Method for determining the position of a track-guided vehicle

Abstract

The invention comprises a method for determining the position of a track-guided vehicle (FZ). A vehicle-side sensor (SN) generates a measurement result during the vehicle's (FZ) travel, representing a track (GL) traversed by the vehicle (FZ). Based on this measurement result, the vehicle's (FZ's) current position on the track (GL) is determined by a computer. The measurement result includes a distance profile (AP), which describes a change (a) in the distance (a) of the sensor (SN) from the track superstructure (OB) comprising the track (GL) and its ballast, dependent on the distance traveled by the vehicle (FZ). Starting from a known reference position (RPOS), a relative positioning of the vehicle (FZ) is performed by the computer. A repeating pattern (MT) in the distance profile (AP), corresponding to predefined path segments, is detected and counted by the computer.To determine the position, the respective length (L) of the path segments to the reference position (RPOS) is added for each detected pattern (MT).

Description

Technical field

[0001] The invention comprises a method for determining the position of a track-guided vehicle. Furthermore, the invention comprises a vehicle for track-guided traffic. The invention also comprises a computer program product containing program instructions. Finally, the invention comprises a computer-readable storage medium containing data. Technical background

[0002] For smooth operation, railway operators require that platforms equipped with platform screen doors (PSD) have a large number of stopping points (e.g., more than 7 stopping points) while maintaining high stopping accuracy (e.g., less than 30 cm) and in both directions of travel to achieve high operational flexibility.

[0003] To approach each stopping position, the control system of a vehicle, for example the ATO (Automatic Train Operation) component of a vehicle control system (which operates, for example, according to the principles of the European Train Control System (ETCS) or Communication Based Train Control (CBTC)), requires the reading of several fixed data balises (hereinafter referred to as balises) embedded in the track. These balises must be installed in spatially defined windows in front of the stopping point. When the vehicle's balise antenna passes over the balises, the absolute position of the vehicle is always determined, and the distance-dependent measurement error of a relative position determination (e.g., by odometry or radar) is reset. If the windows of all stopping points to be planned are taken into account, a large number of balises are required per station. This results in considerable costs for project implementation.

[0004] To avoid the use of balises, it is known to locate vehicles on a railway line by scanning the track with a sensor, for example, using radar or optical imaging, and then comparing the sensor reading with a reference result that was previously recorded and stored for the purpose of recognizing the location and subsequently locating the vehicle. Document EP 795455 A1, for example, describes how, for this purpose, the track bed at railway stations can be scanned and the resulting track bed image compared with reference images. However, this method has the disadvantage that, particularly in the vicinity of railway stations, the risk of altering the current track bed image is especially high, for example, because passengers throw debris onto the track bed.This creates the risk that location tracking using this method will fail. While DE 19529986A1 proposes that particularly distinctive features outside the track, such as train stations, can also be used for location tracking, this method is also difficult to implement, especially on platforms, because such objects can be obscured by passengers waiting on the platform.

[0005] Furthermore, current state-of-the-art methods involve a comparatively high level of equipment and are also computationally intensive. It must be considered that each vehicle would need to be equipped with the necessary sensors and computing power if tracking is to be implemented for all vehicles at the station. This expense is comparable to the cost of equipping all stations with balises, meaning that the current state-of-the-art solution can quickly prove uneconomical. Summary of the invention

[0006] The object of the invention is to overcome the problems described in the prior art. In particular, it is an object to provide a method for locating track-guided vehicles, especially in the vicinity of railway stations, with a reasonable expenditure of hardware and computing power and with sufficient stopping accuracy. Specifically, the stopping accuracy should be sufficient for stopping at platforms with platform screen doors. Furthermore, it is an object of the invention to provide a vehicle, a computer program, and a computer-readable storage medium with which the improved method can be implemented.

[0007] According to a first aspect of the invention, a method for determining the position of a track-guided vehicle is described, in which a) a vehicle-side sensor generates a measurement result during the vehicle's journey, which represents a track traversed by the vehicle, b) based on the measurement result, a computer determines the current location of the vehicle on the track.

[0008] This is a tracking method that the vehicle can perform autonomously using its own onboard sensors. Therefore, it does not depend on a data connection to railway infrastructure to carry out the tracking process.

[0009] A device is computer-aided or computer-implemented if it has at least one computer or processor, or a method if at least one computer or processor performs at least one step of the method.

[0010] A computing environment is an IT infrastructure consisting of functional components such as processors, memory units, programs, and the data to be processed by these programs. This data is used to execute at least one application, which has a specific task to perform. Additional functional components can include sensors and actuators, which enable the computing environment to interact with the outside world. The IT infrastructure can also be organized as a network of these functional components.

