Unmanned aerial vehicle anti-collision early warning method and system, medium and electronic equipment

Abstract

The invention provides an unmanned aerial vehicle anti-collision early warning method and system, a medium and electronic equipment, and relates to the technical field of unmanned aerial vehicles, the method comprises the steps that aircraft state information is acquired, and the aircraft state information comprises state information broadcasted by a second unmanned aerial vehicle and / or state information, sent by a server, of an aircraft in a target airspace; the target airspace is the airspace where the first unmanned aerial vehicle is located; according to the aircraft state information, a target aircraft meeting the monitoring condition is recognized, and the target aircraft is a second unmanned aerial vehicle or an aircraft; predicting future trajectories of the first unmanned aerial vehicle and the target aircraft according to the state information of the target aircraft and the state information of the first unmanned aerial vehicle; determining the closeness degree between the future trajectory of the first unmanned aerial vehicle and the future trajectory of the target aircraft; and outputting anti-collision early warning information for the first unmanned aerial vehicle in response to determining that the proximity degree meets a preset collision risk condition. Anti-collision early warning can be timely and effectively carried out, and the flight safety of the unmanned aerial vehicle is ensured.

Description

Technical Field

[0001] This application relates to the field of unmanned aerial vehicle (UAV) technology, and in particular to a method, system, medium, and electronic device for UAV collision avoidance warning. Background Technology

[0002] With the large-scale application of drones in various scenarios, their operational density and frequency are constantly increasing, highlighting the growing potential risks of collisions between drones and between drones and manned aircraft in low-altitude airspace. To address this risk, the industry has developed various technologies to achieve aerial perception and collision avoidance for drones.

[0003] However, existing technological solutions rely on single and incomplete information sources for risk decision-making. This makes it difficult to form a unified, complete, and reliable real-time situational awareness, limiting the practicality of their early warning functions in complex real-world environments and resulting in poor collision avoidance warning effects. Summary of the Invention

[0004] The technical problem this application aims to solve is to provide a method, system, medium, and electronic device for anti-collision warning of unmanned aerial vehicles (UAVs), and to improve the effectiveness of anti-collision warning. The specific solution is as follows:

[0005] A method for preventing collisions and providing early warning for unmanned aerial vehicles (UAVs), characterized in that it is applied to an early warning device, the early warning device being mounted on a first UAV, and the method comprising:

[0006] The aircraft status information is acquired, including the status information broadcast by the second UAV and / or the status information of the aircraft in the target airspace sent by the server; the target airspace is the airspace where the first UAV is located.

[0007] Based on the aircraft status information, at least one target aircraft that meets the preset monitoring conditions is identified, wherein the target aircraft is the second UAV or the aircraft.

[0008] Based on the status information of the target aircraft and the status information of the first UAV, predict the future trajectories of the first UAV and the target aircraft;

[0009] Determine the degree of proximity between the future trajectory of the first UAV and the future trajectory of the target aircraft;

[0010] In response to determining that the proximity meets a preset collision risk condition, a collision avoidance warning is output for the first drone.

[0011] Optionally, in the above method, obtaining aircraft status information includes:

[0012] Receive a wireless signal compliant with the Broadcast Remote Identification (ROI) specification broadcast by at least one second UAV; decode the wireless signal to obtain the status information of the second UAV;

[0013] Establish a communication connection with the server and receive status information of aircraft in the target airspace sent by the server.

[0014] Optionally, in the above method, identifying at least one target aircraft that meets preset monitoring conditions based on the aircraft status information includes:

[0015] Based on aircraft status information, the current relative distance and relative orientation between the candidate aircraft and the first UAV are calculated; the candidate aircraft includes at least one of the second UAV and the aircraft.

[0016] Determine whether the current relative distance of the candidate aircraft is within a preset monitoring distance range, and determine whether the relative orientation of the candidate aircraft is within a preset conflict sector;

[0017] If the current relative distance of the candidate aircraft is within the monitoring distance range and the relative orientation of the candidate aircraft is within the preset conflict sector, the candidate aircraft is identified as the target aircraft that meets the preset monitoring conditions.

[0018] Optionally, in the above method, predicting the future trajectories of the first UAV and the target aircraft based on the state information of the target aircraft and the state information of the first UAV includes:

[0019] Based on the state information of the target aircraft, calculate the first expected position of the target aircraft at multiple consecutive time points in the future, and generate the future trajectory of the target aircraft based on the first expected position at the multiple consecutive time points.

[0020] Based on the state information of the first drone, calculate the second expected position of the first drone at multiple consecutive time points in the future, and generate the future trajectory of the first drone based on the second expected position at the multiple consecutive time points.

