Train positioning method and system

Abstract

The invention discloses a train positioning method and system. The method comprises the steps that when a train drives into an inactive area, first positioning information of the train is determined according to an ultra-wideband signal of the train; mapping the first positioning information of the train to a station map, and determining track section occupation information of the train; when the train drives into an activation area, acquiring point cloud data detected by the train in real time; according to the point cloud data and the station yard map, determining second positioning information of identification equipment of the activation area; and according to the second positioning information, carrying out intrusion detection on the train to obtain a train intrusion result. According to the embodiment of the invention, the accuracy of train positioning can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and particularly to a train positioning method and system. Background Art

[0002] Train intrusion detection is an essential part of railway traffic safety. It is necessary to check whether there are obstacles intruding into the train running limit during the train operation, so as to avoid collisions or hindering the train movement, thus providing a strong guarantee for the safe and efficient operation of the train.

[0003] Currently, accurate train positioning information can ensure the accuracy of train intrusion detection. Train positioning can be achieved by manual means or by combining track circuits with balises.

[0004] Among them, the manual operation process is complex, error-prone, and has great potential safety hazards. The positioning method of combining track circuits with balises is that the track circuit sends the information of the forward route to the train by carrying the coded information. When the train receives the permission signal and passes the balise, the train positioning is completed. The positioning method of combining track circuits with balises can only provide point positioning information. When the train starts to run, the on-board equipment of the train powers on and starts, and it is impossible to obtain the initial positioning information; the trackside equipment is scattered; the project cost and maintenance cost are high; the positioning accuracy is limited; the adaptability of the track circuit is poor and it is easily affected by external factors. Summary of the Invention

[0005] The present invention provides a train positioning method and system, which can improve the accuracy of train positioning.

[0006] In a first aspect, an embodiment of the present invention provides a train positioning method, which includes:

[0007] When the train enters the non-activated area, determining the first positioning information of the train according to the ultra-wideband signal of the train;

[0008] Mapping the first positioning information of the train to the yard map to determine the track section occupancy information of the train;

[0009] When the train enters the activated area, acquiring the point cloud data detected by the train in real time;

[0010] According to the point cloud data and the yard map, determining the second positioning information of the identification device in the activated area;

[0011] According to the second positioning information, performing an intrusion check on the train to obtain a train intrusion result.

[0012] In a second aspect, an embodiment of the present invention further provides a train positioning system, including: ground equipment and on-board equipment;

[0013] The ground equipment is used to determine the first positioning information of the train according to the ultra-wideband signal of the train when the train enters the non-activated area;

[0014] The ground equipment is used to map the first positioning information of the train into the station yard map to determine the occupancy information of the track section of the train;

[0015] The on-vehicle equipment is used to obtain the point cloud data detected by the train in real time when the train enters the activated area;

[0016] The on-vehicle equipment is used to determine the second positioning information of the identification equipment in the activated area according to the point cloud data and the station yard map;

[0017] The on-vehicle equipment is used to perform intrusion inspection on the train according to the second positioning information to obtain the train intrusion result.

[0018] The technical solution of the embodiment of the present invention performs the first positioning by using the ultra-wideband signal of the train when the train enters the non-activated area, determines the occupancy information of the track section based on the first positioning, performs the second positioning by using the point cloud data collected by the train when the train enters the activated area, and determines the train intrusion result based on the second positioning. It can achieve precise positioning within the track section with fewer devices, reduce the equipment maintenance cost of positioning, realize the simplification of positioning devices, and adopt two-level positioning with different precision granularities to adapt to different operation sections. While reducing the positioning cost, it takes into account the positioning accuracy, can avoid the problem of poor adaptability of track circuits, and adapt to the positioning scenarios of diverse external environments, and the compatibility and adaptability of the positioning system.

[0019] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present invention, nor is it used to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. Description of the Drawings

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0021] Figure 1 is a flowchart of a train positioning method provided according to an embodiment of the present invention;

[0022] Figure 2 is a flowchart of a train positioning method provided according to an embodiment of the present invention;

[0023] Figure 3 It is a schematic diagram of a scenario where a train enters a station according to an embodiment of the present invention;

[0024] Figure 4 It is a schematic diagram of a scenario where multiple trains are accessed in a track section and / or a turnout-free section according to an embodiment of the present invention;

[0025] Figure 5 It is a structural diagram of a train positioning system according to an embodiment of the present invention;

[0026] Figure 6 It is a structural diagram of a train positioning system according to an embodiment of the present invention;

[0027] Figure 7 It is a schematic structural diagram of devices in a train positioning system according to an embodiment of the present invention. Detailed implementation manners

[0028] In order to enable those skilled in the art to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0029] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily need to describe a specific order or sequence. It should be understood that such used data can be interchanged under appropriate circumstances so that the embodiments of the present invention described here can be implemented in an order other than those illustrated or described here. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units does not necessarily need to be limited to those clearly listed steps or units, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0030] In the technical solution of the embodiment of the present invention, the acquisition, storage, application, etc. of the driving trajectory points and the like all comply with the provisions of relevant laws and regulations and do not violate public order and good customs.

