Train position correction method and apparatus, device, and medium
By setting up sensing markers on the train track bed and matching the sensing devices with offline semantic maps, the problem of inaccurate train position correction in harsh environments was solved, enabling rapid and accurate train position correction and ensuring driving safety.
Patent Information
- Application Number
- PCT/CN2025/093349
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2025-05-08
- Publication Date
- 2026-11-12
AI Technical Summary
In existing technologies, when trains use signs to correct their position in harsh environments, the positioning results are inaccurate, affecting train operation safety.
By setting up sensing markers on the train track bed, using the train's sensing equipment to identify these markers, and matching them with feature information in a pre-built offline semantic map, the train's position can be determined, ensuring accurate correction of the train's position even in harsh environments.
Even in harsh environments such as heavy fog, rain, snow, and dust, the sensing equipment can detect targets in a timely manner, quickly and accurately determine the train's location, and ensure train driving safety.
Smart Images

Figure CN2025093349_12112026_PF_FP_ABST
Abstract
Description
Train position correction method, device, equipment and medium TECHNICAL FIELD
[0001] The present application relates to the technical field of rail transit, in particular to a train position correction method, device, equipment and medium. BACKGROUND
[0002] Real-time and accurate acquisition of train position information is a guarantee for safe and efficient operation of the train.
[0003] After initial positioning of the train is completed, the train speed is measured by measuring the rotation speed of the train wheels through the speed sensor, the train running distance is obtained by integrating the train speed with respect to time, and the train position is obtained according to the initial positioning and the train running distance. However, as the train running distance increases, the train speed and distance positioning error will gradually increase as the train runs, which will affect the train positioning. Therefore, it is necessary to correct the train position during train operation, that is, to reposition the train.
[0004] In related technologies, the train position is mainly corrected by a signboard. However, due to the influence of harsh environments such as heavy fog, rain, snow, dust, etc., the positioning result obtained by correcting the train position through the signboard is inaccurate, which affects the safety of train driving. SUMMARY
[0005] The embodiments of the present application provide a train position correction method, device, equipment and medium, which can improve the safety of train driving.
[0006] In a first aspect, the embodiments of the present application provide a train position correction method, comprising:
[0007] identifying a perception tag set on a track bed of a track on which the train travels through a perception device installed on the train;
[0008] matching first feature information of the perception tag currently identified by the perception device with feature information of a plurality of groups of perception tags combined in a partial offline semantic map; wherein the partial offline semantic map is a part of the offline semantic map corresponding to the visibility range of the perception device when the train is at a second position, the second position is a position calculated according to a third position and a first time length, the third position is a position obtained by initially positioning the train, and the first time length is a running time length of the train after the initial positioning of the train;
[0009] In a case where only one set of feature information of the combination of the perception markers matches the first feature information in the partial offline semantic map, the first position of the train is determined according to the position of the first perception marker recognized by the perception device, wherein the combination of the perception markers includes a plurality of perception markers, and the first perception marker is any one of the first combination of the perception markers that matches the first feature information in the partial offline semantic map.
[0010] The current position of the train is corrected to the first position.
[0011] In a second aspect, an embodiment of the present application provides a train position correction device, comprising:
[0012] The recognition module is configured to recognize, by the perception device installed on the train, the perception markers arranged on the track bed of the track on which the train travels.
[0013] The matching module is configured to match the first feature information of the perception markers currently recognized by the perception device with the feature information of a plurality of sets of the combination of the perception markers in the partial offline semantic map, wherein the partial offline semantic map is a partial semantic map corresponding to the visibility range of the perception device when the train is at a second position in the pre-constructed offline semantic map, the second position is a position calculated according to a third position and a first time length, the third position is a position obtained by performing initial positioning on the train, and the first time length is a running time length of the train after the initial positioning is performed on the train.
[0014] The first determination module is configured to, in a case where only one set of feature information of the combination of the perception markers matches the first feature information in the partial offline semantic map, determine the first position of the train according to the position of the first perception marker recognized by the perception device, wherein the combination of the perception markers includes a plurality of perception markers, and the first perception marker is any one of the first combination of the perception markers that matches the first feature information in the partial offline semantic map.
[0015] The first correction module is configured to correct the current position of the train to the first position.
