle at a second moment based on the motion state information of the unmanned aerial vehicle at the first moment; determining a first adjustment distance of the unmanned aerial vehicle in the transition route based on the second position under the condition of predicting that the unmanned aerial vehicle passes through the transition route corresponding to the first waypoint; and correcting the second position based on the first adjustment distance to predict a third position of the unmanned aerial vehicle at the second moment. According to the scheme, the position prediction precision of the unmanned aerial vehicle can be improved.

Description

Technical Field

[0001] The present application relates to vertical industry fields, and in particular to a method, device, equipment and storage medium for predicting the position of a drone. Background Art

[0002] Drone position prediction is crucial for improving air traffic safety, the reliability of multi-drone collaborative missions and swarm control, and ensuring the safety of drone activities. Existing drone position prediction methods primarily use historical sensor information to predict future drone positions, but their accuracy is relatively poor. Summary of the Invention

[0003] The embodiments of the present application provide a method, apparatus, device, and storage medium for predicting the position of a drone, which can improve the accuracy of drone position prediction.

[0004] The technical solution of the embodiment of the present application is implemented as follows:

[0005] In a first aspect, an embodiment of the present application provides a method for predicting the position of a drone, the method comprising:

[0006] Obtaining a first position and a first waypoint of the drone at a first moment; wherein the first waypoint is a waypoint at which the drone adjusts its first flight direction to a second flight direction after passing the first position, and the first flight direction and the second flight direction are different flight directions;

[0007] Predicting a second position of the drone at a second moment based on the motion state information of the drone at the first moment;

[0008] When predicting that the UAV passes through a transition route corresponding to the first waypoint, determining a first adjustment distance of the UAV on the transition route based on the second position;

[0009] The second position is corrected based on the first adjusted distance to predict a third position of the drone at the second moment.

[0010] In a second aspect, an embodiment of the present application provides a device for predicting the position of a drone, the device comprising:

[0011] a first acquisition module, configured to acquire a first position and a first waypoint of the drone at a first moment; wherein the first waypoint is a waypoint at which the drone adjusts its first flight direction to a second flight direction after passing the first position, the first flight direction and the second flight direction being different flight directions;

[0012] a first prediction module, configured to predict a second position of the UAV at a second moment based on the motion state information of the UAV at the first moment;

[0013] a first determining module, configured to determine, based on the second position, a first adjustment distance of the UAV on the transition route when predicting that the UAV passes through the transition route corresponding to the first waypoint;

[0014] The first correction module is configured to correct the second position based on the first adjustment distance to predict a third position of the UAV at the second moment.

[0015] In a third aspect, an embodiment of the present application provides an electronic device comprising a memory and a processor, wherein the memory stores a computer program that can be run on the processor; when the processor executes the program, the position prediction method of the drone described above in the claim is implemented.

[0016] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium storing a computer program for implementing the above-mentioned drone position prediction method when executed by a processor.

[0017] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program or instructions, which, when executed by a processor, implements the steps of the above-mentioned drone position prediction method.

[0018] The embodiments of the present application provide a method, apparatus, device, and storage medium for predicting the position of a drone, which obtains a first position and a first waypoint of the drone at a first moment; wherein the first waypoint is a waypoint at which the drone adjusts its first flight direction to a second flight direction after passing the first position, and the first flight direction and the second flight direction are different flight directions; based on the motion state information of the drone at the first moment, the second position of the drone at the second moment is predicted; when the drone is predicted to pass through a transition route corresponding to the first waypoint, a first adjustment distance of the drone on the transition route is determined based on the second position; and the second position is corrected based on the first adjustment distance to predict the third position of the drone at the second moment. Because the drone passes through the transition route corresponding to the first waypoint at the second moment, and the predicted second position of the drone is corrected, the third position of the drone at the second moment is ultimately obtained. Therefore, adopting this solution can improve the accuracy of drone position prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The accompanying drawings herein are incorporated into and constitute a part of this specification. These drawings illustrate embodiments consistent with the present application and, together with the specification, serve to illustrate the technical solutions of the present application. Obviously, the drawings described below are merely some embodiments of the present application. Those skilled in the art can, without inventive effort, derive other drawings from these drawings.

[0020] The flowcharts shown in the accompanying drawings are for illustrative purposes only and do not necessarily include all contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may be decomposed, while others may be combined or partially combined. Therefore, the actual execution order may vary depending on the actual situation.

