Emergency unmanned aerial vehicle navigation method and apparatus, computer device, and storage medium

Abstract

The present application relates to the field of unmanned aerial vehicle navigation, and discloses an emergency unmanned aerial vehicle navigation method and apparatus, a computer device, and a storage medium. The method comprises: obtaining historical acquired data of a laser radar on an unmanned aerial vehicle for a target tunnel, and establishing an initial three-dimensional model of the target tunnel; upon detection that an emergency event happens, obtaining real-time acquired data of the laser radar on the unmanned aerial vehicle for the target tunnel, and establishing a current three-dimensional model of the target tunnel; comparing the initial three-dimensional model with the current three-dimensional model, comparing an ultra-wideband positioning location with the location of an ultra-wideband base station, and determining a current location of the unmanned aerial vehicle; determining a target flight heading angle; and obtaining a destination location of the unmanned aerial vehicle, and on the basis of the current location, the destination location and the target flight heading angle of the unmanned aerial vehicle, navigating the unmanned aerial vehicle. The present application implements flight navigation of the unmanned aerial vehicle by acquiring data by means of the laser radar, positioning the unmanned aerial vehicle, and obtaining the target flight heading angle on the basis of the initial three-dimensional model and the real-time acquired data.

Description

Emergency UAV navigation method, device, computer equipment and storage medium

[0001] This application claims priority to the Chinese patent application filed with the China Patent Office on December 19, 2023, with application number 202311754758.X and invention name “A method, device, computer equipment and storage medium for emergency drone navigation”, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The present application relates to the field of drone navigation technology, and specifically to an emergency drone navigation method, device, computer equipment, and storage medium. Background Art

[0003] As highway construction continues to make breakthroughs, the number and length of tunnels are increasing, and the probability of emergencies occurring within tunnels is also increasing. After an emergency occurs, vehicles are often unable to pass normally, necessitating the use of drones to survey the site and take appropriate action.

[0004] Existing technologies typically use lighting fixtures to inspect the tunnel entrance, middle, and exit sections separately, providing full coverage and comprehensive inspection of all tunnel sections. This allows drones to navigate based on the actual situation. However, when smoke is thick and visibility is low in the tunnel, drone navigation becomes difficult.

[0005] Summary of the Invention

[0006] In view of this, the present application provides an emergency drone navigation method, device, computer equipment and storage medium to solve the problem of excessive smoke in tunnels, low visibility and difficulty in drone navigation in the prior art.

[0007] In a first aspect, the present application provides an emergency drone navigation method, the method comprising:

[0008] Obtain the location of the ultra-wideband base station in the target tunnel and the historical data collected by the UAV's lidar on the target tunnel, and build an initial 3D model of the target tunnel based on the historical data;

[0009] When an emergency event is detected, the real-time data collected by the UAV's lidar on the target tunnel and the ultra-wideband positioning data collected by the UAV's airborne ultra-wideband are obtained, and the current three-dimensional model of the target tunnel is established based on the real-time collected data;

[0010] Compare the initial 3D model with the current 3D model, compare the UWB positioning position with the UWB base station position, and determine the current position of the UAV based on the comparison results;

[0011] Determine the target flight heading angle of the UAV based on the initial 3D model and real-time collected data;

[0012] Get the destination position of the drone and navigate the drone based on its current position, destination position, and target flight heading angle.

[0013] This application uses lidar to collect data from the target tunnel, establishes an initial three-dimensional model of the target tunnel based on historical collected data, and establishes a current three-dimensional model based on real-time collected data. The use of lidar can collect data on the target tunnel without being affected by thick smoke and visibility in the tunnel. The initial three-dimensional model and the current three-dimensional model are compared, and the ultra-wideband positioning position and the ultra-wideband base station position are compared to achieve positioning of the drone. The target flight heading angle of the drone is obtained based on the initial three-dimensional model and the real-time collected data, thereby achieving navigation of the drone from the current position to the end position according to the target flight heading angle.

[0014] In an optional embodiment, comparing the initial three-dimensional model with the current three-dimensional model, comparing the ultra-wideband positioning position with the ultra-wideband base station position, and determining the current position of the drone based on the comparison results includes:

[0015] Extracting a first feature point cloud from the initial three-dimensional model and extracting a second feature point cloud from the current three-dimensional model;

[0016] Comparing the first feature point cloud with the second feature point cloud to determine a first position of the UAV;

[0017] Compare the UWB positioning position with the UWB base station position to determine the second position of the UAV;

[0018] The first position and the second position are weightedly fused, and the weighted fused position is determined as the current position of the UAV.