[0016] In a third aspect, an embodiment of the present application provides an electronic device, comprising a processor and a memory, wherein the memory stores programs or instructions executable on the processor, and the programs or instructions are executed by the processor to implement the steps of the train position correction method provided in the embodiments of the present application.
[0017] In a fourth aspect, an embodiment of the present application provides a readable storage medium, wherein the readable storage medium stores programs or instructions, and the programs or instructions are executed by a processor to implement the steps of the train position correction method provided in the embodiments of the present application.
[0018] In this embodiment, a sensing device installed on the train identifies sensory markers set on the track bed. The first feature information of the sensory marker currently identified by the sensing device is matched with feature information of multiple sets of sensory marker combinations in a partial offline semantic map. If only one set of sensory marker combinations in the partial offline semantic map matches the first feature information, the first position of the train is determined based on the position of the first sensory marker identified by the sensing device. The first sensory marker is any one of the first sensory marker combinations in the partial offline semantic map that matches the first feature information. The train's current position is then corrected to the first position. Because multiple sensory markers are set on the track bed, even when the train is traveling in adverse environments such as heavy fog, rain, snow, or dust, the sensing device can promptly detect the sensory markers, quickly and accurately determine the train's position, and then use the determined train position to correct the train's current position, thus ensuring train driving safety. Attached Figure Description
[0019] The features, advantages, and technical effects of exemplary embodiments of this application will now be described with reference to the accompanying drawings.
[0020] Figure 1 is a schematic flowchart of the train position correction method provided in an embodiment of this application;
[0021] Figure 2 is a schematic diagram of setting a sensing target on the track bed according to an embodiment of this application;
[0022] Figure 3 is a schematic diagram of the sensing target assembly provided in an embodiment of this application;
[0023] Figure 4 is a schematic diagram of a point cloud map provided in an embodiment of this application;
[0024] Figure 5 is a schematic diagram of the sensory punctuation cloud provided in an embodiment of this application;
[0025] Figure 6 is a schematic diagram of the train position correction device provided in an embodiment of this application;
[0026] Figure 7 is a schematic diagram of an electronic device provided in an embodiment of this application. Detailed Implementation
[0027] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.
[0028] The terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such use of data can be interchanged where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first," "second," etc., are generally of the same class and the number of objects is not limited; for example, a first object can be one or more. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.
[0029] The train position correction method, device, equipment, and medium provided in this application will be described in detail below with reference to the accompanying drawings and through specific embodiments and application scenarios.
[0030] It should be noted that the train position correction method and device provided in this application are applied to trains, and the trains are equipped with sensing devices, including but not limited to lidar.
[0031] Figure 1 is a schematic flowchart of the train position correction method provided in an embodiment of this application. The train position correction method may include the following steps:
[0032] Step 101: Identify the sensor targets set on the track bed of the train using the sensing equipment installed on the train;
[0033] In some possible implementations of the embodiments of this application, the sensing markers in the embodiments of this application are markers set on the track bed for sensing devices to perform sensing.
[0034] In some possible implementations of the embodiments of this application, the sensing markers in the embodiments of this application may be passive, that is, the sensing markers are passive marks set on the track bed for sensing devices to perform sensing.
[0035] In some possible implementations of this application's embodiments, sensing markers can be pre-deployed on the track bed. During train operation, sensing devices detect and identify the sensing markers on the track bed. It is understood that the sensing markers in this application's embodiments differ from the signs placed around the track.
[0036] As shown in Figure 2, Figure 2 is a schematic diagram of setting sensory markers on the track bed according to an embodiment of this application. In Figure 2, sensory markers 203 are set on the track bed 202 of the track 201.
[0037] In some possible implementations of the embodiments of this application, multiple sensors can be combined into a single sensor group, with different spacing between the sensors within the same sensor group. When setting sensors on the track bed, the sensors within the same sensor group are set according to the prescribed sensor spacing.
[0038] For example, as shown in FIG3, FIG3 is a schematic diagram of a sensing beacon combination provided in an embodiment of the present application. In FIG3, the sensing beacon combination includes four sensing beacons, wherein the distance from the first sensing beacon to the second sensing beacon is S1, the distance from the second sensing beacon to the third sensing beacon is S2, and the distance from the third sensing beacon to the fourth sensing beacon is S3.