[0031] Figure 1The flowchart of a train positioning method provided by an embodiment of the present invention. The embodiment of the present invention is applicable to the situation of how to position a train in a scenario without track circuits. This method can be executed by a train positioning device, which can be implemented in the form of hardware and / or software.

[0032] See Figure 1 The train positioning method shown in the figure includes:

[0033] S101. When the train enters the non-active area, determine the first positioning information of the train according to the ultra-wideband signal of the train.

[0034] Among them, the non-active area is an area for detecting the occupancy of track sections. The non-active area can refer to an area where a relatively low-precision positioning technology is used for positioning. Usually, during the detection of track section occupancy, the safety requirements of the train are relatively loose, and it is only necessary to determine the section where the train is located. At the same time, the area of each section is relatively large, and the precision requirement is relatively low. Therefore, a relatively low-precision positioning technology can be used for positioning in the non-active area. The ultra-wideband (UWB) positioning technology can be used to position the train in the non-active area.

[0035] The first positioning information can refer to the positioning information of the train in the non-active area determined based on the ultra-wideband signal. At least three UWB base stations are arranged near the non-active area, and a UWB on-vehicle tag is configured on the train. Each UWB base station measures the distance between itself and the train according to the ultra-wideband signal sent by the UWB on-vehicle tag, and calculates the first positioning information of the train according to the distances measured by each UWB base station.

[0036] S102. Map the first positioning information of the train to the station yard map to determine the track section occupancy information of the train.

[0037] Among them, the station yard map is used to provide track topology information for detecting the occupancy of track sections and intrusion detection of trains. The station yard map can include geographical information, attribute information of track-related devices, virtual positions, etc. Among them, the geographical information can include at least one of the following: the jurisdiction boundary of the station yard, track sections, topological structure of turnouts, and line data, etc. Track-related devices can include at least one of the following: trackside devices, stations, tracks, turnouts, and signal lights, etc. The attribute information can include at least one of the following: type, position, elevation, geometric shape, color, and naming information, etc. The virtual position can include at least one of the following: preset position information such as virtual balises and virtual demarcation points of track sections, etc. When the first positioning information is mapped to the station yard map, and there are track sections in the station yard map, it is possible to determine whether the position where the train is mapped to the station yard map is located within a certain track section according to the position, so as to detect whether the train occupies the track section and the occupied track section.

[0038] S103. When the train enters the activation area, obtain the point cloud data detected by the train in real time.

[0039] Among them, the activation area is the area for intrusion detection of the train. The activation area can be the area where high-precision positioning technology is used for train positioning. Usually, during the process of intrusion detection in the area, the safety requirements of the train are relatively urgent, and it is necessary to judge the precise distance between the train and the identification device. The identification device occupies a small space and has a high precision requirement. Therefore, relatively high-precision positioning technology can be used for positioning in the activation area. Laser radar positioning technology can be used to position the train in the activation area.

[0040] The lidar is configured on the train. The lidar collects the front of the train's driving direction to obtain point cloud data.

[0041] S104. According to the point cloud data and the station yard map, determine the second positioning information of the identification device in the activation area.

[0042] The second positioning information can refer to the positioning information of the identification device in the activation area determined based on the point cloud data. The identification device in the activation area can refer to the device located on the dangerous side of the activation area. The position of this identification device can be the critical position of the dangerous area. Among them, the activation area refers to a certain part of the track section. One side of the activation area is close to the identification device, and the other side is far from the identification device. The side close to the identification device has a higher risk of intrusion. Therefore, the side close to the identification device is determined as the dangerous side, and the side far from the identification device has no risk of intrusion. Therefore, the side far from the identification device is determined as the safe side.

[0043] The positioning information of the identification device determined based on the point cloud data detected by the lidar can refer to the positioning information of the identification device in the coordinate system of the lidar, that is, the positioning information of the identification device in the coordinate system of the train. According to the station yard map and the coordinates of the train, the coordinate system of the train can be converted into the coordinate system of the station yard map, and according to the conversion relationship between the two coordinate systems, the positioning information directly determined based on the point cloud data can be converted into the second positioning information in the station yard map.

[0044] S105. According to the second positioning information, perform an intrusion check on the train to obtain the train intrusion result.

