Rail locomotive control method and device based on unmanned aerial vehicle, electronic equipment and medium

Abstract

The invention relates to the technical field of metallurgical industry, and discloses a rail locomotive control method and device based on unmanned aerial vehicles, electronic equipment and a medium, and the method comprises the steps that task information of a target rail locomotive and position information of each unmanned aerial vehicle are obtained, and the task information carries the initial position and the final position of the target rail locomotive in a rail line; determining a target unmanned aerial vehicle with the shortest first relative distance according to the initial position, determining a target flight route of the target unmanned aerial vehicle based on the initial position and the final position, carrying out data acquisition on a track where the target track locomotive is located through the target unmanned aerial vehicle to obtain sensing data, carrying out obstacle recognition based on the sensing data, and if an obstacle is recognized, sending the obstacle to the target unmanned aerial vehicle. Calculating a second relative distance between the obstacle and the coupling body based on the sensing data, and controlling the target track locomotive to run according to the second relative distance; through the method, the flexibility of sensing the environment by the rail locomotive is improved, and the number and maintenance workload of sensing equipment are reduced.

Description

Technical Field

[0001] The present application relates to the technical field of metallurgical industry, and specifically to a method, device, electronic equipment and medium for controlling a rail vehicle based on an unmanned aerial vehicle. Background Art

[0002] In the field of modern industry and transportation, the rapid development and widespread application of drone technology have brought revolutionary changes to many industries. Especially in the fields of rail inspection, power facility inspection and public safety, drones have become an indispensable tool with their unique advantages. These advantages are mainly reflected in strong environmental adaptability, refined operations and high efficiency. Drones can conduct inspections in complex and difficult-to-reach environments, and can achieve high-precision data collection and analysis of target areas by carrying advanced imaging and detection equipment such as visible light imaging equipment, infrared thermal imagers and lidar equipment. This operation method not only improves the accuracy and efficiency of inspections, but also greatly reduces the risks and costs of manual inspections.

[0003] However, in terms of the operation monitoring of the locomotive and tank car coupling, the relevant technical solutions still have certain limitations. A common practice is to install industrial vehicle-mounted intelligent sensing kits at both ends of the locomotive and the operating end of the tank car to ensure that there are sensing sensors at the front end of the coupling in the running direction; however, this solution often leads to equipment waste and increased investment in practical applications, because only the front-end sensing kit is usually used during the running of the coupling; in addition, too many sensing kits also increase the workload of equipment maintenance, which is not conducive to long-term stable operation. Another solution is to use a detachable sensing kit. Before each locomotive and tank car coupling runs, the sensing kit is temporarily installed at the front end of its operation. Although this solution reduces the idleness of equipment to a certain extent, it also brings new challenges; on the one hand, the detachable sensing kit needs to be frequently installed and disassembled, which increases the maintenance workload; on the other hand, if the coupling needs to reverse during operation, it is necessary to install detachable sensing kits at both ends of the coupling, which further increases the cost and complexity. Obviously, there is an urgent need for a rail locomotive control method based on drones to solve at least one of the above problems.

[0004] It should be noted that the above content only provides background technical information related to the present application and does not necessarily constitute prior art. Summary of the invention

[0005] In view of the shortcomings of the prior art mentioned above, the present application provides a rail locomotive control method, device, electronic device and medium based on drone to increase the flexibility of environmental perception and reduce the number of sensing devices and maintenance workload.

[0006] Other features and advantages of the present application will become apparent from the following detailed description, or may be learned in part by the practice of the present application.

[0007] According to one aspect of an embodiment of the present application, a method for controlling a rail locomotive based on a drone is provided, comprising: obtaining mission information of a target rail locomotive and position information of each drone, the mission information carrying a starting position and an end position of the target rail locomotive in a rail line; determining a target drone with a shortest first relative distance according to the starting position, and determining a target flight route of the target drone based on the starting position and the end position; collecting data on a track where the target rail locomotive is located by means of the target drone to obtain perception data, and identifying obstacles based on the perception data, the perception data including image data and point cloud data; if an obstacle is identified, calculating a second relative distance between the obstacle and a coupling body based on the perception data, and controlling the travel of the target rail locomotive according to the second relative distance, the coupling body including the target rail locomotive.

[0008] In one embodiment of the present application, based on the aforementioned scheme, the target UAV with the shortest first relative distance is determined according to the starting position, including: calculating based on the position information of each UAV and the starting position respectively to obtain the first relative distance corresponding to each UAV; and determining the UAV with the shortest first relative distance as the target UAV.

[0009] In one embodiment of the present application, based on the aforementioned scheme, the target flight route of the target UAV is determined based on the starting position and the end position, including: determining the pending driving route of the target rail locomotive based on the starting position and the end position, and determining the target driving route of the target rail locomotive based on the route status of the pending driving route; determining the target flight route based on the target driving route and a preset safety height corresponding to the target driving route.

[0010] In one embodiment of the present application, based on the aforementioned scheme, after determining the target flight route of the target UAV based on the starting position and the end position, the method also includes: obtaining the detection distance of the target UAV, calculating based on the detection distance and the height of the target flight route to obtain the perceived safety distance of the target UAV; calculating according to the perceived safety distance and the braking acceleration of the target rail locomotive to obtain the speed limit of the target rail locomotive, so as to control the travel of the target rail locomotive according to the speed limit.

[0011] In one embodiment of the present application, based on the aforementioned scheme, after the target UAV collects data on the track where the target rail locomotive is located and obtains the perception data, the method also includes: performing feature extraction based on the perception data, and if a preset feature is extracted, performing state identification on the preset feature to obtain a preset feature state, wherein the preset feature state includes at least one of a track section state, a signal state, and a switch state; and updating the target driving route of the target rail locomotive and the target flight route of the target UAV according to the preset feature state.

