Unmanned aerial vehicle accurate positioning method and device fusing multi-source positioning data

Abstract

The invention relates to the technical field of unmanned aerial vehicle positioning, discloses an unmanned aerial vehicle accurate positioning method and device fusing multi-source positioning data, electronic equipment, a computer readable storage medium and a computer program product, and is used for solving the technical problem that accurate and stable positioning of an unmanned aerial vehicle cannot be realized in an indoor weak texture scene in the prior art. The method comprises the following steps: acquiring initial positioning data of an unmanned aerial vehicle in real time, the initial positioning data being at least from two information sources; constructing a positioning fusion algorithm based on an unscented Kalman filtering algorithm, evaluating the credibility of initial positioning data from each information source in real time, and calculating a positioning covariance matrix; and adjusting the fusion weight of each initial positioning data based on the positioning covariance matrix, and calling a positioning fusion algorithm to perform weighted fusion on the initial positioning data of each information source to obtain fusion positioning data of the unmanned aerial vehicle. According to the method, the positioning accuracy and stability of the unmanned aerial vehicle in a scene in which GPS signals are lacked and environment textures are weak can be improved.

Description

Technical Field

[0001] The present invention relates to the field of unmanned aerial vehicle (UAV) positioning technology, and in particular to a method, device, electronic device, computer storage medium, and computer program product for accurately positioning a UAV by integrating multi-source positioning data. Background Art

[0002] Visual positioning technology is a key technology widely used in robotics and drone navigation. It uses cameras to acquire real-time visual information about the surrounding environment, calculate and estimate its own motion state and position, and is widely used in a variety of fields, including indoor positioning, intelligent inspection, autonomous driving, and virtual reality. The application of visual positioning technology is particularly important in indoor environments, where GPS signals are difficult to reach.

[0003] In existing visual positioning technologies, when GPS positioning signals are insufficient, algorithms such as visual odometry (VO) or visual inertial odometry (VIO) are typically used to achieve self-positioning. However, in indoor scenes with weak textures, such as corridors, monochromatic walls, uniform floors, and glass curtain walls, traditional visual positioning methods often suffer from a sharp drop in positioning accuracy or large cumulative drift due to a lack of sufficient visual feature points or texture information. Therefore, there is an urgent need for a positioning method that can accurately position drones in weak texture scenes while improving the stability of the positioning system. Summary of the Invention

[0004] The main purpose of the present invention is to solve the technical problem in the prior art that it is impossible to achieve accurate and stable positioning of drones in indoor weak-texture scenes.

[0005] A first aspect of the present invention provides a method for accurately positioning a UAV by fusing multi-source positioning data, comprising:

[0006] Acquire initial positioning data of the UAV in real time, wherein the initial positioning data comes from at least two sources;

[0007] Constructing a positioning fusion algorithm based on the unscented Kalman filter algorithm to evaluate the credibility of the initial positioning data from each source in real time and calculate the positioning covariance matrix;

[0008] The fusion weight of each of the initial positioning data is adjusted based on the positioning covariance matrix, and the positioning fusion algorithm is called to perform weighted fusion on the initial positioning data of each source to obtain the fused positioning data of the UAV.

[0009] Optionally, in a first implementation of the first aspect of the present invention, the real-time evaluation of the credibility of the initial positioning data from each information source and the calculation of the positioning covariance matrix include:

[0010] Calculating the real-time residual of each of the initial positioning data, and calculating the covariance of each of the initial positioning data based on the real-time residual;

[0011] Calculating a dynamic confidence coefficient of each of the initial positioning data based on the real-time residual and the historical performance of each of the initial positioning data;

[0012] A positioning covariance matrix is ​​constructed according to the covariance and the dynamic confidence coefficient.

[0013] Optionally, in a second implementation manner of the first aspect of the present invention, calculating the real-time residual of each initial positioning data includes:

[0014] Presetting a measurement update period, and obtaining actual observation values ​​and predicted values ​​of initial positioning data of each signal source in each measurement update period;

[0015] The difference between the actual observation value and the predicted value is calculated to obtain the real-time residual of each of the initial positioning data.

[0016] Optionally, in a third implementation of the first aspect of the present invention, the initial positioning data includes visual positioning data, visual odometry positioning data, and visual marker positioning data;

[0017] The method for accurately positioning a UAV by integrating multi-source positioning data further includes:

[0018] Determine in real time whether the visual marker point is included in the visual marker positioning range of the current drone;

[0019] If the visual marker positioning range includes the visual marker point, then before adjusting the fusion weight of each of the initial positioning data based on the positioning covariance matrix and weighted fusing the initial positioning data of each signal source to obtain the fused positioning data of the drone, the method further includes:

[0020] Calculating visual marker point positioning data according to the visual marker point;

[0021] The visual positioning data and the visual odometry positioning data are corrected based on the visual marker positioning data, and the accumulated errors of the visual positioning data and the visual odometry positioning data are corrected, and the credibility of the initial positioning data from each source is updated.