[0019] This application obtains the first position of the drone by comparing the feature point cloud of the initial three-dimensional model and the current three-dimensional model, obtains the second position of the drone by comparing the ultra-wideband positioning position and the ultra-wideband base station position, and uses weighted fusion to comprehensively confirm the position of the drone to improve the accuracy of the drone's position.

[0020] In an optional embodiment, weighted fusion of the first position and the second position includes:

[0021] The reliability of the first position and the second position is obtained by experiment;

[0022] Determining a weight of the first position and a weight of the second position based on the credibility of the first position and the second position respectively;

[0023] The first position and the second position are weightedly fused based on the weight of the first position and the weight of the second position.

[0024] The present application obtains the credibility of the first position and the second position through experiments, and uses the credibility to perform weighted fusion of the first position and the second position, thereby flexibly adjusting the weights of the first position and the second position.

[0025] In an optional embodiment, determining the target flight heading angle of the UAV based on the initial three-dimensional model and the real-time collected data includes:

[0026] Based on the initial 3D model, the centerline of the target tunnel is determined and used as the initial flight path for the UAV.

[0027] Establish a lidar coordinate system based on real-time collected data, and establish a tunnel coordinate system based on the initial flight path;

[0028] The heading angle output by the gyroscope on the UAV is obtained, and the target flight heading angle of the UAV is determined based on the angle between the horizontal coordinate axis of the lidar coordinate system and the horizontal coordinate axis of the tunnel coordinate system and the heading angle output by the gyroscope.

[0029] This application establishes a lidar coordinate system and a tunnel coordinate system, integrates the heading angle output by the gyroscope, and comprehensively determines the target heading angle of the drone. It can overcome the errors and noise caused by calculating the heading angle through data from a single sensor, so as to navigate the drone and improve the accuracy of the target flight heading angle.

[0030] In an optional embodiment, after navigating the drone based on the current position, the destination position, and the target flight heading angle of the drone, the method further includes:

[0031] Get the current flight route of the drone;

[0032] Compare the current flight route with the initial flight route to determine whether the drone's flight has deviated;

[0033] If the drone's flight deviates, the drone's flight heading angle is adjusted so that the adjusted flight heading angle is consistent with the target flight heading angle.

[0034] This application determines the drone flight deviation by comparing the current flight route with the initial flight route, and adjusts the drone's flight heading angle in time when the drone flight deviates, so as to avoid the situation where the drone flight deviation causes the branch mission to be unable to be completed.

[0035] In an optional embodiment, after navigating the drone based on the current position, the destination position, and the flight heading angle of the drone, the method further includes:

[0036] Obtain detection data collected by the millimeter-wave radar on the drone and determine the location of obstacles in the target tunnel based on the detection data;

[0037] If the current flight path of the drone coincides with the location of the obstacle, the current flight path will be adjusted.

[0038] This application determines the location of obstacles in the target tunnel so that when the UAV flight route coincides with the obstacle position, the flight route can be adjusted in time to avoid collision between the UAV and the obstacle.

[0039] In a second aspect, the present application provides an emergency drone navigation device, which includes:

[0040] The first model building module is used to obtain the location of the ultra-wideband base station in the target tunnel and the historical data collected by the lidar on the drone on the target tunnel, and to build an initial three-dimensional model of the target tunnel based on the historical data;

[0041] The second model building module is used to obtain the real-time data collected by the UAV's lidar of the target tunnel and the ultra-wideband positioning position collected by the UAV's airborne ultra-wideband when an emergency event is detected, and to build a current three-dimensional model of the target tunnel based on the real-time collected data;

[0042] A first determination module is configured to compare the initial three-dimensional model with the current three-dimensional model, compare the ultra-wideband positioning position with the ultra-wideband base station position, and determine the current position of the UAV based on the comparison results;

[0043] The second determination module is used to determine the target flight heading angle of the UAV based on the initial three-dimensional model and the real-time collected data;

[0044] The navigation module is used to obtain the destination position of the UAV and navigate the UAV based on the current position of the UAV, the destination position and the target flight heading angle.