[0011] Within a computing environment, computing instances form functional units that can be assigned to applications (defined, for example, by a number of program modules) and can execute them. During application execution, these functional units form self-contained systems, either physically (e.g., computer, processor) and / or virtually (e.g., program module).

[0012] Computers are electronic devices consisting of several functional components and possessing data processing capabilities. For example, computers can be clients, servers, handheld computers, communication devices, and other electronic devices for data processing, which may include processors and memory units and may also be interconnected via interfaces to form a network.

[0013] Processors can be, for example, converters, sensors for generating measurement signals, or electronic circuits. A processor can be a central processing unit (CPU), a microprocessor, a microcontroller, or a digital signal processor, possibly in combination with a memory unit for storing program instructions and data. The term "processor" can also refer to a virtualized processor or a soft CPU.

[0014] Storage units can be designed as computer-readable storage in the form of random-access memory (RAM) or data storage (hard drive or data carrier).

[0015] Program modules are individual software functional units that enable a program sequence of process steps according to the invention. These software functional units can be implemented in a single computer program or in several communicating computer programs. The interfaces implemented here can be implemented in software within a single processor or in hardware if multiple processors are used.

[0016] Interfaces can be implemented using hardware, for example via wired or wireless connections, or using software, for example as interaction between individual program modules of one or more computer programs.

[0017] To avoid misunderstandings, it should be noted that individual claim features are numbered with lowercase Latin letters, without regard to the claim numbering. This means that each letter appears only once in the entire claim set, allowing for unambiguous addressing of the relevant claim features without mentioning the claim number. Therefore, the order of the letters is irrelevant.

[0018] According to the invention, it is provided that c) the measurement result contains a distance profile (which can also be referred to as a height profile) that describes a change in the distance of the sensor (which forms a fixed point on the vehicle) from a superstructure comprising the track and its ballast, depending on the distance traveled by the vehicle, d) and starting from a known reference position, a relative location of the vehicle is carried out using a computer, whereby a pattern repeating according to predefined path segments is recognized and counted in the distance profile and, for the purpose of determining the position, the respective length of the path segments is added to the reference position for each recognized pattern.

[0019] In other words, the invention proposes an alternative method for determining the relative vehicle position by means of continuous, for example laser-based, distance measurement between the vehicle—more precisely, the distance measurement sensor attached to the vehicle—and the road surface. A height profile of the distance changes is generated from these distance measurements. This height profile is two-dimensional, being created from one-dimensional measurements, namely the distance values, which extend along the roadway in the direction of travel of the vehicle.

[0020] The track is the roadway for rail vehicles. It consists of the two rails, the sleepers that support and connect them (also called the base), and the fastening devices that secure the rails to the base. Together with the deeper support, the ballast, the track forms the superstructure of a railway line.

[0021] In particular, starting from a known reference position, a relative location of the vehicle can be carried out using a computer in such a way that a repeating pattern in the distance profile according to predefined path segments of constant length (at least over a certain section of the route) is recognized and counted by the computer, and for position determination (at least in the aforementioned section of the route) the number of recognized patterns, multiplied by the length of the path segments, is added to the reference position.

[0022] Typically, track segments have a constant length. This is defined, for example, by the track sleeper spacing (more on this below). If the track segments have a constant length, only this one length needs to be known for the station in question in order to be specified in the procedure. However, it is also possible that different lengths must be considered for the track segments. This is the case, for example, if a platform is first flanked by a straight section and then by a curve in the track, where the track segments have a different length in the curve than in the straight section. In this example, two different track segment lengths must be considered, along with knowing the position where the track segment lengths change, so that this position can also be specified in the procedure.

[0023] One advantage of the invention is that the distance sensor is a cost-effective sensor because it only needs to measure a one-dimensional distance between the vehicle and the superstructure. This also advantageously reduces the computational power required for the method of determining the height profile, as it can be calculated by sequentially recording the individual distance values, taking into account the sampling frequency and the vehicle's speed.

[0024] It should be noted that the distance measurement does not need to be implemented in a safety-relevant manner and only needs to be made available to the ATO (Automatic Train Operator). Safety-relevant position detection for the ATP (Automatic Train Protection) is carried out unchanged using the procedure already implemented in the safety-relevant train control system; however, this procedure has lower requirements for location accuracy than when stopping at platform screen doors. Door release continues to be generated based on the ATP position. Localization via the track's elevation profile serves to align the vehicle doors with the PSDs (Post-Service Devices) as precisely as possible. When safety is mentioned in connection with this invention description, it refers to functional safety (also called safety), which describes the reliability of the railway system in operation. It does not refer to security against unlawful attacks (also called security).