[0022] Optionally, in a fourth implementation of the first aspect of the present invention, if the visual marker positioning range does not include a visual marker point, then before adjusting the fusion weight of each of the initial positioning data based on the positioning covariance matrix and weightedly fusing the initial positioning data of each source to obtain the fused positioning data of the drone, the method further includes:

[0023] Get historical positioning information of visual odometry positioning data;

[0024] The fusion weights of the visual positioning data and the visual odometry positioning data are adjusted based on the positioning covariance matrix, and error suppression is performed in combination with the historical positioning information of the visual odometry positioning data.

[0025] Optionally, in a fifth implementation of the first aspect of the present invention, the visual marker point is an AR Tag.

[0026] A second aspect of the present invention provides a UAV precise positioning device that integrates multi-source positioning data, comprising:

[0027] An acquisition module is used to acquire the initial positioning data of the UAV in real time, wherein the initial positioning data comes from at least two sources;

[0028] A calculation module is used to construct a positioning fusion algorithm based on an unscented Kalman filter algorithm, evaluate the credibility of the initial positioning data from each source in real time, and calculate the positioning covariance matrix;

[0029] The fusion module is used to adjust the fusion weight of each of the initial positioning data based on the positioning covariance matrix, call the positioning fusion algorithm to weightedly fuse the initial positioning data of each source, and obtain the fused positioning data of the drone.

[0030] The third aspect of the present invention provides a UAV precise positioning device that integrates multi-source positioning data, comprising: a memory and at least one processor, wherein the memory stores instructions; the at least one processor calls the instructions in the memory to enable the UAV precise positioning device that integrates multi-source positioning data to perform the steps of the above-mentioned UAV precise positioning method that integrates multi-source positioning data.

[0031] A fourth aspect of the present invention provides a computer-readable storage medium, which stores instructions that, when executed on a computer, enable the computer to execute the steps of the above-mentioned method for precise positioning of a drone by fusing multi-source positioning data.

[0032] A fifth aspect of the present invention provides a computer program product, comprising a computer program / instruction, characterized in that when the computer program / instruction is executed by a processor, the steps of the method for precise positioning of a drone by fusing multi-source positioning data as described above are implemented.

[0033] In the technical solution provided by the present invention, the initial positioning data of the drone is obtained in real time, wherein the initial positioning data comes from at least two sources; a positioning fusion algorithm is constructed based on the unscented Kalman filter algorithm, the credibility of the initial positioning data from each source is evaluated in real time, and the positioning covariance matrix is ​​calculated; the fusion weights of each initial positioning data are adjusted based on the positioning covariance matrix, and the positioning fusion algorithm is called to perform weighted fusion on the initial positioning data of each source to obtain the fused positioning data of the drone. This method can perform accurate and stable positioning even in weak texture scenes when the GPS positioning signal is missing. In addition, a device, electronic device, computer-readable storage medium, and computer program product provided by the present invention also solve corresponding technical problems. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0035] Figure 1 This is a flow chart of a first embodiment of a method for accurately positioning a UAV by fusing multi-source positioning data according to an embodiment of the present invention;

[0036] Figure 2 This is a schematic diagram of a specific method for fusing positioning data in a first embodiment of a method for accurately positioning a UAV by fusing multi-source positioning data in an embodiment of the present invention;

[0037] Figure 3 This is a flow chart of a second embodiment of a method for accurately positioning a UAV by fusing multi-source positioning data according to an embodiment of the present invention;

[0038] Figure 4 Schematic diagram of a specific method for fusing positioning data in a second embodiment of a method for accurately positioning a UAV by fusing multi-source positioning data in an embodiment of the present invention;

[0039] Figure 5 A schematic diagram of an embodiment of a precise positioning device for a UAV that integrates multi-source positioning data according to an embodiment of the present invention;

[0040] Figure 6 A schematic diagram of an embodiment of a precise positioning device for a UAV that integrates multi-source positioning data in an embodiment of the present invention;

[0041] Figure 7 The figure is a schematic diagram of the principle of a computer-readable medium in an embodiment of the present invention. DETAILED DESCRIPTION

[0042] Exemplary embodiments of the present invention will now be described more fully with reference to the accompanying drawings. However, exemplary embodiments can be implemented in various forms, and it should not be understood that the present invention is limited to the embodiments set forth herein. On the contrary, providing these exemplary embodiments enables the present invention to be more comprehensive and complete, making it easier to fully convey the inventive concept to those skilled in the art. In the figures, the same reference numerals represent the same or similar elements, components or parts, and thus their repeated description will be omitted.