[0012] In one embodiment of the present application, based on the aforementioned scheme, a second relative distance between the obstacle and the attachment is calculated based on the perception data, and the target rail locomotive is controlled to travel according to the second relative distance, including: calculating the second relative distance based on the drone position of the target drone, the relative position of the obstacle and the position of the attachment, wherein the perception data includes the relative position of the obstacle, and the relative position of the obstacle is the position of the obstacle relative to the target drone; calculating a safe speed limit based on the second relative distance and a preset parking safety distance to control the target rail locomotive to slow down to travel below the safe speed limit.

[0013] In one embodiment of the present application, based on the aforementioned scheme, after obstacle identification is performed based on the perception data, the method further includes: if no obstacle is identified, controlling the target UAV to continue flying on the target flight route until the mission of the target rail locomotive is completed; comparing the current power of the target UAV with the preset charging power, if the current power is less than the preset charging power, determining the target charging station based on the UAV position of the target UAV and the charging station positions corresponding to each charging station, so as to charge the target UAV through the target charging station.

[0014] According to one aspect of an embodiment of the present application, a rail locomotive control device based on a drone is provided, including: an acquisition module, used to acquire mission information of a target rail locomotive and location information of each drone, the mission information carrying the starting position and the end position of the target rail locomotive in the rail line; a determination module, used to determine a target drone with the shortest first relative distance based on the starting position, and determine a target flight route of the target drone based on the starting position and the end position; an identification module, used to collect data on the track where the target rail locomotive is located through the target drone to obtain perception data, and perform obstacle identification based on the perception data, the perception data including image data and point cloud data; a control module, used to calculate a second relative distance between the obstacle and a coupling body based on the perception data if an obstacle is identified, and control the travel of the target rail locomotive according to the second relative distance, the coupling body including the target rail locomotive.

[0015] According to one aspect of an embodiment of the present application, an electronic device is provided, comprising: one or more processors; a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the electronic device implements a railway locomotive control method based on a drone as described in any one of the above embodiments.

[0016] The present application also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor of a computer, the computer is enabled to execute a method for controlling a railway locomotive based on a drone as described in any one of the above embodiments.

[0017] The beneficial effects of the present application are as follows: the present application obtains the mission information of the target rail locomotive and the position information of each UAV, the mission information carries the starting position and the ending position of the target rail locomotive in the track line, determines the target UAV with the shortest first relative distance according to the starting position, determines the target flight route of the target UAV based on the starting position and the ending position, collects data on the track where the target rail locomotive is located by the target UAV to obtain perception data, and identifies obstacles based on the perception data, the perception data including image data and point cloud data; if an obstacle is identified, calculates the second relative distance between the obstacle and the attachment based on the perception data, and controls the travel of the target rail locomotive according to the second relative distance; collecting perception data by UAV can not only increase the flexibility of environmental perception of the rail locomotive, but also reduce the number of perception equipment and maintenance workload; the UAV has strong environmental adaptability, and can improve operating efficiency while ensuring the safety of the rail locomotive.

[0018] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The drawings herein are incorporated into the specification and constitute a part of the specification, showing embodiments consistent with the present application, and together with the specification, are used to explain the principles of the present application. Obviously, the drawings described below are only some embodiments of the present application, and for those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0020] Figure 1 is a flow chart of a method for controlling a railway locomotive based on a drone according to an exemplary embodiment of the present application;

[0021] Figure 2 is a schematic diagram of the detection range of a millimeter-wave radar of a rail vehicle control method based on a drone according to an exemplary embodiment of the present application;

[0022] Figure 3 It is a schematic diagram of the sensing safety distance of the millimeter wave radar of the rail locomotive control method based on the drone according to an exemplary embodiment of the present application;

[0023] Figure 4 is a flow chart of a method for controlling a railway locomotive based on a drone according to another exemplary embodiment of the present application;

[0024] Figure 5 is a block diagram of a railway locomotive control device based on a drone, shown in an exemplary embodiment of the present application;

[0025] Figure 6 A schematic diagram of the structure of a computer system suitable for implementing an electronic device of an embodiment of the present application is shown. DETAILED DESCRIPTION

[0026] The following will describe the implementation methods of the present application with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand other advantages and effects of the present application from the contents disclosed in this specification. The present application can also be implemented or applied through other different specific implementation methods, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present application. It should be understood that the preferred embodiments are only for illustrating the present application, not for limiting the scope of protection of the present application.

[0027] It should be noted that the illustrations provided in the following embodiments are only used to illustrate the basic concept of the present application in a schematic manner, and therefore the illustrations only show components related to the present application rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed arbitrarily, and the component layout may also be more complicated.

[0028] In the following description, a large number of details are discussed to provide a more thorough explanation of the embodiments of the present application. However, it is obvious to those skilled in the art that the embodiments of the present application can be implemented without these specific details. In other embodiments, well-known structures and devices are shown in the form of block diagrams rather than in detail to avoid making the embodiments of the present application difficult to understand.

[0029] First of all, it should be noted that a rail locomotive is a train that transports liquid or solid materials on railways such as steel mills and mines.

[0030] Track computer interlocking mainly uses color light signal machines, power switch machines and track circuits as three major outdoor equipment, and uses electronic equipment to realize interlocking functions to monitor the track section status, signal status and switch status, and implement control of signal machines and switches.