[0025] Due to varying numbers of passengers, the vehicle can deflect by an offset (in vehicles without automatic load compensation). However, this offset only results in the distance values ​​to the vehicle changing by a constant amount. The height of the rail fastening relative to the substructure is unaffected by this and can still be recognized as a distinct pattern.

[0026] The advantages of the invention can be summarized as follows: The number of balises in a station can be drastically reduced. For example, with multiple stopping windows, a reduction from > 25 balises to 1-2 balises in the station area is feasible to ensure reliable positioning for the ATP (Automated Tramway Tracking). The additional onboard hardware required is limited to a sensor with a downstream electronic evaluation unit. The sensor's unambiguous pattern recognition prevents any further significant inaccuracy from being added to the measurement uncertainty of the last balise passed, which serves as the baseline. The distance between the individual trackside elements is relatively small (approx. 60 cm), so the parallel measurement using odometry and radar along this stretch is unlikely to introduce any relative measurement error. The sensor-based measurement is independent of wheel slip during braking / acceleration. It is also robust against height changes caused by the vehicle's suspension travel when fully loaded with passengers..

[0027] According to a further aspect of the invention, a vehicle for track-guided traffic is described, comprising a computing environment configured to support the control of the vehicle. According to this aspect, the invention provides that e) a distance sensor is mounted on the vehicle, in particular on its underside, which is configured to measure a distance between the sensor and the track superstructure below the vehicle, and f) the computing environment is set up to carry out at least steps b) and d) of the procedure described above.

[0028] The advantages associated with this aspect of the invention have already been explained above, and reference is made to these advantages.

[0029] According to a further aspect of the invention, a computer program product is described, containing program instructions that can be executed by a computing environment. According to this aspect, the invention provides that at least steps b) and d) of the above-described method are carried out.

[0030] According to the invention, a computer program product containing program modules with program instructions is described, wherein the program modules can run on the same or multiple processors. The computer program product, which can comprise one or more computer programs, can be used to implement the method according to the invention and / or its exemplary embodiments, and the advantages described above are achieved through its implementation.

[0031] According to a further aspect of the invention, a computer-readable storage medium containing data, which is stored as data records on the storage medium, is described. According to this aspect, the invention provides that the data records make the computer program product described above, according to the last preceding claim, executable.

[0032] Furthermore, a provisioning device for storing and / or providing the computer program in the form of a computer-readable storage medium is described. The provisioning device is, for example, a storage unit that stores the computer program and makes it available for retrieval. Alternatively or additionally, the provisioning device is a network service, a computer system, a server system, in particular a distributed computer system, such as a cloud-based system or virtual computer system, which stores the computer program on a computer-readable storage medium and preferably makes it available in the form of a data stream.

[0033] The provision of the computer program takes the form of program modules describing program data sets as a file, in particular as a download file, or as a data stream, in particular as a download data stream. The computer program is transferred, for example, using the provisioning device, into a computing environment so that the method according to the invention can be executed in one or more computing instances of this computing environment. Embodiments of the invention

[0034] Further developments of the invention, describing variants, are explained below without limiting the basic idea of ​​the invention.

[0035] According to one variant, the aspects of the invention explained above are determined by the fact that the spacing pattern is recognized as a repeating pattern when passing over rail sleepers and / or fastening devices of the rails on a surface formed by the superstructure.

[0036] For the purposes of this invention, the term "distance profile" refers to the path taken in the distance profile as it occurs when a train passes over a rail sleeper or the rail fastening element. The distance profile is thus a section of the distance profile (also referred to as the height profile) whose characteristics are repetitive and which can be identified using the method according to the invention.

[0037] One advantage of this variant is that the aforementioned spacing pattern repeats regularly; that is, the rail sleepers or the fastening devices attached to them or another substrate support the rail at regular intervals and are therefore well suited for measuring distance according to the invention. These structures are also large compared to the dimensions of the track, which facilitates their detection even at higher speeds. It must be taken into account that trains can enter the station at speeds of up to 80 km / h, so reliable pattern recognition must be ensured, depending on the permissible entry speed.

[0038] Upon entering a station, the distance profile is measured directly next to the rail, starting from the last recorded absolute position, and continuously compared with a track profile stored within the vehicle. Each rail fastening and, if present, sleeper traversed represents a significant change in distance, which is recognized as a pattern. The vehicle's track profile contains a precise position for each rail fastening / sleeper (at least if they are not constant), which is transmitted to the ATO (automatic train operation) upon detection. However, it can also be assumed, for example, that rail fastenings / sleepers are located at approximately 60 cm intervals (corresponding to the length of the track segments).The number of detected patterns is then multiplied by this length, enabling a particularly fast calculation method with very low consumption of computing and storage resources. To determine the localization, the vehicle can also individually consider the position information provided by odometry, the information from the elevation profile (derived from the locations where rail fixings were detected and compared to where they were expected), and the distance between the current and the last rail fixing (if these are not at a constant distance).