[0021] Optionally, in the above method, predicting the future trajectories of the first UAV and the target aircraft based on the state information of the target aircraft and the state information of the first UAV includes:

[0022] The state information of the target aircraft is input into the motion prediction model of the target aircraft to obtain the future trajectory of the target aircraft.

[0023] The state information of the first UAV is input into the operation prediction model of the first UAV to obtain the future trajectory of the first UAV.

[0024] Optionally, in the above method, determining the proximity between the future trajectory of the first UAV and the future trajectory of the target aircraft includes:

[0025] Based on the future trajectory of the first UAV and the future trajectory of the target aircraft, calculate the shortest predicted approach distance between the first UAV and the target aircraft within the prediction time window;

[0026] Based on the velocity vectors and relative positions of the first UAV and the target aircraft, the approach rate and the estimated time required to reach the shortest predicted approach distance are calculated.

[0027] The degree of proximity is determined based on at least one of the shortest predicted approach distance, the approach rate, and the required time.

[0028] Optionally, the process of determining whether the proximity meets a preset collision risk condition in the above method includes:

[0029] The parameters included in the degree of proximity are compared with the risk thresholds corresponding to the parameters to obtain the comparison results of the parameters;

[0030] If the comparison result indicates that the shortest predicted approach distance is less than a first risk threshold and the estimated arrival time is less than a second risk threshold, then the proximity is determined to meet a preset collision risk condition.

[0031] A drone collision avoidance warning system is applied to a warning device, the warning device being mounted on a first drone, the system comprising:

[0032] The acquisition unit is used to acquire aircraft status information, which includes status information broadcast by the second UAV and / or status information of aircraft in the target airspace sent by the server; the target airspace is the airspace where the first UAV is located.

[0033] The identification unit is used to identify at least one target aircraft that meets preset monitoring conditions based on the aircraft status information, wherein the target aircraft is the second UAV or the aircraft.

[0034] The prediction unit is used to predict the future trajectories of the first UAV and the target aircraft based on the state information of the target aircraft and the state information of the first UAV.

[0035] A determining unit is configured to determine the degree of proximity between the future trajectory of the first UAV and the future trajectory of the target aircraft;

[0036] The output unit is used to output anti-collision warning information for the first UAV in response to determining that the proximity meets the preset collision risk conditions.

[0037] A storage medium includes storage instructions, wherein, when the instructions are executed, the device containing the storage medium is controlled to perform the drone collision avoidance warning method as described above.

[0038] An electronic device includes a memory and one or more instructions, wherein one or more instructions are stored in the memory and configured to be executed by one or more processors as described above for drone collision avoidance warning method.

[0039] Based on the above, this application provides a method, system, medium, and electronic device for anti-collision warning of unmanned aerial vehicles (UAVs). The method is applied to a warning device installed on a first UAV. The method includes: acquiring aircraft status information, including status information broadcast by a second UAV and / or status information of aircraft in a target airspace sent by a server; the target airspace is the airspace where the first UAV is located; identifying at least one target aircraft that meets preset monitoring conditions based on the aircraft status information, the target aircraft being either the second UAV or the first UAV; predicting the future trajectories of the first UAV and the target aircraft based on the status information of the target aircraft and the first UAV; determining the degree of proximity between the future trajectories of the first UAV and the target aircraft; and outputting anti-collision warning information for the first UAV in response to determining that the degree of proximity meets preset collision risk conditions. This method enables timely and effective anti-collision warnings, ensuring the flight safety of the UAV. Attached Figure Description

[0040] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of this application. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0041] Figure 1 A flowchart of a method for anti-collision warning of unmanned aerial vehicles provided in this application;

[0042] Figure 2A flowchart illustrating a process for determining whether a proximity meets preset collision risk conditions, as provided in this application;

[0043] Figure 3 This application provides a schematic diagram of the structure of an unmanned aerial vehicle (UAV) collision avoidance and early warning system.

[0044] Figure 4 This is a schematic diagram of the structure of an electronic device provided in this application. Detailed Implementation

[0045] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0046] In this application, the terms "comprising," "including," or any other variations thereof are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0047] This application provides a method for anti-collision warning of unmanned aerial vehicles (UAVs). This method can be applied to an electronic device, which can be a warning device installed on a first UAV. The flowchart of the method is shown below. Figure 1 As shown, it specifically includes:

[0048] S101: Obtain aircraft status information, which includes the status information broadcast by the second UAV and / or the status information of aircraft in the target airspace sent by the server; the target airspace is the airspace where the first UAV is located.

[0049] In this embodiment, the target airspace is the three-dimensional spatial range in which the first UAV is currently located or about to enter, and in which airspace monitoring needs to be implemented. This range can be set according to airspace classification, flight rules, or mission requirements. For example, it can be a spherical airspace with a preset radius centered on the first UAV, or a corridor airspace defined according to the flight path.