[0039] Step 102: Match the first feature information of the currently identified beacon by the sensing device with the feature information of multiple sets of beacon combinations in the partial offline semantic map; wherein, the partial offline semantic map is a partial semantic map corresponding to the visual range of the sensing device when the train is in the second position in the pre-constructed offline semantic map; the second position is the position calculated based on the third position and the first duration, the third position is the position obtained by initial positioning of the train, and the first duration is the running time of the train after initial positioning;
[0040] In some possible implementations of this application's embodiments, after the sensor beacons are installed on the track bed, the train can be controlled to travel at low speed on the track. Three-dimensional spatial point cloud information during the train's movement is collected in real time using sensing devices. The collected three-dimensional spatial point cloud information is then used to construct an offline point cloud map according to the train's trajectory. Figure 4 is a schematic diagram of the point cloud map provided in this application's embodiment. The sensor beacon point cloud is shown in Figure 5, which is also a schematic diagram of the sensor beacon point cloud provided in this application's embodiment. Then, an offline semantic map is constructed based on the offline point cloud map and the feature information of the sensor beacons. The feature information includes, but is not limited to, the position of the sensor beacons and the distance between adjacent sensor beacons. In this application's embodiment, the feature information of a combination of sensor beacons is considered as a set of semantic information.
[0041] In some possible implementations of the embodiments of this application, the visible range is the range that the sensing device can perceive, and it can also be referred to as the sensing range.
[0042] After the train is initially positioned, the rotational speed of the train wheels is measured using speed sensors. Based on the rotational speed of the train wheels measured by the speed sensors and the train's running time, the train's travel distance can be determined. Then, based on the train's initial positioning position (i.e., the third position in this embodiment) and the travel distance, the position that the train should reach after the corresponding running time (i.e., the second position in this embodiment) can be determined.
[0043] During train operation, the sensing devices collect point cloud information of the three-dimensional space along the train's route and send this information to the host of the active sensing system on the train. The host analyzes the point cloud information and calculates the distance between two adjacent sensing targets identified by the sensing devices. The feature information of the currently identified sensing targets is then matched with the feature information of multiple sets of sensing targets in a pre-constructed offline semantic map corresponding to the portion of the semantic map within the sensing devices' visibility range when the train is in its second position.
[0044] Step 103: In the case where only one set of sensory beacon combination features match the first feature information in the partial offline semantic map, determine the first position of the train based on the position of the first sensory beacon identified by the sensing device. The sensory beacon combination includes multiple sensory beacons, and the first sensory beacon is any one of the sensory beacons in the first sensory beacon combination that matches the first feature information in the partial offline semantic map.
[0045] In a partial semantic map, if only one set of sensor beacon combination features matches the feature information of the currently identified sensor beacon, it indicates that the feature information of the currently identified sensor beacon is unique, and the currently identified sensor beacon can be used to determine the train's position. In this case, any one of the sensor beacons in the combination that matches the feature information of the currently identified sensor beacon can be used to determine the train's position.
[0046] In some possible implementations of the embodiments of this application, in step 103, the distance from the sensing device to the sensing target can be obtained through the sensing device, and then the distance from the train to the sensing target can be determined based on the distance, so as to obtain the position of the train.
[0047] When at least two sets of sensory beacon combination feature information in a partial semantic map match the feature information of the sensory beacon currently identified by the sensing device, it indicates that the feature information of the sensory beacon currently identified by the sensing device is not unique, and the train position cannot be accurately determined using the sensory beacon currently identified by the sensing device.
[0048] Step 104: Correct the train's current position to the first position.
[0049] In some possible implementations of the embodiments of this application, step 104 in the embodiments of this application may include: when the first position satisfies the second condition, correcting the current position of the train to the first position, wherein the second condition is a condition used to control whether to correct the position of the train.
[0050] In some possible implementations of the embodiments of this application, the second condition in the embodiments of this application may include the difference between the train position determined based on the position of the sensing beacon and the train position determined based on the position obtained from the initial positioning of the train being less than or equal to the speed and distance measurement positioning error corresponding to the train's running time after the initial positioning. Accordingly, when the first position satisfies the second condition, correcting the train's current position to the first position may include: updating the train's current position from the second position to the first position when the difference between the first position and the second position is less than or equal to the speed and distance measurement positioning error corresponding to the first time duration.
[0051] This application does not limit the method used to obtain the speed and distance measurement positioning error corresponding to the running time of the train after initial positioning. Any available method can be applied to this application.
