Target tracking based aircraft closed loop maneuvering method, device, equipment and medium

Abstract

The application relates to a target tracking-based aircraft closed-loop maneuvering method, device, equipment and medium, and relates to the technical field of aircraft maneuvering.The method comprises the following steps: acquiring first flight state information of an attacking aircraft and second flight state information of a target aircraft in real time; determining first reference data corresponding to a pure tracking strategy based on the first flight state information and the second flight state information; determining second reference data corresponding to each non-pure tracking strategy and a decision factor corresponding to the second reference data based on the first flight state information and the second flight state information; and determining flight guidance point information corresponding to the attacking aircraft according to the first reference data and / or each second reference data and each decision factor.The application has the effect that advantage flight guidance point information is calculated according to the maneuvering action of the attacking aircraft and the flight state information of the target aircraft, so that the attacking aircraft can timely lock the target.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of aircraft maneuvering, and in particular to an aircraft closed-loop maneuvering method based on tracking targets, an apparatus, a device and a medium. BACKGROUND

[0002] Aircraft one-on-one air combat maneuvering refers to one-on-one air combat between two aircrafts in air combat, in which the aircrafts compete for air superiority through maneuvering actions, tactical strategies and weapon systems.

[0003] Traditional aircraft one-on-one air combat maneuvering often adopts an open-loop control method, in which a decision system selects one maneuvering action according to the current situation of both sides according to a certain decision period, and sends the selected maneuvering action to the attacking aircraft, which executes the maneuvering action in an open loop within a single decision period.

[0004] When the attacking aircraft executes a certain maneuvering action within the decision period, the attacking aircraft maneuvering is out of contact with the target aircraft movement, and the potential maneuvering of the target aircraft is ignored, so that the maneuvering result of the attacking aircraft may deviate from the expected tactical effect, affecting the decision efficiency and leading to the failure to achieve the timely occupation of the advantageous position. SUMMARY

[0005] In order to reduce the deviation of the attacking aircraft maneuvering result from the expected tactical effect, the present application provides an aircraft closed-loop maneuvering method based on tracking targets, an apparatus, a device and a medium.

[0006] In a first aspect, the present application provides an aircraft closed-loop maneuvering method based on tracking targets, which adopts the following technical solution:

[0007] The aircraft closed-loop maneuvering method based on tracking targets comprises:

[0008] real-time acquisition of first flight state information of an attacking aircraft and second flight state information of a target aircraft;

[0009] determination of first reference data corresponding to a pure tracking strategy based on the first flight state information and the second flight state information, the pure tracking strategy being a strategy corresponding to the same target tracking position of the attacking aircraft and the position of the target aircraft when the attacking aircraft tracks the target aircraft;

[0010] determine, based on the first flight state information and the second flight state information, second reference data corresponding to each non-pure pursuit strategy, and a decision factor corresponding to each of the second reference data, wherein, for each of the first reference data and each of the second reference data, the reference data is data for describing the position of the target aircraft, and the decision factor is a parameter representing the importance of the reference data relative to flight guide point information, and the flight guide point information is a vector corresponding to a target pursuit position to which the attacking aircraft flies;

[0011] determine, based on the first reference data, each of the second reference data, and each of the decision factors, flight guide point information corresponding to the attacking aircraft, so as to guide the attacking aircraft to fly according to the flight guide point information.

[0012] The present application has the advantages that: according to the first flight state information and the second flight state information obtained in real time, the first reference data and at least one second reference data corresponding to each time point are determined, the flight guide point information is determined in space, the attacking aircraft is guided to fly according to the flight guide point information, and the attacking aircraft can lock the target in time. The flight guide point information corresponding to the attacking aircraft changes continuously with the second flight state information of the target aircraft, and the maneuvering action of the attacking aircraft guided according to the flight guide point information changes continuously with the second flight state information of the target aircraft, so that a closed loop relationship between the maneuvering action of the attacking aircraft and the second flight state of the target aircraft is established.

[0013] Further, the determination of the first reference data corresponding to the pure pursuit strategy based on the first flight state information and the second flight state information comprises:

[0014] obtaining a target coordinate of the target aircraft based on a ground coordinate system, and taking the target coordinate as the first reference data, wherein the target coordinate is a coordinate of the current position of the target aircraft;

[0015] The determination of the second reference data corresponding to each non-pure pursuit strategy and the decision factor corresponding to each of the second reference data based on the first flight state information and the second flight state information comprises:

[0016] For each of the non-pure pursuit strategies, the reference vector corresponding to the non-pure pursuit strategy is calculated based on a preset algorithm corresponding to each of the non-pure pursuit strategies, each of the second reference data comprises a reference vector, and the reference vector is taken as the second reference data corresponding to the non-pure pursuit strategy;

[0017] The decision factor corresponding to each of the reference vectors is obtained in real time based on a pre-trained artificial intelligence model.

[0018] The beneficial effect of the above further scheme is that the first flight state information and the second flight state information obtained in real time are taken as inputs of the artificial intelligence model, and the artificial intelligence model outputs decision factors corresponding to different reference vectors, so that the decision factors corresponding to different reference vectors can change with the changes of the first flight state information and the second flight state information, thereby improving the accuracy of flight guidance point information determination.

[0019] Further, the flight guidance point information corresponding to the attacking aircraft is determined according to the first reference data, each second reference data, and each decision factor, comprising:

[0020] The reference vectors are weighted and calculated based on the decision factors to obtain a first calculation value;

[0021] The sum of the first calculation value and the target coordinates is calculated to obtain a second calculation value, and the second calculation value is taken as the flight guidance point information.

[0022] The beneficial effect of the above further scheme is that the target coordinates are combined with multiple weighted and calculated reference vectors to determine the flight guidance point coordinates in real time in space, and the first calculation value and the second calculation value can continuously change with the changes of the first flight state information and the second flight state information, thereby guiding the attacking aircraft to fly through the closed-loop continuous flight guidance point information, avoiding many unnecessary maneuvering actions, and improving the decision efficiency.

