Unmanned aerial vehicle indoor positioning method, apparatus, device, and medium

Abstract

This application relates to a method, apparatus, device, and medium for indoor drone positioning. The method includes responding to a drone positioning command and acquiring multiple Bluetooth beacons in the indoor environment where the drone is located; determining the azimuth information between the drone and the Bluetooth beacons; determining multiple position coordinates corresponding to the drone based on the azimuth information and an AOA positioning model; transmitting the multiple position coordinates corresponding to the drone to a positioning data fusion center; constructing a Gaussian function model corresponding to the multiple position coordinates based on the multiple position coordinates; and processing the Gaussian function model based on a Bayesian fusion theory model to determine the corresponding positioning coordinates of the drone, thereby completing the indoor positioning of the drone. This application achieves accuracy and real-time performance in indoor drone positioning, avoiding the problem of inaccurate indoor positioning caused by confined spaces and complex environments.

Description

Technical Field

[0001] This application relates to the field of indoor positioning technology, and in particular to an indoor positioning method for unmanned aerial vehicles (UAVs), a corresponding device, electronic equipment, and a computer-readable storage medium. Background Technology

[0002] With their outstanding efficiency and flexibility, powerful data collection and monitoring capabilities, excellent cost-effectiveness and innovation, drones have been widely used in various industries.

[0003] Currently, there are various indoor positioning methods suitable for small drones, but they generally have some drawbacks. For example, GPS positioning is affected by the external environment and has low positioning accuracy, making it unable to achieve accurate indoor positioning; traditional camera positioning is easily affected by lighting conditions, and positioning is prone to inaccuracy under poor lighting conditions; binocular cameras and host computer equipment are bulky and consume a lot of power, which is often difficult for small drones to carry, and the system construction cost is also high; UWB positioning has the problems of high power consumption and high difficulty and cost in construction.

[0004] In view of the problems that existing GPS positioning schemes are affected by the external environment and have low positioning accuracy, and cannot achieve accurate indoor positioning, traditional camera positioning schemes are easily affected by lighting, and are prone to inaccurate positioning under poor lighting conditions, as well as the problems that binocular cameras and host computer equipment are bulky and consume a lot of power, the applicant has made corresponding explorations to solve these problems. Summary of the Invention

[0005] The purpose of this application is to solve the above-mentioned problems by providing an indoor positioning method for unmanned aerial vehicles (UAVs), a corresponding device, electronic equipment, and a computer-readable storage medium.

[0006] To achieve the various objectives of this application, the following technical solution is adopted:

[0007] An indoor positioning method for unmanned aerial vehicles (UAVs) proposed to meet one of the purposes of this application includes:

[0008] In response to the drone positioning command, acquire multiple Bluetooth beacons in the indoor environment where the drone to be located is located;

[0009] Determine the azimuth information between the drone and the Bluetooth beacon, and based on the azimuth information, determine multiple position coordinates of the drone according to the AOA positioning model;

[0010] The multiple location coordinates corresponding to the UAV are transmitted to the positioning data fusion center, and a Gaussian function model corresponding to the multiple location coordinates is constructed based on the multiple location coordinates corresponding to the UAV.

[0011] The Gaussian function model is processed based on the Bayesian fusion theory model to determine the corresponding positioning coordinates of the UAV, thereby completing the UAV's indoor positioning.

[0012] Optionally, after responding to the drone positioning command and obtaining multiple Bluetooth beacons in the indoor environment where the drone to be located is located, the process includes:

[0013] Acquire light pixel data collected by the optical flow sensor in the UAV, and convert the light pixel data into three-axis velocity based on the Lucas_Kanade optical flow algorithm;

[0014] The distance the drone flies is determined by integrating the three-axis velocity, and the location coordinates of the drone are determined based on the distance.

[0015] Optionally, the step of transmitting multiple location coordinates corresponding to the UAV to a positioning data fusion center, and constructing a Gaussian function model corresponding to the multiple location coordinates based on the multiple location coordinates corresponding to the UAV, includes:

[0016] In response to the instruction to construct a Gaussian function model, multiple position coordinates of the UAV at the same location are obtained. These position coordinates are determined by the position coordinates obtained from the optical flow sensor and the two-dimensional position coordinates obtained from multiple Bluetooth beacons.

[0017] Construct a Gaussian function model corresponding to the multiple position coordinates of the same location.

[0018] Optionally, the step of processing the Gaussian function model based on the Bayesian fusion theory model to determine the corresponding positioning coordinates of the UAV includes:

[0019] Based on the Bayesian fusion theory model, the Gaussian function models corresponding to multiple position coordinates are fused to calculate and determine the position coordinates of the UAV with the highest probability at the current moment.

