Unmanned aerial vehicle autonomous inspection system

Abstract

The invention discloses an unmanned aerial vehicle autonomous inspection system, and the system comprises a far-end monitoring device which receives and stores information related to the traffic condition of each road section from at least one big data platform, generates a task instruction enabling an unmanned aerial vehicle to execute autonomous cruise, and transmits the task instruction to a cloud server; the cloud server receives and analyzes the task instruction, generates a control instruction for enabling the unmanned aerial vehicle to perform autonomous cruise, and sends the control instruction to the unmanned aerial vehicle control device according to the information of the position of the road section; the unmanned aerial vehicle control device receives the control instruction from the cloud server, selects an unmanned aerial vehicle according to a preset rule, and sends the control instruction to the selected unmanned aerial vehicle; and the unmanned aerial vehicle performs autonomous cruise based on the control instruction received from the unmanned aerial vehicle control device. According to the unmanned aerial vehicle autonomous inspection system, the accuracy and efficiency of the unmanned aerial vehicle autonomous inspection system for road network monitoring are improved by counting traffic road condition information from each channel, and the unmanned aerial vehicle autonomous inspection system is applied to construction of a Qinghai-Tibet Plateau bulk mineral database.

Description

Technical Field

[0001] The present invention belongs to the technical field of traffic dispatching, and in particular relates to an autonomous inspection system for unmanned aerial vehicles. Background Art

[0002] In urban traffic management systems, video surveillance equipment or vehicle speed measuring equipment are usually installed at key nodes to monitor traffic conditions in real time. For a given area's road network, the number of such video surveillance equipment and vehicle speed measuring equipment is limited, considering installation and maintenance costs. Furthermore, the installation locations of video surveillance equipment and vehicle speed measuring equipment remain fixed, and relying on this traditional model to monitor road traffic and violations presents monitoring blind spots due to fixed equipment locations and untimely fault repairs. Furthermore, due to special circumstances, such as vehicle accidents, road or bridge collapses, or the inability of fixed-installation equipment to operate normally due to natural disasters or malfunctions, traffic congestion or even outages may occur at unspecified locations, necessitating the rapid acquisition of on-site conditions and relevant information.

[0003] In recent years, drones have been increasingly used in road safety applications, including routine traffic information collection, road traffic incident detection, and emergency rescue. Compared to traditional transportation methods, drones offer advantages such as ease of use, flexibility, and high flight speed. Furthermore, equipped with specialized cameras, drones can clearly monitor large areas from their high altitude, significantly improving the efficiency of traffic management and enforcement. However, these applications also present technical and operational challenges.

[0004] Currently, for applications such as road traffic incident detection and emergency rescue, drone mission instructions are typically issued by personnel based on surveillance footage from traffic monitoring centers, alarm information from vehicles on the road, and shared traffic information. This determines whether to launch a drone for road network inspections. However, the data sources for surveillance footage, alarm information, and shared traffic information are often fragmented, and information aggregation takes time. Furthermore, accurate judgment based on this data requires time and experience, leaving room for improvement in the speed of response to drone inspection mission instructions. Summary of the Invention

[0005] In response to the above-mentioned deficiencies in the prior art, the present invention provides an autonomous inspection system for unmanned aerial vehicles (UAVs) that solves the problem of low accuracy and efficiency in starting autonomous inspections for existing road network monitoring UAVs.

[0006] In order to achieve the above-mentioned purpose, the technical solution adopted by the present invention is: an autonomous inspection system of a drone, comprising:

[0007] The remote monitoring device receives and stores information related to traffic conditions for each road section from at least one big data platform, generates a mission instruction for the drone to perform autonomous cruising on the corresponding road section based on the received information related to traffic conditions, and transmits the generated mission instruction to a cloud server, the mission instruction including information indicating the location of the road section;

[0008] The cloud server receives the mission instruction for the UAV sent by the remote monitoring device, parses the mission instruction to generate a control instruction for the UAV to perform autonomous cruising, and sends the control instruction to at least one UAV control device based on the information indicating the position of the road section obtained by the parsing;

[0009] at least one drone control device, receiving the control instruction from the cloud server, selecting a drone according to a predetermined rule, and sending the control instruction to the selected drone;

[0010] and at least one UAV that performs autonomous cruising based on the control instructions received from the at least one UAV control device.

