Guidance control method, device and electronic equipment for folding drone

Abstract

A guidance and control method, device, and electronic device for a foldable drone relate to the field of drones. In this method, a first image of a target object is captured at a first position; a second image of the target object is acquired, the second image and the first image being taken at the same time; first position data of the target object is calculated based on the first and second images; a determination is made as to whether the first drone is in an uncontrolled state; if the first drone is determined to be in an uncontrolled state, the first position data and an attack instruction are sent to a second drone, causing the second drone to attack the target object; after the second drone attacks the target object, if the target object is determined to be in a moving state, a flight path for attacking the target object is calculated; and a secondary attack on the target object is completed based on the flight path. Implementing the technical solution provided in this application enables precise strikes and secondary strikes on target objects even when the drone is out of control.

Description

Technical Field

[0001] The present application relates to the field of data processing, and specifically to a guidance and control method, device, and electronic equipment for a folding drone. Background Art

[0002] With the rapid development of science and technology, especially breakthroughs in microelectronics, mechanical engineering, and wireless communications, foldable drones, as an emerging drone form factor, have demonstrated their unique advantages in multiple fields. Their design allows for wings and other parts to be folded up when not in use, greatly facilitating transportation and storage, and enabling rapid deployment.

[0003] Folding drones have seen rapid development and adoption due to their portability and flexibility. However, due to their limited size and payload capacity, folding drones often struggle to operate in complex or changing environments when operated alone. Furthermore, single drones often lack effective self-rescue mechanisms in the event of loss of control or malfunction, which is particularly problematic during critical missions.

[0004] Therefore, there is an urgent need for a guidance and control method, device, and electronic equipment for a foldable drone. Summary of the Invention

[0005] The present application provides a guidance and control method, device, and electronic equipment for a foldable drone, which can still achieve precise strikes and secondary strikes on target objects when the drone loses control.

[0006] In a first aspect of the present application, a guidance and control method for a folding drone is provided, which is applied to a first drone, and the first drone is communicatively connected to a second drone. The method includes: collecting a first image of a target object at a first position, where the first position is the current position of the first drone, and the first image is taken by a first camera of the first drone; obtaining a second image of the target object, where the second image is taken by a second camera of the second drone, and the second image is taken at the same time as the first image; calculating first position data of the target object based on the first image and the second image; judging whether the first drone is in an uncontrolled state; if it is determined that the first drone is in an uncontrolled state, sending the first position data and an attack instruction to the second drone, so that the second drone attacks the target object; after the second drone attacks the target object, if it is determined that the target object is in a moving state, calculating a flight route for attacking the target object; and completing a secondary attack on the target object according to the flight route.

[0007] By adopting the above technical solution, by capturing a first image of the target object at a first position and obtaining a second image taken by a second drone at the same time, the first image and the second image can be combined in the calculation process to achieve the precise location of the target object (first position data). By determining whether the first drone is in an uncontrolled state, the state of the first drone can be monitored in real time, and corresponding measures can be taken when the first drone loses control, and an attack instruction can be sent to the second drone. If the target object is still in a moving state after the second drone attacks, the flight path of the target object is calculated in real time, and a secondary attack is carried out based on the calculation results to enhance the effectiveness of the attack. Even when the first drone loses control, it is still possible to achieve accurate strikes on the target object and a secondary attack.

[0008] Optionally, before capturing the first image of the target object at the first position, the method further includes: capturing a third image of the target object at the second position, the third image being captured by the first drone at the second position; determining the similarity between the third image and the second image; if the similarity is greater than a preset similarity threshold, moving to the first position, and capturing the first image using the first camera at the first position, wherein the similarity between the first image and the second image is less than or equal to a preset similarity threshold, and the distance between the second position and the first position is less than a preset distance threshold.

[0009] By adopting the above technical solution, before the first drone captures the first image of the target object, the shooting position of the first drone is optimized by comparing the image similarity with the second drone, so as to improve the subsequent positioning effect of the target object.

[0010] Optionally, based on the first image and the second image, the first position data of the target object is calculated, specifically including: obtaining first orientation data of the first drone and second orientation data of the second drone, the orientation data including yaw angle, pitch angle and roll angle; capturing a first feature point in the first image and a second feature point in the second image; calculating a first line of sight vector from the first drone to the first feature point according to the first orientation data, and calculating a second line of sight vector from the second drone to the second feature point according to the second orientation data; and calculating the first position data of the target object using a triangulation positioning algorithm based on the first line of sight vector and the second line of sight vector.

[0011] By adopting the above technical solution, by obtaining the first orientation data of the first drone and the second orientation data of the second drone and capturing the feature points in the first image and the second image, the first position data of the target object can be calculated based on the triangulation positioning algorithm, thereby achieving high-precision positioning of the target object, so that the first drone can accurately track and attack the target object.