[0020] Optionally, after responding to the drone positioning command and obtaining multiple Bluetooth beacons in the indoor environment where the drone to be located is located, the process includes:

[0021] The drone receives two Bluetooth beacons and calculates the corresponding position coordinates of the drone based on the magnetic compass information in the drone and the indoor coordinate system after zero-point offset.

[0022] Optionally, the step of determining the azimuth information between the drone and the Bluetooth beacon, and determining multiple position coordinates of the drone based on the azimuth information and the AOA positioning model, includes:

[0023] The drone acquires three or more Bluetooth beacons to determine the coordinates and radius of the fixed circle in the AOA positioning model;

[0024] The corresponding position coordinates of the UAV are determined based on the coordinates and radius of the fixed circle in the AOA positioning model.

[0025] Optionally, the step of processing the Gaussian function model based on the Bayesian fusion theory model to determine the corresponding positioning coordinates of the UAV includes:

[0026] In response to the position coordinate iteration command, the system calculates the corresponding positioning coordinate decision threshold of the UAV based on the iterative algorithm, determines the iterated positioning coordinates, and completes the indoor positioning of the UAV.

[0027] An indoor positioning device for unmanned aerial vehicles (UAVs) provided for another purpose of this application includes:

[0028] The Bluetooth beacon identification module is configured to respond to drone positioning commands and acquire multiple Bluetooth beacons in the indoor environment where the drone to be located is located.

[0029] The position coordinate determination module is configured to determine the azimuth information between the UAV and the Bluetooth beacon, and based on the azimuth information, determine multiple position coordinates corresponding to the UAV according to the AOA positioning model.

[0030] The Gaussian model construction module is configured to transmit multiple position coordinates corresponding to the UAV to the positioning data fusion center, and construct a Gaussian function model corresponding to the multiple position coordinates based on the multiple position coordinates corresponding to the UAV.

[0031] The UAV positioning module is configured to process the Gaussian function model based on the Bayesian fusion theory model to determine the corresponding positioning coordinates of the UAV, thereby completing the indoor positioning of the UAV.

[0032] An electronic device provided for another purpose of this application includes a central processing unit and a memory, the central processing unit being configured to invoke and run a computer program stored in the memory to perform the steps of the UAV indoor positioning method of this application.

[0033] A computer-readable storage medium is provided for another purpose of this application, which stores, in the form of computer-readable instructions, a computer program implemented according to the UAV indoor positioning method, which, when invoked by a computer, executes the steps included in the corresponding method.

[0034] Compared to existing technologies, this application addresses the problems of low positioning accuracy of existing GPS positioning schemes due to the influence of external environment, inability to achieve accurate indoor positioning, susceptibility of traditional camera positioning schemes to lighting conditions leading to inaccurate positioning, and the bulky size and high power consumption of binocular cameras and host computer devices. This application provides, but is not limited to, the following beneficial effects:

[0035] Firstly, this application obtains multiple position coordinate information of the UAV through calculation and processing, and then fuses these position coordinate information data based on Bayesian theory to determine its precise coordinate position and obtain system stability information, which can greatly improve the accuracy of indoor positioning, and is low in cost, highly automated, and can meet engineering needs.

[0036] Secondly, this application does not require a CPU with high computing power and can achieve good positioning results indoors, which can greatly reduce the time consumption of the positioning algorithm, realize the accuracy and real-time performance of UAV indoor positioning, and avoid the problem of inaccurate indoor positioning caused by the small indoor space and complex environment. Attached Figure Description

[0037] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein:

[0038] Figure 1 This is an exemplary network architecture used in the UAV indoor positioning method of this application;

[0039] Figure 2 This is a diagram showing the angle values ​​when the drone detects two Bluetooth signals in an embodiment of this application.

[0040] Figure 3 This is a mathematical schematic diagram of the Bayesian fusion algorithm involved in the embodiments of this application.

[0041] Figure 4 This is a schematic diagram illustrating the Bluetooth arrangement and distribution and the drone signal reception in the embodiments of this application;

[0042] Figure 5 This is a schematic block diagram of the indoor positioning device for unmanned aerial vehicles (UAVs) in the embodiments of this application;

[0043] Figure 6 This is a schematic diagram of the structure of the computer device in the embodiments of this application. Detailed Implementation

[0044] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain this application, and should not be construed as limiting this application.

[0045] Those skilled in the art will understand that, unless specifically stated otherwise, the singular forms “a,” “an,” “the,” and “the” used herein may also include the plural forms. It should be further understood that the term “comprising” as used in this application means the presence of the stated features, integers, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof. It should be understood that when we say an element is “connected” or “coupled” to another element, it can be directly connected or coupled to the other element, or there may be intermediate elements. Furthermore, “connected” or “coupled” as used herein can include wireless connections or wireless coupling. The term “and / or” as used herein includes all or any units and all combinations of one or more associated listed items.

