Unmanned refueling machine accurate positioning route planning method and system based on multi-sensor fusion

Abstract

The invention discloses an unmanned refueling machine accurate positioning route planning method and system based on multi-sensor fusion, and the method comprises the following steps: employing multiple sensors to collect GPS coordinate data, inertial navigation attitude information and visual image data at the same time, and obtaining an original multi-mode data set; preprocessing the original multi-modal data set to obtain a synchronous calibration data set, and fusing the synchronous calibration data set to obtain a fusion positioning result; the relative position deviation of the unmanned oiling machine and the oil receiving machine is obtained based on the fusion positioning result, and a position deviation vector is obtained; and on the basis of the position deviation vector, an A * algorithm is adopted to generate an initial route path, and iterative adjustment is performed in combination with real-time airflow disturbance data to obtain a final route path. According to the invention, high-precision docking and dynamic route adjustment can be realized, and the docking safety and efficiency of the unmanned refueling machine are remarkably improved.

Description

Technical Field

[0001] This invention relates to the field of refueling aircraft path planning technology, specifically to a method and system for precise positioning and route planning of unmanned refueling aircraft based on multi-sensor fusion. Background Technology

[0002] As a crucial technological branch of modern aviation, unmanned aerial refueling (UAV) tankers' precise positioning and flight path planning directly impact the safety and efficiency of aerial refueling operations. Especially in complex environments, such as high-speed flight, adverse weather conditions, or electromagnetic interference scenarios, UAV tankers need to acquire high-precision position information in real time and rapidly plan their routes to ensure accurate docking with the receiving aircraft. Technological advancements in this field not only enhance the flexibility of military operations but also offer broad prospects for automated operations in civil aviation. However, existing technologies still have significant shortcomings in meeting the real-time and accuracy requirements of dynamic and complex environments, necessitating groundbreaking solutions.

[0003] Currently, the positioning and flight path planning methods for unmanned aerial refueling (UAV) aircraft largely rely on single or limited sensor data processing, such as GPS or inertial navigation systems. While these methods can provide a certain level of positioning accuracy under ideal conditions, environmental interference and the inherent limitations of the sensors make them unsuitable for high-dynamic scenarios in practical applications. For example, GPS signals may be lost under strong electromagnetic interference, and inertial navigation systems experience a decline in positioning accuracy due to error accumulation over long periods of operation. Visual positioning, although providing supplementary information, involves complex data processing and is easily affected by lighting conditions and weather. These methods struggle to achieve high-frequency, high-precision positioning updates in changing environments, thus impacting the real-time performance and reliability of flight path planning.

[0004] A deeper technological challenge lies in effectively integrating multi-source sensor data to improve the real-time performance of positioning. During high-speed flight, unmanned aerial refueling (UAV) aircraft generate massive amounts of sensor data from diverse sources, including GPS coordinates, inertial navigation attitude information, and image data from vision systems. This data needs to be acquired, processed, and fused within an extremely short time to generate reliable positioning results. However, the speed of data processing becomes a bottleneck. Traditional serial processing methods cannot complete the computation of large amounts of data in a short time, resulting in insufficient positioning update frequency. For example, during aerial refueling, the UAV needs to update its position within tens of milliseconds to ensure that the relative position error with the receiver aircraft is controlled within the centimeter level, but existing technologies often cannot meet this requirement due to computational delays.

[0005] Furthermore, the limitation of data processing speed directly impacts the dynamic adjustment capability of flight path planning. During high-speed flight, unmanned aerial refueling (UAV) aircraft need to rapidly generate or adjust their flight paths based on real-time positioning data to cope with changes in the receiver aircraft's position or sudden environmental disturbances. However, the latency of positioning data prevents timely response in flight path planning. For example, if the receiver aircraft shifts position due to airflow disturbances, and the UAV cannot quickly update its positioning and replan its flight path, docking may fail or even collision may occur. This lack of dynamic adjustment capability stems from the absence of an efficient collaborative mechanism in the processing of multi-sensor data.

[0006] Therefore, how to achieve rapid processing and fusion of multi-sensor data in a high-speed dynamic environment, so as to ensure the high update frequency of unmanned refueling aircraft positioning and the real-time adjustment capability of flight path planning, has become a key issue. Summary of the Invention

[0007] To address the above technical problems, this invention provides a method for precise positioning and route planning of unmanned refueling aircraft based on multi-sensor fusion, comprising the following steps:

[0008] By simultaneously acquiring GPS coordinate data, inertial navigation attitude information, and visual image data using multiple sensors, a raw multimodal dataset is obtained.

