Space domain conflict detection method and system based on space-time grid, and computing device

Through the airspace conflict detection method based on space-time grid, the Beidou grid code and prediction algorithm are used to solve the problem of not considering dynamic flying objects in the UAV route planning, and efficient judgment and avoidance of airspace conflicts are achieved, ensuring that no Safe flight of human-machine.

CN118942289APending Publication Date: 2024-11-12BEIJING ZHIWANG YILIAN TECH CO LTD
View PDF 0 Cites 7 Cited by

Patent Information

Application Number
CN202410939499.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-12
Publication Date
2024-11-12

AI Technical Summary

Technical Problem

The existing drone route planning fails to effectively consider dynamic sudden flying objects, such as birds and other drones, resulting in safety accidents prone to real flight scenarios.

Method used

The airspace conflict detection method based on space-time grid is adopted to mesh the airspace suitable for the drone through Beidou grid code to determine the grid code trajectory of the target drone, and use linear regression algorithm and Kalman filtering algorithm Predict the position of the flying object, determine whether there is airspace conflict, and then control the drone to avoid conflict.

Benefits of technology

It realizes the advance judgment of air dynamic uncertain flying objects, improves the calculation speed and accuracy of airspace conflict detection, and ensures safe flight of the drone.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118942289A_ABST
    Figure CN118942289A_ABST
Patent Text Reader

Abstract

The invention discloses an airspace conflict detection method and system based on a space-time grid, and a computing device, and the method comprises the steps: carrying out the mesh generation of a suitable flight airspace of a target unmanned plane based on a Beidou mesh code, and obtaining a mesh airspace; determining a target grid code track of the target unmanned aerial vehicle in the grid airspace, and controlling the target unmanned aerial vehicle to fly based on the target grid code track; based on the real-time position grid code of the flying object, judging whether the flying object is in an early warning area of the target unmanned aerial vehicle; if yes, current position information of the flying object is obtained every preset time interval, so that a position grid code set is generated; predicting each first predicted position grid code corresponding to each future moment of the flying object based on the position grid code set, and generating a predicted grid code track; and based on the predicted grid code trajectory and the target grid code trajectory, determining whether the flying object will have an airspace conflict with the target unmanned aerial vehicle. The airspace conflict can be judged in advance for the flying object, and the calculation speed is increased.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of low-altitude flight technology, and in particular to an airspace conflict detection method, an airspace conflict detection system and a computing device based on a space-time grid. Background Art

[0002] Currently, drone route planning almost only considers static obstacles, such as buildings and electric poles, but rarely considers dynamic and sudden flying objects, such as birds and other drones. If these dynamic and sudden flying objects are not considered, safety accidents are likely to occur in real drone flight scenarios. How to judge airspace conflicts in advance for dynamic and uncertain flying objects in the air and then avoid airspace conflicts is an urgent problem to be solved.

[0003] Therefore, a spatial conflict detection method based on space-time grid is needed to solve the problems existing in the above technical solutions. Summary of the invention

[0004] To this end, the present invention provides a spatial conflict detection method and a spatial conflict detection system based on a space-time grid to solve or at least alleviate the above problems.

[0005] According to one aspect of the present invention, there is provided an airspace conflict detection method based on spatiotemporal grids, which is executed in a computing device, which is communicatively connected to a target UAV, and the method comprises: gridding the suitable flying airspace of the target UAV based on the Beidou grid code, so as to divide the suitable flying airspace of the target UAV into a plurality of grids, and assigning a unique corresponding grid code to each of the grids to obtain a grid airspace; determining a target grid code trajectory of the target UAV in the grid airspace, and controlling the target UAV to fly based on the target grid code trajectory; obtaining the corresponding real-time position grid code of each flying object in the grid airspace, and judging whether the flying object is in the warning area of ​​the target UAV based on the real-time position grid code of the flying object; and if confirmed, If the flying object is determined to be within the warning area, the current position information of the flying object corresponding to the current moment is obtained at predetermined time intervals to generate a position grid code set corresponding to the current moment, wherein the position grid code set includes an observed position grid code corresponding to the current moment and a plurality of observed position grid codes corresponding to a plurality of historical moments before the current moment; a linear regression algorithm is used to predict the first predicted position grid codes corresponding to the flying object at each future moment based on the position grid code set to generate a predicted grid code trajectory of the flying object; and based on the predicted grid code trajectory of the flying object and the target grid code trajectory of the target UAV, it is determined whether the flying object will have an airspace conflict with the target UAV.

[0006] Optionally, in the airspace conflict detection method based on the space-time grid according to the present invention, the predicted grid code trajectory of the flying object is generated, including: using a Kalman filtering algorithm to filter each first predicted position grid code corresponding to the flying object at each future moment to obtain each optimal position grid code corresponding to each future moment; based on the each optimal position grid code, generating the predicted grid code trajectory of the flying object.

[0007] Optionally, in the airspace conflict detection method based on the space-time grid according to the present invention, a Kalman filter algorithm is used to filter each first predicted position grid code corresponding to the flying object at each future moment to obtain each optimal position grid code corresponding to each future moment, including: using a Kalman filter algorithm, based on the position grid code set, predicting each second predicted position grid code corresponding to the flying object at each future moment; for each future moment, calculating the average value of the first predicted position grid code and the second predicted position grid code corresponding to the future moment, and using the average value as the optimal position grid code corresponding to the future moment.

[0008] Optionally, in the airspace conflict detection method based on the space-time grid according to the present invention, a Kalman filter algorithm is used to predict each second predicted position grid code corresponding to the flying object at each future moment based on the position grid code set, including: based on the position grid code set, determining each observation state vector corresponding to the observed position grid code at each moment in the position grid code set, and calculating the variance of each observation state vector, and based on the variance of each observation state vector corresponding to each of the observed position grid codes, obtaining the observation covariance matrix corresponding to the current moment, wherein the observation state vector is used to represent the speed in each direction corresponding to the observed position grid code; based on the updated state vector corresponding to the previous moment of the current moment and the updated covariance matrix, determining the predicted state vector corresponding to the current moment and predicted covariance matrix, wherein the updated state vector and updated covariance matrix corresponding to the previous moment are obtained by updating the predicted state vector and predicted covariance matrix corresponding to the previous moment based on the observed state vector and observed covariance matrix corresponding to the previous moment; based on the observed state vector and observed covariance matrix corresponding to the current moment, the predicted state vector and predicted covariance matrix corresponding to the current moment are updated to obtain the updated state vector and updated covariance matrix corresponding to the current moment; repeat the above steps to obtain each updated state vector and each updated covariance matrix corresponding to the flying object at each future moment; for each future moment, based on the updated state vector and updated covariance matrix corresponding to the future moment, determine the second predicted position grid code corresponding to the future moment.