[0045] In an optional implementation, the first determining module includes:

[0046] an extraction unit, configured to extract a first feature point cloud from the initial three-dimensional model and a second feature point cloud from the current three-dimensional model;

[0047] a first determining unit, configured to compare the first feature point cloud with the second feature point cloud to determine a first position of the UAV;

[0048] a second determining unit, configured to compare the ultra-wideband positioning position with the ultra-wideband base station position to determine a second position of the UAV;

[0049] The third determining unit is configured to perform weighted fusion on the first position and the second position, and determine the weighted fusion position as the current position of the UAV.

[0050] In a third aspect, the present application provides a computer device comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, computer instructions being stored in the memory, and the processor executing the computer instructions to thereby execute the emergency drone navigation method of the first aspect or any corresponding embodiment thereof.

[0051] In a fourth aspect, the present application provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the emergency drone navigation method of the above-mentioned first aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the specific implementation methods of the present application or the technical solutions in the prior art, the following is a brief introduction to the drawings required for use in the specific implementation methods or the description of the prior art. Obviously, the drawings described below are some implementation methods of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0053] FIG1 is a schematic diagram of a flow chart of an emergency drone navigation method according to an embodiment of the present application;

[0054] FIG2 is a schematic diagram of an application of an emergency drone navigation method according to an embodiment of the present application;

[0055] FIG3 is a structural block diagram of an emergency drone navigation device according to an embodiment of the present application;

[0056] FIG4 is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present application. DETAILED DESCRIPTION

[0057] To make the purpose, technical solutions, and advantages of the embodiments of the present application more clear, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without making creative efforts shall fall within the scope of protection of this application.

[0058] With the increasing number and length of tunnels, the probability of emergencies occurring within them has significantly increased. When an emergency occurs, the situation becomes urgent, necessitating the use of drones to quickly reach the scene and conduct a survey. Drones, with their high flight speed and unaffected by ground traffic conditions, are ideal tools for investigating and handling emergencies within tunnels.

[0059] In related technologies, tunnel surveys using lighting fixtures are easily affected by thick smoke, and drone navigation is difficult under conditions of low visibility. There is often no satellite navigation and positioning information in tunnels, making it impossible to use satellite positioning information to navigate and locate drones. Since a large number of vehicles may pass through tunnels, the vehicles cause electromagnetic field disturbances, and the magnetic compass cannot work properly. Therefore, the method of using a magnetic compass or dual GPS (Global Positioning System) antennas for navigation and positioning is completely ineffective. The space in the tunnel is small, and the accuracy requirements for drone positioning and the flight control requirements for drones are high. Therefore, how to navigate drones in the event of an emergency is an urgent problem to be solved.

[0060] According to an embodiment of the present application, an embodiment of an emergency drone navigation method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0061] In this embodiment, an emergency drone navigation method is provided, which can be used for a mobile terminal. FIG1 is a flow chart of the emergency drone navigation method according to an embodiment of the present application. As shown in FIG1 , the process includes the following steps:

[0062] Step S101: obtain the location of the ultra-wideband base station in the target tunnel and the historical data collected by the laser radar on the drone on the target tunnel, and establish an initial three-dimensional model of the target tunnel based on the historical data.

[0063] In an embodiment of the present application, an ultra-wideband base station is pre-installed in the target tunnel, and the drone is equipped with a sensor including a laser radar and an airborne ultra-wideband (UWB).

[0064] When the data collection conditions in the target tunnel are good, for example, when there are no vehicles or few vehicles passing through the target tunnel, the laser radar on the drone is used to collect data from the target tunnel to obtain historical collection data, and the initial three-dimensional model of the target tunnel is pre-established using the historical collection data.

[0065] Step S102: When an emergency event is detected, the real-time data collected by the UAV's laser radar on the target tunnel and the ultra-wideband positioning position collected by the UAV's airborne ultra-wideband are obtained, and the current three-dimensional model of the target tunnel is established based on the real-time collected data.

[0066] In an embodiment of the present application, when an emergency event occurs, the mobile terminal sends a flight mission to the drone. When the drone performs the flight mission, it uses a lidar to collect data on the target tunnel in real time, obtains real-time collected data, and uses the real-time collected data to establish a current three-dimensional model of the target tunnel.

[0067] The UAV's onboard ultra-wideband communicates with the ultra-wideband base station in the target tunnel to obtain the ultra-wideband positioning position collected by the UAV's onboard ultra-wideband.