[0052] In this embodiment, a sensing device installed on the train identifies sensory markers set on the track bed. The first feature information of the sensory marker currently identified by the sensing device is matched with feature information of multiple sets of sensory marker combinations in a partial offline semantic map. If only one set of sensory marker combinations in the partial offline semantic map matches the first feature information, the first position of the train is determined based on the position of the first sensory marker identified by the sensing device. The first sensory marker is any one of the first sensory marker combinations in the partial offline semantic map that matches the first feature information. The train's current position is then corrected to the first position. Because multiple sensory markers are set on the track bed, even when the train is traveling in adverse environments such as heavy fog, rain, snow, or dust, the sensing device can promptly detect the sensory markers, quickly and accurately determine the train's position, and then use the determined train position to correct the train's current position, thus ensuring train driving safety.
[0053] In some possible implementations of this application's embodiments, after the initial positioning of the train is completed, the speed and distance measurement positioning error will gradually increase as the train travels further. When the speed and distance measurement positioning error exceeds a certain range, the train's active sensing system determines that the positioning has been lost, and the position needs to be re-initialized and corrected during train operation. Based on this, step 101 in this application's embodiments may include: when the train's speed and distance measurement positioning error is greater than a first threshold, identifying the sensed target through the sensing device.
[0054] In some possible implementations of the embodiments of this application, the first threshold can be determined by the initial ranging error, the measured distance between the sensor beacon combination, the ranging error rate, and the sensor beacon installation error.
[0055] In some possible implementations of the embodiments of this application, the first threshold can be determined by the following formula (1): x=e1+d×r+e2 (1)
[0056] In formula (1), x is the first threshold, e1 is the initial ranging error, d is the measurement distance between the sensor and the beacon combination, r is the ranging error rate, and e2 is the sensor and the beacon installation error.
[0057] In some possible implementations of the embodiments of this application, during train operation, the attitude of the sensing device may change due to train vibration or other reasons. Therefore, it is necessary to correct the attitude of the sensing device. Based on this, the train position correction method provided in the embodiments of this application may further include: when the sensing beacon in the first sensing beacon combination satisfies a first condition, determining a first attitude of the sensing device based on the angular acceleration and / or linear acceleration of the sensing device measured by the sensor, wherein the first condition is a condition used to control whether to determine the attitude of the sensing device; and correcting the current attitude of the sensing device to the first attitude.
[0058] This application does not elaborate on the process of determining the first attitude of the sensing device based on the angular acceleration and / or linear acceleration measured by the sensor. For details, please refer to related technologies for the process of determining attitude through angular acceleration and / or linear acceleration. The attitude of the sensing device in this application embodiment may include: roll angle, pitch angle, and yaw angle. The attitude of the sensing device can be the attitude of the sensing device relative to the geocentric coordinate system.
[0059] In some possible implementations of the embodiments of this application, the first condition may include the distance between the position of the sensor beacon in the sensor beacon combination in the pre-built offline point cloud map and its position in the real-time point cloud currently collected by the sensing device being less than or equal to a first distance; correspondingly, when the sensor beacon in the first sensor beacon combination satisfies the first condition, the first attitude of the sensing device is determined based on the angular acceleration and / or linear acceleration of the sensing device measured by the sensor, which may include: when the distance between the fourth position and the fifth position is less than the first distance, the first attitude is determined based on the angular acceleration and / or linear acceleration; wherein, the fourth position is the position of the third sensor beacon in the offline point cloud map, the fifth position is the position of the second sensor beacon in the real-time point cloud, and the second sensor beacon is any one of the sensor beacons in the first sensor beacon combination.
[0060] In some possible implementations of this application, the point cloud data of the sensed target in the offline point cloud map and the point cloud data of the sensed target extracted from the point cloud collected in real time by the sensing device can be compared in the same three-dimensional coordinate system. The attitude of the sensing device is measured by the distance between the positions of the same sensed target in the offline point cloud map and the positions in the real-time point cloud. When the distance is less than or equal to a set distance threshold (i.e., the first distance), the current attitude of the sensing device is corrected to the first attitude.
