Passenger transport line positioning method and system based on multi-source position fusion

Abstract

The invention provides a passenger line positioning method and system based on multi-source position fusion, and the method comprises the steps: obtaining the driving positioning data of a passenger car in real time, constructing at least one driving curve based on the driving positioning data, the driving positioning data comprising data of a plurality of positioning modes, each driving curve corresponds to one positioning mode; extracting a railway line where the passenger car is located and position points on the driving curve, and constructing a position point set; performing line fitting based on the position point set to obtain a fitted line; in the driving process of the passenger car, whether the positioning signal is lost or not is judged in real time, if the positioning signal is lost, a predicted driving point is calculated based on the current fitting line, and after the positioning signal is received again, the position of the predicted driving point is corrected. According to the scheme, combined positioning of multiple positioning modes is realized, so that the positioning precision of the combined positioning system is improved, and a more reliable and more accurate solution is provided for train positioning in a complex environment.

Description

Technical Field

[0001] The present invention relates to the field of railway positioning technology, and in particular to a passenger line positioning method and system based on multi-source position fusion. Background Art

[0002] The positioning of passenger train lines plays a vital role in ensuring driving safety and is an important cornerstone for protecting the lives and property of passengers and maintaining railway transportation order.

[0003] First of all, accurate train positioning is the prerequisite for realizing the automation of train operation and dispatching. By adopting global navigation satellite systems (GNSS) such as the global satellite positioning system (GPS) and the Beidou system, combined with various technical means such as ground transponders and track circuits, the train's location information can be obtained in real time and accurately, providing reliable data support for the train operation control system. This not only helps to optimize the train's running path and speed, avoid conflicts and rear-end collisions between trains, but also improves the efficiency and comfort of train operation. Secondly, the reliability of train positioning technology is directly related to driving safety. During the train's operation, any slight positioning error may cause serious safety accidents. Therefore, the use of multiple technical means for combined positioning, such as the combination of inertial navigation system (INS) and GNSS, can compensate for each other's errors and improve the accuracy and stability of positioning. At the same time, auxiliary positioning equipment such as ground transponders and track circuits can also provide accurate train location information at critical moments, providing strong protection for driving safety.

[0004] In addition, the development of train positioning technology can also promote the intelligentization and informatization of railway transportation. By monitoring the train position in real time, it is possible to fully control the train's operating status and promptly discover and deal with potential safety hazards. At the same time, train positioning data can also provide important operational decision-making basis for railway transportation companies, help optimize transportation organization and resource allocation, and improve the overall efficiency and service level of railway transportation. However, the positioning of existing technologies often relies solely on the positioning accuracy of positioning equipment, and it is difficult to further improve the accuracy. Summary of the invention

[0005] In view of this, an embodiment of the present invention provides a passenger route positioning method and system based on multi-source position fusion to eliminate or improve one or more defects existing in the prior art.

[0006] One aspect of the present invention provides a passenger route positioning method based on multi-source position fusion, the method comprising the steps of:

[0007] Acquire the driving positioning data of the bus in real time, and construct at least one driving curve based on the driving positioning data, wherein the driving positioning data includes data of multiple positioning methods, and each driving curve corresponds to one positioning method;

[0008] Extracting the railway line where the passenger car is located and the position points on the driving curve, and constructing them into a position point set;

[0009] Performing route fitting based on the set of position points to obtain a fitted route;

[0010] During the driving process of the bus, it is determined in real time whether the positioning signal is lost. If the positioning signal is lost, the expected driving point is calculated based on the current fitting route, and the position of the expected driving point is corrected after the positioning signal is received again.

[0011] By adopting the above scheme, this scheme can first fit the route through multiple positioning data, and when the positioning signal is lost, it can predict the position based on the known fitting route, and when the positioning signal is received again, it can calculate the final correction parameters through the correction algorithm to achieve combined positioning of multiple positioning methods, thereby improving the positioning accuracy of the combined positioning system and providing a more reliable and accurate solution for train positioning in complex railway line environments.

[0012] In some embodiments of the present invention, in the step of acquiring the driving positioning data of the bus in real time, the driving positioning data of the bus includes positioning data of the on-board Beidou positioning device and the crew's handheld terminal.

[0013] In some embodiments of the present invention, the driving positioning data includes positioning points corresponding to multiple time points. In the step of constructing at least one driving curve based on the driving positioning data, the corresponding positioning points are sequentially connected based on the time sequence of the time points to obtain a driving curve corresponding to each driving positioning data.

