Unmanned aerial vehicle conflict detection and automatic release method, system and device and storage medium

Abstract

The invention provides an unmanned aerial vehicle conflict detection and automatic release method, system and device, and a storage medium. The method comprises the following steps: establishing a conflict detection model; according to the conflict detection model, conflict occurrence conditions are set; a conflict detection model is adopted, and conflict prediction is carried out through conflict occurrence conditions according to the position and the speed of the intrusion aircraft sensed by the unmanned aerial vehicle; when the conflict condition is met, the speed of the unmanned aerial vehicle is adjusted, so that the unmanned aerial vehicle and the intrusion aircraft do not conflict in a period of time in the future, and the change angle between the adjusted speed and the specified movement direction is minimum and the speed value is maximum; and when the conflict occurrence condition is not met, the unmanned aerial vehicle flies according to the specified movement speed. Potential conflicts can be found in time, a release path can be planned in real time, and the unmanned aerial vehicle can fly towards the target point more quickly.

Description

Technical Field

[0001] The present invention belongs to the technical field of unmanned aerial vehicles, and in particular relates to a method, system, device and storage medium for detecting and automatically releasing unmanned aerial vehicle conflicts. Background Art

[0002] In recent years, the exponential development of drone technology and its large-scale application in fields such as military reconnaissance, logistics, and environmental monitoring has led to an increasingly acute conflict between airspace resources and the number of drones. The increasing number of drones has exacerbated airspace constraints and significantly increased the risk of collisions. To address this challenge, numerous conflict resolution algorithms have emerged to prevent unforeseen obstacles from appearing in their flight paths.

[0003] Traditional UAV conflict resolution algorithms (such as those based on static path planning or simple obstacle avoidance strategies) rely on preset rules or offline calculations, cannot detect potential conflicts early, and have difficulty achieving real-time response in complex dynamic environments. For example, when a UAV suddenly encounters another aircraft in dense airspace, traditional methods cause delays in avoidance actions due to computational delays or high path planning complexity, making it impossible to avoid a collision. Existing resolution strategies are mostly fixed rules (such as hovering, returning home, or vertical avoidance), lack adaptability to dynamic environments, and affect the time it takes for the UAV to reach the target point. For example, fixed avoidance directions may cause multiple UAVs to repeatedly conflict in the same area (such as "giving way to each other" leading to a deadlock). Summary of the Invention

[0004] To this end, the technical problem to be solved by the present invention is to provide a method, system, device and storage medium for drone conflict detection and automatic release, which can timely detect potential conflicts, plan the release path in real time, and enable the drone to fly towards the target point more quickly.

[0005] First invention, the present invention provides a method for detecting and automatically releasing a UAV conflict, the method comprising:

[0006] Establish a conflict detection model;

[0007] Setting the conditions for conflict occurrence according to the conflict detection model;

[0008] Using the conflict detection model, based on the position and speed of the intruder aircraft sensed by the UAV, conflict prediction is performed according to the conflict conditions;

[0009] When the conditions for a conflict are met, the speed of the drone is adjusted so that there will be no conflict between the drone and the intruder in the next period of time, and the angle between the adjusted speed and the specified movement direction is minimized and the speed value is maximized;

[0010] When the conflict conditions are not met, the drone flies at the specified speed.

[0011] Furthermore, establishing a conflict detection model includes:

[0012] Assume that the drone and the intruder are represented by A and B respectively, and the safety zones of A and B are respectively with radius R a and R b circle;

[0013] Expand the safe area of ​​B to a radius of R c circle, where R c =R a +R b , modeling A as a point mass;

[0014] With A as the origin, establish the position coordinate system XOY, C and D are two rays emitted from A and the radius R c The tangent point of the circle;

[0015] Assume that A and B meet at time t, the position of B in XOY is vector P, and the velocity of A is V a , the speed of B is V b , V b Relative to V a The speed is V ab , that is, V ab =V a -V b ;

[0016] The process of adjusting the speed of the drone is as follows: a Adjust the velocity vector to u and map u directly to the distance V between the two rays AC or AD. ab On a closer ray.