[0046] It will be understood by those skilled in the art that, unless otherwise defined, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains. It should also be understood that terms such as those defined in general dictionaries should be understood to have the same meaning as in the context of the prior art, and should not be interpreted in an idealized or overly formal sense unless specifically defined as herein.

[0047] Those skilled in the art will understand that the terms "client," "terminal," and "terminal device" as used herein include both devices that receive wireless signals, devices that only possess wireless signal receiver capabilities without transmission capabilities, and devices with receiving and transmitting hardware, devices that have receiving and transmitting hardware capable of bidirectional communication over a bidirectional communication link. Such devices may include: cellular or other communication devices such as personal computers or tablets, having single-line displays, multi-line displays, or cellular or other communication devices without multi-line displays; PCS (Personal Communications Service) that can combine voice, data processing, fax, and / or data communication capabilities; PDA (Personal Digital Assistant) that may include a radio frequency receiver, pager, internet / intranet access, web browser, notepad, calendar, and / or GPS (Global Positioning System) receiver; and conventional laptops and / or handheld computers or other devices that have and / or include radio frequency receivers. As used herein, "client," "terminal," and "terminal device" can be portable, transportable, installed in a means of transportation (air, sea, and / or land), or suitable and / or configured to operate locally and / or in a distributed manner, operating in any other location on Earth and / or in space. "Client," "terminal," and "terminal device" as used herein can also be a communication terminal, an internet access terminal, or a music / video playback terminal, such as a PDA, a MID (Mobile Internet Device), and / or a mobile phone with music / video playback capabilities, or a smart TV, set-top box, etc.

[0048] The hardware referred to by the names "server," "client," and "service node" in this application is essentially an electronic device with the equivalent capabilities of a personal computer. It is a hardware device with the necessary components revealed by the von Neumann architecture, such as a central processing unit (including an arithmetic logic unit and a control unit), memory, input devices, and output devices. The computer program is stored in its memory, and the central processing unit loads the program stored in the secondary storage into the main memory to run it, execute the instructions in the program, and interact with the input and output devices to complete specific functions.

[0049] It should be noted that the concept of "server" used in this application can also be extended to the case of server clusters. Based on the network deployment principles understood by those skilled in the art, the servers should be logically divided. Physically, these servers can be independent of each other but accessible through interfaces, or they can be integrated into a single physical computer or a computer cluster. Those skilled in the art should understand this flexibility and should not use it to constrain the implementation of the network deployment method in this application.

[0050] One or more of the technical features of this application, unless explicitly specified herein, can be deployed on a server and accessed by a client remotely calling the online service interface provided by the server, or can be directly deployed and run on a client for access.

[0051] Unless otherwise specified, the neural network models referenced or potentially referenced in this application may be deployed on a remote server and invoked remotely on the client, or deployed on a client with the capability to invoke directly. In some embodiments, when running on the client, the corresponding intelligence may be acquired through transfer learning in order to reduce the requirements on the client's hardware resources and avoid excessive consumption of the client's hardware resources.

[0052] Unless otherwise specified, all data involved in this application may be stored remotely on a server or on a local terminal device, as long as it is suitable for use by the technical solution of this application.

[0053] Those skilled in the art will understand that although the various methods in this application are described based on the same concept and thus present commonality among them, they can be performed independently unless otherwise specified. Similarly, the various embodiments disclosed in this application are all based on the same inventive concept; therefore, concepts expressed in the same way, as well as concepts that are appropriately changed for convenience but are expressed differently, should be understood equivalently.

[0054] Unless otherwise expressly stated, the various embodiments disclosed in this application can be combined in a cross-cutting manner to flexibly construct new embodiments, as long as such combination does not depart from the inventive spirit of this application and can meet the needs of the prior art or solve a certain deficiency in the prior art. Those skilled in the art should be aware of such modifications.

[0055] Based on the above exemplary scenarios, please refer to Figure 1 In one embodiment of the UAV indoor positioning method of this application, the method includes:

[0056] Step S10: Respond to the drone positioning command and obtain multiple Bluetooth beacons in the indoor environment where the drone to be located is located;

[0057] In some embodiments, the Bluetooth beacon is a Bluetooth positioning beacon. The drone to be located may be equipped with an IMU six-axis sensor, a three-axis magnetic compass, an optical flow sensor, an altitude sensor, and a Bluetooth receiver, etc. The indoor environment where the drone to be located is located may be equipped with several Bluetooth positioning beacons with defined location coordinates, and a Bluetooth mesh network may be established, while the positioning system information is synchronized in the network.