[0014] In some embodiments of the present invention, the step of constructing at least one driving curve based on the driving positioning data also includes calculating the distance value between each positioning point and the railway line where the passenger car is located, comparing the distance value with a preset distance threshold, and deleting the positioning point corresponding to the distance value if the distance value is greater than the preset distance threshold.

[0015] In some embodiments of the present invention, in the step of performing line fitting based on the position point set to obtain a fitted line, line fitting is performed based on the position point set and using a cubic B-spline curve fitting method to obtain a fitted line.

[0016] In some embodiments of the present invention, in the step of calculating the expected driving points based on the current fitting route if the positioning signal is lost, if the positioning signal is lost, the driving points in the current fitting route are extracted and input into a pre-trained first prediction model, and the predicted driving points are output through the first prediction model. During the time period when the positioning signal is lost, the predicted driving points and the driving points in the original fitting route are continuously input into the pre-trained first prediction model, and new predicted driving points are output.

[0017] By adopting the above scheme, the present scheme can predict the travel point based on the original fitting route. When the train loses the positioning signal, the predicted travel point can be provided as a reference for the train crew to ensure the travel safety of the train.

[0018] In some embodiments of the present invention, in the step of calculating the expected driving points based on the current fitted route, if the positioning signal is not lost, the driving points in the current fitted route are extracted and input into a pre-trained first prediction model, the predicted driving points are output by the first prediction model, and the actually fitted driving points are used as label positions to train the first prediction model.

[0019] In some embodiments of the present invention, in the step of correcting the position of the predicted driving point after the positioning signal is received again, the driving point where the positioning signal is received again and the driving point before the positioning signal is lost are input into a pre-trained second prediction model, and the second prediction model outputs the predicted driving point within the time period when the positioning signal is lost.

[0020] In some embodiments of the present invention, after the positioning signal is received again, the step of correcting the position of the expected driving point also includes constructing the driving points within the time period of lost positioning signal output by the first prediction model and the driving points within the time period of lost positioning signal output by the second prediction model into paths respectively, fitting the two paths, and obtaining a corrected path.

[0021] The second aspect of the present invention also provides a passenger route positioning system based on multi-source position fusion, the system includes a computer device, the computer device includes a processor and a memory, the memory stores computer instructions, the processor is used to execute the computer instructions stored in the memory, when the computer instructions are executed by the processor, the system implements the steps implemented by the method described above.

[0022] The third aspect of the present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps implemented by the aforementioned passenger route positioning method based on multi-source position fusion.

[0023] Additional advantages, purposes, and features of the present invention will be described in part in the following description, and will become apparent to those skilled in the art after studying the following, or may be learned from the practice of the present invention. The purposes and other advantages of the present invention can be specifically pointed out and obtained in the specification and the accompanying drawings.

[0024] Those skilled in the art will appreciate that the objectives and advantages that can be achieved with the present invention are not limited to the above specific description, and the above and other objectives that can be achieved by the present invention will be more clearly understood from the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The drawings described herein are used to provide a further understanding of the present invention, constitute a part of this application, and do not constitute a limitation of the present invention.

[0026] Figure 1 A schematic diagram of an implementation method of the passenger route positioning method based on multi-source position fusion in this scheme;

[0027] Figure 2 It is a schematic diagram of another implementation method of the passenger route positioning method based on multi-source position fusion in this scheme;

[0028] Figure 3 This is a schematic diagram of the overall architecture of this solution;

[0029] Figure 4 This is a schematic diagram of the corresponding relationship between the attributes of this scheme and the line elements;

[0030] Figure 5 This is a schematic diagram of the calculation principle of the linear referencing system of this scheme. DETAILED DESCRIPTION

[0031] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the embodiments and the accompanying drawings. Here, the illustrative embodiments of the present invention and their descriptions are used to explain the present invention, but are not intended to limit the present invention.

[0032] It should also be noted that, in order to avoid obscuring the present invention due to unnecessary details, only structures and / or processing steps closely related to the solutions according to the present invention are shown in the accompanying drawings, while other details that are not closely related to the present invention are omitted.