[0009] The original multimodal dataset is preprocessed to obtain a synchronous calibration dataset, and the synchronous calibration dataset is fused to obtain a fused localization result;

[0010] Based on the fusion positioning results, the relative position deviation between the unmanned refueling aircraft and the receiving aircraft is obtained, and the position deviation vector is obtained.

[0011] Based on the position deviation vector, the A* algorithm is used to generate a preliminary flight path, and iterative adjustments are made in conjunction with real-time airflow disturbance data to obtain the final flight path.

[0012] Preferably, the method for obtaining the synchronous calibration dataset includes:

[0013] Extract timestamps from the original multimodal dataset;

[0014] Based on the timestamp, the GPS coordinate data, the inertial navigation attitude information, and the visual image data are synchronized in time to obtain a time-aligned dataset;

[0015] If the timestamp deviation in the time-aligned dataset exceeds a first preset threshold, the GPS coordinate data and the inertial navigation attitude information are adjusted by linear interpolation to obtain the synchronization calibration dataset.

[0016] Preferably, the method for obtaining the fusion localization result includes:

[0017] For the aforementioned synchronous calibration dataset, a feature extraction method is used to obtain the key features of each mode, resulting in a feature set;

[0018] The integrity of the feature set is checked. If the integrity condition is met, the feature set is fused using the extended Kalman filter algorithm to obtain a preliminary localization result.

[0019] Based on the preliminary positioning results, the positioning trajectory is optimized using a particle filter algorithm to obtain the final fusion positioning result.

[0020] Preferably, the method for obtaining the position deviation vector includes:

[0021] The fused positioning results are transformed to obtain position information in a unified coordinate system, and the relative position coordinates are determined.

[0022] Based on the relative position coordinates, the vector difference calculation method is used to obtain the relative position deviation vector between the unmanned refueling aircraft and the receiving aircraft;

[0023] If the magnitude of the relative position deviation vector is greater than the second preset threshold, the direction information of the relative position deviation vector is determined by vector decomposition.

[0024] The deviation angle is calculated based on the direction information to obtain the angle value of the deviation direction, and the component representation of the relative position deviation vector in the coordinate system is determined according to the angle value;

[0025] If the component represents a coordinate range that exceeds the preset range, the fused positioning result is smoothed by Kalman filtering, and the position deviation vector is determined based on the smoothed fused positioning result.

[0026] Preferably, the method for obtaining the final flight path includes:

[0027] Acquire real-time environmental data, and use the A* algorithm to generate a preliminary flight path based on the real-time environmental data to obtain a preliminary path sequence;

[0028] For the initial path sequence, the safety and feasibility of the path are analyzed. If the route constraints are not met, the path is adjusted using Dijkstra's algorithm to obtain an optimized path sequence.

[0029] Acquire airflow disturbance data and calculate the real-time airflow change trend based on the airflow disturbance data;

[0030] Based on the airflow change trend, the preliminary path sequence is updated using a particle filter algorithm to obtain the final flight path.

[0031] The present invention also provides a precise positioning and route planning system for unmanned refueling aircraft based on multi-sensor fusion. The system applies the above-mentioned method and includes: a data acquisition module, a data fusion module, a deviation calculation module, and a route generation module.

[0032] The data acquisition module uses multiple sensors to simultaneously acquire GPS coordinate data, inertial navigation attitude information, and visual image data to obtain the original multimodal dataset.

[0033] The data fusion module is used to preprocess the original multimodal dataset to obtain a synchronous calibration dataset, and to fuse the synchronous calibration dataset to obtain a fused positioning result.

[0034] The deviation calculation module obtains the relative position deviation between the unmanned refueling aircraft and the receiving aircraft based on the fused positioning results, and obtains the position deviation vector.

[0035] The route generation module generates a preliminary route path based on the position deviation vector using the A* algorithm, and then iteratively adjusts it by combining real-time airflow disturbance data to obtain the final route path.

[0036] Preferably, the process of obtaining the synchronous calibration dataset in the data fusion module includes:

[0037] Extract timestamps from the original multimodal dataset;

[0038] Based on the timestamp, the GPS coordinate data, the inertial navigation attitude information, and the visual image data are synchronized in time to obtain a time-aligned dataset;

[0039] If the timestamp deviation in the time-aligned dataset exceeds a first preset threshold, the GPS coordinate data and the inertial navigation attitude information are adjusted by linear interpolation to obtain the synchronization calibration dataset.