[0045] The positioning information of all trains in the station yard can be obtained, and according to the second positioning information, it can be judged whether the train intrudes into the limit range of the adjacent track section.

[0046] In the technical solution of the embodiment of the present invention, when the train enters the non-activated area, the ultra-wideband signal of the train is used for the first positioning, and the occupancy information of the track section is determined based on the first positioning. When the train enters the activated area, the point cloud data collected by the train is used for the second positioning, and the train intrusion result is determined based on the second positioning. It is possible to achieve precise positioning within the track section with fewer devices, reduce the equipment maintenance cost of positioning, realize the simplification of positioning devices, and adopt two-level positioning with different precision granularities to adapt to different operation sections. While reducing the positioning cost, the positioning accuracy is taken into account, the problem of poor adaptability of track circuits can be avoided, and the positioning scenarios of diverse external environments can be adapted, as well as the compatibility and adaptability of the positioning system.

[0047] Figure 2 It is a flowchart of a train positioning method provided by an embodiment of the present invention. Based on the above embodiment, in the embodiment of the present invention, "determine the second positioning information of the identification device in the activated area according to the point cloud data and the station yard map" is refined to "determine the device positioning information of the collection device that collects the point cloud data relative to the station yard map according to the first positioning information; obtain the attitude information of the collection device of the point cloud data; determine the coordinate transformation matrix according to the device positioning information and the attitude information; identify the identification device in the point cloud data to obtain the device coordinates of the identification device; determine the second positioning information of the identification device in the activated area according to the coordinate transformation matrix and the device coordinates".

[0048] It should be noted that for the parts not detailed in the embodiments of the present invention, reference can be made to the descriptions of other embodiments.

[0049] See Figure 2 The train positioning method shown includes:

[0050] S201. When the train enters the non-activated area, determine the first positioning information of the train according to the ultra-wideband signal of the train.

[0051] S202. Map the first positioning information of the train to the station yard map to determine the occupancy information of the track section of the train.

[0052] S203. When the train enters the activated area, obtain the point cloud data detected by the train in real time.

[0053] S204. Determine the device positioning information of the collection device that collects the point cloud data relative to the station yard map according to the first positioning information.

[0054] Among them, the device positioning information of the acquisition device can be determined according to the first positioning information. In some embodiments, the first positioning information can be determined as the device positioning information. In some embodiments, the first positioning information is actually the positioning information of the device that emits the UWB signal. The relative position between the device that emits the UWB signal and the acquisition device is fixed. The positioning information of the acquisition device can be obtained according to the relative position between the device that emits the UWB signal and the acquisition device, and the positioning information of the acquisition device is mapped to the station yard map to obtain the device positioning information.

[0055] S205. Obtain the attitude information of the acquisition device of the point cloud data.

[0056] Among them, the attitude information can refer to the three-axis attitude angle and motion state of the acquisition device. An Inertial Measurement Unit (IMU) can be used to detect the three-axis attitude angle (or angular rate) and acceleration, etc. of the acquisition device.

[0057] S206. Determine a coordinate transformation matrix according to the device positioning information and the attitude information.

[0058] Among them, the coordinate transformation matrix can refer to the transformation matrix from the coordinate system of the acquisition device to the coordinate system of the station yard map. Determine the rotation matrix according to the attitude information, determine the translation matrix according to the device positioning information, and determine the coordinate transformation matrix according to the translation matrix and the rotation matrix. Among them, the first 3*3 elements in the coordinate transformation matrix are the rotation matrix, and the last column of elements is the translation matrix.

[0059] S207. Identify the identification device in the point cloud data to obtain the device coordinates of the identification device.

[0060] Among them, the point cloud data can include all objects in front of the train driving direction. The device coordinates can refer to the position of the identification device in the coordinate system of the acquisition device. Before matching, the point cloud data can be classified and preprocessed first: the train collects point cloud data along the track, combines with a high-resolution color camera module to collect images, and synchronously obtains information such as color and geometry.

[0061] In some embodiments, usually the shape of the identification device is fixed, and a matching search algorithm can be used to identify the identification device in the point cloud data. The fixed features of the identification device can be used to match each point in the point cloud data to obtain the points of the identification device, and the points belonging to the identification device are determined as the identification result of the identification device. The device coordinates of the identification device are determined according to the position of the identification device in the point cloud data.

[0062] In some embodiments, through a pre-trained deep learning model, the deep learning model can classify trackside devices, achieve point cloud segmentation and point cloud classification for a single trackside device, and eliminate non-effective point cloud information such as catenaries, workers, buildings, and noise points.

[0063] S208. Determine the second positioning information of the identification device in the activation area according to the coordinate transformation matrix and the device coordinates.