[0023] Further, the non-pure pursuit strategy includes a front pursuit strategy and a rear pursuit strategy; the reference vector corresponding to each non-pure pursuit strategy is calculated based on a preset algorithm corresponding to the non-pure pursuit strategy, comprising:

[0024] The first preset algorithm corresponding to the front pursuit strategy and the second preset algorithm corresponding to the rear pursuit strategy are obtained;

[0025] Based on the first flight state and the second flight state, each first parameter value in the first preset algorithm and each second parameter value in the second preset algorithm are obtained;

[0026] Based on each first parameter value, the reference vector corresponding to the front pursuit strategy is obtained through the first preset algorithm Based on each second parameter value, the reference vector corresponding to the rear pursuit strategy is obtained through the second preset algorithm Wherein,

[0027] The first preset algorithm is:

[0028]

[0029] The second preset algorithm is:

[0030]

[0031] In the first preset algorithm and the second preset algorithm, k is a predicted value of the target aircraft's maneuvering capability, V B is the current speed of the target aircraft, Δt is the time required for each decision, is a unit vector of the Ox k axis in the track coordinate system of the target aircraft.

[0032] The beneficial effects of the above further scheme are that the reference vector and the reference vector are calculated according to the first flight state information and the second flight state information obtained in real time.

[0033] Further, the non-pure pursuit strategy includes a climbing maneuvering strategy and a diving maneuvering strategy; and the calculation of the corresponding reference vector based on the preset algorithm corresponding to each non-pure pursuit strategy further includes:

[0034] obtaining a third preset algorithm corresponding to the climbing maneuvering strategy and a fourth preset algorithm corresponding to the diving maneuvering strategy;

[0035] obtaining each third parameter value in the third preset algorithm and each fourth parameter value in the fourth preset algorithm based on the first flight state and the second flight state;

[0036] obtaining the reference vector of the climbing maneuvering strategy through the third preset algorithm based on each third parameter value; obtaining the reference vector of the diving maneuvering strategy through the fourth preset algorithm based on each fourth parameter value.

[0037] The third preset algorithm is:

[0038]

[0039] The fourth preset algorithm is:

[0040]

[0041] In the third preset algorithm and the fourth preset algorithm, k is a predicted value of the target aircraft's maneuvering capability, VA is the current speed of the attacking aircraft, g is the acceleration of gravity, is a unit vector of the Oy i axis in the reference coordinate system of the target aircraft.

[0042] An advantage of the above further solution is that the reference vector and the reference vector are calculated according to the first flight state information and the second flight state information obtained in real time.

[0043] Further, the non-pure pursuit strategy further includes an inner-loop circling strategy and an outer-loop circling strategy; and the calculation of the reference vector corresponding to each of the non-pure pursuit strategies based on the preset algorithm corresponding to each of the non-pure pursuit strategies further includes:

[0044] obtaining a fifth preset algorithm corresponding to the inner-loop circling strategy and a sixth preset algorithm corresponding to the outer-loop circling strategy;

[0045] obtaining each fifth parameter value in the fifth preset algorithm and each sixth parameter value in the sixth preset algorithm based on the first flight state and the second flight state;

[0046] obtaining the reference vector corresponding to the inner-loop circling strategy based on each of the fifth parameter values through the fifth preset algorithm obtaining the reference vector corresponding to the outer-loop circling strategy based on each of the sixth parameter values through the sixth preset algorithm wherein,

[0047] The fifth preset algorithm is:

[0048]

[0049] The sixth preset algorithm is:

[0050]

[0051] In the fifth preset algorithm and the sixth preset algorithm, k is a predicted value of the target aircraft's maneuverability, Q AB is a distance vector between the attacking aircraft and the turning center of the target aircraft in a horizontal plane based on a ground coordinate system, is a unit vector of an Oz k axis in a track coordinate system of the target aircraft.

[0052] An advantage of the above further solution is that the reference vector and the reference vector are calculated according to the first flight state information and the second flight state information obtained in real time.

[0053] Further, the predicted value k of the target aircraft's maneuverability is obtained by the following method:

[0054] obtaining image information of the target aircraft;

[0055] Based on the image information, obtain the aircraft type information of the target aircraft;

[0056] The predicted value k of maneuverability is obtained based on the aircraft type information.

[0057] The beneficial effect of adopting the above-mentioned further solutions is that it improves the accuracy of aircraft model information identification.

[0058] Secondly, this application provides a closed-loop maneuvering device for aircraft based on target tracking, comprising:

[0059] The first acquisition module is used to acquire the first flight status information of the attacking aircraft and the second flight status information of the target aircraft in real time.

[0060] The first determining module is used to determine the first reference data corresponding to the pure tracking strategy based on the first flight state information and the second flight state information. The pure tracking strategy is the strategy corresponding to the target tracking position of the attacking aircraft being the same as the position of the target aircraft when the attacking aircraft tracks the target aircraft.

[0061] The second determining module is used to determine, based on the first flight state information and the second flight state information, the second reference data corresponding to each non-pure tracking strategy, and the decision factor corresponding to each second reference data. For each reference data in the first reference data and each second reference data, the reference data is data used to describe the position of the target aircraft, and the decision factor is a parameter characterizing the importance of the reference data relative to the flight guidance point information. The flight guidance point information is a vector corresponding to the target tracking position to which the attack aircraft has flown.

[0062] The third determining module is used to determine the flight guidance point information corresponding to the attack aircraft based on the first reference data, each of the second reference data and each of the decision factors, so as to guide the attack aircraft to fly according to the flight guidance point information.

[0063] Thirdly, this application provides an electronic device, including a processor coupled to the memory;

[0064] The processor is configured to execute a computer program stored in the memory, causing the electronic device to perform the method as described in any of the first aspects.

[0065] Fourthly, this application provides a computer-readable storage medium including a computer program or instructions that, when executed on a computer, cause the computer to perform the method as described in any of the first aspects. Attached Figure Description

[0066] Figure 1 A flowchart of a method for tracking target based aircraft closed-loop maneuvering according to an embodiment of the present application;

[0067] Figure 2 A schematic diagram of an inner loop circling strategy according to an embodiment of the present application;

[0068] Figure 3 A schematic diagram of an outer loop circling strategy according to an embodiment of the present application;

[0069] Figure 4 A flowchart of a method for determining flight guidance point information according to an embodiment of the present application;

[0070] Figure 5 A schematic diagram of all reference vectors between an attacking aircraft A and a target aircraft B according to an embodiment of the present application;

[0071] Figure 6 A block diagram of a tracking target based aircraft closed-loop maneuvering device according to an embodiment of the present application;

[0072] Figure 7 A block diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0073] The present application will be further described below in conjunction with the accompanying drawings.