[0061] In some possible implementations of the embodiments of this application, the first condition may include the distance deviation between two adjacent sensor beacons in the sensor beacon combination in a pre-constructed offline point cloud map and their distance in the real-time point cloud currently collected by the sensing device being within a first distance deviation range; correspondingly, when the sensor beacons in the first sensor beacon combination satisfy the first condition, determining the first attitude of the sensing device based on the angular acceleration and / or linear acceleration measured by the sensor may include: when the distance deviation between the first sensor beacon distance and the second sensor beacon distance is within the first distance deviation range, determining the first attitude of the sensing device based on the angular acceleration and / or linear acceleration, wherein the first sensor beacon distance is the distance between the third and fourth sensor beacons in the offline point cloud map, the second sensor beacon distance is the distance between the third and fourth sensor beacons in the real-time point cloud, and the third and fourth sensor beacons are two adjacent sensor beacons in the first sensor beacon combination.
[0062] In some possible implementations of this application, the point cloud data of the sensed targets in the offline point cloud map and the point cloud data of the sensed targets extracted from the point cloud collected in real time by the sensing device can be compared in the same three-dimensional coordinate system. The attitude of the sensing device is measured by the deviation of the distance between two adjacent sensed targets in the same sensed target combination in the offline point cloud map and the real-time point cloud, respectively. When the deviation value is within the set distance deviation range (i.e. the first distance deviation range), the current attitude of the sensing device is corrected to the first attitude.
[0063] In some possible implementations of the embodiments of this application, the train position correction method provided in the embodiments of this application further includes: when the sensor in the first sensor combination does not meet the first condition, outputting alarm information, wherein the alarm information is used to instruct the train control system of the train to guide the safety side for protection.
[0064] In some possible implementations of the embodiments of this application, when the distance between the fourth position and the fifth position is greater than a set distance threshold (i.e., the first distance) or the distance deviation between the first sensing gauge distance and the second sensing gauge distance is not within the first distance deviation range, it indicates that the attitude of the sensing device has changed significantly. At this time, an alarm message is output to instruct the train control system to guide the safety side for protection.
[0065] In some possible implementations of this application's embodiments, two sensing devices can be installed at each end of the train. After receiving data from the two sensing devices, the host of the train's active sensing system performs a binary-selection-two-output process on the data to ensure its reliability. This binary-selection-two-output process enables the train's Communication Based Train Control (CBTC) system to reach the highest level of Safety Integrity Level (SIL).
[0066] In some possible implementations of the embodiments of this application, the sensing beacon in the embodiments of this application can be a high-reflectivity rail spike. Because high-reflectivity rail spikes have a high reflectivity, they are easily detected by the sensing equipment on the train and are not affected by adverse environments such as heavy fog, rain, snow, and dust. The position of the train can be determined in a timely and accurate manner through high-reflectivity rail spikes, ensuring the safety of train driving.
[0067] This application also provides a train position correction device. As shown in Figure 6, Figure 6 is a structural schematic diagram of the train position correction device provided in this application embodiment. The train position correction device 600 may include:
[0068] The identification module 601 is used to identify sensor targets set on the track bed of the train by means of sensing devices installed on the train;
[0069] The matching module 602 is used to match the first feature information of the sensing beacon currently identified by the sensing device with the feature information of multiple sets of sensing beacon combinations in a partial offline semantic map; wherein, the partial offline semantic map is a partial semantic map corresponding to the visual range of the sensing device when the train is in the second position in a pre-constructed offline semantic map; the second position is the position calculated based on the third position and the first duration, the third position is the position obtained by initial positioning of the train, and the first duration is the running time of the train after initial positioning;
[0070] The first determining module 603 is used to determine the first position of the train based on the position of the first sensing beacon identified by the sensing device when only one set of sensing beacon combination features information in a partial offline semantic map matches the first feature information. The sensing beacon combination includes multiple sensing beacons, and the first sensing beacon is any one of the sensing beacons in the first sensing beacon combination that matches the first feature information in the partial offline semantic map.
[0071] The first correction module 604 is used to correct the train's current position to the first position.
[0072] In this embodiment, a sensing device installed on the train identifies sensory markers set on the track bed. The first feature information of the sensory marker currently identified by the sensing device is matched with feature information of multiple sets of sensory marker combinations in a partial offline semantic map. If only one set of sensory marker combinations in the partial offline semantic map matches the first feature information, the first position of the train is determined based on the position of the first sensory marker identified by the sensing device. The first sensory marker is any one of the first sensory marker combinations in the partial offline semantic map that matches the first feature information. The train's current position is then corrected to the first position. Because multiple sensory markers are set on the track bed, even when the train is traveling in adverse environments such as heavy fog, rain, snow, or dust, the sensing device can promptly detect the sensory markers, quickly and accurately determine the train's position, and then use the determined train position to correct the train's current position, thus ensuring train driving safety.