[0064] Among them, the coordinate transformation matrix is used to convert the coordinates in the coordinate system of the acquisition device into the coordinates in the station yard map. In some embodiments, the coordinates obtained by multiplying the device coordinates by the coordinate transformation matrix are used as the second positioning information in the station yard map.

[0065] S209. Perform intrusion inspection on the train according to the second positioning information to obtain a train intrusion result.

[0066] The technical solution of the embodiment of the present invention can determine the coordinate transformation matrix from the coordinate system of the acquisition device to the coordinate system of the station yard map according to the attitude information of the acquisition device and the device positioning information of the acquisition device in the station yard map, and based on the coordinate transformation matrix, convert the device coordinates of the identification device identified from the point cloud data into the second positioning information in the coordinate system of the station yard map, so as to obtain the positioning information of the train in the activation area of the station yard map, and thus perform intrusion detection in real time and accurately according to the positioning information in the station yard map, improving the accuracy of intrusion detection.

[0067] In some embodiments, the performing intrusion inspection on the train according to the second positioning information to obtain a train intrusion result includes: determining the distance between the train and the identification device according to the second positioning information; performing intrusion inspection on the train according to the distance between the train and the identification device to obtain a train intrusion result.

[0068] Among them, the identification device can be understood as a device located at the critical position between the dangerous area and the safe area. The position difference between the train and the identification device can be calculated according to the first positioning information and the second positioning information, and the distance between the train and the identification device can be calculated according to the position difference. In some embodiments, when the distance is greater than or equal to the preset safety distance threshold, it is determined that the train intrusion result is non-intrusion, and when the distance is less than the safety distance threshold, it is determined that the train intrusion result is intrusion.

[0069] In addition, after the activation duration when the train lidar starts to collect point cloud data is greater than or equal to the duration threshold, or when the train crosses the lidar response area within the activation area, it is determined that the identification device fails to identify, and an identification error message is autonomously reported to alert the user. The train intrusion detection method is switched to manual observation. When the identification device is recognized, the train intrusion result is determined according to the comparison result between the ranging result of the lidar and the safety distance threshold. Among them, the lidar response area can start from the boundary point between the activation area and the non-activation area and be within the activation area, and the length of the lidar response area is less than the activation area. The lidar response area is used to intervene manually in a timely manner when the lidar cannot normally implement the project, so as to avoid dangerous driving of the train due to the abnormal function of the lidar.

[0070] It can be seen that by calculating the distance between the train and the identification device according to the second positioning information and performing intrusion detection on the train based on the distance, the train intrusion result is obtained. The intrusion detection can be realized only through the point cloud data and the signal lamp, which simplifies the intrusion detection operation and reduces the implementation cost of the intrusion detection.

[0071] In some embodiments, the identification device includes a signal lamp or a fouling mark, the activation area is located on the safe side of the identification device, and the non-activation area is located on the safe side of the activation area.

[0072] In one example, as Figure 3 shown, a fouling mark or a signal lamp is arranged on one side of the turnout, and the starting point of the activation area is determined according to the position of the fouling mark or the signal lamp. For example, the fouling mark or the signal lamp can be used as the starting point of the activation area. Among them, the preset distance can be 15-20 m, and the preset distance fully considers the positioning error of UWB. Starting from the starting point of the activation area, a first length is extended in the direction away from the fouling mark or the signal lamp to form the activation area. The end point of the activation area is used as the starting point of the non-activation area, and starting from the starting point of the non-activation area, a second length is extended in the direction away from the activation area, the fouling mark or the signal lamp to form the non-activation area. Among them, the first length and the second length can be the same or different, and the first length and the second length are independent of each other. The intersection point between the activation area and the non-activation area is also the end point of the activation area or the starting point of the non-activation area, which is used as the lidar activation point. When the train crosses the lidar activation point and enters the activation area, the lidar is activated and starts to collect the point cloud data in front of the train. Starting from the lidar activation point, a third length is extended in the direction close to the fouling mark or the signal lamp to form the lidar response area. The third length is less than the first length. The boundary points of the lidar response area are the lidar activation point and the manual intervention point. An intrusion alarm point is set at a fourth distance along the direction away from the fouling mark or the signal lamp at the starting point of the activation area. When the train crosses the intrusion alarm point, an alarm needs to be sent to the train and the computer interlocking system for timely safety processing to avoid the risk of train intrusion.

[0073] When the train enters the non - activation area, the UWB positioning system wakes up and starts to work. It checks the occupancy of the track section according to the real - time positioning information. When the train enters the activation area, the lidar is activated and enters the working state. It starts to identify the fouling marks and / or signal lights in front of the train, conducts intrusion detection based on the distance between the fouling marks and / or signal lights and the train, and feeds back the distance information and intrusion results to the man - machine interface (Driver Machine Interface, DMI) and the computer interlocking system in the train control system.