[0039] According to one variant, the aspects of the invention explained above are determined by the fact that the sensor repeatedly or continuously measures the distance of measuring points on the superstructure below the vehicle, wherein the measurement result contains a two-dimensional distance profile oriented in the direction of travel of the vehicle and having a plurality of measuring points.

[0040] One advantage of this approach is that it generates a continuous distance profile representing the distance traveled. This profile is obtained by interpolating the measurement points and is therefore virtually continuous. The measurement points must be sufficiently close together so that the resolution of the distance profile allows the patterns to be mapped in such a way that they can be recognized by a computer. The sensor's sampling rate must be selected to ensure sufficient measurement point density and will need to be in the range of > 10 kHz to provide adequate resolution for the trackside elements (rail fixings, sleepers) at typical station entry speeds of up to 80 km / h.

[0041] It is advantageous to optimize the stored route profile using machine learning algorithms. Repeatedly driving over the same route segments is used to generate training data. The result of this training is a more accurate and less error-prone position detection function.

[0042] According to one variant, the aspects of the invention explained above are determined by the fact that the sensor measures the distance at a constant lateral offset to one of the rails, such that the determined distance profile contains measuring points relating to the fastening devices of the rail on the substrate as a pattern.

[0043] Lateral offset, as defined in the invention, is a distance from the rail measured horizontally and perpendicular to the vehicle's direction of travel. This means that the lateral offset remains essentially constant as the vehicle moves along the track. The lateral offset is also selected such that the measurement sweeps over the rail's fastening devices on the substrate. Therefore, these are included as a pattern in the resulting distance profile. This pattern is advantageously particularly distinctive. It typically includes the brackets of a rail fastening clamp and the associated fastening screw, which create several characteristic jumps in the height profile in quick succession. Each time this characteristic is detected, a path segment extending from rail sleeper to rail sleeper is thus identified.

[0044] The hardware required is one or more distance sensors mounted on the bogie, with their measuring direction directed vertically downwards. Mounting near the wheel is advantageous to ensure accurate positioning above the trackside rail fixings, especially in curves.

[0045] According to one variant, the aspects of the invention explained above are determined by the fact that the method is carried out when the vehicle enters a station until the vehicle comes to a standstill, in particular when the vehicle is simultaneously aligned with platform doors mounted on a platform of the station.

[0046] One advantage of this variant is that the positioning accuracy for locating the vehicle within a station must be particularly precise compared to open track. This is the only way to ensure that passenger trains stop at the point expected by passengers. This is especially important when platform screen doors are in use, as the alignment of the train's doors with the platform screen doors must be precise. The exact stopping position of the vehicle at the platform is therefore supported by the ATO (Automatic Train Operator), while the ATP (Automatic Train Protection) remains responsible for door release.

[0047] According to one variant, the aspects of the invention explained above are determined by the fact that the reference position is determined by the vehicle and / or transferred to the vehicle before the vehicle enters the station.

[0048] One advantage of this approach is that the closer the reference position is determined as a precise location event to the station, the more accurate the tracking on the platform becomes. This tracking can be performed externally, for example, by a satellite (GNSS system). Another possibility is passing over a beacon that sends a telegram for tracking purposes. In these cases, the reference position, or at least an identifier for determining the reference position, is transmitted to the vehicle. If the vehicle uses its own sensors to determine an absolute position, for example, by detecting a waypoint, the reference position is determined by the vehicle itself.

[0049] According to one variant, the aspects of the invention explained above are determined by the fact that the length of the path segments, together with lengths of path segments for other track sections of the station being traversed and / or for other stations, is stored in a storage unit of the vehicle and is selected before entry, taking into account a route plan, or is transferred to the vehicle via an external interface before entry into the station.

[0050] One advantage of this approach is that reliable positioning is possible even in stations with track segments that do not conform to a standard length. This applies, for example, to uneven sleeper spacing, where the track segments are defined by sleepers or elements on the sleepers such as screws or fastening clips. In extreme cases, a separate length can even be stored for each track segment. Another application arises when track sections with track segments of varying lengths are used along the platform, with the track segments within each section being of the same length. This can occur, for example, when a platform has both a straight track section and a curved track section. In this case, each track section only needs to have a uniform length for the relevant track segments stored.

