Rail electronic map automatic generation method, system, medium and electronic device

Abstract

The present disclosure relates to a rail electronic map automatic generation method, system, medium and electronic device, belonging to the field of rail transit, which can automatically generate and update electronic maps. A rail electronic map automatic generation method comprises: obtaining coordinate nodes; filtering the obtained coordinate nodes, taking the filtered coordinate nodes as map nodes on the electronic map; performing sliding window type geometric semantic analysis on the map nodes to determine turnout nodes on the electronic map; generating virtual signal machines on the electronic map based on the exploration distance of the train relative to the turnout nodes, the exploration distance being determined according to the maximum driving speed of the train and the turnout switching time; determining the nearest neighbor map node of the coordinate node with zero speed on the electronic map; determining the parking point position corresponding to the coordinate node with zero speed on the electronic map based on the coordinate node with zero speed and its nearest neighbor map node.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the field of rail transit, in particular, to a rail electronic map automatic generation method, system, medium and electronic device. BACKGROUND

[0002] The existing electronic map generation method of rail line is mainly realized by the way of pre-artificial surveying and mapping trackside equipment and post-artificial labeling. Therefore, there are a large amount of artificial surveying and mapping work and artificial labeling cost. Moreover, the electronic map also needs to be updated due to the change of trackside equipment. Therefore, the existing electronic map generation method has large artificial surveying and mapping cost, artificial labeling cost and artificial maintenance cost. SUMMARY

[0003] The purpose of the present disclosure is to provide a rail electronic map automatic generation method, system, medium and electronic device, which can automatically generate and update the electronic map, reduce the cost of artificial surveying and mapping, artificial labeling and artificial maintenance, and improve the accuracy of the generated electronic map.

[0004] In order to achieve the above purpose, the present disclosure provides a rail electronic map automatic generation method, comprising: acquiring coordinate nodes, wherein the information of the coordinate nodes comprises Cartesian coordinates of the coordinate nodes and train speed at the coordinate nodes; filtering the acquired coordinate nodes, and taking the filtered coordinate nodes as map nodes on an electronic map; performing sliding window type geometric semantic analysis on the map nodes to determine turnout nodes on the electronic map; generating virtual signal machines on the electronic map based on the exploration distance of the train relative to the turnout nodes, wherein the exploration distance is determined according to the maximum running speed of the train and turnout switching time; determining the nearest neighbor map nodes of the coordinate nodes with zero speed on the electronic map; determining the stop point positions corresponding to the coordinate nodes with zero speed on the electronic map based on the acquired coordinate nodes with zero speed and their nearest neighbor map nodes.

[0005] The present disclosure also provides a rail electronic map automatic generation system, comprising: a collection device for collecting coordinate nodes by a multi-sensor fusion method, wherein the information of the coordinate nodes comprises Cartesian coordinates of the coordinate nodes and train speed at the coordinate nodes; a map generation device for acquiring the coordinate nodes from the collection device and executing the steps of the method according to the present disclosure based on the acquired coordinate nodes.

[0006] The present disclosure also provides a non-transitory computer readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method according to the present disclosure.

[0007] The electronic device also comprises a memory storing a computer program, and a processor configured to execute the computer program to implement the steps of the method.

[0008] By using the above technical solution, the electronic map can be automatically generated and updated, the cost of manual surveying, manual marking and manual maintenance is reduced, and the accuracy of the generated electronic map is improved.

[0009] Other features and advantages of the present disclosure will be described in detail in the following detailed description. BRIEF DESCRIPTION OF DRAWINGS

[0010] The accompanying drawings are included to provide a further understanding of the present disclosure and constitute a part of the specification, which together with the detailed description, serve to explain the present disclosure. In the drawings:

[0011] Figure 1 is a flowchart of a track electronic map automatic generation method according to an embodiment of the present disclosure.

[0012] Figure 2 shows a schematic diagram of coordinate nodes collected according to a coordinate node collection strategy of the present disclosure.