[0040] Preferably, the process for obtaining the fused positioning result in the data fusion module includes:

[0041] For the aforementioned synchronous calibration dataset, a feature extraction method is used to obtain the key features of each mode, resulting in a feature set;

[0042] The integrity of the feature set is checked. If the integrity condition is met, the feature set is fused using the extended Kalman filter algorithm to obtain a preliminary localization result.

[0043] Based on the preliminary positioning results, the positioning trajectory is optimized using a particle filter algorithm to obtain the final fusion positioning result.

[0044] Preferably, the workflow of the deviation calculation module includes:

[0045] The fused positioning results are transformed to obtain position information in a unified coordinate system, and the relative position coordinates are determined.

[0046] Based on the relative position coordinates, the vector difference calculation method is used to obtain the relative position deviation vector between the unmanned refueling aircraft and the receiving aircraft;

[0047] If the magnitude of the relative position deviation vector is greater than the second preset threshold, the direction information of the relative position deviation vector is determined by vector decomposition.

[0048] The deviation angle is calculated based on the direction information to obtain the angle value of the deviation direction, and the component representation of the relative position deviation vector in the coordinate system is determined according to the angle value;

[0049] If the component represents a coordinate range that exceeds the preset range, the fused positioning result is smoothed by Kalman filtering, and the position deviation vector is determined based on the smoothed fused positioning result.

[0050] Preferably, the workflow of the route generation module includes:

[0051] Acquire real-time environmental data, and use the A* algorithm to generate a preliminary flight path based on the real-time environmental data to obtain a preliminary path sequence;

[0052] For the initial path sequence, the safety and feasibility of the path are analyzed. If the route constraints are not met, the path is adjusted using Dijkstra's algorithm to obtain an optimized path sequence.

[0053] Acquire airflow disturbance data and calculate the real-time airflow change trend based on the airflow disturbance data;

[0054] Based on the airflow change trend, the preliminary path sequence is updated using a particle filter algorithm to obtain the final flight path.

[0055] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0056] This invention addresses the positioning deviations and suboptimal flight paths caused by multi-source data noise, time asynchrony, and airflow disturbances during the docking of unmanned refueling aircraft and receiver aircraft. It employs a parallel computing framework to filter noise and synchronize time between GPS, inertial navigation, and visual image data, generating a low-noise synchronization calibration dataset. Then, an extended Kalman filter algorithm is used to fuse multimodal information to obtain high-precision relative position deviations. When the deviation exceeds a safety threshold, the A* algorithm is used to generate a preliminary flight path, which is iteratively optimized using real-time airflow disturbances to ultimately form a precise flight trajectory and update the control command sequence. This invention enables high-precision docking and dynamic flight path adjustments, significantly improving the safety and efficiency of unmanned refueling aircraft docking. Attached Figure Description

[0057] To more clearly illustrate the technical solution of the present invention, the drawings used in the embodiments are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0058] Figure 1 This is a schematic diagram of the method flow according to an embodiment of the present invention;

[0059] Figure 2 This is a schematic diagram of the structure of an electronic device according to an embodiment of the present invention.

[0060] Explanation of reference numerals in the attached figures:

[0061] 1010, Processor; 1020, Memory; 1030, Input / Output Interface; 1040, Communication Interface; 1050, Bus. Detailed Implementation

[0062] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0063] It should be noted that, unless otherwise defined, the technical or scientific terms used in the embodiments of this disclosure should have the ordinary meaning understood by one of ordinary skill in the art to which this disclosure pertains. The terms "first," "second," and similar terms used in the embodiments of this disclosure do not indicate any order, quantity, or importance, but are merely used to distinguish different components. Terms such as "comprising" or "including" mean that the element or object preceding the word encompasses the elements or objects listed following the word and their equivalents, without excluding other elements or objects. Terms such as "connected" or "linked" are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. Terms such as "upper," "lower," "left," and "right" are used only to indicate relative positional relationships; when the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0064] Example 1

[0065] In this embodiment, as Figure 1 As shown, a method for precise positioning and route planning of unmanned refueling aircraft based on multi-sensor fusion includes the following steps:

[0066] S1. Simultaneously collect GPS coordinate data, inertial navigation attitude information, and visual image data using multiple sensors to obtain the original multimodal dataset.

[0067] S2. Preprocess the original multimodal dataset to obtain a synchronous calibration dataset, and fuse the synchronous calibration dataset to obtain the fused localization result.

[0068] The method for obtaining the synchronization calibration dataset includes: extracting timestamps from the original multimodal dataset; synchronizing GPS coordinate data, inertial navigation attitude information, and visual image data based on the timestamps to obtain a time-aligned dataset; if the timestamp deviation in the time-aligned dataset exceeds a first preset threshold, adjusting the GPS coordinate data and inertial navigation attitude information through linear interpolation to obtain the synchronization calibration dataset.

