Unmanned aerial vehicle positioning system and method based on multi-source position signal fusion

Abstract

The invention discloses an unmanned aerial vehicle positioning system and method based on multi-source position signal fusion, and relates to the technical field of unmanned aerial vehicle positioning, and the system comprises a plurality of positioning data collection units which are carried on an unmanned aerial vehicle, and each type is specially used for collecting positioning data of a single source; the positioning data processing unit is suitable for calculating a confidence coefficient value based on the attribute parameter of each positioning data, and determining a weight of each positioning data according to the confidence coefficient value; and the positioning data fusion unit is suitable for fusing all the positioning data by applying a fusion algorithm and combining the weights of the positioning data to generate fused positioning data. According to the system, the confidence of each source positioning data is evaluated in real time, and the fusion weight is dynamically optimized according to the confidence, so that the dynamic evaluation and optimal fusion of the multi-source positioning data are realized, and the positioning precision and reliability of the unmanned aerial vehicle in a complex environment are improved.

Description

Technical Field

[0001] This invention relates to the field of unmanned aerial vehicle (UAV) positioning, and specifically to a UAV positioning system and method based on multi-source location signal fusion. Background Technology

[0002] With the large-scale application of drones in logistics inspection, disaster relief, and agricultural plant protection, high-precision and high-reliability positioning has become a core requirement for ensuring their safe operation. Traditional drone positioning systems mainly rely on a single data source, such as the Global Navigation Satellite System (GNSS). However, GNSS signals are susceptible to building obstruction, electromagnetic interference, and multipath effects, resulting in a sharp drop in positioning accuracy or even complete failure in complex environments such as urban canyons, indoor spaces, or dense forests.

[0003] To improve robustness, existing technologies attempt to introduce multi-source positioning data fusion schemes, such as: loosely coupled fusion: merging GNSS and inertial navigation system (INS) data through Kalman filtering, but INS has accumulated errors and positioning diverges rapidly when GNSS fails for a long time; tightly coupled fusion: deeply fusing visual odometry (VIO) or ultra-wideband (UWB) data with GNSS / INS, which can alleviate single-point failures, but still has significant drawbacks: static weight allocation: most systems use fixed weights to fuse data from each source (e.g., preset GNSS weight > VIO), which cannot dynamically respond to environmental changes (e.g., the weight should be reduced when GNSS loses lock); unquantified data reliability: ignoring real-time quality differences between data sources (e.g., a sharp drop in GNSS accuracy due to a decrease in the number of satellites), resulting in low-confidence data contaminating the fusion results; spatiotemporal misalignment: asynchronous timestamps and inconsistent coordinate systems / units between multiple source data (e.g., GNSS uses WGS-84, visual data uses a local coordinate system), directly introducing systematic biases into the fusion.

[0004] Furthermore, existing solutions lack sufficient tolerance for abnormal positioning data. For example, when some members of a drone swarm experience pose changes due to interference, directly using their data from neighboring drones will trigger cascading positioning errors. Although some studies have attempted to detect anomalies based on distance thresholds, they do not consider the joint anomaly determination of multiple attribute parameters (such as speed consistency and sensor health status), resulting in a high false positive rate.

[0005] Therefore, there is an urgent need for an adaptive and robust multi-source fusion positioning system. Summary of the Invention

[0006] In view of the above problems, the present invention is proposed to provide a UAV positioning system and method based on multi-source location signal fusion to overcome or at least partially solve the above problems.

[0007] According to one aspect of the present invention, a UAV positioning system based on multi-source location signal fusion is provided, comprising: multiple positioning data acquisition units mounted on a UAV, each positioning data acquisition unit being dedicated to acquiring positioning data from a single source, including: Global Navigation Satellite System, Real-time Dynamic Positioning, Inertial Navigation System, Visual Inertial Odometry, Ultra-Wideband Positioning, and Synchronous Positioning and Mapping; a positioning data processing unit adapted to calculate the confidence value of each positioning data based on attribute parameters, and determine the weight of each positioning data according to the confidence value; and a positioning data fusion unit adapted to apply a fusion algorithm, combining the weights of each positioning data, to fuse all positioning data and generate fused positioning data.