[0033] In the prior art:

[0034] Passenger train lines require high-precision positioning to ensure driving safety, improve operating efficiency and enhance service quality, especially in complex railway environments. Traditional positioning technology may not provide sufficient accuracy, and a single source of location information (such as a satellite positioning system) is also difficult to meet the requirements of precise positioning. Therefore, it is necessary to combine multiple information sources, such as crew handheld terminals, line mileage data, intersection data, etc., through line mileage reference construction, railway line geometry correction, position fuzzy matching and other technologies to obtain more accurate and reliable positioning data. At the same time, the existing positioning technology has problems of insufficient accuracy and reliability in some cases (such as tunnels, high-rise buildings, densely populated urban areas or places with poor signal coverage). By integrating location data from different sources and introducing new technologies such as the new generation of train-mounted Beidou positioning equipment, the limitations of a single positioning method can be made up, thereby improving positioning accuracy and stability;

[0035] like Figure 1 As shown, the present invention proposes a passenger route positioning method based on multi-source position fusion, the steps of the method include:

[0036] Step S100, obtaining the driving positioning data of the bus in real time, and constructing at least one driving curve based on the driving positioning data, wherein the driving positioning data includes data of multiple positioning modes, and each driving curve corresponds to one positioning mode;

[0037] In the specific implementation process, the driving positioning data of the bus includes the positioning data of the on-board Beidou positioning device and the crew's handheld terminal;

[0038] In the specific implementation process, the spatial information of passenger trains in transit can be collected through on-board Beidou positioning equipment, crew handheld terminals, etc., and passenger line data can be obtained through passenger train positioning. At the same time, the mileage positioning data of in-transit trains is increased, and the collected raw data is pre-processed, which may include data cleaning, removal of outliers, data format conversion, etc.; basic information is obtained through the ledger of each railway unit, and data cleaning, deduplication, format standardization, etc. are performed to ensure data consistency and availability. The geometric line type of the railway line can be obtained through the line plan design drawing, terminal acquisition trajectory fitting, etc. At the same time, the precise line trajectory data of the passenger train is obtained through image processing, fitting algorithm processing, etc., to achieve passenger line positioning based on multi-source position fusion.

[0039] Finally, the collected passenger route spatial information will be matched and integrated with the ledger information, and pre-processing work such as data matching, field alignment, and data association will be performed to ensure the consistency and integrity of the two.

[0040] Step S200, extracting the railway line where the bus is located and the position points on the driving curve, and constructing them into a position point set;

[0041] In the specific implementation process, the control terminal of the passenger car pre-stores the route map of each railway line.

[0042] Step S300, performing route fitting based on the set of position points to obtain a fitted route;

[0043] In some embodiments of the present invention, in the step of performing line fitting based on the set of position points to obtain a fitted line, a variety of line fitting methods may be used, including:

[0044] 1. Cubic spline interpolation fitting:

[0045] Cubic spline interpolation fitting is a method that constructs a function composed of cubic polynomials through a series of known data points, and these polynomials meet certain continuity and smoothness conditions at the segmentation points. Cubic spline interpolation fitting can obtain a smooth curve, and the curve is a cubic polynomial at each segmentation point. For the fitting of non-closed curves or only one segment of the curve, cubic spline interpolation fitting can usually achieve better results than cubic B-spline fitting.

[0046] 2. Catmull-Rom spline fitting

[0047] Catmull-Rom spline fitting is an interpolation technique that can pass through all given control points and generate a smooth curve. Catmull-Rom spline fitting requires at least four control points, but the curve will only pass through some of the control points (not the first and last control points). The first and last control points are auxiliary points and do not participate in the direct generation of the curve, but affect the shape and direction of the curve. It is suitable for scenarios where the curve needs to pass through all given control points, such as lane line detection.

[0048] 3. Bezier curve fitting

[0049] The Bezier curve is a parametric curve widely used in computer graphics. It is defined by a series of control points, and the curve passes through the first and last control points, but not necessarily the middle control points. The Bezier curve can flexibly generate curves of various shapes by adjusting the position and number of control points. It is often used to draw smooth curve shapes, such as path planning, graphic design, etc. It should be noted that the Bezier curve may not pass through all the middle control points, which is different from the Catmull-Rom spline fitting.

[0050] 4. Least Squares Fitting

[0051] Least squares fitting is a method of finding the best function match to the data by minimizing the sum of squared errors.

[0052] The least squares fitting method is widely used in the fitting and regression analysis of various data. It can be used to fit various types of functions such as straight lines, polynomial curves, exponential curves, etc. In lane line fitting, the collected lane line data is often projected onto a bird's-eye view, and the least squares method is used to fit the cubic curve. However, the results of this method may be unstable, with oscillation at the far end.