[0069] In this embodiment, the original multimodal dataset is acquired by a GPS module, an inertial measurement unit (IMU), and an image acquisition device, including GPS coordinates, inertial navigation attitude, and visual image data. The GPS module provides latitude and longitude coordinates 10 times per second, the IMU provides attitude data 100 times per second, including pitch and yaw angles, and the image acquisition device acquires 1080p images at 30 frames per second, extracting timestamp records to ensure synchronization. Based on the timestamps, the GPS coordinate data, inertial navigation attitude information, and visual image data are synchronized to obtain a time-aligned dataset. Noise is filtered from the time-aligned dataset using a wavelet transform algorithm to generate a denoised dataset. If the timestamp deviation in the denoised dataset exceeds a first preset threshold, a linear interpolation method is used to calibrate the timestamps, resulting in a time-calibrated dataset.

[0070] The method for obtaining the fused localization result includes: for the synchronous calibration dataset, using the feature extraction method to obtain the key features of each mode to obtain the feature set; checking the integrity of the feature set, and if the integrity condition is met, fusing the feature set through the extended Kalman filter algorithm to obtain the preliminary localization result; and based on the preliminary localization result, using the particle filter algorithm to optimize the localization trajectory to obtain the final fused localization result.

[0071] In this embodiment, firstly, absolute position features are extracted from the latitude and longitude coordinates provided by the GPS module, and short-term relative displacement and attitude change features are extracted from the pitch, yaw, and acceleration data output by the IMU at high frequency. Simultaneously, computer vision algorithms (such as ORB or SIFT feature extractors) are used to extract rich environmental feature points and geometric constraint information from the visual image frames corresponding to the synchronized timestamps, thus constructing a multimodal feature set containing absolute position, relative motion, and visual semantics. Then, the integrity of the feature set is checked, including verifying whether the timestamp alignment error of each modal data stream is within a microsecond threshold, whether there are any lost data packets or failed feature extraction frames, and whether the spatial distribution of feature points meets the minimum number requirement for subsequent fusion calculations. After passing the integrity verification, the Extended Kalman Filter (EKF) is used as the core fusion framework. The absolute position observations from GPS and the relative pose observations calculated from the visual reprojection error are input. A linearized nonlinear system model is used to efficiently filter out noise and preliminarily estimate the six degrees of freedom of the system, forming a preliminary positioning result. Finally, particle filtering (PF) is used for optimization: the output of the previous extended Kalman filter is used as the importance sampling distribution to initialize hundreds of particles, each representing a possible state hypothesis. The particle weights are updated by fusing the motion prediction of the IMU with the observation likelihood values ​​of visual features, and resampling is performed periodically to eliminate low-weight particles, thus finally outputting the fused localization result.

[0072] S3. Based on the fusion positioning results, obtain the relative position deviation between the unmanned refueling aircraft and the receiving aircraft, and obtain the position deviation vector.

[0073] The method for obtaining the position deviation vector includes: transforming the coordinate system of the fused positioning result to obtain position information in a unified coordinate system and determining the relative position coordinates; using the vector difference calculation method based on the relative position coordinates to obtain the relative position deviation vector between the unmanned refueling aircraft and the receiving aircraft; if the magnitude of the relative position deviation vector is greater than a second preset threshold, then the direction information of the relative position deviation vector is determined by the vector decomposition method; calculating the deflection angle based on the direction information to obtain the angle value of the deviation direction, and determining the component representation of the relative position deviation vector in the coordinate system based on the angle value; if the component representation exceeds the preset coordinate range, then the fused positioning result is smoothed by Kalman filtering, and the position deviation vector is determined based on the smoothed fused positioning result.

[0074] In this embodiment, based on the high-precision fusion positioning results obtained from the aforementioned steps, the position information of the unmanned refueling aircraft and the receiving aircraft is first unified to the same geographic coordinate system or body coordinate system through coordinate system transformation. The geocentric fixed coordinate system (ECEF) is used as an intermediate medium, and attitude alignment is completed with the help of a rotation matrix to accurately determine the relative position coordinates between the two. Subsequently, based on the relative position coordinates, the relative position deviation vector of the unmanned refueling aircraft pointing to the receiving aircraft is directly solved using the vector difference calculation method. If the magnitude of this vector is greater than a second preset threshold (usually dynamically set according to the mission safety distance and sensor accuracy), it is further projected onto the vertical axis, horizontal axis, and vertical axis of the body coordinate system through vector decomposition to resolve the direction information of the deviation. Based on the decomposed axial components, the deviation angle values ​​such as yaw angle and pitch angle are calculated, thereby completely describing the direction and magnitude of the deviation vector in polar coordinates or component form. If the component value in a certain direction exceeds the preset allowable coordinate range (e.g., the tolerance range of the oil probe docking), a smoothing correction mechanism based on Kalman filtering is triggered to perform real-time filtering on the fused positioning results, suppress positioning jitter and outlier interference, and recalculate the deviation vector based on the smoothed position, finally outputting a stable and reliable position deviation vector.