[0068] Specifically, the data collected by the lidar is point cloud data. The initial three-dimensional model is established based on the historical collected data, and the current three-dimensional model is established based on the real-time collected data. Both can be achieved through Trimble RealWorks point cloud data processing software. The point cloud data collected by the lidar is imported into the point cloud data processing software, the point cloud data is pre-processed, and the pre-processed point cloud data is converted into a format suitable for Houdini. The three-dimensional model is loaded using Houdini software. The three-dimensional model can also be generated by other methods. This is only an example and is not intended to be limiting.

[0069] Step S103 : Compare the initial three-dimensional model with the current three-dimensional model, compare the ultra-wideband positioning position with the ultra-wideband base station position, and determine the current position of the UAV based on the comparison results.

[0070] In an embodiment of the present application, the current three-dimensional model is compared with the pre-built initial three-dimensional model to determine the specific position of the tunnel segment corresponding to the constructed current three-dimensional model in the entire target tunnel segment, and the ultra-wideband positioning position is compared with the ultra-wideband base station position to determine the communication distance between the drone and the ultra-wideband in the target tunnel, and the current position of the drone is comprehensively determined.

[0071] Step S104: determining the target flight heading angle of the UAV based on the initial three-dimensional model and the real-time collected data.

[0072] In an embodiment of the present application, the target flight heading angle is determined based on the initial three-dimensional model and real-time collected data to navigate the flight of the drone based on the situation in the target tunnel and the real-time flight situation of the drone.

[0073] Step S105: Acquire the destination position of the UAV, and navigate the UAV based on the current position of the UAV, the destination position, and the target flight heading angle.

[0074] In an embodiment of the present application, the end position of the drone is obtained, which can be the end position input by the user in real time, or the end position pre-set when the drone performs a flight mission. Based on the current position and end position of the drone, the drone is navigated according to the target flight heading angle.

[0075] The emergency drone navigation method provided in this embodiment uses a laser radar to collect data from a target tunnel, establishes an initial three-dimensional model of the target tunnel based on historically collected data, and establishes a current three-dimensional model based on real-time collected data. The laser radar can collect data from the target tunnel without being affected by thick smoke or visibility in the tunnel. The initial three-dimensional model is compared with the current three-dimensional model, and the ultra-wideband positioning position is compared with the ultra-wideband base station position to achieve positioning of the drone. The target flight heading angle of the drone is obtained based on the initial three-dimensional model and the real-time collected data, thereby enabling navigation of the drone from its current position to its destination position according to the target flight heading angle.

[0076] Specifically, in one embodiment, the above step S103 specifically includes the following steps:

[0077] Step S1031 : extracting a first feature point cloud from the initial three-dimensional model and extracting a second feature point cloud from the current three-dimensional model.

[0078] Step S1032: Compare the first feature point cloud and the second feature point cloud to determine the first position of the UAV.

[0079] Step S1033: Compare the ultra-wideband positioning position with the ultra-wideband base station position to determine the second position of the UAV.

[0080] Step S1034: Perform weighted fusion on the first position and the second position, and determine the weighted fused position as the current position of the UAV.

[0081] In an embodiment of the present application, a first feature point cloud and a second feature point cloud are extracted from the initial three-dimensional model and the current three-dimensional model, respectively. The feature point cloud in the three-dimensional model can be extracted using point feature histograms (PFH), or the feature point cloud in the three-dimensional model can be extracted using fast point feature histograms (FPFH). This is only an example and is not intended to be limiting.

[0082] The first feature point cloud and the second feature point cloud are compared. The first feature point cloud and the second feature point cloud can be compared using a point cloud registration algorithm. Specifically, the distance between the first feature point cloud and the second feature point cloud can be calculated using an ICP (Iterative Closest Point) point cloud registration algorithm. The distance between the first feature point cloud and the second feature point cloud is determined as the position of the current three-dimensional model in the initial three-dimensional model. According to the correspondence between the three-dimensional model and the target tunnel, the actual position of the UAV in the target tunnel is determined.

[0083] The UAV’s onboard ultra-wideband communicates with the ultra-wideband base station through the UWB tag, and determines the actual position of the UAV in the target tunnel based on the signal received by the UAV’s onboard ultra-wideband.

[0084] The positions of the UAV obtained by the above two methods are weighted and fused to obtain the current position of the UAV.

[0085] The first position of the UAV is obtained by comparing the feature point cloud of the initial three-dimensional model with the current three-dimensional model. The second position of the UAV is obtained by comparing the ultra-wideband positioning position with the ultra-wideband base station position. The position of the UAV is comprehensively confirmed using weighted fusion to improve the accuracy of the UAV position.