[0011] Furthermore: the at least one big data platform includes at least one of a traffic accident alarm platform, a road traffic monitoring platform, a car navigation system platform, and a natural disaster rescue platform.

[0012] Furthermore: the remote monitoring device includes:

[0013] a traffic information database, for each predetermined period, storing the received information related to traffic conditions by road section as a traffic condition record, wherein the traffic condition record includes an item for recording an autonomous cruise warning value, the autonomous cruise warning value being an accumulated value of warning values ​​corresponding to emergency situations;

[0014] a task instruction generating unit, configured to generate a task instruction for autonomous cruising for a road section corresponding to any traffic condition record when the autonomous cruise warning value recorded in any traffic condition record exceeds a preset threshold;

[0015] and a communication unit for sending the task instruction to the cloud server.

[0016] Furthermore: the cloud server parses the task instruction to generate the control instruction, and sends the control instruction to the at least one drone control device according to the road section corresponding to the task instruction;

[0017] The at least one drone control device selects at least one drone according to the flight range of the drones and sends the control instruction to the drone.

[0018] Furthermore, the calculation method of the autonomous cruise warning value is specifically as follows:

[0019] In response to receiving traffic accident alarm information or traffic congestion information from the at least one big data platform, the remote monitoring device is controlled to extract description information of the accident location or traffic congestion location and accident condition or congestion condition keywords from the traffic accident alarm information or traffic congestion information through any one of a pre-trained speech recognition neural network, a text extraction neural network, and an image recognition neural network, locate the accident location or traffic congestion location based on the description information of the accident location or traffic congestion location, search for the traffic condition records related to the accident location or traffic congestion location, and accumulate the autonomous cruise warning values ​​in the traffic condition records with the warning values ​​corresponding to the accident condition keywords or the congestion condition keywords;

[0020] In response to receiving natural disaster information from the at least one big data platform, the control remote monitoring device extracts descriptive information of the location where the natural disaster occurred and natural disaster condition keywords from the natural disaster information through any one of the voice recognition neural network, the text extraction neural network, and the image recognition neural network, locates the location where the natural disaster occurred according to the descriptive information of the location where the natural disaster occurred, searches for the related traffic condition records according to the location where the natural disaster occurred, and accumulates the autonomous cruise warning values ​​in the traffic condition records and the warning values ​​corresponding to the natural disaster condition keywords.

[0021] Furthermore: the drone control device is arranged near the drone hangar, or is arranged as an independent base station in the area to be monitored including the service area of ​​the highway and the area prone to natural disasters;

[0022] The drone library is used to store the at least one drone.

[0023] Furthermore: the road traffic monitoring platform includes traffic information collection units arranged at the entrance and exit of each road section;

[0024] The traffic information collection unit is used to collect traffic flow information of each road section, and send the location information, traffic flow information and information collection time information of the road section as the information related to the traffic conditions to the remote monitoring device;

[0025] The remote monitoring device saves the information related to the traffic condition into the traffic condition record of the road section according to the position information of the road section.

[0026] Furthermore: the cloud server also generates an inspection map based on the map data and the three-dimensional model, and plans the inspection route, inspection points, and the position of the drone when the inspection point is located during the construction of the inspection map;

[0027] Among them, the three-dimensional model is established through drone scanning. During the scanning process, the map features are obtained through the laser radar carried by the drone to ensure that the coordinates of each object in the three-dimensional model are consistent with the real world. The three-dimensional model and the inspection map share the coordinate system to mark or identify objects that are not reflected in the existing map.

[0028] Furthermore: the cloud server also performs target recognition on objects based on the images received from the at least one drone, confirms each object and its status at the inspection point, and displays it to the operator in real time through the remote monitoring device.