[0021] Figure 1 Schematic diagram of a process for predicting the position of a drone provided in an embodiment of the present application Figure 1 ;

[0022] Figure 2 A schematic diagram of a route for an optional method for predicting the position of a drone provided in an embodiment of the present application;

[0023] Figure 3 Schematic diagram of a process for predicting the position of a drone provided in an embodiment of the present application Figure 2 ;

[0024] Figure 4 Schematic diagram of a transition route of an optional drone position prediction method provided in an embodiment of the present application Figure 1 ;

[0025] Figure 5 Schematic diagram of a transition route of an optional drone position prediction method provided in an embodiment of the present application Figure 2 ;

[0026] Figure 6 Schematic diagram of a process for predicting the position of a drone provided in an embodiment of the present application Figure 3 ;

[0027] Figure 7 A schematic diagram of the structure of a position prediction device for a drone provided in an embodiment of the present application;

[0028] Figure 8 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0029] In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the specific technical solutions of the present application will be described in further detail below in conjunction with the accompanying drawings in the embodiments of the present application. The following examples are used to illustrate the present application, but are not intended to limit the scope of the present application. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by those skilled in the art of the technical field of the present application. The terms used herein are only for the purpose of describing the embodiments of the present application and are not intended to limit the present application.

[0030] It should be understood that in the following description, references to "one embodiment," "an embodiment," or "some embodiments" throughout the specification mean that a particular feature, structure, or characteristic associated with the embodiment is included in at least one embodiment of the present application. Therefore, the appearance of "in one embodiment," "in an embodiment," or "some embodiments" throughout the specification does not necessarily refer to the same embodiment. Furthermore, these particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments without conflict.

[0031] It should be understood that in the various embodiments of the present application, the size of the sequence number of each process does not mean the order of execution, and the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present application. The above sequence numbers of the embodiments of the present application are only for description and do not represent the advantages and disadvantages of the embodiments. The above description of the various embodiments tends to emphasize the differences between the various embodiments, and the same or similar aspects can refer to each other. For the sake of brevity, this article will not go into details.

[0032] If similar descriptions of "first / second" appear in the application documents, the following explanation is added. In the following description, the terms "first\second\third" involved are merely used to distinguish similar objects and do not represent a specific order for the objects. It can be understood that "first\second\third" can be interchanged with a specific order or sequence where permitted, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein.

[0033] It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as generally understood by those skilled in the art in the art to which the embodiments of the present application belong. It should also be understood that terms such as those defined in general dictionaries should be understood to have meanings consistent with their meanings in the context of the prior art, and will not be interpreted in an idealized or overly formal sense unless specifically defined as herein.

[0034] To facilitate understanding of this solution, before describing the embodiments of the present application, the application background of the embodiments of the present application will be described.

[0035] In recent years, drone research and applications have been increasingly applied in civilian applications, such as multi-drone coordination, multi-drone surveillance, and multi-drone task allocation. To accomplish these tasks, drones need to know their current and future locations. Drone position prediction is a crucial component in addressing these needs. For example, in multi-drone collision warning systems, more accurate prediction of drone positions significantly improves collision warning accuracy.

[0036] Existing UAV position prediction methods mainly use historical sensor information to predict the future UAV position. They do not introduce prior route information for fusion and do not compensate for the UAV's transition process state, making their prediction accuracy relatively poor.

[0037] The current mainstream solution first uses an external measurement unit to obtain the current reference position information of the UAV; then calculates the difference between the current reference position information and the position information estimated by the speed-displacement prediction model to obtain the position error between the reference position information and the position information estimated by the speed-displacement prediction model; then designs a third-order phase-locked loop filter; and finally designs a speed-displacement prediction model to achieve tracking of the UAV's speed and position.

[0038] The existing methods have the following problems: 1. No Kalman filter system is established, and Kalman filtering is not used to estimate acceleration. Instead, a third-order phase-locked loop filter is used to estimate acceleration. The advantage of this solution is simplicity, but the disadvantage is that the prediction effect is poorer than that of Kalman filtering; 2. This solution does not introduce prior route information; 3. The transition process state of the drone is not considered, but it is directly processed in a uniform speed or uniform acceleration state.

[0039] Based on the above problems, this application proposes a method for predicting the position of a drone. Figure 1 Schematic diagram of the process of an optional drone position prediction method provided in an embodiment of the present application Figure 1 ,like Figure 1 As shown, the present application can be implemented through S110, S120, S130 and S140, specifically:

[0040] Step S110, obtaining a first position and a first waypoint of the drone at a first moment; wherein the first waypoint is a waypoint at which the drone adjusts its first flight direction to a second flight direction after passing the first position, and the first flight direction and the second flight direction are different flight directions.

[0041] Here, the first moment can be the current moment, the first position is the position of the UAV on the planned route at the current moment, the first flight direction is the flight direction of the UAV at the first moment, and the second flight direction is the direction after the flight direction of the UAV changes after passing the first position. For example, the UAV turns after passing the first position, that is, the first flight direction of the UAV changes and is adjusted to the second flight direction after the turn, and the first waypoint is the waypoint at the turn.

[0042] Step S120: predicting a second position of the drone at a second moment based on the motion state information of the drone at the first moment.

[0043] Here, the motion state information includes the first position and first speed of the UAV at the first moment, and the second moment may be the target moment.

[0044] Step S130: When it is predicted that the UAV passes through a transition route corresponding to the first waypoint, a first adjustment distance of the UAV on the transition route is determined based on the second position.