[0008] Optionally, in the positioning system according to the present invention, the attribute parameters include quality parameters, error parameters, historical parameters, and environmental parameters. The quality parameters indicate the signal strength and clarity of the positioning data, the error parameters indicate the offset of the positioning data from the historical trajectory or external truth value, the historical parameters indicate the reliability of the positioning data within a pre-preset time period, and the environmental parameters indicate the degree to which the positioning data is affected by the external environment.

[0009] Optionally, in the positioning system according to the present invention, the confidence value of each positioning data is calculated according to the following formula: Confidence_i = w1 × Quality_i + w2 × (1 - Error_i) + w3 × History_i + w4 × Env_i; Where Confidence_i is the confidence value of the i-th location data, Quality_i is the quality parameter of the i-th location data, w1 is the weight of the quality parameter, Error_i is the error parameter of the i-th location data, w2 is the weight of the error parameter, History_i is the historical parameter of the i-th location data, w3 is the weight of the historical parameter, Eev_i is the environmental parameter of the i-th location data, and w4 is the weight of the environmental parameter.

[0010] Optionally, in the positioning system according to the present invention, the positioning data processing unit integrates a pre-trained confidence model and is also adapted to obtain the corresponding confidence value by inputting the attribute parameters of each positioning data into the confidence model for processing.

[0011] Optionally, the positioning system according to the present invention further includes: a model self-feedback unit, adapted to train the confidence model using fused positioning data as training data and external ground truth as test data, wherein the external ground truth indicates the positioning data collected by the ground base station.

[0012] Optionally, in the positioning system according to the present invention, the positioning data processing unit is further adapted to calculate anomaly scores based on the attribute parameters of each positioning data, and to remove the corresponding positioning data or reduce the weight of the corresponding positioning data when the anomaly score is greater than a threshold.

[0013] Optionally, in the positioning system according to the invention, the anomaly score is the sum of the anomaly sub-scores, each sub-score being determined by the parameter residuals of the UAV and neighboring UAVs on the same attribute.

[0014] Optionally, in the positioning system according to the present invention, the positioning data processing unit is further adapted to preprocess the positioning data, the preprocessing including timestamp alignment and format standardization.

[0015] Optionally, in the positioning system according to the present invention, the fusion algorithm is one of weighted Kalman filtering, adaptive Bayesian fusion, and deep learning fusion.

[0016] According to another aspect of the present invention, a UAV positioning method based on multi-source location signal fusion is provided, comprising: collecting positioning data from different sources, including: Global Navigation Satellite System, Real-time Dynamic Positioning, Inertial Navigation System, Visual Inertial Odometry, Ultra-Wideband Positioning, and Synchronous Positioning and Mapping; calculating the confidence value of each positioning data based on the attribute parameters of each positioning data, and determining the weight of each positioning data according to the confidence value; applying a fusion algorithm, combining the weights of each positioning data, to fuse all positioning data to generate fused positioning data.

[0017] According to another aspect of the present invention, a computing device is provided, comprising: at least one processor; and a memory storing program instructions, wherein the program instructions are configured to be executed by the at least one processor, the program instructions including instructions for performing the methods described above.

[0018] According to another aspect of the present invention, a readable storage medium storing program instructions is provided, which, when read and executed by a computing device, causes the computing device to perform the method described above.

[0019] According to the present invention, by evaluating the confidence level of each source positioning data in real time and dynamically optimizing the fusion weight based on the confidence level, dynamic evaluation and optimal fusion of multi-source positioning data are achieved, thereby improving the positioning accuracy and reliability of UAVs in complex environments.

[0020] According to the present invention, the confidence level of each source is quantified based on the attribute parameters (quality / error / history / environment) of the positioning data, and the fusion weight is dynamically allocated to effectively suppress the impact of low-quality data on the positioning results; by synchronizing the timestamps and unifying the format of multi-source data, system-level deviations are eliminated to ensure the reliability of the fusion input basis; and by identifying abnormal data, the propagation of abnormal data is effectively identified and suppressed.

[0021] According to the present invention, the positioning accuracy and reliability of UAVs in complex environments can be significantly improved; dynamic modeling and adaptive fusion of multi-source signal confidence can be achieved to prevent abnormal signals from affecting positioning; anomaly detection and elimination can be supported to improve system robustness and security; model self-learning and feedback optimization can be supported to continuously improve positioning performance; it is applicable to a variety of UAV application scenarios and has broad promotional value.