[0031] Color light signal has the important task of ensuring the safety of train operation and indicating the running status of train. In this application, train refers to the connection of rail locomotive and tank car. By emitting light signals of different colors, color light signal can indicate whether the train can move forward or needs to stop. For example, if the signal shows green light or yellow light (driving light is allowed), it means that the corresponding route has been established and the locomotive can travel along the route. If a red light is displayed, it means that the route has not been established or there is danger, and the locomotive cannot enter. Color light signal helps train drivers and related staff to accurately grasp the running status of the train, so as to make correct operations and decisions.

[0032] The power switch is an important part of the electric centralized interlocking system and the microcomputer interlocking system. It has three key functions: switching switches, locking switches, and reflecting switch status. The power switch plays a vital role in ensuring driving safety, improving transportation efficiency, and effectively improving working conditions.

[0033] Track circuits also play an important role in railway and subway systems. They are mainly used to monitor the occupancy of trains, reflect the idleness of lines, and provide a basis for opening signals, establishing routes, or forming blocks. At the same time, track circuits can also transmit driving information. For example, frequency-shift automatic blocking uses track circuits to transmit different frequency information to reflect the position of trains, determine the display of passing signals, or determine the target speed of train operation, thereby controlling train operation. The performance of track circuits directly affects driving safety and transportation efficiency, and is an important basic equipment for railway signals.

[0034] Figure 1 is a flow chart of a method for controlling a railway locomotive based on a drone according to an exemplary embodiment of the present application. The method for controlling a railway locomotive based on a drone can be executed by a computing and processing device. Figure 1As shown, the UAV-based rail vehicle control method includes at least steps S110 to S140, which are described in detail as follows:

[0035] In step S110, the mission information of the target rail vehicle and the location information of each drone are obtained.

[0036] In one embodiment of the present application, the mission information carries the starting position and the end position of the target rail vehicle in the rail line. The mission information may also include, but is not limited to, the passing signal lights, the tank cars carried (including the tank cars and the number of tank cars), and the mission direction may also be determined by the starting position and the end position. The location information of each drone is the current location information of each drone.

[0037] In step S120, a target UAV with the shortest first relative distance is determined according to the starting position, and a target flight route of the target UAV is determined based on the starting position and the end position.

[0038] In one embodiment of the present application, the process of determining the target UAV with the shortest first relative distance based on the starting position includes the following steps: calculating based on the position information of each UAV and the starting position respectively to obtain the first relative distance corresponding to each UAV; determining the UAV with the shortest first relative distance as the target UAV.

[0039] In this embodiment, the location information of each drone is matched with the starting location, and the location information of the drone closest to the starting location is defined as successfully matched with the starting location, and the target drone is determined based on the matching result.

[0040] In some embodiments, the working state of the target drone is an idle state, and the current remaining power of the target drone is greater than a preset power threshold, wherein the preset power threshold is determined according to current mission information.

[0041] In one embodiment of the present application, the process of determining the target flight route of the target drone based on the starting position and the ending position includes the following steps: determining the pending driving route of the target rail locomotive based on the starting position and the ending position, and determining the target driving route of the target rail locomotive based on the route state of the pending driving route; determining the target flight route based on the target driving route and a preset safety height corresponding to the target driving route.

[0042] In this embodiment, the process of determining the target driving route of the target rail locomotive based on the route status of the pending driving route may include the following steps: obtaining the route status of each pending driving route and the selection priority of each route status, determining the corresponding priority of the pending driving route according to the selection priority of each route status, and determining the target driving route based on the priority of each pending driving route. If the priorities of the pending driving routes are the same, the pending driving routes are sorted in ascending order according to the number of rail locomotives on the pending driving routes, and the pending driving route with the first ranking is determined as the target driving route. If the number of rail locomotives on the pending driving routes is equal, any pending driving route is determined as the target driving route. For example, the route status includes but is not limited to an idle state, an occupied state, and a fault state, and the selection priorities corresponding to the idle state, the occupied state, and the fault state are the first level, the second level, and the third level, respectively. Assume that there are 5 pending travel routes a1, a2, a3, a4 and a5 from the starting position A to the end position B, and the route states corresponding to the pending travel routes are a1 idle state, a2 occupied state, a3 occupied state, a4 occupied state and a5 fault state, respectively. According to the selection priority of each route state, the pending travel route a1 is selected first, and the pending travel route a1 is determined as the target travel route. It should be noted that this embodiment is only for illustrative purposes, and does not specifically limit the specific process and rules for determining the target travel route of the target rail locomotive based on the route state of the pending travel route, nor should it bring any limitation to the function and scope of use of the embodiment of the present application.

[0043] In this embodiment, the target flight route is determined based on the target driving route and a preset safety altitude corresponding to the target driving route, wherein the preset safety altitude is determined in the following manner: the preset safety altitude is determined based on work scene information, wherein the work scene information includes information such as facilities and buildings above a preset range of each rail line, including high-rise conditions such as on-site power lines, corridor bridges, and gas ducts.

[0044] In this embodiment, the target UAV with the shortest first relative distance is determined according to the starting position, and after the target flight route of the target UAV is determined based on the starting position and the end position, the target UAV is controlled to fly on the target flight route according to a preset flight speed.

[0045] In one embodiment of the present application, the process after determining the target flight route of the target UAV based on the starting position and the end position also includes the following steps: obtaining the detection distance of the target UAV, calculating based on the detection distance and the height of the target flight route to obtain the perceived safety distance of the target UAV; calculating based on the perceived safety distance and the braking acceleration of the target rail locomotive to obtain the speed limit of the target rail locomotive, so as to control the travel of the target rail locomotive according to the speed limit.