[0029] The beneficial effects of the present invention are as follows: the UAV autonomous inspection system of the present invention records traffic conditions according to road sections, and counts information related to traffic conditions received from multiple big data platforms for each road section. When the autonomous cruise warning value in the record corresponding to any road section exceeds a preset threshold, it automatically generates a task instruction instructing the UAV to start patrolling the road section. It can aggregate big data platform data from multiple channels, thereby preventing omissions of monitoring data, and can automatically generate a start-up instruction for the UAV to start autonomous cruising according to the severity of traffic accidents, congestion and natural disasters, thereby improving the accuracy and efficiency of the UAV autonomous inspection system for road network monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 This is a structural schematic diagram of an autonomous inspection system for unmanned aerial vehicles of the present invention. DETAILED DESCRIPTION

[0031] The specific embodiments of the present invention are described below to facilitate understanding of the present invention by those skilled in the art. However, it should be clear that the present invention is not limited to the scope of the specific embodiments. For those skilled in the art, as long as various changes are within the spirit and scope of the present invention as defined and determined by the appended claims, these changes are obvious, and all inventions and creations utilizing the concepts of the present invention are protected.

[0032] like Figure 1As shown, in one embodiment of the present invention, the drone autonomous inspection system includes: a remote monitoring device, which receives and stores information related to traffic conditions of each road section from at least one big data platform, generates a task instruction for the drone to perform autonomous cruising on the corresponding road section based on the received information related to traffic conditions, and sends the generated task instruction to a cloud server, wherein the task instruction includes information indicating the location of the road section; the cloud server receives the task instruction for the drone sent by the remote monitoring device, parses the task instruction and generates a control instruction for the drone to perform autonomous cruising, and sends the control instruction to at least one drone control device based on the information indicating the location of the road section obtained by parsing; at least one drone control device receives the control instruction from the cloud server, selects a drone according to a predetermined rule, and sends the control instruction to the selected drone; and at least one drone performs autonomous cruising based on the control instruction received from the at least one drone control device.

[0033] The present invention is applied to the construction of a bulk mineral database on the Qinghai-Tibet Plateau.

[0034] In one embodiment of the present invention, the drone control device is located near a drone hangar, or as an independent base station in an area to be monitored, including a highway service area and areas prone to natural disasters. The drone hangar is used to store at least one drone. In one embodiment of the present invention, the drone autonomous inspection system can be set up for a predetermined range, and the drone autonomous inspection system can monitor a preset area (e.g., a road) within this range. In the present invention, the size of the predetermined range is not limited and can be divided according to administrative divisions, topography, or landforms. There can be multiple drone hangars, each located in an area with a high concentration of monitored locations, such as highway service areas and areas prone to natural disasters (e.g., floods, mudslides, rockfalls, etc.), thereby covering the area to be monitored. The drone control device can be a wireless signal transceiver for drone control. For example, it can be located near the drone hangar, or as an independent base station in an appropriate location to cover the entire area to be monitored. In the drone control device, identification information of at least one drone is stored in association with its respective range and model. When the drone control device receives a control instruction to perform autonomous cruise from the cloud server, it selects a drone capable of performing autonomous cruise based on the stored information such as the flight history and model of each drone, and sends the control instruction to the selected drone.

[0035] Existing drone mission instructions for autonomous road traffic patrol are issued by traffic control center staff based on surveillance footage, traffic accident alarms, natural disaster alarms, and shared traffic condition information. However, these data sources, such as surveillance footage, traffic accident alarms, natural disaster alarms, and shared traffic condition information, are sourced from multiple platforms or apps, across a diverse range of channels. Different traffic conditions contribute to the activation of autonomous drone patrols to varying degrees, so compiling this information and determining the necessity of drone patrol activation takes time and requires staff to possess the necessary technical expertise. Consequently, there are cases where staff miss information and fail to schedule drone patrols in a timely manner, or schedule drone patrols unnecessarily, leading to low accuracy and efficiency in the activation of autonomous drone patrols.

[0036] In one embodiment of the present invention, the remote monitoring device includes a communication unit that can be connected to at least one big data platform via a communication network to receive information related to traffic conditions. The at least one big data platform includes at least one of a traffic accident alarm platform, a road traffic monitoring platform, a car navigation system platform, and a natural disaster relief platform. In the present invention, the communication network can be either a wired network or a wireless network corresponding to mobile communication standards such as the fourth generation (4G), fifth generation (5G), and long-term evolution (LTE).