[0022] The above description is merely an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention and to implement it in accordance with the contents of the specification, and in order to make the above and other objects, features and advantages of the present invention more apparent and understandable, specific embodiments of the present invention are described below. Attached Figure Description

[0023] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings: Figure 1 A schematic diagram of the structure of an unmanned aerial vehicle (UAV) positioning system 100 based on multi-source location signal fusion according to an embodiment of the present invention is shown. Figure 2 A schematic diagram of a computing device 200 provided according to an embodiment of the present invention is shown; Figure 3 A flowchart of a UAV positioning method 300 based on multi-source location signal fusion according to an embodiment of the present invention is shown. Detailed Implementation

[0024] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

[0025] For complex environments, such as UAV navigation in urban environments with tall buildings, signal obstruction, and severe interference, multi-source signal fusion is used to ensure positioning; UAV swarm flight and mutual reference among multiple UAVs improve overall positioning accuracy and robustness; in emergency rescue / disaster environments, where GNSS is ineffective or interfered with, multi-source fusion and dynamic confidence adjustment are relied upon; and for indoor / underground space flight, in environments without GNSS, UWB, VIO, SLAM, and other signals are fused.

[0026] In these complex environments, UAV positioning mainly relies on single or a few sensors, achieving fusion through simple weighting or filtering. This lack of dynamic modeling and anomaly handling for the confidence levels of each source signal leads to decreased positioning accuracy and reliability in complex environments with signal obstruction, interference, and drift. For example, single GNSS / RTK positioning is susceptible to obstruction, interference, and reflection, and cannot guarantee positioning when these fail; simple GNSS+INS fusion, achieved through methods like Kalman filtering, lacks adaptive handling for abnormal signals and drift; multi-source weighted averaging, with fixed or manually set weights for each source signal, cannot dynamically reflect changes in signal quality; and visual / laser SLAM, usable in environments without GPS, is sensitive to lighting, texture, and dynamic obstacles.

[0027] The above methods suffer from several problems, including the inability to dynamically assess the confidence level of each source signal, leading to abnormal signals affecting the fusion results; the lack of anomaly detection and removal mechanisms, making them susceptible to drift, distortion, and sudden changes; fixed fusion weights that cannot be adaptively adjusted, making it difficult to cope with complex environmental changes; and insufficient positioning accuracy and robustness, affecting the safe operation of UAVs.

[0028] To address the problems existing in the prior art, this invention proposes a solution. This application presents a UAV positioning system based on multi-source location signal fusion. This UAV positioning system is suitable for highly reliable positioning and safe operation of UAVs in complex environments. By real-time evaluation of the confidence level of each source positioning data and dynamic optimization of the fusion weights based on the confidence level, it achieves dynamic evaluation and optimal fusion of multi-source positioning data, thereby improving the positioning accuracy and reliability of UAVs in complex environments.

[0029] In this embodiment, multi-source positioning data refers to the UAV simultaneously receiving position information from multiple sensors or systems, such as Global Navigation Satellite System (GNSS), Real-Time Kinematic (RTK), Inertial Navigation System (INS), Visual-Inertial Odometry (VIO), Ultra Wide Band (UWB), and Simultaneous Localization and Mapping (SLAM).

[0030] Confidence level refers to a quantitative indicator of the degree of trustworthiness of a certain location data, usually expressed as a probability or score.

[0031] Figure 1 A schematic diagram of the structure of an unmanned aerial vehicle (UAV) positioning system 100 based on multi-source location signal fusion according to an embodiment of the present invention is shown.

[0032] like Figure 1 As shown, the UAV positioning system 100 includes multiple positioning data acquisition units 102, positioning data processing units 104, and positioning data fusion units 106.

[0033] Each positioning data acquisition unit 102 is mounted on the UAV. Each type of positioning data acquisition unit is dedicated to acquiring positioning data from a single source, including positioning systems such as GNSS, RTK, INS, VIO, UWB, and SLAM. The positioning data acquisition unit 102 can be various types of sensors. In other words, each source corresponds to at least one sensor.

[0034] The positioning data processing unit 104 can process the positioning data collected by each positioning data acquisition unit 102.

[0035] Specifically, after receiving the positioning data, the positioning data processing unit 104 will obtain the corresponding attribute parameters based on the positioning data.