[0073] In some possible implementations of the embodiments of this application, the train position correction device 600 provided in the embodiments of this application may further include:
[0074] The second determining module is used to determine the first attitude of the sensing device based on the angular acceleration and / or linear acceleration of the sensing device measured by the sensor when the sensing device in the first sensing target combination satisfies the first condition, wherein the first condition is a condition used to control whether to determine the attitude of the sensing device.
[0075] The second correction module is used to correct the current posture of the sensing device to the first posture.
[0076] In some possible implementations of the embodiments of this application, the first condition may include that the distance between the position of the sensing beacon in the sensing beacon combination in the pre-built offline point cloud map and its position in the real-time point cloud currently collected by the sensing device is less than or equal to a first distance; correspondingly, the second determining module is specifically used for:
[0077] If the distance between the fourth and fifth positions is less than or equal to the first distance, the first attitude is determined based on the angular acceleration and / or linear acceleration; wherein the fourth position is the position of the third sensory beacon in the pre-constructed offline point cloud map, the fifth position is the position of the second sensory beacon in the real-time point cloud currently collected by the sensing device, and the second sensory beacon is any one of the first sensory beacon combinations.
[0078] In some possible implementations of the embodiments of this application, the first condition may include the distance deviation between two adjacent sensory targets in the sensory target combination in a pre-built offline point cloud map and their distance in the real-time point cloud currently collected by the sensing device being within a first distance deviation range; correspondingly, the second determining module is specifically used to: determine a first attitude based on angular acceleration and / or linear acceleration when the distance deviation between the first sensory target distance and the second sensory target distance is within the first distance deviation range; wherein, the first sensory target distance is the distance between the third and fourth sensory targets in the pre-built offline point cloud map, the second sensory target distance is the distance between the third and fourth sensory targets in the real-time point cloud currently collected by the sensing device, and the third and fourth sensory targets are two adjacent sensory targets in the first sensory target combination.
[0079] In some possible implementations of the embodiments of this application, the train position correction device 600 provided in the embodiments of this application may further include:
[0080] The output module is used to output alarm information if the first condition is not met. The alarm information is used to instruct the train control system to guide the train to the safety side for protection.
[0081] In some possible implementations of the embodiments of this application, the first correction module 604 is specifically used for:
[0082] If the first position satisfies the second condition, the train's current position is corrected to the first position, where the second condition is a condition used to control whether the train's position is corrected.
[0083] In some possible implementations of the embodiments of this application, the second condition in the embodiments of this application may include the difference between the train position determined based on the position of the sensing beacon and the train position determined based on the position obtained from the initial positioning of the train being less than or equal to the speed and distance measurement positioning error corresponding to the train's running time after the initial positioning. Accordingly, the first correction module 604 is specifically used for:
[0084] If the difference between the first position and the second position is less than or equal to the speed and distance measurement positioning error corresponding to the first time duration, the train's current position will be updated from the second position to the first position.
[0085] In some possible implementations of the embodiments of this application, the identification module 601 is specifically used for:
[0086] If the speed measurement, distance measurement, and positioning error of the train exceeds the first threshold, the sensing device identifies the target.
[0087] In some possible implementations of the embodiments of this application, the spacing between the sensor targets in the sensor target combination is different.
[0088] Figure 7 is a schematic diagram of the structure of the electronic device provided in an embodiment of this application.
[0089] The electronic device may include a processor 701 and a memory 702 storing computer program instructions.
[0090] Specifically, the processor 701 may include a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of this application.
[0091] Memory 702 may include mass storage for data or instructions. For example, and not limitingly, memory 702 may include a hard disk drive (HDD), floppy disk drive, flash memory, optical disk, magneto-optical disk, magnetic tape, or Universal Serial Bus (USB) drive, or a combination of two or more of these. Where suitable, memory 702 may include removable or non-removable (or fixed) media. Where suitable, memory 702 may be internal or external to an electronic device. In some specific embodiments, memory 702 is a non-volatile solid-state memory.