[0012] Optionally, determining whether the first drone is in an uncontrolled state specifically includes: sending a heartbeat signal to the controller at intervals of a preset time period; if no response signal from the controller is received within the preset time period, determining that the first drone is in an uncontrolled state.

[0013] By adopting the above technical solution, the first drone's status can be monitored in real time by regularly sending heartbeat signals to the controller. This real-time monitoring helps promptly detect whether the first drone has lost connection with the controller. If the server does not receive a response signal from the controller within a preset time period, the first drone can quickly self-detect that it is out of control. This rapid response capability helps to take necessary measures in a timely manner.

[0014] Optionally, determining that the target object is in a moving state specifically includes: continuously shooting multiple target images of the target object; judging the target similarity between a first target image and a second target image, wherein the first target image is any target image among the multiple target images, and the second target image is any target image among the multiple target images except the first target image; if the target similarity is less than or equal to a preset target similarity threshold, determining that the target object is in a moving state.

[0015] By employing this technical solution, the server can accurately determine whether a target object is in motion by continuously capturing multiple images and comparing their similarity. This method effectively distinguishes between stationary and moving states, providing accurate data support for subsequent decision-making. Once the server determines that a target object is in motion, it can quickly take appropriate action.

[0016] Optionally, calculating the flight route for attacking the target object specifically includes: obtaining the real-time position and moving speed of the target object; predicting the target position of the target object based on the real-time position and moving speed; and using a path planning algorithm to calculate the flight route to the predicted target position.

[0017] By adopting the above technical solution, the real-time position and movement speed of the target object are obtained, and the target object's trajectory is tracked in real time. This allows the drone to always stay within the attack range of the target object and adjust its flight path in a timely manner.

[0018] Optionally, a secondary attack on the target object is completed based on the flight route, specifically including: calculating the real-time distance between the target object and the target object in real time; judging whether the real-time distance is less than or equal to a preset distance threshold, and if the real-time distance is less than or equal to the preset distance threshold, executing the secondary attack.

[0019] By employing the above technical solution, the first drone can precisely approach the target object by flying according to a pre-calculated flight path. This helps ensure the accuracy of the attack timing, allowing the attack to more accurately hit the target object. The drone determines the distance based on a preset position threshold and executes the attack once the distance falls below the preset position threshold. This method improves the efficiency of the attack, allowing the attack to be carried out at the most appropriate time and reducing errors and waste.

[0020] In a second aspect of the present application, a guidance and control device for a foldable drone is provided. The device includes: an acquisition module and a processing module, wherein: the acquisition module is used to capture a first image of a target object at a first position, where the first position is the current position of the first drone, and the first image is captured by a first camera of the first drone; the acquisition module is also used to capture a second image of the target object, where the second image is captured by a second camera of the second drone, and the second image and the first image are captured at the same time; the processing module is used to calculate first position data of the target object based on the first image and the second image; the processing module is also used to determine whether the first drone is in an uncontrolled state; the processing module is also used to, if it is determined that the first drone is in an uncontrolled state, send the first position data and an attack instruction to the second drone, so that the second drone attacks the target object; the processing module is also used to, after the second drone attacks the target object, if it is determined that the target object is in a moving state, calculate a flight path for attacking the target object; and the processing module is also used to complete a secondary attack on the target object based on the flight path.

[0021] In the third aspect of the present application, an electronic device is provided, including a processor, a memory, a user interface and a network interface, the memory is used to store instructions, the user interface and the network interface are both used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device performs any of the methods described above.

[0022] In a fourth aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores instructions. When the instructions are executed, any one of the methods described above is executed.

[0023] In summary, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0024] 1. By capturing a first image of the target object at a first location and obtaining a second image captured by a second drone at the same time, the first and second images can be combined during the calculation process to accurately determine the target object's location. By determining whether the first drone is in an uncontrolled state, the first drone's status can be monitored in real time. If the first drone loses control, appropriate measures can be taken, such as sending an attack command to the second drone. If the target object is still moving after the second drone's attack, the target object's flight path is calculated in real time, and a second attack is carried out based on the calculated results, enhancing the effectiveness of the attack. This allows for precise strikes on the target object even when the first drone loses control.

[0025] 2. By obtaining the first orientation data of the first drone and the second orientation data of the second drone and capturing feature points in the first image and the second image, the first position data of the target object can be calculated based on the triangulation positioning algorithm, thereby achieving high-precision positioning of the target object, enabling the first drone to accurately track and attack the target object.