[0036] The attribute parameters include position parameters, quality parameters, error parameters, history parameters, and environmental parameters. Among them, the position parameter is the three-dimensional coordinate of the UAV collected by the sensor; the quality parameter indicates the signal strength and clarity of the positioning data; the error parameter indicates the offset of the positioning data from the historical trajectory or external truth value; the history parameter indicates the reliability of the positioning data within a pre-set time period; and the environmental parameter indicates the degree to which the positioning data is affected by the external environment.

[0037] Quality parameters can be directly acquired by the sensor (i.e., the positioning data acquisition unit 102). These parameters reflect the quality of the positioning data itself, such as signal strength and clarity. Common indicators include: SNR (Signal-to-Noise Ratio), RSSI (Signal Strength Index), number of satellites (GNSS / RTK), and IMU noise (INS). The data type of quality parameters is generally numerical (decimal numbers from 0 to 1, the larger the better), for example, 0.8 (very strong signal) and 0.2 (very weak signal).

[0038] Error parameters represent the deviation of positioning data from historical trajectories or external ground truth. Common methods for obtaining them include comparing the smoothness with historical trajectories, comparing the error with ground base stations / known points, and obtaining the residuals from fusion results with other signal sources (nearby drones). Error parameters are data types that are numerical (decimals from 0 to 1, the smaller the better), for example, 0.1 (very close), 0.7 (far from).

[0039] Historical parameters indicate the stability and reliability of the location data over a period of time. In this embodiment, historical parameters can be determined through historical indicators related to them, including historical confidence mean, variance, volatility, and anomaly frequency. The data type of historical parameters is also numerical (decimal numbers from 0 to 1, the larger the better), for example, 0.9 (consistently stable), 0.3 (frequently erroneous).

[0040] Environmental parameters represent the impact of the external environment on the signal, such as obstruction and interference. They are determined by monitoring the degree of obstruction (e.g., being blocked by other drones), interference intensity, and dynamic obstacles when the drone is collecting positioning data via ground base stations. The data type for environmental types is numerical (a decimal between 0 and 1, the larger the better), for example, 0.95 (very good environment) and 0.2 (very poor environment).

[0041] In addition, after obtaining the attribute parameters, the positioning data processing unit 104 will calculate the abnormal score based on the attribute parameters of each positioning data, and remove the corresponding positioning data when the abnormal score is greater than the threshold, or reduce its weight when determining the weight in the subsequent process.

[0042] Specifically, the anomaly score is the sum of the anomaly sub-scores, and each sub-score is determined by the parameter residuals of the UAV and its neighboring UAVs on the same attribute.

[0043] For example, taking the position parameter (three-dimensional coordinates) in the positioning data as an example, its corresponding sub-score = abs(Signal_i["position"]-Fused_Position), where Signal_i["position"] is the position parameter of the i-th positioning data of the currently processed UAV, and Fused_Position is the three-dimensional coordinates of the fused positioning data after the fusion of adjacent UAVs, which is an array of [x, y, z].

[0044] It is worth noting that the sub-score of the calculated location parameter is a decimal between 0 and 1. The larger the value, the more abnormal it is. It can reflect the parameter characteristics of the location data in terms of quality, history, environment, etc.

[0045] Similarly, the sub-score of the quality parameter of the positioning data = abs(Signal_i["quality "]-Fused_quality), where Signal_i["quality "] is the quality parameter of the i-th positioning data of the currently processed UAV, and Fused_Position is the quality parameter of the fused positioning data after the fusion of neighboring UAVs.

[0046] During anomaly detection, the positioning data processing unit 104 adds up the sub-scores corresponding to all attribute parameters of each positioning data to obtain an anomaly score. The anomaly score is compared with a threshold. If the anomaly score is greater than the threshold, it indicates that the positioning data is abnormal data, and it is deleted or its weight is reduced in subsequent weight calculations.

[0047] After obtaining the attribute parameters of the positioning data, the positioning data processing unit 104 will preprocess the positioning data. At this time, the positioning data includes both position parameters (three-dimensional coordinates) and attribute parameters.

[0048] In some embodiments, the preprocessing process includes timestamp alignment and format normalization.

[0049] Timestamp alignment refers to filtering out positioning data collected by each sensor at the same time. It should be noted that all sensors collect data in real time.

[0050] Format standardization refers to extracting the attribute parameters of location data from various sources and storing them using a unified recording method.