[0009] Optionally, in the airspace conflict detection method based on space-time grid according to the present invention, the flying objects include flying objects with sensing devices and flying objects without sensing devices; the current position information of the flying objects at the current moment is obtained at predetermined time intervals, including: when the flying object is a flying object without sensing equipment, the current position information of the flying object at the current moment is obtained through the radar and camera of the target unmanned aerial vehicle at predetermined time intervals, and the current position information corresponding to the current moment is converted into an observation position grid code corresponding to the current moment; when the flying object is a flying object with sensing equipment, the current position grid code of the flying object at the current moment is directly obtained at predetermined time intervals.

[0010] Optionally, in the airspace conflict detection method based on spatiotemporal grid according to the present invention, determining whether the flying object will have an airspace conflict with the target drone based on the predicted grid code trajectory of the flying object and the target grid code trajectory of the target drone includes: judging whether there are overlapping grids between the predicted grid code trajectory of the flying object and the target grid code trajectory of the target drone; if there are overlapping grids, determining a first time corresponding to the overlapping grid on the predicted grid code trajectory, a second time corresponding to the overlapping grid on the target grid code trajectory, and determining the time difference between the first time and the second time; if the time difference is less than or equal to a predetermined time threshold, determining that the flying object will have an airspace conflict with the target drone; if the time difference is greater than the predetermined time threshold, determining that the flying object will not have an airspace conflict with the target drone.

[0011] Optionally, in the airspace conflict detection method based on space-time grid according to the present invention, it also includes: if it is determined that the flying object will have an airspace conflict with the target UAV, before the target UAV flies to the overlapping grid, the target UAV is controlled to rise a predetermined distance and then return to the original target grid code trajectory to continue flying.

[0012] Optionally, in the airspace conflict detection method based on space-time grid according to the present invention, the real-time position grid code corresponding to each flying object in the grid airspace is obtained, including: in response to detecting the presence of one or more flying objects in the suitable flying airspace of the target UAV, obtaining the real-time position grid code corresponding to each flying object in the grid airspace.

[0013] According to one aspect of the present invention, there is provided an airspace conflict detection system, comprising: a target UAV; a computing device, communicatively connected to the target UAV, wherein an airspace conflict detection device is deployed in the computing device, and the airspace conflict detection device comprises: a segmentation module, adapted to perform grid segmentation on the suitable flying airspace of the target UAV based on the Beidou grid code, so as to divide the suitable flying airspace of the target UAV into a plurality of grids, and assign a unique corresponding grid code to each of the grids to obtain a grid airspace; a determination module, adapted to determine the target grid code trajectory of the target UAV in the grid airspace, and control the target UAV to fly based on the target grid code trajectory; a first judgment module, adapted to obtain the corresponding real-time position grid code of each flying object in the grid airspace, and judge whether the flying object is within the warning of the target UAV based on the real-time position grid code of the flying object. an acquisition module, if it is determined that the flying object is in the warning area, the acquisition module is suitable for acquiring the current position information of the flying object at the current moment at predetermined time intervals to generate a position grid code set corresponding to the current moment, wherein the position grid code set includes an observed position grid code corresponding to the current moment, and a plurality of observed position grid codes respectively corresponding to a plurality of historical moments before the current moment; a prediction module, suitable for predicting each first predicted position grid code corresponding to the flying object at each future moment based on the position grid code set using a linear regression algorithm to generate a predicted grid code trajectory of the flying object; a second judgment module, suitable for determining whether the flying object will have an airspace conflict with the target drone based on the predicted grid code trajectory of the flying object and the target grid code trajectory of the target drone.

[0014] According to one aspect of the present invention, there is provided a computing device, comprising: at least one processor; and a memory storing program instructions, wherein the program instructions are configured to be suitable for execution by the at least one processor, and the program instructions include instructions for executing the spatial domain conflict detection method based on the space-time grid as described above.

[0015] According to one aspect of the present invention, a computer program product is provided, comprising a computer program / instruction, wherein the computer program / instruction implements the method as described above when executed by a processor.

[0016] According to one aspect of the present invention, a readable storage medium storing program instructions is provided. When the program instructions are read and executed by a computing device, the computing device executes the spatial domain conflict detection method based on the space-time grid as described above.

[0017] According to the technical solution of the present invention, a method for detecting airspace conflicts based on time-space grid is provided. The airspace suitable for target UAV is grid-divided based on Beidou grid code, the target grid code trajectory of target UAV is determined and the target UAV is controlled to fly based on the target grid code trajectory. At the same time, the real-time position grid code of each flying object is used to determine whether each flying object is in the warning area of ​​the target UAV. If the flying object is in the warning area, the current position information of the flying object is obtained at predetermined time intervals and a position grid code set is generated. Then, the first predicted position grid codes corresponding to the flying object at each future moment are predicted based on the position grid code set, and the predicted grid code trajectory of the flying object is generated. Based on the predicted grid code trajectory and the target grid code trajectory, it is determined whether the flying object will have an airspace conflict with the target UAV. In this way, the present invention can judge airspace conflicts in advance for flying objects with uncertain dynamics in the air, and thus can avoid airspace conflicts. Moreover, when judging airspace conflicts, the present invention replaces complex spatial calculations with grid code bit operations, which can greatly improve the calculation speed, thereby timely avoiding airspace conflicts and realizing safer flight of UAVs.

[0018] Furthermore, the present invention utilizes the Kalman filter algorithm to filter and obtain the optimal position grid codes corresponding to each future moment, and generates the predicted grid code trajectory of the flying object based on each optimal position grid code. In this way, the accuracy of the predicted grid code trajectory can be improved, and airspace conflicts can be judged more accurately.

[0019] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented according to the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] To achieve the above and related purposes, certain illustrative aspects are described herein in conjunction with the following description and accompanying drawings, which indicate various ways in which the principles disclosed herein can be practiced, and all aspects and their equivalents are intended to fall within the scope of the claimed subject matter. The above and other purposes, features and advantages of the present disclosure will become more apparent by reading the following detailed description in conjunction with the accompanying drawings. Throughout the present disclosure, the same reference numerals generally refer to the same parts or elements.

[0021] Figure 1 A schematic diagram of an airspace conflict detection system 100 provided according to an embodiment of the present invention is shown;

[0022] Figure 2 A schematic diagram of a computing device 200 provided according to an embodiment of the present invention is shown;

[0023] Figure 3 A schematic flow chart of a spatial domain conflict detection method 300 based on a space-time grid provided according to an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0024] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0025] In order to facilitate understanding, the terms involved in the present invention are first explained below.

[0026] Beidou Grid Code (BGC), also known as Beidou Grid Location Code, is a geographic space coding method based on the Beidou Navigation Satellite System (BDS). It divides the earth's surface into grid cells of varying sizes according to certain mathematical rules, and assigns a unique code to each grid cell to identify the location of the grid cell. As a national standard, Beidou Grid Location Code has the following advantages: it can provide grid codes of different accuracy levels to meet different positioning needs; it can divide the earth's surface into grid cells of varying sizes and assign a unique grid code to each grid cell; Beidou Grid Location Code provides a global geographic grid coding solution; the coding model supports efficient spatial data indexing and retrieval, is suitable for large-scale video surveillance networks, and has high computational efficiency.