[0058] Specifically, the terminal device can respond to the drone positioning command and obtain multiple Bluetooth beacons in the indoor environment where the drone is located. During the flight of the drone, the Bluetooth receiver installed on the drone will receive information from multiple Bluetooth beacons in real time.

[0059] Step S20: Determine the azimuth information between the UAV and the Bluetooth beacon, and determine multiple position coordinates of the UAV based on the azimuth information and the AOA positioning model;

[0060] After receiving information from multiple Bluetooth beacons in real time, the Bluetooth receiver mounted on the drone determines the azimuth information between the drone and the Bluetooth beacons, and determines the corresponding multiple position coordinates of the drone based on the azimuth information and the AOA positioning model.

[0061] In some embodiments, the AOA positioning model is an Angle-of-Arrival (AOA) model. Positioning algorithms based on the angle of arrival (AOA) are typical ranging-based positioning algorithms. In wireless sensor network applications, AOA is a common positioning algorithm for network node self-localization, characterized by low cost and high positioning accuracy. It primarily involves detecting the direction of arrival of the transmitted signal through application firmware, and then, based on the intersecting angle between the receiving node and the originating node, using triangulation or other angular measurements to deduce the location of any unknown nodes within the transmitted signal.

[0062] The Bluetooth receiver on the drone acquires three or more Bluetooth beacons and determines the coordinates and radius of the fixed circle of the AOA positioning model; based on the coordinates and radius of the fixed circle of the AOA positioning model, the corresponding position coordinates of the drone are determined.

[0063] Specifically, please refer to Figure 2 If the Bluetooth receiver in the UAV simultaneously receives three or more Bluetooth beacon signals, the orientation angle information is processed based on the AOA positioning model to determine multiple corresponding position coordinates of the UAV. The specific formula is as follows:

[0064]

[0065]

[0066] In the above formulas (1) and (2), formula (1) is used to determine the coordinates and radii of the three fixed circles in the AOA positioning model. After determining the coordinates and radii of the three fixed circles, formula (2) is used to determine the current position information of the UAV based on the coordinates and radii of the three fixed circles. In formula (2), (xnow, ynow) represents the current position coordinates of the UAV.

[0067] In some embodiments, the drone receives two Bluetooth beacons and calculates and determines the corresponding position coordinates of the drone based on the magnetic compass information in the drone and the indoor coordinate system after zero-point offset.

[0068] Specifically, if a drone receives two Bluetooth beacon signals simultaneously, its coordinates need to be calculated by combining the information from the drone's magnetic compass with the indoor coordinate system after zero-point offset. The calculation method is as follows:

[0069]

[0070] Please see Figure 2 In the formula, α1 and α2 are the orientation angles jointly determined by the Bluetooth beacon and the magnetic compass. The red arrow represents the drone's orientation angle, which needs to be considered in conjunction with the indoor coordinate system reference established for positioning. Whether a negative sign should be added before the Bluetooth orientation angle depends on the drone's different orientation angles.

[0071] Step S30: Transmit the multiple location coordinates corresponding to the UAV to the positioning data fusion center, and construct a Gaussian function model corresponding to the multiple location coordinates based on the multiple location coordinates corresponding to the UAV.

[0072] In some embodiments, the terminal device on the drone can respond to the Gaussian function model construction instruction, obtain multiple position coordinates of the same location of the drone, and transmit the multiple position coordinates corresponding to the drone to the positioning data fusion center. The multiple position coordinates corresponding to the drone can be determined by the position coordinates obtained by the optical flow sensor and the two-dimensional position coordinates obtained by multiple Bluetooth beacons. A Gaussian function model corresponding to the multiple position coordinates is constructed based on the multiple position coordinates of the same location.

[0073] After obtaining multiple location coordinates of the UAV corresponding to the optical flow from the optical flow sensor and the Bluetooth beacon, a Gaussian function model corresponding to the multiple location coordinates is constructed based on the multiple location coordinates of the same location. The actual location of the UAV is described by a Gaussian distribution function, and its expression is as follows:

[0074]

[0075] In the formula, x is a two-dimensional vector, ∑ is the covariance of x, and μ is the observed coordinate matrix (x,y).

[0076] Step S40: Process the Gaussian function model based on the Bayesian fusion theory model to determine the corresponding positioning coordinates of the UAV, so as to complete the indoor positioning of the UAV.