[0051] In a specific example, a structure can be used to uniformly record the location data, as follows: Signal = { "type": "GNSS", # Data source, string "position": [x, y, z], # Position parameter, 3D coordinates, array / vector "timestamp": 1234567890, # Timestamp, integer or floating-point number "quality": 0.85, # Quality parameter, a decimal between 0 and 1 "error": 0.12, # Error parameter, a decimal between 0 and 1 "history": 0.90, # History parameter, a decimal number between 0 and 1 "env": 0.95, # Environment parameter, a decimal between 0 and 1 "anomaly_score": 0.08 # Anomaly score, a decimal between 0 and 1 } Meanwhile, each location data is stored in a list (array) format, for example, Signals = [Signal1,Signal2, Signal3, ...], and each Signal structure contains the above fields.

[0052] Subsequently, the positioning data processing unit 104 can calculate the confidence value of each positioning data based on its attribute parameters, and determine the weight of each positioning data according to the confidence value.

[0053] In some embodiments, the positioning data processing unit 104 may calculate the confidence value of each positioning data using the following formula: Confidence_i = w1 × Quality_i + w2 × (1 - Error_i) + w3 × History_i + w4 × Env_i; Where i refers to the i-th location data, and w1, w2, w3, and w4 are weights (e.g., 0.4, 0.3, 0.2, and 0.1), which sum to 1. Quality_i, History_i, and Env_i should be as large as possible, while Error_i should be as small as possible, so (1 - Error_i) is used. For example, assuming the weights are 0.4, 0.3, 0.2, and 0.1, and the four parameters are 0.7, 0.2, 0.8, and 0.9 respectively, then: Confidence_i = 0.4×0.7 + 0.3×(1-0.2) + 0.2×0.8 + 0.1×0.9 = 0.28 + 0.24+0.16 + 0.09 = 0.77. The weights of each attribute parameter can be set according to the actual situation, and this application does not limit this.

[0054] In other embodiments, the positioning data processing unit 104 can also obtain the confidence value through an integrated pre-trained confidence model. That is, the positioning data processing unit 104 processes the attribute parameters of each positioning data by inputting them into the confidence model to obtain the corresponding confidence value.

[0055] The training data for the confidence model can be obtained using the aforementioned Confidence_i calculation formula. In other words, when the initial amount of data is small, the positioning data processing unit 104 uses the aforementioned Confidence_i calculation formula to calculate the confidence of the positioning data. After the amount of data increases, the confidence model can be trained using a large amount of data. After the model is trained, the model can be used to obtain the confidence value of each positioning data.

[0056] In some embodiments, the weight of each location data point is obtained using the following formula: Weight_i = Confidence_i / Sum(Confidence_j); Where i refers to the i-th location data, and Weight_i is the weight of the i-th location data.

[0057] After obtaining the weight of each location data, the location data fusion unit 106 applies a fusion algorithm to combine the weights of each location data to fuse all the location data and generate fused location data.

[0058] In this embodiment, the fusion algorithm mainly fuses the position parameters (i.e., three-dimensional coordinates) of the positioning data, which can be expressed by the following formula: Fused_Position = Sum(Weight_i * Position_i); Where Fused_Position represents the fused positioning data, Position_i is the position parameter of the i-th positioning data, and Weight_i is the weight of the i-th positioning data.

[0059] In some embodiments, the fusion algorithm is one of weighted Kalman filtering, adaptive Bayesian fusion, and deep learning fusion.

[0060] In some embodiments, the system 100 further includes a model self-feedback unit 108, which can use the final fused positioning data as training data and external ground truth as test data to train the confidence model. The external ground truth indicates the positioning data collected by the ground base station. That is, the confidence model in the positioning data processing unit supports model self-learning and parameter adaptive optimization.

[0061] The system 100 provided by this invention evaluates the confidence level of each source positioning data in real time and dynamically optimizes the fusion weight based on the confidence level, thereby achieving dynamic evaluation and optimal fusion of multi-source positioning data and improving the positioning accuracy and reliability of UAVs in complex environments.

[0062] System 100 quantifies the confidence level of each source based on the attribute parameters (quality / error / history / environment) of the positioning data, dynamically allocates fusion weights, and effectively suppresses the impact of low-quality data on the positioning results; by synchronizing the timestamps of multi-source data and unifying the format, it eliminates system-level deviations and ensures the reliability of the fusion input base; and by identifying abnormal data, it effectively identifies and suppresses the propagation of abnormal data.