[0045] Here, the transition route corresponding to the first waypoint is the route that the drone experiences a transition process before and after passing the first waypoint. When passing the transition route before the first waypoint, the drone decelerates to zero speed, and when passing the transition route after the first waypoint, it accelerates to the specified speed. The first adjustment distance is the distance deviation caused by the change in the first acceleration during the transition route, which can be understood as the distance deviation between the drone's actual predicted position and the second position.

[0046] Step S140: Correct the second position based on the first adjusted distance to predict a third position of the UAV at the second moment.

[0047] Here, the third position is the actual position after correction at the second moment.

[0048] In the embodiment of the present application, since the situation that the drone passes through the transition route corresponding to the first waypoint at the second moment is taken into consideration and the predicted second position of the drone is corrected, the third position of the drone at the second moment is finally obtained. Therefore, the adoption of this solution can improve the accuracy of the drone position prediction.

[0049] The above step S120 of “predicting the second position of the drone at a second moment based on the motion state information of the drone at a first moment” includes the following steps:

[0050] Step 121: Based on the first position and the first velocity, use the Kalman filter equation to predict the first acceleration of the UAV at the first moment.

[0051] Here, in the embodiment of the present application, it is assumed that the acceleration of the drone obeys the classic Singer model. Therefore, the expression of acceleration is the following formula (1):

[0052]

[0053] Among them, w(t) expresses Gaussian white noise, and its mean is zero and its variance is α is the inverse of the time constant of the maneuvering target, and t represents time.

[0054] Based on the first position and first velocity of the UAV and the first acceleration expression of the UAV, the position-velocity-acceleration motion equation of the UAV is established, where the first position of the UAV in the inertial coordinate system is x I ,y I , z I , the first speed of the drone is v xI , v yI , v zI , the projection of the first acceleration of the UAV in the inertial coordinate system is a xI 、a yI 、a zI , we can establish the following three sets of motion equations:

[0055]

[0056] Among them, in the above formula (2), Represents the position derivative of the drone's x-axis, Represents the velocity derivative of the drone's x-axis, Represents the acceleration derivative of the drone's x-axis, v xI Represents the speed of the drone's x-axis, a xI represents the acceleration of the drone's x-axis, λ x Represents the inverse of the time constant of the maneuvering target corresponding to the x-axis of the UAV, w xI Represents the system noise of the drone's x-axis.

[0057]

[0058] Among them, in the above formula (3), Represents the position derivative of the drone's y-axis, Represents the velocity derivative of the drone's y-axis, Represents the acceleration derivative of the drone's y-axis, v yI Represents the speed of the drone's y-axis, a yI Represents the acceleration of the drone's y-axis, λ y represents the inverse of the time constant of the maneuvering target corresponding to the y-axis, wyI Represents the system noise of the UAV's y-axis.

[0059]

[0060] Among them, in the above formula (4), Represents the position derivative of the drone's z-axis, Represents the velocity derivative of the drone's z-axis, Represents the acceleration derivative of the drone's z-axis, v zI Represents the speed of the drone's z-axis, a zI Represents the acceleration of the drone's z-axis, λ z represents the inverse of the time constant of the maneuvering target corresponding to the z-axis, w zI Represents the system noise of the drone's z-axis.

[0061] Based on the above three sets of motion equations, the state variables of the UAV are defined as follows:

[0062] x=[x I y I z I v xI v yI v zI a xI a yI a zI ] T (5);

[0063] Wherein, in the above formula (5), x represents the first state variable of the UAV.

[0064] Based on the above three sets of motion equations, the state equation of the UAV can be obtained as follows:

[0065]

[0066] in, is the state derivative, F tx is the state transfer matrix, w is Gaussian white noise, for example:

[0067]

[0068] w=[0 0 0 0 0 0 w xI w yI w zI ]

[0069] After discretizing the above formula (6) with a certain period △t, the discretized drone state variable is obtained as follows:

[0070] F=exp(F tx △t) (7);

[0071] Where △t represents the discrete period.

[0072] Based on formula (6) and formula (7), the state equation of the discretized UAV is as follows:

[0073] x(k+1)=Fx(k)+w(k) (8);

[0074] Among them, x(k+1) represents the state of the drone at time K+1, x(k) represents the state of the drone at time K, and w(k) represents Gaussian white noise.

[0075] The first position and first velocity are obtained from the measurement information of the UAV, so its measurement equation is as follows (9):

[0076] y(k)=Hx(k)+v(k) (9);

[0077] Where H is the input matrix, k represents the time, v(k) is the measurement noise, x(k) is the state of the drone at time k, and y(k) represents the measurement value of the drone at time k. For example,

[0078]

[0079] The Kalman filter equation is constructed by the state equation of the UAV in the above formula (8) and the measurement equation of the UAV in the above formula (9). The first acceleration of the UAV is predicted in real time using the Kalman filter. That is, when the first position and the first velocity of the UAV are updated, the above Kalman filter process is used to obtain the predicted first state. The first state represents the relationship between the first position, the first velocity and time of the UAV. The first acceleration of the UAV can be predicted based on the first state.