[0053] In the specific implementation process, this plan uses the research to integrate multi-source positions such as crew handheld terminals, design drawings, and positioning measurement data, and uses fuzzy matching positions and railway line geometry correction technologies to achieve precise spatial positioning of train lines in transit. At the same time, based on the position data collected by the Beidou positioning equipment on the new generation of trains, a higher-precision positioning technology for multi-source position fusion of passenger lines is proposed.

[0054] Step S400, during the driving process of the bus, determining in real time whether the positioning signal is lost;

[0055] Step S410: If the positioning signal is lost, the predicted driving point is calculated based on the current fitting route, and the position of the predicted driving point is corrected after the positioning signal is received again.

[0056] By adopting the above scheme, this scheme can first fit the route through multiple positioning data, and when the positioning signal is lost, it can predict the position based on the known fitting route, and when the positioning signal is received again, it can calculate the final correction parameters through the correction algorithm to achieve combined positioning of multiple positioning methods, thereby improving the positioning accuracy of the combined positioning system and providing a more reliable and accurate solution for train positioning in complex railway line environments.

[0057] In some embodiments of the present invention, in the step of acquiring the driving positioning data of the bus in real time, the driving positioning data of the bus includes positioning data of the on-board Beidou positioning device and the crew's handheld terminal.

[0058] The multi-source position fusion positioning technology route for passenger lines mainly includes data collection, data preprocessing, geometric line acquisition and processing, data matching and integration, multi-source position fusion positioning, and positioning technology optimization, such as Figure 3 shown.

[0059] (1) Data collection:

[0060] Use the on-board Beidou positioning equipment and the crew's handheld terminal to collect real-time data on passenger line spatial information. Obtain basic information ledger data provided by the railway unit, including mileage, line type and other information.

[0061] (2) Data preprocessing:

[0062] Pre-process the collected raw data, including data cleaning, removal of outliers, data format conversion, etc. Clean, remove duplicates, and standardize the format of basic information ledger data to ensure data consistency and availability.

[0063] (3) Geometric line type acquisition and processing:

[0064] The geometric line information of the railway line is obtained by fitting the line plan and the terminal acquisition trajectory, and adopting the railway line fitting algorithm based on the cubic B-spline curve. The railway line space vector data and the railway line mileage account information data are processed by image processing and fitting algorithm, and a line-mileage linear reference system is constructed to extract effective geometric information with line mileage as reference.

[0065] (4) Data matching and integration:

[0066] The collected passenger route spatial information is matched and integrated with the ledger information, and pre-processing work such as data matching, field alignment, and data association is performed to ensure the consistency and integrity of the two.

[0067] (5) Multi-source position fusion positioning:

[0068] Combine multiple information sources for location fusion positioning, including fuzzy matching location, crew handheld terminal and railway line geometry correction. By integrating location data from different sources, the positioning accuracy and stability are improved, especially in complex railway environments. Utilize the line fuzzy location matching algorithm to combine dead reckoning, Beidou and map matching to achieve high-precision positioning.

[0069] (6) Positioning technology optimization:

[0070] Introduce new technologies such as the new generation of train-mounted Beidou positioning equipment to make up for the limitations of traditional positioning technology and improve positioning accuracy and stability. Continue to improve positioning technology to solve the problem that existing technologies are not accurate enough or unreliable enough in some cases, especially in tunnels, high-rise buildings, densely populated urban areas or places with poor signal coverage.

[0071] Beidou satellite navigation and positioning terminal is a device that uses the Beidou satellite system for positioning. Its positioning principle is based on satellite navigation technology. It adopts a deep-coupled combined navigation algorithm, and integrates high-precision GNSS boards and high-performance MEMSIMU. For intelligent driving applications in different scenarios, it uses vehicle motion models and antenna phase detection proprietary technologies to optimize the situation where navigation results are prone to divergence in harsh scenarios such as urban canyons and long-term loss of lock, and provides users with high-precision and highly reliable three-dimensional position, attitude, and speed solutions. In addition, the algorithm design supports a variety of applications other than land, such as aviation, ocean, and train control series, and supports the output of navigation raw data to meet the user's needs for deep fusion of multiple sensors.