[0013] Figure 3 shows a schematic diagram of a map node.

[0014] Figure 4 is a schematic diagram of an electronic map generated according to an embodiment of the present disclosure.

[0015] Figure 5 is a schematic block diagram of a track electronic map automatic generation system according to an embodiment of the present disclosure.

[0016] Figure 6 is a block diagram of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0017] The detailed description of the present disclosure will be described in detail below with reference to the accompanying drawings. It should be understood that the detailed description described herein is only used to illustrate and explain the present disclosure, and is not used to limit the present disclosure.

[0018] Figure 1 is a flowchart of a track electronic map automatic generation method according to an embodiment of the present disclosure. As shown in Figure 1 , the method comprises the following steps S11 to S16.

[0019] In step S11, a coordinate node is obtained, wherein the information of the coordinate node includes the Cartesian coordinates of the coordinate node and the speed of the train at the coordinate node.

[0020] In some embodiments, the coordinate node can be obtained from a multi-sensor fusion locator. The multi-sensor fusion locator is a locator that fuses multiple types of sensors.

[0021] Multi-sensor fusion refers to using multiple sensors to collect the pose and speed of the train, and fusing the collection results of multiple sensors to obtain the final coordinate node. These sensors can include lidar, inertial sensors (IMU), global navigation satellite systems (GNSS), carrier phase differential technology, etc. Through the multi-sensor fusion method, stable high-precision coordinate information can be obtained in complex scenes, and the precision can reach centimeter level, which improves the precision of the generated electronic map.

[0022] During the process of the train starting from the starting point and traversing all track lines, the multi-sensor fusion locator installed on the train will continuously collect the coordinate nodes of the train, and obtain the information of the collected coordinate node node(n, x, y, z, v) by means of high-precision multi-sensor fusion positioning technology, wherein n represents the coordinate node number in time sequence, x, y, z represent the Cartesian coordinates, and v represents the speed of the train passing through the coordinate node.

[0023] In some embodiments, the step of obtaining the coordinate node is performed when any of the following conditions is met: (1) the Euclidean distance between the current position of the train and the last obtained coordinate node is greater than a preset distance threshold, for example, a distance of 1 meter; (2) the change in heading angle between the current heading angle of the train and the heading angle of the train at the last obtained coordinate node is greater than a preset angle threshold, for example, a preset angle threshold of 0.3°; (3) the current speed of the train is zero speed. That is, as long as the first condition is met, the coordinate node will be obtained immediately, as long as the second condition is met, the coordinate node will be obtained immediately, and as long as the third condition is met, the coordinate node will be obtained immediately. Under the above coordinate node acquisition strategy, denser coordinate nodes can be obtained in the curve section.

[0024] In addition, the coordinate node through which the train passes at zero speed is called a parking point coordinate node, and these parking point coordinate nodes can participate in or not participate in the subsequent step of filtering the coordinate nodes. However, these parking point coordinate nodes need to be specially saved for use in subsequent determination of the position of the parking point on the electronic map.

[0025] Figure 2 A schematic diagram of the coordinate nodes obtained according to the above coordinate node acquisition strategy is shown. Figure 2 In this context, P0(x,y,z) represents the coordinate node of the parking point.

[0026] In step S12, the obtained coordinate nodes are filtered, and the filtered coordinate nodes are used as map nodes (map_node(n,x,y,z)) on the electronic map.

[0027] Since the coordinate nodes obtained during train operation are sequential data, if... Figure 1 When a complex route structure exists, the obtained coordinate nodes will have a large number of duplicates. In this disclosure, a sliding window filtering strategy is used to filter out duplicate coordinate nodes in both directions.