[0063] System 100 can significantly improve the positioning accuracy and reliability of UAVs in complex environments; it enables dynamic modeling and adaptive fusion of multi-source signal confidence to prevent abnormal signals from affecting positioning; it supports anomaly detection and elimination to improve system robustness and security; it supports model self-learning and feedback optimization to continuously improve positioning performance; it is suitable for various UAV application scenarios and has broad promotional value.

[0064] In some embodiments, the positioning data processing unit 104, the positioning data fusion unit 106, and the model self-feedback unit 108 of the positioning system 100 described above can be implemented as a computing device as described below.

[0065] Figure 2 A schematic diagram of a computing device 200 according to an embodiment of the present invention is shown. Figure 2 As shown, in a basic configuration, computing device 200 includes at least one processing unit 202 and system memory 204. According to one aspect, depending on the configuration and type of the computing device, the processing unit 202 may be implemented as a processor. System memory 204 includes, but is not limited to, volatile memory (e.g., random access memory), non-volatile memory (e.g., read-only memory), flash memory, or any combination of such memories. According to one aspect, system memory 204 includes an operating system 205.

[0066] According to one aspect, operating system 205 is, for example, suitable for controlling the operation of computing device 200. Furthermore, examples are practiced in conjunction with graphics libraries, other operating systems, or any other applications, and are not limited to any particular application or system. Figure 2 The basic configuration is illustrated by the components within the dashed lines. According to one aspect, the computing device 200 has additional features or functions. For example, according to one aspect, the computing device 200 includes additional data storage devices (removable and / or non-removable), such as disks, optical discs, or magnetic tapes. This additional storage... Figure 2The middle part is shown by removable storage device 209 and non-removable storage device 210.

[0067] As stated above, according to one aspect, program module 203 is stored in system memory 204. According to one aspect, program module 203 may include one or more applications. The present invention does not limit the type of application; for example, applications may include: email and contact applications, word processing applications, spreadsheet applications, database applications, slideshow applications, drawing or computer-aided applications, web browser applications, etc.

[0068] In an embodiment of the present invention, program module 203 includes multiple program instructions for executing the UAV positioning method 300 based on multi-source location signal fusion of the present invention.

[0069] According to one aspect, examples can be practiced on circuits including discrete electronic components, packaged or integrated electronic chips containing logic gates, circuits utilizing microprocessors, or on a single chip containing electronic components or a microprocessor. For example, it can be practiced via wherein... Figure 2 Each or many of the components shown can be implemented as an example by integrating a System-on-a-Chip (SOC) on a single integrated circuit. According to one aspect, such an SOC device may include one or more processing units, graphics units, communication units, system virtualization units, and various application functions, all integrated (or “burned in”) as a single integrated circuit onto a chip substrate. When operating via the SOC, the functions described herein can be operated via dedicated logic integrated on a single integrated circuit (chip) with other components of the computing device 200. Embodiments of the invention can also be implemented using other techniques capable of performing logical operations (e.g., AND, OR, and NOT), including but not limited to mechanical, optical, fluid, and quantum technologies. Additionally, embodiments of the invention can be implemented within a general-purpose computer or in any other circuit or system.

[0070] According to one aspect, computing device 200 may also have one or more input devices 212, such as a keyboard, mouse, pen, voice input device, touch input device, etc. It may also include output devices 214, such as a display, speaker, printer, etc. The foregoing devices are examples and other devices may also be used. Computing device 200 may include one or more communication connections 216 that allow communication with other computing devices 218. Examples of suitable communication connections 216 include, but are not limited to: RF transmitter, receiver and / or transceiver circuitry; Universal Serial Bus (USB), parallel and / or serial ports.

[0071] As used herein, the term computer-readable medium includes computer storage medium. Computer storage medium can include volatile and non-volatile, removable and non-removable media implemented using any method or technology for storing information (e.g., computer-readable instructions, data structures, or program modules). System memory 204, removable storage device 209, and non-removable storage device 210 are examples of computer storage media (i.e., memory storage). Computer storage media can include random access memory (RAM), read-only memory (ROM), electrically erasable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital universal disc (DVD) or other optical storage, magnetic tape, magnetic tape, disk storage or other magnetic storage devices, or any other article of manufacture that can be used to store information and is accessible by computing device 200. According to one aspect, any such computer storage medium can be part of computing device 200. Computer storage media does not include carrier waves or other transmitted data signals.