[0051] According to one variant, the aspects of the invention explained above are determined by the fact that the reference position and / or the length of the path segments is transmitted to the vehicle by a balise mounted in the track in an entry area of ​​the station.

[0052] One advantage of this variant is that the balise (especially a Eurobalise) provides a standardized track element, allowing communication with the vehicle to utilize existing hardware. Furthermore, positioning with a balise is possible with high precision. If the balise also transmits the length of the track segments, vehicles without pre-stored track segment lengths can also be advantageously operated using the inventive method. These lengths are then transmitted only upon entry into the station. This makes the method advantageously available without local restrictions for all vehicles equipped with the inventive hardware (vehicle-mounted sensor) or software (computer program).

[0053] According to one variant, the aspects of the invention explained above are determined by the fact that machine learning is applied to set up and / or optimize the method during the operation of the vehicle, in which the patterns are created and / or optimized.

[0054] One advantage of this variant is that the process can be optimized when vehicles repeatedly visit certain stations. Specific characteristics regarding the lengths of the route segments at the stations in question can be taken into account when the vehicle repeatedly visits these stations.

[0055] In the context of this invention, artificial intelligence (hereinafter also abbreviated as AI) refers specifically to the capability of computer-based machine learning (hereinafter also abbreviated as ML). This involves the statistical learning of algorithm parameterization, preferably for highly complex applications. Using ML, the system recognizes and learns patterns and regularities in the acquired process data based on previously inputted training data. With the aid of suitable algorithms, ML can independently find solutions to emerging problems. ML is divided into three areas: supervised learning, unsupervised learning, and reinforcement learning, with more specific applications such as regression and classification, structure recognition and prediction, data generation (sampling), and autonomous action.

[0056] In supervised learning, the system is trained by observing the relationship between input and corresponding output of known data, thereby learning approximate functional relationships. The availability of suitable and sufficient data is crucial, because if the system is trained with unsuitable (e.g., non-representative) data, it will learn incorrect functional relationships. In unsupervised learning, the system is also trained with example data, but only with input data and without a connection to a known output. It learns how to form and extend data groups, what is typical for the respective use case, and where deviations or anomalies occur. This allows use cases to be described and errors to be detected.In reinforcement learning, the system learns through trial and error by proposing solutions to given problems and receiving positive or negative feedback on these proposals. Depending on the reward mechanism, the AI ​​system learns to perform corresponding functions.

[0057] According to one variant, the aspects of the invention explained above are determined by the fact that an optical distance sensor, in particular a laser-based distance sensor, is mounted as the sensor.

[0058] One advantage of this approach is that optical sensors are inexpensive to purchase and reliable in operation. In particular, with a laser-based distance sensor, the measured values ​​can be generated at the required frequency, allowing the generation of measurement points at the necessary density, as previously explained.

[0059] According to one variant, the aspects of the invention explained above are determined by the fact that the vehicle's computing environment includes a computing instance which is configured to perform the functionality of an Automatic Train Operation (hereinafter also referred to as ATO), and that this computing instance is also configured to perform at least steps b) and d) of the method described above.

[0060] One advantage of this variant is that the ATO is equipped to locate the vehicle with a level of precision sufficient for stopping at a platform. The device according to the invention, comprising the vehicle-side sensor, can advantageously support the ATO in this task by carrying out the method according to the invention. Exemplary embodiments of the drawing

[0061] Further details of the invention are described below with reference to the drawing. Identical or corresponding drawing elements are provided with the same reference numerals in each figure and are only explained more than once to the extent that differences arise between the individual figures.

[0062] The exemplary embodiments described below are preferred embodiments of the invention. In these exemplary embodiments, the described components each represent individual variants of the invention, which can be considered independently of one another. Each of these variants further develops the invention independently and can therefore be regarded as part of the invention, either individually or in a combination other than that shown. Furthermore, the described components can also be combined with the variants of the invention described above.

[0063] Figure 1Figure 1 schematically shows an embodiment of the device according to the invention with its interactions between the functional components used.

[0064] Figure 2 Figure 1 shows an exemplary longitudinal section of a track segment of a superstructure and the resulting distance profile as a measurement result of an embodiment of the method according to the invention.

[0065] Figure 3 shows an exemplary embodiment of a computing environment for the device according to Figure 1 as a block diagram of the individual functional components and the interfaces formed between them, wherein individual computing instances execute program modules that can each run in one or more of the exemplary computers shown, and wherein the interfaces shown can accordingly be implemented in software in one computer or in hardware between different computers.