[0077] After determining the Gaussian function models corresponding to multiple position coordinates of the same location of the UAV, the Gaussian function models are processed based on the Bayesian fusion theory model. It is necessary to find the position coordinates with the highest probability in multiple position coordinate domains, and use the Bayesian fusion theory model to calculate the position where the UAV has the highest probability of appearing, and determine the corresponding positioning coordinates of the UAV to complete the indoor positioning of the UAV.

[0078] In some embodiments, based on the Bayesian fusion theory model and using the maximum a posteriori probability fusion criterion, the main formula is expressed as follows:

[0079]

[0080]

[0081]

[0082]

[0083] In the above formulas (3), (4), (5), and (6), formulas (3) and (4) are two-dimensional Gaussian distribution functions of single-location observations, and the p-value in the Bayesian fusion model is taken as... i (z i H1) is a Gaussian function constructed based on the current drone position, with p... i (z i |H0) is a Gaussian function constructed from the previous verification position of the UAV.

[0084] Formulas (5) and (6) represent the Bayesian fusion function, where k is the number of location observation functions, and u = (u1, u2, u3, ..., uN). i =1 indicates that the location information determines it to be H1, u i =0 indicates that the location information is determined as H0.

[0085] Combining the detection probability and false detection probability of each location information, a binary hypothesis judgment formula is given as follows:

[0086]

[0087] Where u0 = 1 indicates that H1 and C have been determined. F To mitigate the risk of false detections in Bayesian methods, C D To detect risks using Bayesian methods.

[0088] Please see Figure 3 All points that are determined to be H1 are Figure 3 On the plane in which C is located, in the set of these points, C F P(u|H0)-C D The smaller the value of P(u|H1), the higher the probability of falling into H1. Substituting the coordinate vector (x0, y0) corresponding to the u position information of the minimum value back into the Gaussian function yields the current maximum probability coordinates of the UAV through the Bayesian fusion model, denoted as (x0, y0). f ,y f These points should be in Figure 3 On the plane in the middle.

[0089] In some embodiments, the stability of a system is assessed through the system's Bayesian risk, and its calculation method is expressed as follows:

[0090]

[0091] In some embodiments, please refer to Figure 4 Bluetooth is strategically distributed indoors to form a mesh network, with the gray area representing the range within which the drone can receive Bluetooth signals. The drone's location coordinates and relevant information from the Bayesian fusion system are synchronized in real-time via the Bluetooth mesh network. This flexible information enhances system performance.

[0092] In some embodiments, the Bluetooth mesh network monitors the drone's coordinates to control Bluetooth power consumption within the network and optimize its own positioning data. When the drone does not pass through certain Bluetooth beacon areas, it can control the Bluetooth beacons in those areas to enter low-power mode. Simultaneously, it optimizes subsequent positioning data by monitoring changes in their Bayesian risk in real time. F C D The weighting of the values ​​is adjusted to achieve a more accurate positioning effect.

[0093] In some embodiments, the positioning system needs to ensure that the Bluetooth receiver on the drone is oriented stably and that the optical flow sensor is oriented perpendicular to the ground. A small stabilizing gimbal can be installed on the drone to correct the real-time orientation of the Bluetooth and optical flow sensors by constantly reading the quaternion information on the drone.

[0094] As can be seen from the above embodiments, compared with the prior art, this application addresses the problems of low positioning accuracy of GPS positioning schemes due to the influence of the external environment, inability to achieve accurate indoor positioning, susceptibility of traditional camera positioning schemes to lighting conditions leading to inaccurate positioning, and the large size and high power consumption of binocular cameras and host computer devices. This application has, but is not limited to, the following beneficial effects:

[0095] Firstly, this application obtains multiple position coordinate information of the UAV through calculation and processing, and then fuses these position coordinate information data based on Bayesian theory to determine its precise coordinate position and obtain system stability information, which can greatly improve the accuracy of indoor positioning, and is low in cost, highly automated, and can meet engineering needs.

[0096] Secondly, this application does not require a CPU with high computing power and can achieve good positioning results indoors, which can greatly reduce the time consumption of the positioning algorithm, realize the accuracy and real-time performance of UAV indoor positioning, and avoid the problem of inaccurate indoor positioning caused by the small indoor space and complex environment.

[0097] Based on any embodiment of this application, after the step of obtaining multiple Bluetooth beacons in the indoor environment where the drone to be located is located in response to the drone positioning command, the method includes:

[0098] Acquire light pixel data collected by the optical flow sensor in the UAV, and convert the light pixel data into three-axis velocity based on the Lucas_Kanade optical flow algorithm;

[0099] The distance the drone flies is determined by integrating the three-axis velocity, and the location coordinates of the drone are determined based on the distance.