[0080] Here, the Kalman filter process includes the following formula, where the state one-step prediction equation is as follows (10):

[0081]

[0082] in, represents the state at time k+1, Φ k+1,k represents a one-step transfer matrix from time k to time k+1, Represents the state at time k.

[0083] The state estimation equation is as follows (11):

[0084]

[0085] Among them, K k+1represents the Kalman gain, Z k+1 represents the measurement value at time k, H k+1 Represents the measurement array.

[0086] The filter gain equation is as follows (12):

[0087]

[0088] Among them, P k+1 / k represents the state covariance matrix, R k+1` represents the observation noise covariance matrix.

[0089] The one-step prediction mean square error equation is as follows (13):

[0090]

[0091] Among them, Q k Represents the covariance of the system process.

[0092] The estimated mean square error equation is as follows (14):

[0093] P k+1 =(IK k+1 H k+1 )P k+1 / k (14);

[0094] Among them, K k+1 represents the filter gain matrix.

[0095] In the embodiment of the present application, the use of Kalman filtering to predict the first acceleration is more accurate than the acceleration obtained by differentiating the velocity, because the Kalman filter itself can eliminate the negative impact of position and velocity wild values, and can also eliminate the influence of noise.

[0096] Step 122: Predict a second position based on the first position, the first velocity, and the first acceleration.

[0097] Here, the first position, first velocity and first acceleration of the drone at the first moment are obtained according to the above step 121, so the second position at the second moment can be obtained by recursively calculating the first position based on the ratio of the second moment to the period of the Kalman filter using the state equation of the drone.

[0098] For example, the second position can be predicted by the following pseudo code (15):

[0099]

[0100] end

[0101] Among them, in the above formula (15) is the first position of the drone at the first moment, is the second position of the UAV at time T0, and △t is the period of Kalman filter. Here the second moment is T0, is the position variable, k represents the moment, and i is the time variable.

[0102] In an embodiment of the present application, the acceleration estimated by the Kalman filter is used to predict the second position of the drone at the second moment, which can reduce the error of the second position prediction and provide higher-precision position data for subsequent drones to correct the second position when passing through a transition route, thereby improving the accuracy of the drone position prediction.

[0103] After the above step S120 of "predicting the second position of the drone at the target time based on the current motion state information of the drone", the following steps are also included:

[0104] Step 123: Obtain a first distance between the first position and the second position.

[0105] Here, the first distance can be obtained by the distance formula between the first position and the second position. For example, when a UAV flies from the first position on the planned route, after time T0, the predicted distance traveled by the UAV can be obtained by the following formula (16):

[0106]

[0107] Where L is the first distance, is the first position of the drone at the first moment, is the second position of the drone at the second moment.

[0108] Step 124: Obtain a second distance between the first position and the first waypoint.

[0109] Step 125: Based on the first distance and the second distance, predict whether the drone passes through the transition route corresponding to the first waypoint.

[0110] Here, if the first acceleration decreases for the first time when the drone is traveling over the first distance, the position where the first acceleration decreases for the first time is defined as the first transition point, and a first transition distance from the first position to the first transition point is obtained.

[0111] If the first distance is less than the first transition distance, it is predicted that the drone will not pass through the transition route corresponding to the first waypoint.

[0112] If the first distance is greater than or equal to the first transition distance, the transition route corresponding to the first waypoint is predicted to be passed by the drone.

[0113] In an embodiment of the present application, by predicting whether the drone passes through the transition route corresponding to the first waypoint based on the first distance and the second distance, the flight status of the drone on the planned route can be predicted, so that the second position can be corrected when the drone passes through the transition route, thereby improving the reliability of the drone position prediction.

[0114] Figure 2 The present application provides an optional route diagram of a method for predicting the position of a drone, such as Figure 2 As shown in the figure, A, B, and C are waypoints on the planned route. The route is composed of two segments, AB and BC. P is the drone's position at the first moment. When the drone travels from point A to point B, it needs to decelerate to zero just before reaching point B. This deceleration process involves a dynamic process. Similarly, when the drone travels from point B to point C, it also experiences a dynamic acceleration process. These two processes are technically referred to as transition processes (i.e., transition routes) in control. To more accurately predict the drone's position, we need to compensate for this transition process.

[0115] The above step S130 "determining a first adjustment distance of the UAV on the transition route based on the second position when predicting that the UAV passes through the transition route corresponding to the first waypoint" includes the following steps: Figure 3 As shown:

[0116] Step S310: predicting the second speed of the drone entering the transition route based on the first position, the first speed, and the first acceleration, and predicting the transition time of the drone flying on the transition route to the first waypoint based on the first acceleration; wherein, the acceleration of the drone entering the transition route is the first acceleration, and the acceleration of the drone at the first waypoint is a null value.