[0043] Under the premise of being consistent with the technical concept of the present invention, the features, structures, characteristics or other details described in a specific embodiment do not exclude that they can be combined in one or more other embodiments in a suitable manner.

[0044] In the description of specific embodiments, the features, structures, characteristics, or other details of the present invention are described to enable those skilled in the art to fully understand the embodiments. However, this does not preclude those skilled in the art from practicing the technical solutions of the present invention without one or more of the specific features, structures, characteristics, or other details.

[0045] The flowcharts shown in the accompanying drawings are for illustrative purposes only and do not necessarily include all contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may be decomposed, while others may be combined or partially combined. Therefore, the actual execution order may vary depending on the actual situation.

[0046] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically separate entities. That is, these functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0047] The term "and / or" or "and / or" includes all combinations of any one or more of the associated listed items.

[0048] See also Figure 1 and Figure 2 The first embodiment of the method for accurately positioning a UAV by integrating multi-source positioning data in the embodiment of the present invention includes:

[0049] S101, obtaining the initial positioning data of the UAV in real time;

[0050] It is understood that the execution subject of the present invention can be a UAV precise positioning device that integrates multi-source positioning data, or a terminal or a server, and the specific implementation is not limited here. The embodiment of the present invention is described by taking the server as the execution subject as an example.

[0051] In this embodiment, the initial positioning data of the drone acquired in real time specifically comes from multiple sources. In one specific embodiment, the initial positioning data comes from at least two sources; for example, visual positioning data acquired by a visual sensor via SLAM (Simultaneous Localization and Mapping) and visual odometry positioning data from a visual odometry (or visual-inertial odometry). In another embodiment, the initial positioning data may also include visual marker positioning data determined from visual markers contained in images acquired by the visual sensor.

[0052] In a specific embodiment, ORB-SLAM visual data can be collected by a depth camera installed on a drone, visual odometry positioning data can be obtained by the drone's built-in visual odometry, and visual marker positioning data can be obtained by pre-deploying AR Tags as visual markers.

[0053] S102, constructing a positioning fusion algorithm based on the unscented Kalman filter algorithm, evaluating the credibility of the initial positioning data from each source in real time, and calculating the positioning covariance matrix;

[0054] In this step, after obtaining the initial positioning data from multiple sources, the initial positioning data are fused according to the reliability of each initial positioning data based on the positioning fusion algorithm. During the fusion, the fusion ratio of the initial positioning data from the more reliable positioning data source is specifically increased to achieve the goal of improving the positioning accuracy.

[0055] The specific implementation steps include: calculating the real-time residual of each of the initial positioning data, and calculating the covariance of each of the initial positioning data based on the real-time residual; calculating the dynamic confidence coefficient of each of the initial positioning data based on the real-time residual and the historical performance of each of the initial positioning data; and constructing a positioning covariance matrix based on the covariance and the dynamic confidence coefficient.

[0056] The calculation of the real-time residual of each of the initial positioning data includes: presetting a measurement update period, obtaining the actual observation value and predicted value of the initial positioning data of each source in each measurement update period; calculating the difference between the actual observation value and the predicted value to obtain the real-time residual of each of the initial positioning data.

[0057] In a specific embodiment, the positioning fusion algorithm described in this embodiment is based on the idea of ​​the Unscented Kalman Filter (UKF) algorithm and is constructed for the special needs of this embodiment. The positioning fusion algorithm can describe the state transition of the drone and the measurement process of each source based on a nonlinear function, and capture the non-Gaussian characteristics of the state distribution based on the Unscented Kalman Filter algorithm, propagate and perform state prediction for this moment based on the previous moment, and obtain the optimal prediction value of the drone positioning data; then the actual initial positioning data of each source at this moment is used as the actual measurement value, and the difference between the actual measurement value and the optimal prediction value is made to obtain the real-time residual. The covariance of each source is calculated based on the real-time residual, and a dynamic confidence coefficient is generated based on the real-time residual and the historical performance of the positioning information of each source, and a positioning covariance matrix is ​​constructed based on the covariance and the dynamic confidence coefficient.

[0058] S103: Adjust the fusion weight of each initial positioning data based on the positioning covariance matrix, call the positioning fusion algorithm to perform weighted fusion on the initial positioning data of each source, and obtain the fused positioning data of the UAV.

[0059] In this embodiment, weighted fusion is mainly performed based on the positioning covariance matrix obtained in the above steps. Specifically, the fusion weights of each initial positioning data are adjusted based on the positioning covariance matrix, and the initial positioning data of each source are weightedly fused based on the positioning fusion algorithm according to the fusion weights, and finally the fused positioning data of the drone is calculated.