[0046] In this embodiment, considering that the safe braking distance of the coupling of locomotives and tank trucks is generally far, a target drone carrying a radar detector is taken as an example. It is assumed that the radar is a millimeter wave radar, and its detection angle is 360 degrees in the horizontal direction, 60 degrees in the vertical direction, and 45 degrees above. The detection distance is 1.5 meters to 30 meters. Figure 2 , Figure 2 This is a schematic diagram of the detection range of the millimeter-wave radar of the UAV-based rail locomotive control method shown in an exemplary embodiment of the present application. The obstacle avoidance function supports a maximum speed of 10 meters per second and can effectively detect various obstacles such as planar, rod-shaped, and linear obstacles. Exemplarily, the millimeter-wave radar can be installed on the bottom of the drone. It is understandable that the millimeter-wave radar can also be installed on the top, side, or other locations of the drone, and the present application does not limit this. Assuming that the maximum detection distance of the radar is 30 meters, it cannot meet the safety braking requirements of the unmanned locomotive. Utilizing the specific 360-degree scanning range of the sensing device, when the drone flies to the front of the attached body When the distance is refer to Figure 3 As shown, Figure 3 This is a schematic diagram of the sensing safety distance of the millimeter wave radar of the rail locomotive control method based on the drone, which is shown in an exemplary embodiment of the present application. The braking acceleration a of the attached body on the track is obtained through artificial testing. According to the uniform deceleration s=v*v / 2a, the control safety speed of the locomotive can be calculated. The locomotive onboard module controls the locomotive speed in a closed loop according to the safety distance sensed by the drone.

[0047] In step S130, the target UAV collects data on the track where the target locomotive is located to obtain perception data, and obstacle identification is performed based on the perception data.

[0048] In one embodiment of the present application, the perception data includes image data and point cloud data. The drone is equipped with one or more perception sensors such as high-definition cameras, laser radars, visible light imaging devices, infrared thermal imagers, millimeter wave radars, etc. Based on technologies such as artificial intelligence, computer vision, and deep learning, multiple sensors are used to intelligently perceive and measure external information, realize target recognition, positioning, segmentation, and other functions of the surrounding environmental information of intelligent logistics equipment, and make the unmanned operation of industrial production logistics more intelligent, safe, and efficient. And with the maturity of drone technology, drones are widely used in rail inspections, power facility inspections, public safety, and other fields. The advantages of drones are mainly: 1. Strong environmental adaptability. Many inspection environments are complex, located in traffic dead zones, unmanned areas, etc., and drones make up for the defects of some scenes not having favorable traffic conditions through remote control or autonomous route planning. 2. Refined operation. Drones can be equipped with visible light imaging devices, infrared thermal imagers, laser radar devices, etc., to accurately collect information data such as images, videos, point clouds, etc., that is, perception data, and perform refined inspection and analysis of data through the wireless image transmission system and server processing of drones. 3. High efficiency. Industrial drones, as precise, efficient, convenient and remotely controlled aircraft, improve operational efficiency.

[0049] In this embodiment, the process of obstacle identification based on the sensed data includes: extracting features based on the sensed data, identifying the extracted features, and if the target features are identified, it is determined that the obstacle is identified. Among them, the target features include but are not limited to the features of obstacles such as people, animals, vehicles, and equipment. If the sensed data includes image data, image recognition is performed on the sensed data, and obstacle features are extracted. If the sensed data includes point cloud data, the geometric features in the point cloud data are processed and analyzed, and the point set different from the ground or background is identified and classified using an algorithm or a deep learning model, so as to determine the position and shape of the obstacle in three-dimensional space, and realize the identification of the obstacle. Among them, the point cloud data may include three-dimensional point cloud data and two-dimensional point cloud data, and the video data may be a collection of multiple image data within a period of time. Further, obstacle identification can be performed based on artificial intelligence, computer vision, deep learning, point cloud processing and other technologies.

[0050] In one embodiment of the present application, the target UAV collects data on the track where the target rail locomotive is located, and the process after obtaining the perception data further includes the following steps: extracting features based on the perception data, and if a preset feature is extracted, identifying the state of the preset feature to obtain a preset feature state, the preset feature state includes at least one of the track section state, signal state and turnout state; updating the target driving route of the target rail locomotive and the target flight route of the target UAV according to the preset feature state. The target flight route is updated following the target driving route.

[0051] In this embodiment, it can be understood that the target driving route of the target rail locomotive and the target flight route of the target UAV are planned according to the preset characteristic state. The preset characteristic state can be determined by the perception data obtained by the target UAV, or by monitoring through the track microcomputer interlocking system, and then the preset characteristic state is determined. The preset characteristics include but are not limited to color light signal machines, track switches and track sections, and the preset characteristic states corresponding to the above preset characteristics are signal state, switch state and track section state, respectively.

[0052] In this embodiment, if the preset characteristic state is determined by the perception data obtained by the target UAV, feature extraction is performed based on the perception data; if the color light signal, track switch and preset track section are extracted, after the state identification, it is determined that the interlocking condition is met according to the switch state, track section state and signal state, and the target track locomotive is controlled to pass directly, that is, there is no need to update the target driving route and target flight route according to the preset characteristic state; if the interlocking condition is not met, the target driving route and target flight route are updated according to the preset characteristic state. For example, if the switch state is in the reverse position state and the corresponding track section state is in the occupied state, then the track section state on the track corresponding to the switch state is obtained as the positioning state. If it is in the idle state and consistent with the selected route, the switch state is adjusted to the positioning state, and the signal state is correspondingly adjusted to the green light to travel through the idle track section, and the target driving route of the target track locomotive and the target flight route of the target UAV are updated. For example, there are two track sections x and y that can go from position E to position F. If x meets the interlocking condition and y does not meet the interlocking condition, x replaces y to update the target driving route and the target flight route. The target driving route and the target flight route are updated based on the principle of a relatively safe path with a shorter time. It can be understood that the corresponding relationship between the updated target driving route and the target flight route corresponding to each preset characteristic state in this embodiment is only for illustration, and this application does not limit this. In the actual application process, it can be defined according to the needs. The basic state of the turnout includes the positioning state and the reverse state, wherein the positioning state is a basic state of the turnout, usually referring to the turnout opening a fixed direction (such as straight or lateral) and being in a locked state. The reverse state is opposite to the positioning state, and the turnout opens another direction and is in a locked state. When the train running direction needs to be changed, the turnout will be converted from the positioning state to the reverse state, and vice versa.