[0028] Now for reference Figure 2 Let's describe the sliding window filtering strategy. First, sequentially traverse the obtained coordinate nodes to determine the coordinate node currently being traversed (i.e.,...). Figure 2 The nearest neighbor coordinate node of the hollow circle (in the diagram), where the nearest neighbor coordinate node is the node located at the first Euclidean distance from the currently traversed coordinate node. Figure 2 Let r represent the coordinate nodes within a range. Then, filter out the nearest neighbor coordinate nodes and use the filtered coordinate nodes as map nodes on the electronic map. That is, filter out coordinate nodes that are within the first Euclidean distance (e.g., 1 meter) of the currently traversed coordinate node and have not yet been traversed. This filters out duplicate coordinate nodes, thus eliminating repeated visits. Figure 2 For example, this means filtering out the three solid coordinate nodes located within the radius r of the hollow circle. The first Euclidean distance can be set according to the actual situation. Its value cannot be too small, otherwise it will not be able to filter out the coordinate nodes that are going back and forth repeatedly. However, its value cannot be too large either, otherwise it will cause too many coordinate nodes near the turnout to be filtered out.

[0029] Figure 3 The diagram shows a sparse coordinate node obtained by filtering coordinate nodes.

[0030] In step S13, a sliding window geometric semantic analysis is performed on the map nodes to determine the turnout nodes on the electronic map.

[0031] Next, refer to Figure 3 This describes how to determine the turnout node.

[0032] First, iterate through the map nodes using a sliding window approach, based on the currently traversed map node map_node(n,x,y,z) (in... Figure 3 The middle part represents map node 3) and its nearest neighbor historical traversal map nodes map_node(n-1,x,y,z) (inFigure 3 In the case of the map node 2), a line segment Ln is created. The historically traversed map node refers to a map node that has been traversed previously. Then, a map node search_node(n, x, y, z) that has not been traversed and is located within a second Euclidean distance (for example, 1.5 meters) range of the current traversed map node map_node(n, x, y, z) is searched, in Figure 3 In the case of the map node 2), a line segment Ln is created. The historically traversed map node refers to a map node that has been traversed previously. Then, a map node search_node(n, x, y, z) that has not been traversed and is located within a second Euclidean distance (for example, 1.5 meters) range of the current traversed map node map_node(n, x, y, z) is searched, in Figure 3 For example, the map node 3 is a turnout node.

[0033] The specific values of the first Euclidean distance, the second Euclidean distance, and the preset angle threshold value can be set and fine-tuned according to the actual line conditions to adapt to the mapping effect. For example, the first Euclidean distance can be 1 meter, the second Euclidean distance can be 1.5 meters, and the preset angle threshold value can be 30°.

[0034] In some embodiments, a corresponding link relationship can also be established according to whether a map node is a turnout node. For example, if the current traversed map node is determined to be a turnout node, a single link relationship is established between the current traversed map node and its nearest neighbor historically traversed map node; if the current traversed map node is determined to be a non-turnout node, a double link relationship is established between the current traversed map node and its nearest neighbor historically traversed map node. As Figure 4 shown, the corresponding link relationship and the turnout node are shown. As Figure 4 shown, the turnout node corresponding to the map node 3 is the map node 19, so the link relationship between the map node 3 and the map node 19 is a single link relationship (represented by a one-way arrow); the map node 3 and the map node 2 and the map node 4 are all non-turnout neighbor nodes, so they are all double link relationships (represented by double-headed arrows).

[0035] In step S14, the virtual signal is generated on the electronic map based on the exploration distance of the train relative to the turnout node, wherein the exploration distance is determined according to the maximum running speed of the train and the turnout switching time.

[0036] Since the downlink direction is usually taken as the reference when the electronic map is constructed, in some embodiments, in this step, the virtual signal can be generated on the electronic map based on the map node corresponding to the train running the exploration distance in the downlink direction relative to the turnout node, and the offset relative to the map node. The exploration distance D_s is determined by the maximum running speed Vmax of the train and the turnout switching time dt, i.e. D_s = Vmax*dt. Referring to the map nodes and turnout nodes that have been generated Figure 4 , the map node 2 is the downlink point of the map node 3, the map node 3 is the uplink point of the map node 2, and the map node 3 is also a turnout node. The map node corresponding to the train running the exploration distance D_s in the downlink direction relative to the turnout node 3 is the map node 2, so the position of the virtual signal on the electronic map can be represented by the map node 2 and the offset from the map node 2 to the virtual signal, which is the distance between the map nodes 2 and 3 minus the exploration distance D_s.