[0060] In a specific embodiment, since different scenes may have different environmental characteristics, when certain environmental characteristics lead to a large observation residual of a certain source, the dynamic confidence coefficient of the positioning data of the source is correspondingly increased, thereby reducing the influence weight of the source in the update process, and the initial positioning data of each source is weightedly fused based on the positioning fusion algorithm according to the fusion weight, and finally the fused positioning data of the drone is calculated. Figure 2 Taking the positioning data from three sources, namely visual positioning data, visual odometry positioning data and visual marker positioning data, as an example, we first perform state estimation based on the data of each source to calculate the state prediction value, update the confidence weight of each source according to the state prediction value, and generate accurate positioning information based on the confidence weight.

[0061] In a specific embodiment, the visual marker point positioning data described in this embodiment may not be available at all times. When the visual marker point positioning data is lacking within the visual positioning range of the drone, the visual positioning data and the visual odometry positioning data are preferentially used for fusion; but when the visual positioning range of the drone contains visual marker points and the visual marker point positioning data can be obtained, the influence weight of the visual marker point positioning data during fusion is increased to improve the positioning accuracy.

[0062] The technical solution in the embodiment of the present invention can dynamically fuse multiple positioning data based on the reliability of positioning data from various different sources to calculate the final precise positioning result, which can improve the positioning accuracy and stability of drones in scenarios where there is a lack of GPS signals and the environmental texture is weak.

[0063] Please see Figure 3 and Figure 4 The second embodiment of the method for accurately positioning a UAV by integrating multi-source positioning data in the embodiment of the present invention includes:

[0064] S201, obtaining the initial positioning data of the UAV in real time;

[0065] Specifically, the initial positioning data comes from at least two sources. In this embodiment, the initial positioning data comes from three sources, specifically including visual positioning data, visual odometry positioning data, and visual marker positioning data.

[0066] In a specific embodiment, ORB-SLAM visual data can be collected by a depth camera installed on a drone, visual odometry positioning data can be obtained by the drone's built-in visual odometry (or visual inertial odometry), and visual marker point positioning data can be obtained by pre-deploying AR Tags as visual marker points.

[0067] S202, constructing a positioning fusion algorithm based on the unscented Kalman filter algorithm, evaluating the credibility of the initial positioning data from each source in real time, and calculating the positioning covariance matrix;

[0068] In a specific embodiment, the positioning fusion algorithm described in this embodiment is based on the Unscented Kalman Filter (UKF) algorithm and is constructed for the special needs of this embodiment. The positioning fusion algorithm can describe the state transition of the drone and the measurement process of each source based on a nonlinear function to obtain a fused measurement vector. In a specific example, the fused measurement vector specifically includes three types of data: visual positioning data, visual odometry positioning data, and visual marker positioning data:

[0069]

[0070] Among them, z k represents the fused measurement vector, z ORB,k represents the pose measurement data extracted by ORB-SLAM based on visual features, z VO,k Represents the pose measurement data of the visual odometry data, z AT,k Represents the absolute position measurement data obtained based on the AR Tag; and:

[0071] z ORB,k =h ORB (x k )+v ORB,k

[0072] z VO,k =h dji (x k )+v VO,k

[0073] z AT,k =h AT (x k )+v AT,k

[0074] Where h represents the nonlinear measurement model of each signal source, which is used to describe the mapping relationship between the drone's state and the sensor's measurement value. v represents the statistical characteristics of the measurement noise or error of each signal source, which can be obtained through calibration experiments, sensor parameter manuals, online adaptive estimation, and other methods.

[0075] Subsequently, the system propagates the information and performs a state prediction for this moment based on the previous moment, obtaining the optimal predicted value for the drone's positioning data. The actual initial positioning data of each source at this moment is then used as the actual measurement value, and the difference between the actual measurement value and the optimal predicted value is calculated to obtain a real-time residual. The covariance of each source is calculated based on the real-time residual, and a dynamic confidence coefficient is generated based on the real-time residual and the historical performance of each source's positioning information. A positioning covariance matrix is ​​constructed based on the covariance and the dynamic confidence coefficient.

[0076] In a specific embodiment, the specific steps of constructing the positioning covariance matrix include: generating an initialized Sigma point set, capturing the non-Gaussian characteristics of the state distribution based on the unscented Kalman filter algorithm, completing the state prediction through the Sigma point set propagation, and obtaining the predicted value of the measurement vector Predicted value based on the measurement vector and the fused measurement vector z k Calculate the real-time residual ε k ; Then according to the real-time residual ε k Compute the covariance.

[0077] This also includes adjusting the contribution of each source in the fusion process according to its actual measurement residual to ensure high-precision and stable positioning performance in indoor weak-texture environments. Specifically, in order to reflect the credibility of each source at the current moment, a dynamic confidence coefficient γ is introduced. i,k ; Among them, the dynamic confidence coefficient γ i,k The total measurement noise covariance matrix is ​​constructed based on the real-time residuals and historical performance adjustments as follows:

[0078]

[0079] Among them, R k represents the overall measurement noise covariance matrix, R ORB 、R VO and R AT Represent the measurement noise covariance of visual positioning data, visual odometry positioning data and visual marker positioning data respectively. In this way, when the actual positioning calculation process, if the observation residual of a certain source is large, the corresponding dynamic confidence coefficient γ i,k Increase, thereby reducing the influence weight of the source in the update process.