[0037] In one embodiment of the present invention, as information related to traffic conditions, for example, a remote monitoring device receives traffic accident alarm information from a traffic accident alarm platform, which is provided to the alarm platform by the caller via voice, images, etc. Typically, the caller will describe the location of the traffic accident and the severity of the traffic accident via voice, images, etc. The location of the traffic accident can be described, for example, by the name of the road where the accident occurred, a landmark building, a traffic signal, etc. The severity of the traffic accident can include, for example, whether a vehicle exploded or burned, whether there were any casualties, and other information.

[0038] In one embodiment of the present invention, for example, the remote monitoring device also receives information related to traffic conditions from a traffic management bureau's road traffic monitoring platform. For example, the road traffic monitoring platform includes traffic information collection units located at the entrance and exit of each road section. The traffic information collection units are configured to collect traffic flow information for each road section and transmit the location information, traffic flow information, and information collection time information of each road section as the information related to traffic conditions to the remote monitoring device. The location information of each road section is represented, for example, by the longitude and latitude information of the section's entrance and exit. In one embodiment of the present invention, for example, the remote monitoring device determines whether a road section is congested based on the number of vehicles entering and exiting the section during a predetermined period. In one embodiment of the present invention, for example, the remote monitoring device is also connected to a car navigation system platform via a communication network and determines whether the road section is congested based on the vehicle speeds of each road section as reported by the car navigation system platform. In one embodiment of the present invention, for example, the remote monitoring device determines whether each road section is at a high, medium, or low congestion level based on traffic flow information or vehicle speed information.

[0039] In one embodiment of the present invention, the remote monitoring device is also connected to the natural disaster rescue platform of the rescue center involved in the disaster relief work through a communication network. For example, in the event of road interruption due to earthquakes, rainstorms, mudslides, etc., the remote monitoring device receives information related to the natural disaster from the natural disaster rescue platform. Among them, the information related to the occurrence of natural disasters includes information related to the occurrence of disasters reported by the victims through voice, pictures, etc. when the disaster occurs. The information related to the occurrence of disasters includes location information describing the occurrence of natural disasters and the severity of natural disasters. The location of the occurrence of natural disasters can be described, for example, by the name of the road where the natural disaster occurs, landmark buildings, landmark geographical landscapes, etc. The severity of natural disasters can include, for example, information related to whether landslides or mudslides occur, whether roads are broken, whether bridges collapse, whether casualties occur, etc.

[0040] In one embodiment of the present invention, a remote monitoring device includes: a traffic information database, which stores, for each predetermined period, received information related to traffic conditions according to road sections as traffic condition records, wherein the traffic condition records include an item for recording an autonomous cruise warning value, wherein the autonomous cruise warning value is an accumulated value of warning values ​​corresponding to emergency situations; and a task instruction generation unit, which generates a task instruction for autonomous cruise control for the road section corresponding to the traffic condition record when the autonomous cruise warning value in any of the traffic condition records exceeds a preset threshold value.

[0041] and a communication unit for sending the task instruction to the cloud server.

[0042] The cloud server parses the mission instruction to generate the control instruction, and sends the control instruction to the at least one drone control device according to the road section corresponding to the mission instruction;

[0043] The at least one drone control device selects at least one drone according to the flight range of the drones and sends the control instruction to the drone.

[0044] Preferably, in one embodiment of the present invention, for each predetermined period, traffic condition information for each road section within the monitoring area is stored in the traffic information database as a traffic condition record based on the location information of the starting point of each road section, such as the longitude and latitude of the starting point. Each traffic condition record includes an option for an autonomous cruise warning value indicating the degree to which autonomous cruise control is necessary for the drone to execute autonomous cruise. This autonomous cruise warning value is the cumulative value of warning values ​​corresponding to emergency cruise conditions. Specifically, in the present invention, the autonomous cruise warning value represents the cumulative value of all values ​​related to the need for autonomous cruise control for the road section corresponding to the record. Values ​​related to the need for autonomous cruise control include values ​​corresponding to the severity of traffic accidents, traffic congestion, and natural disasters. Furthermore, regardless of the occurrence of a traffic accident, congestion, or natural disaster, only the alarm information immediately after the event is of practical significance for initiating autonomous cruise control for the drone. Therefore, the predetermined period can be appropriately set based on factors such as storage costs. For example, it can be set to any length, such as 10 minutes, 30 minutes, or 1 hour. The present invention does not limit the length of the predetermined period. When the predetermined period expires, the system resets the autonomous cruise warning value.