[0066] Figure 4An embodiment of the method according to the invention is shown as a flowchart, wherein the process steps shown can be implemented individually or in groups by program modules, and wherein the computing instances and interfaces are defined according to Figure 3 are indicated by example. Detailed description of the exemplary implementations

[0067] In Figure 1 The diagram shows a vehicle FZ, which is either moving or stationary on a track GL with wheels RD. The track GL consists of rails SC, which are fastened to sleepers SW by means of fastening screws BS. The track GL is embedded in a ballast ST, which forms the track bed, with the track GL and the ballast ST together forming the superstructure OB.

[0068] When the vehicle FZ travels over track GL, a distance a to the surface of the track superstructure OB is measured by a sensor SN. This distance a is measured perpendicularly in the z-direction, indicated by a coordinate system whose origin lies at sensor SN. The train travels in an x-direction, which in this example is defined according to Figure 1 is identical to the direction of travel. Furthermore, the SN sensor is located in a Figure 1 indicated y-direction laterally offset from the one in Figure 1 The depicted rail SC is attached to the vehicle FZ.

[0069] The sleepers SW are each spaced a distance apart of a first length L1, which defines a first path segment WS1, a second length L2, which defines a second path segment WS2, a third length L3, which defines a third path segment WS3, and a fourth length L4, which defines a fourth path segment WS4. To understand the process of the positioning according to the invention, knowledge of the relationships between the path segments and the lengths L (as the totality of lengths is to be called, regardless of whether there is only one length or several lengths at the platform) is required. As soon as the vehicle FZ passes over the balise BL, absolute positioning, the determination of the reference position RPOS, is carried out with high accuracy using the balise BL.The sensor SN then detects each crossing of the rail sleepers SC, thus successively registering the completion of the first path segment WS1, the second path segment WS2, the third path segment WS3, and the fourth path segment WS4. To perform relative positioning, the first length L1 is added to the absolute position determined by the balise BL after crossing the first path segment WS1, the second length L2 after crossing the second path segment WS2, the third length L3 after crossing the third path segment WS3, the fourth length L4 after crossing the fourth path segment WS4, and so on. POS = RPOS + L1 + L2 + L3 + L4

[0070] This example of the process flow according to the invention is used when an individual length L is available for each path segment, which is stored, for example, in the vehicle FZ. When calculating the current position of the vehicle FZ, the different lengths L are then individually retrieved. As already explained, the lengths L can be determined by machine learning or, alternatively, by an exact measurement of the track superstructure OB.

[0071] Instead of individual lengths L of the path segments, a uniform (e.g., average) length L of the path segments can also be used to calculate the relative position. In the example shown, this is the average threshold spacing SW. In this case, the procedure is simplified, since each crossing of the thresholds SW after detection by sensor SN only needs to be counted and multiplied by the average length L of the path segments. The result is then added to the absolute reference position RPOS determined by the crossing of the balise BL, as already explained. POS = RPOS + N * L

[0072] In Figure 2 A cross-section of the track superstructure OB is shown in more detail. The sleepers SW, to which the rail SC is fastened with the fastening screws BS, are visible. Fastening clips BK are also used, which are shown in the diagram for clarity. Figure 1 are not shown.

[0073] A distance profile AP, shown to the same scale as the section of the superstructure OB, can be seen, which is defined by the sensor SN, shown in Figure 1 , was determined. This assumes an average length L of the path segment, as described in more detail above. Recurring patterns MT can be identified in the spacing profile AP, corresponding to the respective spacing profile AP (i.e., the height profile) of the sleepers SW, including the fastening clips BK and the fastening screws BS. These patterns MT can be easily identified using computer-aided design due to their distinct characteristics. It is also evident that the spacing profile AP of the fill ST is uneven, resulting in no recognizable spacing profile AP patterns.

[0074] A computing environment RU in which the inventive method takes place can be considered jointly by Figure 1 and Figure 3The computing instances used in the Automatic Train Protection (ATP), Automatic Train Operation (ATO), and sensor module (SNM), along with their functional components, interact via interfaces. A first interface, S1, connects a vehicle-side sensor (SN) and a fourth processor (PR4). A second interface, S2, connects a fourth processor (PR4) and a first processor (PR1). A third interface, S3, connects a third processor (PR3) and the first processor (PR1). A fourth interface, S4, connects the first processor (PR1) and a second processor (PR2). A fifth interface, S5, allows the third processor (PR3) and a balise (BL) to be connected via a radio interface when the vehicle (FZ) passes over the balise (BL).For this purpose, the vehicle FZ and the balise BL are equipped with AT antennas that enable this transmission.