[0074] Before introducing the present application, first, the related background and terms in the present application are explained.

[0075] Artificial intelligence (AI) is to use digital computers or digital computer controlled machines to simulate, extend and expand human intelligence, perceive environment, acquire knowledge and use knowledge to obtain the best results. In other words, artificial intelligence is a comprehensive technology of computer science, which tries to understand the essence of intelligence and produce a new intelligent machine that can react in a similar way to human intelligence. Artificial intelligence is to study the design principles and implementation methods of various intelligent machines, so that the machine has the functions of perception, reasoning and decision-making.

[0076] Artificial intelligence technology is a comprehensive discipline, involving a wide range of fields, both hardware and software technologies. Artificial intelligence basic technologies generally include technologies such as sensors, special artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation / interaction system, mechatronics, etc. Artificial intelligence software technology mainly includes computer vision technology, speech processing technology, natural language processing technology, and machine learning / deep learning, etc. several major directions.

[0077] Machine Learning (ML) is a multi-disciplinary subject involving probability theory, statistics, approximation theory, convex analysis, algorithmic complexity theory, etc. It is a specialized study of how computers simulate or implement human learning behavior to acquire new knowledge or skills, reorganize existing knowledge structure, and continuously improve their performance. Machine learning is the core of artificial intelligence and the fundamental approach to making computers intelligent. It is applied in various fields of artificial intelligence. Machine learning and deep learning usually include artificial neural networks, belief networks, reinforcement learning, transfer learning, inductive learning, and adversarial learning.

[0078] Big data refers to a collection of data that cannot be captured, managed, and processed within a certain time frame using conventional software tools. It is a massive, high-growth, and diverse information asset that requires new processing models to have stronger decision-making, insight discovery, and process optimization capabilities. With the advent of the cloud era, big data has attracted more and more attention. Big data requires special techniques to effectively process large amounts of data over time. Techniques suitable for big data include large-scale parallel processing databases, data mining, distributed file systems, distributed databases, cloud computing platforms, the Internet, and scalable storage systems.

[0079] The embodiment of the present application provides a kind of aircraft closed loop maneuvering method based on tracking target, which can be executed by equipment, which can be server also can be terminal equipment, wherein the server can be independent physical server, can also be multiple physical servers constitute server cluster or distributed system, it can also be cloud server that provides cloud computing service.Terminal equipment can be smart phone, tablet computer, desktop computer etc., but not limited to this.

[0080] As shown in Figure 1 A kind of aircraft closed loop maneuvering method based on tracking target, with electronic equipment as the main body of execution, the main process of its method is described as follows (step S101-S104):

[0081] Step S101: the first flight state information of attack aircraft and the second flight state information of target aircraft are acquired in real time.

[0082] The aircraft includes unmanned aerial vehicles, manned aircraft and other types of flying devices. In the embodiment, the aircraft can be a fixed-wing aircraft. The aircraft in one-to-one air combat includes attack aircraft and target aircraft, wherein the attack aircraft is the aircraft corresponding to the current electronic device, and the target aircraft is the air combat target of the attack aircraft. The first flight state information and the second flight state information both include flight speed and current position, etc. information that can reflect the flight state.

[0083] Before step S101, the method comprises: establishing a reference coordinate system Ox i y i z i and a flight path coordinate system Ox k y k z k .

[0084] The origin O of the reference coordinate system is located at the center of mass of the aircraft, the Ox i axis is fixed to point north, the Oy i axis is vertically upward in the vertical plane, and the Oz i axis is perpendicular to the x i Oy i plane to form a right-handed coordinate system, and the Oz i axis points east;

[0085] The origin O of the flight path coordinate system is located at the center of mass of the aircraft, the Ox k axis is along the direction of the aircraft speed, the Oy k axis is perpendicular to the Ox k axis in the vertical plane containing the Ox k axis upward, and the Oz k axis is perpendicular to the x k Oy k plane to form a right-handed coordinate system.

[0086] Step S102: determining first reference data corresponding to the pure pursuit strategy based on the first flight state information and the second flight state information, the pure pursuit strategy being a strategy corresponding to the fact that, when the attacking aircraft pursues the target aircraft, the target pursuit position of the attacking aircraft is the same as the position of the target aircraft.

[0087] Step S103: determining second reference data corresponding to each non-pure pursuit strategy and a decision factor corresponding to each second reference data based on the first flight state information and the second flight state information, wherein, for each reference data in the first reference data and the second reference data, the reference data is data used to describe the position of the target aircraft, and the decision factor is a factor representing the importance of the reference data relative to the flight guidance point information.

[0088] During the air combat, a plurality of established maneuvering strategies are generated according to the flight state information of the aircrafts of both sides and existing air combat experience. The maneuvering strategies include a pure pursuit strategy and a plurality of non-pure pursuit strategies other than the pure pursuit strategy. In this embodiment, the non-pure pursuit strategies include a front pursuit strategy, a rear pursuit strategy, and / or a climb maneuvering strategy, a dive maneuvering strategy, and / or an inner loop circling strategy, an outer loop circling strategy.

[0089] A forward-tracking strategy means the attack aircraft points ahead of the target aircraft, which allows it to approach the target more quickly for fire control weapon lock-on. A backward-tracking strategy means the attack aircraft points behind the target aircraft, which helps the attack aircraft maintain a superior position, especially when the target aircraft is making a sharp turn, preventing the attack aircraft from overtaking.

[0090] A climb maneuver means the attacking aircraft is positioned above the target aircraft, favoring an attack from above. The climb maneuver converts kinetic energy into potential energy by slowing down during a climb, preventing the attacking aircraft from overtaking due to excessive speed and converting excess energy into high-altitude advantage. A dive maneuver means the attacking aircraft is positioned below the target aircraft, favoring an attack from below. The dive maneuver converts potential energy into kinetic energy by accelerating during a dive, allowing the attacking aircraft to gain positional advantage and rapidly approach the target.