[0086] Specifically, in one embodiment, the weighted fusion of the first position and the second position in step S1034 includes the following steps:

[0087] Step S10341: obtain the credibility of the first position and the second position through experiments.

[0088] Step S10342: Determine the weight of the first position and the weight of the second position based on the credibility of the first position and the second position respectively.

[0089] Step S10343: performing weighted fusion on the first position and the second position based on the weight of the first position and the weight of the second position.

[0090] In an embodiment of the present application, the credibility of the first position and the second position is obtained through a limited number of experiments. For example, if the credibility of the first position is 80% and the credibility of the second position is 20%, the weight of the first position is set to 0.8 and the weight of the second position is set to 0.2. A weighted fusion is performed based on the weight of the first position and the weight of the second position to finally obtain the position of the drone.

[0091] The credibility of the first position and the second position is obtained through experiments, and the first position and the second position are weightedly fused using the credibility, so as to flexibly adjust the weights of the first position and the second position.

[0092] Specifically, in one embodiment, determining the target flight heading angle of the UAV based on the initial three-dimensional model and the real-time collected data in step S104 specifically includes the following steps:

[0093] Step S1041: Based on the initial three-dimensional model, determine the center line of the target tunnel, and determine the center line as the initial flight route of the UAV.

[0094] Step S1042: establishing a laser radar coordinate system based on the real-time collected data, and establishing a tunnel coordinate system based on the initial flight route.

[0095] Step S1043, obtaining the heading angle output by the gyroscope on the UAV, and determining the target flight heading angle of the UAV based on the angle between the horizontal coordinate axis of the lidar coordinate system and the horizontal coordinate axis of the tunnel coordinate system and the heading angle output by the gyroscope.

[0096] In an embodiment of the present application, the centerline of the target tunnel is determined as the initial flight path of the drone based on the initial three-dimensional model. Specifically, the initial flight path can be determined by taking the distances between the top and bottom of the target tunnel and the distances between the left and right sides of the target tunnel into account. If there are vehicles passing through, the initial flight path can also be determined by taking the same curves from the top, bottom, left, and right sides of the target tunnel into account, based on the height of the vehicles passing through the target tunnel.

[0097] Based on real-time data, a LiDAR coordinate system was established, with the drone's position as the origin and the LiDAR-collected point cloud data as coordinates. The x-axis was horizontally forward, the y-axis was horizontally leftward, and the z-axis was vertically upward. A tunnel coordinate system was established based on the initial flight path, with a point on the initial flight path as the origin, the x-axis as the tangent of the horizontal projection of the initial flight path, the y-axis determined according to the right-hand rule, and the z-axis pointing vertically upward.

[0098] The heading angle output by the three-axis gyroscope inside the UAV flight control system is obtained. Since there are noise errors in the data collected by the lidar and the data measured by the gyroscope, the angle between the x-axis of the lidar coordinate system and the x-axis of the tunnel coordinate system and the heading angle output by the three-axis gyroscope inside the UAV flight control system are fused. The data is cleaned to reduce the noise error, and the heading angle after data fusion is determined as the target flight heading angle.

[0099] By establishing the lidar coordinate system and the tunnel coordinate system, integrating the heading angle output by the gyroscope, and comprehensively determining the target heading angle of the UAV, and using multiple sensors to fuse the heading angle data, it is possible to overcome the errors and noise caused by calculating the heading angle through data from a single sensor, thereby improving the accuracy of the target flight heading angle.

[0100] Specifically, in one embodiment, the emergency drone navigation method provided by the embodiment of the present application further includes the following steps:

[0101] Step S105: Obtain the current flight route of the UAV.

[0102] Step S106: Compare the current flight route with the initial flight route to determine whether the UAV flight has deviated.

[0103] Step S107: If the UAV flight deviates, the flight heading angle of the UAV is adjusted so that the adjusted flight heading angle is consistent with the target flight heading angle.

[0104] In this embodiment, the drone's current flight path is determined by acquiring data collected by the drone's laser radar, millimeter-wave radar, and airborne ultra-wideband radar. The drone's current flight path is compared with the initial flight path to determine whether the drone's position and heading angle have deviated.

[0105] If the drone's position and heading angle do not deviate, it will continue to fly at the current heading angle and execute the next flight mission. If the drone's position and heading angle deviate, it will adjust the heading angle so that the adjusted heading angle is consistent with the target heading angle, and the drone will move closer to the initial flight path. After the heading angle is adjusted, it will continue to fly and execute the next flight mission.

