Combined training target

Abstract

The application discloses a combined training target, which comprises a main target body, a cover target body, a collection module, an identification module, a control module, a maneuvering module, a striking module and a communication module; the collection module is used for collecting image information; the identification module is used for target identification on the image information to obtain identification information; the control module is used for determining a maneuvering strategy and a striking strategy according to the identification information; the maneuvering module is used for executing a maneuvering action according to the maneuvering strategy; the striking module is used for executing a striking action according to the striking strategy; the communication module is used for sending the identification information to other targets and receiving identification information of other targets; and the control module is further used for adjusting the maneuvering strategy and the striking strategy according to the identification information and the identification information of other targets. The combined training target improves the realistic degree of training.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of military training simulation, in particular to a combined training target. BACKGROUND

[0002] Traditional training targets are generally fixed in position or move along a track, with poor flexibility. Moreover, traditional targets can only be hit by the attacking side and cannot be hit or counterattacked, making it difficult to simulate a real combat scene.

[0003] In the existing training target technology, the patent with the publication number CN115615242A "Intelligent individual target for battlefield exercise" proposes an intelligent individual target that can independently move and detect in the exercise area, and identify and attack enemy targets, realizing the tactical behavior of real enemy personnel and improving the real experience of exercise participants.

[0004] In real combat, enemy personnel usually protect themselves with shelters and can communicate with each other to share combat information, so it is necessary to simulate shelter protection, inter-personnel communication, and combat information sharing. However, the existing technology lacks simulation of the above combat behaviors, and the training realism is low. SUMMARY

[0005] The present application provides a combined training target to solve the problem of lack of reliable simulation of shelter protection, inter-personnel communication, and combat information sharing in the prior art, and low training realism.

[0006] In one aspect, the present application provides a combined training target, comprising: a main target body, a shelter target body, a collection module, an identification module, a control module, a mobile module, a strike module, and a communication module.

[0007] The collection module is configured to collect image information.

[0008] The identification module is configured to perform target identification on the image information to obtain identification information.

[0009] The control module is configured to determine a mobile strategy and a strike strategy based on the identification information.

[0010] The mobile module is configured to perform a mobile action according to the mobile strategy.

[0011] The strike module is configured to perform a strike action according to the strike strategy.

[0012] The communication module is configured to send the identification information to other targets and receive identification information from other targets.

[0013] The control module is further configured to adjust the maneuvering strategy and the attack strategy according to the identification information and identification information of the other targets.

[0014] In a possible implementation, the shield target body is a mobile shield target body moving with the main target body, a hostage target body or a fixed shield target body fixed on the ground.

[0015] In a possible implementation, the collection module comprises a visible light image collection unit and an infrared image collection unit.

[0016] In a possible implementation, the identification module adopts a YOLOV5 network to perform target identification on the image information.

[0017] In a possible implementation, the control module adopts a BP neural network to determine the maneuvering strategy.

[0018] The maneuvering strategy comprises a maneuvering position strategy, a maneuvering speed strategy and a maneuvering trajectory strategy.

[0019] In a possible implementation, the attack strategy comprises an attack priority strategy, an attack feature strategy and an attack firepower strategy.

[0020] In a possible implementation, the control module is further configured to adjust relative positions of the main target body and the shield target body according to the identification information and identification information of the other targets.

[0021] In a possible implementation, the control module is further configured to correct the maneuvering strategy and the attack strategy according to state information of the main target body and the shield target body.

[0022] The state information comprises position information, simulated physical strength information and simulated injury information.

[0023] In a possible implementation, the communication module is further configured to send the state information to other targets and receive state information of other targets.

[0024] The control module is further configured to correct the maneuvering strategy according to the state information and state information of the other targets.

[0025] A combined training target in the application has the following advantages:

[0026] The proposed main target body, cover target body, collection module, identification module, control module, maneuvering module, striking module and communication module add simulation of cover protection, inter-personnel communication and battle information sharing, thereby improving the realistic degree of training; the proposed identification module uses a YOLOV5 network to perform target identification on the image information, thereby improving the realistic degree of target identification; and the proposed control module uses a BP neural network to determine the maneuvering strategy, thereby improving the realistic degree of maneuvering simulation. BRIEF DESCRIPTION OF DRAWINGS

[0027] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description only constitute some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor on the basis of these drawings.

[0028] Figure 1 A composition schematic diagram of the combined training target provided by the embodiments of the present application. DETAILED DESCRIPTION

[0029] The technical solutions in the embodiments of the present application will be described clearly and completely in the following with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments only constitute some embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the protection scope of the present application.