[0091] like Figure 2 As shown, the two aircraft engaged in a one-on-one air combat are attack aircraft A and target aircraft B. The inner-loop turning strategy means that attack aircraft A points into the turning circle of target aircraft B. Attack aircraft A and target aircraft B are in a single-loop turning posture, which is beneficial for attack aircraft A to stay behind target aircraft B and accumulate angular advantage. Figure 3 As shown, the outer ring circling strategy means that the attack aircraft A points outside the turning circle of the target aircraft B. The attack aircraft A and the target aircraft B are in a double-ring turning posture, which is beneficial for the attack aircraft A to turn in the opposite direction to the target aircraft B in advance, so as to lock onto the target as soon as possible.

[0092] The first reference data for a pure tracking strategy includes the target coordinates, which are the coordinates of the target aircraft's current position; the second reference data for each non-pure tracking strategy defines a corresponding reference vector.

[0093] Multiple reference vectors corresponding to the non-pure tracking strategy form a three-dimensional maneuvering decision space around the target aircraft in real time, wherein the origin of each reference vector coincides with the centroid of the target aircraft.

[0094] The decision factor is a weight coefficient ranging from 0 to 1, used to reflect the maneuvering tendency of the attack aircraft. The influence of the baseline vector of different decision factors on the guidance point information obtained in subsequent calculations is different. Therefore, the decision factor corresponding to each baseline vector may be different.

[0095] In this embodiment, step S102 includes the following processing: based on the ground coordinate system, the target coordinates of the target aircraft are obtained, and the target coordinates are used as the first reference data.

[0096] Step S103 comprises the following processing: for each non-pure pursuit strategy, calculating a reference vector corresponding to the non-pure pursuit strategy based on a preset algorithm corresponding to the non-pure pursuit strategy, taking the reference vector as second reference data corresponding to the non-pure pursuit strategy; and obtaining a decision factor corresponding to each reference vector in real time based on a pre-trained artificial intelligence model.

[0097] The ground coordinate system is a coordinate system whose reference coordinate system is consistent with that of the attacking aircraft and whose origin is a point on the ground. The electronic device pre-stores preset algorithms corresponding to the reference vectors of each non-pure pursuit strategy.

[0098] In this embodiment, the decision factor is taken as the action space, the first flight state information and the second flight state information of the two aircrafts (the target aircraft and the attacking aircraft) are taken as the state space, a reward function is designed according to the action space and the state space, and after training on a sample data set, a trained artificial intelligence model is obtained. Then, the first flight state information and the second flight state information of the two aircrafts are taken as the input of the artificial intelligence model, and the artificial intelligence model outputs the decision factors of all non-pure pursuit strategies in real time when the first flight state information and the second flight state information are input.

[0099] The first flight state information and the second flight state information obtained in real time are taken as the input of the artificial intelligence model, and the artificial intelligence model outputs the decision factors corresponding to different reference vectors, so that the decision factors corresponding to different reference vectors can change with the changes of the first flight state information and the second flight state information, thereby improving the accuracy of the determination of the flight guidance point information.

[0100] Step S104: determining flight guidance point information corresponding to the attacking aircraft according to the first reference data, each second reference data and each decision factor, so as to guide the flight of the attacking aircraft according to the flight guidance point information. The flight guidance point information is a vector corresponding to the target tracking position of the attacking aircraft.

[0101] When the attacking aircraft flies towards the flight guidance point, it flies by using a guidance method in which the velocity vector always points to the flight guidance point information.

[0102] In this embodiment, according to the first flight state information and the second flight state information obtained in real time, the first reference data and the at least one second reference data are combined in each time, the closed-loop continuous flight guidance point information is determined in space, and the attack aircraft is guided to fly according to the flight guidance point information, so that the attack aircraft can timely lock the target. The flight guidance point information corresponding to the attack aircraft changes continuously with the second flight state information of the target aircraft, and the maneuvering action of the attack aircraft guided to fly according to the flight guidance point information changes continuously with the second flight state information of the target aircraft, so that the closed-loop relationship between the maneuvering action of the attack aircraft and the second flight state of the target aircraft is established.

[0103] As shown in Figure 4 Step S104 includes the following processing:

[0104] Step S1041: Each reference vector is weighted and calculated based on the decision factor to obtain a first calculation value.

[0105] Step S1042: The sum of the first calculation value and the target coordinates is calculated to obtain a second calculation value, and the second calculation value is taken as the flight guidance point information.

[0106] Based on the target coordinates, the reference vectors of multiple weighted calculations are combined to determine the flight guidance point coordinates in space in real time. The first calculation value and the second calculation value can change continuously with the changes of the first flight state information and the second flight state information, so that the attack aircraft is guided to fly through the closed-loop continuous flight guidance point information, many unnecessary maneuvering actions are avoided, the decision efficiency is improved, and a new solution idea is provided for air combat maneuvering strategy.

[0107] If the non-pure pursuit strategy includes a pre-position pursuit strategy and a post-position pursuit strategy, the corresponding reference vector is calculated based on the preset algorithm corresponding to each non-pure pursuit strategy, including the following processing:

[0108] The first preset algorithm corresponding to the pre-position pursuit strategy and the second preset algorithm corresponding to the post-position pursuit strategy are obtained.

[0109] Based on the first flight state and the second flight state, each first parameter value in the first preset algorithm and each second parameter value in the second preset algorithm are obtained.

[0110] Based on each first parameter value, the reference vector corresponding to the pre-position pursuit strategy is obtained through the first preset algorithm Based on each second parameter value, the reference vector corresponding to the post-position pursuit strategy is obtained through the second preset algorithm Wherein,

[0111] The first preset algorithm is:

[0112]

[0113] The second preset algorithm is:

[0114]

[0115] In the first preset algorithm and the second preset algorithm, k is a predicted value of the target aircraft's maneuverability, the maneuverability refers to the ability of the target aircraft to change its flight state or trajectory, V B is a current speed of the target aircraft, and Δt is a time required for each decision, is a unit vector in the positive direction of the Ox k axis in a track coordinate system of the target aircraft.