[0053] In this embodiment, the track microcomputer interlocking system is the core part of the modern railway signal system. It uses computer technology to centrally control and interlock track circuits, signal machines, turnouts and other equipment. The system can receive and process status information from various devices in real time, and generate corresponding control commands based on this information to ensure the safety and efficiency of train operation. The signal machine is an important indicator device on the railway. It displays different light signals according to the status of the track circuit and turnout to indicate whether the train can enter or cross a certain track section. The turnout is a device that connects different track sections, and its position determines the path that the train can travel. The track section is the basic unit for train travel, and each section has a corresponding track circuit to detect its occupancy status.

[0054] In this embodiment, the preset characteristic state is monitored, and then the interlocking condition is judged. Specifically, the following steps can be referred to: before determining the path of the rail locomotive, the signal state is monitored by the rail microcomputer interlocking system. When determining the path of the rail locomotive, the turnout state and the track section state are monitored by the rail microcomputer interlocking system, and then the rail microcomputer interlocking system will judge whether the interlocking condition is met according to the signal state, the turnout state and the track section state. If the interlocking condition is met, the system will generate a corresponding control command, open the signal and lock the turnout, allowing the locomotive to travel along the selected route; if the interlocking condition is not met, the system will issue an alarm message and prohibit the locomotive from entering the route, and then update the target driving route of the target rail locomotive and the target flight route of the target drone according to the preset characteristic state. For example, if the signal state is to allow driving lights (such as green), the turnout state is in a positioning state or a reverse position state, and is consistent with the selected route, and the track section state is in an idle state, then it is determined that the interlocking condition is met.

[0055] In step S140, if an obstacle is identified, a second relative distance between the obstacle and the attachment is calculated based on the sensing data, and the target rail vehicle is controlled to travel according to the second relative distance.

[0056] The coupling body includes a target rail locomotive, and the coupling body may also include one or more tank cars. The coupling body has at least the following two connection modes: 1. The rail locomotive is in front and the tank car is in the back; 2. The rail locomotive is in the back and the tank car is in the front.

[0057] In one embodiment of the present application, a second relative distance between an obstacle and a coupling body is calculated based on the perception data, and a process of controlling the target rail locomotive to travel according to the second relative distance includes the following steps: based on the drone position of the target drone, the relative position of the obstacle and the position of the coupling body, the second relative distance is calculated, wherein the second relative distance represents the position of the obstacle relative to the coupling body, the perception data includes the relative position of the obstacle, and the relative position of the obstacle is the position of the obstacle relative to the target drone; a safe speed limit is calculated based on the second relative distance and a preset parking safety distance to control the target rail locomotive to slow down to travel below the safe speed limit.

[0058] In this embodiment, the position of the obstacle relative to the attachment (x22, y22, z22) is calculated based on the position of the drone (x1, y1, z1), the position of the obstacle relative to the drone (x11, y11, z11), and the attachment position of the locomotive and tanker (x2, y2, z2). The calculation formula is as follows: x22 = x11 + x1-x2; y22 = y11 + y1-y2; z22 = z11 + z1-z2, and the obstacle information is fed back to the locomotive onboard decision module in real time. Distance from the locomotive (tanker) attachment to the obstacle: The parking safety distance d represents the distance from the attachment to the obstacle after the attachment stops. The on-board decision module calculates the safe speed limit v through the following formula: Where a is the braking acceleration of the target rail locomotive, and then the target rail locomotive is controlled to decelerate to below the safe speed limit v to ensure that the vehicle can stop in front of the obstacle, thereby ensuring the safety of the target rail locomotive. Until the obstacle disappears or a subsequent command is issued. If the obstacle disappears, the system continues to execute the task after the obstacle disappears; if a subsequent command is received, the subsequent command is executed.

[0059] In one embodiment of the present application, the process after obstacle identification based on perception data also includes the following steps: if no obstacle is identified, controlling the target UAV to continue flying on the target flight route until the mission of the target rail locomotive is completed; comparing the current power of the target UAV with the preset charging power, if the current power is less than the preset charging power, determining the target charging station based on the UAV position of the target UAV and the charging station positions corresponding to each charging station, so as to charge the target UAV through the target charging station.

[0060] In this embodiment, the preset charging power can be a fixed power value defined by humans, or it can be determined by the drone position of the target drone and the position of the charging station closest to it. Based on the drone position of the target drone and the charging station positions corresponding to each charging station, the third relative distance between each charging station and the target drone is calculated respectively, and the charging station is sorted in ascending order based on the third relative distance, and the charging station ranked first is determined as the target charging station, that is, the charging station with the shortest third relative distance is determined as the target charging station. The process of determining the charging station ranked first as the target charging station includes: obtaining the charging status corresponding to each charging position in the charging station ranked first, if there is a charging position corresponding to an idle state, then charging the target drone through the charging position corresponding to the idle state; if there is no charging position corresponding to an idle state, then the charging station ranked second is determined as the target charging station, and so on, which will not be repeated here.