[0026] 3. By regularly sending heartbeat signals to the controller, the first drone's status can be monitored in real time. This real-time monitoring helps promptly detect if the first drone has lost connection to the controller. If the server does not receive a response signal from the controller within a preset period of time, the first drone can quickly self-diagnose that it is out of control. This rapid response capability helps to take necessary measures in a timely manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 This is a flow chart of a guidance and control method for a folding drone disclosed in an embodiment of the present application;

[0028] Figure 2 This is a module schematic diagram of a guidance and control device for a foldable drone disclosed in an embodiment of the present application;

[0029] Figure 3 This is a structural diagram of an electronic device disclosed in an embodiment of the present application.

[0030] Description of the accompanying drawings: 201, acquisition module; 202, processing module; 300, electronic device; 301, processor; 302, communication bus; 303, user interface; 304, network interface; 305, memory. DETAILED DESCRIPTION

[0031] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments.

[0032] In the description of the embodiments of this application, words such as "for example" or "for instance" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as "for example" or "for instance" in the embodiments of this application should not be construed as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "for example" or "for instance" is intended to present the relevant concepts in a concrete manner.

[0033] In the description of the embodiments of the present application, the term "multiple" means two or more. For example, multiple systems refer to two or more systems, and multiple screen terminals refer to two or more screen terminals. In addition, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized.

[0034] With the rapid development and widespread application of drone technology, UAVs have become an indispensable force on the modern battlefield. With their small size, low cost, and high concealment, UAVs are playing an increasingly important role in reconnaissance, surveillance, and strike missions. Micro-UAVs, in particular, are becoming the "star" equipment of future battlefields due to their enhanced maneuverability and penetration capabilities.

[0035] Although micro-UAV platform technology is relatively mature, significant challenges remain in autonomous control and coordinated operations in complex environments. Traditional UAV guidance and control methods rely primarily on remote control from ground stations, making them incapable of adapting to the dynamic battlefield environment. Furthermore, the communication link between the UAV and the ground station is susceptible to enemy interference and blocking. If communication is disrupted, the UAV will become "out of control" and unable to complete its mission.

[0036] In related technologies, single drones operating complex tasks (such as large-scale surveillance and locating moving targets) are often constrained by a single viewpoint and limited sensor data, potentially preventing them from completing the task efficiently and accurately. This technical solution leverages the collaborative work of a first and second drone to capture images of the target object from two different viewpoints. Triangulation algorithms are then used to precisely calculate the target's position, significantly improving the accuracy and reliability of task execution.

[0037] In conventional drone operations, if a drone loses control or malfunctions, manual intervention is usually required. This can lead to mission failure in urgent situations or when a quick human response is impossible. However, in this technical solution, if the first drone determines it is out of control, it automatically transmits mission data and attack instructions to the second drone to continue the mission. Simultaneously, the first drone activates an emergency mechanism, launching a secondary attack after the second drone completes its attack, thus ensuring mission continuity and stability.

[0038] This application provides a guidance and control method for a folding drone, referring to Figure 1 , Figure 1 This is a flow chart of a guidance and control method for a folding drone provided in an embodiment of the present application. The method is applied to a server and includes steps S101 to S107, which are as follows:

[0039] Step S101: capturing a first image of a target object at a first position, where the first position is the current position of a first drone, and the first image is captured by a first camera of the first drone.

[0040] In step S101, while performing a mission, the first drone obtains its current position in real time using positioning equipment such as GPS and inertial navigation, recording it as a first position. When a target object needs to be identified and located, the drone, in accordance with mission instructions, uses its onboard first camera to image the target object, generating a first image. The first camera is a high-resolution visible light or infrared camera with functions such as zoom, focus, and exposure control.

[0041] For example, when the first drone is cruising at an altitude of 100 meters above an urban area and spots a suspicious vehicle traveling at high speed on the road, the first drone quickly activates its first camera, locks its field of view on the target vehicle, and tracks and records it for 10 seconds, obtaining a high-definition image of the target vehicle. This image is recorded as the first image, and the shooting time and current location of the drone are marked for subsequent processing.

[0042] Step S102: Acquire a second image of the target object. The second image is captured by a second camera of a second drone. The second image and the first image are captured at the same time.

[0043] In step S102, because a single-viewpoint target image cannot determine the specific location of the target object, it is necessary to image the target object from multiple angles. A first drone establishes a communication connection with a second drone via a data link, exchanging information such as their position and posture in real time and coordinating their respective tasks. The first drone serves as the master control drone, and the second drone serves as the slave control drone. When the first drone begins imaging the target object, it issues a synchronization command to the second drone. Upon receiving the command, the second drone immediately uses its second camera to capture the same target object. To ensure that the target images obtained by the two drones are taken at the same moment, their clocks must be strictly synchronized.

[0044] In one possible embodiment, before capturing a first image of the target object at the first position, the method further includes: capturing a third image of the target object at the second position, the third image being captured by the first drone at the second position; determining a similarity between the third image and the second image; if the similarity is greater than a preset similarity threshold, moving to the first position and capturing the first image using the first camera at the first position, wherein the similarity between the first image and the second image is less than or equal to the preset similarity threshold, and the distance between the second position and the first position is less than a preset distance threshold.