[0106] By comparing the current flight route with the initial flight route, the drone flight deviation is determined, and when the drone flight deviates, the drone's flight heading angle is adjusted in time to avoid the situation where the drone flight deviation causes the branch mission to be unable to be completed.

[0107] Specifically, in one embodiment, the emergency drone navigation method provided by the embodiment of the present application further includes the following steps:

[0108] Step S108: Acquire detection data collected by the millimeter-wave radar on the UAV, and determine the location of obstacles in the target tunnel based on the detection data.

[0109] Step S109: If the current flight route of the UAV coincides with the position of the obstacle, the current flight route is adjusted.

[0110] In this embodiment of the present application, the sensors onboard the drone also include four millimeter-wave radars, mounted forward, upward, left, and right. These radars detect obstacles in all directions of the target tunnel and, based on the detection data, determine the location of obstacles within the target tunnel, including the tunnel section within the target tunnel and its relative position to the target tunnel section. The drone then determines whether the current flight path of the drone overlaps with the obstacle. If so, the drone adjusts its flight path by circumventing the obstacle to the left or right, thereby avoiding the obstacle.

[0111] By determining the location of obstacles in the target tunnel, the flight route of the UAV can be adjusted in time when the flight route of the UAV coincides with the location of the obstacle to avoid collision between the UAV and the obstacle.

[0112] As a specific application embodiment of the present application, as shown in FIG2 , the sensors installed on the drone include a laser radar, a three-axis gyroscope, an airborne ultra-wideband, and a millimeter-wave radar. Based on the historical data collected by the laser radar on the drone on the target tunnel, an initial three-dimensional model of the target tunnel is pre-constructed, and the position of the ultra-wideband base station in the target tunnel and in the initial three-dimensional model are pre-calibrated. When the drone performs a flight mission, the real-time data collected by the laser radar on the drone on the target tunnel is obtained, and the current three-dimensional model of the target tunnel is constructed in real time. The current three-dimensional model is compared with the initial three-dimensional model, and the position of the drone is determined by combining the comparison results of the ultra-wideband positioning position and the ultra-wideband base station position. The target flight heading angle is determined by combining the heading angle output by the three-axis gyroscope, and the drone is navigated.

[0113] During a drone mission, the current flight path is compared with the initial flight path to determine if the drone has deviated. If the drone has not deviated, it continues to fly in the direction of the current heading angle and executes the next mission. If the drone has deviated, the heading angle is adjusted and the next mission is executed after the adjustment is complete. Obstacle locations are determined based on millimeter-wave radar detection data. If the drone's flight path coincides with the obstacle, it avoids the obstacle by maneuvering left or right. Finally, it determines whether the drone has reached the end of its trajectory, or manually takes over the drone and waits until the drone reaches the end of its trajectory before navigation is completed.

[0114] This embodiment also provides an emergency drone navigation device, which is used to implement the above-mentioned embodiments and optional implementations. Details that have already been described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation using hardware, or a combination of software and hardware, is also possible and contemplated.

[0115] This embodiment provides an emergency drone navigation device, as shown in FIG3 , including:

[0116] The first model building module 301 is used to obtain the location of the ultra-wideband base station in the target tunnel and the historical data collected by the laser radar on the drone on the target tunnel, and to build an initial three-dimensional model of the target tunnel based on the historical data.

[0117] The second model building module 302 is used to obtain the real-time data collected by the UAV's lidar on the target tunnel and the ultra-wideband positioning position collected by the UAV's onboard ultra-wideband when an emergency event is detected, and to build a current three-dimensional model of the target tunnel based on the real-time collected data.

[0118] The first determination module 303 is configured to compare the initial 3D model with the current 3D model, compare the ultra-wideband positioning position with the ultra-wideband base station position, and determine the current position of the UAV based on the comparison results.

[0119] The second determination module 304 is configured to determine the target flight heading angle of the UAV based on the initial three-dimensional model and the real-time collected data.

[0120] The navigation module 305 is used to obtain the destination position of the drone and navigate the drone based on the current position of the drone, the destination position and the target flight heading angle.

[0121] In some optional implementations, the first determining module 303 includes:

[0122] The extraction unit is used to extract a first feature point cloud from the initial three-dimensional model and a second feature point cloud from the current three-dimensional model.

[0123] The first determining unit is configured to compare the first feature point cloud with the second feature point cloud to determine a first position of the UAV.

[0124] The second determining unit is configured to compare the ultra-wideband positioning position with the ultra-wideband base station position to determine a second position of the UAV.