[0050] In this embodiment, acquiring aircraft status information can include two parallel data sources. One source is a second UAV, which periodically broadcasts its own status via an onboard transmitter. This broadcast signal conforms to the relevant technical specifications for broadcast remote identification, integrating the second UAV's identification code, real-time latitude and longitude, altitude, ground speed, heading, and other status parameters. The early warning device captures this wireless signal through a corresponding receiving module and parses the status information from it via decoding circuitry or processing software. The other source is a remote server, which is an air traffic management or airspace information service platform that aggregates multi-source surveillance data from radar, ADS-B ground stations, and other sources. The early warning device establishes a data transmission link with the server via a cellular mobile communication network and receives a list of aircraft dynamic information related to the target airspace sent by the server according to a predetermined protocol. This list may contain real-time status summaries of other UAVs or manned aircraft operating in the airspace besides the first UAV.

[0051] S102: Based on the aircraft status information, identify at least one target aircraft that meets the preset monitoring conditions, wherein the target aircraft is the second UAV or the aircraft.

[0052] In this embodiment, the target aircraft refers to an aircraft that may have a potential conflict with the first drone, which may be the second drone or an aircraft indicated by the server information.

[0053] In this embodiment, all acquired aircraft status information can be parsed to extract the current relative motion geometric relationship between each aircraft and the first UAV. Key parameters include relative distance and relative bearing. Preset monitoring conditions may include spatial proximity criteria and motion direction criteria. For example, the spatial proximity criterion sets a monitoring distance threshold; when the real-time distance between another aircraft and the first UAV is less than this threshold, the spatial proximity condition is met. The motion direction criterion sets a potential conflict sector, which is an angular range extending forward and laterally based on the first UAV's current heading; if the relative bearing of another aircraft falls within this sector, it is considered that there is a possible head-on or intersecting conflict heading. Each aircraft can be sequentially calculated and compared with these criteria, and the aircraft that simultaneously meets all preset monitoring conditions is identified as the target aircraft.

[0054] S103: Based on the state information of the target aircraft and the state information of the first UAV, predict the future trajectories of the first UAV and the target aircraft.

[0055] Optionally, the future trajectory can refer to the expected continuous spatial position sequence of an aircraft over a future period of time, derived by extrapolation from a kinematic or dynamic model based on the known motion state at the current moment.

[0056] In this embodiment, the state information of the first UAV may include position, velocity, acceleration, directional angular velocity, etc., and this state information can be acquired in real time through onboard sensors or the flight control system bus. The prediction process uses a motion extrapolation model, such as a uniform velocity model, a uniform acceleration model, or a coordinated turn model. Specifically, the processing unit inputs the current state vectors of the first UAV and the target aircraft into the selected prediction model. Based on the laws of physical motion, the model calculates the expected position coordinates of both parties at discrete time points with fixed time intervals within a preset future duration. Connecting these discrete position points in chronological order constitutes the future trajectory of the first UAV and the future trajectory of the target aircraft. The prediction accuracy is affected by the model complexity and the update frequency of the state information. In an optional implementation, an interactive multi-model algorithm can be used to adapt to different possible motion patterns of the target.

[0057] S104: Determine the degree of proximity between the future trajectory of the first UAV and the future trajectory of the target aircraft.

[0058] In this embodiment, proximity is a comprehensive metric used to quantify the proximity relationship between two predicted trajectories in the spatial and temporal dimensions.

[0059] In this embodiment, the instantaneous spatial distance between the first UAV and the target aircraft at the same future time point can be calculated based on the future trajectory point sequence of the first UAV and the target aircraft. By traversing all time points, the shortest distance between the two trajectories can be found and determined as the expected minimum approach distance. Furthermore, by combining the velocity vectors of both parties near that time, the rates at which they approach or move away from each other can be calculated. Based on this shortest distance and approach rate, the remaining time required to reach the expected minimum approach distance point from the current time can be calculated, that is, the time to reach the closest point. The degree of proximity can be characterized by one or more of the expected minimum approach distance, approach rate, and time to reach the closest point. For example, the expected minimum approach distance can be used as the degree of proximity.

[0060] S105: In response to determining that the proximity level meets the preset collision risk conditions, output anti-collision warning information for the first drone.

[0061] In this embodiment, the collision risk condition is a warning threshold set for one or more parameters of the aforementioned proximity level. The collision avoidance warning information is a prompting instruction or structured data packet generated after the warning is triggered, and its content may include information such as risk level, threat target identifier, and suggested avoidance direction.

[0062] Specifically, the proximity parameter can be compared with the corresponding risk threshold. The proximity parameter includes, for example, the expected minimum approach distance D. The risk threshold includes, for example, the minimum safe distance threshold D_th. It is worth noting that this risk threshold may not be a fixed value, but can be dynamically adjusted based on various factors such as real-time airspace congestion, the performance of the UAV itself, and current weather conditions.