[0117] Here, the second speed can be calculated by obtaining the time it takes for the drone to enter the transition route from the first position and then based on the drone's first speed at the first moment. The transition duration can be calculated by the time it takes for the drone's first acceleration to decrease to a null value. When entering the transition route, the drone will first decelerate, and the first acceleration will also decrease, with the acceleration being null at the first waypoint.

[0118] Figure 4 The present application provides an optional transition route diagram of a method for predicting the position of a UAV, such as Figure 4As shown, A, B, and C are waypoints on the planned route, P is the position of the drone at the first moment, S1 is the position where the acceleration first decreases when the drone enters the transition route, and S2 is the position where the acceleration of the drone increases to the acceleration threshold during the transition route. When the drone flies from S1 to B, a transition process 1 occurs in which the acceleration of the drone decays to 0. When the drone flies from B to S2, a transition process 2 occurs in which the acceleration of the drone accelerates from 0 to the specified acceleration.

[0119] Step S320: Predict a third distance that the UAV will travel during the transition period based on the first acceleration.

[0120] Here, considering the transition route, since the acceleration of the UAV at the first waypoint is a null value, it can be assumed that the transition time of the UAV in the transition route is T1. Then the recursive formula of the third distance of the UAV in the transition route can be obtained by the following formula (17):

[0121]

[0122] Wherein, s'1 represents the third distance of the transition route, a represents the first acceleration of entering the transition route, and T1 represents the transition duration of the transition route.

[0123] Here, since the flight control parameters in the UAV system are fixed, we first collect the data of the UAV's first acceleration from 0 to 1 and from 1 to 0 offline; then fit it according to the first-order transfer function, and the fitting method uses the system identification toolbox of Matlab. The final fitted transfer function is The time constant for obtaining the transition route is ι. Therefore, the entire adjustment time T1 can be approximately 3t.

[0124] Step S330: predicting a fourth distance traveled by the UAV during the transition period based on the second speed and the first acceleration.

[0125] When predicting the second position, if the transition process is not considered, the CV model is used for prediction, that is, the first acceleration is considered to be a constant. Since the acceleration of the UAV is 0 when it reaches the first waypoint, the recursive formula for the fourth distance traveled by the UAV on the transition route to the first waypoint is as follows (18):

[0126]

[0127] Among them, v e is the second speed of the UAV when entering the transition route, a represents the first acceleration, T1 represents the transition time, and s1 is the fourth distance.

[0128] Step S340: Determine a first deviation distance of the UAV on the transition route based on the third distance and the fourth distance.

[0129] Here, in actual circumstances, the third distance from the drone to the first waypoint is s'1, so the predicted distance from the drone to the first waypoint during the transition route will increase, that is, the first deviation distance is the difference between the fourth distance and the third distance, which can be obtained by the following formula (19):

[0130] △s=v e T1 (19);

[0131] where v e is the second speed of the UAV at the moment of entering the transition process, T1 represents the transition duration, and △s is the first deviation distance.

[0132] Step S350: Based on the positional relationship between the second position and the first waypoint, a first adjustment distance is determined using the first deviation distance and the third distance.

[0133] Here, the first adjustment distance is the adjustment distance generated on the transition route when the UAV flies to the second position, which can be obtained by utilizing the linear difference method based on the positional relationship between the second position and the first waypoint, wherein the positional relationship between the second position and the first waypoint can be obtained according to the relationship between the coordinates of the second position and the first waypoint on the route, or it can be obtained by the ratio of the distance between the second position and the first waypoint and the distance traveled by the UAV on the entire transition route.

[0134] In an embodiment of the present application, by considering the first deviation distance generated by the UAV on the transition route, the distance compensation of the UAV in the transition process state is performed, that is, the second position predicted for the first time is corrected, thereby improving the position prediction accuracy of the UAV.

[0135] The above step S350 of “determining the first adjustment distance using the first deviation distance and the third distance based on the positional relationship between the second position and the first waypoint” includes the following steps:

[0136] Step 351: If the second position is located on the transition route, obtain a distance ratio between the distance from the second position to the first waypoint and the third distance.

[0137] Step 352: Determine the product of the distance ratio and the first deviation distance as the first adjustment distance.

[0138] Here, by obtaining the distance ratio between the second position and the first waypoint and the third distance, and using the method of linear interpolation, based on the first deviation distance generated when the UAV enters the transition route, the first adjustment distance actually generated when the UAV flies to the second position on the transition route is obtained. The second position can be located on the transition route before the first waypoint or on the transition route after the first waypoint.

[0139] Step 353: If the second position is located after the transition route, then twice the first deviation distance is determined as the first adjustment distance.

[0140] Here, if the second position of the UAV is located after the transition route, that is, the UAV passes through and leaves the transition route. At this time, the UAV will experience a dynamic process of two acceleration changes on the transition route, and two first deviation distances will be generated. Then the first adjustment distance is twice the first deviation distance.