[0072] The BeiDou satellite system consists of a group of satellites in orbit around the Earth that transmit navigation signals to the ground. BeiDou positioning terminals receive navigation signals from multiple BeiDou satellites through built-in receiving antennas. The received satellite signals contain time and position information from different satellites. BeiDou positioning terminals use this information to calculate their own position, speed and time through triangulation or more complex positioning algorithms. In addition to time and position information, satellite signals also contain the Doppler effect caused by motion. BeiDou positioning terminals calculate the relative speed between themselves and the satellite by analyzing the Doppler shift, thereby improving positioning accuracy. Since various factors (such as atmospheric delay, multipath effect, clock error, etc.) affect the propagation and reception of satellite signals, error correction is required to improve positioning accuracy. BeiDou positioning terminals may use differential GPS technology or other correction methods to reduce errors. After signal reception, solution and error correction, BeiDou positioning terminals will output the positioning results to the user, usually in the form of longitude, latitude and altitude, as well as possible speed and time information.

[0073] Passenger transport "route-mileage" linear reference system

[0074] The coordinate solution of the line mileage uses a dynamic segmentation technology in the ArcGIS-based linear reference measurement system. This method manages geographic information by storing the relative positions of features along the strip of railway lines. Specifically, the relative distance from the unknown feature to the starting point of the known linear feature is used to locate the measurement event along the line. This technology uses the information of the points along the line provided in the ledger table, calculates based on the relative position, and attaches one or more sets of attributes to the railway line features, such as Figure 4 As shown, the attribute information can be displayed, queried, edited and analyzed without changing the geometric shape of the railway line.

[0075] Through the passenger railway line trajectory vector data and real-life images, the spatial data along the railway is solved, a strip railway linear reference system is constructed, and a spatial mapping relationship between spatial data and mileage information is established. The railway mileage value is the point parameter along the line obtained through the mileage ledger table, including the latitude and longitude of the point and the corresponding mileage information. The linear reference system creates a series of linear events on the strip data, and dynamically calculates point events and line events according to the parameters of the linear reference, thereby generating strip vector data that integrates the corresponding linear reference parameters and realizing dynamic segmentation technology. Using the passenger line mileage data, a linear reference system based on the spatial coordinates and mileage correspondence between the trajectory and infrastructure along the passenger line is established. The spatial position can be located according to the line mileage value, or the mileage value of any position along the line can be queried, and statistical analysis of geometric data can be performed, such as calculating the total length of the railway line in a certain area.

[0076] The calculation process is as follows: first, establish the railway line vector data path in two-dimensional space and store the linear reference parameter M value; then organize the point set data containing spatial coordinates and corresponding mileage; then dynamically segment the point events converted from the ledger table and the line events of the railway path elements, and finally obtain linear vector data that can be used for storage, query, analysis, and display. The calculation principle is as follows: Figure 5 shown.

[0077] In some embodiments of the present invention, the driving positioning data includes positioning points corresponding to multiple time points. In the step of constructing at least one driving curve based on the driving positioning data, the corresponding positioning points are sequentially connected based on the time sequence of the time points to obtain a driving curve corresponding to each driving positioning data.

[0078] In some embodiments of the present invention, the step of constructing at least one driving curve based on the driving positioning data also includes calculating the distance value between each positioning point and the railway line where the passenger car is located, comparing the distance value with a preset distance threshold, and deleting the positioning point corresponding to the distance value if the distance value is greater than the preset distance threshold.

[0079] By adopting the above scheme, this scheme can delete invalid positioning points and complete data purification.

[0080] In some embodiments of the present invention, in the step of performing line fitting based on the position point set to obtain a fitted line, line fitting is performed based on the position point set and using a cubic B-spline curve fitting method to obtain a fitted line.

[0081] In the specific implementation process, the steps of cubic B-spline curve fitting specifically include:

[0082] 1. Parameterization

[0083] The discrete points are parameterized using the chord length parameterization method, that is, the parameter value is determined according to the distance between adjacent discrete points. Let the discrete point sequence be P i (i=0,1,...,n), calculate the distance d between two adjacent points i =|P i+1 -P i |, cumulative distance Then the parameter value of the i-th point is In this way, a correspondence is established between the discrete points and the parameter value t.

[0084] 2. Determine the node vector

[0085] The knot vector is an important parameter for defining a B-spline curve. For a cubic B-spline curve, a uniform knot vector or a non-uniform knot vector is usually used. If a uniform knot vector is used, the number of discrete points is set to n+1, and the knot vector U = [u0,u1,...,u m ], where m = n + 3 (for cubic B-splines), and u i is uniformly distributed on the interval [0,1], for example If non-uniform node vectors are used, they can be set according to the density of the discrete points. For example, the node spacing is smaller in areas with dense discrete points to better fit the curve shape.