[0063] If the comparison result meets the risk conditions, such as when the calculated expected minimum approach distance D is less than the preset minimum safe distance threshold D_th, a collision risk is determined to exist. In response to this determination, a collision avoidance warning message is generated. This collision avoidance warning message includes, for example,: first, local output, such as driving an audible and visual alarm to issue an audio-visual warning; second, transmission to the ground station of the first UAV's remote controller, displayed in graphical and textual form on the flight control interface; and third, uploading the information to a cloud monitoring platform via a wireless communication link for remote monitoring and dispatch. The specific content of the warning message can be graded according to the risk level, such as divided into different levels like caution, warning, and emergency, and may include a simple avoidance suggestion vector.

[0064] In one embodiment provided in this application, based on the above-described solution, optionally, obtaining aircraft status information includes:

[0065] Receive a wireless signal compliant with the Broadcast Remote Identification (ROI) specification broadcast by at least one second UAV; decode the wireless signal to obtain the status information of the second UAV;

[0066] Establish a communication connection with the server and receive status information of aircraft in the target airspace sent by the server.

[0067] In this embodiment, a wireless signal conforming to the Broadcast Remote Identification (BRI) specification can be received from at least one second UAV and decoded to obtain the status information of the second UAV. The Broadcast Remote Identification (BRI) specification refers to a technical standard developed and published by air traffic control agencies or standards organizations, requiring UAVs to continuously broadcast their identity and status data during flight. This specification mandates definitions for the signal format, modulation method, transmission frequency, power, and included data fields to ensure interoperability between devices from different manufacturers. The wireless signal refers to a radio frequency electromagnetic wave carrying the data required by the aforementioned specification; its physical carrier is a radio wave in a specific frequency band, such as the ISM band, where digital information is loaded onto a carrier wave through a specific modulation method such as GFSK.

[0068] In this specific implementation, the early warning device integrates a radio frequency receiving module capable of tuning to the target frequency band. This module continuously listens for wireless signals in the airspace. When it captures a signal that matches preset characteristics, it performs down-conversion and demodulation processing, converting the radio frequency signal into a baseband digital data stream. Subsequently, the decoding unit parses the data stream according to the data frame structure specified in the broadcast remote identification specification. The decoding process includes, but is not limited to, frame synchronization, checksum decoding, and information field extraction. After successful decoding, structured status information of the second UAV can be obtained. This status information contains a set of standardized data fields, exemplarily including at least the UAV's unique identification code (e.g., serial number), real-time three-dimensional geographic coordinates (e.g., latitude, longitude, and altitude), ground velocity vector, heading angle, and timestamp.

[0069] In this embodiment, fused airspace situational information can be obtained from the server. Specifically, a communication connection is established with the server, and the system receives status information about aircraft in the target airspace from the server. The server, in this context, specifically refers to a ground-based remote computing platform with powerful data aggregation and processing capabilities. This platform, acting as an airspace information service center, functions to aggregate data from multiple surveillance sources. The communication connection refers to the network link established between the early warning equipment and the aforementioned server for bidirectional data exchange. This link can be implemented based on various wireless communication technologies, exemplarily including but not limited to cellular mobile communication networks such as 4G LTE or 5G NR, satellite communication links, or dedicated data links. The connection establishment process involves standard communication procedures such as network attachment, authentication, and IP session establishment.

[0070] In this specific implementation, the wireless communication module within the early warning device periodically or as needed executes a connection establishment procedure with a preset server address. Once the connection is successfully established and maintained, the device can initiate a data request to the server according to a predetermined protocol, or subscribe to a continuously pushed data stream from the server. This protocol may be, for example, an application layer protocol based on TCP or IP. The server responds to the request or, according to the subscription relationship, sends status information of aircraft in the target airspace. This aircraft status information covers a summary of the status of multiple aircraft detected within the target airspace, which is the geographical area of ​​current interest to the first UAV. These aircraft may include other UAVs whose broadcast signals were not directly detected, as well as, more importantly, manned aircraft equipped with ADS-B transmitters. The data format sent by the server can be a structured list or array, where each record corresponds to an aircraft, and the record fields include identification, location, altitude, speed, and heading. Through this approach, the early warning device obtains a more comprehensive airspace traffic situation picture that transcends its direct perception range, particularly supplementing manned aircraft information that cannot be obtained solely by receiving UAV broadcast signals.

[0071] In one embodiment provided in this application, based on the above-described scheme, optionally, identifying at least one target aircraft that meets preset monitoring conditions based on the aircraft status information includes:

[0072] Based on aircraft status information, the current relative distance and relative orientation between the candidate aircraft and the first UAV are calculated; the candidate aircraft includes at least one of the second UAV and the aircraft.