[0141] As Figure 5 shown, A, B, and C are waypoints on the planned route, P is the position of the UAV at the first moment, S1 is the position where the acceleration of the UAV first decreases when entering the transition route, S2 is the position where the acceleration of the UAV increases to the acceleration threshold on the transition route, d1 and d2 respectively correspond to the first adjustment distances of the second position of the UAV on the transition route and after the transition route, E1 and E2 are the third positions, D1 and D2 are the second positions of the UAV on the transition route and after the transition route. Then, in different situations where the UAV passes through the transition route, the first distance between the first position and the second position of the UAV is set as L (that is, PD1 or PD2). Among them, the process corresponding to the transition route before point B of the first waypoint is transition process 1, and the process corresponding to the transition route after point B of the first waypoint is transition process 2. The method for determining the first adjustment distance is as follows:

[0142] (1) When PS1 > L, the UAV predicts that it will not pass through the transition route, that is, there is no need to correct the second position, then the third position of the UAV is the second position.

[0143] (2) When PS1 < L < PB, the UAV predicts that it will pass through the transition route and trigger transition process 1. That is, when the second position is at point D1, the distance ratio between the second position and the first waypoint and the third distance is the ratio of D1B to S1B. That is, the calculation formula for the first adjustment distance is as follows formula (20):

[0144]

[0145] Here, L c represents the first adjustment distance, s'1 represents the third distance of the UAV in transition process 1, and △s represents the first deviation distance of the UAV in transition process 1.

[0146] (3) Similarly, when PB < L < PB + BS2, the UAV experiences the entire transition process 1 and triggers the transition process 2 at this time. Then, the calculation of the first adjustment distance is as shown in the following formula (21):

[0147]

[0148] (4) When L > PB + BS2, the UAV experiences the entire transition process 1 and the transition process 2 at this time. That is, when the second position is at point D2, that is, the first adjustment distance is twice the first deviation distance. Then, the calculation of the first adjustment distance is as shown in the following formula (22):

[0149] L c = 2△s (22);

[0150] In the embodiment of the present application, by considering the first adjustment distance generated when the UAV travels on the transition route and correcting the second position of the UAV at the second moment based on the difference between the first distance and the first adjustment distance, the accuracy of the UAV's position prediction can be improved.

[0151] The above step S140 "correcting the second position based on the first adjustment distance to predict the third position of the UAV at the second moment" further includes the following process:

[0152] Determine the position on the UAV's route that is before the second position and is at a distance of the first adjustment distance from the second position as the third position.

[0153] As Figure 5 shown, when D1 is the predicted second position of the UAV, that is, the second position is on the transition route, then the position at a distance of the first adjustment distance d1 from D1, that is, point E1, is determined as the third position. When D2 is the predicted second position of the UAV, that is, the second position is after the transition route, then the position at a distance of the first adjustment distance d2 from D2, that is, point E2, is determined as the third position.

[0154] In the embodiment of the present application, by determining the first adjustment distance of the UAV on the transition route, the second position of the UAV is constrained using the route information. At the same time, the transition process that exists when the state of the UAV changes during actual flight is considered and compensated, thereby improving the accuracy of the UAV's position prediction.

[0155] The above UAV position prediction method further includes the following process:

[0156] If the UAV continues to pass through the transition route after passing through the first waypoint, then fuse the route information and update the predicted third position of the UAV, and predict the third position of the UAV at the next moment according to the above UAV position prediction method, and repeat until the end or the end point of the UAV route is reached.

[0157] The following describes an exemplary application of the embodiments of the present application in a practical application scenario.

[0158] Figure 6 Schematic diagram of a process for predicting the position of a drone provided in an embodiment of the present application Figure 3 ;like Figure 6 As shown, the embodiment of the present application can be implemented by the following steps:

[0159] Step S601: Establish a Kalman filter model.

[0160] Here, a Kalman filter model is established based on the first position and first velocity of the UAV at the first moment.

[0161] Step S602: predict current acceleration information.

[0162] Here, based on the Kalman filter model, the current acceleration information is predicted, and the current moment is the first moment.

[0163] Step S603: predict the future T0 time displacement.

[0164] Here, the first position, first velocity and first acceleration of the drone at the first moment can be used to predict the second position and first distance of the drone at the future time T0 with the help of the cycle of the Kalman filter, where T0 is the second moment.

[0165] Step S604: introduce prior route information for correction.

[0166] Here, considering that the UAV passes through a transition route, the prior route information is introduced to correct the second position.

[0167] Step S605: The UAV is in a transition state and needs to perform position compensation.

[0168] Here, when the UAV is in a transition route state, since the acceleration of the UAV decreases to 0 and increases from 0 to a specified acceleration in a dynamic process on the transition route, the second position needs to be corrected and compensated.

[0169] Step S606: Obtain the final drone position prediction information.

[0170] Here, by correcting the second position and combining it with the planned route, the final drone position prediction information, i.e., the third position, can be obtained.

[0171] In an embodiment of the present application, by correcting the predicted position of the drone when the route direction of the drone changes, it is possible to avoid the predicted position of the drone following the previous route direction, which may cause errors in the trajectory of the drone. This then ensures that the corrected predicted position of the drone is integrated with the route information, thereby improving the accuracy of the drone position prediction and reducing the probability of collision between drones.