[0116] The reference vector corresponding to the pre-position pursuit strategy is is a unit vector in the positive direction of the Ox k axis in a track coordinate system of the target aircraft. The reference vector corresponding to the post-position pursuit strategy is is a unit vector in the negative direction of the Ox k axis in a track coordinate system of the target aircraft.

[0117] If the non-pure pursuit strategy includes a climbing maneuver strategy and a diving maneuver strategy, the corresponding reference vector is calculated based on a preset algorithm corresponding to each non-pure pursuit strategy, including the following processing:

[0118] A third preset algorithm corresponding to the climbing maneuver strategy and a fourth preset algorithm corresponding to the diving maneuver strategy are obtained.

[0119] Based on the first flight state and the second flight state, each third parameter value in the third preset algorithm and each fourth parameter value in the fourth preset algorithm are obtained.

[0120] Based on each third parameter value, the reference vector corresponding to the climbing maneuver strategy is obtained through the third preset algorithm Based on each fourth parameter value, the reference vector corresponding to the diving maneuver strategy is obtained through the fourth preset algorithm wherein,

[0121] The third preset algorithm is:

[0122]

[0123] The fourth preset algorithm is:

[0124]

[0125] In the third preset algorithm and the fourth preset algorithm, k is a predicted value of the target aircraft's maneuverability, the maneuverability refers to the ability of the target aircraft to change its flight state or trajectory, V Ais the current speed of the attacking aircraft, g is the acceleration of gravity, is a unit vector of the Oy axis in the reference coordinate system of the target aircraft, i is a unit vector of the Oy axis in the reference coordinate system of the target aircraft.

[0126] is a reference vector corresponding to the climbing maneuver strategy is a unit vector of the Oy axis in the reference coordinate system of the target aircraft, i is a reference vector corresponding to the diving maneuver strategy in the positive direction of the Oy axis, is a unit vector of the Oy axis in the reference coordinate system of the target aircraft, i is a unit vector of the Oy axis in the reference coordinate system of the target aircraft.

[0127] If the non-pure pursuit strategy includes an inner loop circling strategy and an outer loop circling strategy, the reference vector corresponding to each non-pure pursuit strategy is calculated based on a preset algorithm corresponding to the non-pure pursuit strategy, including the following processing:

[0128] Obtaining a fifth preset algorithm corresponding to the inner loop circling strategy and a sixth preset algorithm corresponding to the outer loop circling strategy;

[0129] Based on the first flight state and the second flight state, obtaining each fifth parameter value in the fifth preset algorithm and each sixth parameter value in the sixth preset algorithm;

[0130] Based on each fifth parameter value, the reference vector corresponding to the inner loop circling strategy is obtained through the fifth preset algorithm Based on each sixth parameter value, the reference vector corresponding to the outer loop circling strategy is obtained through the sixth preset algorithm wherein,

[0131] The fifth preset algorithm is:

[0132]

[0133] The sixth preset algorithm is:

[0134]

[0135] In the fifth preset algorithm and the sixth preset algorithm, k is a predicted value of the maneuvering capability of the target aircraft, the maneuvering capability refers to the ability of the target aircraft to change its flight state or trajectory, Q AB is a distance vector between the turning center of the attacking aircraft and the target aircraft in the horizontal plane based on the ground coordinate system, is a unit vector of the Oz axis in the flight path coordinate system of the target aircraft, k is a unit vector of the Oz axis in the flight path coordinate system of the target aircraft.

[0136] is a reference vector corresponding to the inner loop circling strategy is a unit vector of the Oz axis in the flight path coordinate system of the target aircraft, k is a reference vector corresponding to the outer loop circling strategy in the positive direction of the Oz axis Oz in the track coordinate system of the target aircraft k negative direction of the axis.

[0137] In this embodiment, the values of the same parameters in each first parameter value, each second parameter value, each third parameter value, each fourth parameter value, each fifth parameter value, and each sixth parameter value can be the same.

[0138] As Figure 5 shown, in this embodiment, the attack aircraft A and the target aircraft B perform one-to-one air combat, the non-pure pursuit strategy includes the pre-tracking strategy, the post-tracking strategy, the climbing maneuver strategy, the diving maneuver strategy, the inner loop circling strategy, and the outer loop circling strategy, therefore, the reference vectors include and The pure pursuit strategy is a strategy corresponding to the situation that the target tracking position of the attack aircraft corresponding to the target aircraft is the same as the position of the target aircraft. Figure 5 the line connecting the center of mass of the attack aircraft A and the center of mass of the target aircraft B in the

[0139] The first calculation value can be expressed as:

[0140]

[0141] The second calculation value can be expressed as:

[0142] The second calculation value P t = the first calculation value + the target coordinate P B

[0143] wherein α1, α2, α3, α4, α5, and α6 are decision factors, P t is the flight guidance point information of the attack aircraft, the target coordinate P B is the current position coordinate of the target aircraft.

[0144] According to the above six non-pure pursuit strategies and the pure pursuit strategy, the electronic device combines six reference vectors based on the target coordinate at each time, so as to determine the closed-loop continuous flight guidance point coordinates in the space to guide the flight of the attack aircraft. The generated flight guidance point information corresponding to the attack aircraft continuously changes with the second flight state information of the target aircraft, and the maneuver action of the attack aircraft guided according to the flight guidance point information continuously changes with the second flight state information of the target aircraft, so that a closed-loop relationship between the maneuver action of the attack aircraft and the second flight state of the target aircraft is established.

[0145] In this embodiment, each algorithm parameter value includes a predicted value k of the maneuverability of the target aircraft, wherein the predicted value k of the maneuverability of the target aircraft is obtained by: obtaining image information of the target aircraft; obtaining model information of the target aircraft based on the image information; and obtaining the predicted value k of the maneuverability based on the model information.

[0146] The attacking aircraft is also provided with an image acquisition device, which is in communication connection with the electronic device. Exemplarily, the image acquisition device is a camera. The electronic device stores contrast images of aircrafts of various models. The model information of the target aircraft can be obtained by comparing the image information with the contrast images. The electronic device also stores a mapping relationship table of model information and the predicted value of the maneuverability. The predicted value k of the maneuverability can be obtained by querying the mapping relationship table according to the obtained model information. The model information of the target aircraft is analyzed based on big data, thereby improving the accuracy of the model information determination.