[0030] Figure 1 A composition schematic diagram of the combined training target provided by the embodiments of the present application. The embodiments of the present application provide a combined training target, which comprises a main target body, a cover target body, a collection module, an identification module, a control module, a maneuvering module, a striking module and a communication module.

[0031] The collection module is used to collect image information.

[0032] The identification module is used to perform target identification on the image information to obtain identification information.

[0033] The control module is used to determine a maneuvering strategy and a striking strategy according to the identification information.

[0034] The maneuvering module is used to perform a maneuvering action according to the maneuvering strategy.

[0035] The striking module is used to perform a striking action according to the striking strategy.

[0036] The communication module is configured to send the identification information to other targets and receive identification information of other targets.

[0037] The control module is further configured to adjust the maneuvering strategy and the attack strategy according to the identification information and the identification information of other targets.

[0038] Specifically, the identification information includes target category information, target position information, target injury information, target importance information and target feature information.

[0039] Illustratively, the cover target body is a mobile cover body moving with the main target body, a hostage target body or a fixed cover body fixed on the ground.

[0040] Illustratively, the acquisition module includes a visible light image acquisition unit and an infrared image acquisition unit.

[0041] Illustratively, the identification module uses a YOLOV5 network to perform target identification on the image information.

[0042] Specifically, the embodiment pre-establishes a dataset of visible light images and corresponding infrared images, and uses a TIF fusion algorithm to fuse each set of visible light images and corresponding infrared images in the dataset, and then transmits the fused images into a YOLOV5 network for training. Finally, the trained YOLOV5 network is used to identify the target in the image information, and the TIF fusion algorithm is also used to fuse the image information before target identification.

[0043] Illustratively, the control module uses a BP neural network to determine the maneuvering strategy.

[0044] The maneuvering strategy includes a maneuvering position strategy, a maneuvering speed strategy and a maneuvering trajectory strategy.

[0045] Specifically, the embodiment pre-establishes a dataset of target category information, target position information, target injury information, target importance information and target feature information, and uses the dataset to train the BP neural network. During the training process, a genetic algorithm is used to optimize the BP neural network to obtain optimal parameter weights and parameter thresholds. Finally, the identification information is used as the input feature of the trained BP neural network, and the maneuvering strategy is output, wherein the maneuvering position strategy is the optimal maneuvering position, the maneuvering speed strategy is the optimal speed to reach the optimal maneuvering position, and the maneuvering trajectory strategy is the optimal trajectory to reach the optimal maneuvering position.

[0046] When receiving the identification information of other targets, the identification information and the identification information of other targets are both used as input features of the trained BP neural network, and the output of the BP neural network is the adjusted maneuvering strategy.

[0047] Exemplarily, the attack strategy comprises an attack priority strategy, an attack feature strategy and an attack firepower strategy.

[0048] Specifically, when it is identified that the target category is the attackable category, firstly, all the attackable category targets identified are prioritized, and the priority calculation weight parameters comprise target position information, target injury information, target importance information and target feature information. The closer the target position, the more serious the target injury, the higher the target importance, and the more attackable features of the target, the higher the priority of the target.

[0049] When the identification information of other targets is received, all the attackable category targets in the identification information and the identification information of the other targets are prioritized, and then the attack priority strategy, the attack feature strategy and the attack firepower strategy are determined, that is, the adjusted attack strategy.

[0050] In this embodiment, the attack priority strategy is to attack the target with the highest priority, the attack feature strategy is to attack the most deadly feature in the attackable features of the target, and the attack firepower strategy is to use the firepower predicted to kill the target.

[0051] In other possible embodiments, the attack feature strategy can also be to attack the feature with the largest range in the attackable features of the target, or other features; and the attack firepower strategy can also be to use the firepower predicted to make the target lose the ability to act.

[0052] Exemplarily, the control module is further configured to adjust the relative positions of the main target body and the cover target body according to the identification information and the identification information of the other targets.

[0053] Specifically, the control module obtains threat degree information of the targets according to the identification information and the identification information of the other targets, and adjusts the relative positions of the main target body and the cover target body according to the threat degree information of the targets.

[0054] In this embodiment, adjusting the relative positions of the main target body and the cover target body comprises that the main target body faces the target with the highest threat degree, and the cover target body is located in front of the main target body. When the cover target body is a mobile cover, the flexibility of adjusting the relative positions is higher but the simulation life of the cover target body is lower; when the cover target body is a hostage target, the probability of the main target body being attacked is lower; and when the cover target body is a fixed cover, the flexibility of adjusting the relative positions is lower but the simulation life of the cover target body is higher.

[0055] Exemplarily, the control module is further configured to correct the maneuvering strategy and the attack strategy according to the state information of the main target body and the cover target body.

[0056] The state information includes position information, simulated physical strength information, and simulated injury information.