[0080] S203, determining in real time whether the visual marker positioning range of the current UAV contains the visual marker point;

[0081] S204, performing error correction or error suppression based on the result of determining whether the visual marker point is included in the visual marker positioning range;

[0082] In this embodiment, the visual marker location data may not be available at all times, so please refer to the attached Figure 3 In this embodiment, it is determined in real time whether the visual marker point is included in the visual marker positioning range of the current drone, and error correction or error suppression is performed based on the determination result of whether the visual marker point is included in the visual marker positioning range.

[0083] In a specific embodiment, the visual marker positioning range is first set based on the farthest visual marker positioning range obtained when the accuracy of the visual marker point positioning data can meet the accuracy threshold when the drone calculates the positioning data based on the visual marker; then, it is determined in real time whether the visual marker point is included in the visual marker positioning range of the current drone, and based on the judgment result, it is determined whether to perform error correction based on the real-time obtained visual marker point positioning data or to perform error suppression based on the historical visual marker point positioning data.

[0084] (1) When the judgment result is that the visual marker point is included in the visual marker positioning range:

[0085] That is, when the drone approaches the pre-set AR Tag, it uses its precise posture information to perform real-time correction on the cumulative errors generated by the visual positioning data and visual odometry positioning data generated by ORB-SLAM, thereby reducing positioning drift during long-term operation. Specifically, a positioning fusion algorithm based on the unscented Kalman filter algorithm is used to achieve dynamic confidence fusion of multi-source data and optimize weight distribution in real time. The positioning uncertainty of each source is quantified by calculating the covariance matrix (such as the feature matching error of the visual positioning data and the integral drift of the visual odometry positioning data), and abnormal data is detected based on historical residual analysis (such as observation failure caused by the occlusion of the AR Tag), thereby constructing a dynamic evaluation mechanism for the accuracy and reliability of each source.

[0086] Specifically, the solution also includes periodic cumulative error correction using AR Tags: in each measurement update period, based on the residual between the actual observation value and the predicted value of each source, where the measurement update period can be determined based on preset information, the specific expression for residual calculation is:

[0087]

[0088] Dynamic confidence coefficient update formula:

[0089]

[0090] in Represents the variance value of each source, which is calculated through historical residual data or sliding window statistics. i,k Used to construct a new measurement noise matrix R k , thereby adaptively reducing the weight of data with greater noise or lower source reliability during the update process.

[0091] (2) When the judgment result is that the visual marker positioning range does not contain the visual marker point:

[0092] That is, in areas far away from the AR Tag or where the AR Tag is invisible, the AR Tag historical correction information is used as a state space constraint to suppress long-term drift, and the visual positioning data is integrated with the visual odometry positioning data to ensure that the UAV can still maintain stable and high-precision positioning in an unmarked environment, thereby ensuring the reliability of its navigation and mission execution.

[0093] Specifically, in the absence of AR Tag, the system state x k Still using the nonlinear state transfer model:

[0094] x k =f(x k-1 ,u k-1 )+w k-1 wk-1 ~N(0,Q)

[0095] Where f(·) is the state transition function; u k-1 is the control input of the UAV; w k-1 is the process noise, N(0,Q) represents the distribution used to describe the process noise, where 0 represents the mean vector of the distribution is zero, and Q is the noise covariance during the UAV state transition process, which is used to quantify the uncertainty of the process noise and is usually determined by the uncertainty of the system dynamics model;

[0096] At the same time, construct the joint measurement vector z k :

[0097]

[0098] Among them, v ORB,k ~(0,R ORB ) and v VO,k ~N(0,R VO ) represent the measurement noise of the visual localization data and the visual odometry localization data, respectively.

[0099] S205: Adjust the fusion weight of each initial positioning data based on the positioning covariance matrix, call the positioning fusion algorithm to perform weighted fusion on the initial positioning data of each source, and obtain the fused positioning data of the UAV.

[0100] After obtaining the actual positioning covariance matrix of each initial positioning data, the fusion weight of each initial positioning data is adjusted based on the positioning covariance matrix, and the initial positioning data of each source are weightedly fused based on the positioning fusion algorithm according to the fusion weight, and finally the fused positioning data of the drone is calculated.