[0061] In one embodiment of the present application, the second relative distance is compared with the preset relative distance, and the driving state of the target rail locomotive is determined according to the comparison result; if the second relative distance is greater than or equal to the preset relative distance, the target rail locomotive is controlled to slow down; if the second relative distance is less than the preset relative distance, the target rail locomotive is controlled to stop.

[0062] In one embodiment of the present application, each drone can share the perception data it has acquired, and each rail locomotive can also share its mission information, position information, speed information and other data. The locomotive position information, mission execution information and locomotive speed information of the rail locomotives other than the target rail locomotive on the target driving route are obtained, and the estimated position of each rail locomotive at the preset time is calculated based on the locomotive position information, mission execution information and locomotive speed information. If there is a fourth relative distance between any rail locomotive and the target rail locomotive that is less than the preset distance threshold, the target rail locomotive is controlled to slow down according to the fourth relative distance. This is to avoid collisions between other target rail locomotives and other rail locomotives on their target driving route, and further prompt safety.

[0063] In one embodiment of the present application, the present application also provides a rail locomotive control system based on drones, which is an unmanned driving system that controls the coordinated movement of perception drones and rail locomotives. The system includes a rail locomotive body, a rail microcomputer interlocking, a locomotive onboard decision module, a perception drone, a drone nest and a drone collaborative control module. Among them, the locomotive onboard decision module is responsible for controlling the acceleration, deceleration, and parking of the rail locomotive body, and communicates with the drone collaborative control module to send locomotive positioning, speed and other data, and receive drone positioning, perceived obstacles and other data. It can be understood that the locomotive onboard decision module sends locomotive positioning, speed and other data to the drone collaborative control module to calculate the second relative distance between the obstacle and the attachment, and then control the target rail locomotive to travel according to the second relative distance; the locomotive onboard decision module receives drone positioning, perceived obstacles and other data is also used to calculate the second relative distance between the obstacle and the attachment, that is, the second relative distance can be calculated by the locomotive onboard decision module and / or the drone collaborative control module. Track microcomputer interlocking is an interlocking control system that realizes the interlocking function with route control as the main content. It mainly uses color light signal, power switch and track circuit as three major outdoor equipment, and uses electronic equipment to realize the interlocking function to monitor the track section status, signal status and turnout status, and control the signal and turnout. The perception drone is a special drone equipped with perception sensors such as cameras, laser radars and millimeter wave radars. The drone nest is deployed in a suitable location near the track, which can provide drones with parking platforms, automatic charging (replacement) and communication control functions. The drone collaborative control module is responsible for receiving the task information of the locomotive onboard decision module, and selects, plans and controls the perception drone according to the task information, track map, track microcomputer interlocking and locomotive onboard decision module Real-time data provides perception functions for the movement of rail locomotives.

[0064] Figure 4 is a flow chart of a method for controlling a railway locomotive based on a drone, shown in another exemplary embodiment of the present application, with reference to Figure 4 As shown, the operation steps are as follows:

[0065] Since both locomotives and drones require unmanned operation, in order to ensure the safety of drone routes, a high-precision track route map is first required. According to the high-rise conditions such as on-site wires and corridors, the safety height h is selected to generate the corresponding perception drone flight route. Then, according to the on-site operation plan, the track microcomputer interlocking will turn on the railway track approach signal light. Next, the drone collaborative control module receives the approach signal light turned on by the microcomputer interlocking, and confirms the drone flight route data according to the track route map of the signal light. The drone route confirmed according to the track approach can confirm the safety of the drone according to the track safety rules. Then, the drone collaborative control module calls the nearest, idle and fully charged perception drone from the machine nest to the confirmed unmanned route start position according to the current status and deployment position of the perception drone deployed in the station. Then, the perception drone starts to use high-definition cameras and millimeter-wave radars to scan the track below the drone and return the perception data to the drone airport. Then, the UAV collaborative control module receives the perception data of the UAV airport and the position of the UAV, controls the UAV to fly forward at the specified speed on the confirmed UAV route, and establishes a communication connection with the locomotive onboard decision-making module; the UAV perception device scans the track to realize the function of calculating the type, size, position, etc. of the track approach environmental information obstacles. If the perception UAV identifies an obstacle on the forward track, the UAV collaborative control module will control the UAV to slow down and hover, waiting for the obstacle to disappear or subsequent commands, and calculate the position of the obstacle relative to the attachment body (x22, y22, z22) based on the UAV position (x1, y1, z1), the obstacle position relative to the UAV (x11, y11, z11), and the locomotive (tank car) attachment body position (x2, y2, z2), and feedback the obstacle information to the locomotive onboard decision-making module in real time. The distance from the locomotive (tank car) attachment body to the obstacle The safe parking distance d is calculated by the onboard decision module to obtain the safe speed limit v through the following formula: Among them, a is the braking acceleration of the target track locomotive. Then, the locomotive onboard decision module controls the locomotive speed in a closed loop according to the obstacle data in front of the track sent back by the perception drone, so that the locomotive stops safely in front of the obstacle. After the obstacle disappears, the system continues to perform the task; finally, the locomotive and tank car coupling complete the running task, and the perception drone returns to the airport to charge and wait for the next task.