[0074] It can be seen that by taking the signal light or fouling mark as the identification device for the train entry scenario and determining the activation area and non - activation area based on the identification device, the occupancy detection of the track section and the train intrusion detection can be carried out, improving the accuracy of train positioning.

[0075] In some embodiments, the identification device includes a signal light or the rear of the preceding train. The activation area is on the safe side of the identification device, and the non - activation area is on the safe side of the activation area.

[0076] Among them, for the scenario where multiple trains are simultaneously accessed in a track or a turnout - free section, the Centralized traffic control (CTC) arranges the train - receiving route according to the length of the track and / or turnout - free section. Since multiple trains enter the station in sequence in a serial manner, the leading train can take the signal light as the identification device. For the trains after the leading train, that is, the trailing trains, there is no track - side device as the identification device, and the rear of the preceding train can be taken as the identification device. In this way, each train has a different identification device, which is equivalent to obtaining the activation area and non - activation area for each train.

[0077] In an example, such as Figure 4As shown, the starting point of the activation zone is determined according to the signal machine or the boundary point far from the rear of the leading vehicle. For example, the signal machine can be used as the starting point of the activation zone, or the point at a certain safe distance from the rear of the leading vehicle can be used as the starting point of the activation zone. Among them, the area between the rear of the leading vehicle and the starting point of the activation zone is the rear safety envelope area. Starting from the starting point of the activation zone, extend a first length in the direction away from the rear of the leading vehicle to form the activation zone. The end point of the activation zone is used as the starting point of the non-activation zone. Starting from the starting point of the non-activation zone, extend a second length in the direction away from the activation zone, the signal machine or the rear of the leading vehicle to form the activation zone. Among them, the first length and the second length can be the same or different, and the first length and the second length are independent of each other. Among them, the intersection point between the activation zone and the non-activation zone is also the end point of the activation zone or the starting point of the non-activation zone, which is used as the lidar activation point. When the train crosses the lidar activation point and enters the activation zone, the lidar is activated and starts to collect the point cloud data in front of the train. Starting from the lidar activation point, along the direction close to the signal machine or the rear of the leading vehicle, the point at a distance of the activation distance from the lidar activation point is used as the virtual demarcation point. When the train crosses the virtual demarcation point, an alarm needs to be sent to the train and the computer interlocking system to prompt the train of the risk of rear-end collision.

[0078] When the train enters the non-activation zone, the UWB positioning system wakes up and starts to work, and checks the occupancy of the virtual track section according to the real-time positioning information. When the train enters the activation zone, the lidar is activated and enters the working state, starts to identify the signal machine in front of the train or the stopped train, checks the risk of rear-end collision according to the distance between the signal machine in front or the stopped train and the train, and feeds back the distance information and the intrusion result to the man-machine interface (Driver Machine Interface, DMI) and the computer interlocking system in the train control system.

[0079] It can be seen that by targeting the scenario where multiple trains enter the track or the turnout-free section, using the signal machine or the rear of the stopped leading vehicle as the identification device, and determining the activation zone and the non-activation zone based on the identification device, it is possible to detect the occupancy and intrusion of the track or the turnout-free section and check the risk of train rear-end collision, improving the accuracy and operation efficiency of train positioning in the track or the turnout-free section.

[0080] In some embodiments, the activation zone of the leading vehicle is located on the safe side of the signal machine, and the activation zone of the following vehicle is obtained by dividing according to the safe distance from the stopping point of the leading vehicle in the track and / or the turnout-free section.

[0081] Among them, the first train stops behind the signal, and subsequent multiple trains stop behind the previous train in turn. Thus, the first train can use the signal as an identification device, while for the trains after the first train, i.e., the following trains, there is no trackside device as an identification device, and the rear of the previous train can be used as an identification device. In this way, each train has a different identification device, which is equivalent to dividing the section for each train to obtain the activation area and non-activation area of each train. Considering the safety distance between trains, the track section and / or the turnout-free section is divided again. The first train enters the target track section and / or the turnout-free section and stops outside the departure signal / detention signal for shunting; the (n + 1)-th train, i.e., the following train, travels with the n-th virtual demarcation point of the re-divided track section as the target stopping point. The second train and subsequent trains travel towards the target stopping point through the activation area and the non-activation area. The non-activation area is initially located according to the UWB signal of the train, and the activation area collects secondary positioning information with the rear of the previous train as the target according to the lidar of the train, and the train prevents overrunning the virtual demarcation point.