[0075] According to Figure 3 The computers forming the respective computing instances are described in more detail below. In a first computer CP1, a first processor PR1 is connected to a first memory unit SE1 via an eleventh interface S11. In a second computer CP2, a second processor PR2 is connected to a second memory unit SE2 via a twelfth interface S12. When this description of the invention refers only to computers, processors, memory units, or interfaces, the information generally refers to all of the computers, processors, memory units, and other functional components named above in detail, which, connected via the interfaces, contribute to forming the computing environment RU.

[0076] The following describes the method according to the invention by way of example, as shown in the flowchart according to Figure 4 will be presented and explained step by step. Figure 4 Furthermore, the boxes provide an example of how functional components and computing instances are contained within them. Figure 1 and 3 The individual steps can be carried out. Computer-aided steps take place in the processors, which are not shown in detail. The reading and saving of data to the storage units is shown as an example. Insofar as the interfaces are as described above... Figure 1 and 2 These can also be used in Figure 3 marked.

[0077] In the first step 1, the process is started (abbreviated: START).

[0078] In a second step, the vehicle FZ (LOC) is located. Here, the reference position RPOS is determined and stored in the first storage unit SE1 via the eleventh interface S11. As already explained, the reference position RPOS can be determined by passing over a balise BL.

[0079] In a third step, the distance a from sensor SN to the track superstructure OB (abbreviated as MSR) is measured. As already explained, the sum of the measured distances a yields a distance profile AP, which serves as the basis for the subsequent process. The distance profile AP can, for example, be generated in the fourth processor PR4 and transmitted to the first processor PR1 via the second interface S2 in a manner not shown in detail.

[0080] In a fourth step, the first processor PR1 checks whether a pattern MT (abbreviated MT?) has been detected in the existing distance profile AP. For this purpose, pattern recognition is performed in the first processor PR1. This involves using known computer-aided pattern recognition methods, which can preferably be trained using artificial intelligence through machine learning. The training can be performed prior to the execution of the procedure according to... Figure 4This process may be carried out and / or improved during its execution to optimize pattern recognition (MT). Furthermore, machine learning, using a track atlas, can be employed to learn the individual lengths (L) of track segments, for example, defined by the sleepers (SW) of the track (GL), at individual platforms. If a pattern (MT) is recognized, the process proceeds to step seven (7). If no pattern (MT) is recognized, the process proceeds to step five (5).

[0081] In a fifth step (5), the system checks whether the process should be stopped (abbreviated as STP?). This is the case, for example, if the vehicle FZ has stopped. If necessary, the process would then restart after the first step (1) when the vehicle FZ resumes driving. If the process should not be stopped, it recursively continues to the third step (3). If the process should be stopped, it proceeds to a sixth step (6, abbreviated as STOP). This step terminates the process.

[0082] In step seven, a query is performed to determine whether individual lengths Li exist for single or groups of path segments (abbreviated: Li?). If so, the process continues with step ten, step ten. If not, it proceeds to step eight, step eight.

[0083] In an eighth step (8), a counter variable N is incremented by one (N = N + 1). This counter variable is used when no individual lengths Li of the individual path segments are available, but only a standardized length L is required, which, for example, represents the average length or the exact length L of the path segments within a tolerance range. For instance, this length L could correspond to the uniform sleeper spacing SW on the railway track.

[0084] In a ninth step, the current position is calculated in a single calculation step according to equation (2) (abbreviated: CLC). For the purpose of this calculation, the standardized length L and the current position, i.e., the reference position RPOS (if this step is performed for the first time) or the last calculated position (if this step is performed repeatedly), are read from the first storage unit SE1 via the eleventh interface S11.

[0085] In a tenth step 10, alternatively (i.e., in the other case of the query according to the seventh step 7), the current position is calculated in a single calculation step according to equation (1) (abbreviated: CLC). For the purpose of the calculation, the current length Ln and the current position, i.e., the reference position RPOS (if this step is performed for the first time) or the last calculated position (if this step is performed repeatedly), are read from the first storage unit SE1 via the eleventh interface S11.