[0172] Based on the drone position prediction method of the above embodiment, the embodiment of the present application also provides a drone position prediction device, such as Figure 7 As shown, the device 7 includes:

[0173] The first acquisition module 701 is used to obtain the first position and the first waypoint of the drone at the first moment; wherein, the first waypoint is the waypoint at which the drone adjusts the first flight direction to the second flight direction after passing the first position, and the first flight direction and the second flight direction are different flight directions.

[0174] The first prediction module 702 is configured to predict a second position of the UAV at a second moment based on the motion state information of the UAV at the first moment.

[0175] The first determining module 703 is configured to determine a first adjustment distance of the UAV on the transition route based on the second position when it is predicted that the UAV passes through the transition route corresponding to the first waypoint.

[0176] The first correction module 704 is configured to correct the second position based on the first adjusted distance to predict a third position of the UAV at the second moment.

[0177] In some embodiments, the first prediction module 701 includes a first prediction submodule and a second prediction submodule, wherein the first prediction submodule is used to predict the first acceleration of the drone at the first moment based on the first position and the first velocity using the Kalman filter equation; the second prediction submodule is used to predict the second position based on the first position, the first velocity and the first acceleration.

[0178] In some embodiments, the device further includes a second acquisition module, a third acquisition module and a third prediction module, wherein the second acquisition module is used to obtain a first distance between the first position and the second position; the third acquisition module is used to obtain a second distance between the first position and the first waypoint; and the third prediction module is used to predict whether the drone passes through the transition route corresponding to the first waypoint based on the first distance and the second distance.

[0179] In some embodiments, the first determination module 703 further includes a third prediction submodule, a fourth prediction submodule, a fifth prediction submodule, a first determination submodule and a second determination submodule, wherein the third prediction submodule is used to predict the second speed of the drone entering the transition route based on the first position, the first speed and the first acceleration, and predict the transition time of the drone flying on the transition route to the first waypoint based on the first acceleration; wherein the acceleration of the drone entering the transition route is the first acceleration, and the acceleration of the drone at the first waypoint is a null value; the fourth prediction submodule is used to predict the third distance traveled by the drone during the transition time based on the first acceleration; the fifth prediction submodule is used to predict the fourth distance traveled by the drone during the transition time based on the second speed and the first acceleration; the first determination submodule is used to determine the first deviation distance of the drone in the transition route based on the third distance and the fourth distance; the second determination submodule is used to determine the first adjustment distance using the first deviation distance and the third distance based on the positional relationship between the second position and the first waypoint.

[0180] In some embodiments, the device further includes a fourth acquisition module, a third determination module and a fourth determination module, the fourth acquisition module being used to obtain the distance ratio of the distance from the second position to the first waypoint to the third distance if the second position is located on the transition route; the third determination module being used to determine the product of the distance ratio and the first deviation distance as the first adjustment distance; and the fourth determination module being used to determine twice the first deviation distance as the first adjustment distance if the second position is located after the transition route.

[0181] In some embodiments, the first correction module 704 further includes a third determination submodule, configured to determine a position on the route of the UAV that is before the second position and is at the first adjustment distance from the second position as the third position.

[0182] Based on the method for predicting the position of a drone in the above embodiment, the embodiment of the present application further provides an electronic device, such as Figure 8 As shown, the device 8 includes: a processor 801 and a memory 802, wherein the memory 802 is used to store a computer program; the processor 801 is used to call and run the computer program from the memory 802 to execute the position prediction method of the drone as described in the above embodiment.

[0183] In the embodiment of the present application, the processor 801 may be at least one of an application-specific integrated circuit (ASIC), a digital signal processor (DSP), a digital signal processing device (DSPD), a programmable logic device (PLD), a field programmable gate array (FPGA), a central processing unit (CPU), a controller, a microcontroller, and a microprocessor. It is understood that for different devices, the electronic device used to implement the above-mentioned processor function may also be other, and the embodiment of the present application does not specifically limit this.

[0184] Based on the drone position prediction method of the above embodiment, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, which implements the above drone position prediction method when executed by a processor.

[0185] In the embodiments of the present application, the above-mentioned storage medium includes various media that can store program codes, such as mobile storage devices, read-only memories (ROM), magnetic disks or optical disks, and can also be other media, which are not specifically limited in the embodiments of the present application.

[0186] Illustratively, the program instructions corresponding to a method for predicting the position of a drone in this embodiment can be stored on a storage medium such as a CD, a hard disk, or a USB flash drive. When the program instructions corresponding to a method for predicting the position of a drone in the storage medium are read or executed by an electronic device, the method for predicting the position of a drone as described in any of the above embodiments can be implemented.

[0187] Based on the drone position prediction method of the above embodiment, the embodiment of the present application provides a computer program product, including a computer program or instructions, which, when executed by a processor, implements the steps of the above drone position prediction method.