[0027] Kalman filter is a highly efficient recursive filter (autoregressive filter) that can estimate the state of a dynamic system from a series of incomplete and noisy measurements. Kalman filter will produce an estimate of the unknown variable based on the values ​​of each measurement at different times, taking into account the joint distribution at each time, so it will be more accurate than the estimation method based on a single measurement. The Kalman filter algorithm is a two-step procedure. In the estimation step, the Kalman filter will produce an estimate of the current state, which also includes uncertainty. As long as the next measurement is observed (which must contain a certain degree of error, including random noise). The estimate will be updated by weighted averaging, and the more certain the measurement is, the higher the weight. The algorithm is iterative and can be executed in a real-time control system. It only needs the current input measurement, the previous calculated value and its uncertainty matrix, and does not require other previous information. A typical example of Kalman filtering is to predict the coordinates and velocity of an object's position from a finite, noisy, observation sequence of the object's position (which may be biased).

[0028] Kalman filtering is a recursive estimation, that is, as long as the estimated value of the state at the previous moment and the observed value of the current state are known, the estimated value of the current state can be calculated, so there is no need to record historical information of observation or estimation. The difference between the Kalman filter and most filters is that it is a pure time domain filter. It does not need to be designed in the frequency domain and then converted to the time domain like frequency domain filters such as low-pass filters. Kalman filtering is mainly divided into two parts: prediction and update. It is necessary to construct the state equation and observation equation of the system, and the initial state of the system is known. In the prediction stage, the filter uses the estimate of the previous state to make an estimate of the current state. In the update stage, the filter uses the observed value of the current state to optimize the predicted value obtained in the prediction stage to obtain a more accurate new estimate.

[0029] In the existing technology, dynamic and sudden flying objects such as birds and other drones are rarely taken into consideration in drone route planning, which makes it easy for safety accidents to occur in real drone flight scenarios.

[0030] In order to determine airspace conflicts in advance for flying objects with uncertain dynamics in the air and thus avoid airspace conflicts, the embodiment of the present invention provides an airspace conflict detection method and system based on a spatiotemporal grid. According to the technical solution of the present invention, when determining airspace conflicts, grid code bit operations are used instead of complex spatial calculations, which can greatly improve the calculation speed, thereby being able to avoid airspace conflicts in a timely manner and achieve safer flight of drones.

[0031] The spatial conflict detection method based on the space-time grid provided according to the embodiment of the present invention can be implemented in a spatial conflict detection system. The spatial conflict detection system of the present invention is introduced below.

[0032] Figure 1 A schematic diagram of an airspace conflict detection system 100 provided according to an embodiment of the present invention is shown.

[0033] like Figure 1 As shown, the airspace conflict detection system 100 includes a computing device 200 and a target drone 110. The computing device 200 is in communication connection with the target drone 110 and can plan a flight path (three-dimensional path) for the target drone 110.

[0034] In an embodiment of the present invention, the computing device 200 can perform grid division on the suitable flying airspace of the target UAV based on the Beidou grid code to divide the suitable flying airspace of the target UAV into multiple grids, and assign a unique corresponding grid code to each grid, thereby obtaining the grid airspace corresponding to the suitable flying airspace of the target UAV. It should be noted that the suitable flying airspace of the target UAV is the aviation airspace range in which the target UAV 110 performs the mission.

[0035] The computing device 200 can determine the target grid code trajectory of the target drone 110 in the grid airspace, and control the target drone 110 to fly based on the target grid code trajectory. At the same time, the computing device 200 can obtain the corresponding real-time position grid code of each flying object (such as a bird, other drones, etc.) in the suitable flying airspace of the target drone in the grid airspace, and determine whether the flying object is in the warning area of ​​the target drone 110 based on the real-time position grid code of the flying object. If the computing device 200 determines that the flying object is in the warning area, the current position information corresponding to the flying object at the current moment is obtained at predetermined time intervals to generate a set of position grid codes corresponding to the current moment. The set of position grid codes corresponding to the current moment includes the observed position grid code corresponding to the flying object at the current moment, and multiple observed position grid codes corresponding to the flying object at multiple historical moments before the current moment. Furthermore, the computing device 200 can use a linear regression algorithm to predict the first predicted position grid codes corresponding to the flying object at each future moment based on the position grid code set corresponding to the current moment, so as to generate a predicted grid code trajectory of the flying object, and based on the predicted grid code trajectory of the flying object and the target grid code trajectory of the target UAV 110, determine whether the flying object will have an airspace conflict with the target UAV 110.

[0036] It should be noted that the observed position grid code is the position grid code of the flying object actually detected / acquired.

[0037] In an embodiment of the present invention, Figure 1 As shown, a spatial conflict detection device 250 is deployed in the computing device 200, and the spatial conflict detection device 250 can be configured to execute the spatial conflict detection method 300 based on the spatiotemporal grid of the present invention.

[0038] In an embodiment of the present invention, Figure 1 As shown, the airspace conflict detection device 250 includes a segmentation module 251, a determination module 252, a first judgment module 253, an acquisition module 254, a prediction module 255, and a second judgment module 256 which are coupled in sequence.

[0039] Among them, the segmentation module 251 can perform grid segmentation on the suitable flying airspace of the target UAV based on the Beidou grid code to divide the suitable flying airspace of the target UAV into multiple grids, and assign a unique corresponding grid code to each grid to obtain a grid airspace.

[0040] The determination module 252 may determine a target grid code trajectory of the target UAV 110 within the grid airspace, and control the target UAV 110 to fly based on the target grid code trajectory.

[0041] The first judgment module 253 can obtain the real-time position grid code corresponding to each flying object in the grid airspace, and judge whether the flying object is in the warning area of ​​the target UAV 110 based on the real-time position grid code of the flying object.

[0042] If it is determined that the flying object is in the warning area, the acquisition module 254 can obtain the current position information of the flying object at the current moment at predetermined time intervals to generate a position grid code set corresponding to the current moment, wherein the position grid code set includes the observed position grid code corresponding to the current moment and multiple observed position grid codes corresponding to multiple historical moments before the current moment.

[0043] The prediction module 255 can use a linear regression algorithm to predict each first predicted position grid code corresponding to the flying object at each future moment based on the position grid code set, so as to generate a predicted grid code trajectory of the flying object.

[0044] The second determination module 256 may determine whether the flying object will have an airspace conflict with the target UAV 110 based on the predicted grid code trajectory of the flying object and the target grid code trajectory of the target UAV 110 .

[0045] It should be pointed out that regarding the specific execution logic of the segmentation module 251, determination module 252, first judgment module 253, acquisition module 254, prediction module 255 and second judgment module 256 in the airspace conflict detection device 250, reference can be made to the description of steps 310 to 360 in the airspace conflict detection method 300 based on the space-time grid below.