[0037] In step S15, the nearest neighbor map node of the coordinate node with zero speed obtained is determined on the electronic map.

[0038] In some embodiments, the nearest neighbor search method can be used to search for the nearest neighbor map node of the coordinate node with zero speed obtained on the electronic map. For example, in order to determine the parking point position of the coordinate node with zero speed on the electronic map in the subsequent step, three nearest neighbor map nodes can be searched in step S15, i.e. the first nearest neighbor map node, the second nearest neighbor map node and the third nearest neighbor map node.

[0039] In step S16, the parking point position corresponding to the coordinate node with zero speed is determined on the electronic map based on the coordinate node with zero speed obtained and its nearest neighbor map node.

[0040] Now how to determine the parking point position will be described in combination with Figure 4 .

[0041] Firstly, the distances (which can be Euclidean distances) between the three nearest neighbor map nodes searched in the previous step and the coordinate node P0(x, y, z) with zero speed are determined, i.e., the first distance between the obtained coordinate node P0(x, y, z) with zero speed and the first nearest neighbor map node, the second distance between the obtained coordinate node P0(x, y, z) with zero speed and the second nearest neighbor map node, and the third distance between the obtained coordinate node P0(x, y, z) with zero speed and the third nearest neighbor map node are determined, wherein the first distance < the second distance < the third distance. Figure 4 In the coordinate node P0(x, y, z) with zero speed is located at the position S0 on the electronic map, therefore, the three nearest neighbor map nodes of the coordinate node P0(x, y, z) with zero speed are map nodes 5, 6 and 7 respectively.

[0042] Then, according to the second distance, the third distance, and the interval between the adjacent nearest neighbor map nodes, the map position of the obtained coordinate node P0(x, y, z) with zero speed on the electronic map is determined.

[0043] This operation is based on the consideration that, referring to Figure 4 If the intervals of the three map nodes 5, 6, 7 are uniform, then according to the distances between the coordinate node P0(x, y, z) with zero speed and the three map nodes, it can be determined that the coordinate node P0(x, y, z) with zero speed is between the map nodes 6 and 7; however, in the case of non-uniform map node intervals, this determination method has problems. Therefore, more stringent constraints need to be added. That is, according to the second distance, the third distance, and the interval between the adjacent nearest neighbor map nodes, the map position of the obtained coordinate node P0(x, y, z) with zero speed on the electronic map is further determined.

[0044] That is, if the second distance is less than or equal to the interval between the first nearest neighbor map node and the second nearest neighbor map node, then it is determined that the obtained coordinate node P0(x, y, z) with zero speed is between the first nearest neighbor map node and the second nearest neighbor map node on the electronic map; if the third distance is less than or equal to the interval between the third nearest neighbor map node and the first nearest neighbor map node, then it is determined that the obtained coordinate node P0(x, y, z) with zero speed is between the first nearest neighbor map node and the third nearest neighbor map node on the electronic map.

[0045] For example, Figure 4For example, if the coordinate node P0(x, y, z) with zero speed is determined to be between the map nodes 6 and 7 in the previous step, it is further determined whether the distance from the coordinate node P0(x, y, z) with zero speed to the map node 7 is less than or equal to the distance between the map nodes 6 and 7; similarly, if the coordinate node P0(x, y, z) with zero speed is determined to be between the map nodes 5 and 6 in the previous step, it is further determined whether the distance from the coordinate node P0(x, y, z) with zero speed to the map node 5 is less than or equal to the distance between the map nodes 5 and 6.