[0057] Specifically, the lower the simulated physical strength of the main target body and the more serious the simulated injury, the slower the speed of executing the maneuvering strategy and the attack strategy. When the shield target body is a hostage target body, the lower the simulated physical strength of the shield target body and the more serious the simulated injury, the slower the speed of executing the maneuvering strategy and the attack strategy.

[0058] Illustratively, the communication module is further configured to send the state information to other targets and receive state information of other targets.

[0059] The control module is further configured to correct the maneuvering strategy according to the state information and the state information of other targets.

[0060] Specifically, when the simulated injury of the main target body of other targets is higher than the simulated injury of the main target body of the target and higher than a preset simulated injury threshold (the simulated injury threshold is set to 30% of the simulated life in the embodiment), or the simulated physical strength of the main target body of other targets is lower than the simulated physical strength of the main target body of the target and lower than a preset simulated physical strength threshold (the simulated physical strength threshold is set to 30% of the simulated physical strength in the embodiment), the target satisfies the above condition, and the position information of other targets closest to the target is used as a corrected maneuvering position strategy, and a corrected maneuvering speed strategy and a corrected maneuvering trajectory strategy are determined according to the corrected maneuvering position strategy.

[0061] The main target body, the shield target body, the collection module, the identification module, the control module, the maneuvering module, the attack module, and the communication module proposed in the embodiment add simulation of shelter protection and inter-person communication and battle information sharing, and improve the realistic degree of training. The identification module proposed in the embodiment uses a YOLOV5 network to perform target identification on the image information, and improves the realistic degree of target identification. The control module proposed in the embodiment uses a BP neural network to determine the maneuvering strategy, and improves the realistic degree of maneuvering simulation.

[0062] Although the preferred embodiments of the present application have been described, those skilled in the art who understand the basic inventive concept can make additional changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0063] Obviously, those skilled in the art can make various modifications and variations to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A combined training target, characterized in that, include: Main target, cover target, data acquisition module, identification module, control module, maneuver module, strike module, and communication module; The acquisition module is used to acquire image information; The recognition module is used to perform target recognition on the image information to obtain recognition information; The control module is used to determine the maneuver strategy and the attack strategy based on the identification information; The maneuver module is used to perform maneuver actions according to the maneuver strategy; The strike module is used to execute strike actions according to the strike strategy; The communication module is used to send the identification information to other targets and receive the identification information of other targets; The control module is also used to adjust the maneuver strategy and the strike strategy based on the identification information and the identification information of the other targets; The identification information includes: target category information, target location information, target injury information, target importance information, and target feature information; The control module uses a BP neural network to determine the maneuver strategy; the maneuver strategy includes: maneuver position strategy, maneuver speed strategy, and maneuver trajectory strategy. A dataset containing target category information, target location information, target injury information, target importance information, and target feature information is pre-established. The BP neural network is trained using this dataset. During training, a genetic algorithm is used to optimize the BP neural network to obtain the optimal parameter weights and parameter thresholds. Finally, the recognition information is used as the input features of the trained BP neural network to output the maneuvering strategy, where the maneuvering position strategy is the optimal maneuvering position, the maneuvering speed strategy is the optimal speed to reach the optimal maneuvering position, and the maneuvering trajectory strategy is the optimal trajectory to reach the optimal maneuvering position. The control module is also used to modify the maneuver strategy and the attack strategy based on the status information of the main target and the cover target; the status information includes: position information, simulated physical strength information and simulated injury information; The lower the simulated physical strength and the more severe the simulated injury of the main target, the slower the speed at which maneuvering and attack strategies are executed; when the cover target is a hostage target, the lower the simulated physical strength and the more severe the simulated injury of the cover target, the slower the speed at which maneuvering and attack strategies are executed.

2. The combined training target according to claim 1, characterized in that, The cover target is: a mobile cover that moves with the main target, a hostage target, or a fixed cover fixed on the ground.

3. The combined training target according to claim 1, characterized in that, The acquisition module includes a visible light image acquisition unit and an infrared image acquisition unit.

4. The combined training target according to claim 3, characterized in that, The recognition module uses the YOLOv5 network to perform target recognition on the image information.

5. A combined training target according to claim 1, characterized in that, The strike strategy includes: strike priority strategy, strike characteristic strategy, and strike firepower strategy.

6. A combined training target according to claim 1, characterized in that, The control module is also used to adjust the relative positions of the main target and the cover target based on the identification information and the identification information of the other targets.

7. A combined training target according to claim 1, characterized in that, The communication module is also used to send the status information to other targets and receive the status information of other targets; The control module is also used to modify the maneuver strategy based on the status information and the status information of the other targets.

Images