[0188] When performing the drone position prediction method of the above embodiment, only the division of the above program modules is used as an example. In actual application, the above processing can be assigned to different program modules as needed, that is, the internal structure of the device can be divided into different program modules to complete all or part of the above-described processing. In addition, the drone position prediction device provided in the above embodiment and the drone position prediction method embodiment are based on the same concept. The specific implementation process and beneficial effects are detailed in the method embodiment and will not be repeated here. For technical details not disclosed in the embodiment of this device, please refer to the description of the method embodiment of this application for understanding.

[0189] Those skilled in the art will understand that all or part of the steps of implementing the above-mentioned method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the embodiment of the above-mentioned drone position prediction method.

[0190] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of hardware embodiments, software embodiments, or embodiments combining software and hardware. Furthermore, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage and optical storage, etc.) containing computer-usable program code.

[0191] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the steps in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0192] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0193] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0194] The above is merely an implementation of the embodiments of the present application, but the scope of protection of the embodiments of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of the embodiments of the present application. Therefore, the scope of protection of the embodiments of the present application should be based on the scope of protection of the claims.

Claims

1. A method for predicting the position of a drone, characterized in that: The method comprises: Obtaining a first position and a first waypoint of the drone at a first moment; wherein the first waypoint is a waypoint at which the drone adjusts its first flight direction to a second flight direction after passing the first position, and the first flight direction and the second flight direction are different flight directions; Predicting a second position of the drone at a second moment based on the motion state information of the drone at the first moment; When predicting that the UAV passes through a transition route corresponding to the first waypoint, determining a first adjustment distance of the UAV on the transition route based on the second position; The second position is corrected based on the first adjusted distance to predict a third position of the drone at the second moment.

2. The method according to claim 1, characterized in that The motion state information includes a first speed and a first acceleration of the UAV at the first moment, The predicting a second position of the drone at a second moment based on the motion state information of the drone at the first moment includes: Predicting the first acceleration of the UAV at the first moment using a Kalman filter equation based on the first position and the first velocity; The second position is predicted based on the first position, the first velocity, and the first acceleration.

3. The method according to claim 1, characterized in that After predicting the second position of the drone at a second moment based on the motion state information of the drone at the first moment, the method further includes: Obtaining a first distance between the first position and the second position; Obtaining a second distance between the first position and the first waypoint; Based on the first distance and the second distance, it is predicted whether the drone passes through a transition route corresponding to the first waypoint.

4. The method according to claim 1, wherein The step of determining a first adjustment distance of the UAV on the transition route based on the second position when predicting that the UAV passes through the transition route corresponding to the first waypoint includes: Predicting a second speed of the UAV entering the transition route based on the first position, the first speed, and the first acceleration, and predicting a transition duration for the UAV to fly along the transition route to the first waypoint based on the first acceleration; wherein the acceleration of the UAV entering the transition route is the first acceleration, and the acceleration of the UAV at the first waypoint is a null value; Predicting a third distance traveled by the drone during the transition period based on the first acceleration; predicting a fourth distance traveled by the drone during the transition period based on the second speed and the first acceleration; Determining a first deviation distance of the UAV on the transition route based on the third distance and the fourth distance; Based on a positional relationship between the second position and the first waypoint, the first adjustment distance is determined using the first deviation distance and the third distance.

5. The method according to claim 4, characterized in that The determining the first adjustment distance by using the first deviation distance and the third distance based on the positional relationship between the second position and the first waypoint includes: If the second position is located on the transition route, obtaining a distance ratio between the distance from the second position to the first waypoint and the third distance; determining the first adjustment distance as the product of the distance ratio and the first deviation distance; If the second position is located after the transition route, twice the first deviation distance is determined as the first adjustment distance.

6. The method according to claim 5, characterized in that The correcting the second position based on the first adjusted distance to predict a third position of the UAV at the second moment includes: A position on the route of the UAV that is before the second position and is separated from the second position by the first adjustment distance is determined as the third position.

7. A device for predicting the position of a drone, characterized in that: The device comprises: a first acquisition module, configured to acquire a first position and a first waypoint of the drone at a first moment; wherein the first waypoint is a waypoint at which the drone adjusts its first flight direction to a second flight direction after passing the first position, the first flight direction and the second flight direction being different flight directions; a first prediction module, configured to predict a second position of the UAV at a second moment based on the motion state information of the UAV at the first moment; a first determining module, configured to determine, based on the second position, a first adjustment distance of the UAV on the transition route when predicting that the UAV passes through the transition route corresponding to the first waypoint; The first correction module is configured to correct the second position based on the first adjustment distance to predict a third position of the UAV at the second moment.

8. An electronic device, characterized in that: include: memory for storing computer programs; A processor, configured to implement the method according to any one of claims 1 to 6 when executing the computer program stored in the memory.

9. A computer-readable storage medium, characterized in that A computer program is stored, which is used to implement the method according to any one of claims 1 to 6 when executed by a processor.

10. A computer program product comprising a computer program or instructions, characterized in that When the computer program or instruction is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images