[0046] In addition, the coordinate node P0(x, y, z) with zero speed obtained by the method described above corresponds to the map position S0 in the electronic map, however, the map position S0 is not a map node, and therefore, in order to accurately represent the map position S0, it is necessary to represent the position using a map node and an offset, for example, the map position S0 is represented using the map node 6 and the corresponding offset offset_s0. The offset offset_s0 is offset in the upward direction from the map node 6. It can also be defined as offset in the downward direction from the map node 7. Figure 4

[0047] Then, based on the map position and the installation position distribution of the locator on the train, the parking point positions of the two ends of the train on the electronic map are determined.

[0048] For example, according to the map position S0 and the installation position distribution of the locator on the train, upward and downward exploration is performed, thereby obtaining the parking contour points as the map positions S1 and S2. The upward end of the train is defined as the a end, and the downward end is defined as the b end, and then based on the map position S0 (represented by the map node 6 and the upward direction offset) and the longitudinal lengths a_len and b_len of the locators relative to the a and b ends of the train, position search is performed, and the parking point positions of the a and b ends can be obtained, as shown in FIG. 6, which are the map positions S2 and S1, respectively. The two map positions are still represented by a map node and an offset, the map position S2 is represented by the map node 6 and the offset offset_a, and the map position S1 is represented by the map node 4 and the offset offset_b. In this way, the corresponding parking point positions on the electronic map are obtained as the map positions S1 and S2. Figure 4 Figure 4 By using the technical solutions described above, since the coordinate nodes can be automatically obtained, the coordinate nodes can be automatically filtered, the turnout nodes can be automatically determined, the virtual signal machines can be automatically generated, and the parking point positions of the zero speed coordinate nodes on the electronic map can be automatically determined, the electronic map can be automatically generated and updated, the cost of manual surveying, manual marking, and manual maintenance is reduced, and the accuracy of the generated electronic map is improved.

[0049] By using the technical solutions described above, since the coordinate nodes can be automatically obtained, the coordinate nodes can be automatically filtered, the turnout nodes can be automatically determined, the virtual signal machines can be automatically generated, and the parking point positions of the zero speed coordinate nodes on the electronic map can be automatically determined, the electronic map can be automatically generated and updated, the cost of manual surveying, manual marking, and manual maintenance is reduced, and the accuracy of the generated electronic map is improved. ​​

[0050] Figure 5 is a schematic block diagram of a track electronic map automatic generation system according to an embodiment of the present disclosure. As shown in Figure 5 the system includes: a collection device 51 configured to collect coordinate nodes by a multi-sensor fusion method, wherein information of the coordinate nodes includes Cartesian coordinates of the coordinate nodes and a train speed at the coordinate nodes; and a map generation device 52 configured to obtain the coordinate nodes from the collection device 51 and perform steps of the track electronic map automatic generation method according to an embodiment of the present disclosure based on the obtained coordinate nodes.

[0051] As to the system in the above embodiments, the specific manner in which each module performs operations has been described in detail in the embodiments of the method, and will not be described in detail here.

[0052] By adopting the above technical solutions, since the coordinate nodes can be automatically collected by the multi-sensor fusion method, the coordinate nodes can be automatically filtered, the turnout nodes can be automatically determined, the virtual signal machines can be automatically generated, and the zero-speed coordinate nodes can be automatically determined to be the stopping point positions on the electronic map, therefore, the electronic map can be automatically generated and updated, the cost of manual surveying, manual labeling and manual maintenance is reduced, and the accuracy of the generated electronic map is improved.

[0053] Figure 6 is a block diagram of an electronic device 700 according to an example embodiment. As shown in Figure 6 the electronic device 700 can include a processor 701 and a memory 702. The electronic device 700 can also include one or more of a multimedia component 703, an input / output (I / O) interface 704, and a communication component 705.