[0073] Determine whether the current relative distance of the candidate aircraft is within a preset monitoring distance range, and determine whether the relative orientation of the candidate aircraft is within a preset conflict sector;

[0074] If the current relative distance of the candidate aircraft is within the monitoring distance range and the relative orientation of the candidate aircraft is within the preset conflict sector, the candidate aircraft is identified as the target aircraft that meets the preset monitoring conditions.

[0075] In this embodiment, the relative motion geometry can be calculated first. Specifically, based on the acquired aircraft state information, the current relative distance and current relative bearing between the candidate aircraft and the first UAV are calculated. Here, "candidate aircraft" is an intermediate set concept, referring to all individual aircraft extracted from the aircraft state information that require threat assessment. This includes at least one type of aircraft, including the second UAV identified through direct broadcast signals and aircraft obtained through server data, specifically manned aircraft. The current relative distance represents the instantaneous straight-line interval between the candidate aircraft and the first UAV in three-dimensional space. It can be calculated based on the geographical coordinates of both parties, such as longitude, latitude, and altitude, using spatial geometric formulas, such as the spherical distance calculation formula based on an Earth model or a simplified Euclidean distance formula. The current relative bearing is a vector description representing the direction from the first UAV's position to the candidate aircraft's position. Its calculation can be achieved by converting the difference in horizontal coordinates between the two parties into the angle relative to geographic north or the UAV's nose direction, i.e., the azimuth and pitch angles.

[0076] Furthermore, it is determined whether the current relative distance of the candidate aircraft falls within a preset monitoring distance range, and simultaneously, whether the relative bearing of the candidate aircraft is within a preset conflict sector. The preset monitoring distance range is a predefined distance threshold interval, with a lower limit greater than zero and an upper limit set according to the UAV's performance, airspace category, and safety redundancy requirements. For example, this range might be set to 100 meters to 1000 meters from the first UAV. Determining whether the relative distance falls within this range involves checking whether the calculated distance value falls within this threshold interval. The preset conflict sector is a solid angular spatial region defined with the first UAV as its center and its current direction of motion as its reference axis. This sector aims to cover the directions where head-on, crossing, or tail-to-tail collisions are most likely to occur. For example, this sector can be defined as a horizontal sector area of ​​60 degrees to the left and right of the nose direction, and may include a certain vertical angle range. Determining whether the relative bearing is within this sector involves checking whether the calculated azimuth and pitch angles fall within this preset angle range.

[0077] Finally, when the judgment result for a candidate aircraft meets the following conditions: its current relative distance is within the monitoring distance range, and its relative bearing is within the preset conflict sector, the candidate aircraft is identified as a target aircraft that meets the preset monitoring conditions. Identifying a candidate aircraft as a target aircraft means that in the system's internal data representation, the object is marked with a specific threat identifier, and it is moved from the general candidate list to a high-priority target list for more accurate trajectory prediction and conflict analysis.

[0078] In one embodiment provided in this application, based on the above-described scheme, optionally, predicting the future trajectories of the first UAV and the target aircraft based on the state information of the target aircraft and the state information of the first UAV includes:

[0079] Based on the state information of the target aircraft, calculate the first expected position of the target aircraft at multiple consecutive time points in the future, and generate the future trajectory of the target aircraft based on the first expected position at the multiple consecutive time points.

[0080] Based on the state information of the first drone, calculate the second expected position of the first drone at multiple consecutive time points in the future, and generate the future trajectory of the first drone based on the second expected position at the multiple consecutive time points.

[0081] This involves calculating the target aircraft's first expected position at multiple consecutive future time points based on its state information, and then generating the target aircraft's future trajectory based on these first expected positions. The target aircraft's state information includes at least its spatial position at the latest moment, such as longitude, latitude, and altitude, as well as its velocity vector (magnitude and direction) and possible acceleration information. Multiple consecutive future time points refer to a series of discrete time points divided into fixed time intervals (time steps) extending into the future from the current moment. For example, this time interval could be the next thirty seconds, with a time step of 0.1 seconds or 1 second, forming a series of time points such as T + 0.1 seconds, T + 0.2 seconds, up to T + 30.0 seconds.

[0082] In the specific implementation of this embodiment, a preset motion extrapolation algorithm can be invoked, such as a uniform velocity model or a uniform acceleration and turning model. This algorithm uses the current state information of the target aircraft as the initial input condition. During calculation, the algorithm iteratively extrapolates along the time axis based on Newton's laws of motion. For each future discrete time point, the algorithm, based on the assumed motion state of the aircraft at the previous extrapolation time (its initial state being the current measured state), and combining its speed and possible rate of change of heading, integrates to calculate the spatial coordinates that the aircraft is expected to reach at that time point. These coordinates are the first expected position corresponding to that time point.