[0075] S4. Based on the position deviation vector, the A* algorithm is used to generate a preliminary flight path, and iterative adjustments are made in combination with real-time airflow disturbance data to obtain the final flight path.

[0076] The method for obtaining the final flight path includes: acquiring real-time environmental data; generating a preliminary flight path using the A* algorithm based on the real-time environmental data to obtain a preliminary path sequence; analyzing the safety and feasibility of the preliminary path sequence; if the flight path constraints are not met, adjusting the path using the Dijkstra algorithm to obtain an optimized path sequence; acquiring airflow disturbance data and calculating the real-time airflow change trend based on the airflow disturbance data; and updating the preliminary path sequence using a particle filter algorithm based on the airflow change trend to obtain the final flight path.

[0077] In this embodiment, real-time environmental data is first acquired. Then, based on the real-time environmental data and the acquired positional deviation vector between the unmanned refueling aircraft and the receiving aircraft, preliminary route planning is performed in the global environment map using the A* algorithm, according to the relative pose relationship indicated by the vector and the mission objective. The path cost is evaluated through a heuristic function, and a preliminary path sequence consisting of continuous waypoints is generated. Subsequently, a safety and feasibility analysis is performed on this sequence to check whether it avoids known no-fly zones and static obstacles and meets the dynamic constraints of the unmanned aircraft. If segments in the path are identified that do not meet the preset safety radius or curvature limits, the Dijkstra algorithm is called for local replanning to optimize the path point sequence, resulting in an optimized path sequence. On this basis, real-time airflow disturbance data is introduced, and the airflow change trend is modeled through time series analysis. An environmental disturbance model is then constructed based on this model. Then, a particle filter algorithm is used to incorporate the influence of airflow dynamics into the path update process. By predicting the interference effect of airflow on flight attitude and position, the position and flight sequence of each waypoint are dynamically adjusted, and a final route path that meets geometric constraints, effectively offsets environmental disturbances, and ensures a stable and safe docking process is generated through iterative optimization.

[0078] It should be noted that the method of this disclosure embodiment can be executed by a single device, such as a computer or server. The method of this embodiment can also be applied to a distributed scenario, where multiple devices cooperate to complete the task. In such a distributed scenario, one of these devices may execute only one or more steps of the method of this disclosure embodiment, and the multiple devices will interact with each other to complete the method described.

[0079] It should be noted that the above description describes some embodiments of this disclosure. Other embodiments are within the scope of the appended claims. In some cases, it should be understood that the sequence number of each step in the above embodiments does not imply the order of execution; the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention. The actions or steps recorded in the claims can be performed in a different order than that in the above embodiments and can still achieve the desired result. In addition, the processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0080] Example 2

[0081] In this embodiment, an unmanned refueling aircraft precise positioning and route planning system based on multi-sensor fusion includes: a data acquisition module, a data fusion module, a deviation calculation module, and a route generation module.

[0082] The data acquisition module uses multiple sensors to simultaneously collect GPS coordinate data, inertial navigation attitude information, and visual image data to obtain the raw multimodal dataset.

[0083] The data fusion module is used to preprocess the original multimodal dataset to obtain a synchronous calibration dataset, and then fuse the synchronous calibration dataset to obtain the fused positioning result.

[0084] In the data fusion module, the process of obtaining the synchronous calibration dataset includes: extracting timestamps from the original multimodal dataset; synchronizing GPS coordinate data, inertial navigation attitude information, and visual image data based on the timestamps to obtain a time-aligned dataset; if the timestamp deviation in the time-aligned dataset exceeds a first preset threshold, adjusting the GPS coordinate data and inertial navigation attitude information through linear interpolation to obtain the synchronous calibration dataset.

[0085] In the data fusion module, the process of obtaining the fused positioning result includes: for the synchronous calibration dataset, the key features of each mode are obtained by feature extraction to obtain a feature set; the integrity of the feature set is checked, and if the integrity condition is met, the feature set is fused by the extended Kalman filter algorithm to obtain the preliminary positioning result; based on the preliminary positioning result, the positioning trajectory is optimized by the particle filter algorithm to obtain the final fused positioning result.