[0086] In the eleventh step (11), the calculated position (OT-POS) is output. The data record containing the position can be transferred, for example, via the fourth interface S4 to the second processor PR2 to ensure the functionality of the ATP in the vehicle FZ. The process then continues with the fifth step (5), which has already been described. Reference symbol list

[0087] aDistance APDistance profile ATAAntennas ATOAutomatic Train Operation ATPAutomatic Train Protection BKMounting brackets BLBalise BSMounting screws CP1First computer CP2Second computer FZVehicle GLTrack LLength L1First length L2Second length L3Third length L4Fourth length MTPattern OBSuperstructure POSPosition PR1First processor PR2Second processor PR3Third processor PR4Fourth processor RDRears RPOSReference position RURacuity environment S1First interface S11Eleventh interface S12Twelfth interface S2Second interface S3Third interface S4Fourth interface S5Fifth interface SCRails SE1First storage unit SE2Second storage unit SNSensor SNMSensor module STLoad SWSleepers WS1First travel segment WS2Second travel segment WS3Third travel segment WS4Fourth travel segment

Claims

1. Method for determining the position of a track-guided vehicle (FZ), wherein a) a vehicle-side (FZ) sensor (SN) generates a measurement result during the vehicle's (FZ) journey, which represents a track (GL) traversed by the vehicle (FZ), b) based on the measurement result, a computer determines the current location of the vehicle (FZ) on the track (GL), characterized by the fact thatc) the measurement result contains a distance profile (AP) which describes a change in the distance (a) of the sensor (SN) from a track superstructure (OB) comprising the track (GL) and its ballast, depending on the distance traveled by the vehicle (FZ), d) and starting from a known reference position (RPOS), a relative localization of the vehicle (FZ) is carried out using a computer, wherein a pattern (MT) repeating according to predefined path segments is recognized and counted in the distance profile (AP) and, for position determination, the respective length (L) of the path segments is added to the reference position (RPOS) for each recognized pattern (MT).

2. Method according to claim 1, characterized by the fact that The spacing pattern is recognized as a repeating pattern (MT) when passing over rail sleepers (SC) and / or rail fastening devices (SC) on a substrate formed by the superstructure (OB).

3. Method according to claim 1 or 2, characterized by the fact that the sensor (SN) repeatedly or continuously measures the distance (a) of measuring points on the superstructure (OB) below the vehicle (FZ), the measurement result comprising a two-dimensional distance profile (AP) oriented in the direction of travel of the vehicle (FZ) and having a plurality of measuring points.

4. Method according to claim 3, characterized by the fact that the sensor (SN) measures the distance (a) at a constant lateral offset to one of the rails (SC), such that the determined distance profile (AP) contains measurement points relating to the fastening devices of the rail (SC) on the substrate as a pattern (MT).

5. Method according to any one of the preceding claims, characterized by the fact that This is carried out when the vehicle (FZ) enters a station until the vehicle (FZ) comes to a standstill, in particular when the vehicle (FZ) is simultaneously aligned with platform doors mounted on a platform of the station.

6. Method according to claim 5, characterized by the fact that The reference position (RPOS) is determined by the vehicle (FZ) and / or transmitted to the vehicle (FZ) before the vehicle (FZ) enters the station.

7. Method according to one of claims 5 or 6, characterized by the fact that The length (L) of the path segments, together with lengths (L) of path segments for other track sections (GL) of the station being traversed and / or for other stations, is stored in a storage unit of the vehicle (FZ) and is selected before entry taking into account a route plan or is transferred to the vehicle (FZ) via an external (FZ) interface before entry into the station.

8. Method according to claim 5, characterized by the fact that The reference position (RPOS) and / or the length (L) of the path segments is transmitted to the vehicle (FZ) by a balise (BL) mounted in the track (GL) in an entry area of ​​the station.

9. Method according to any one of the preceding claims, characterized by the fact that Machine learning is used to set up and / or optimize the procedure during the operation of the vehicle (FZ), in which the patterns (MT) are created and / or optimized.

10. Vehicle for track-guided traffic, comprising a computing environment (RU) that is set up to support the control of the vehicle (FZ), characterized by the fact that e) a distance sensor is mounted on the vehicle (FZ), in particular on its underside, which is configured to measure a distance (a) between the sensor (SN) and the superstructure (OB) having the track (GL) below the vehicle (FZ), and f) the computing environment (RU) is configured to carry out at least steps b) and d) of the method according to any one of claims 1 - 9.

11. Vehicle according to claim 10, characterized by the fact that An optical distance sensor, in particular a laser-based distance sensor, is mounted as a sensor (SN).

12. Vehicle according to claim 10 or 11, characterized by the fact that the computing environment (RU) of the vehicle (FZ) includes a computing instance which is configured to perform the functionality of an Automatic Train Operation (ATO), and which is also configured to perform at least steps b) and d) of the method according to any one of claims 1 - 9.

13. Computer program product containing program instructions that can be executed by a computing environment (RU) such that at least steps b) and d) of the method according to any one of claims 1 - 9 are carried out.

14. Computer-readable storage medium containing data which are stored as data records on the storage medium, such that the data records make the computer program product according to the last preceding claim executable.

Images