[0101] The technical solution in the embodiment of the present invention can dynamically fuse multiple positioning data based on the reliability of positioning data from various different sources to calculate the final precise positioning result, which can improve the positioning accuracy and stability of drones in scenarios where there is a lack of GPS signals and the environmental texture is weak. Through the technical solution in this embodiment, the dependence on environmental texture during positioning can be further reduced, and the continuity and stability of positioning in weak-texture environments can be improved; through the dynamic confidence fusion algorithm, the misjudgment rate of the zero-speed state is effectively reduced, and the positioning accuracy and positioning stability are improved; at the same time, based on the periodic cumulative error correction of the AR Tag, the positioning drift during long-term operation is significantly reduced, further improving the overall positioning accuracy and ensuring the success rate of drone mission execution in complex scenarios.

[0102] The above describes the precise positioning method of a UAV that integrates multi-source positioning data in an embodiment of the present invention. The following describes the precise positioning device of a UAV that integrates multi-source positioning data in an embodiment of the present invention. Figure 5 An embodiment of a precise positioning device for a UAV that integrates multi-source positioning data in an embodiment of the present invention includes:

[0103] An acquisition module 501 is configured to acquire initial positioning data of the UAV in real time, wherein the initial positioning data comes from at least two sources;

[0104] A calculation module 502 is configured to construct a positioning fusion algorithm based on an unscented Kalman filter algorithm, evaluate the credibility of the initial positioning data from each source in real time, and calculate a positioning covariance matrix;

[0105] The fusion module 503 is used to adjust the fusion weight of each of the initial positioning data based on the positioning covariance matrix, call the positioning fusion algorithm to weightedly fuse the initial positioning data of each source, and obtain the fused positioning data of the drone.

[0106] The technical solution in the embodiment of the present invention can dynamically fuse multiple positioning data based on the reliability of positioning data from various different sources to calculate the final precise positioning result, which can improve the positioning accuracy and stability of drones in scenarios where there is a lack of GPS signals and the environmental texture is weak.

[0107] In another embodiment of the present application, the calculation module 502 is used to calculate the real-time residual of each of the initial positioning data, and calculate the covariance of each of the initial positioning data based on the real-time residual;

[0108] Calculating a dynamic confidence coefficient of each of the initial positioning data based on the real-time residual and the historical performance of each of the initial positioning data;

[0109] A positioning covariance matrix is ​​constructed according to the covariance and the dynamic confidence coefficient.

[0110] In another embodiment of the present application, calculating the real-time residual of each of the initial positioning data includes:

[0111] Presetting a measurement update period, and obtaining actual observation values ​​and predicted values ​​of initial positioning data of each signal source in each measurement update period;

[0112] The difference between the actual observation value and the predicted value is calculated to obtain the real-time residual of each of the initial positioning data.

[0113] In another embodiment of the present application, the initial positioning data includes visual positioning data, visual odometry positioning data, and visual marker positioning data;

[0114] The acquisition module 501 is further specifically used to determine in real time whether the visual marker positioning range of the current drone contains a visual marker point;

[0115] The UAV precise positioning device integrating multi-source positioning data further includes a visual marker auxiliary correction module for:

[0116] If the visual marker positioning range includes a visual marker point, the visual marker point positioning data is calculated based on the visual marker point; the visual positioning data and the visual odometry positioning data are corrected based on the visual marker point positioning data, and the accumulated errors of the visual positioning data and the visual odometry positioning data are corrected, and the credibility of the initial positioning data from each source is updated.

[0117] In another embodiment of the present application, the visual marker auxiliary correction module is further used to:

[0118] If the visual marker positioning range does not include the visual marker point, the fusion weight of the visual positioning data and the visual odometry positioning data is adjusted based on the positioning covariance matrix, and error suppression is performed in combination with the historical positioning information of the visual odometry positioning data.

[0119] In another embodiment of the present application, the visual marker point is an AR Tag.

[0120] In addition, the specific implementation details of the UAV precise positioning device that integrates multi-source positioning data described in this embodiment during operation can be found in the specific description of the aforementioned method embodiment, so they will not be repeated here.

[0121] The device of the embodiment of the present invention can dynamically fuse multiple positioning data based on the reliability of positioning data from various different sources to calculate a final precise positioning result, which can improve the positioning accuracy and stability of drones in scenarios where GPS signals are lacking and the environmental texture is weak. The technical solution in this embodiment can further reduce the reliance on environmental texture during positioning, improving the continuity and stability of positioning in weak-texture environments. The dynamic confidence fusion algorithm effectively reduces the misjudgment rate of zero-speed states, improves positioning accuracy and stability, further enhances overall positioning accuracy, and ensures the success rate of drone mission execution in complex scenarios.

[0122] Based on the same inventive concept, an embodiment of this specification also provides an electronic device for accurately positioning a drone by integrating multi-source positioning data. The electronic device for accurately positioning a drone by integrating multi-source positioning data in an embodiment of the present invention is described in detail below from the perspective of hardware processing.