[0125] The third determining unit is configured to perform weighted fusion on the first position and the second position, and determine the weighted fusion position as the current position of the UAV.

[0126] In some optional implementations, the third determining unit includes:

[0127] The credibility obtaining subunit is used to obtain the credibility of the first position and the second position through experiments.

[0128] The determining subunit is configured to determine a weight of the first position and a weight of the second position respectively based on the credibility of the first position and the second position.

[0129] The weighted fusion subunit is configured to perform weighted fusion on the first position and the second position based on the weight of the first position and the weight of the second position.

[0130] In some optional implementations, the second determining module 304 includes:

[0131] The fourth determining unit is used to determine the center line of the target tunnel based on the initial three-dimensional model, and determine the center line as the initial flight route of the UAV.

[0132] The establishment unit is used to establish a lidar coordinate system based on real-time collected data and to establish a tunnel coordinate system based on the initial flight route.

[0133] The fifth determination unit is used to obtain the heading angle output by the gyroscope on the UAV, and determine the target flight heading angle of the UAV according to the angle between the horizontal coordinate axis of the lidar coordinate system and the horizontal coordinate axis of the tunnel coordinate system and the heading angle output by the gyroscope.

[0134] In some optional embodiments, the device further comprises:

[0135] The acquisition module is used to obtain the current flight route of the drone.

[0136] The judgment module is used to compare the current flight route with the initial flight route to determine whether the drone flight has deviated.

[0137] The first adjustment module is used to adjust the flight heading angle of the drone if the drone flight deviates, so that the adjusted flight heading angle is consistent with the target flight heading angle.

[0138] In some optional embodiments, the device further comprises:

[0139] The third determination module is used to obtain detection data collected by the millimeter wave radar on the UAV and determine the location of obstacles in the target tunnel based on the detection data.

[0140] The second adjustment module is used to adjust the current flight route if the current flight route of the UAV coincides with the position of the obstacle.

[0141] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0142] The emergency drone navigation device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0143] An embodiment of the present application also provides a computer device having the emergency drone navigation device shown in Figure 3 above.

[0144] Please refer to Figure 4, which is a structural diagram of a computer device provided by an optional embodiment of the present application. As shown in Figure 4, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. The various components are connected to each other using different buses and can be installed on a common motherboard or installed in other ways as needed. The processor can process instructions executed within the computer device, including instructions stored in or on the memory to display graphical information of a GUI on an external input / output device (such as a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 4 takes a processor 10 as an example.

[0145] The processor 10 may be a central processing unit (CPU), a network processor (NPU), or a combination thereof. The processor 10 may also include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The programmable logic device (PLD) may be a complex programmable logic device (CPLD), a field programmable gate array (FPGA), a general purpose array logic (GAL), or any combination thereof.

[0146] The memory 20 stores instructions that can be executed by at least one processor 10, so as to enable at least one processor 10 to execute the method shown in the above embodiment.

[0147] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and application programs required for at least one function; the data storage area may store data created based on the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely located relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0148] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0149] The computer device further includes an input device 30 and an output device 40. The processor 10, the memory 20, the input device 30, and the output device 40 may be connected via a bus or other means, with FIG4 taking the bus connection as an example.

[0150] The input device 30 can receive input digital or character information and generate key signal input related to user settings and function control of the computer device, such as a touch screen, etc. The output device 40 can include a display device, etc.

[0151] The embodiments of the present application also provide a computer-readable storage medium. The above-mentioned method according to the embodiment of the present application can be implemented in hardware, firmware, or implemented as a computer code that can be recorded in a storage medium, or implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and downloaded through a network and will be stored in a local storage medium, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state drive, etc.; optionally, the storage medium can also include a combination of the above-mentioned types of memory. It can be understood that a computer, a processor, a microprocessor controller or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor or hardware, the method shown in the above embodiment is implemented.

[0152] Although the embodiments of the present application have been described with reference to the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present application, and such modifications and variations shall fall within the scope defined by the appended claims.