[0045] The following describes in detail the method for calculating the autonomous cruise warning value in the present invention. Those skilled in the art will appreciate that the calculation method described in the embodiment herein is merely an example and is not intended to limit the scope of the invention. The present invention can also be implemented through variations equivalent to the embodiment.

[0046] In one embodiment of the present invention, in response to receiving traffic accident alarm information or traffic congestion information from at least one big data platform, a remote monitoring device is controlled to extract, from the traffic accident alarm information or traffic congestion information, a description of the accident location or the traffic congestion location, and accident or congestion condition keywords, using any one of a pre-trained speech recognition neural network, a text extraction neural network, and an image recognition neural network. The accident location or traffic congestion location is located based on the description of the accident location or traffic congestion location. Related traffic condition records are searched based on the accident location or traffic congestion location, and autonomous cruise warning values ​​in the traffic condition records are accumulated, weighted based on the accident condition keywords or congestion condition keywords. The speech recognition neural network, the text extraction neural network, and the image recognition neural network can be obtained using a known training model, and the present invention is not limited thereto.

[0047] In one embodiment of the present invention, for example, when the extracted accident status keywords include keywords such as "minor scratches" and "no injuries" indicating that the severity of the accident is relatively minor, or when the extracted congestion status keywords include keywords such as "minor congestion" indicating that the road congestion is light, the autonomous cruise warning value is added by 1; when the extracted accident status keywords include keywords such as "fire" and "casualties" indicating that the severity of the accident is relatively high, or when the extracted congestion status keywords include keywords such as "blocked" and "difficult to move" indicating that the road congestion is serious, in order to start the drone to start autonomous cruising as soon as possible to obtain more detailed information about the scene, the autonomous cruise warning value will be added with an arbitrary value greater than 1, for example, it can be directly increased to the same value as the pre-set threshold.

[0048] In one embodiment of the present invention, in response to receiving natural disaster information from at least one big data platform, the remote monitoring device is controlled to extract descriptive information of the location where the natural disaster occurred and natural disaster condition keywords from the natural disaster information through any one of a speech recognition neural network, a text extraction neural network, and an image recognition neural network, locate the location where the natural disaster occurred based on the descriptive information of the location where the natural disaster occurred, search for related traffic condition records according to the location where the natural disaster occurred, and accumulate the autonomous cruise warning values ​​in the traffic condition records and the warning values ​​corresponding to the natural disaster condition keywords.

[0049] In one embodiment of the present invention, when the extracted natural disaster condition keywords include "light rain", "a few falling rocks", "no casualties" and other keywords indicating that the natural disaster is relatively mild, the autonomous cruise warning value is added by 1; when the extracted natural disaster condition keywords include "bridge collapsed", "road blocked", "huge falling rocks", "mudslide" and other keywords indicating that the natural disaster is relatively serious, in order to start the drone to start autonomous cruising as soon as possible to obtain more detailed information about the scene, the autonomous cruise warning value will be added with an arbitrary value greater than 1, for example, it can be directly increased to the same value as the pre-set threshold.

[0050] In one embodiment of the present invention, when the location information indicating the location where an accident or congestion occurred received by the remote monitoring device from the road traffic monitoring platform is the name of the road where the accident or congestion occurred, a landmark building, a traffic signal, etc., the received location information is converted into corresponding longitude and latitude information with reference to pre-stored map data, so as to search for traffic road condition records of the relevant road section based on the converted longitude and latitude information.

[0051] In one embodiment of the present invention, the remote monitoring device may generate a task instruction for the drone by any of the following two methods:

[0052] (1) When the autonomous cruise warning value in any traffic condition record exceeds a preset threshold, a task instruction for autonomous cruise is generated for the road section corresponding to the traffic condition record, and the task instruction is sent to the cloud server;

[0053] (2) Based on the monitoring area set by the staff operating the remote monitoring device, the autonomous cruise mission instructions corresponding to the monitoring area are generated and sent to the cloud server.