[0123] Figure 6This is a schematic diagram of the structure of an electronic device provided in the embodiment of this specification. Figure 6 The electronic device 600 according to this embodiment of the present invention will be described. Figure 6 The electronic device 600 shown is merely an example and should not limit the functions and scope of use of the embodiments of the present invention.

[0124] like Figure 6 As shown, electronic device 600 is implemented as a general-purpose computing device. Components of electronic device 600 may include, but are not limited to, at least one processing unit 610, at least one storage unit 620, a bus 630 connecting various system components (including storage unit 620 and processing unit 610), a display unit 640, and the like.

[0125] The storage unit stores program codes that can be executed by the processing unit 610, so that the processing unit 610 performs the steps according to various exemplary embodiments of the present invention described in the above processing method section of this specification. For example, the processing unit 610 can perform the following steps: Figure 1 or Figure 3 The steps of the method are shown.

[0126] The storage unit 620 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 6201 and / or a cache memory unit 6202 , and may further include a read-only memory unit (ROM) 6203 .

[0127] The storage unit 620 may also include a program / utility 6204 having a set (at least one) of program modules 6205, such program modules 6205 including but not limited to: an operating system, one or more application programs, other program modules and program data, each of which or some combination may include an implementation of a network environment.

[0128] Bus 630 may represent one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0129] The electronic device 600 may also communicate with one or more external devices 100 (e.g., keyboards, pointing devices, Bluetooth devices, etc.), one or more devices that enable a user to interact with the electronic device 600, and / or any device that enables the electronic device 600 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed through an input / output (I / O) interface 650. Furthermore, the electronic device 600 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through a network adapter 660. The network adapter 660 may communicate with other modules of the electronic device 600 through the bus 630. It should be understood that although Figure 6 Not shown, other hardware and / or software modules may be used in conjunction with electronic device 600, including but not limited to microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0130] In addition, the present invention also provides a computer program product, including a computer program / instruction, which, when executed by a processor, implements the method for accurately positioning a drone by fusing multi-source positioning data as described in any of the above embodiments.

[0131] Through the description of the above embodiments, it is easy for those skilled in the art to understand that the exemplary embodiments described in the present invention can be implemented by software, or by combining software with necessary hardware. Therefore, the technical solution according to the embodiment of the present invention can be embodied in the form of a software product, which can be stored in a computer-readable storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes a number of instructions to enable a computing device (which can be a personal computer, a server, or a network device, etc.) to execute the above method according to the present invention. When the computer program is executed by a data processing device, the computer-readable medium is enabled to implement the above method of the present invention, that is: Figure 1 or Figure 3 The method shown.

[0132] Figure 7 A schematic diagram of a computer-readable medium provided in accordance with an embodiment of this specification.

[0133] accomplish Figure 1 or Figure 3The computer program of the method shown can be stored on one or more computer-readable media. The computer-readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can be, for example, but not limited to, a system, device or component of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination thereof. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0134] The computer-readable storage medium may include a data signal propagated in baseband or as part of a carrier wave, wherein the readable program code is carried. The data signal propagated may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The readable storage medium may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, device, or component. The program code contained on the readable storage medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination thereof.

[0135] The program code for performing the operations of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, and the like, as well as conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a stand-alone software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving a remote computing device, the remote computing device may be connected to the user computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0136] In summary, the present invention can be implemented in hardware, or in a software module running on one or more processors, or in a combination thereof. It will be appreciated by those skilled in the art that general data processing equipment such as a microprocessor or a digital signal processor (DSP) can be used in practice to implement some or all of the functions of some or all of the components in the embodiments of the present invention. The present invention can also be implemented as a device or apparatus program (e.g., a computer program and a computer program product) for executing a part or all of the methods described herein. Such a program for implementing the present invention can be stored on a computer-readable medium, or can have the form of one or more signals. Such a signal can be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0137] The specific embodiments described above further illustrate the objectives, technical solutions, and beneficial effects of the present invention. It should be understood that the present invention is not inherently related to any specific computer, virtual device, or electronic device, and various general-purpose devices can also implement the present invention. The above description is only a specific embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention shall be included in the scope of protection of the present invention.

[0138] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments.

[0139] If the technical solution of this application involves personal information, the product that applies the technical solution of this application has clearly informed the personal information processing rules and obtained the individual's voluntary consent before processing personal information. If the technical solution of this application involves sensitive personal information, the product that applies the technical solution of this application has obtained the individual's separate consent before processing sensitive personal information, and at the same time meets the "explicit consent" requirement. For example, on personal information collection devices such as cameras, a clear and prominent sign is set to inform that the personal information collection scope has been entered and personal information will be collected. If the individual voluntarily enters the collection scope, it is deemed that they agree to the collection of their personal information; or on the personal information processing device, when the personal information processing rules are notified by obvious signs / information, the individual's authorization is obtained through pop-up information or by asking the individual to upload their personal information; among which, the personal information processing rules may include information such as the personal information processor, the purpose of personal information processing, the processing method, and the type of personal information processed.