[0046] According to the airspace conflict detection system 100 provided by the embodiment of the present invention, the suitable airspace of the target drone is gridded based on the Beidou grid code, the target grid code trajectory of the target drone 110 is determined, and the target drone 110 is controlled to fly based on the target grid code trajectory. At the same time, based on the real-time position grid code of each flying object, it is determined whether each flying object is in the warning area of ​​the target drone 110. If the flying object is in the warning area, the current position information of the flying object is obtained at every predetermined time interval and a position grid code set is generated. Then, based on the position grid code set, each first predicted position grid code corresponding to the flying object at each future moment is predicted, and a predicted grid code trajectory of the flying object is generated. Based on the predicted grid code trajectory and the target grid code trajectory, it is determined whether the flying object will have an airspace conflict with the target drone 110. In this way, the present invention can judge airspace conflicts in advance for flying objects with uncertain dynamics in the air, and thus can avoid airspace conflicts. Moreover, when judging airspace conflicts, the present invention replaces complex spatial calculations with grid code bit operations, which can greatly improve the calculation speed, thereby being able to avoid airspace conflicts in time and realize safer flight of drones.

[0047] Figure 2 FIG. 2 shows a schematic diagram of a computing device 200 provided according to an embodiment of the present invention. Figure 2 As shown, in a basic configuration, the computing device 200 includes at least one processing unit 202 and a system memory 204. According to one aspect, depending on the configuration and type of the computing device, the processing unit 202 can be implemented as a processor. The system memory 204 includes, but is not limited to, volatile storage (e.g., random access memory), non-volatile storage (e.g., read-only memory), flash memory, or any combination of such memories. According to one aspect, the system memory 204 includes an operating system 205.

[0048] According to one aspect, operating system 205 is suitable for controlling the operation of computing device 200, for example. Furthermore, examples are practiced in conjunction with graphics libraries, other operating systems, or any other application programs, and are not limited to any particular application or system. Figure 2 The basic configuration is shown in FIG. 2 by those components within the dashed lines. According to one aspect, the computing device 200 has additional features or functionality. For example, according to one aspect, the computing device 200 includes additional data storage devices (removable and / or non-removable), such as magnetic disks, optical disks, or tapes. Such additional storage Figure 2 2 is illustrated by a removable storage device 209 and a non-removable storage device 210.

[0049] As stated above, according to one aspect, a program module 203 is stored in the system memory 204. According to one aspect, the program module 203 may include one or more application programs, and the present invention does not limit the type of application program, for example, the application program may include: email and contact application programs, word processing application programs, spreadsheet application programs, database application programs, slide show application programs, drawing or computer-aided application programs, web browser application programs, etc.

[0050] In an embodiment according to the present invention, the program module 203 includes a plurality of program instructions for executing the spatial conflict detection method 300 based on the space-time grid of the present invention.

[0051] According to one aspect, the examples may be practiced on a circuit comprising discrete electronic components, a packaged or integrated electronic chip containing logic gates, a circuit utilizing a microprocessor, or a single chip containing electronic components or a microprocessor. Figure 2Each or many components shown in can be integrated into a system on a chip (SOC) on a single integrated circuit to practice examples. According to one aspect, such a SOC device may include one or more processing units, a graphics unit, a communication unit, a system virtualization unit, and various application functions, all of which are integrated (or "burned") into a chip substrate as a single integrated circuit. When operated via SOC, the functions described in this article can be operated via a dedicated logic integrated with other components of the computing device 200 on a single integrated circuit (chip). Other technologies that can perform logical operations (such as AND, OR, and NOT) can also be used to practice embodiments of the present invention, including but not limited to mechanical, optical, fluid, and quantum technologies. In addition, embodiments of the present invention can be practiced in a general-purpose computer or in any other circuit or system.

[0052] According to one aspect, the computing device 200 may also have one or more input devices 212, such as a keyboard, a mouse, a pen, a voice input device, a touch input device, etc. Output devices 214 may also be included, such as a display, a speaker, a printer, etc. The aforementioned devices are examples and other devices may also be used. The 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 transmitters, receivers and / or transceiver circuits; Universal Serial Bus (USB), parallel and / or serial ports.

[0053] The term computer-readable medium as used herein includes computer storage media. Computer storage media may include volatile and non-volatile, removable and non-removable media implemented in 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 all examples of computer storage media (i.e., memory storage). Computer storage media may include random access memory (RAM), read-only memory (ROM), electrically erasable read-only memory (EEPROM), flash memory or other memory technology, CD-ROM, digital versatile disk (DVD) or other optical storage, cassettes, tapes, disk storage or other magnetic storage devices, or any other products that can be used to store information and can be accessed by computing device 200. According to one aspect, any such computer storage medium can be a part of computing device 200. Computer storage media does not include carrier waves or other propagated data signals.

[0054] According to one aspect, communication media 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 transport mechanism), and includes any information delivery media. According to one aspect, the term "modulated data signal" describes a signal that has one or more characteristics set or changed in a manner that encodes information in the signal. By way of example and not limitation, communication media includes wired media such as a wired network or direct-wired connection, and wireless media such as acoustic, radio frequency (RF), infrared, and other wireless media.

[0055] In an embodiment according to the present invention, the computing device 200 is configured to execute the spatial conflict detection method 300 based on the spatiotemporal grid. The computing device 200 includes one or more processors and one or more readable storage media storing program instructions. When the program instructions are configured to be executed by one or more processors, the computing device executes the spatial conflict detection method 300 based on the spatiotemporal grid in the embodiment of the present invention. By executing the spatial conflict detection method 300 based on the spatiotemporal grid of the present invention, the computing device 200 can judge the spatial conflict in advance for the flying objects with uncertain dynamics in the air.

[0056] In an embodiment of the present invention, the computing device 200 executing the spatial conflict detection method 300 based on the spatiotemporal grid of the present invention may be a server or a terminal. The computing device 200 may be connected to the target drone 110 for communication and may plan a flight path for the target drone 110.

[0057] The following is a detailed description of the spatial conflict detection method 300 based on the space-time grid in an embodiment of the present invention.

[0058] Figure 3 FIG. 3 is a flow chart of a spatial domain conflict detection method 300 based on a space-time grid according to an embodiment of the present invention. Figure 3 As shown, the spatial domain conflict detection method 300 based on the space-time grid includes the following steps 310-360.

[0059] Step 310, the computing device 200 can grid the suitable flying airspace of the target UAV based on the Beidou grid code to divide the suitable flying airspace of the target UAV into multiple grids, and assign a unique corresponding grid code to each grid, thereby obtaining the grid airspace corresponding to the suitable flying airspace of the target UAV.

[0060] It should be noted that the suitable flying airspace of the target UAV is the airspace range in which the target UAV 110 performs the mission. In the embodiment of the present invention, the computing device 200 pre-grids the suitable flying airspace of the target UAV based on the Beidou grid code to divide the suitable flying airspace of the target UAV into multiple grids, and assigns a unique corresponding grid code to each grid. In this way, it is convenient to detect airspace conflicts through grid code calculation later.

[0061] Step 320: The computing device 200 determines a target grid code trajectory of the target UAV 110 in the grid airspace, and controls the target UAV 110 to fly based on the target grid code trajectory.