[0045] Specifically, before a first drone captures a first image of a target object at a first location, it performs a series of operations to optimize its own shooting position and enhance the collaborative shooting effect with the second drone. First, the first drone flies to an initial position (the second location) and uses its onboard camera (the first camera) to capture the target object, generating a third image. This step provides a reference for subsequent image similarity comparisons.

[0046] At the same time, the first drone immediately sends a synchronization command to the second drone via the data link, requesting it to capture the second image. After issuing the synchronization command, the first drone waits for the second drone to complete its capture task and receives the second image it transmits back. Simultaneously, the first drone determines the similarity between the third and second images. This similarity is determined using a feature point matching algorithm. The first drone first extracts significant feature points (such as SIFT, SURF, etc.) from the third and second images. It then uses feature descriptors to match them, calculating the number and distribution of matching feature point pairs. If the number of matching feature point pairs exceeds a preset number (such as 500), the similarity between the two images is considered greater than a preset threshold (such as 0.8). This indicates that the spatial positions of the two drones are too close and the imaging angles are not sufficiently different, making it difficult to obtain a high-quality stereo image. At this point, the first drone needs to move to the first position and adjust its posture and perspective. The selection of the first position requires comprehensive consideration of the following factors: the distance to the second position must be less than or equal to a preset distance threshold (such as 50 meters); the angle with the second position must be greater than or equal to a preset range (such as 30 degrees) to widen the parallax; the first drone can use its own inertial navigation and GPS positioning functions to plan the optimal movement path and control the aircraft to move smoothly to the first position.

[0047] Finally, the first drone uses the first camera again at the first position to capture the target object, obtaining a new third image. The similarity determination and position adjustment process repeats until the similarity between the two images falls below or equals the preset similarity threshold. This creates a dynamic stereo vision system with the second drone. By optimizing the distance and angle between the two viewpoints, high-quality, multi-view images of the target can be acquired.

[0048] Step S103: Calculating first position data of the target object based on the first image and the second image.

[0049] In step S103, first orientation data of the first UAV and second orientation data of the second UAV are obtained; a first feature point in the first image and a second feature point in the second image are captured; a first sight line vector from the first UAV to the first feature point is calculated based on the first orientation data, and a second sight line vector from the second UAV to the second feature point is calculated based on the second orientation data; and a triangulation positioning algorithm is used to calculate first position data of the target object based on the first sight line vector and the second sight line vector.

[0050] Specifically, the first drone needs to obtain its own attitude data, namely, first orientation data. This first orientation data includes three Euler angles: yaw, pitch, and roll. The first drone obtains these angles using its onboard inertial measurement unit (IMU). Simultaneously, the first drone receives second orientation data from the second drone via a data link. This second orientation data also includes the second drone's yaw, pitch, and roll angles. The first drone performs feature extraction on the first image it acquires. It uses the SIFT algorithm (Scale-Invariant Feature Transform) to extract SIFT features from the first image, obtaining a set of image coordinates of feature points and corresponding feature descriptors, which are denoted as first feature points. Similarly, the second drone performs feature extraction on the second image and sends the results to the first drone. Based on the first orientation data and the first feature points, the first drone calculates a first gaze vector. The first gaze vector describes the spatial orientation of the first feature point in the camera coordinate system of the first camera, corresponding to the position of the first feature point in the image plane. The relationship between these two can be described using the pinhole imaging model: (u, v, 1) = K*(x, y, z, 1).

[0051] Among them, (u, v) is the image coordinate of the feature point, (x, y, z) is its spatial coordinate in the camera coordinate system of the first camera, and K is the intrinsic parameter matrix of the camera. The intrinsic parameter matrix contains the focal length and the coordinates of the principal point, which can be obtained by prior calibration. To convert the image coordinates of the first feature point to the camera coordinate system, it is necessary to consider the posture of the first drone. Assuming that the yaw angle of the first drone is yaw1, the pitch angle is pitch1, and the roll angle is roll1, the corresponding rotation matrix is: R1=R(roll1)*R(pitch1)*R(yaw1);

[0052] Where R1 represents the rotation matrix around a certain axis. Combining the rotation matrix with the pinhole imaging model, we can get: (x1, y1, z1, 1) = R1^(-1)*K^(-1)*(u1, v1, 1), (x1, y1, z1) is the coordinate of the first feature point in the camera coordinate system. Normalizing it, we get the first line of sight vector (dx1, dy1, dz1) = (x1, y1, z1) / (x1^2 + y1^2 + z1^2)

[0053] Similarly, the first drone calculates the second sight line vector (dx2, dy2, dz2) based on the second orientation data and the second feature point. Finally, the first drone calculates the first position data of the target object using the triangulation principle.