[0054] The processor 701 is configured to control overall operations of the electronic device 700 to complete all or part of the steps of the above-described track electronic map automatic generation method. The memory 702 is configured to store various types of data to support operations of the electronic device 700, which can include, for example, instructions for operating any application or method on the electronic device 700, and application-related data, such as contact data, sent and received messages, pictures, audio, video, and the like. The memory 702 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk. The multimedia component 703 can include a screen and an audio component. The screen can be, for example, a touch screen, and the audio component is configured to output and / or input audio signals. For example, the audio component can include a microphone configured to receive external audio signals. The received audio signals can be further stored in the memory 702 or transmitted through the communication component 705. The audio component also includes at least one speaker configured to output audio signals. The I / O interface 704 provides an interface between the processor 701 and other interface modules, which can be a keyboard, a mouse, a button, and the like. The buttons can be virtual buttons or physical buttons. The communication component 705 is configured to perform wired or wireless communication between the electronic device 700 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, near field communication (NFC), 2G, 3G, 4G, NB-IOT, eMTC, or other 5G, and the like, or a combination of one or more of them, is not limited herein. Therefore, the corresponding communication component 705 can include a Wi-Fi module, a Bluetooth module, an NFC module, and the like.

[0055] In an exemplary embodiment, the electronic device 700 can be implemented by one or more Application Specific Integrated Circuit (ASIC), Digital Signal Processor (DSP), Digital Signal Processing Device (DSPD), Programmable Logic Device (PLD), Field Programmable Gate Array (FPGA), controller, microcontroller, microprocessor or other electronic elements for executing the above-mentioned track electronic map automatic generation method.

[0056] In another exemplary embodiment, a computer readable storage medium including program instructions is also provided, which, when executed by a processor, implements the steps of the above-mentioned track electronic map automatic generation method. For example, the computer readable storage medium can be the above-mentioned memory 702 including program instructions, and the above-mentioned program instructions can be executed by the processor 701 of the electronic device 700 to complete the above-mentioned track electronic map automatic generation method.

[0057] The preferred embodiments of the present disclosure are described in detail above with reference to the accompanying drawings, but the present disclosure is not limited to the specific details in the above-described embodiments. Within the technical concept of the present disclosure, various simple modifications can be made to the technical solutions of the present disclosure, and these simple modifications all belong to the protection scope of the present disclosure.

[0058] In addition, it should be noted that each specific technical feature described in the above specific embodiments can be combined in any appropriate manner without contradiction. In order to avoid unnecessary repetition, various possible combinations are not described again in the present disclosure.

[0059] In addition, any combination of various different embodiments of the present disclosure can also be made, as long as it does not deviate from the idea of the present disclosure, and it should also be considered as disclosed in the present disclosure.

Claims

1. A method for automatically generating an electronic map of a track, characterized in that, The method comprises: acquiring coordinate nodes, wherein information of the coordinate nodes comprises Cartesian coordinates of the coordinate nodes and train speeds of the train at the coordinate nodes; filtering the acquired coordinate nodes, and taking the filtered coordinate nodes as map nodes on an electronic map; performing sliding window geometric semantic analysis on the map nodes to determine switch nodes on the electronic map; generating virtual signal machines on the electronic map based on an exploration distance of the train relative to the switch nodes, wherein the exploration distance is determined according to a maximum running speed of the train and switch switching time; determining a nearest neighbor map node of a coordinate node with a zero speed on the electronic map; determining a parking point position corresponding to the coordinate node with the zero speed on the electronic map based on the coordinate node with the zero speed and the nearest neighbor map node thereof; the performing of the sliding window geometric semantic analysis on the map nodes to determine the switch nodes on the electronic map comprises: sliding window traversing the map nodes, creating a line segment Ln based on a currently traversed map node and a nearest neighbor historical traversed map node thereof; searching for a yet-to-be-traversed map node within a second Euclidean distance range of the currently traversed map node; determining a distance Dnm between the yet-to-be-traversed map node and the line segment Ln, and an included angle between a line segment composed of the yet-to-be-traversed map node and the currently traversed map node and the line segment Ln; if the distance Dnm is greater than a first Euclidean distance and smaller than the second Euclidean distance, and the included angle is greater than a preset included angle threshold, determining that the currently traversed map node is a switch node on the electronic map.