[0072] According to one aspect, a communication medium is implemented by computer-readable instructions, data structures, program modules, or other data in a modulated data signal (e.g., a carrier wave or other transmission mechanism), and includes any information transmission medium. According to one aspect, the term "modulated data signal" describes a signal having one or more sets of characteristics or altered in a manner that encodes information in the signal. By way of example and not limitation, a communication medium includes wired media such as wired networks or direct wired connections, and wireless media such as acoustic, radio frequency (RF), infrared, and other wireless media.

[0073] In an embodiment of the present invention, a computing device 200 is configured to execute a data processing method 300. The computing device 200 includes one or more processors and one or more readable storage media storing program instructions, which, when configured to be executed by the one or more processors, enable the computing device to execute the UAV positioning method 300 based on multi-source location signal fusion according to an embodiment of the present invention.

[0074] The UAV positioning method 300 based on multi-source location signal fusion in the embodiments of the present invention will be described in detail below. Figure 3 A flowchart of a UAV localization method 300 based on multi-source location signal fusion according to an embodiment of the present invention is shown. Method 300 is adapted to be executed in a computing device (e.g., the aforementioned computing device 200).

[0075] like Figure 3As shown, the purpose of method 300 is to realize an adaptive and robust UAV positioning method based on multi-source positioning data fusion. It begins with step 302, in which positioning data from different sources are collected, including: Global Navigation Satellite System, Real-time Dynamic Positioning, Inertial Navigation System, Visual Inertial Odometry, Ultra Wideband Positioning, and Synchronous Positioning and Mapping.

[0076] In step 304, the confidence value of each location data is calculated based on its attribute parameters, and the weight of each location data is determined based on the confidence value.

[0077] In step 306, a fusion algorithm is applied to combine the weights of each location data point and fuse all the location data to generate fused location data.

[0078] It should be noted that the working principle and process of the method 300 provided in this embodiment are similar to those of the system 100 described above. For relevant details, please refer to the description of the system 100 described above, which will not be repeated here.

[0079] The various techniques described herein can be implemented in combination with hardware or software, or a combination thereof. Thus, the methods and apparatus of the present invention, or certain aspects or portions thereof, can take the form of program code (i.e., instructions) embedded in a tangible medium, such as a removable hard disk, USB flash drive, floppy disk, CD-ROM, or any other machine-readable storage medium, wherein when the program is loaded into and executed by a machine such as a computer, the machine becomes an apparatus for practicing the present invention.

[0080] When the program code is executed on a programmable computer, the computing device generally includes a processor, a processor-readable storage medium (including volatile and non-volatile memory and / or storage elements), at least one input device, and at least one output device. The memory is configured to store program code; the processor is configured to execute the method of the present invention according to instructions in the program code stored in the memory.

[0081] By way of example, and not limitation, readable media include readable storage media and communication media. Readable storage media stores information such as computer-readable instructions, data structures, program modules, or other data. Communication media generally embodies computer-readable instructions, data structures, program modules, or other data in the form of modulated data signals such as carrier waves or other transmission mechanisms, and includes any information delivery medium. Any combination of the above is also included within the scope of readable media.

[0082] In the specification provided herein, the algorithms and displays are not inherently related to any particular computer, virtual system, or other device. Various general-purpose systems can also be used with the examples of this invention. The required structure for constructing such systems is apparent from the above description. Furthermore, this invention is not directed to any particular programming language. It should be understood that the contents of the invention described herein can be implemented using various programming languages, and the above description of specific languages ​​is for the purpose of disclosing preferred embodiments of the invention.

[0083] Numerous specific details are set forth in the specification provided herein. However, it will be understood that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures, and techniques have not been shown in detail so as not to obscure the understanding of this specification.

[0084] Those skilled in the art will understand that modules, units, or components of the devices disclosed in the examples herein can be arranged in the devices described in this embodiment, or alternatively, can be located in one or more devices different from the devices in this example. The modules in the foregoing examples can be combined into a single module or, in addition, can be divided into multiple sub-modules.

