Unmanned aerial vehicle group dynamic interception decision-making method based on situation awareness

Abstract

The invention discloses an unmanned aerial vehicle group dynamic interception decision-making method based on situation awareness, and the method comprises the following steps: 1, building a state dominance model based on the position and speed information of our and enemy unmanned aerial vehicles; step 2, constructing an air combat capability dominant function based on the combat capabilities of the friend and the foe; designing a target allocation algorithm according to the step 3 or the step 3 '; 3, for the i-th unmanned aerial vehicle of the our part, calculating the maximum value of all the enemy unmanned aerial vehicles Pt and sorting, and taking the enemy unmanned aerial vehicle with the highest score as an interception object optimally allocated to the i-th unmanned aerial vehicle of the our part; 3, for the i-th unmanned aerial vehicle of the our part, all the enemy unmanned aerial vehicles L, Pv, Pw and Pc are subjected to sorting assignment, the assignment is subjected to summation sorting, and the enemy unmanned aerial vehicle with the highest score serves as an interception object of optimal allocation of the i-th unmanned aerial vehicle of the our part. According to the dynamic interception decision-making method provided by the invention, the combat effectiveness of the unmanned aerial vehicle group can be maximized, and the task completion efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of drone swarms, and in particular to a situation awareness-based dynamic interception decision method for drone swarms. Background Art

[0002] With the development of science and technology, Unmanned Aerial Vehicle (UAV) has been active in many fields such as civil and military confrontation due to its small size, high flexibility, low cost and many other advantages. In the face of natural disasters, UAVs can be used to search and rescue survivors and provide material support, thereby effectively ensuring the safety of search and rescue personnel and reducing the rescue costs in high-risk areas. In the military field, UAVs are mostly used for strategic tasks such as reconnaissance, detection and precision strikes on targets. Although a single drone can be equipped with different sensors to complete the corresponding tasks, it still shows many limitations in today's increasingly complex military practice.

[0003] In order to perform relatively complex tasks in complex environments, multiple isomorphic or heterogeneous UAVs are usually used to perform coordinated operations using information interaction. Quantity advantage is the main condition for swarm combat, and drone swarms are often able to carry out saturation attacks on targets because of their numerical advantage. By decomposing difficult tasks into several simpler combinations of task objectives through a multi-task allocation system, low-cost strikes on high-value tasks can be achieved. Relying on intelligence, drone swarms can perceive battlefield situations in multiple dimensions, autonomously execute combat plans, accurately select targets, and autonomously allocate offensive tasks. Moreover, due to the small size of drone swarms and the small radar technology signal characteristics, they are not easily detected by the enemy. At the same time, they can also use multiple platforms to achieve high-speed launches, which facilitates concentrated attacks in an instant, thereby achieving unexpected results. And this advantage is precisely the reason why countries are now stepping up the development of drone swarm countermeasure technology.

[0004] A drone swarm can be considered as a large and complex multi-agent group. The total performance of a drone swarm mission is not equal to the sum of the performance of each drone within it. The internal UAVs use collaborative control laws to orderly complete the assigned tasks while radiating the surrounding drones of the same group, greatly improving the efficiency of task execution and making it possible for drone swarms to complete more complex tasks. Its core is group intelligence, which will not affect the completion of the entire group's mission due to failures such as disconnection in a certain unit, and has strong robustness. Drone swarms are self-organizing, and their ability to complete various complex tasks is the intelligence that emerges through the interaction of simple individuals within the group. Summary of the invention

[0005] The present invention provides a decision-making method for dynamic interception of a drone swarm based on situational awareness, which provides a more scientific and effective basis and support for a target allocation algorithm when the enemy and us are in confrontation.