[0086] The deviation calculation module obtains the relative position deviation between the unmanned refueling aircraft and the receiving aircraft based on the fusion positioning results, and obtains the position deviation vector.

[0087] The workflow of the deviation calculation module includes: transforming the fused positioning results into a coordinate system to obtain position information in a unified coordinate system and determining the relative position coordinates; based on the relative position coordinates, using the vector difference calculation method to obtain the relative position deviation vector between the unmanned refueling aircraft and the receiving aircraft; if the magnitude of the relative position deviation vector is greater than a second preset threshold, then using a vector decomposition method to determine the direction information of the relative position deviation vector; calculating the deflection angle based on the direction information to obtain the angle value of the deviation direction, and determining the component representation of the relative position deviation vector in the coordinate system based on the angle value; if the component representation exceeds the preset coordinate range, then using Kalman filtering to smooth the fused positioning results, and determining the position deviation vector based on the smoothed fused positioning results.

[0088] The route generation module uses the A* algorithm based on the position deviation vector to generate a preliminary route path, and then iteratively adjusts it by combining real-time airflow disturbance data to obtain the final route path.

[0089] The workflow of the route generation module includes: acquiring real-time environmental data; generating preliminary route paths using the A* algorithm based on the real-time environmental data to obtain a preliminary route sequence; analyzing the safety and feasibility of the preliminary route sequence; if the route constraints are not met, adjusting the path using the Dijkstra algorithm to obtain an optimized route sequence; acquiring airflow disturbance data and calculating real-time airflow change trends based on the airflow disturbance data; and updating the preliminary route sequence using a particle filter algorithm based on the airflow change trends to obtain the final route path.

[0090] The system described in the above embodiments is used to implement the corresponding multi-sensor fusion-based precise positioning and route planning method for unmanned refueling aircraft in any of the foregoing embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0091] It should be noted that the aforementioned unmanned refueling aircraft precise positioning and route planning system based on multi-sensor fusion is embodied in the form of functional units. The term "module" here can be implemented in software and / or hardware, without specific limitations.

[0092] For example, a "module" can be a software program, hardware circuit, or a combination of both that implements the above functions. Hardware circuits may include application-specific integrated circuits (ASICs), electronic circuits, processors (e.g., shared processors, proprietary processors, or group processors) and memory for executing one or more software or firmware programs, combined logic circuits, and / or other suitable components that support the described functions.

[0093] Example 3

[0094] Based on the same inventive concept, corresponding to the methods of any of the above embodiments, the present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the method for precise positioning and route planning of unmanned refueling aircraft based on multi-sensor fusion as described in any of the above embodiments.

[0095] Figure 2 This embodiment illustrates a more specific hardware structure of an electronic device, which may include a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040, and a bus 1050. The processor 1010, memory 1020, input / output interface 1030, and communication interface 1040 are interconnected internally via the bus 1050.

[0096] The processor 1010 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.

[0097] The memory 1020 can be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 1020 can store the operating system and other applications. When the technical solutions provided in the embodiments of this specification are implemented by software or firmware, the relevant program code is stored in the memory 1020 and is called and executed by the processor 1010.

[0098] The input / output interface 1030 is used to connect input / output modules to realize information input and output. Input / output modules can be configured as components within the device (not shown in the figure) or externally connected to the device to provide corresponding functions. Input devices may include keyboards, mice, touchscreens, microphones, various sensors, etc., while output devices may include displays, speakers, vibrators, indicator lights, etc.

[0099] The communication interface 1040 is used to connect a communication module (not shown in the figure) to enable communication between this device and other devices. The communication module can communicate via wired means (such as USB (Universal Serial Bus), network cable, etc.) or wireless means (such as mobile network, WIFI (Wireless Fidelity), Bluetooth, etc.).

[0100] Bus 1050 includes a pathway for transmitting information between various components of the device, such as processor 1010, memory 1020, input / output interface 1030, and communication interface 1040.

[0101] It should be noted that although the above-described device only shows the processor 1010, memory 1020, input / output interface 1030, communication interface 1040, and bus 1050, in specific implementations, the device may also include other components necessary for normal operation. Furthermore, those skilled in the art will understand that the above-described device may only include the components necessary for implementing the embodiments of this specification, and not necessarily all the components shown in the figures.

