A vehicle positioning method based on multi-source information fusion

Abstract

This invention discloses a vehicle positioning method based on multi-source information fusion. It includes: deploying magnetic markers and RFID tags; generating local error correction codes based on the deployment of electromagnetic markers; longitudinal vehicle positioning, where upon receiving RTK data, the nearest magnetic marker sequence is determined based on latitude and longitude and the local error correction code; upon receiving RFID data, the nearest magnetic marker sequence is determined based on the EPC number and the local error correction code; upon receiving magnetic marker sequence data, the magnetic marker sequence is maintained by counting and the vehicle's longitudinal position is determined based on the magnetic marker sequence; and lateral vehicle positioning, where the lateral deviation of the vehicle relative to the road is calculated when the vehicle receives magnetic field strength through an array of sensing units. This invention employs multi-source information fusion for both lateral and longitudinal vehicle positioning, ensuring that the vehicle's position can be determined at any location on the route based on the local error correction code, combined with RTK or RFID, thus improving positioning accuracy, practicality, and engineering feasibility.

Description

Technical Field

[0001] This invention relates to the field of vehicle guidance and navigation technology, and more specifically, to a vehicle positioning method based on multi-source information fusion. Background Technology

[0002] In recent years, autonomous driving technology has developed rapidly. Various sensors, such as vision systems, millimeter-wave radar, lidar, and RTK, provide autonomous vehicles with numerous ways to perceive and locate. Various driver assistance systems, such as surround-view systems and vision assistance systems, have been widely used in autonomous vehicles.

[0003] Existing research offers numerous methods for vehicle positioning. Patent "CN114690231A" proposes a satellite signal-based positioning method. This patent employs a target positioning algorithm to determine the vehicle's lateral positioning error based on the deviation between satellite positioning data and the target driving curve. Patent "CN114279453" proposes a vehicle positioning method for autonomous vehicles based on vehicle-road cooperation. By acquiring vehicle reference position information sent by roadside equipment, it determines the vehicle's position on a global map, ensuring positioning accuracy even in extreme environments. Patent "CN104460665A" provides a method for establishing a magnetic navigation unmanned vehicle and its map based on a road curvature map. During autonomous driving, the vehicle can achieve effective tracking control by controlling the computer and combining the vehicle's own parameters with curvature map information. This method effectively overcomes the geographical limitations of navigation coordinate map methods, and the magnetic navigation road layout using magnetic nails laid on the ground has been widely accepted by most technicians. Patent "CN108052107A" utilizes onboard magnetic sensors and gyroscopes to collect lateral deviation data and attitude angle data of the vehicle relative to magnetic nails, achieving tracking control for autonomous vehicles.

[0004] The shortcomings of the existing technology are that the above-mentioned patents mainly rely on a single sensor to achieve the lateral or longitudinal positioning of the vehicle, which cannot simultaneously ensure the high accuracy and high robustness of vehicle positioning. Summary of the Invention

[0005] To address the problems of low accuracy and insufficient robustness in current vehicle positioning methods, this invention provides a vehicle positioning method based on multi-source information fusion. This method includes lateral and longitudinal positioning of the vehicle, and ensures accurate positioning by fusing multiple data sources.

[0006] This invention is achieved through the following technical means: a vehicle positioning method based on multi-source information fusion, characterized by comprising the following steps:

[0007] 1) Install RTK equipment, including RTK mobile station, base station and antenna;

[0008] RTK antennas are installed at the front and rear of the vehicle, an RTK mobile station is installed in the middle of the vehicle, and an RTK base station is installed on the ground to obtain the vehicle's latitude and longitude coordinates.

[0009] 2) Deploy electromagnetic markers, including magnetic markers and RFID tags;

[0010] Magnetic tags and RFID tags are arranged on the line in an array-like distribution. The magnetic tags are encoded by expanding the sequence of magnetic tags according to their N / S polarity in a binary encoding manner. The magnetic tag encoding includes local error correction coding and padding segments.

[0011] 3) Generate local error correction codes based on the arrangement of electromagnetic markers;

[0012] The magnetic markers on the line are encoded. The local error correction coding sequence is the same on different road segments. The local error correction code is determined based on the obtained magnetic marker sequence data, and code padding is set between the local error correction codes of each road segment.

[0013] Preferably, the following steps are also included:

[0014] 1) Vehicle longitudinal positioning;

[0015] After receiving magnetic tag sequence data, RFID data, or RTK data, the vehicle records its current mileage and determines its longitudinal position based on this data.

[0016] a. When the vehicle receives magnetic tag sequence data, it maintains the magnetic tag sequence by counting, determines the local error correction code based on the magnetic tag sequence, and determines the longitudinal position of the vehicle based on the local error correction code and the magnetic tag sequence.