[0100] Specifically, the optical flow sensor is placed under the drone for positioning. It calculates speed based on changes in ambient light. The light pixel data is collected and determined by the optical flow sensor. Then, based on the Lucas_Kanade optical flow algorithm, the speed of the drone is calculated and determined based on the light pixel data. The speed of the drone is integrated to determine the distance the drone has flown, and the location coordinates of the drone are determined based on the distance.

[0101] In some embodiments, the Lucas–Kanade optical flow algorithm is a two-frame difference optical flow estimation algorithm. It was proposed by Bruce D. Lucas and Takeo Kanade. The concept of optical flow (or optic flow) is a motion pattern referring to the apparent movement of an object, surface, or edge between an observer (e.g., eye, camera) and the background from a given viewpoint. Optical flow techniques, such as motion detection and image segmentation, temporal collision, motion compensation coding, and 3D stereo parallax, all utilize this edge or surface motion. The movement of a 2D image relative to the observer is the projection of the movement of a 3D object onto the image plane. For ordered images, the instantaneous image rate or discrete image transfer of a 2D image can be estimated. Optical flow algorithms evaluate the deformation between two images, based on the fundamental assumptions of voxel and image pixel conservation. It assumes that the color of an object does not change significantly between consecutive frames. Based on this idea, image constraint equations can be derived. Different optical flow algorithms address optical flow problems with different additional assumptions.

[0102] In some embodiments, the ray pixel data obtained by the optical flow sensor is converted into three-axis velocity using the Lucas-Kanade algorithm, thereby obtaining the real-time coordinates of the UAV. The specific conversion formula of the Lucas-Kanade algorithm is as follows:

[0103]

[0104] In the formula, I(x,y,z) is the pixel of the image signal at position (x,y,z).

[0105] Based on any embodiment of this application, the step of transmitting multiple location coordinates corresponding to the UAV to a positioning data fusion center, and constructing a Gaussian function model corresponding to the multiple location coordinates based on the multiple location coordinates corresponding to the UAV, includes:

[0106] In response to the instruction to construct a Gaussian function model, multiple position coordinates of the UAV at the same location are obtained. These position coordinates are determined by the position coordinates obtained from the optical flow sensor and the two-dimensional position coordinates obtained from multiple Bluetooth beacons.

[0107] Construct a Gaussian function model corresponding to the multiple position coordinates of the same location.

[0108] Specifically, after obtaining multiple position coordinates of the UAV corresponding to the optical flow from the optical flow sensor and the Bluetooth beacon, a Gaussian function model corresponding to the multiple position coordinates is constructed based on the multiple position coordinates of the same location. The actual location of the UAV is described by a Gaussian distribution function, and its expression is as follows:

[0109]

[0110] In the formula, x is a two-dimensional vector, ∑ is the covariance of x, and μ is the observed coordinate matrix (x,y).

[0111] Based on any embodiment of this application, the step of processing the Gaussian function model based on the Bayesian fusion theory model to determine the corresponding positioning coordinates of the UAV includes:

[0112] Based on the Bayesian fusion theory model, the Gaussian function models corresponding to multiple position coordinates are fused to calculate and determine the position coordinates of the UAV with the highest probability at the current moment.

[0113] Based on any embodiment of this application, after the step of obtaining multiple Bluetooth beacons in the indoor environment where the drone to be located is located in response to the drone positioning command, the method includes:

[0114] The drone receives two Bluetooth beacons and calculates the corresponding position coordinates of the drone based on the magnetic compass information in the drone and the indoor coordinate system after zero-point offset.

[0115] Specifically, if a drone receives two Bluetooth beacon signals simultaneously, its coordinates need to be calculated by combining the information from the drone's magnetic compass with the indoor coordinate system after zero-point offset. The calculation method is as follows:

[0116]

[0117] In the formula, α1 and α2 are the orientation angles jointly determined by the Bluetooth beacon and the magnetic compass. The red arrow represents the drone's orientation angle, which needs to be considered in conjunction with the indoor coordinate system reference established for positioning. Whether a negative sign should be added before the Bluetooth orientation angle depends on the drone's different orientation angles.

[0118] Based on any embodiment of this application, the step of determining the azimuth information between the UAV and the Bluetooth beacon, and determining multiple position coordinates corresponding to the UAV based on the azimuth information and the AOA positioning model, includes:

[0119] The drone acquires three or more Bluetooth beacons to determine the coordinates and radius of the fixed circle in the AOA positioning model;

[0120] The corresponding position coordinates of the UAV are determined based on the coordinates and radius of the fixed circle in the AOA positioning model.