[0147] Based on the same technical concept, the application also provides a target tracking based aircraft closed-loop maneuvering device, as shown in the accompanying drawings, the target tracking based aircraft closed-loop maneuvering device 200 mainly comprises: Figure 6

[0148] A first acquisition module 201 is configured to acquire first flight state information of the attacking aircraft and second flight state information of the target aircraft in real time.

[0149] A first determination module 202 is configured to determine first reference data corresponding to a pure tracking strategy based on the first flight state information and the second flight state information. The pure tracking strategy is a strategy corresponding to a situation that a target tracking position of the attacking aircraft corresponds to a position of the target aircraft when the attacking aircraft tracks the target aircraft.

[0150] A second determination module 203 is configured to determine second reference data corresponding to each non-pure tracking strategy and a decision factor corresponding to each second reference data based on the first flight state information and the second flight state information. For each reference data in the first reference data and the second reference data, the reference data is data used to describe the position of the target aircraft, and the decision factor is a parameter used to represent an importance degree of the reference data relative to flight guidance point information. The flight guidance point information is a vector corresponding to the target tracking position to which the attacking aircraft flies.

[0151] A third determination module 204 is configured to determine flight guidance point information corresponding to the attacking aircraft according to the first reference data, the second reference data and the decision factors, so as to guide the attacking aircraft to fly according to the flight guidance point information.

[0152] Optionally, the first determination module 202 comprises: ​

[0153] The first obtaining sub-module is configured to obtain a target coordinate of the target aircraft based on a ground coordinate system, and take the target coordinate as first reference data, where the target coordinate is a coordinate of a current position of the target aircraft.

[0154] Optionally, the second determining module 203 comprises:

[0155] The first calculating sub-module is configured to calculate, for each non-pure pursuit strategy, a reference vector corresponding to the non-pure pursuit strategy based on a preset algorithm corresponding to the non-pure pursuit strategy, and take the reference vector as second reference data corresponding to the non-pure pursuit strategy, where each second reference data comprises a reference vector.

[0156] The second obtaining sub-module is configured to obtain, in real time, a decision factor corresponding to each reference vector based on a pre-trained artificial intelligence model.

[0157] Optionally, the third determining module 204 comprises:

[0158] The second calculating sub-module is configured to perform weighted calculation on each reference vector based on the decision factor to obtain a first calculation value.

[0159] The third calculating sub-module is configured to calculate a sum of the first calculation value and the target coordinate to obtain a second calculation value, and take the second calculation value as flight guidance point information.

[0160] The non-pure pursuit strategy comprises a pre-position pursuit strategy and a post-position pursuit strategy; and optionally, the first calculating sub-module comprises:

[0161] The third obtaining sub-module is configured to obtain a first preset algorithm corresponding to the pre-position pursuit strategy and a second preset algorithm corresponding to the post-position pursuit strategy.

[0162] The fourth obtaining sub-module is configured to obtain each first parameter value in the first preset algorithm and each second parameter value in the second preset algorithm based on the first flight state and the second flight state.

[0163] The fourth calculating sub-module is configured to obtain, based on each first parameter value, a reference vector corresponding to the pre-position pursuit strategy through the first preset algorithm obtain, based on each second parameter value, a reference vector corresponding to the post-position pursuit strategy through the second preset algorithm

[0164] The non-pure pursuit strategy comprises a climb maneuver strategy and a dive maneuver strategy; and optionally, the first calculating sub-module comprises:

[0165] The fifth obtaining sub-module is configured to obtain a third preset algorithm corresponding to the climb maneuver strategy and a fourth preset algorithm corresponding to the dive maneuver strategy.

[0166] The sixth obtaining sub-module is configured to obtain each third parameter value in the third preset algorithm and each fourth parameter value in the fourth preset algorithm based on the first flight state and the second flight state.

[0167] The fifth calculating sub-module is configured to obtain the reference vector corresponding to the climbing maneuvering strategy by the third preset algorithm based on each third parameter value. The sixth calculating sub-module is configured to obtain the reference vector corresponding to the diving maneuvering strategy by the fourth preset algorithm based on each fourth parameter value.

[0168] The non-pure pursuit strategy further includes an inner-loop circling strategy and an outer-loop circling strategy. Optionally, the first calculating sub-module includes:

[0169] The seventh obtaining sub-module is configured to obtain a fifth preset algorithm corresponding to the inner-loop circling strategy and a sixth preset algorithm corresponding to the outer-loop circling strategy.

[0170] The eighth obtaining sub-module is configured to obtain each fifth parameter value in the fifth preset algorithm and each sixth parameter value in the sixth preset algorithm based on the first flight state and the second flight state.

[0171] The sixth calculating sub-module is configured to obtain the reference vector corresponding to the inner-loop circling strategy by the fifth preset algorithm based on each fifth parameter value. The seventh calculating sub-module is configured to obtain the reference vector corresponding to the outer-loop circling strategy by the sixth preset algorithm based on each sixth parameter value.

[0172] Optionally, the predicted value k of the maneuvering capability of the target aircraft is obtained by the following manner:

[0173] The ninth obtaining sub-module is configured to obtain image information of the target aircraft.

[0174] The tenth obtaining sub-module is configured to obtain model information of the target aircraft based on the image information.

[0175] The eleventh obtaining sub-module is configured to obtain the predicted value of the maneuvering capability based on the model information.

[0176] In one example, the modules in any of the above apparatuses can be one or more integrated circuits configured to implement one or more of the above methods, such as one or more application specific integrated circuits (ASICs), or one or more digital signal processors (DSPs), or one or more field programmable gate arrays (FPGAs), or a combination of at least two of these integrated circuit forms.

[0177] For another example, when the modules in the apparatus can be implemented in the form of a processing element scheduler, the processing element can be a general-purpose processor, such as a central processing unit (CPU) or other processor that can invoke programs. For another example, the modules can be integrated together to be implemented in the form of a system-on-a-chip (SOC).