[0092] In some specific embodiments, the memory may include read-only memory (ROM), random access memory (RAM), disk storage media devices, optical storage media devices, flash memory devices, and electrical, optical, or other physical / tangible memory storage devices. Therefore, typically, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the train position correction method according to this application.
[0093] The processor 701 reads and executes computer program instructions stored in the memory 702 to implement the train position correction method provided in this application embodiment.
[0094] In one example, the electronic device may also include a communication interface 703 and a bus 710. As shown in Figure 7, the processor 701, memory 702, and communication interface 703 are connected via the bus 710 and communicate with each other.
[0095] The communication interface 703 is mainly used to realize communication between various modules, devices, units and / or equipment in the embodiments of this application.
[0096] Bus 710 includes hardware, software, or both, that couples components of an electronic device together. For example, and not limitingly, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an Infinite Bandwidth Interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local Bus (VLB) bus, or other suitable buses, or a combination of two or more of these. Where appropriate, bus 710 may include one or more buses. Although specific buses are described and illustrated in the embodiments of this application, this application considers any suitable bus or interconnection.
[0097] The electronic device can execute the train position correction method provided in the embodiments of this application, thereby achieving the corresponding technical effects of the train position correction method provided in the embodiments of this application.
[0098] In addition, in conjunction with the train position correction method in the above embodiments, this application also provides a computer-readable storage medium for implementation. This computer-readable storage medium stores computer program instructions; when these computer program instructions are executed by a processor, they implement the train position correction method provided in this application. Examples of computer-readable storage media include non-transitory computer-readable media, such as ROM, RAM, magnetic disks, or optical disks.
[0099] This application provides a computer program product. When the instructions in the computer program product are executed by the processor of an electronic device, the electronic device performs the train position correction method provided in this application and achieves the same technical effect. To avoid repetition, it will not be described again here.
[0100] It should be clarified that this application is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of this application is not limited to the specific steps described and shown. Those skilled in the art can make various changes, modifications, and additions, or change the order of steps, after understanding the spirit of this application.
[0101] The functional blocks shown in the above-described block diagram can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, they can be, for example, electronic circuits, application-specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, etc. When implemented in software, the elements of this application are programs or code segments used to perform the required tasks. Programs or code segments can be stored on a machine-readable medium or transmitted over a transmission medium or communication link via data signals carried on a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable read-only memory (EROM), floppy disks, compact disc read-only memory (CD-ROM), optical disks, hard disks, fiber optic media, radio frequency (RF) links, etc. Code segments can be downloaded via computer networks such as the Internet, intranets, etc.
[0102] It should also be noted that the exemplary embodiments mentioned in this application describe methods or systems based on a series of steps or apparatus. However, this application is not limited to the order of the above steps; that is, the steps can be performed in the order mentioned in the embodiments, or in a different order, or several steps can be performed simultaneously.
[0103] It should also be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.
[0104] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a computer software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal (which may be a computer, server, or network device, etc.) to execute the methods described in the various embodiments of this application.
[0105] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of this application without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of this application.
Claims
1. A train position correction method, comprising: identifying a sensing landmark arranged on a track bed of a track on which a train travels by a perception device mounted on the train; matching first feature information of a sensing landmark currently identified by the perception device with feature information of a plurality of sensing landmark combinations in a partial offline semantic map; wherein the partial offline semantic map is a partial semantic map corresponding to a visible range of the perception device when the train is at a second position in a pre-constructed offline semantic map; the second position is a position calculated according to a third position and a first time length, the third position is a position obtained by initially positioning the train, and the first time length is a running time length of the train after the train is initially positioned; in a case where there is only one set of feature information of a sensing landmark combination in the partial offline semantic map that matches the first feature information, determining a first position of the train according to a position of a first sensing landmark identified by the perception device, wherein the sensing landmark combination includes a plurality of sensing landmarks, and the first sensing landmark is any one of the sensing landmarks in the first sensing landmark combination that matches the first feature information in the partial offline semantic map; correcting a current position of the train to the first position. 2.The method of claim 1, further comprising: in a case where a sensing landmark in the first sensing landmark combination satisfies a first condition, determining a first attitude of the perception device according to angular acceleration and / or linear acceleration of the perception device measured by a sensor; wherein the first condition is a condition for controlling whether to determine an attitude of the perception device; correcting a current attitude of the perception device to the first attitude.