[0017] Furthermore, the adjustment speed vector u is calculated by the following formula:

[0018]

[0019] Where w = V ab -tP;

[0020]

[0021] Furthermore, for multiple intruders, after calculating the adjusted speed vector u, the straight line The pointed plane is the ORCA half plane, and the final target speed is obtained according to the ORCA linear programming algorithm.

[0022] Furthermore, the condition for a conflict is that if the conflict determination distance h satisfies:

[0023] h>|P|

[0024] Then A and B may conflict;

[0025] Where |P| represents the size of vector P.

[0026] In a second aspect, the present invention further provides a UAV conflict detection and automatic release system, the system comprising:

[0027] A model building module is used to build a conflict detection model;

[0028] A conflict condition setting module, which sets the conditions for conflict occurrence according to the conflict detection model;

[0029] The conflict prediction and resolution module uses the conflict detection model to predict conflicts based on the location and speed of the intruder aircraft sensed by the UAV and the conflict conditions.

[0030] When the collision condition is met, the speed of the drone is adjusted so that the drone and the intruder do not collide for a period of time in the future, and the angle between the adjusted speed and the specified motion direction is minimized and the speed value is maximized;

[0031] When the conflict condition is not met, the UAV flies at the specified speed.

[0032] Furthermore, establishing a conflict detection model includes:

[0033] Assume that the drone and the intruder are represented by A and B respectively, and the safety zones of A and B are respectively with radius R a and R b circle;

[0034] Expand the safe area of ​​B to a radius of R c circle, where R c =R a +R b , modeling A as a point mass;

[0035] With A as the origin, establish the position coordinate system XOY, C and D are two rays emitted from A and the radius R c The tangent point of the circle;

[0036] Assume that A and B meet at time t, the position of B in XOY is vector P, and the velocity of A is V a , the speed of B is V b , V b Relative to V a The speed is V ab , that is, V ab =Va -V b ;

[0037] The process of adjusting the speed of the drone is as follows: a Adjust the velocity vector to u and map u directly to the distance V between the two rays AC or AD. ab On a closer ray.

[0038] Furthermore, the adjustment speed vector u is calculated by the following formula:

[0039]

[0040] Where w = V ab -tP;

[0041]

[0042] In a third aspect, the present invention also provides a drone conflict detection and automatic release device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the method when executing the computer program; the device is installed on a drone, and the drone receives instructions from the device to implement conflict detection and automatic release.

[0043] In a fourth aspect, the present invention also provides a computer-readable storage medium for drone conflict detection and automatic release, on which a computer program is stored, and the computer program implements the method when executed by a processor.

[0044] Beneficial effects:

[0045] The UAV conflict detection and automatic resolution method provided by the present invention establishes a conflict detection model, and performs conflict prediction based on the conditions for conflict according to the position and speed of the intruder perceived by the UAV;

[0046] The present invention reselects the speed by using the improved ORCA algorithm, and directly maps the change amount to the distance V. ab The strategy on the nearest tangent line tries to choose the direction with the smallest angle of change and the maximum speed when calculating the speed, so that the UAV and the intruder will not collide in the future. There is no need to frequently reselect the UAV speed, which reduces the number of calculations and allows the UAV to fly toward the target point more quickly. It also avoids the problem of arbitrary reselection of speed when avoiding existing speed obstacles, which causes UAV jitter.

[0047] The present invention also provides a UAV conflict detection and automatic release system, equipment and computer-readable storage medium, which also have the above-mentioned beneficial effects. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to make the contents of the present invention more clearly understood, the present invention is further described in detail below based on specific embodiments of the present invention in conjunction with the accompanying drawings.