[0082] It can be seen that by re-dividing the track section or the turnout-free section for the scenario where multiple trains enter the track section or the turnout-free section, dividing the activation area and the non-activation area for each train, and controlling the safe stop of each train, the demand for accommodating high-density trains can be met.

[0083] In some embodiments, for the scenario of train start, the originating train enters the standby mode, the train collects key information such as the departure track and the station name, and assists the ATP (Automatic Train Protection) to establish a communication connection with the ground equipment.

[0084] In some embodiments, after determining the first positioning information of the train according to the ultra-wideband signal of the train when the train enters the non-activation area, it further includes: obtaining the pose information of the train; correcting the first positioning information according to the pose information of the train.

[0085] Among them, the pose information of the train may refer to the motion state of the train. For example, the pose information may include: inertial measurement data, speed, distance, etc. Correction may be: adjusting the obviously incorrect pose information into correct data, and / or deleting the redundant pose information, etc.

[0086] In some embodiments, combining the track linear characteristics of the station yard map and the inertial measurement data obtained by detecting the train, filtering the data with low positioning quality based on UWB, and making full use of the non-holonomic constraint characteristics of the train moving on the track to eliminate the longitudinal positioning error. Since the train should travel on the track and will not exceed the longitudinal range of the track, the positioning data that deviates too much from the track in the longitudinal direction is deleted from the first positioning information.

[0087] In some embodiments, according to the inertial measurement data, the speed measurement and ranging unit is fused for processing, and outputs speed, distance, etc., estimates and compensates for the error of the positioning information obtained by UWB, and maintains the UWB positioning accuracy and stability.

[0088] In some embodiments, the number of UWB base stations is 3 + 1. Among them, the distances detected by 3 UWB base stations can determine the first positioning information, and 1 UWB base station is a redundant base station. When the Nth UWB ground base station device fails, the distance detected by this 1 redundant UWB base station, combined with the distances detected by 2 normally working UWB base stations, can still determine the first positioning information. In this way, adding 1 redundant UWB base station can improve the stability and fault tolerance of UWB positioning detection. Considering reducing error interferences such as non-line-of-sight propagation and multipath effects of UWB, the ground base stations are installed on both sides of the joint between the track and the turnout throat in principle, and 1 set of equipment for hot standby redundancy is separately set at both ends of the train for the UWB vehicle-mounted tag. The real-time positioning function of UWB ensures that the train control system correctly judges the running direction of the moving train. The redundant UWB base stations can be used to screen the data with high UWB positioning errors, make full use of the redundant devices of the UWB ground base stations, switch the UWB base stations for positioning, reduce the consumption of simple and blind traversal operations, and improve the effectiveness of UWB positioning. Ranging methods such as, but not limited to, TOF (Time Of Flight), TOA (Time of Arrival), or TDOA (Time Difference of Arrival) can be used to calculate the first positioning information according to the UWB signal.

[0089] It can be seen that by correcting the first positioning information according to the pose information of the train, the accuracy of the first positioning information can be improved.

[0090] Figure 5 This is a schematic structural diagram of a train positioning system provided by an embodiment of the present invention. As Figure 5 shown, the train positioning system 500 includes: a ground device 501 and a vehicle-mounted device 502;

[0091] The ground device 501 is used to determine the first positioning information of the train according to the ultra-wideband signal of the train when the train enters the non-active area; map the first positioning information of the train into the station yard map to determine the track section occupancy information of the train.

[0092] The vehicle-mounted device 502 is used to obtain the point cloud data detected in real time by the train when the train enters the active area; determine the second positioning information of the identification device in the active area according to the point cloud data and the station yard map; perform intrusion inspection on the train according to the second positioning information to obtain the train intrusion result.

[0093] The technical solution of the embodiment of the present invention configures the train positioning system as ground equipment and on-vehicle equipment, and integrates multi-source information such as UWB, map, and point cloud data. The train's real-time positioning is completed through UWB, the occupancy check of the track section is completed in combination with the map, and the train's autonomous intrusion check is realized by using the point cloud data collected by the lidar. At the same time, it does not affect and is compatible with the existing train positioning method that combines track circuits and ground transponders, has good compatibility, and through a simple positioning method, while taking into account the positioning accuracy, simplifies the positioning operation.

[0094] As Figure 6 shown, in some embodiments, the ground equipment includes: an ultra-wideband ground base station, an electronic map server, a first communication interface unit A, a first processor A, and a maintenance upper computer.