[0054] In the case of (1), the generated autonomous cruise mission instruction can also be displayed on the display of the remote monitoring device, and when a confirmation instruction is received from the staff, the mission instruction is sent to the cloud server. A predetermined time threshold can also be set, and when the mission instruction is displayed on the remote monitoring device and the time threshold has passed, the mission instruction is sent to the cloud server.

[0055] In one embodiment of the present invention, a cloud server stores information corresponding to the location of at least one drone control device and a drone hangar near the device. The cloud server parses a mission instruction received from a remote monitoring device and, based on the information obtained from the parsed information indicating the location of the road section where drone charter cruise is required, sends the generated control instruction to at least one drone control device corresponding to the drone hangar located within that road section. If a drone hangar is not provided for every road section, the control instruction may also be sent to a drone control device corresponding to a drone hangar located in an adjacent road section or the road section closest to the road section.

[0056] In one embodiment of the present invention, staff can also select road sections for inspection through remote monitoring equipment, and set multiple inspection points in the map of the section (for example, sections with frequent accidents, sections with steep roads, sections with complex road conditions, etc.). The remote monitoring equipment sends inspection instructions to the cloud server, and the cloud server can select a suitable drone according to predetermined rules (for example, a drone on standby in the nearest hangar, or a drone returning nearby).

[0057] The cloud server generates an inspection map based on existing map data and a three-dimensional model, and plans the inspection routes, inspection points, and the position of the drone when constructing the inspection map;

[0058] Among them, the three-dimensional model is established through drone scanning. During the scanning process, the map features are obtained through the laser radar carried by the drone to ensure that the coordinates of each object in the three-dimensional model are consistent with the real world. The three-dimensional model and the inspection map share the coordinate system to mark or identify objects that are not reflected in the existing map.

[0059] In this embodiment, because existing map data may be out of date or inaccurate, the present invention utilizes a drone to scan and pre-establish a 3D model of the local area. A drone control device controls the drone to perform a comprehensive scan of the road network in a predetermined area. During the scanning process, the drone's onboard laser radar acquires map features, and a 3D model of the area surrounding the road network is created on a cloud server. The coordinates of each object in the 3D model are consistent with those in the real world, and the 3D model shares a coordinate system with the inspection map. By pre-establishing the 3D model, objects not represented in existing maps, such as low-altitude obstacles like power lines and poles, trees, and signboards, can be marked or identified. This allows for more accurate and safe inspection routes and avoids collisions with obstacles when low-altitude drone monitoring is required. In other words, by establishing and updating the 3D model, it is possible to determine the areas within which the drone can fly, enabling the drone to autonomously approach when necessary to obtain more accurate and clear images or information.

[0060] The three-dimensional model can also be updated in real time based on the map features obtained by the drone during daily inspections to further avoid collisions between the drone and obstacles during low-altitude monitoring.

[0061] After the drone arrives at the inspection point, it can temporarily stop at the inspection point and notify the operator. If the operator needs to manually control the drone, it switches to manual control mode. The operator can use the remote monitoring device to set multiple inspection points in the small area for more detailed inspections or switch to manual control mode to freely inspect specific targets or target areas.

[0062] After completing the inspection, the drone can autonomously fly back to the drone hangar along the original route, or perform the next task according to further instructions.

[0063] The cloud server also generates an inspection map based on the map data and the three-dimensional model, and plans the inspection routes, inspection points, and the position of the drone when the inspection points are located during the construction of the inspection map;

[0064] Among them, the three-dimensional model is established through drone scanning. During the scanning process, the map features are obtained through the laser radar carried by the drone to ensure that the coordinates of each object in the three-dimensional model are consistent with the real world. The three-dimensional model and the inspection map share the coordinate system to mark or identify objects that are not reflected in the existing map.

[0065] The cloud server also performs target recognition on objects based on the images received from the at least one drone, confirms each object and its status at the inspection point, and displays it to the operator in real time through the remote monitoring device.