[0086] 3. Constructing the system of equations

[0087] According to the mathematical expression of cubic B-spline curve (where N i,3 (t) is the cubic B-spline basis function, P i is the control point) and the parameter value of the discrete point, construct the equation system. For each discrete point P j , its parameter value t j Substituting into the curve equation, we get This results in a system of n+1 equations, with the unknown number P i are the coordinates of the control points.

[0088] 4. Solve for control points

[0089] Use the least squares method to solve the above equations to obtain the coordinates of the control points. The goal of the least squares method is to make the sum of squared errors Minimum. Write the system of equations in matrix form AP=B, where A is the coefficient matrix composed of basis function values, P is the control point coordinate vector, and B is the discrete point coordinate vector. By solving this linear system of equations, the coordinate values ​​of the control points can be obtained. In actual calculations, it may be necessary to use numerical calculation methods, such as singular value decomposition (SVD), to solve the matrix equations in order to improve the stability and accuracy of the calculation.

[0090] 5. Curve evaluation and adjustment

[0091] Fitting effect evaluation is to calculate the error index between the fitting curve and the discrete points, such as the root mean square error (RMSE). At the same time, the overlap between the fitting curve and the discrete points can be visually observed to check whether there is a poor local fit, such as excessive deviation of the curve near some discrete points.

[0092] If the fitting effect is not satisfactory, make adjustments based on the evaluation results. You can adjust the node vector, for example, increase the node density in certain key areas of the non-uniform node vector. You can also recheck the discrete point data to see if there are any data problems that need further processing, or adjust parameters such as weights in the least squares method, and then re-solve the control points until a satisfactory fitting curve is obtained.

[0093] At the same time, due to the geometric invariance, continuity, symmetry and recursion of B-spline curves, local fitting can be achieved in areas with complex railway line shapes and inaccurate positioning and acquisition. This method can effectively match the location of in-transit passenger lines with railway line trajectories and correct the railway line trajectories multiple times to make them more accurate.

[0094] like Figure 2 As shown, in some embodiments of the present invention, if the positioning signal is lost, the step of calculating the expected travel point based on the current fitting route includes:

[0095] Step S411, if the positioning signal is lost, extract the driving points in the current fitting route and input them into the pre-trained first prediction model, and output the predicted driving points through the first prediction model;

[0096] Step S412: During the time period when the positioning signal is lost, the predicted driving points and the driving points in the original fitting route are continuously input into the pre-trained first prediction model, and new predicted driving points are output.

[0097] By adopting the above scheme, the present scheme can predict the travel point based on the original fitting route. When the train loses the positioning signal, the predicted travel point can be provided as a reference for the train crew to ensure the travel safety of the train.

[0098] In the specific implementation process, in complex railway scenarios, due to the obstruction of the receiver signal by obstacles such as mountains and buildings, the positioning information of passenger trains will have large deviations or even signal loss, which is far from meeting the requirements of train positioning. To address this problem, this solution can use a positioning method that combines dead reckoning, Beidou and map matching.

[0099] In some embodiments of the present invention, in the step of calculating the expected driving points based on the current fitted route, if the positioning signal is not lost, the driving points in the current fitted route are extracted and input into a pre-trained first prediction model, the predicted driving points are output by the first prediction model, and the actually fitted driving points are used as label positions to train the first prediction model.

[0100] In some embodiments of the present invention, after receiving the positioning signal again, the step of correcting the position of the estimated driving point includes:

[0101] Step S420: input the driving point where the positioning signal is re-received and the driving point before the positioning signal is lost into a pre-trained second prediction model, and the second prediction model outputs the predicted driving point within the time period of lost positioning signal.

[0102] In some embodiments of the present invention, after the positioning signal is received again, the step of correcting the position of the expected driving point also includes step S430, constructing the driving points within the time period of lost positioning signal output by the first prediction model and the driving points within the time period of lost positioning signal output by the second prediction model as paths respectively, fitting the two paths, and obtaining a corrected path.

[0103] In some embodiments of the present invention, when the Beidou signal is lost, the accurate position information before the Beidou signal is lost is first obtained and recorded, and the speed and heading information output by the sensors on the train are collected. Based on these data, the dead reckoning algorithm based on the information of sensors such as odometers and gyroscopes is used to calculate the position of the train, thereby supplementing the positioning during the loss of the Beidou signal.

[0104] In some embodiments of the present invention, correction after signal recovery: When the Beidou system resumes operation, the high-precision positioning data of Beidou is compared with the position information obtained by dead reckoning. The error generated by dead reckoning is calculated through the root mean square error model, and then the dead reckoning system is corrected and compensated in real time based on this error, so that the result of dead reckoning is more accurate and the cumulative error is reduced.