[0006] The technical solution adopted to achieve the purpose of the present invention is:

[0007] A method for dynamic interception decision of a drone swarm based on situational awareness comprises the following steps:

[0008] Step 1: Based on the position and speed information of our and enemy drones, a state advantage model is constructed. The state advantage model includes the distance value L between the enemy and us, the speed advantage P v , load advantage P w ;

[0009] Step 2: Based on the combat capabilities of both sides, construct an air combat capability advantage function and calculate the air combat capability advantage P c ;

[0010] Design a target allocation algorithm according to step 3 or step 3';

[0011] Step 3: Assume that there are n enemy drones in the confrontation. For our i-th drone, collect the distance value L and speed advantage P between it and all enemy drones. v , load advantage P w , Air Combat Capability Advantage c , calculate the comprehensive advantage P t :

[0012] P t =K1*L+K2*P v +K3*P w +K4*P c

[0013] Wherein, K1, K2, K3, K4 are weight coefficients, and K1+K2+K3+K4=1;

[0014] Calculate the P of all enemy drones t The maximum value of is sorted, and the enemy drone with the highest score is used as the optimal interception target for our i-th drone;

[0015] Step 3', for our ith UAV, collect the distance value L and speed advantage P between it and all enemy UAVs v , load advantage P w , Air Combat Capability Advantage c , and rank and assign values ​​to the above parameters of all enemy drones, add and sort the values, and use the enemy drone with the highest score as the optimal interception target for our i-th drone.

[0016] In the above technical solution, the calculation formula of the distance value L in step 1 is:

[0017]

[0018] Where l1 is the relative distance between our ith UAV and the enemy's jth UAV in the X-axis direction, l2 is the relative distance between our ith UAV and the enemy's jth UAV in the Y-axis direction, l3 is the relative distance between our ith UAV and the enemy's jth UAV in the Z-axis direction, P i (x), P i (y), P i (z) is the real-time position of our i-th UAV, P j (x), P j (y), P j (z) is the real-time position of the jth enemy UAV.

[0019] In the above technical solution, the calculation formula of the distance value L in step 1 is the real-time position P of our i-th drone i (x), P i (y), P i The calculation formula of (z) is:

[0020]

[0021] The real-time position P of the enemy's jth drone j (x), P j (y), P j The calculation formula of (z) is:

[0022]

[0023] In the formula, α is the inclination angle of the UAV itself, β is the deflection angle of the UAV itself, v is the flight speed, and t represents time;

[0024] The initial position expression of the enemy and our side is:

[0025]

[0026] In the formula, the enemy and our side each have n drones, X j represents the X-axis coordinate and Y-axis coordinate of our i-th drone i represents the Y-axis coordinate and Z-axis coordinate of our i-th drone i represents the Z-axis coordinate of our i-th drone, X j represents the X-axis coordinate and Y-axis coordinate of the j-th enemy drone j represents the Y-axis coordinate and Z-axis coordinate of the j-th enemy drone j represents the Z-axis coordinate of the jth enemy drone, Pi , P j They represent the coordinate positions of our i-th UAV and the enemy's j-th UAV respectively.

[0027] In the above technical solution, the speed advantage P of our i-th drone in step 1 is v The mathematical expression is as follows:

[0028]

[0029] In the formula, and are the speeds of our i-th UAV and the enemy j-th UAV respectively.

[0030] In the above technical solution, the load advantage P from the perspective of our i-th drone in step 1 is w The mathematical expression is:

[0031]

[0032] In the formula, w i and w j are the loads of our i-th UAV and the enemy j-th UAV respectively.

[0033] In the above technical solution, the air combat capability advantage P in step 2 c The mathematical expression is:

[0034]

[0035] In the formula, C i and C j are the air combat capability indexes of our i-th UAV and the enemy j-th UAV respectively. The calculation formula of air combat capability index C is as follows:

[0036] C=[lnB+ln(A1+1)+ln(A2)]ε1ε2ε3ε4

[0037] Wherein, B is the mobility parameter of the UAV; A1 is the firepower parameter of the UAV; A2 is the search capability parameter of the UAV; ε1 is the control coefficient, 0<ε1<1; ε2 is the survival coefficient, 0<ε2<1; ε3 is the communication range coefficient, 0<ε3<1; ε4 is the electronic warfare capability coefficient, 0<ε4<1.