[0121] Specifically, if the Bluetooth receiver in the drone simultaneously receives three or more Bluetooth beacon signals, the orientation angle information is processed based on the AOA positioning model to determine multiple corresponding position coordinates of the drone. The specific formula is as follows:

[0122]

[0123]

[0124] In the above formulas (1) and (2), formula (1) is used to determine the coordinates and radii of the three fixed circles in the AOA positioning model. After determining the coordinates and radii of the three fixed circles, formula (2) is used to determine the current position information of the UAV based on the coordinates and radii of the three fixed circles. In formula (2), (xnow, ynow) represents the current position coordinates of the UAV.

[0125] Based on any embodiment of this application, the step of processing the Gaussian function model based on the Bayesian fusion theory model to determine the corresponding positioning coordinates of the UAV includes:

[0126] In response to the position coordinate iteration command, the system calculates the corresponding positioning coordinate decision threshold of the UAV based on the iterative algorithm, determines the iterated positioning coordinates, and completes the indoor positioning of the UAV.

[0127] In some embodiments, the decision threshold T needs to be iterated through multiple times using the position coordinate information obtained by the UAV to improve the stability and reliability of the positioning system. The iterative calculation method is expressed as follows:

[0128]

[0129]

[0130]

[0131]

[0132] Iterate until The output can then be the iteration result.

[0133] As can be seen from the above embodiments, this application does not require a CPU with high computing power and can achieve good positioning results indoors. It can greatly reduce the time consumption of the positioning algorithm, realize the accuracy and real-time performance of UAV indoor positioning, and avoid the problem of inaccurate indoor positioning caused by the small indoor space and complex environment.

[0134] Please see Figure 5 This application provides an indoor drone positioning device, comprising a Bluetooth beacon determination module 1100, a position coordinate determination module 1200, a Gaussian model construction module 1300, and a drone positioning module 1400, for one of the purposes of this application. The Bluetooth beacon determination module 1100 is configured to respond to a drone positioning command and acquire multiple Bluetooth beacons in the indoor environment where the drone is located. The position coordinate determination module 1200 is configured to determine the azimuth information between the drone and the Bluetooth beacons, and based on the azimuth information, determine multiple position coordinates corresponding to the drone according to an AOA positioning model. The Gaussian model construction module 1300 is configured to transmit the multiple position coordinates corresponding to the drone to a positioning data fusion center, and construct a Gaussian function model corresponding to the multiple position coordinates. The drone positioning module 1400 is configured to process the Gaussian function model based on a Bayesian fusion theory model to determine the corresponding positioning coordinates of the drone, thereby completing the indoor positioning of the drone.

[0135] Based on any embodiment of this application, please refer to Figure 6 Another embodiment of this application also provides an electronic device, which can be implemented by a computer device, such as... Figure 6 The diagram shows the internal structure of a computer device. The computer device includes a processor, a computer-readable storage medium, a memory, and a network interface connected via a system bus. The computer-readable storage medium stores an operating system, a database, and computer-readable instructions. The database may store a sequence of control information. When the computer-readable instructions are executed by the processor, the processor can implement a UAV indoor positioning method. The processor of the computer device provides computing and control capabilities, supporting the operation of the entire computer device. The memory of the computer device may store computer-readable instructions. When the computer-readable instructions are executed by the processor, the processor can execute the UAV indoor positioning method of this application. The network interface of the computer device is used for communication with a terminal. Those skilled in the art will understand that… Figure 6 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0136] In this embodiment, the processor is used to execute... Figure 5The system contains the specific functions of each module and its sub-modules. The memory stores the program code and various data required to execute these modules or sub-modules. The network interface is used for data transmission between the user terminal and the server. In this embodiment, the memory stores the program code and data required to execute all modules / sub-modules in the UAV indoor positioning device of this application. The server can call the server's program code and data to execute the functions of all sub-modules.

[0137] This application also provides a storage medium storing computer-readable instructions, which, when executed by one or more processors, cause the one or more processors to perform the steps of the UAV indoor positioning method described in any embodiment of this application.

[0138] This application also provides a computer program product, including a computer program / instructions that, when executed by one or more processors, implement the steps of the UAV indoor positioning method described in any embodiment of this application.

[0139] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments of this application can be implemented by a computer program instructing related hardware. This computer program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the methods described above. The aforementioned storage medium can be a magnetic disk, optical disk, read-only memory (ROM), or random access memory (RAM), etc.

[0140] The above description is only a partial embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

[0141] In summary, this application does not require a CPU with high computing power and can achieve good positioning results indoors. It can greatly reduce the time consumption of positioning algorithms, realize the accuracy and real-time performance of UAV indoor positioning, and avoid the problem of inaccurate indoor positioning caused by the small indoor space and complex environment.