3. The method of claim 2, wherein, the first condition includes that a distance between a position of a sensing landmark in a pre-constructed offline point cloud map and a position of the sensing landmark in a real-time point cloud currently collected by the perception device is less than or equal to a first distance; the determining, in the case where the sensing landmark in the first sensing landmark combination satisfies the first condition, the first attitude of the perception device according to the angular acceleration and / or the linear acceleration of the perception device measured by the sensor, comprises: in a case where a distance between the fourth position and the fifth position is less than or equal to the first distance, determining the first attitude according to the angular acceleration and / or the linear acceleration; wherein the fourth position is a position of a third sensing landmark in the offline point cloud map, and the fifth position is a position of a second sensing landmark in the real-time point cloud, the second sensing landmark being any one of the sensing landmarks in the first sensing landmark combination.
4. The method of claim 2, wherein, the first condition includes that a distance between two adjacent sensing landmarks in a pre-constructed offline point cloud map and a distance between the two adjacent sensing landmarks in a real-time point cloud currently collected by the perception device have a spacing deviation within a first spacing deviation range; the determining, in the case where the sensing landmark in the first sensing landmark combination satisfies the condition, the first attitude of the perception device according to the angular acceleration and / or the linear acceleration measured by the sensor, comprises: In a case where a distance deviation between a first known marker distance and a second known marker distance is within a first distance deviation range, the first attitude is determined according to the angular acceleration and / or the linear acceleration, wherein the first known marker distance is a distance between a third known marker and a fourth known marker in the offline point cloud map, the second known marker distance is a distance between the third known marker and the fourth known marker in the real-time point cloud, and the third known marker and the fourth known marker are two adjacent known markers in the first known marker combination.
5. The method of claim 2, further comprising: in a case where a known marker in the first known marker combination does not satisfy a first condition, outputting alarm information, wherein the alarm information is used to instruct a train control system of the train to guide a safety side for protection.
6. The method of claim 1, wherein, The correction of the current position of the train to the first position comprises: in a case where the first position satisfies a second condition, correcting the current position of the train to the first position, wherein the second condition is a condition for controlling whether to correct the position of the train.
7. The method of claim 6, wherein, The second condition comprises that a position difference between a train position determined according to the position of the known marker and a train position determined according to a position obtained by initial positioning of the train is less than or equal to a speed and distance positioning error corresponding to a running duration of the train after the initial positioning of the train; The correction of the current position of the train to the first position in a case where the first position satisfies the second condition comprises: in a case where a position difference between the first position and a second position is less than or equal to a speed and distance positioning error corresponding to a first duration, updating the current position of the train from the second position to the first position.
8. The method of claim 1, wherein, The identification of the known markers arranged on a track bed of a track on which the train travels by the perception device mounted on the train comprises: in a case where a speed and distance positioning error of the train is greater than a first threshold, identifying the known markers by the perception device.
9. The method of claim 1, wherein, The distances between the known markers in the known marker combination are different.
10. A train position correction apparatus, comprising: an identification module configured to identify known markers arranged on a track bed of a track on which a train travels by a perception device mounted on the train; a matching module configured to match first feature information of known markers currently identified by the perception device with feature information of a plurality of known marker combinations in a partial offline semantic map, wherein the partial offline semantic map is a partial semantic map corresponding to a visibility range of the perception device when the train is at a second position in a pre-constructed offline semantic map, the second position is a position calculated according to a third position and a first duration, the third position is a position obtained by initial positioning of the train, and the first duration is a running duration of the train after the initial positioning of the train. a first determining module, configured to determine a first position of the train according to a position of a first landmark recognized by the perception device, in a case where only a set of landmark combinations in the partial offline semantic map has feature information matching the first feature information, wherein the set of landmarks comprises a plurality of landmarks, and the first landmark is any one of the first set of landmark combinations matching the first feature information in the partial offline semantic map; a correcting module, configured to correct a current position of the train to the first position.
11. An electronic device, comprising: a processor and a memory, the memory storing programs or instructions executable on the processor, the programs or instructions being executed by the processor to implement steps of the train position correction method according to any one of claims 1-9.
12. A readable storage medium, the readable storage medium storing programs or instructions executable on a processor, the programs or instructions being executed by the processor to implement steps of the train position correction method according to any one of claims 1-9.