[0083] After obtaining the first expected positions for all selected future time points in sequence, these discrete positions are connected and encapsulated in chronological order. This connection is not a simple straight-line connection, but rather forms an ordered spatial position sequence. This spatial position sequence describes the continuous movement path of the target aircraft within the predicted time period, which is the generated future trajectory of the target aircraft.

[0084] On the other hand, the trajectory prediction sub-process for the first UAV includes: calculating the second expected position of the first UAV at multiple consecutive time points in the future based on the state information of the first UAV, and then generating the future trajectory of the first UAV based on the second expected position at these multiple consecutive time points. The state information of the first UAV is obtained in real time through airborne sensors such as a GPS receiver, inertial measurement unit, or directly from the flight control system bus. Its information dimensions are similar to those of the target aircraft's state information, including its own real-time position, speed, heading, and other data. The second expected position is logically identical to the first expected position, both referring to future spatial coordinates obtained through motion extrapolation. The term "second" is used here only for distinction.

[0085] In this embodiment, for the first UAV, a motion extrapolation model, which may be the same as or different from that of the target aircraft, can be used, with the current state of the first UAV itself as the initial input condition. Following the same time step sequence, the expected spatial coordinates of the first UAV at each future time point are iteratively calculated, thereby obtaining a series of second expected positions. By organizing and constructing these second expected position points in chronological order, a future trajectory of the first UAV describing its future plans or possible paths is formed.

[0086] In one embodiment provided in this application, based on the above-described scheme, optionally, predicting the future trajectories of the first UAV and the target aircraft based on the state information of the target aircraft and the state information of the first UAV includes:

[0087] The state information of the target aircraft is input into the motion prediction model of the target aircraft to obtain the future trajectory of the target aircraft.

[0088] The state information of the first UAV is input into the operation prediction model of the first UAV to obtain the future trajectory of the first UAV.

[0089] In this embodiment, the motion prediction model is a state deduction algorithm built based on physical laws of motion or historical data statistics. The target aircraft's state information serves as the model input parameters, including data fields such as timestamps, three-dimensional spatial coordinates, velocity vectors, and heading angles. Upon receiving this input vector, the model iteratively calculates using its embedded algorithm to deduce the expected spatial position sequence of the target aircraft at various consecutive time points within a preset time window in the future, which is the target aircraft's future trajectory.

[0090] Optionally, a separate operational prediction model is used to process the first UAV itself. The real-time state information of the first UAV is acquired via an onboard bus or sensor interface and formatted into an input vector that meets the model's requirements. The model parses and calculates the input state information, outputting the expected spatial position sequence of the first UAV within the same future time period.

[0091] In one embodiment provided in this application, based on the above-described scheme, optionally, determining the proximity between the future trajectory of the first UAV and the future trajectory of the target aircraft includes:

[0092] Based on the future trajectory of the first UAV and the future trajectory of the target aircraft, calculate the shortest predicted approach distance between the first UAV and the target aircraft within the prediction time window;

[0093] Based on the velocity vectors and relative positions of the first UAV and the target aircraft, the approach rate and the estimated time required to reach the shortest predicted approach distance are calculated.

[0094] The degree of proximity is determined based on at least one of the shortest predicted approach distance, the approach rate, and the required time.

[0095] In this embodiment, the shortest predicted approach distance can be calculated. Specifically, based on the future trajectories of the first UAV and the target aircraft, the shortest predicted approach distance between them within a prediction time window is calculated. The prediction time window refers to a future time interval covered during trajectory prediction, such as the next thirty seconds. The future trajectories of the first UAV and the target aircraft each represent a series of expected spatial locations arranged in chronological order. Calculating the shortest predicted approach distance requires traversing all corresponding or potentially intersecting time points on the two trajectories and calculating the straight-line spatial distance between them at each instant. The minimum value selected by comparing all these instantaneous distance values ​​is defined as the shortest predicted approach distance.

[0096] Optionally, the approach rate and estimated arrival time can be calculated. This involves calculating the approach rate and the estimated time required to reach the shortest predicted approach distance based on the velocity vectors and relative positions of the first UAV and the target aircraft. The velocity vector is a directed line segment describing the magnitude and direction of the aircraft's velocity, which can be obtained from its state information. The relative position describes the relative direction of the two aircraft in space at the current moment. The approach rate is a scalar representing the speed at which the first UAV and the target aircraft move closer or further apart along the line connecting them; its calculation requires projecting their respective velocity vectors onto the direction of their relative positions and then synthesizing them. The estimated arrival time is a time quantity representing the time required to reach the future shortest predicted approach distance point, calculated based on the current approach rate and the current relative distance.