[0066] The cloud server also performs target recognition on the objects based on the received images, confirms each object and its status at the inspection point, and displays it to the operator in real time through the remote monitoring device, and issues an early warning. The method for issuing an early warning is as follows:

[0067] In one scenario of this embodiment, after a long period of rainfall on a certain mountainous road section, it is estimated that the risk of rockfall is high. Therefore, the operator can set up multiple (for example, 20) inspection points for the mountainous road section with higher risk (for example, 10 kilometers), and conduct inspections at predetermined time intervals (for example, once every 2 hours). During the inspection process, the cloud server performs target recognition on the received images, and can detect whether there are fallen rocks on the road and its surrounding areas, the size and location of the fallen rocks, whether there are stopped cars, the license plate number of the vehicle, and other information. After detecting the above situation, the cloud server sends the information to the remote monitoring device. After receiving the information, the remote monitoring device can send a reminder or alarm to the operator so that the operator can make a countermeasure to close the road or provide rescue.

[0068] In one scenario of this embodiment, the drone can be set to fly along a certain section of road, looking for vehicles with speeds below a threshold to find the location of vehicles that may have been involved in a traffic accident, collect relevant information about the vehicles, and send back images to determine whether assistance and traffic diversion are needed.

[0069] In one scenario of this embodiment, when a flood peak passes, there may be a risk of pipe bursts or dam breaches. Therefore, operators can set up multiple inspection points for the riverbank area with higher risks and conduct inspections at predetermined time intervals (for example, once every half an hour). During the inspection process, the cloud server performs target recognition on the received riverbank image to detect whether there are pipe bursts, dam breaches, and other conditions on the riverbank and its surrounding areas, as well as their severity. After detecting the above situation, the cloud server sends the information to the remote monitoring device. After receiving the information, the remote monitoring device can send a reminder or alarm to the operator so that the operator can take corresponding countermeasures.

[0070] The drone is equipped with a radar ranging sensor, an infrared sensor and a high-definition image sensor. Based on the onboard sensors, the drone can perform close observation based on data of a three-dimensional model to obtain clearer and more accurate data.

[0071] The beneficial effects of the present invention are as follows: the present invention provides a drone autonomous inspection system, which records traffic conditions according to road sections, counts information related to traffic conditions received from multiple big data platforms for each road section, and sets a cumulative value of the addition of autonomous cruise warning values ​​corresponding to emergency situations according to the urgency of various traffic conditions. When the autonomous cruise warning value corresponding to any road section exceeds a preset threshold, a task instruction instructing the drone to start inspection of the road section is automatically generated. Therefore, data from multiple big data platforms can be accurately counted, thereby preventing the occurrence of situations where the staff misses information and fails to arrange the drone for autonomous cruise in time, or arranges the drone for cruise when it is unnecessary, thereby improving the accuracy of the start-up of the drone autonomous inspection and the system operation efficiency.

[0072] In the description of the present invention, it should be understood that the terms "center", "thickness", "upper", "lower", "horizontal", "top", "bottom", "inner", "outer", "radial", etc., indicating the orientation or positional relationship, are based on the orientation or positional relationship shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operate in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first", "second", and "third" are used for descriptive purposes only and cannot be understood as indicating or implying the relative importance or the number of technical features implicitly specified. Therefore, the features defined by "first", "second", and "third" may explicitly or implicitly include one or more of such features.

Claims

1. An autonomous inspection system for unmanned aerial vehicles, characterized in that: include: The remote monitoring device receives and stores information related to traffic conditions of each road section from at least one big data platform, generates a task instruction for the drone to perform autonomous cruising on the corresponding road section based on the received information related to traffic conditions, and sends the generated task instruction to a cloud server, wherein the task instruction includes information indicating the location of the road section; The cloud server receives the task instruction for the UAV sent by the remote monitoring device, analyzes the task instruction to generate a control instruction for the UAV to perform autonomous cruising, and sends the control instruction to at least one UAV control device according to the information indicating the position of the road section obtained by the analysis; at least one drone control device receives the control instruction from the cloud server, selects a drone according to a predetermined rule, and sends the control instruction to the selected drone; and at least one UAV that performs autonomous cruising based on the control instructions received from the at least one UAV control device.