[0066] In this embodiment, drones are equipped with sensing sensors such as cameras, laser radars, and millimeter-wave radars, and equipped with drone airports and drone collaborative management and control systems to control drones to fly to the direction of locomotives and tank car attachments in real time, scan, increase the flexibility of environmental perception of the intelligent transportation system, and reduce the number of sensing devices and maintenance workload. For example: There are 6 locomotives and 28 tank cars in a certain intelligent molten iron unmanned transportation scene. According to the relevant technical solution, two sets of vehicle-mounted sensing kits are installed on each locomotive, and one set of vehicle-mounted sensing kits is installed on each tank car. A total of 6*2+28=40 sets of vehicle-mounted sensing kits are required to ensure the safety of unmanned driving of locomotives. If the solution of this application is used, the deployment of drones and airports will take into account the on-site track and environmental conditions, and select a suitable location to deploy on the ground. In this way, a set of sensing drones can serve multiple locomotive running tasks at different times. It only needs to ensure that each locomotive has a sensing drone to cooperate with the running, and a total of 6 sets can ensure the safety of unmanned driving of locomotives.

[0067] One drone perception in the present application can correspond to multiple locomotives, and the drone can adjust the spatial position of the perception equipment according to the on-site conditions, scan the track in the direction of the locomotive's travel, and ensure the safety of the locomotive in all directions; compared with the detachable perception kit that requires manual intervention to disassemble and assemble the perception kit, the unmanned collaborative management and control module controls the perception drone to automatically bind to the track locomotive; it can solve the problem that unmanned molten iron or slag cannot be transported safely due to the installation of the perception kit on the transportation equipment and the drone perception equipment detecting distance is too close.

[0068] Figure 5 1 is a block diagram of a railway locomotive control device based on a drone, shown in an exemplary embodiment of the present application. The device can be configured in a computer device. The device can also be applied to other exemplary implementation environments and specifically configured in other devices. This embodiment does not limit the implementation environment to which the device is applied.

[0069] like Figure 5 As shown, the exemplary UAV-based rail locomotive control device includes: an acquisition module 510, a determination module 520, an identification module 530 and a control module 540.

[0070] Among them, the acquisition module 510 is used to obtain the mission information of the target rail locomotive and the position information of each drone, and the mission information carries the starting position and the end position of the target rail locomotive in the track line; the determination module 520 is used to determine the target drone with the shortest first relative distance according to the starting position, and determine the target flight route of the target drone based on the starting position and the end position; the identification module 530 is used to collect data on the track where the target rail locomotive is located through the target drone to obtain perception data, and identify obstacles based on the perception data, and the perception data includes image data and point cloud data; the control module 540 is used to calculate the second relative distance between the obstacle and the attachment based on the perception data if an obstacle is identified, and control the target rail locomotive to travel according to the second relative distance, and the attachment includes the target rail locomotive.

[0071] It should be noted that the UAV-based rail locomotive control device provided in the above embodiment and the UAV-based rail locomotive control method provided in the above embodiment belong to the same concept, wherein the specific manner in which each module and unit performs the operation has been described in detail in the method embodiment and will not be repeated here. In actual application, the UAV-based rail locomotive control device provided in the above embodiment can distribute the above functions to different functional modules as needed, that is, divide the internal structure of the device into different functional modules to complete all or part of the functions described above, and this is not limited here.

[0072] An embodiment of the present application also provides an electronic device, comprising: one or more processors; a storage device for storing one or more programs, and when the one or more programs are executed by one or more processors, the electronic device implements the drone-based rail locomotive control method provided in the above-mentioned embodiments.

[0073] Figure 6 The structure diagram of the computer system suitable for implementing the electronic device of the embodiment of the present application is shown. It should be noted that: Figure 6 The computer system 600 of the electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0074] like Figure 6As shown, the computer system 600 includes a central processing unit (CPU) 601, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 602 or the program loaded from the storage part 608 to the random access memory (RAM) 603, such as executing the methods provided in the above-mentioned various embodiments. In the RAM 603, various programs and data required for system operation are also stored. The CPU 601, the ROM 602 and the RAM 603 are connected to each other through the bus 604. The input / output (I / O) interface 605 is also connected to the bus 604.

[0075] The following components are connected to the I / O interface 605: an input section 606 including a keyboard, a mouse, etc.; an output section 607 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 608 including a hard disk, etc.; and a communication section 609 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to the I / O interface 605 as needed. A removable medium 611, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 610 as needed so that a computer program read therefrom is installed into the storage section 608 as needed.

[0076] In particular, according to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication section 609, and / or installed from a removable medium 611. When the computer program is executed by a central processing unit (CPU) 601, various functions defined in the system of the present application are executed.

[0077] It should be noted that the computer-readable medium shown in the embodiment of the present application can be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium can be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, wherein a computer-readable computer program is carried. This propagated data signal can take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. A computer program contained on a computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0078] The flowchart and block diagram in the accompanying drawings illustrate the possible architecture, functions and operations of the system, method and computer program product according to various embodiments of the present application. Wherein, each box in the flowchart or block diagram can represent a module, a program segment, or a part of the code, and the above-mentioned module, program segment, or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0079] The units involved in the embodiments described in this application may be implemented by software or hardware, and the units described may also be set in a processor. The names of these units do not, in some cases, constitute limitations on the units themselves.

[0080] Another aspect of the present application further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor of a computer, causes the computer to execute the method for controlling a railway locomotive based on a drone as provided in each of the above embodiments. The computer-readable storage medium may be included in the electronic device described in the above embodiments, or may exist independently without being assembled into the electronic device.

[0081] It should be noted that, although several modules or units of the equipment for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present application, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into being embodied by multiple modules or units.

[0082] Another aspect of the present application also provides a computer program product or a computer program, which includes a computer instruction stored in a computer-readable storage medium. A processor of a computer device reads the computer instruction from the computer-readable storage medium, and the processor executes the computer instruction, so that the computer device executes the rail vehicle control method based on a drone provided in each of the above embodiments.