[0049] Figure 1 is a schematic diagram of the ORCA half plane;

[0050] Figure 2 This is the position coordinate system of embodiment 1 of the present invention;

[0051] Figure 3 A graph constructed by solving the vector u in Example 1 of the present invention;

[0052] Figure 4 This is a position diagram of UAVs A and B under the simulation of Example 1 of the present invention;

[0053] Figure 5 This is a diagram showing the specific parameters of UAV A according to Example 1 of the present invention;

[0054] Figure 6 This is a diagram showing the specific parameters of UAV B according to Example 1 of the present invention;

[0055] Figure 7 This is a schematic diagram of multiple drones in Example 1 of the present invention. DETAILED DESCRIPTION

[0056] The present invention will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments. The principles and features of the present invention will be described below in conjunction with the accompanying drawings. It should be noted that the embodiments and features of the embodiments in this application may be combined with each other unless there is a conflict. The embodiments are provided only to illustrate the present invention and are not intended to limit the scope of the invention.

[0057] ORCA is a method based on speed to avoid collisions with moving obstacles. It is simple and intuitive, has good real-time performance, and can meet the requirements of online obstacle avoidance. ORCA has achieved good results in local obstacle avoidance and is therefore used to solve the conflict resolution problem of drones. Figure 1 As shown, the original ORCA algorithm has high requirements on computing power and requires real-time calculation to resolve conflicts.

[0058] This invention aims to address the collision risk of drones in complex airspace environments, often caused by intersecting and highly overlapping flight paths. Through real-time monitoring and precise detection, potential conflicts are promptly identified, and an algorithm is used to plan an escape path. This intelligent escape path planning allows for the avoidance of secondary collisions, ensuring safe and orderly flight for drones and improving airspace efficiency and flight safety.

[0059] Example 1

[0060] This embodiment provides a method for detecting and resolving UAV conflicts based on an improved ORCA algorithm, including the following steps:

[0061] Step 1: Establish a conflict detection model

[0062] Step 2: Determine whether a conflict occurs based on the conflict detection model

[0063] Step 3: The drone senses the location and speed of the intruder and performs conflict prediction based on the conflict detection model:

[0064] When the conflict condition is met, that is, when a conflict is predicted to occur in the future, the speed of the UAV is reselected according to the improved ORCA conflict resolution algorithm;

[0065] When the no-conflict condition is met, that is, when it is predicted that no conflict will occur in the future, the UAV will fly towards the next target point at the specified maximum speed;

[0066] The drone keeps looping step 3 until it reaches the final destination.

[0067] Specifically, the method for establishing the conflict detection model in step 1 is as follows:

[0068] Assume that the drone and the intruder are represented by symbols A and B respectively, and the safety zones of A and B are respectively with radius R a and R b circle.

[0069] Expand the safe area of ​​B to a radius of R c circle, where R c =R a +R b , so that A can be regarded as a mass point for convenient modeling. Figure 2 As shown, with A as the origin, establish the position coordinate system XOY, C and D are two rays emitted from A and the radius R c Assume that A and B meet at time t, the position of B in XOY is vector P, and the speed of A is V a , the speed of B is V b , V b Relative to V a The speed is V ab , that is, V ab =V a -V b .

[0070] Combine Figure 3To find the ORCA half plane, first calculate the relevant angle between A and B. Assume that the range of the relevant angle is [0-90°]. The relevant angles include angle φ, angle φ1, and angle θ, where φ = φ1; angle φ is the direction angle of the line connecting the positions of A and B relative to AC, and angle θ is the direction angle of the line connecting the positions of A and B relative to vector V ab The direction angle; the calculation formula of angle φ and angle θ is as follows:

[0071]

[0072]

[0073] Where |P| represents the size of vector P, that is, the distance between A and B. The condition for a conflict is: conflict judgment distance h. If h>|P|, then A and B may conflict.

[0074] Then let w = V ab -tP, known:

[0075]

[0076] |w|cosφ=|V ab -P v |=|V ab |sinθ

[0077]

[0078] According to the root-finding formula of a quadratic equation, we can get

[0079]

[0080] Among them, t1 is a suitable solution, so we can find w, then

[0081]

[0082] u is the initial velocity V a The adjusted vectors, w and u, are collinear and parallel to BC, as Figure 3 shown.