[0062] In an embodiment of the present invention, the target grid code trajectory is a pre-planned grid code trajectory corresponding to the three-dimensional flight path of the target UAV 110 in the grid airspace.

[0063] Step 330, the computing device 200 obtains the corresponding real-time position grid code of each flying object in the suitable flying airspace of the target UAV in the grid airspace, and determines whether the flying object is in the warning area of ​​the target UAV 110 based on the real-time position grid code of the flying object.

[0064] In an embodiment of the present invention, the computing device 200 can detect whether there are flying objects in the suitable flying airspace of the target UAV. When one or more flying objects are detected in the suitable flying airspace of the target UAV, in response to detecting the presence of one or more flying objects in the suitable flying airspace of the target UAV, the corresponding real-time position grid code of each flying object in the grid airspace is obtained.

[0065] In some embodiments, flying objects may include, for example, flying objects without sensing devices (such as flying birds) and flying objects with sensing devices (such as other drones). For flying objects with sensing devices (such as other drones), the corresponding real-time position grid code of the flying object in the grid airspace can be directly obtained. For flying objects without sensing devices (such as flying birds), the real-time position information of the flying object can be obtained, and the real-time position grid code corresponding to the real-time position information in the grid airspace can be determined (the real-time position information is converted into the corresponding real-time position grid code), thereby obtaining the real-time position grid code of the flying object. Furthermore, it can be determined whether the flying object is in the warning area of ​​the target drone 110 based on the real-time position grid code of the flying object.

[0066] In an embodiment of the present invention, the warning area of ​​the target drone 110 is also the perception area of ​​the target drone 110. In some embodiments, the warning area (perception area) of the target drone 110 can be 100 8-level grids (0.97m×0.97m) in the horizontal direction and 50 8-level grids in the vertical direction of the target drone 110.

[0067] In the embodiment of the present invention, when it is determined that the flying object is within the warning area of ​​the target drone 110, airspace conflict detection will be performed for the flying object (subsequent steps 340 to 360 will be executed). If the flying object is not within the warning area of ​​the target drone 110, there is no need to perform airspace conflict detection for the flying object (subsequent steps 340 to 360 will no longer be executed).

[0068] Step 340: If the computing device 200 determines that the flying object is within the warning area, it obtains the current position information of the flying object at the current time at a predetermined time interval (e.g., 1 second) to generate a set of position grid codes corresponding to the current time. The set of position grid codes corresponding to the current time includes the observed position grid code corresponding to the flying object at the current time, and multiple observed position grid codes corresponding to multiple historical times before the current time.

[0069] In the embodiment of the present invention, the observed position grid code is the position grid code of the flying object actually detected / acquired.

[0070] It can be understood that the location grid code set corresponding to the current time contains multiple discrete observation location grid codes, each of which corresponds to a time. The location grid code set corresponding to the current time can be expressed as [(bdcode1, t1), (bdcode2, t2) ...]. Here, bdcode represents the location grid code and t represents the time.

[0071] Step 350, the computing device 200 uses a linear regression algorithm to predict each first predicted position grid code corresponding to the flying object at each future moment based on the position grid code set corresponding to the current moment, so as to generate a predicted grid code trajectory of the flying object.

[0072] In an embodiment of the present invention, the computing device 200 may generate a predicted grid code trajectory of the flying object based on each first predicted position grid code corresponding to the flying object at each future moment.

[0073] In step 360 , the computing device 200 may determine whether the flying object will have an airspace conflict with the target UAV 110 based on the predicted grid code trajectory of the flying object and the target grid code trajectory of the target UAV 110 .

[0074] It should be noted that, in an embodiment of the present invention, spatial attributes can be abstracted into a visual grid representation based on the grid code. When judging spatial conflicts, grid code bit operations are used instead of complex spatial calculations, which can greatly improve the calculation speed, which is 10 times faster.

[0075] In some embodiments, in step 360, the computing device 200 may determine whether the flying object will have an airspace conflict with the target drone 110 in the following manner:

[0076] First, the computing device 200 may determine whether there are overlapping grids between the predicted grid code trajectory of the flying object and the target grid code trajectory of the target UAV 110. Overlapping grids are grids that both the predicted grid code trajectory and the target grid code trajectory pass through.

[0077] If the computing device 200 determines that there are overlapping grids between the predicted grid code trajectory of the flying object and the target grid code trajectory of the target drone 110, a first time corresponding to the overlapping grid on the predicted grid code trajectory and a second time corresponding to the overlapping grid on the target grid code trajectory are determined, and then a time difference between the first time and the second time is determined.

[0078] Next, the computing device 200 determines whether the time difference between the first time and the second time is less than or equal to a predetermined time threshold. If the time difference is less than or equal to the predetermined time threshold, it is determined that the flying object will have an airspace conflict with the target drone 110. If the time difference is greater than the predetermined time threshold, it is determined that the flying object will not have an airspace conflict with the target drone 110. In some embodiments, the predetermined time threshold may be 20 seconds, but the present invention is not limited thereto. The predetermined time threshold may be set by a person skilled in the art according to actual conditions.

[0079] If the computing device 200 determines that the flying object will have an airspace conflict with the target drone 110, before the target drone 110 flies to the overlapping grid, the target drone 110 can be controlled to be lifted off a predetermined distance and then return to the original target grid code track to continue flying. Specifically, if the computing device 200 determines that the flying object will have an airspace conflict with the target drone 110, before the flight position of the target drone 110 is a predetermined distance (e.g., 20 grids) away from the overlapping grid, the target drone 110 can be controlled to be lifted off a predetermined distance (away from the collision zone), and then the target drone 110 can be controlled to return to the original target grid code track to continue flying.

[0080] In addition, if the computing device 200 determines that the flying object will not cause airspace conflict with the target UAV 110, the target UAV 110 can be controlled to continue flying based on the target grid code trajectory without changing the target grid code trajectory of the target UAV 110.

[0081] In some embodiments, flying objects may include flying objects without sensing devices (such as birds) and flying objects with sensing devices (such as other drones). For flying objects without sensing devices, the location information of the flying objects can be obtained by using the radar and camera of the target drone 110 at a relatively close distance to the flying objects, and the location information can be converted into a corresponding location grid code in the grid airspace. For flying objects with sensing devices, the location grid code of the flying object can be directly obtained based on the communication between the flying object and the ground base station.

[0082] Specifically, in step 340, the specific manner in which the computing device 200 obtains the current position information corresponding to the flying object at the current moment at every predetermined time interval is as follows: in the case where the flying object is a non-sensing device flying object (such as a flying bird), the current position information corresponding to the non-sensing device flying object at the current moment (i.e., the position of the non-sensing device flying object relative to the target drone 110) can be obtained through the radar and camera of the target drone 110 (at a relatively close position to the flying object) at every predetermined time interval, and the current position information corresponding to the current moment is converted into the observation position grid code corresponding to the current moment. Similarly, multiple observation position grid codes corresponding to multiple historical moments before the current moment can also be obtained in the above manner. Furthermore, the computing device 200 can generate a set of position grid codes corresponding to the current moment based on the observation position grid code corresponding to the current moment and the multiple observation position grid codes corresponding to multiple historical moments before the current moment.