[0105] In summary, this solution combines Beidou and dead reckoning from the perspective of map matching. A navigation positioning data correction algorithm based on fuzzy logic is adopted, which takes multiple factors such as Beidou's positioning accuracy, the reliability of dead reckoning, and the correction results of map matching as input variables of fuzzy logic. Through the fuzzy rule library of the line positioning test, these variables are fuzzy reasoning is performed to calculate the final correction parameters, and the combined positioning of Beidou, dead reckoning, and map matching is realized, thereby improving the positioning accuracy of the combined positioning system and providing a more reliable and accurate solution for train positioning in complex railway line environments.

[0106] The beneficial effects of this program include:

[0107] 1. Propose a multi-source position fusion positioning method and technical process for passenger lines, and combine the on-board Beidou positioning equipment and the crew's handheld terminal data in the data collection stage, and use the "line-mileage" coordinate system to establish a linear reference system for railway lines, stations, and infrastructure positioning.

[0108] 2. Deeply coupled combined navigation algorithm is integrated with high-performance MEMSIMU. The deeply coupled navigation algorithm combines GNSS and IMU data to provide more accurate positioning results through complex fusion algorithms. Especially in harsh scenarios such as urban canyons and tunnels, the algorithm can optimize navigation results, avoid data divergence, and provide high-precision and high-reliability three-dimensional position, attitude and velocity solutions.

[0109] 4. Multi-scenario application support and navigation raw data output. Beidou positioning terminal is designed to support multiple application scenarios and can output navigation raw data to meet the needs of users for multi-sensor deep fusion. This design ensures the versatility and scalability of the device, is suitable for different application scenarios, and improves the flexibility and adaptability of the system. Users can customize navigation solutions based on raw data to enhance the application value of the system.

[0110] 5. Construct a passenger "line-mileage" linear reference system. Based on passenger lines and collected mileage ledger data, dynamic segmentation technology is used to calculate the mileage value of the entire passenger line and construct a passenger "line-mileage" linear reference system, which can realize accurate positioning of railway infrastructure according to the linear reference system.

[0111] 6. Railway line fitting method based on the combination of multiple fitting algorithms. This method combines the advantages of multiple railway line fitting algorithms and proposes a railway line fitting method based on cubic B-spline curve fitting. By using the longitude and latitude information collected by the Beidou positioning terminal and the railway line vector data generated according to the design drawings, the train route can be effectively fitted. Compared with a single fitting algorithm, this method can fit the railway line more accurately in different scenarios, solving the problems of fixed parameters and large errors in the single algorithm model.

[0112] 7. Local fitting capability and trajectory correction. By utilizing the geometric invariance, continuity, symmetry and recursion of B-spline curves, this method can perform local fitting in areas with complex railway line shapes and areas with inaccurate positioning and acquisition. This local fitting capability allows multiple corrections to the positions of in-transit passenger lines and railway line trajectories, improving the accuracy and stability of trajectory matching and making railway line trajectories more accurate.

[0113] 8. Combined train positioning method combined with map matching technology. This invention combines dead reckoning, Beidou navigation and map matching technology to achieve high-precision train positioning when Beidou signal is lost. When the Beidou system signal is lost, the position information before the signal is lost and the speed and heading information output by the sensor are used to supplement the positioning through dead reckoning; after the Beidou system resumes working, the dead reckoning error is corrected and compensated in real time.

[0114] 9. Navigation positioning data correction algorithm based on fuzzy logic. A fuzzy logic-based algorithm was developed for the correction of Beidou, dead reckoning and map matching combined positioning data. The algorithm processes multi-source data through fuzzy logic, optimizes and adjusts between different positioning technologies, and enhances the robustness and accuracy of the combined positioning system, especially in complex environments (such as mountains and buildings). Improve the accuracy and reliability of train positioning.

[0115] An embodiment of the present invention also provides a passenger route positioning system based on multi-source position fusion, the system comprising a computer device, the computer device comprising a processor and a memory, the memory storing computer instructions, the processor being used to execute the computer instructions stored in the memory, and when the computer instructions are executed by the processor, the system implements the steps implemented by the method described above.

[0116] The embodiment of the present invention also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps implemented by the aforementioned passenger route positioning method based on multi-source position fusion are implemented. The computer-readable storage medium can be a tangible storage medium, such as a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a floppy disk, a hard disk, a removable storage disk, a CD-ROM, or any other form of storage medium known in the technical field.