[0095] Among them, the ultra-wideband ground base station is used to transmit and receive UWB signals and provide a positioning reference for the train. The electronic map server is used to manage and store the station yard map. The first communication interface unit is used to provide a communication channel for the first processor to communicate with on-vehicle equipment, computer interlocking systems, and CTC (Centralized traffic control) systems, etc., and send the train's identification information and positioning information to on-vehicle equipment and computer interlocking systems, etc. The first processor is used to process UWB signals, determine positioning information, map it to the station yard map to obtain the first positioning information, correct the first positioning information, and communicate with external devices, etc. The maintenance upper computer is used to realize human-computer interaction, as well as functions such as management, monitoring, maintenance, and display of the train positioning system.

[0096] In some embodiments, the ground equipment includes: an ultra-wideband on-vehicle tag, a second communication interface unit B, a lidar module, a high-resolution color camera module, and a second processor B.

[0097] Among them, the ultra-wideband on-vehicle tag is used to send UWB signals to realize the train's autonomous positioning. The second communication interface unit is used to provide a communication channel for the second processor to communicate with ground equipment and computer interlocking systems, and obtain the train's positioning information and attitude information. The lidar module is used to sense the position and geometric information of the surrounding environment and generate a point cloud map. The lidar module may include: a laser emitter, an optical receiver, a turntable, an IMU (Inertial Measurement Unit), and an information processing system, etc. The high-resolution color camera module is used to collect images in front of the train and capture pixel information of the surrounding environment. The second processor has the functions of processing point cloud data and images, communicating with ground equipment and computer interlocking systems, matching pixels and point clouds, classifying and labeling identification devices, solving the conversion between the lidar coordinate system and the station yard electronic map coordinate system, screening target fouling marks and / or signal lights, and judging whether the train is intruding, etc.

[0098] It can be seen that by obtaining the first positioning information through the ground equipment based on UWB and obtaining the second positioning information through the on-vehicle equipment based on the point cloud data, the train can be simply modified. Combining with the ground equipment, precise positioning within the track section can be achieved with fewer devices, reducing the equipment maintenance cost of positioning, realizing streamlined positioning equipment, and adopting two-level positioning with different precision granularities to adapt to different operation sections. While reducing the positioning cost, the positioning accuracy is taken into account, the problem of poor adaptability of track circuits can be avoided, and the positioning scenarios of diverse external environments can be adapted, as well as the compatibility and adaptability of the positioning system.

[0099] In addition, a train control system is also configured on the train. The train control system includes train control system equipment, a DMI, and a speed and distance measurement unit. Among them, the train control system equipment is communicatively connected to the second processor B. The DMI is used to realize human-machine interaction and enable the driver to control the train. The speed and distance measurement unit is used to measure the speed and distance of the train.

[0100] The above train positioning system can execute the train positioning method, and the system can be implemented in the form of hardware and / or software.

[0101] The train positioning system provided by the embodiments of the present invention can execute the train positioning method provided by any embodiment of the present invention, and has corresponding functional modules and beneficial effects for executing the train positioning method.

[0102] Figure 7 The structural schematic diagram of the device (on-vehicle device or ground device) 700 in the train positioning system that can be used to implement the embodiments of the present invention is shown.

[0103] The train positioning system includes a first processor and a second processor, as well as a first memory communicatively connected to the first processor and a second memory communicatively connected to the second processor. For each processor 701, and a memory communicatively connected to the processor 701, such as a read-only memory (ROM) 702, a random access memory (RAM) 703, etc. Among them, the memory stores a computer program executable by at least one processor. The processor 701 can execute various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 702 or the computer program loaded from the storage unit 708 into the random access memory (RAM) 703. In the RAM 703, various programs and data required for the operation of the device 700 in the train positioning system can also be stored. The processor 701, the ROM 702, and the RAM 703 are connected to each other through a bus 704. The input / output (I / O) interface 705 is also connected to the bus 704.

[0104] Multiple components in device 700 of the train positioning system are connected to I / O interface 705, including: input unit 706, such as a keyboard, mouse, etc.; output unit 707, such as various types of displays, speakers, etc.; storage unit 708, such as a disk, optical disc, etc.; and communication unit 709, such as a network card, modem, wireless communication transceiver, etc. Communication unit 709 allows device 700 in the train positioning system to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0105] Processor 701 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 701 include but are not limited to a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 501 executes the various methods and processes described above, such as the train positioning method.

[0106] In some embodiments, the train positioning method can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as storage unit 708. In some embodiments, part or all of the computer program can be loaded and / or installed onto device 700 in the train positioning system via ROM 702 and / or communication unit 709. When the computer program is loaded into RAM 703 and executed by processor 701, one or more steps of the train positioning method described above can be executed. Alternatively, in other embodiments, processor 701 can be configured to execute the train positioning method by any other suitable means (e.g., by means of firmware).

[0107] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip systems (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a dedicated or general-purpose programmable processor, and can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit the data and instructions to the storage system, the at least one input device, and the at least one output device.