[0038] In the above technical solution, it is assumed that there are n enemy drones in the confrontation, and the method for assigning the enemy distance value L in step 3' is as follows:

[0039] Our ith drone will sort and assign the collected distance values ​​L between it and all enemy drones, with the closest enemy drone being assigned a value of n and the farthest enemy drone being assigned a value of 1.

[0040] In the above technical solution, the enemy speed advantage P in step 3' v The assignment method is as follows:

[0041] Our i-th drone will collect the speed advantage P of each enemy drone unit v Sort and assign values, the slowest one is assigned to n, and the fastest one is assigned to 1.

[0042] Enemy load advantage P in step 3' w The assignment method is as follows:

[0043] Our i-th UAV will collect the unit load advantage P of each enemy UAV w Sorting and assignment are performed, the enemy drone with the highest payload advantage is assigned a value of n, and the enemy drone with the lowest value is assigned a value of 1.

[0044] The enemy's air combat capability advantage parameter P in step 3' c The assignment method is as follows:

[0045] The i-th UAV of our side will collect the air combat capability advantage parameter P of each enemy UAV c Sort and divide them into 5 levels, with the highest level enemy drone assigned a value of 5 and the lowest level enemy drone assigned a value of 1.

[0046] Compared with the prior art, the present invention has the following beneficial effects:

[0047] 1. The present invention controls the movement behavior of each intelligent agent by sensing the position and speed of other intelligent agents around each intelligent agent. This rapid response capability can make the drone swarm more adaptable to dynamic and complex battlefield environments.

[0048] 2. The present invention is based on the advantages of our and enemy drones, and integrates speed advantage, distance advantage, payload advantage and other advantage indicators to establish a dynamic perception model, and calculates the air combat capability advantage by integrating multiple indicators to evaluate the pros and cons of the drone group in air confrontation, and uses the target allocation algorithm to allocate drone interception targets, maximize the combat effectiveness of the drone group, and improve the efficiency of the drone group in completing tasks. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 Shown is a schematic diagram of situation awareness comparison between the enemy and our side in the situation awareness-based UAV swarm dynamic interception decision-making method of the present invention. DETAILED DESCRIPTION

[0050] The present invention is further described in detail below in conjunction with specific embodiments. 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.

[0051] Example 1

[0052] A decision-making method for dynamic interception of a drone swarm based on situational awareness, comprising:

[0053] Step 1: Based on the position and speed information of our and enemy drones, a state advantage model is constructed. The state advantage model includes the distance value L between the enemy and us, the speed advantage P v , load advantage P w .

[0054] The state advantage model is based on the position and speed information of both sides, and calculates the relative position and relative speed of the two sides, so as to determine who is in a more advantageous position and who is in a disadvantageous position. The state advantage model mainly focuses on the position and path parameters of each drone on both sides. In the initial state, each drone first obtains the position information n. There are n drones on each side, X i represents the X-axis coordinate and Y-axis coordinate of our i-th drone i represents the Y-axis coordinate and Z-axis coordinate of our i-th drone i represents the Z-axis coordinate of our i-th UAV, P i , P j They represent the coordinate positions of our i-th UAV and the enemy j-th UAV, respectively. The initial positions of the enemy and our side are P i , P j The expression is:

[0055]

[0056] Since the UAVs are maneuvering in three-dimensional space, the inclination angle α and deflection angle β of each UAV should be taken into account. As the confrontation progresses, the real-time positions of the two will change. The flight speed is v, the time is t, and the real-time position P of our UAV on the X-axis, Y-axis, and Z-axis is i (x), P i (y), P i The calculation formula of (z) is:

[0057]

[0058] The real-time position P of the enemy's jth drone on the X-axis, Y-axis, and Z-axis j (x), P j (y), P j The calculation formula of (z) is:

[0059]

[0060] According to the above formula, the position of our i-th drone can be updated in real time. Real-time updating of confrontation information can effectively help the drone group to allocate tasks and improve completion efficiency. Similarly, in the large-scale drone group confrontation practice based on game theory, the obtained position information needs to be calculated and converted into a distance value L that can be used for judgment. The core idea here is to distribute the intelligence and decision-making ability of the system among the drones, so that each drone has a certain degree of autonomy and decision-making ability, so that the drone can prioritize the enemy individuals by comparing the distance, and select the best confrontation individual to attack. The conversion formula of the distance value L is as follows:

[0061]

[0062] Where l1 is the relative distance between our ith UAV and the enemy's jth UAV in the X-axis direction, l2 is the relative distance between our ith UAV and the enemy's jth UAV in the Y-axis direction, l3 is the relative distance between our ith UAV and the enemy's jth UAV in the Z-axis direction, P i (x), P i (y), P i (z) represents the real-time position of our i-th UAV, P j (x), P j (y), P j (z) represents the real-time position of the jth enemy UAV.

[0063] Speed ​​advantage v It is mainly an indicator that reflects the difference in mobility between enemy and friendly drones. Maneuverability is a very important indicator in drone swarm confrontation, which affects the combat effectiveness and survivability of drone swarms. Highly maneuverable drones can reach the target area more quickly, perform reconnaissance and strike missions, and show advantages in supporting friendly aircraft. With high-speed maneuverability, drone swarms can form a situation of many versus few on the local battlefield, thereby greatly improving combat effectiveness. In actual confrontation scenarios, drone swarms with high mobility can often adjust tactics more flexibly and occupy more advantageous battlefield positions to gain greater strategic advantages. From the perspective of our i-th drone, the speed advantage P v The mathematical expression is as follows:

[0064]

[0065] In the formula and Represent the speeds of our i-th UAV and the enemy's j-th UAV respectively.

[0066] Step 2: Based on the combat capabilities of both sides, construct an air combat capability advantage function and calculate the air combat capability advantage P c ;

[0067] The air combat capability advantage model is based on the combat capability of both sides. Combining this state advantage model with the air combat capability advantage model for comprehensive analysis, a more accurate air combat capability advantage assessment can be obtained.

[0068] Air Combat Capability Advantage c It is to evaluate the advantages and disadvantages of drone swarms in air confrontation by combining multiple indicators. In air combat, the maneuverability, firepower, target detection capability, control efficiency, survivability, navigation capability, electronic warfare capability and other indicators of drones will affect their combat effectiveness. Therefore, evaluating the advantages of drone swarms in air combat capability requires comprehensive consideration of these indicators and systematic judgment. Among them, maneuverability refers to the flexibility and maneuverability of drones when flying in the air, including turning radius, speed and acceleration; firepower refers to the weapons and equipment of drones during attack and their use capabilities; target detection capability refers to the ability of drones to detect and track targets in the air, including sensor types and enemy identification capabilities; control efficiency refers to the efficiency of the command and control system of the drone swarm, including the stability of the command link, transmission speed and data processing capabilities; survivability refers to the drone's ability to resist strikes and self-repair when encountering enemy attacks; navigation capability refers to the drone's long flight time capability and navigation capability in complex environments; electronic warfare capability refers to the drone's ability in electronic interference and countermeasures.

[0069] The comprehensive evaluation of these indicators can help determine the actual capability level of drone swarms in air confrontation and formulate more effective tactical plans. c The mathematical expression is as follows:

[0070]

[0071] In the formula, C i and C j They represent the air combat capability index of our i-th UAV and the enemy j-th UAV respectively. The mathematical expression of air combat capability C is as follows:

[0072] C=[lnB+ln(A1+1)+ln(A2)]ε1ε2ε3ε4

[0073] In the formula, B represents the UAV maneuverability parameter; A1 represents the UAV firepower parameter; A2 represents the UAV search capability parameter; ε1 represents the control coefficient, 0<ε1<1; ε2 represents the survivability coefficient, 0<ε2<1; ε3 represents the communication range coefficient, 0<ε3<1; ε4 represents the electronic warfare capability coefficient, 0<ε4<1.