[0085] Furthermore, some of the embodiments described herein are methods or combinations of method elements that can be implemented by a processor of a computer system or by other means of performing the functions. Therefore, a processor having the necessary instructions for implementing the methods or method elements forms means for implementing the methods or method elements. Furthermore, the elements described herein in the apparatus embodiments are examples of means for implementing the functions performed by elements for the purposes of carrying out the invention.

[0086] As used herein, unless otherwise specified, the use of ordinal numbers such as “first,” “second,” “third,” etc., to describe ordinary objects merely indicates different instances of similar objects and is not intended to imply that the objects being described must have a given order in time, space, ordering, or any other manner.

[0087] Although the invention has been described with reference to a limited number of embodiments, those skilled in the art will understand from the foregoing description that other embodiments are conceivable within the scope of the invention described herein. Furthermore, it should be noted that the language used in this specification has been chosen primarily for readability and instructional purposes, and not for the purpose of interpreting or limiting the subject matter of the invention. Therefore, many modifications and alterations will be apparent to those skilled in the art without departing from the scope and spirit of the appended claims.

Claims

1. A UAV positioning system based on multi-source location signal fusion, comprising: Multiple positioning data acquisition units are mounted on the drone. Each positioning data acquisition unit is used to collect positioning data from a single source, including: Global Navigation Satellite System, Real-time Dynamic Positioning, Inertial Navigation System, Visual Inertial Odometry, Ultra Wideband Positioning, and Positioning-Synchronous Mapping. The positioning data processing unit is adapted to calculate the confidence value of each positioning data based on its attribute parameters, and to determine the weight of each positioning data based on the confidence value. The positioning data fusion unit is suitable for applying fusion algorithms, combining the weights of each positioning data point, to fuse all positioning data and generate fused positioning data.

2. The system as claimed in claim 1, wherein, The attribute parameters include quality parameters, error parameters, historical parameters, and environmental parameters. The quality parameters indicate the signal strength and clarity of the positioning data. The error parameters indicate the offset of the positioning data from historical trajectories or external truth values. The historical parameters indicate the reliability of the positioning data within a preset time period. The environmental parameters indicate the degree to which the positioning data is affected by the external environment.

3. The system as described in claim 2, wherein, Calculate the confidence value of each location data point using the following formula: Confidence_i = w1 × Quality_i + w2 × (1 - Error_i) + w3 × History_i +w4 × Env_i; Where Confidence_i is the confidence value of the i-th location data, Quality_i is the quality parameter of the i-th location data, w1 is the weight of the quality parameter, Error_i is the error parameter of the i-th location data, w2 is the weight of the error parameter, History_i is the historical parameter of the i-th location data, w3 is the weight of the historical parameter, Env_i is the environmental parameter of the i-th location data, and w4 is the weight of the environmental parameter.

4. The system as described in claim 2, wherein, The location data processing unit integrates a pre-trained confidence model and is also suitable for processing the attribute parameters of each location data by inputting them into the confidence model to obtain its corresponding confidence value.

5. The system as described in claim 4, wherein, Also includes: The model self-feedback unit is adapted to use the fused positioning data as training data and the external ground truth as test data to train the confidence model, wherein the external ground truth indicates the positioning data collected by the ground base station.

6. The system as claimed in claim 2, wherein, The location data processing unit is also adapted to calculate anomaly scores based on the attribute parameters of each location data, and to remove or reduce the weight of the corresponding location data when the anomaly score is greater than the threshold.

7. The system of claim 6, wherein, The anomaly score is the sum of the anomaly sub-scores, and each sub-score is determined by the parameter residuals of the drone and its neighboring drones on the same attribute.

8. The system of claim 1, wherein, The location data processing unit is also adapted to preprocess the location data, the preprocessing including timestamp alignment and format standardization.

9. The system as claimed in claim 1, wherein, The fusion algorithm is one of weighted Kalman filtering, adaptive Bayesian fusion, or deep learning fusion.

10. A UAV positioning method based on multi-source location signal fusion, comprising: It collects positioning data from various sources, including: Global Navigation Satellite System, real-time dynamic positioning, inertial navigation system, visual inertial odometry, ultra-wideband positioning, and synchronous positioning and mapping. The confidence score of each location data point is calculated based on its attribute parameters, and the weight of each location data point is determined based on the confidence score. By applying a fusion algorithm and combining the weights of each location data point, all location data are fused to generate fused location data.

Images