[0083] When calculating the speed, try to choose the direction with the smallest change angle and the maximum speed. a Adjust the velocity vector to u and map u directly to the distance V between the two rays AC or AD. ab The nearest ray is used to reduce the number of calculations.

[0084] like Figure 7 As shown, we can get a The vertical line divides the space into two planes. The plane pointed to is the desired ORCA half-plane. For multiple intruders, multiple ORCA half-planes are obtained, and the optimal speed needs to be found, as shown in the shaded area in the figure. The final target speed needs to be determined using the original ORCA linear programming algorithm.

[0085] For example, the following is an analysis of a simulation result using the above method:

[0086] The conflict detection and resolution problem of two UAVs A and B in the present invention is simulated by Airsim. Assume that A and B enter the cruising state and set the initial positions of the two UAVs to (0, 0, 10) and (200, 200, 10), and their destinations are (200, 200, 10) and (0, 0, 10) respectively. If conflict detection and resolution are not performed, A and B will definitely conflict. Now set the conflict judgment distance h = 48, and the safety zone radius of A and B is R respectively. a =3 and R b =3, in fact R a and R b are larger than the actual fuselage radius of the drone. Figure 4 It can be seen that when A and B have a conflict, the improved ORCA algorithm can successfully detect and resolve the conflict. Figure 5 and Figure 6 is the parameter diagram of specific A and B, where distance is the relative distance between A and B, R c is the radius of the safety zone, where R c =R a +R b , h is the collision judgment distance, A_x_velocity is the component velocity of A on the X axis; A_y_velocity is the component velocity of A on the Y axis; A_z_velocity is the component velocity of A on the Z axis.

[0087] Example 2

[0088] This embodiment also provides a UAV conflict detection and automatic release system, the system comprising:

[0089] A model building module is used to build a conflict detection model;

[0090] A conflict condition setting module, which sets the conditions for conflict occurrence according to the conflict detection model;

[0091] The conflict prediction and resolution module uses the conflict detection model to predict conflicts based on the location and speed of the intruder aircraft sensed by the UAV and the conflict conditions.

[0092] When the collision condition is met, the speed of the drone is adjusted so that the drone and the intruder do not collide for a period of time in the future, and the angle between the adjusted speed and the specified motion direction is minimized and the speed value is maximized;

[0093] When the conflict condition is not met, the UAV flies at the specified speed.

[0094] Furthermore, establishing a conflict detection model includes:

[0095] Assume that the drone and the intruder are represented by A and B respectively, and the safety zones of A and B are respectively with radius R a and R b circle;

[0096] Expand the safe area of ​​B to a radius of R c circle, where R c =R a +R b , modeling A as a point mass;

[0097] With A as the origin, establish the position coordinate system XOY, C and D are two rays emitted from A and the radius R c The tangent point of the circle;

[0098] Assume that A and B meet at time t, the position of B in XOY is vector P, and the velocity of A is V a , the speed of B is V b , V b Relative to V a The speed is V ab , that is, V ab =V a -V b ;

[0099] The process of adjusting the speed of the drone is as follows: a Adjust the velocity vector to u and map u directly to the distance V between the two rays AC or AD. ab On a closer ray.

[0100] The adjustment speed vector u is calculated by the following formula:

[0101]

[0102] Where w = V ab -tP;

[0103]

[0104] Example 3

[0105] This embodiment provides a drone conflict detection and automatic release device, which includes a memory and a processor. The memory stores a computer program, and the processor implements the method described in Example 1 when executing the computer program. The device is installed on a drone, and the drone receives instructions from the device to implement conflict detection and automatic release.

[0106] Example 4

[0107] This embodiment provides a computer-readable storage medium for drone conflict detection and automatic resolution, on which a computer program is stored. When the computer program is executed by a processor, the method described in Example 1 is implemented.