[0054] Assume the spatial coordinates of the first drone are (x1, y1, z1), the spatial coordinates of the second drone are (x2, y2, z2), and the spatial coordinates of the target object are (x, y, z), then we have the following equation:

[0055] (x,y,z)=(x1,y1,z1)+λ1*(dx1,dy1,dz1)

[0056] (x,y,z)=(x2,y2,z2)+λ2*(dx2,dy2,dz2)

[0057] Among them, λ1 and λ2 are two unknown quantities, representing the distances from the target object to the two drones respectively. Expanding and merging the two equations, we can get a system of four linear equations:

[0058] x1+λ1*dx1=x2+λ2*dx2

[0059] y1+λ1*dy1=y2+λ2*dy2

[0060] z1+λ1*dz1=z2+λ2*dz2

[0061] By solving the equation group, the values ​​of λ1 and λ2 can be obtained, and then the spatial coordinates (x, y, z) of the target object, that is, the first position data, can be calculated.

[0062] For example, assume the coordinates of the first and second drones in space are (100, 50, 200) and (120, 80, 180), respectively. A pair of matching SIFT feature points are extracted from the target images captured by the two drones, with image coordinates of (200, 150) and (250, 130), respectively. Through attitude calculation, the first drone's yaw angle is determined to be 10°, its pitch angle is 5°, and its roll angle is 2°; the second drone's yaw angle is 15°, its pitch angle is -3°, and its roll angle is 1°. Using camera intrinsic parameters and attitude data, the two gaze vectors are calculated to be (0.21, 0.53, 0.82) and (0.17, 0.62, 0.77), respectively. Solving the triangulation equations yields λ1=35.8 and λ2=28.4. Substituting these into the spatial coordinate calculation formula yields the target object's three-dimensional position of (108.6, 68.2, 191.3), representing the first position data.

[0063] Step S104: Determine whether the first UAV is in an uncontrolled state.

[0064] In step S104, it is determined whether the first drone is in an uncontrolled state, specifically including: sending a heartbeat signal to the controller at intervals of a preset time period; if no response signal from the controller is received within the preset time period, it is determined that the first drone is in an uncontrolled state.

[0065] Specifically, a status monitor is built into the first UAV to manage the heartbeat communication between the UAV and the controller. The status monitor establishes two-way communication with the controller of the ground control station through a wireless data link, and periodically sends and receives heartbeat signals. The heartbeat signal is a short data packet that contains the current status information of the first UAV, such as GPS coordinates, attitude, battery level, and a timestamp indicating the time when the signal was sent. The status monitor of the first UAV sets a fixed time interval T, such as 1 second, as the period for sending the heartbeat signal. Every T seconds, the status monitor of the first UAV automatically collects the current status information, generates a heartbeat data packet, and sends it to the controller through the data link. At the same time, the status monitoring module also sets a timer to record the time t that has passed since the last heartbeat signal was sent. If t exceeds the preset time threshold T max (e.g., 3 seconds), it is considered that the controller did not respond in time and the first drone may be in an uncontrolled state.

[0066] Preset time threshold T max The selection of T needs to consider factors such as the quality of the communication link, the delay of data processing, and the response speed of the controller. max It should be greater than the heartbeat period T to tolerate certain communication delays and packet loss. Therefore, it is necessary to select a suitable T based on the actual application scenario and system characteristics. max This application is only used as an example and is not intended to be limiting.

[0067] Step S105: If it is determined that the first UAV is in an uncontrolled state, the first position data and the attack instruction are sent to the second UAV, so that the second UAV attacks the target object.

[0068] In step S105, if the first drone detects that it is out of control, meaning it has lost communication with the ground control station, it will activate automatic attack mode and send an attack command to the pre-defined secondary control drone (the second drone). The attack command includes the first drone's identification information; at the same time, the first drone also needs to send the first location data of the target object to the second drone.

[0069] After receiving the attack command from the first drone, the second drone needs to send a confirmation signal to the first drone, indicating that it has received the attack command and starting the mission. At the same time, the second drone needs to maintain communication with the first drone to exchange mission progress. Based on the first position data of the target object, the second drone plans an optimal attack trajectory and flies along this optimal attack trajectory to deliver the guided bomb to the target object.

[0070] Step S106: After the second UAV attacks the target object, if it is determined that the target object is in a moving state, a flight path for attacking the target object is calculated.

[0071] In step S106, determining that the target object is in motion involves: continuously capturing multiple target images of the target object; determining target similarity between a first target image and a second target image, where the first target image is any target image from the multiple target images, and the second target image is any target image from the multiple target images other than the first target image; and determining that the target object is in motion if the target similarity is less than or equal to a preset similarity threshold. Calculating a flight path for attacking the target object involves: obtaining the real-time position and movement speed of the target object; predicting the target position of the target object based on the real-time position and movement speed; and calculating a flight path to the predicted target position using a path planning algorithm.