[0074] Step 3, refer to Figure 1, for our i-th UAV, collect the distance value L and speed advantage P between it and all enemy UAVs v , load advantage P w , Air Combat Capability Advantage c , calculate the comprehensive advantage P t :

[0075] P t =K1*L+K2*P v +K3*P w +K4*P c

[0076] Wherein, K1, K2, K3, K4 are weight coefficients, and K1+K2+K3+K4=1;

[0077] Calculate P of all enemy drone units t And sort them, and the enemy drone with the highest score will be the optimal interception target for our i-th drone;

[0078] Example 2

[0079] The difference from Example 1 is step 3. The target allocation method adopted in this example is as follows:

[0080] Step 3', assuming that there are n enemy drones in the confrontation, for our i-th drone, collect the distance value L and speed advantage P between it and all enemy drones v , load advantage P w , Air Combat Capability Advantage c , and rank and assign values ​​to the above parameters of all enemy drones, and add and sort the values. The enemy drone with the highest score will be the optimally assigned interception target for our i-th drone.

[0081] The assignment method of the enemy distance value L is as follows:

[0082] Our ith drone will sort and assign the collected distance values ​​L between it and all enemy drones, with the closest enemy drone being assigned a value of n and the farthest enemy drone being assigned a value of 1.

[0083] Enemy Speed ​​Advantage P v The assignment method is as follows:

[0084] Our i-th UAV will collect the speed advantage P of each enemy UAV v Sort and assign values, the slowest one is assigned to n, and the fastest one is assigned to 1.

[0085] Enemy Load Advantage P w The assignment method is as follows:

[0086] Our i-th UAV will collect the payload advantage P of each enemy UAV w Sorting and assignment are performed, the enemy drone with the highest payload advantage is assigned a value of n, and the enemy drone with the lowest value is assigned a value of 1.

[0087] Enemy air combat capability advantage parameter P c The assignment method is as follows:

[0088] The i-th UAV of our side will collect the air combat capability advantage parameter P of each enemy UAV c Sort and divide them into 5 levels, with the highest level enemy drone assigned a value of 5 and the lowest level enemy drone assigned a value of 1.

[0089] The above information will continue to change with the drone game between the two sides. Our i-th drone system will dynamically solve the target allocation problem it faces as the confrontation changes.

[0090] The above is only a preferred embodiment of the present invention. It should be pointed out that, for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A dynamic interception decision method for drone swarms based on situational awareness, characterized in that: The following steps are involved: Step 1: Based on the position and speed information of our and enemy drones, a state advantage model is constructed. The state advantage model includes the distance value L between the enemy and us, the speed advantage P v , load advantage P w ; Step 2: Based on the combat capabilities of both sides, construct an air combat capability advantage function and calculate the air combat capability advantage P c ; Design a target allocation algorithm according to step 3 or step 3'; Step 3: Assume that there are n drones on each side of the enemy in the confrontation. For the i-th drone of our side, collect the distance value L and speed advantage P between it and all enemy drones. v , load advantage P w , air combat capability advantage c , calculate the comprehensive advantage P t : P t =K1*L+K2*P v +K3*P w +K4*P c Wherein, K1, K2, K3, K4 are weight coefficients, and K1+K2+K3+K4=1; Calculate the P of all enemy drones t The maximum value of is sorted, and the enemy drone with the highest score is used as the optimal interception target for our i-th drone; Step 3', for our ith UAV, collect the distance value L and speed advantage P between it and all enemy UAVs v , load advantage P w , air combat capability advantage c , rank and assign values ​​to the above parameters of all enemy drone units, and add and sort the values. The enemy drone with the highest score is used as the optimally assigned interception target for our i-th drone.

2. The method for dynamic interception decision of drone swarm based on situational awareness according to claim 1, characterized in that: The calculation formula for the distance value L in step 1 is: Where l1 is the relative distance between our ith UAV and the enemy's jth UAV in the X-axis direction, l2 is the relative distance between our ith UAV and the enemy's jth UAV in the Y-axis direction, l3 is the relative distance between our ith UAV and the enemy's jth UAV in the Z-axis direction, P i (x), P i (y), P i (z) is the real-time position of our i-th UAV on the X, Y, and Z axes, P j (x), P j (y), P j (z) is the real-time position of the jth enemy UAV on the X, Y, and Z axes.