[0017] b. When the vehicle receives RTK data, first determine the latitude and longitude of the vehicle's location based on the RTK data, then determine the nearest magnetic marker sequence based on the latitude and longitude and the local error correction code, and finally determine the longitudinal position of the vehicle based on the RTK latitude and longitude data and the local error correction code.

[0018] c. When the vehicle receives RFID data, it first determines the EPC number of the RFID tag at its location based on the RFID data, then determines the nearest magnetic tag sequence based on the EPC number and the local error correction code, and finally determines the longitudinal position of the vehicle based on the magnetic tag sequence.

[0019] 2) Vehicle lateral positioning;

[0020] After receiving camera data and magnetic tag sequence data, the vehicle's lateral position is determined based on this data;

[0021] a. The vehicle's lateral deviation is obtained by directly measuring the distance between the vehicle and the center lane line through a camera;

[0022] b. By collecting information on the distribution of the spatial magnetic field when the vehicle passes the magnetic marker, the lateral distance of the vehicle relative to the fixed magnetic marker is determined, and the magnitude of the lateral deviation of the vehicle is finally obtained.

[0023] After the vehicle passes a complete magnetic marker, the encoded segment data of the magnetic marker is obtained through reverse decoding, thereby updating the local error correction code. The longitudinal position of the vehicle in the local error correction code is obtained by longitudinal integration between magnetic markers. The longitudinal integration is to integrate parameters such as speed in the vehicle's driving direction. Then, the longitudinal position of the vehicle is updated in an incremental manner after passing each magnetic marker position.

[0024] Preferably, the local error correction code consists of 16 magnetic tags, and the code formed by any four consecutive magnetic tags in the local error correction code is different;

[0025] When a vehicle passes through a local error correction code, the initial longitudinal position of the vehicle is determined by comparing the received RFID data or RTK data with the local error correction code.

[0026] Preferably, the magnetic markers of the filled segments all have the same polarity.

[0027] Preferred: After the vehicle receives the magnetic tag sequence data and maintains the magnetic tag sequence, it determines whether it can match the local error correction code;

[0028] If not, after judging the mileage threshold and preconditions, the magnetic tag sequence matching algorithm is used to perform local error correction coding matching based on RTK data and RFID data;

[0029] If so, the approximate longitudinal position of the vehicle is determined, and the historical magnetic marker sequence is matched with the on-line magnetic marker sequence to finally determine the longitudinal position of the vehicle on the global road.

[0030] Preferably, when a vehicle collects spatial magnetic field distribution information when passing a magnetic marker via a positioning sensor, the magnetic sensor will be affected by the ambient magnetic field other than the magnetic field of the magnetic marker; the electromagnetic positioning sensor includes multiple magnetic sensing units, and by repeatedly measuring the magnetic field at the location of the magnetic sensing unit and obtaining the average magnetic field value of each magnetic sensing unit, the magnetic field value of each magnetic sensing unit is subtracted from the average magnetic field value of all magnetic sensing units as the deviation, and this deviation is subtracted from each magnetic field data obtained by the subsequent electromagnetic positioning sensor to eliminate the influence of the surrounding environment.

[0031] Preferred method: When the vehicle receives magnetic field data of the magnetic marker through the positioning sensor, the data consistency is calculated by calculating the standard deviation of the magnetic field data of each frame; when the standard deviation of the magnetic field data is less than or equal to a certain value, it is determined to be the magnetic field data of the deployed magnetic marker.

[0032] Preferably, the magnetic markers and RFID tags are arranged in one or more rows at a fixed interval in the center of the line.

[0033] Compared with the prior art, the beneficial effects of the present invention are:

[0034] By fully combining the characteristics of magnetic tag sequence data, RFID data, camera data and RTK data, multi-source information fusion is used to perform lateral and longitudinal positioning of vehicles, ensuring that the vehicle's position can be determined based on data and magnetic tag coding at any location on the route.

[0035] Compared to traditional vehicle positioning methods, this method offers higher accuracy and lower positioning costs, significantly improving practicality and engineering feasibility. It addresses the issues of insufficient robustness and low accuracy in existing positioning methods, providing new ideas and feasible solutions for autonomous vehicle positioning technology. Attached Figure Description

[0036] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0037] Figure 1 This is a schematic diagram of a vehicle positioning method based on multi-source information fusion according to the present invention.

[0038] Figure 2 This is a flowchart of the longitudinal positioning process of a vehicle positioning method based on multi-source information fusion according to the present invention.