2. The method of claim 1, wherein, The acquiring of the coordinate nodes is performed when any of the following conditions is met: a Euclidean distance between a current position of the train and a last acquired coordinate node is greater than a preset distance threshold; a heading angle change between a current heading angle of the train and a heading angle of the train at the last acquired coordinate node is greater than a preset angle threshold; and a current train speed is zero.

3. The method of claim 1, wherein, The filtering of the acquired coordinate nodes and taking of the filtered coordinate nodes as the map nodes on the electronic map comprises: sequentially traversing the acquired coordinate nodes to determine a nearest neighbor coordinate node of a currently traversed coordinate node, wherein the nearest neighbor coordinate node is a coordinate node within a first Euclidean distance range of the currently traversed coordinate node; filtering out the nearest neighbor coordinate node, and taking the filtered coordinate node as the map node on the electronic map.

4. The method of claim 1, wherein, The method further comprises: if the currently traversed map node is determined to be a switch node, establishing a single link relationship between the currently traversed map node and a nearest neighbor historical traversed map node thereof; if the currently traversed map node is determined to be a non-switch node, establishing a double link relationship between the currently traversed map node and a nearest neighbor historical traversed map node thereof.

5. The method of claim 1, wherein, The step of generating a virtual signal on the electronic map based on the exploration distance of the train relative to the turnout node includes: The virtual signal is generated on the electronic map based on the map node corresponding to the train after traveling the exploration distance relative to the turnout node in the down direction, and the offset relative to that map node.

6. The method according to claim 1, characterized in that, The determination of the nearest neighbor map node of the obtained coordinate node with zero speed on the electronic map includes: using the nearest neighbor search method to search for the first nearest neighbor map node, the second nearest neighbor map node, and the third nearest neighbor map node of the obtained coordinate node with zero speed on the electronic map. The step of determining the parking point location corresponding to the zero-speed coordinate node on the electronic map based on the acquired coordinate nodes of zero speed and their nearest neighbor map nodes includes: Determine the first distance between the obtained coordinate node with a vehicle speed of zero and the first nearest neighbor map node, the second distance between the node and the second nearest neighbor map node, and the third distance between the node and the third nearest neighbor map node, wherein the first distance < the second distance < the third distance; Based on the second distance, the third distance, and the distance between adjacent nearest neighbor map nodes, the map position of the obtained coordinate node with a vehicle speed of zero speed on the electronic map is determined. Based on the map location and the distribution of the locators installed on the train, the stopping points at both ends of the train on the electronic map are determined.

7. The method of claim 6, wherein, Determining the map position of the obtained coordinate node with a vehicle speed of zero on the electronic map based on the second distance, the third distance, and the distance between adjacent nearest neighbor map nodes includes: If the second distance is less than or equal to the distance between the first nearest neighbor map node and the second nearest neighbor map node, then the obtained coordinate node with a vehicle speed of zero is determined to be located between the first nearest neighbor map node and the second nearest neighbor map node on the electronic map. If the third distance is less than or equal to the distance between the third nearest neighbor map node and the first nearest neighbor map node, then the obtained coordinate node with a vehicle speed of zero is determined to be located on the electronic map between the first nearest neighbor map node and the third nearest neighbor map node.

8. A system for automatically generating an electronic map of a track, characterized in that it comprises: include: The data acquisition device is used to acquire coordinate nodes through a multi-sensor fusion method, wherein the information of the coordinate nodes includes the Cartesian coordinates of the coordinate nodes and the train speed at the coordinate nodes. A map generation apparatus for acquiring the coordinate nodes from the acquisition device and performing the steps of the method according to any one of claims 1 to 7 based on the acquired coordinate nodes.

9. A non-transitory computer-readable storage medium having stored thereon a computer program, characterized in that, When executed by a processor, the program implements the steps of the method described in any one of claims 1-7.

10. An electronic device, comprising: include: A memory on which computer programs are stored; a processor for executing the computer program in the memory to implement the steps of the method of any of claims 1-7.

Images