[0108] A computer program for implementing the method of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, a special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions / operations specified in the flowchart and / or block diagram to be implemented. The computer programs may be executed entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.

[0109] In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, the computer-readable storage medium may be a machine-readable signal medium. More specific examples of the machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0110] In order to provide interaction with the driver, the systems and techniques described herein may be implemented on an operation detection device that has: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the driver; and a keyboard and a pointing device (e.g., a mouse or a trackball) through which the driver can provide input to the train positioning device. Other kinds of devices may also be used to provide interaction with the user; for example, the feedback provided to the driver may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the driver may be received in any form (including acoustic input, voice input, or tactile input).

[0111] The systems and techniques described herein can be implemented in a computing system including backend components (e.g., as a data server), or a computing system including middleware components (e.g., an application server), or a computing system including frontend components (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described herein), or a computing system including any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected with each other by digital data communication in any form or medium (e.g., a communication network). Examples of communication networks include: local area network (LAN), wide area network (WAN), blockchain network, and the Internet.

[0112] The computing system can include a client and a server. The client and the server are generally remote from each other and typically interact through a communication network. The client-server relationship is created by computer programs running on respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system, and solves the defects of difficult management and weak business scalability existing in traditional physical hosts and VPS (Virtual Private Server) services.

[0113] It should be understood that various forms of the processes shown above can be used, with steps reordered, added, or deleted. For example, the steps recited in the present invention can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved, and no limitation is made herein.

[0114] The above specific embodiments do not constitute a limitation on the protection scope of the present invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A train positioning method, characterized in that, The method includes: When the train enters the non - active area, determining the first positioning information of the train according to the ultra - wideband signal of the train; Mapping the first positioning information of the train into the station yard map to determine the occupancy information of the track section of the train; When the train enters the active area, acquiring the point cloud data detected by the train in real time; According to the point cloud data and the station yard map, determining the second positioning information of the identification device in the active area; According to the second positioning information, performing an intrusion check on the train to obtain the train intrusion result.

2. The method according to claim 1, wherein The determining the second positioning information of the identification device in the active area according to the point cloud data and the station yard map includes: According to the first positioning information, determining the device positioning information of the acquisition device that acquires the point cloud data relative to the station yard map; Acquiring the attitude information of the acquisition device of the point cloud data; According to the device positioning information and the attitude information, determining the coordinate transformation matrix; Identifying the identification device in the point cloud data to obtain the device coordinates of the identification device; According to the coordinate transformation matrix and the device coordinates, determining the second positioning information of the identification device in the active area.

3. The method according to claim 1, characterized in that, The performing an intrusion check on the train according to the second positioning information to obtain the train intrusion result includes: According to the second positioning information, determining the distance between the train and the identification device; According to the distance between the train and the identification device, performing an intrusion check on the train to obtain the train intrusion result.

4. The method according to claim 1, wherein The identification device includes a signal lamp or a fouling mark. The active area is on the safe side of the identification device, and the non - active area is on the safe side of the active area.

5. The method according to claim 1, characterized in that, The identification device includes a signal lamp or the rear end of the preceding train. The active area is on the safe side of the identification device, and the non - active area is on the safe side of the active area.

6. The method according to claim 5, wherein The active area of the leading train is on the safe side of the signal lamp, and the active area of the trailing train is obtained by dividing according to the safe distance from the stopping point of the preceding train in the track and / or turnout - free section.

7. The method according to claim 1, wherein After determining the first positioning information of the train according to the ultra - wideband signal of the train when the train enters the non - active area, it further includes: Acquiring the pose information of the train; Correcting the first positioning information according to the pose information of the train.

8. A train positioning system, characterized in that, It includes: Ground equipment and on - vehicle equipment; The ground equipment is used to determine the first positioning information of the train according to the ultra - wideband signal of the train when the train enters the non - active area; The ground equipment is used to map the first positioning information of the train into the station yard map to determine the occupancy information of the track section of the train; The on - vehicle equipment is used to acquire the point cloud data detected by the train in real time when the train enters the active area; The on - vehicle equipment is used to determine the second positioning information of the identification device in the active area according to the point cloud data and the station yard map; The on - vehicle equipment is used to perform an intrusion check on the train according to the second positioning information to obtain the train intrusion result.

9. The train positioning system according to claim 8, characterized in that, The ground equipment includes: an ultra - wideband ground base station, an electronic map server, a first communication interface unit, a first processor, and a maintenance upper computer.

10. The train positioning system according to claim 8, characterized in that, The ground equipment includes: an ultra-wideband vehicle-mounted tag, a second communication interface unit, a lidar module, a high-resolution color camera module, and a second processor.

Images