[0178] In the present application, various objects such as messages / information / equipment / network elements / systems / apparatuses / actions / operations / processes / concepts, etc. that can occur are named. It can be understood that these specific names do not constitute a limitation on the related objects, and the assigned names can be changed according to factors such as scenes, contexts, or usage habits. The technical meaning of the technical terms in the present application should be mainly determined according to the functions and technical effects embodied / implemented in the technical solutions.

[0179] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described system, apparatus, and module can refer to the corresponding processes in the foregoing method embodiments, which will not be described here.

[0180] Those of ordinary skill in the art can realize that the modules and algorithm steps of the examples described in combination with the embodiments disclosed herein can be implemented by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are performed in hardware or software depends on the specific application and design constraints of the technical solutions. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0181] Based on the same technical concept, the present application also provides an electronic device, such as Figure 7 As shown, the electronic device 300 includes a processor 301 and a memory 302, and can further include one or more of an information input / output I / O interface 303, a communication component 304, and a communication bus 305.

[0182] The processor 301 is configured to control overall operations of the electronic device 300 to complete all or part of the steps of the above-mentioned aircraft closed-loop maneuvering method based on tracking targets. The memory 302 is configured to store various types of data to support operations of the electronic device 300. The data can include, for example, instructions for any application or method operating on the electronic device 300, and application-related data. The memory 302 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as one or more of a static random access memory (SRAM), an electrically erasable programmable read-only memory (EEPROM), an erasable programmable read-only memory (EPROM), a programmable read-only memory (PROM), a read-only memory (ROM), a magnetic memory, a flash memory, a magnetic disk, or an optical disk.

[0183] The I / O interface 303 provides an interface between the processor 301 and other interface modules, which can be a keyboard, a mouse, a button, and the like. The buttons can be virtual buttons or physical buttons. The communication component 304 is configured to test wired or wireless communication between the electronic device 300 and other devices. The wireless communication, such as Wi-Fi, Bluetooth, near field communication (NFC), 2G, 3G, or 4G, or a combination of one or more of them, so the corresponding communication component 304 can include a Wi-Fi component, a Bluetooth component, and an NFC component.

[0184] The communication bus 305 can include a path for transmitting information between the above-mentioned components. The communication bus 305 can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The communication bus 305 can be divided into an address bus, a data bus, a control bus, etc.

[0185] The electronic device 300 can be implemented with one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), controllers, micro-controllers, microprocessors, or other electronic elements for performing the tracking target-based aircraft closed-loop maneuvering method according to the above-described embodiments.

[0186] The electronic device 300 can include, but is not limited to, a mobile terminal such as a digital broadcasting receiver, a PDA (Personal Digital Assistant), a PMP (Portable Multimedia Player), and the like, and a fixed terminal such as a digital TV, a desktop computer, and the like, and can also be a server or the like.

[0187] The present application also provides a computer-readable storage medium having a computer program stored thereon, the computer program being executed by a processor to implement the steps of the tracking target-based aircraft closed-loop maneuvering method described above.

[0188] The computer-readable storage medium can include a U disk, a mobile hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and the like, which are various media capable of storing program codes.

[0189] The term "include" or "comprise" or any other variant thereof is intended to cover a non-exclusive inclusion, so that a process, method, article, or apparatus that includes a list of elements not only includes those elements, but also includes other elements not expressly listed or inherent to such a process, method, article, or apparatus.

[0190] The above description is merely the preferred embodiments of the present application and a description of the principles of the applied technology. It should be understood by those skilled in the art that the scope of the application involved in the present application is not limited to the technical solutions formed by the specific combinations of the above technical features, and should also cover other technical solutions formed by any combinations of the above technical features or equivalent features without departing from the above application concept. For example, the above features can be replaced with technical features having similar functions according to the application (but not limited to) to form technical solutions.

Claims

1. A closed-loop maneuvering method for aircraft based on target tracking, characterized in that, include: Real-time acquisition of the first flight status information of the attacking aircraft and the second flight status information of the target aircraft; Based on the first flight status information and the second flight status information, the first reference data corresponding to the pure tracking strategy is determined. The pure tracking strategy is the strategy corresponding to the target tracking position of the attacking aircraft being the same as the position of the target aircraft when the attacking aircraft tracks the target aircraft. Based on the first flight status information and the second flight status information, second reference data corresponding to each non-pure tracking strategy and decision factors corresponding to each second reference data are determined. For each reference data in the first reference data and each second reference data, the reference data is data used to describe the position of the target aircraft, and the decision factor is a parameter characterizing the importance of the reference data relative to the flight guidance point information. The flight guidance point information is a vector corresponding to the target tracking position to which the attack aircraft has flown. Based on the first reference data, each of the second reference data, and each of the decision factors, the flight guidance point information corresponding to the attack aircraft is determined, so as to guide the flight of the attack aircraft according to the flight guidance point information; The step of determining the first baseline data corresponding to the pure tracking strategy based on the first flight state information and the second flight state information includes: Based on the ground coordinate system, the target coordinates of the target aircraft are obtained, and the target coordinates are used as the first reference data, wherein the target coordinates are the coordinates of the current position of the target aircraft; The step of determining the second baseline data corresponding to each non-pure tracking strategy and the decision factor corresponding to each second baseline data based on the first flight state information and the second flight state information includes: For each of the non-pure tracking strategies, a reference vector corresponding to the non-pure tracking strategy is calculated based on a preset algorithm corresponding to each non-pure tracking strategy. Each second reference data includes a reference vector, and the reference vector is used as the second reference data corresponding to the non-pure tracking strategy. Based on a pre-trained artificial intelligence model, the decision factors corresponding to each benchmark vector are obtained in real time. The step of determining the flight guidance point information corresponding to the attack aircraft based on the first reference data, each of the second reference data, and each of the decision factors includes: Based on the decision factors, a weighted calculation is performed on each of the benchmark vectors to obtain a first calculated value; The sum of the first calculated value and the target coordinates is calculated to obtain the second calculated value, which is then used as the flight guidance point information.