Claims

1. A method for indoor positioning of a drone, the method comprising: include: In response to the drone positioning command, acquire multiple Bluetooth beacons in the indoor environment where the drone to be located is located; Acquire light pixel data collected by the optical flow sensor in the UAV, and convert the light pixel data into three-axis velocity based on the Lucas_Kanade optical flow algorithm; The distance flown by the drone is determined by integrating the three-axis velocities, and the location coordinates of the drone are determined based on the distance. Determine the azimuth information between the drone and the Bluetooth beacon, and based on the azimuth information, determine multiple position coordinates of the drone according to the AOA positioning model; The multiple location coordinates corresponding to the UAV are transmitted to the positioning data fusion center. The actual location of the UAV is described using a Gaussian distribution function. Based on the multiple location coordinates corresponding to the UAV, a Gaussian function model corresponding to the multiple location coordinates is constructed, which includes: In response to the instruction to construct a Gaussian function model, multiple position coordinates of the UAV at the same location are obtained. These position coordinates are determined by the position coordinates obtained from the optical flow sensor and the two-dimensional position coordinates obtained from multiple Bluetooth beacons. Construct a Gaussian function model corresponding to the multiple position coordinates based on the multiple position coordinates of the same location; The Gaussian function model is processed based on the Bayesian fusion theory model to determine the corresponding positioning coordinates of the UAV, thereby completing the UAV's indoor positioning. 2.The indoor positioning method of claim 1, wherein, The steps for processing the Gaussian function model based on the Bayesian fusion theory model to determine the corresponding positioning coordinates of the UAV include: Based on the Bayesian fusion theory model, the Gaussian function models corresponding to multiple position coordinates are fused to calculate and determine the position coordinates of the UAV with the highest probability at the current moment. 3.The indoor positioning method of claim 1, wherein, After responding to the drone positioning command and obtaining multiple Bluetooth beacons in the indoor environment where the drone to be located is located, the process includes: The drone receives two Bluetooth beacons and calculates the corresponding position coordinates of the drone based on the magnetic compass information in the drone and the indoor coordinate system after zero-point offset. 4.The indoor positioning method of claim 1, wherein, The steps of determining the azimuth information between the drone and the Bluetooth beacon, and determining multiple position coordinates of the drone based on the azimuth information and an AOA positioning model, include: The drone acquires three or more Bluetooth beacons to determine the coordinates and radius of the fixed circle in the AOA positioning model; The corresponding position coordinates of the UAV are determined based on the coordinates and radius of the fixed circle in the AOA positioning model.

5. The indoor positioning method of claim 1 to 4, wherein, The steps for processing the Gaussian function model based on the Bayesian fusion theory model to determine the corresponding positioning coordinates of the UAV include: In response to the position coordinate iteration command, the system calculates the corresponding positioning coordinate decision threshold of the UAV based on the iterative algorithm, determines the iterated positioning coordinates, and completes the indoor positioning of the UAV.

6. An indoor positioning device for unmanned aerial vehicles (UAVs), characterized in that, include: The Bluetooth beacon determination module is configured to respond to the drone positioning command, acquire multiple Bluetooth beacons in the indoor environment where the drone to be located is located; acquire light pixel data collected by the optical flow sensor in the drone, and convert the light pixel data into three-axis velocity based on the Lucas_Kanade optical flow algorithm; The distance flown by the drone is determined by integrating the three-axis velocities, and the location coordinates of the drone are determined based on the distance. The position coordinate determination module is configured to determine the azimuth information between the UAV and the Bluetooth beacon, and based on the azimuth information, determine multiple position coordinates corresponding to the UAV according to the AOA positioning model. The Gaussian model construction module is configured to transmit multiple location coordinates corresponding to the UAV to the positioning data fusion center, describe the actual location of the UAV using a Gaussian distribution function, and construct a Gaussian function model corresponding to the multiple location coordinates based on the multiple location coordinates of the UAV, which includes: In response to the instruction to construct a Gaussian function model, multiple position coordinates of the UAV at the same location are obtained. These position coordinates are determined by the position coordinates obtained from the optical flow sensor and the two-dimensional position coordinates obtained from multiple Bluetooth beacons. Construct a Gaussian function model corresponding to the multiple position coordinates based on the multiple position coordinates of the same location; The UAV positioning module is configured to process the Gaussian function model based on the Bayesian fusion theory model to determine the corresponding positioning coordinates of the UAV, thereby completing the indoor positioning of the UAV.

7. An electronic device comprising a central processing unit and a memory, characterized in that, The central processing unit is used to invoke and run a computer program stored in the memory to perform the steps of the method as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, It stores, in the form of computer-readable instructions, a computer program implemented according to any one of claims 1 to 5, which, when invoked by a computer, executes the steps included in the corresponding method.

Images