[0108] Obviously, the above embodiments are merely examples for clarity of explanation and are not intended to limit the implementation methods. Those skilled in the art will readily appreciate that other variations or modifications based on the above descriptions are possible. It is not necessary and impossible to enumerate all implementation methods here. Obvious variations or modifications arising therefrom remain within the scope of protection of the present invention.

Claims

1. A method for detecting and automatically relieving a UAV conflict, characterized in that: The method comprises: Establish a conflict detection model; Setting the conditions for conflict occurrence according to the conflict detection model; Using the conflict detection model, based on the position and speed of the intruder aircraft sensed by the UAV, conflict prediction is performed according to the conflict conditions; When the collision condition is met, the speed of the drone is adjusted so that the drone and the intruder do not collide for a period of time in the future, and the angle between the adjusted speed and the specified motion direction is minimized and the speed value is maximized; When the conflict condition is not met, the UAV flies at the specified speed.

2. The method according to claim 1, characterized in that Described establishing conflict detection model comprises: Assume that the drone and the intruder are represented by A and B respectively, and the safety zones of A and B are respectively with radius R a and R b circle; Expand the safe area of ​​B to a radius of R c circle, where R c =R a +R b , modeling A as a point mass; With A as the origin, establish the position coordinate system XOY, C and D are two rays emitted from A and the radius R c The tangent point of the circle; Assume that A and B meet at time t, the position of B in XOY is vector P, and the velocity of A is V a , the speed of B is V b , V b Relative to V a The speed is V ab , that is, V ab =V a -V b ; The process of adjusting the speed of the drone is as follows: a Adjust the velocity vector to u and map u directly to the distance V between the two rays AC or AD. ab On a closer ray.

3. The method according to claim 2, characterized in that The adjustment speed vector u is calculated by the following formula: Where w = V ab -tP; 4. The method according to claim 3, characterized in that For multiple intruders, after calculating the adjusted velocity vector u, the straight line The pointed plane is the ORCA half plane, and the final target speed is obtained according to the ORCA linear programming algorithm.

5. The method according to claim 2, characterized in that The condition for the occurrence of a conflict is that if the conflict determination distance h satisfies: h>|P| Then A and B may conflict; Where |P| represents the size of vector P.

6. A UAV conflict detection and automatic release system, characterized in that: The system comprises: A model building module is used to build a conflict detection model; A conflict condition setting module, which sets the conditions for conflict occurrence according to the conflict detection model; The conflict prediction and resolution module uses the conflict detection model to predict conflicts based on the location and speed of the intruder aircraft sensed by the UAV and the conflict conditions. When the collision condition is met, the speed of the drone is adjusted so that the drone and the intruder do not collide for a period of time in the future, and the angle between the adjusted speed and the specified motion direction is minimized and the speed value is maximized; When the conflict condition is not met, the UAV flies at the specified speed.

7. The system according to claim 6, characterized in that Described establishing conflict detection model comprises: Assume that the drone and the intruder are represented by A and B respectively, and the safety zones of A and B are respectively with radius R a and R b circle; Expand the safe area of ​​B to a radius of R c circle, where R c =R a +R b , modeling A as a point mass; With A as the origin, establish the position coordinate system XOY, C and D are two rays emitted from A and the radius R c The tangent point of the circle; Assume that A and B meet at time t, the position of B in XOY is vector P, and the velocity of A is V a , the speed of B is V b , V b Relative to V a The speed is V ab , that is, V ab =V a -V b ; The process of adjusting the speed of the drone is as follows: a Adjust the velocity vector to u and map u directly to the distance V between the two rays AC or AD. ab On a closer ray.

8. The system according to claim 7, characterized in that The adjustment speed vector u is calculated by the following formula: Where w = V ab -tP; 9. A UAV conflict detection and automatic release device, comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 5 is implemented; the device is installed on a drone, and the drone receives instructions from the device to implement conflict detection and automatic resolution.

10. A computer-readable storage medium for detecting and automatically releasing unmanned aerial vehicle conflicts, having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.

Images