[0083] For example, the current position information (the position of the bird relative to the target drone 110) of the non-sensing device flying object (bird) at the current moment obtained by the radar and camera of the target drone 110 can be expressed as (X 鸟 , Y 鸟 , Z 鸟 ). The position coordinates of the target drone 110 are expressed as (X, Y, Z). The current position information corresponding to the current moment can be converted into the observation position grid code corresponding to the current moment by the following formula:

[0084]

[0085] In the formula, Indicates the actual length of the 8th level Beidou code (0.97m), distance x Indicates the number of grids on the X-axis of the north-facing coordinate system, distance y Indicates the number of grids on the Y axis of the north coordinate system, distance z Indicates the number of grids on the Z axis (i.e. vertical height) of the north coordinate system.

[0086] According to the above formula, the offset in each direction (the number of grids on the X, Y, and Z axes) can be calculated. Then, by adding the current grid code coordinates of the target UAV 110 to the offset in each direction mentioned above, the grid code coordinates corresponding to the flying bird at the current moment can be obtained, and then the grid code of the observation position corresponding to the flying bird at the current moment can be obtained.

[0087] In addition, when the flying object is a flying object with a sensing device (such as other drones), the computing device 200 can directly obtain the current position grid code of the flying object at the current moment at every predetermined time interval (based on the communication between the flying object and the ground base station).

[0088] In some embodiments, in step 350, the computing device 200 may use a linear regression function to predict the first predicted position grid codes corresponding to the flying object at each future time based on the position grid code set corresponding to the current time. The linear regression function is as follows:

[0089] y=β0+β1x+∈

[0090] Among them, y is the first predicted location grid code to be determined, x is the future time corresponding to the first predicted location grid code, and β0 is the initial location grid code. ∈ is the error term, which can be obtained by the average value of the difference between the first predicted location grid code obtained by multiple calculations and the corresponding actual detected observation location grid code (the corresponding value in the location grid code set). β1 is the regression coefficient of the independent variable x, which can be obtained by the following formula:

[0091]

[0092] Where m is the number of observed location grid codes contained in the location grid code set (number of samples), and y i is the i-th observed location grid code in the location grid code set, x i is the time corresponding to the grid code of the i-th observation position.

[0093] According to the above linear regression function and formula, the first predicted position grid code y corresponding to the flying object at each future time x can be obtained. Then, the points corresponding to each first predicted position grid code can be connected to obtain the predicted grid code trajectory of the flying object.

[0094] In some embodiments, in step 350, the computing device 200 may further generate a predicted grid code trajectory of the flying object in the following manner: using a Kalman filter algorithm, filtering each first predicted position grid code corresponding to the flying object at each future moment to obtain each optimal position grid code corresponding to each future moment. Further, based on each optimal position grid code, a predicted grid code trajectory of the flying object may be generated.

[0095] It should be noted that the present invention utilizes the Kalman filter algorithm to enhance the accuracy of predicting the grid code trajectory.

[0096] In some embodiments, the computing device 200 uses the Kalman filter algorithm to filter each first predicted position grid code corresponding to the flying object at each future moment to obtain each optimal position grid code corresponding to each future moment. The specific method is as follows:

[0097] First, the Kalman filter algorithm can be used to predict the second predicted position grid codes corresponding to the flying object at each future moment based on the position grid code set corresponding to the current moment. Then, for each future moment, the average value of the first predicted position grid code and the second predicted position grid code corresponding to the future moment is calculated, and the average value is used as the optimal position grid code corresponding to the future moment. In this way, the optimal position grid codes corresponding to each future moment can be obtained.

[0098] In some embodiments, the computing device 200 uses the Kalman filter algorithm to predict the second predicted position grid codes corresponding to the flying object at each future time based on the position grid code set corresponding to the current time as follows:

[0099] The computing device 200 can determine each observation state vector corresponding to the observed position grid code at each moment in the position grid code set based on the position grid code set corresponding to the current moment, and calculate the variance of each observation state vector, and obtain the observation covariance matrix corresponding to the current moment based on the variance of each observation state vector corresponding to each observation position grid code, wherein the observation state vector is used to represent the speed in each direction (X, Y, and Z axes) corresponding to the observed position grid code.

[0100] For example, the observed state vector can be expressed as: [bdcode, V x ,V y ,V z Here, bdcode represents the observed position grid code of the flying object actually detected. Vx, Vy, and Vz represent the speeds corresponding to the observed position grid code on the X-axis, Y-axis, and Z-axis, respectively, which can be calculated based on the observed position grid code at each moment in the position grid code set.

[0101] The observation covariance matrix can be expressed as: here, It corresponds to each observation state vector corresponding to each observation position grid code in the position grid code set.

[0102] Next, the computing device 200 may predict and update the state vector and covariance matrix at each moment.

[0103] In the prediction stage, the computing device 200 can determine the predicted state vector and predicted covariance matrix corresponding to the current moment based on the updated state vector and updated covariance matrix corresponding to the previous moment of the current moment. The updated state vector and updated covariance matrix corresponding to the previous moment are obtained by updating the predicted state vector and predicted covariance matrix corresponding to the previous moment based on the observed state vector and observed covariance matrix corresponding to the previous moment.

[0104] For example, the computing device 200 may determine the predicted state vector corresponding to the current moment based on the updated state vector corresponding to the previous moment of the current moment by the following formula:

[0105] X k|k-1 =FX k-1|k-1 +Bu k

[0106] In the above formula, X k|k-1 is the predicted state vector at time k (current time); X k-1|k-1 is the updated state vector at time k-1 (the previous moment of the current moment); F represents the state transfer matrix, which can be set as Δt represents the time interval for obtaining the observed position grid code (i.e., the predetermined time interval, i.e., the difference between the times corresponding to two adjacent observed position grid codes in the position grid code set), and the time interval may be, for example, 1s; B represents the control input matrix, which may be set as u k is the control input vector, which can be set to Where a is the corresponding acceleration, which can be obtained based on Vx, Vy, and Vz.

[0107] In addition, the computing device 200 can determine the prediction covariance matrix corresponding to the current moment based on the updated covariance matrix corresponding to the previous moment by the following formula:

[0108] P k|k-1 =FP k-1|k-1 F T +Q

[0109] In the above formula, P k|k-1 is the prediction covariance matrix at time k (current time); P k-1|k-1 is the updated covariance matrix at time k-1 (previous moment); Q is the process noise covariance matrix, and the observation covariance matrix can be used here.

[0110] Subsequently, in the update phase, the computing device 200 may update (optimize) the predicted state vector and predicted covariance matrix corresponding to the current moment based on the observed state vector and observed covariance matrix corresponding to the current moment to obtain the updated state vector and updated covariance matrix corresponding to the current moment.