[0072] Specifically, after the second drone completes its initial attack on the target object, the first drone begins continuous surveillance of the target object. The first drone continuously captures multiple images of the target object at regular intervals (e.g., 1 second). These images form a time series, reflecting the target object's movement over time. From the multiple images captured, the first drone selects two images taken at different times for comparison to determine whether the target object has moved. Specifically, the first drone labels any one of the images as the first target image and then selects another from the remaining images as the second target image. The first drone then uses the SIFT (Scale Invariant Feature Transform) algorithm to calculate the similarity between the first and second images. Specifically, the first drone first extracts a series of keypoints from each of the two images and calculates the scale, orientation, and 128-dimensional descriptor of each keypoint. The first drone then compares the keypoint descriptors in the two images to find the best set of matching point pairs. Based on the number and spatial distribution of matching point pairs, the similarity between the two images can be calculated, represented by a value between 0 and 1, with a value closer to 1 indicating greater similarity.

[0073] The first drone compares the calculated similarity with the preset target similarity threshold. The preset target similarity threshold is an empirical value that can be set according to factors such as the type, size, and shooting distance of the target object. It is usually between 0.7 and 0.9, and this application does not limit this. If the similarity is less than or equal to the preset target similarity threshold, it means that there is a significant difference between the two target images, and the target object has shifted and is in a moving state. Conversely, if the target similarity is higher than the preset target similarity threshold, it means that the position of the target object has not changed much and is in a stationary state.

[0074] The first drone needs to obtain the real-time location and movement speed of the target object. In the above steps, the first drone has determined that the target object is in motion through similarity analysis. After determining that the target object is in motion, the first drone needs to calculate a suitable flight path based on the target object's movement trend in order to carry out a secondary attack on the moving target object. The first drone performs positioning and solution on multiple target images to obtain the spatial coordinates of the target object at different times. The first drone uses the Kalman filter target tracking algorithm to fit the target object's motion trajectory and predict the target object's position within a period of time in the future. Based on the prediction results, the first drone plans a flight path that can continuously track and strike the moving target object. The flight path is a straight line or curve parallel to the target object's direction of movement and slightly higher than the target.

[0075] Step S107: completing a secondary attack on the target object according to the flight route.

[0076] In step S107, the real-time distance between the target object and the target object is calculated in real time; and it is determined whether the real-time distance is less than or equal to a preset distance threshold. If the real-time distance is less than or equal to the preset distance threshold, a secondary attack is performed.

[0077] Specifically, the first drone performs autonomous flight according to the flight route generated in step S106. In the process of approaching the target object, the first drone needs to calculate the real-time distance between itself and the target object in real time. The first drone uses the Euclidean distance formula to calculate the straight-line distance between the drone and the target object based on the coordinate positions of the drone and the target object. The first drone compares the calculated distance with the preset position threshold. The preset position threshold is a safe distance that can be determined based on factors such as the effective range of the missile and the defense capability of the target, and this application does not limit this. When the distance between the drone and the target object is less than the preset position threshold, it means that the drone has entered the missile launch range and can initiate a secondary attack to send a missile to the target object.

[0078] Reference Figure 2The present application also provides a guidance and control device for a foldable drone, the device being a first drone, comprising an acquisition module 201 and a processing module 202, wherein: the acquisition module 201 is configured to capture a first image of a target object at a first position, where the first position is the current position of the first drone, and the first image is captured by a first camera of the first drone; the acquisition module 201 is further configured to capture a second image of the target object, where the second image is captured by a second camera of a second drone, and the second image and the first image are captured at the same time; the processing module 202 is configured to calculate first position data of the target object based on the first image and the second image; the processing module 202 is further configured to determine whether the first drone is in an uncontrolled state; the processing module 202 is further configured to, if it is determined that the first drone is in an uncontrolled state, send the first position data and an attack command to the second drone, so that the second drone attacks the target object; the processing module 202 is further configured to, after the second drone attacks the target object, if it is determined that the target object is in a moving state, calculate a flight path for attacking the target object; and the processing module 202 is further configured to complete a secondary attack on the target object based on the flight path.

[0079] In one possible embodiment, before the processing module 202 captures the first image of the target object at the first position, it also includes: the processing module 202 captures the third image of the target object at the second position, and the third image is taken by the first drone at the second position; the processing module 202 determines the similarity between the third image and the second image; if the similarity is greater than a preset similarity threshold, the processing module 202 moves to the first position and uses the first camera at the first position to capture the first image, wherein the similarity between the first image and the second image is less than or equal to the preset similarity threshold, and the distance between the second position and the first position is less than the preset distance threshold.