[0097] Optionally, the degree of proximity can be determined. This involves determining the final degree of proximity based on at least one of three parameters: the calculated shortest predicted approach distance, the approach speed, and the estimated time to reach the target. The degree of proximity itself is a comprehensive assessment result; it can be a direct value of a single parameter or a composite index obtained by weighting or logically combining multiple parameters. For example, in a simple determination, the value of the shortest predicted approach distance can be directly used as the degree of proximity. In more complex assessments, a comprehensive evaluation function can be established, incorporating the distance, speed, and time parameters simultaneously in the calculation, outputting a value or level reflecting the overall risk level. In this way, the geometric analysis, kinematic analysis, and temporal analysis of the trajectory are integrated into a unified and comparable degree of proximity value. This value will be directly used for comparison with preset collision risk conditions, thereby triggering corresponding early warning decisions.

[0098] In one embodiment provided in this application, based on the above-described scheme, optionally, the process of determining whether the proximity meets a preset collision risk condition is as follows: Figure 2 As shown, it includes:

[0099] S201: Compare the parameters included in the proximity level with the risk thresholds corresponding to the parameters to obtain the comparison results of the parameters.

[0100] In this embodiment, one or more specific parameters included in the proximity level can be compared one by one with a risk threshold pre-set and stored for each parameter to obtain the comparison result of the parameters. Specifically, the parameters included in the proximity level can refer to the aforementioned calculated shortest predicted approach distance, approach speed, and estimated arrival time, etc. The risk threshold set for each parameter is a pre-determined threshold value based on a combination of factors such as airspace operation rules, UAV safety performance, and historical statistical data.

[0101] S202: If the comparison result indicates that the shortest predicted approach distance is less than the first risk threshold and the estimated arrival time is less than the second risk threshold, determine that the degree of proximity meets the preset collision risk condition.

[0102] Optionally, a risk warning can be triggered based on the comparison results of the parameters, using preset logical rules. The preset logical rules define the method for making warning decisions based on the comparison results of one or more parameters.

[0103] For example, in one implementation, the rule can be a simple veto system, where an alert is immediately triggered as soon as the single parameter of the shortest predicted approach distance falls below its safety threshold. In another implementation, the rule can be a multi-parameter combined voting system, such as requiring both the shortest predicted approach distance and the estimated arrival time to simultaneously exceed their respective thresholds before triggering an alert; alternatively, the threshold for the shortest predicted approach distance can be dynamically adjusted based on the approach rate, followed by a comprehensive judgment. In practical implementation, the judgment operation involves the logic processing unit parsing and calculating the aforementioned comparison results, and outputting a final binary decision signal based on the built-in judgment logic: whether to trigger an alert or not.

[0104] and Figure 1 Corresponding to the method, embodiments of this application also provide a drone collision avoidance warning system for... Figure 1 The specific implementation of the method is shown in the following structural diagram: Figure 3 As shown, it includes:

[0105] The acquisition unit 301 is used to acquire aircraft status information, which includes status information broadcast by the second UAV and / or status information of aircraft in the target airspace sent by the server; the target airspace is the airspace where the first UAV is located.

[0106] The identification unit 302 is used to identify at least one target aircraft that meets preset monitoring conditions based on the aircraft status information, wherein the target aircraft is the second UAV or the aircraft.

[0107] Prediction unit 303 is used to predict the future trajectories of the first UAV and the target aircraft based on the state information of the target aircraft and the state information of the first UAV.

[0108] Determining unit 304 is used to determine the degree of proximity between the future trajectory of the first UAV and the future trajectory of the target aircraft;

[0109] The output unit 305 is used to output anti-collision warning information for the first drone in response to determining that the proximity meets the preset collision risk conditions.

[0110] This application also provides an electronic device, the structural schematic diagram of which is shown below. Figure 4 As shown, it specifically includes a memory 401 and one or more instructions 402, wherein one or more instructions 402 are stored in the memory 401 and are configured to be executed by one or more processors 403 to perform the above-mentioned communication tunnel establishment method.

[0111] It should be noted that the various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0112] Finally, it should be noted that in this paper, relational terms such as first and second are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations.

[0113] For ease of description, the above system is described by dividing it into various functional units. Of course, in implementing this application, the functions of each unit can be implemented in one or more software and / or hardware.

[0114] As can be seen from the above description of the embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus necessary general-purpose hardware platforms. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in various embodiments or some parts of the embodiments of this application.