[0111] Specifically, the formula for calculating the Kalman gain is as follows:

[0112] K k =P k|k-1 H T (HP k|k-1 H T +R) -1

[0113] In the formula, K k is the Kalman gain matrix at time k (the current time); H is the observation matrix, which only needs the observation coordinate information and can be set to R is the observation noise covariance matrix, which can be determined based on the index of the position sensor device. For example, if the standard deviation of the measurement noise of the position sensor is 0.1 meters, its variance is 0.01 square meters.

[0114] The computing device 200 may update the predicted state vector corresponding to the current moment according to the following formula to obtain an updated state vector corresponding to the current moment:

[0115] X k|k =X k|k-1 +X k (z k -HX k|k-1 )

[0116] Where, X k|k is the updated state vector at time k (the current time); z k is the observed state vector at time k (current time); X k|k-1 is the predicted state vector at time k (the current time).

[0117] The computing device 200 may update the prediction covariance matrix corresponding to the current moment according to the following formula to obtain an updated covariance matrix corresponding to the current moment:

[0118] P k|k =(IK k K)P k|k-1

[0119] Where P k|k is the updated covariance matrix at time k (the current time); P k|k-1 is the prediction covariance matrix at time k (the current time); I is the identity matrix; K kis the Kalman gain matrix at time k (the current time).

[0120] Afterwards, the computing device 200 can continue to predict and update the state vector and covariance matrix at the next moment: based on the updated state vector and updated covariance matrix corresponding to the current moment, determine the predicted state vector and predicted covariance matrix corresponding to the next moment; based on the observed state vector and observed covariance matrix corresponding to the next moment, update (optimize) the predicted state vector and predicted covariance matrix corresponding to the next moment to obtain the updated state vector and updated covariance matrix corresponding to the next moment.

[0121] In this way, by repeatedly executing the above steps, each updated state vector and each updated covariance matrix corresponding to the flying object at each future moment can be obtained.

[0122] Furthermore, for each future moment, the computing device 200 can determine the second predicted position grid code corresponding to the future moment based on the updated state vector and the updated covariance matrix corresponding to the future moment. Moreover, by calculating the average value of the first predicted position grid code and the second predicted position grid code corresponding to the future moment, the average value can be used as the optimal position grid code corresponding to the future moment, so that each optimal position grid code corresponding to each future moment can be obtained. The predicted grid code trajectory of the flying object is generated based on each optimal position grid code, which can improve the accuracy of the predicted grid code trajectory.

[0123] According to the airspace conflict detection method 300 based on the spatiotemporal grid of the present invention, the suitable airspace of the target UAV is grid-divided based on the Beidou grid code, the target grid code trajectory of the target UAV is determined and the target UAV is controlled to fly based on the target grid code trajectory. At the same time, based on the real-time position grid code of each flying object, it is determined whether each flying object is in the warning area of ​​the target UAV. If the flying object is in the warning area, the current position information of the flying object is obtained at every predetermined time interval and a position grid code set is generated. Then, based on the position grid code set, each first predicted position grid code corresponding to the flying object at each future moment is predicted, and a predicted grid code trajectory of the flying object is generated. Based on the predicted grid code trajectory and the target grid code trajectory, it is determined whether the flying object will have an airspace conflict with the target UAV. In this way, the present invention can judge airspace conflicts in advance for flying objects with uncertain dynamics in the air, and thus can avoid airspace conflicts. Moreover, when judging airspace conflicts, the present invention replaces complex spatial calculations with grid code bit operations, which can greatly improve the calculation speed, thereby being able to avoid airspace conflicts in time and realize safer flight of the UAV.

[0124] Furthermore, the present invention utilizes the Kalman filter algorithm to filter and obtain the optimal position grid codes corresponding to each future moment, and generates the predicted grid code trajectory of the flying object based on each optimal position grid code. In this way, the accuracy of the predicted grid code trajectory can be improved, and airspace conflicts can be judged more accurately.

[0125] In addition, the embodiment of the present invention also discloses: A8, a method as described in any one of A1-A7, wherein obtaining the corresponding real-time position grid code of each flying object in the grid airspace includes: in response to detecting the presence of one or more flying objects in the suitable flying airspace of the target UAV, obtaining the corresponding real-time position grid code of each flying object in the grid airspace. B12, a readable storage medium storing program instructions, when the program instructions are read and processed by a computing device, the computing device processes the method as described in any one of A1-A8.

[0126] The various techniques described herein may be implemented in combination with hardware or software, or a combination thereof. Thus, the method and apparatus of the present invention, or some aspects or parts of the method and apparatus of the present invention may be in the form of program codes (i.e., instructions) embedded in a tangible medium, such as a removable hard disk, a USB flash drive, a floppy disk, a CD-ROM, or any other machine-readable storage medium, wherein when the program is loaded into a machine such as a computer and executed by the machine, the machine becomes a device for practicing the present invention.

[0127] In the case where the program code is executed on a programmable computer, the mobile terminal generally includes a processor, a storage medium readable by the processor (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 the program code; the processor is configured to execute the spatial domain conflict detection method based on the space-time grid of the present invention according to the instructions in the program code stored in the memory.

[0128] 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 embody computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transmission mechanism, and include any information transfer medium. Any combination of the above is also included within the scope of readable media.

[0129] In the description provided herein, algorithms and displays are not inherently related to any particular computer, virtual system or other device. Various general purpose systems can also be used together with the examples of the present invention. According to the above description, it is obvious that the structure required for constructing such systems. In addition, the present invention is not directed to any specific programming language either. It should be understood that various programming languages ​​can be utilized to implement the content of the present invention described herein, and the above description of specific languages ​​is for the purpose of disclosing the best mode of the present invention.

[0130] In the description provided herein, a large number of specific details are described. However, it is understood that embodiments of the present invention can be practiced without these specific details. In some instances, well-known methods, structures and techniques are not shown in detail so as not to obscure the understanding of this description.

[0131] Similarly, it should be understood that in order to streamline the present disclosure and aid in understanding one or more of the various inventive aspects, in the above description of exemplary embodiments of the present invention, various features of the present invention are sometimes grouped together into a single embodiment, figure, or description thereof.

[0132] Those skilled in the art will appreciate that the modules or units or components of the devices in the examples disclosed herein may be arranged in the devices described in the embodiment, or alternatively may be located in one or more devices different from the devices in the examples. The modules in the foregoing examples may be combined into one module or may be divided into multiple submodules.

[0133] Unless otherwise specified, the use of ordinal numbers "first", "second", "third", etc. to describe common objects merely indicates that different instances of similar objects are involved and is not intended to imply that the objects so described must have a given order in time, space, order or in any other manner.