2. The autonomous inspection system of unmanned aerial vehicle according to claim 1, characterized in that: The at least one big data platform includes at least one of a traffic accident alarm platform, a road traffic monitoring platform, a car navigation system platform, and a natural disaster rescue platform.

3. The autonomous inspection system of unmanned aerial vehicle according to claim 1, characterized in that: The remote monitoring device comprises: a traffic information database, for each predetermined period, storing the received information related to traffic conditions according to road sections as traffic condition records, wherein the traffic condition records are provided with an item for recording an autonomous cruise warning value, wherein the autonomous cruise warning value is an accumulated value of warning values ​​corresponding to emergency conditions; a task instruction generating unit, which generates a task instruction for autonomous cruising for a road section corresponding to any traffic condition record when the autonomous cruise warning value recorded in any traffic condition record exceeds a preset threshold; and a communication unit for sending the task instruction to the cloud server.

4. The autonomous inspection system of unmanned aerial vehicle according to claim 3, characterized in that: The cloud server parses the task instruction to generate the control instruction, and sends the control instruction to the at least one drone control device according to the road section corresponding to the task instruction; The at least one drone control device selects at least one drone according to the flight range of the drones and sends the control instruction to the drone.

5. The autonomous inspection system of unmanned aerial vehicle according to claim 3, characterized in that: The calculation method of the autonomous cruise warning value is specifically as follows: In response to receiving traffic accident alarm information or traffic congestion information from the at least one big data platform, the control remote monitoring device extracts description information of the accident location or traffic congestion location and accident condition or congestion condition keywords from the traffic accident alarm information or traffic congestion information through any one of the pre-trained speech recognition neural network, text extraction neural network and image recognition neural network, locates the accident location or traffic congestion location according to the description information of the accident location or traffic congestion location, searches for the relevant traffic road condition records according to the accident location or traffic congestion location, and accumulates the warning values ​​corresponding to the accident condition keywords or the congestion condition keywords for the autonomous cruise warning values ​​in the traffic road condition records; In response to receiving natural disaster information from the at least one big data platform, the control remote monitoring device extracts description information of the location where the natural disaster occurs and natural disaster condition keywords from the natural disaster information through any one of the voice recognition neural network, the text extraction neural network and the image recognition neural network, locates the location where the natural disaster occurs according to the description information of the location where the natural disaster occurs, searches for the related traffic condition records according to the location where the natural disaster occurs, and accumulates the warning values ​​corresponding to the natural disaster condition keywords for the autonomous cruise warning values ​​in the traffic condition records.

6. The autonomous inspection system of unmanned aerial vehicle according to claim 1, characterized in that: The drone control device is arranged near the drone hangar, or as an independent base station in the area to be monitored including the service area of ​​the expressway and the area prone to natural disasters; The drone hangar is used to store the at least one drone.

7. The autonomous inspection system of unmanned aerial vehicle according to claim 2, characterized in that: The road traffic monitoring platform includes traffic information collection units arranged at the entrance and exit of each road section; The traffic information collection unit is used to collect traffic flow information of each road section, and send the location information, traffic flow information and information collection time information of the road section as the information related to the traffic conditions to the remote monitoring device; The remote monitoring device saves the information related to the traffic conditions into the traffic condition record of each road section according to the position information of the road section.

8. The autonomous inspection system of unmanned aerial vehicle according to claim 1, characterized in that: The cloud server also generates an inspection map based on the map data and the three-dimensional model, and plans the inspection route, inspection points, and the position of the drone when the inspection point location is constructed; Among them, the three-dimensional model is established through drone scanning. During the scanning process, the map features are obtained through the laser radar carried by the drone to ensure that the coordinates of each object in the three-dimensional model are consistent with the real world. The three-dimensional model and the inspection map share the coordinate system to mark or identify objects that are not reflected in the existing map.

9. The autonomous inspection system of unmanned aerial vehicle according to claim 1, characterized in that: The cloud server also performs target recognition on objects based on the images received from the at least one drone, confirms each object and its status at the inspection point, and displays it to the operator in real time through the remote monitoring device.

Images