[0140] The foregoing is merely an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should all be included within the scope of the claims of the present application.

Claims

1. A method for accurately positioning an unmanned aerial vehicle by integrating multi-source positioning data, characterized in that: include: Acquire initial positioning data of the UAV in real time, wherein the initial positioning data comes from at least two sources; Constructing a positioning fusion algorithm based on the unscented Kalman filter algorithm to evaluate the credibility of the initial positioning data from each source in real time and calculate the positioning covariance matrix; The fusion weight of each of the initial positioning data is adjusted based on the positioning covariance matrix, and the positioning fusion algorithm is called to perform weighted fusion on the initial positioning data of each source to obtain the fused positioning data of the UAV.

2. The method for accurately positioning a UAV by integrating multi-source positioning data according to claim 1, characterized in that: The real-time evaluation of the credibility of the initial positioning data from each information source and calculation of the positioning covariance matrix includes: Calculating the real-time residual of each of the initial positioning data, and calculating the covariance of each of the initial positioning data based on the real-time residual; Calculating a dynamic confidence coefficient of each of the initial positioning data based on the real-time residual and the historical performance of each of the initial positioning data; A positioning covariance matrix is ​​constructed according to the covariance and the dynamic confidence coefficient.

3. The method for accurately positioning a UAV by integrating multi-source positioning data according to claim 2, characterized in that: Calculating the real-time residual of each of the initial positioning data includes: Presetting a measurement update period, and obtaining actual observation values ​​and predicted values ​​of initial positioning data of each signal source in each measurement update period; The difference between the actual observation value and the predicted value is calculated to obtain the real-time residual of each initial positioning data.

4. The method for accurately positioning a UAV by integrating multi-source positioning data according to any one of claims 1 to 3, characterized in that: The initial positioning data includes visual positioning data, visual odometry positioning data and visual marker positioning data; The method for accurately positioning a UAV by integrating multi-source positioning data further includes: Determine in real time whether the visual marker point is included in the visual marker positioning range of the current drone; If the visual marker positioning range includes the visual marker point, then before adjusting the fusion weight of each of the initial positioning data based on the positioning covariance matrix and weighted fusing the initial positioning data of each signal source to obtain the fused positioning data of the drone, the method further includes: Calculating visual marker point positioning data according to the visual marker point; The visual positioning data and the visual odometry positioning data are corrected based on the visual marker positioning data, and the accumulated errors of the visual positioning data and the visual odometry positioning data are corrected, and the credibility of the initial positioning data from each source is updated.

5. The method for accurately positioning a UAV by integrating multi-source positioning data according to claim 4, characterized in that: If the visual marker positioning range does not include the visual marker point, then before adjusting the fusion weights of the initial positioning data based on the positioning covariance matrix and weighted fusing the initial positioning data of each source to obtain the fused positioning data of the drone, the method further includes: Get historical positioning information of visual odometry positioning data; The fusion weights of the visual positioning data and the visual odometry positioning data are adjusted based on the positioning covariance matrix, and error suppression is performed in combination with the historical positioning information of the visual odometry positioning data.

6. The method for accurately positioning a UAV by integrating multi-source positioning data according to claim 5, characterized in that: The visual marker point is an AR Tag.

7. A precise positioning device for unmanned aerial vehicles that integrates multi-source positioning data, characterized in that: The UAV precise positioning device integrating multi-source positioning data includes: An acquisition module is used to acquire the initial positioning data of the UAV in real time, wherein the initial positioning data comes from at least two sources; A calculation module is used to construct a positioning fusion algorithm based on an unscented Kalman filter algorithm, evaluate the credibility of the initial positioning data from each source in real time, and calculate the positioning covariance matrix; The fusion module is used to adjust the fusion weight of each of the initial positioning data based on the positioning covariance matrix, call the positioning fusion algorithm to weightedly fuse the initial positioning data of each source, and obtain the fused positioning data of the drone.

8. A precise positioning device for unmanned aerial vehicles that integrates multi-source positioning data, characterized in that: The UAV precise positioning device integrating multi-source positioning data includes: a memory and at least one processor, wherein the memory stores instructions; The at least one processor calls the instructions in the memory to enable the UAV precise positioning device that integrates multi-source positioning data to perform the steps of the UAV precise positioning method that integrates multi-source positioning data as described in any one of claims 1-6.

9. A computer-readable storage medium having a computer program / instruction stored thereon, characterized in that: When the program / instruction is executed by the processor, the steps of the method for accurately positioning a drone by fusing multi-source positioning data as described in any one of claims 1 to 6 are implemented.

10. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the steps of the method for accurately positioning a drone by fusing multi-source positioning data are implemented as described in any one of claims 1 to 6.

Images