[0115] The solution provided in this application has been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of this application. The description of the above embodiments is only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for preventing collisions and providing early warning for unmanned aerial vehicles (UAVs), characterized in that, The method is applied to an early warning device, which is mounted on a first unmanned aerial vehicle (UAV), and includes: The aircraft status information is acquired, including the status information broadcast by the second UAV and / or the status information of the aircraft in the target airspace sent by the server; the target airspace is the airspace where the first UAV is located. Based on the aircraft status information, at least one target aircraft that meets the preset monitoring conditions is identified, wherein the target aircraft is the second UAV or the aircraft. Based on the status information of the target aircraft and the status information of the first UAV, predict the future trajectories of the first UAV and the target aircraft; Determine the degree of proximity between the future trajectory of the first UAV and the future trajectory of the target aircraft; In response to determining that the proximity meets a preset collision risk condition, a collision avoidance warning is output for the first drone.

2. The method according to claim 1, characterized in that, The acquisition of aircraft status information includes: Receive a wireless signal compliant with the Broadcast Remote Identification (ROI) specification broadcast by at least one second UAV; decode the wireless signal to obtain the status information of the second UAV; Establish a communication connection with the server and receive status information of aircraft in the target airspace sent by the server.

3. The method according to claim 1, characterized in that, The step of identifying at least one target aircraft that meets preset monitoring conditions based on the aircraft status information includes: Based on aircraft status information, the current relative distance and relative orientation between the candidate aircraft and the first UAV are calculated; the candidate aircraft includes at least one of the second UAV and the aircraft. Determine whether the current relative distance of the candidate aircraft is within a preset monitoring distance range, and determine whether the relative orientation of the candidate aircraft is within a preset conflict sector; If the current relative distance of the candidate aircraft is within the monitoring distance range and the relative orientation of the candidate aircraft is within the preset conflict sector, the candidate aircraft is identified as the target aircraft that meets the preset monitoring conditions.

4. The method according to claim 1, characterized in that, The step of predicting the future trajectories of the first UAV and the target aircraft based on the state information of the target aircraft and the state information of the first UAV includes: Based on the state information of the target aircraft, calculate the first expected position of the target aircraft at multiple consecutive time points in the future, and generate the future trajectory of the target aircraft based on the first expected position at the multiple consecutive time points. Based on the state information of the first drone, calculate the second expected position of the first drone at multiple consecutive time points in the future, and generate the future trajectory of the first drone based on the second expected position at the multiple consecutive time points.

5. The method according to claim 1, characterized in that, The step of predicting the future trajectories of the first UAV and the target aircraft based on the state information of the target aircraft and the state information of the first UAV includes: The state information of the target aircraft is input into the motion prediction model of the target aircraft to obtain the future trajectory of the target aircraft. The state information of the first UAV is input into the operation prediction model of the first UAV to obtain the future trajectory of the first UAV.

6. The method according to claim 1, characterized in that, Determining the proximity between the future trajectory of the first UAV and the future trajectory of the target aircraft includes: Based on the future trajectory of the first UAV and the future trajectory of the target aircraft, calculate the shortest predicted approach distance between the first UAV and the target aircraft within the prediction time window; Based on the velocity vectors and relative positions of the first UAV and the target aircraft, the approach rate and the estimated time required to reach the shortest predicted approach distance are calculated. The degree of proximity is determined based on at least one of the shortest predicted approach distance, the approach rate, and the required time.

7. The method according to claim 6, characterized in that, The process of determining that the proximity meets preset collision risk conditions includes: The parameters included in the degree of proximity are compared with the risk thresholds corresponding to the parameters to obtain the comparison results of the parameters; If the comparison result indicates that the shortest predicted approach distance is less than a first risk threshold and the estimated arrival time is less than a second risk threshold, then the proximity is determined to meet a preset collision risk condition.

8. A drone collision avoidance early warning system, characterized in that, The system is applied to an early warning device, which is mounted on a first unmanned aerial vehicle (UAV), and includes: The acquisition unit is used to acquire aircraft status information, which includes status information broadcast by the second UAV and / or status information of aircraft in the target airspace sent by the server; the target airspace is the airspace where the first UAV is located. The identification unit is used to identify at least one target aircraft that meets preset monitoring conditions based on the aircraft status information, wherein the target aircraft is the second UAV or the aircraft. The prediction unit is used to predict the future trajectories of the first UAV and the target aircraft based on the state information of the target aircraft and the state information of the first UAV. A determining unit is configured to determine the degree of proximity between the future trajectory of the first UAV and the future trajectory of the target aircraft; The output unit is used to output anti-collision warning information for the first UAV in response to determining that the proximity meets the preset collision risk conditions.

9. A storage medium, characterized in that, The storage medium includes storage instructions, wherein, when the instructions are executed, the device containing the storage medium is controlled to perform the drone collision avoidance warning method as described in any one of claims 1 to 7.

10. An electronic device, characterized in that, It includes a memory and one or more instructions, wherein one or more instructions are stored in the memory and configured to be executed by one or more processors as described in any one of claims 1 to 7.

Images