Claims

1. A method for detecting airspace conflicts based on a space-time grid, executed in a computing device, the computing device being in communication with a target drone, the method comprising: Gridding the suitable flying airspace of the target UAV based on the Beidou grid code to divide the suitable flying airspace of the target UAV into a plurality of grids, and assigning a unique corresponding grid code to each of the grids to obtain a grid airspace; Determine a target grid code trajectory of the target UAV in the grid airspace, and control the target UAV to fly based on the target grid code trajectory; Obtaining the real-time position grid code corresponding to each flying object in the grid airspace, and judging whether the flying object is within the warning area of ​​the target UAV based on the real-time position grid code of the flying object; If it is determined that the flying object is within the warning area, the current position information of the flying object at the current moment is obtained at predetermined time intervals to generate a position grid code set corresponding to the current moment, wherein the position grid code set includes an observed position grid code corresponding to the current moment and a plurality of observed position grid codes corresponding to a plurality of historical moments before the current moment; Using a linear regression algorithm, based on the position grid code set, predicting each first predicted position grid code corresponding to the flying object at each future moment, so as to generate a predicted grid code trajectory of the flying object; Based on the predicted grid code trajectory of the flying object and the target grid code trajectory of the target UAV, it is determined whether the flying object will have an airspace conflict with the target UAV.

2. The method of claim 1, wherein: Generating a predicted grid code trajectory of the flying object, comprising: Using a Kalman filter algorithm, filtering each first predicted position grid code corresponding to each future moment of the flying object to obtain each optimal position grid code corresponding to each future moment; Based on the respective optimal position grid codes, a predicted grid code trajectory of the flying object is generated.

3. The method of claim 2, wherein: Using the Kalman filter algorithm, filtering each first predicted position grid code corresponding to the flying object at each future moment to obtain each optimal position grid code corresponding to each future moment, including: Using a Kalman filter algorithm, based on the position grid code set, predict each second predicted position grid code corresponding to the flying object at each future moment; For each future moment, an average value of the first predicted location grid code and the second predicted location grid code corresponding to the future moment is calculated, and the average value is used as the optimal location grid code corresponding to the future moment.

4. The method of claim 3, wherein: Using the Kalman filter algorithm, based on the position grid code set, predicting each second predicted position grid code corresponding to the flying object at each future moment, including: Based on the position grid code set, each observation state vector corresponding to the observation position grid code at each moment in the position grid code set is determined, and the variance of each observation state vector is calculated, and based on the variance of each observation state vector corresponding to each of the observation position grid codes, an observation covariance matrix corresponding to the current moment is obtained, wherein the observation state vector is used to represent the speed in each direction corresponding to the observation position grid code; Based on the updated state vector and updated covariance matrix corresponding to the previous moment of the current moment, determine the predicted state vector and predicted covariance matrix corresponding to the current moment, wherein the updated state vector and updated covariance matrix corresponding to the previous moment are obtained by updating the predicted state vector and predicted covariance matrix corresponding to the previous moment based on the observed state vector and observed covariance matrix corresponding to the previous moment; Based on the observed state vector and the observed covariance matrix corresponding to the current moment, the predicted state vector and the predicted covariance matrix corresponding to the current moment are updated to obtain the updated state vector and the updated covariance matrix corresponding to the current moment; Repeat the above steps to obtain each updated state vector and each updated covariance matrix corresponding to the flying object at each future moment; For each future moment, based on the updated state vector and the updated covariance matrix corresponding to the future moment, a second predicted position grid code corresponding to the future moment is determined.

5. The method according to any one of claims 1 to 4, wherein: The flying objects include flying objects with sensing devices and flying objects without sensing devices; obtaining the current position information of the flying objects at the current moment at every predetermined time interval includes: In the case where the flying object is a flying object without a sensing device, the current position information of the flying object at the current moment is obtained through the radar and camera of the target UAV at a predetermined time interval, and the current position information corresponding to the current moment is converted into an observation position grid code corresponding to the current moment; In the case that the flying object is a flying object with a sensing device, the current position grid code of the flying object at the current moment is directly acquired at every predetermined time interval.

6. The method according to any one of claims 1 to 5, wherein: Determining whether the flying object will have an airspace conflict with the target UAV based on the predicted grid code trajectory of the flying object and the target grid code trajectory of the target UAV includes: Determine whether there are overlapping grids between the predicted grid code trajectory of the flying object and the target grid code trajectory of the target UAV; If there are overlapping grids, determining a first time corresponding to the overlapping grids on the predicted grid code track, a second time corresponding to the overlapping grids on the target grid code track, and determining a time difference between the first time and the second time; If the time difference is less than or equal to a predetermined time threshold, it is determined that the flying object will have an airspace conflict with the target UAV; If the time difference is greater than a predetermined time threshold, it is determined that the flying object will not have an airspace conflict with the target UAV.

7. The method of claim 6, wherein: Also includes: If it is determined that the flying object will cause an airspace conflict with the target UAV, before the target UAV flies to the overlapping grid, the target UAV is controlled to fly a predetermined distance and then return to the original target grid code trajectory to continue flying.

8. An airspace conflict detection system, comprising: Target drones; A computing device is communicatively connected to the target UAV, wherein an airspace conflict detection device is deployed in the computing device, and the airspace conflict detection device includes: A subdivision module is adapted to perform grid subdivision on the suitable flying airspace of the target UAV based on the Beidou grid code, so as to divide the suitable flying airspace of the target UAV into a plurality of grids, and assign a unique corresponding grid code to each of the grids to obtain a grid airspace; A determination module, adapted to determine a target grid code trajectory of the target UAV in the grid airspace, and control the target UAV to fly based on the target grid code trajectory; A first judgment module is adapted to obtain a real-time position grid code corresponding to each flying object in the grid airspace, and judge whether the flying object is within the warning area of ​​the target UAV based on the real-time position grid code of the flying object; an acquisition module, wherein if it is determined that the flying object is within the warning area, the acquisition module is adapted to acquire the current position information of the flying object at the current moment at predetermined time intervals to generate a position grid code set corresponding to the current moment, wherein the position grid code set includes an observed position grid code corresponding to the current moment and a plurality of observed position grid codes respectively corresponding to a plurality of historical moments before the current moment; A prediction module, adapted to use a linear regression algorithm to predict, based on the position grid code set, each first predicted position grid code corresponding to the flying object at each future moment, so as to generate a predicted grid code trajectory of the flying object; The second judgment module is adapted to determine whether the flying object will have an airspace conflict with the target UAV based on the predicted grid code trajectory of the flying object and the target grid code trajectory of the target UAV.

9. A computing device comprising: at least one processor; and A memory storing program instructions, wherein the program instructions are configured to be processed by the at least one processor, and the program instructions include instructions for processing the method according to any one of claims 1 to 7.

10. A computer program product comprising a computer program / instructions, wherein: When the computer program / instructions are executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Citation Information

Cited By

  • Low-altitude flyer rapid detection and flight safety early warning method

    CN120071685A

  • A method for rapid detection of low-altitude flying objects and flight safety warning

    CN120071685B

  • Airline collision risk prediction method and system

    CN120766573A

  • A route collision risk prediction method and system

    CN120766573B

  • Gridding method and system based on flight trajectory data of unmanned aerial vehicle

    CN121528042A