[0117] It should be understood by those skilled in the art that the exemplary components, systems and methods described in conjunction with the embodiments disclosed herein can be implemented in hardware, software or a combination of the two. Whether it is performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, etc. When implemented in software, the elements of the present invention are programs or code segments used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or a communication link via a data signal carried in a carrier.

[0118] It should be clear that the present invention is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present invention is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present invention.

[0119] In the present invention, features described and / or illustrated for one embodiment may be used in the same or similar manner in one or more other embodiments, and / or combined with features of other embodiments or replace features of other embodiments.

[0120] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the embodiments of the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A passenger route positioning method based on multi-source position fusion, characterized in that: The steps of the method include: Acquire the driving positioning data of the bus in real time, and construct at least one driving curve based on the driving positioning data, wherein the driving positioning data includes data of multiple positioning methods, and each driving curve corresponds to one positioning method; Extracting the railway line where the passenger car is located and the position points on the driving curve, and constructing them into a position point set; Performing route fitting based on the set of position points to obtain a fitted route; During the driving process of the bus, it is determined in real time whether the positioning signal is lost. If the positioning signal is lost, the expected driving point is calculated based on the current fitting route, and the position of the expected driving point is corrected after the positioning signal is received again.

2. The passenger route positioning method based on multi-source position fusion according to claim 1 is characterized in that: In the step of acquiring the driving positioning data of the bus in real time, the driving positioning data of the bus includes the positioning data of the on-board Beidou positioning device and the handheld terminal of the crew.

3. The passenger route positioning method based on multi-source position fusion according to claim 1 is characterized in that: The driving positioning data includes positioning points corresponding to a plurality of time points. In the step of constructing at least one driving curve based on the driving positioning data, the corresponding positioning points are sequentially connected based on the time sequence of the time points to obtain a driving curve corresponding to each driving positioning data.

4. The passenger route positioning method based on multi-source position fusion according to claim 1 is characterized in that: The step of constructing at least one driving curve based on the driving positioning data also includes calculating the distance value between each positioning point and the railway line where the passenger car is located, comparing the distance value with a preset distance threshold, and deleting the positioning point corresponding to the distance value if the distance value is greater than the preset distance threshold.

5. The passenger route positioning method based on multi-source position fusion according to claim 1 is characterized in that: In the step of performing line fitting based on the position point set to obtain a fitted line, line fitting is performed based on the position point set and by using a cubic B-spline curve fitting method to obtain a fitted line.

6. The passenger route positioning method based on multi-source position fusion according to claim 1 is characterized in that: In the step of calculating the expected driving points based on the current fitting route if the positioning signal is lost, if the positioning signal is lost, the driving points in the current fitting route are extracted and input into the pre-trained first prediction model, and the predicted driving points are output through the first prediction model. During the time period when the positioning signal is lost, the predicted driving points and the driving points in the original fitting route are continuously input into the pre-trained first prediction model, and new predicted driving points are output.

7. The passenger route positioning method based on multi-source position fusion according to any one of claims 1 to 6, characterized in that: In the step of calculating the expected driving points based on the current fitted route, if the positioning signal is not lost, the driving points in the current fitted route are extracted and input into the pre-trained first prediction model, the predicted driving points are output by the first prediction model, and the actually fitted driving points are used as label positions to train the first prediction model.

8. The passenger route positioning method based on multi-source position fusion according to claim 1 is characterized in that: In the step of correcting the position of the predicted driving point after the positioning signal is received again, the driving point where the positioning signal is received again and the driving point before the positioning signal is lost are input into a pre-trained second prediction model, and the second prediction model outputs the predicted driving point within the time period of lost positioning signal.

9. The passenger route positioning method based on multi-source position fusion according to claim 8, characterized in that: After receiving the positioning signal again, the step of correcting the position of the expected driving point also includes constructing the driving points within the time period of lost positioning signal output by the first prediction model and the driving points within the time period of lost positioning signal output by the second prediction model into paths respectively, fitting the two paths, and obtaining a corrected path.

10. A passenger route positioning system based on multi-source position fusion, characterized in that: The system includes a computer device, which includes a processor and a memory. The memory stores computer instructions. The processor is used to execute the computer instructions stored in the memory. When the computer instructions are executed by the processor, the system implements the steps implemented by the method as described in any one of claims 1 to 9.

Images