Claims

1. An emergency drone navigation method, characterized in that: The method comprises: Obtaining the location of the ultra-wideband base station in the target tunnel and the historical data collected by the laser radar on the drone on the target tunnel, and establishing an initial three-dimensional model of the target tunnel based on the historical data; When an emergency event is detected, the real-time data collected by the laser radar on the drone on the target tunnel and the ultra-wideband positioning position collected by the ultra-wideband on the drone are obtained, and the current three-dimensional model of the target tunnel is established according to the real-time collected data; Comparing the initial three-dimensional model with the current three-dimensional model, comparing the ultra-wideband positioning position with the ultra-wideband base station position, and determining the current position of the drone based on the comparison result; Determine the target flight heading angle of the UAV based on the initial three-dimensional model and the real-time collected data; The destination position of the drone is obtained, and the drone is navigated based on the current position of the drone, the destination position, and the target flight heading angle.

2. The method according to claim 1, characterized in that The step of comparing the initial three-dimensional model with the current three-dimensional model, comparing the ultra-wideband positioning position with the ultra-wideband base station position, and determining the current position of the drone based on the comparison result includes: Extracting a first feature point cloud from the initial three-dimensional model and extracting a second feature point cloud from the current three-dimensional model; Comparing the first feature point cloud with the second feature point cloud to determine a first position of the drone; Comparing the ultra-wideband positioning position with the ultra-wideband base station position to determine a second position of the drone; The first position and the second position are weightedly fused, and the weighted fused position is determined as the current position of the UAV.

3. The method according to claim 2, characterized in that The weighted fusion of the first position and the second position includes: The reliability of the first position and the second position is obtained by experiment; Determine a weight of the first position and a weight of the second position based on the credibility of the first position and the second position respectively; The first position and the second position are weightedly fused based on the weight of the first position and the weight of the second position.

4. The method according to claim 1, characterized in that: The method of determining the target flight heading angle of the UAV based on the initial three-dimensional model and the real-time collected data includes: Based on the initial three-dimensional model, determine the center line of the target tunnel, and determine the center line as the initial flight route of the UAV; Establishing a laser radar coordinate system based on the real-time collected data, and establishing a tunnel coordinate system based on the initial flight route; The heading angle output by the gyroscope on the UAV is obtained, and the target flight heading angle of the UAV is determined based on the angle between the horizontal coordinate axis of the lidar coordinate system and the horizontal coordinate axis of the tunnel coordinate system and the heading angle output by the gyroscope.

5. The method according to claim 4, characterized in that After navigating the drone based on the current position, the end position, and the target flight heading angle of the drone, the method further includes: Get the current flight route of the drone; Compare the current flight route with the initial flight route to determine whether the UAV flight has deviated; If the UAV flight deviates, the flight heading angle of the UAV is adjusted so that the adjusted flight heading angle is consistent with the target flight heading angle.

6. The method according to claim 5, characterized in that After navigating the drone based on the current position, the end position, and the flight heading angle of the drone, the method further includes: Acquire detection data collected by a millimeter-wave radar on the UAV, and determine the location of obstacles in the target tunnel based on the detection data; If the current flight route of the drone coincides with the position of the obstacle, the current flight route is adjusted.

7. An emergency drone navigation device, characterized in that: The device comprises: The first model building module is used to obtain the location of the ultra-wideband base station in the target tunnel and the historical data collected by the laser radar on the drone on the target tunnel, and to build an initial three-dimensional model of the target tunnel according to the historical data; The second model building module is used to obtain the real-time acquisition data of the target tunnel by the laser radar on the drone and the ultra-wideband positioning position acquired by the ultra-wideband on the drone when an emergency event is detected, and to establish a current three-dimensional model of the target tunnel according to the real-time acquisition data; A first determination module is used to compare the initial three-dimensional model with the current three-dimensional model, compare the ultra-wideband positioning position with the ultra-wideband base station position, and determine the current position of the drone based on the comparison result; A second determination module is used to determine the target flight heading angle of the UAV based on the initial three-dimensional model and the real-time collected data; The navigation module is used to obtain the destination position of the drone and navigate the drone based on the current position of the drone, the destination position and the target flight heading angle.

8. The device according to claim 7, characterized in that The first determining module comprises: An extraction unit, configured to extract a first feature point cloud from the initial three-dimensional model and a second feature point cloud from the current three-dimensional model; A first determining unit, configured to compare the first feature point cloud with the second feature point cloud to determine a first position of the drone; A second determination unit is used to compare the ultra-wideband positioning position with the ultra-wideband base station position to determine a second position of the drone; The third determining unit is used to perform weighted fusion on the first position and the second position, and determine the weighted fusion position as the current position of the UAV.

9. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the emergency drone navigation method according to any one of claims 1 to 6 by executing the computer instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the emergency drone navigation method according to any one of claims 1 to 6.

Images