[0080] In one possible embodiment, the processing module 202 calculates the first position data of the target object based on the first image and the second image, specifically including: the acquisition module 201 acquires the first orientation data of the first drone and the second orientation data of the second drone, the orientation data including the yaw angle, the pitch angle and the roll angle; the processing module 202 captures the first feature point in the first image and the second feature point in the second image; the processing module 202 calculates the first line of sight vector from the first drone to the first feature point according to the first orientation data, and calculates the second line of sight vector from the second drone to the second feature point according to the second orientation data; the processing module 202 calculates the first position data of the target object using a triangulation positioning algorithm based on the first line of sight vector and the second line of sight vector.

[0081] In one possible implementation, the processing module 202 determines whether the first drone is in an uncontrolled state, specifically including: the processing module 202 sends a heartbeat signal to the controller at intervals of a preset time period; if no response signal from the controller is received within the preset time period, the processing module 202 determines that the first drone is in an uncontrolled state.

[0082] In one possible implementation, the processing module 202 determines that the target object is in a moving state, specifically including: the processing module 202 continuously captures multiple target images for the target object; the processing module 202 determines the target similarity between the first target image and the second target image, where the first target image is any target image among the multiple target images, and the second target image is any target image among the multiple target images except the first target image; if the target similarity is less than or equal to a preset target similarity threshold, the processing module 202 determines that the target object is in a moving state.

[0083] In one possible implementation, the processing module 202 calculates the flight path of the target object to be attacked, specifically including: the processing module 202 obtains the real-time position and movement speed of the target object; the processing module 202 predicts the target position of the target object based on the real-time position and movement speed; the processing module 202 uses a path planning algorithm to calculate the flight path to the predicted target position.

[0084] In one possible implementation, the processing module 202 completes a secondary attack on the target object based on the flight path, specifically including: the processing module 202 calculates the real-time distance between the target object and the target object in real time; the processing module 202 determines whether the real-time distance is less than or equal to a preset distance threshold, and if the real-time distance is less than or equal to the preset distance threshold, executes the secondary attack.

[0085] It should be noted that the above embodiments provide devices that implement their functions using only the division of the above functional modules as examples. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiments are based on the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.

[0086] This application also provides an electronic device. Figure 3 , Figure 3 3. This is a schematic diagram of the structure of an electronic device provided by an embodiment of the present application. The electronic device 300 may include: at least one processor 301, at least one network interface 304, a user interface 303, a memory 305, and at least one communication bus 302.

[0087] The communication bus 302 is used to implement the connection and communication between these components.

[0088] The user interface 303 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 303 may also include a standard wired interface and a wireless interface.

[0089] The network interface 304 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0090] The processor 301 may include one or more processing cores. Using various interfaces and circuits, the processor 301 connects to various components within the server. It executes instructions, programs, code sets, or instruction sets stored in the memory 305, as well as accesses data stored in the memory 305, to perform various server functions and process data. Optionally, the processor 301 may be implemented using at least one of the following hardware forms: a digital signal processing (DSP), a field-programmable gate array (FPGA), or a programmable logic array (PLA). The processor 301 may integrate one or a combination of a central processing unit (CPU), a graphics processing unit (GPU), and a modem. The CPU primarily processes the operating system, user interface, and application programs; the GPU is responsible for rendering and drawing content displayed on the display screen; and the modem handles wireless communications. It is understood that the modem may not be integrated into the processor 301 but implemented as a separate chip.

[0091] Among them, the memory 305 may include a random access memory (RAM) or a read-only memory (Read-Only Memory). Optionally, the memory 305 includes a non-transitory computer-readable storage medium. The memory 305 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 305 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 305 may also optionally be at least one storage device located away from the aforementioned processor 301. Refer to Figure 3 , the memory 305 as a computer storage medium may include an operating system, a network communication module, a user interface module and an application program for a guidance and control method for a folding drone.

[0092] exist Figure 3 In the electronic device 300 shown, the user interface 303 is mainly used to provide an input interface for the user and obtain data input by the user; and the processor 301 can be used to call an application program stored in the memory 305 for a guidance and control method for a folding drone. When executed by one or more processors 301, the electronic device 300 executes one or more of the methods described in the above embodiments. It should be noted that for the aforementioned method embodiments, for the sake of simplicity of description, they are all expressed as a series of action combinations, but those skilled in the art should know that this application is not limited to the order of the actions described, because according to this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for this application.

[0093] The present application further provides a computer-readable storage medium storing instructions, which, when executed by one or more processors 301 , enable the electronic device 300 to perform one or more of the methods described in the above embodiments.

[0094] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0095] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are merely schematic, such as the division of units, which is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interface, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0096] Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0097] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0098] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of this application, or the portion that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the various embodiments of the method of this application. The aforementioned memory includes various media that can store program code, such as USB flash drives, mobile hard drives, magnetic disks, or optical disks.