[0102] The system described in the above embodiments is used to implement the corresponding multi-sensor fusion-based precise positioning and route planning method for unmanned refueling aircraft in any of the foregoing embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0103] Example 4

[0104] Based on the same inventive concept, corresponding to the methods of any of the above embodiments, the present invention also provides a non-transitory computer-readable storage medium storing computer instructions, which are used to cause the computer to execute the multi-sensor fusion-based precise positioning and route planning method for unmanned refueling aircraft as described in any of the above embodiments.

[0105] The computer-readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transfer medium that can be used to store information accessible by a computing device.

[0106] The computer instructions stored in the storage medium of the above embodiments are used to cause the computer to execute the unmanned refueling aircraft precise positioning and route planning method based on multi-sensor fusion as described in any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0107] Those skilled in the art should understand that the discussion of any of the above embodiments is merely exemplary and is not intended to imply that the scope of this disclosure (including the claims) is limited to these examples; within the framework of this disclosure, the technical features of the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other variations of different aspects of the embodiments of this disclosure as described above, which are not provided in detail for the sake of brevity.

[0108] Additionally, to simplify the description and discussion, and to avoid obscuring the embodiments of this disclosure, the provided drawings may or may not show well-known power / ground connections to integrated circuit (IC) chips and other components. Furthermore, the apparatus may be shown in block diagram form to avoid obscuring the embodiments of this disclosure, and this also takes into account the fact that the details of implementation of these block diagram apparatuses are highly dependent on the platform on which the embodiments of this disclosure will be implemented (i.e., these details should be fully understood by those skilled in the art). While specific details (e.g., circuitry) have been set forth to describe exemplary embodiments of this disclosure, it will be apparent to those skilled in the art that the embodiments of this disclosure may be implemented without these specific details or with variations thereof. Therefore, these descriptions should be considered illustrative rather than restrictive.

[0109] Although this disclosure has been described in conjunction with specific embodiments thereof, many substitutions, modifications, and variations of these embodiments will be apparent to those skilled in the art from the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may be used with the embodiments discussed.

[0110] Therefore, the units of the various examples described in the embodiments of this application can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. 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 this application.

[0111] This disclosure is intended to cover all such substitutions, modifications, and variations that fall within the broad scope of the appended claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for precise positioning and route planning of unmanned refueling aircraft based on multi-sensor fusion, characterized in that, Includes the following steps: By simultaneously acquiring GPS coordinate data, inertial navigation attitude information, and visual image data using multiple sensors, a raw multimodal dataset is obtained. The original multimodal dataset is preprocessed to obtain a synchronous calibration dataset, and the synchronous calibration dataset is fused to obtain a fused localization result; Based on the fusion positioning results, the relative position deviation between the unmanned refueling aircraft and the receiving aircraft is obtained, and the position deviation vector is obtained. Based on the position deviation vector, the A* algorithm is used to generate a preliminary flight path, and iterative adjustments are made in conjunction with real-time airflow disturbance data to obtain the final flight path.

2. The method for precise positioning and route planning of unmanned refueling aircraft based on multi-sensor fusion according to claim 1, characterized in that, The methods for obtaining the synchronous calibration dataset include: Extract timestamps from the original multimodal dataset; Based on the timestamp, the GPS coordinate data, the inertial navigation attitude information, and the visual image data are synchronized in time to obtain a time-aligned dataset; If the timestamp deviation in the time-aligned dataset exceeds a first preset threshold, the GPS coordinate data and the inertial navigation attitude information are adjusted by linear interpolation to obtain the synchronization calibration dataset.

3. The method for precise positioning and route planning of unmanned refueling aircraft based on multi-sensor fusion according to claim 1, characterized in that, The methods for obtaining the fused localization results include: For the aforementioned synchronous calibration dataset, a feature extraction method is used to obtain the key features of each mode, resulting in a feature set; The integrity of the feature set is checked. If the integrity condition is met, the feature set is fused using the extended Kalman filter algorithm to obtain a preliminary localization result. Based on the preliminary positioning results, the positioning trajectory is optimized using a particle filter algorithm to obtain the final fusion positioning result.

4. The method for precise positioning and route planning of unmanned refueling aircraft based on multi-sensor fusion according to claim 1, characterized in that, The methods for obtaining the position deviation vector include: The fused positioning results are transformed to obtain position information in a unified coordinate system, and the relative position coordinates are determined. Based on the relative position coordinates, the vector difference calculation method is used to obtain the relative position deviation vector between the unmanned refueling aircraft and the receiving aircraft; If the magnitude of the relative position deviation vector is greater than the second preset threshold, the direction information of the relative position deviation vector is determined by vector decomposition. The deviation angle is calculated based on the direction information to obtain the angle value of the deviation direction, and the component representation of the relative position deviation vector in the coordinate system is determined according to the angle value; If the component represents a coordinate range that exceeds the preset range, the fused positioning result is smoothed by Kalman filtering, and the position deviation vector is determined based on the smoothed fused positioning result.