[0083] Through the description of the above implementation methods, it is easy for those skilled in the art to understand that the example implementation methods described here can be implemented by software or by combining software with necessary hardware. Therefore, the technical solution according to the implementation methods of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, a touch terminal, or a network device, etc.) to execute the method according to the implementation methods of the present application.

[0084] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the embodiments disclosed herein. The present application is intended to cover any variations, uses or adaptations of the present application, which follow the general principles of the present application and include common knowledge or customary technical means in the art that are not disclosed in the present application.

[0085] The above embodiments are merely illustrative of the principles and effects of the present application, and are not intended to limit the present application. Anyone familiar with the technology may modify or change the above embodiments without violating the spirit and scope of the present application. Therefore, all equivalent modifications or changes made by a person of ordinary skill in the art without departing from the spirit and technical ideas disclosed in the present application shall still be covered by the claims of the present application.

Claims

1. A method for controlling a railway locomotive based on an unmanned aerial vehicle, characterized in that: include: Obtaining mission information of the target rail locomotive and location information of each drone, wherein the mission information carries the starting position and the ending position of the target rail locomotive in the rail line; Determine a target UAV with the shortest first relative distance according to the starting position, and determine a target flight route of the target UAV based on the starting position and the end position; The target UAV collects data on the track where the target track locomotive is located to obtain perception data, and performs obstacle identification based on the perception data, wherein the perception data includes image data and point cloud data; If an obstacle is identified, a second relative distance between the obstacle and the attachment is calculated based on the perception data, and the target rail locomotive is controlled to travel according to the second relative distance, and the attachment includes the target rail locomotive.

2. The method for controlling a railway locomotive based on an unmanned aerial vehicle according to claim 1, characterized in that: Determining a target UAV with a shortest first relative distance according to the starting position includes: Calculating based on the position information of each drone and the starting position to obtain first relative distances corresponding to each drone; The UAV with the shortest first relative distance is determined as the target UAV.

3. The method for controlling a railway locomotive based on a drone according to claim 1, characterized in that: Determining a target flight route of the target UAV based on the starting position and the end position includes: Determine a pending travel route of the target rail locomotive according to the starting position and the end position, and determine a target travel route of the target rail locomotive based on a route state of the pending travel route; The target flight route is determined according to the target driving route and a preset safety altitude corresponding to the target driving route.

4. The method for controlling a railway locomotive based on an unmanned aerial vehicle according to claim 1, characterized in that: After determining the target flight route of the target UAV based on the starting position and the end position, the method further includes: Obtaining the detection distance of the target UAV, and calculating based on the detection distance and the height of the target flight route to obtain the perceived safety distance of the target UAV; A calculation is performed according to the perceived safety distance and the braking acceleration of the target rail locomotive to obtain a speed limit of the target rail locomotive, so as to control the travel of the target rail locomotive according to the speed limit.

5. The method for controlling a railway locomotive based on a drone according to any one of claims 1 to 4, characterized in that: After acquiring the sensing data by collecting data on the track where the target track locomotive is located through the target UAV, the method further includes: Extracting features based on the sensing data, and if a preset feature is extracted, identifying the state of the preset feature to obtain a preset feature state, wherein the preset feature state includes at least one of a track section state, a signal state, and a switch state; The target driving route of the target rail vehicle and the target flight route of the target UAV are updated according to the preset characteristic state.

6. The method for controlling a railway locomotive based on an unmanned aerial vehicle according to any one of claims 1 to 4, characterized in that: Calculating a second relative distance between the obstacle and the attachment based on the sensing data, and controlling the target rail vehicle to travel according to the second relative distance, including: The second relative distance is calculated based on the drone position of the target drone, the relative position of the obstacle, and the position of the attachment, wherein the sensing data includes the relative position of the obstacle, and the relative position of the obstacle is the position of the obstacle relative to the target drone; A safe speed limit is calculated according to the second relative distance and a preset parking safety distance, so as to control the target rail locomotive to decelerate to travel below the safe speed limit.

7. The method for controlling a railway locomotive based on an unmanned aerial vehicle according to any one of claims 1 to 4, characterized in that: After performing obstacle identification based on the perception data, the method further includes: If no obstacle is identified, controlling the target UAV to continue flying on the target flight route until the mission of the target rail vehicle is completed; The current power of the target UAV is compared with the preset charging power. If the current power is less than the preset charging power, the target charging station is determined based on the UAV position of the target UAV and the charging station positions corresponding to each charging station, so as to charge the target UAV through the target charging station.

8. A railway locomotive control device based on an unmanned aerial vehicle, characterized in that: include: An acquisition module is used to acquire the mission information of the target rail locomotive and the position information of each drone, wherein the mission information carries the starting position and the ending position of the target rail locomotive in the track line; A determination module, configured to determine a target UAV with the shortest first relative distance according to the starting position, and determine a target flight route of the target UAV based on the starting position and the end position; An identification module, used to collect data on the track where the target track locomotive is located through the target UAV to obtain perception data, and perform obstacle identification based on the perception data, wherein the perception data includes image data and point cloud data; The control module is used to calculate a second relative distance between the obstacle and the attachment based on the perception data if an obstacle is identified, and control the target rail locomotive to travel according to the second relative distance, wherein the attachment includes the target rail locomotive.

9. An electronic device, characterized in that: The electronic device comprises: one or more processors; A storage device for storing one or more programs, when the one or more programs are executed by the one or more processors, enables the electronic device to implement the UAV-based rail locomotive control method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor of a computer, the computer is caused to execute the unmanned aerial vehicle-based rail vehicle control method described in any one of claims 1 to 7.

Images