2. The closed-loop maneuvering method for aircraft based on target tracking according to claim 1, characterized in that, The non-pure tracking strategy includes a pre-tracking strategy and a post-tracking strategy; The calculation of the corresponding reference vector based on the preset algorithm corresponding to each of the non-pure tracking strategies includes: Obtain the first preset algorithm corresponding to the preceding tracking strategy and the second preset algorithm corresponding to the following tracking strategy; Based on the first flight state and the second flight state, obtain each first parameter value in the first preset algorithm and each second parameter value in the second preset algorithm; Based on each of the first parameter values, the reference vector corresponding to the preceding tracking strategy is obtained through the first preset algorithm. Based on each of the second parameter values, the reference vector corresponding to the post-tracking strategy is obtained through the second preset algorithm. ;in, The first preset algorithm is: The second preset algorithm is: In the first preset algorithm and the second preset algorithm, k is the predicted value of the maneuverability of the target aircraft. The current speed of the target aircraft. The time required for each decision In the trajectory coordinate system of the target aircraft The unit vector of the axis.

3. The closed-loop maneuvering method for an aircraft based on target tracking according to claim 1 or 2, characterized in that, The non-pure tracking strategy includes a climb maneuver strategy and a dive maneuver strategy; the step of calculating the corresponding reference vector based on the preset algorithm corresponding to each of the non-pure tracking strategies further includes: Obtain the third preset algorithm corresponding to the climb maneuver strategy and the fourth preset algorithm corresponding to the dive maneuver strategy; Based on the first flight state and the second flight state, obtain the values ​​of each third parameter in the third preset algorithm and the values ​​of each fourth parameter in the fourth preset algorithm; Based on each of the aforementioned third parameter values, the reference vector corresponding to the climb maneuver strategy is obtained through the third preset algorithm. Based on each of the fourth parameter values, the reference vector corresponding to the dive maneuver strategy is obtained through the fourth preset algorithm. ;in, The third preset algorithm is: The fourth preset algorithm is: In the third and fourth preset algorithms, k is the predicted value of the target aircraft's maneuverability. Let g be the current velocity of the attacking aircraft, and g be the acceleration due to gravity. In the reference coordinate system of the target aircraft The unit vector of the axis.

4. The closed-loop maneuvering method for aircraft based on target tracking according to claim 3, characterized in that, The non-pure tracking strategy further includes an inner loop circling strategy and an outer loop circling strategy; the step of calculating the corresponding reference vector based on the preset algorithm corresponding to each of the non-pure tracking strategies further includes: Obtain the fifth preset algorithm corresponding to the inner loop spiraling strategy and the sixth preset algorithm corresponding to the outer loop spiraling strategy; Based on the first flight state and the second flight state, obtain the values ​​of each fifth parameter in the fifth preset algorithm and the values ​​of each sixth parameter in the sixth preset algorithm; Based on each of the fifth parameter values, the reference vector corresponding to the inner looping strategy is obtained through the fifth preset algorithm. Based on each of the sixth parameter values, the reference vector corresponding to the outer loop hovering strategy is obtained through the sixth preset algorithm. ;in, The fifth preset algorithm is: The sixth preset algorithm is: In the fifth and sixth preset algorithms, k is the predicted value of the target aircraft's maneuverability. Let be the distance vector between the centers of the turning circles of the attacking aircraft and the target aircraft in the horizontal plane based on the ground coordinate system. In the trajectory coordinate system of the target aircraft The unit vector of the axis.

5. The closed-loop maneuvering method for aircraft based on target tracking according to claim 4, characterized in that, The predicted value k of the target aircraft's maneuverability is obtained in the following way: Acquire image information of the target aircraft; Based on the image information, obtain the aircraft type information of the target aircraft; The predicted value k of maneuverability is obtained based on the aircraft type information.

6. A closed-loop maneuvering device for aircraft based on target tracking, characterized in that, include: The first acquisition module is used to acquire the first flight status information of the attacking aircraft and the second flight status information of the target aircraft in real time. The first determining module is used to determine the first reference data corresponding to the pure tracking strategy based on the first flight state information and the second flight state information. The pure tracking strategy is the strategy corresponding to the target tracking position of the attacking aircraft being the same as the position of the target aircraft when the attacking aircraft tracks the target aircraft. The second determining module is used to determine, based on the first flight state information and the second flight state information, the second reference data corresponding to each non-pure tracking strategy, and the decision factor corresponding to each second reference data. For each reference data in the first reference data and each second reference data, the reference data is data used to describe the position of the target aircraft, and the decision factor is a parameter characterizing the importance of the reference data relative to the flight guidance point information. The flight guidance point information is a vector corresponding to the target tracking position to which the attack aircraft has flown. The third determining module is used to determine the flight guidance point information corresponding to the attack aircraft based on the first reference data, each of the second reference data and each of the decision factors, so as to guide the attack aircraft to fly according to the flight guidance point information; The first determining module, when based on the first flight status information and the second flight status information, is specifically used for: Based on the ground coordinate system, the target coordinates of the target aircraft are obtained, and the target coordinates are used as the first reference data, wherein the target coordinates are the coordinates of the current position of the target aircraft; The second determining module, when determining the second baseline data corresponding to each non-pure tracking strategy and the decision factor corresponding to each of the second baseline data based on the first flight state information and the second flight state information, specifically uses the following: For each of the non-pure tracking strategies, a reference vector corresponding to the non-pure tracking strategy is calculated based on a preset algorithm corresponding to each non-pure tracking strategy. Each second reference data includes a reference vector, and the reference vector is used as the second reference data corresponding to the non-pure tracking strategy. Based on a pre-trained artificial intelligence model, the decision factors corresponding to each benchmark vector are obtained in real time. The third determining module, when determining the flight guidance point information corresponding to the attack aircraft based on the first reference data, each of the second reference data, and each of the decision factors, specifically performs the following: Based on the decision factors, a weighted calculation is performed on each of the benchmark vectors to obtain a first calculated value; The sum of the first calculated value and the target coordinates is calculated to obtain the second calculated value, which is then used as the flight guidance point information.

7. An electronic device, characterized in that, Includes a processor, which is coupled to a memory; The processor is configured to execute a computer program stored in the memory, causing the electronic device to perform the method as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, It includes a computer program or instructions that, when run on a computer, cause the computer to perform the method as described in any one of claims 1 to 5.

Images