5. The method for precise positioning and route planning of unmanned refueling aircraft based on multi-sensor fusion according to claim 1, characterized in that, The methods for obtaining the final flight path include: Acquire real-time environmental data, and use the A* algorithm to generate a preliminary flight path based on the real-time environmental data to obtain a preliminary path sequence; For the initial path sequence, the safety and feasibility of the path are analyzed. If the route constraints are not met, the path is adjusted using Dijkstra's algorithm to obtain an optimized path sequence. Acquire airflow disturbance data and calculate the real-time airflow change trend based on the airflow disturbance data; Based on the airflow change trend, the preliminary path sequence is updated using a particle filter algorithm to obtain the final flight path.

6. A precise positioning and route planning system for an unmanned refueling aircraft based on multi-sensor fusion, wherein the system applies the method described in any one of claims 1-5, characterized in that, include: Data acquisition module, data fusion module, deviation calculation module, and route generation module; The data acquisition module uses multiple sensors to simultaneously acquire GPS coordinate data, inertial navigation attitude information, and visual image data to obtain the original multimodal dataset. The data fusion module is used to preprocess the original multimodal dataset to obtain a synchronous calibration dataset, and to fuse the synchronous calibration dataset to obtain a fused positioning result. The deviation calculation module obtains the relative position deviation between the unmanned refueling aircraft and the receiving aircraft based on the fused positioning results, and obtains the position deviation vector. The route generation module generates a preliminary route path based on the position deviation vector using the A* algorithm, and then iteratively adjusts it by combining real-time airflow disturbance data to obtain the final route path.

7. The unmanned refueling aircraft precise positioning and route planning system based on multi-sensor fusion according to claim 6, characterized in that, The process of obtaining the synchronous calibration dataset in the data fusion module includes: Extract timestamps from the original multimodal dataset; Based on the timestamp, the GPS coordinate data, the inertial navigation attitude information, and the visual image data are synchronized in time to obtain a time-aligned dataset; If the timestamp deviation in the time-aligned dataset exceeds a first preset threshold, the GPS coordinate data and the inertial navigation attitude information are adjusted by linear interpolation to obtain the synchronization calibration dataset.

8. The unmanned refueling aircraft precise positioning and route planning system based on multi-sensor fusion according to claim 6, characterized in that, The process for obtaining the fused positioning result in the data fusion module includes: For the aforementioned synchronous calibration dataset, a feature extraction method is used to obtain the key features of each mode, resulting in a feature set; The integrity of the feature set is checked. If the integrity condition is met, the feature set is fused using the extended Kalman filter algorithm to obtain a preliminary localization result. Based on the preliminary positioning results, the positioning trajectory is optimized using a particle filter algorithm to obtain the final fusion positioning result.

9. The unmanned refueling aircraft precise positioning and route planning system based on multi-sensor fusion according to claim 6, characterized in that, The workflow of the deviation calculation module includes: The fused positioning results are transformed to obtain position information in a unified coordinate system, and the relative position coordinates are determined. Based on the relative position coordinates, the vector difference calculation method is used to obtain the relative position deviation vector between the unmanned refueling aircraft and the receiving aircraft; If the magnitude of the relative position deviation vector is greater than the second preset threshold, the direction information of the relative position deviation vector is determined by vector decomposition. The deviation angle is calculated based on the direction information to obtain the angle value of the deviation direction, and the component representation of the relative position deviation vector in the coordinate system is determined according to the angle value; If the component represents a coordinate range that exceeds the preset range, the fused positioning result is smoothed by Kalman filtering, and the position deviation vector is determined based on the smoothed fused positioning result.

10. The unmanned refueling aircraft precise positioning and route planning system based on multi-sensor fusion according to claim 6, characterized in that, The workflow of the route generation module includes: Acquire real-time environmental data, and use the A* algorithm to generate a preliminary flight path based on the real-time environmental data to obtain a preliminary path sequence; For the initial path sequence, the safety and feasibility of the path are analyzed. If the route constraints are not met, the path is adjusted using Dijkstra's algorithm to obtain an optimized path sequence. Acquire airflow disturbance data and calculate the real-time airflow change trend based on the airflow disturbance data; Based on the airflow change trend, the preliminary path sequence is updated using a particle filter algorithm to obtain the final flight path.

Images