[0099] The foregoing is merely an exemplary embodiment of the present disclosure and is not intended to limit the scope of the present disclosure. In other words, any equivalent variations and modifications made in accordance with the teachings of the present disclosure are still within the scope of the present disclosure. Those skilled in the art will readily conceive of other embodiments of the present disclosure after considering the disclosure and the practical implications thereof.

[0100] This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art not described herein. The description and examples are to be considered as exemplary only, and the scope and spirit of the present disclosure are to be defined by the claims.

Claims

1. A guidance and control method for a foldable drone, the method being applied to a first drone, the first drone being communicatively connected to a second drone, the method comprising: Acquire a first image of a target object at a first position, where the first position is a current position of the first drone, and the first image is captured by a first camera of the first drone; Acquire a second image of the target object, where the second image is captured by a second camera of the second drone, and the second image and the first image are captured at the same time; Calculating first position data of the target object based on the first image and the second image; Determining whether the first UAV is in an uncontrolled state; If it is determined that the first drone is in an uncontrolled state, sending the first position data and an attack instruction to the second drone, so that the second drone attacks the target object; After the second UAV attacks the target object, if it is determined that the target object is in a moving state, calculating a flight route for attacking the target object; completing a secondary attack on the target object according to the flight route; Before acquiring the first image of the target object at the first position, the method further includes: collecting a third image of the target object at a second position, where the third image is taken by the first drone at the second position; determining a similarity between the third image and the second image; If the similarity is greater than a preset similarity threshold, move to a first position and use the first camera to shoot the first image at the first position, wherein the similarity between the first image and the second image is less than or equal to the preset similarity threshold, and the distance between the second position and the first position is less than a preset distance threshold.

2. The method according to claim 1, characterized in that The calculating the first position data of the target object based on the first image and the second image specifically includes: Acquire first orientation data of the first drone and second orientation data of the second drone; capturing a first feature point in the first image and a second feature point in the second image; Calculating a first sight line vector from the first drone to the first feature point based on the first orientation data, and calculating a second sight line vector from the second drone to the second feature point based on the second orientation data; A triangulation positioning algorithm is used to calculate first position data of the target object according to the first sight line vector and the second sight line vector.

3. The method according to claim 1, characterized in that The determining whether the first UAV is in an uncontrolled state specifically includes: Send a heartbeat signal to the controller at every preset time interval; If no response signal from the controller is received within the preset time period, it is determined that the first drone is in an uncontrolled state.

4. The method according to claim 1, wherein Determining that the target object is in a moving state specifically includes: Continuously shooting multiple target images of the target object; Determining target similarity between a first target image and a second target image, where the first target image is any one of the plurality of target images, and the second target image is any one of the plurality of target images except the first target image; If the target similarity is less than or equal to a preset target similarity threshold, it is determined that the target object is in a moving state.

5. The method according to claim 1, wherein The calculating of the flight path for attacking the target object specifically includes: Obtaining the real-time position and moving speed of the target object; predicting a target position of the target object based on the real-time position and movement speed; A path planning algorithm is used to calculate a flight route to the target location.

6. The method according to claim 1, characterized in that The completing the secondary attack on the target object according to the flight route specifically includes: Calculating the real-time distance to the target object in real time; It is determined whether the real-time distance is less than or equal to a preset distance threshold; if the real-time distance is less than or equal to the preset distance threshold, the secondary attack is performed.

7. A guidance and control device for a folding drone, characterized in that: The device is used to execute the method according to any one of claims 1 to 6, and the device comprises an acquisition module (201) and a processing module (202), wherein: The acquisition module (201) is used to collect a first image of a target object at a first position, the first position being the current position of the first drone, and the first image being taken by a first camera of the first drone; The acquisition module (201) is further configured to acquire a second image of the target object, the second image being captured by a second camera of the second drone, and the second image being captured at the same time as the first image; The processing module (202) is configured to calculate first position data of the target object based on the first image and the second image; The processing module (202) is further configured to determine whether the first drone is in an uncontrolled state; The processing module (202) is further configured to send the first position data and an attack instruction to the second drone if it is determined that the first drone is in an uncontrolled state, so that the second drone attacks the target object; The processing module (202) is further configured to calculate a flight path for attacking the target object if it is determined that the target object is in a moving state after the second drone attacks the target object; The processing module (202) is further configured to complete a secondary attack on the target object according to the flight route.

8. An electronic device, characterized in that: The electronic device (300) comprises a processor (301), a memory (305), a user interface (303) and a network interface (304), wherein the memory (305) is used to store instructions, the user interface (303) and the network interface (304) are used to communicate with other devices, and the processor (301) is used to execute the instructions stored in the memory (305) so that the electronic device (300) executes the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores instructions, and when the instructions are executed, the method according to any one of claims 1 to 6 is executed.

Images