3. The method for dynamic interception decision of drone swarm based on situational awareness as claimed in claim 2, characterized in that: In the calculation formula of the distance value L described in step 1, the real-time position P of our i-th drone on the X, Y, and Z axes is i (x), P i (y), P i The calculation formula of (z) is: The real-time position P of the enemy's jth drone j (x), P j (y), P j The calculation formula of (z) is: In the formula, α is the inclination angle of the UAV itself, β is the deflection angle of the UAV itself, v is the flight speed, and t is the time; The initial position expression of the enemy and our side is: In the formula, the enemy and our side each have n drones, X i represents the X-axis coordinate and Y-axis coordinate of our i-th drone i represents the Y-axis coordinate and Z-axis coordinate of our i-th drone i represents the Z-axis coordinate of our i-th drone, X j represents the X-axis coordinate and Y-axis coordinate of the jth enemy drone j represents the Y-axis coordinate and Z-axis coordinate of the j-th enemy drone j represents the Z-axis coordinate of the jth enemy drone, P i , P j They represent the coordinate positions of our i-th UAV and the enemy's j-th UAV respectively.

4. The method for dynamic interception decision of drone swarm based on situational awareness according to claim 1, characterized in that: In step 1, the speed advantage P of our i-th drone from its perspective v The mathematical expression is: In the formula, and are the speeds of our i-th UAV and the enemy j-th UAV respectively.

5. The method for dynamic interception decision of drone swarm based on situational awareness according to claim 1, characterized in that: The load advantage P from the perspective of our i-th drone in step 1 w The mathematical expression is: In the formula, w i and w j are the loads of our i-th UAV and the enemy j-th UAV respectively.

6. The method for dynamic interception decision of drone swarm based on situational awareness according to claim 1, characterized in that: Step 2: Air Combat Capability Advantage P c The mathematical expression is: In the formula, C i and C j are the air combat capability indexes of our i-th UAV and the enemy j-th UAV respectively. The calculation formula of air combat capability index C is: C=[lnB+ln(A1+1)+ln(A2)]ε1ε2ε3ε4 Wherein, B is the mobility parameter of the UAV; A1 is the firepower parameter of the UAV; A2 is the search capability parameter of the UAV; ε1 is the control coefficient, 0<ε1<1; ε2 is the survival coefficient, 0<ε2<1; ε3 is the communication range coefficient, 0<ε3<1; ε4 is the electronic warfare capability coefficient, 0<ε4<1.

7. The method for dynamic interception decision of drone swarm based on situational awareness according to claim 1, characterized in that: Assume that there are n enemy drones in the confrontation, and the assignment method of the enemy distance value L in step 3' is as follows: Our ith drone will sort and assign the collected distance values ​​L between it and all enemy drones, with the closest enemy drone being assigned a value of n and the farthest enemy drone being assigned a value of 1.

8. The method for dynamic interception decision of drone swarm based on situational awareness as claimed in claim 1, characterized in that: The enemy's speed advantage P in step 3' v The assignment method is as follows: Our i-th UAV will collect the speed advantage P of each enemy UAV v Sort and assign values, the slowest one is assigned to n, and the fastest one is assigned to 1.

9. The method for dynamic interception decision of drone swarm based on situational awareness as claimed in claim 1, characterized in that: Enemy load advantage P in step 3' w The assignment method is as follows: Our i-th UAV will collect the payload advantage P of each enemy UAV w Sort and assign values, the enemy drone with the highest value is assigned a value of n, and the enemy drone with the lowest value is assigned a value of 1.

10. The method for dynamic interception decision of drone swarm based on situational awareness as claimed in claim 1, characterized in that: The enemy's air combat capability advantage parameter P in step 3' c The assignment method is as follows: The i-th UAV of our side will collect the air combat capability advantage parameter P of each enemy UAV c Sort and divide them into 5 levels, with the highest level enemy drone assigned a value of 5 and the lowest level enemy drone assigned a value of 1.

Images