[0039] Figure 3 yes Figure 2 A flowchart for maintaining the magnetic tag sequence. Detailed Implementation

[0040] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0041] Combination Figure 1 As shown, a vehicle localization method based on multi-source information fusion includes longitudinal vehicle localization and lateral vehicle localization. Longitudinal vehicle localization employs multi-source data fusion, primarily based on detected magnetic tag sequence data, RFID data, and RTK data, in conjunction with a longitudinal vehicle localization algorithm. Lateral vehicle localization employs multi-source data fusion, primarily based on detected magnetic tag sequence data and camera data, in conjunction with a lateral vehicle localization algorithm.

[0042] A vehicle localization method based on multi-source information fusion includes the following steps:

[0043] Step (1): Install RTK equipment, including RTK mobile station, base station and antenna;

[0044] RTK antennas are installed at the front and rear of the vehicle, an RTK mobile station is installed in the middle of the vehicle, and an RTK base station is installed on the ground to obtain the vehicle's latitude and longitude coordinates.

[0045] Similarly, vehicle location information can also be obtained by using an RTK mobile station plus a paid high-precision 4G module.

[0046] Step (2), deploy magnetic tags and RFID tags;

[0047] Magnetic tags and RFID tags are arranged on the line in an array-like distribution. The magnetic tags are encoded by expanding the sequence of magnetic tags according to their N / S polarity in a binary encoding manner. The magnetic tag encoding includes local error correction coding and padding segments.

[0048] Magnetic markers (magnetic nails) have positive and negative poles, equivalent to 0 and 1 in binary. The encoding refers to the numbers formed by different 0s and 1s; for example, 0110 is a 4-bit code, which is 6 in decimal. Filled sections are unimportant road sections, and the magnetic marker codes in these sections have the same polarity, greatly reducing construction difficulty. The arrangement of road magnetic markers and RFID tags directly affects vehicle positioning accuracy. In this embodiment, magnetic markers and RFID tags are arranged in a row in the center of the road, with magnetic markers spaced 1 meter apart and RFID tags spaced 8 meters apart. Each RFID tag is 0.5 meters apart from adjacent magnetic markers. Depending on different working conditions, the spacing between magnetic markers and RFID tags can be set differently, and they can also be laid in two rows.

[0049] Similarly, the spacing between magnetic tags and RFID tags can also be set to other fixed distances.

[0050] Step (3): Generate local error correction codes based on the magnetic marker arrangement;

[0051] The magnetic markers on the track are specifically encoded to form local error correction codes. Code padding is used between these local error correction codes, and the specific arrangement of the codes can be reasonably determined based on construction requirements and scope. After a vehicle passes through a complete local error correction code, the coded segment value is obtained through reverse decoding, thus revealing the vehicle's longitudinal position relative to the local error correction code within a certain range. Subsequently, the vehicle's longitudinal position is updated incrementally each time it passes a magnetic marker.

[0052] In this embodiment, the local error correction code consists of 16 magnetic tags. Any four consecutive magnetic tags in the local error correction code will form a different code; however, the magnetic tag codes in the local error correction code are all the same. The local error correction code is used for local longitudinal positioning, that is, determining the relative position of the vehicle and the magnetic tags over a short distance. When the vehicle passes a local error correction code, the initial longitudinal position of the vehicle is determined by comparing the received RFID data or RTK data with the local error correction code. To improve local positioning, the codes formed by any four consecutive magnetic tags in the local error correction code are set to be different. To reduce the number of codes, the local error correction codes for different road segments are kept consistent.

[0053] Step (4), longitudinal positioning of the vehicle;

[0054] like Figure 2 As shown, regardless of whether the vehicle receives magnetic tag sequence data, RFID data, or RTK data, it first records the current mileage of the vehicle based on these data.

[0055] There are three operating conditions here;

[0056] a. When the vehicle receives magnetic tag sequence data, it maintains the magnetic tag sequence by counting, determines the local error correction code based on the magnetic tag sequence, and determines the longitudinal position of the vehicle based on the local error correction code and the magnetic tag sequence.

[0057] b. When the vehicle receives RTK data, first determine the latitude and longitude of the vehicle's location based on the RTK data, then determine the nearest magnetic marker sequence based on the latitude and longitude and the local error correction code, and finally determine the longitudinal position of the vehicle based on the RTK latitude and longitude data and the local error correction code.

[0058] c. When the vehicle receives RFID data, it first determines the EPC number of the RFID tag at its location based on the RFID data, then determines the nearest magnetic tag sequence based on the EPC number and the local error correction code, and finally determines the longitudinal position of the vehicle based on the magnetic tag sequence.

[0059] Preferably: In step a above, after the vehicle receives the magnetic tag sequence data and maintains the magnetic tag sequence, it determines whether the local longitudinal position has been determined;

[0060] If the local longitudinal position has been determined, proceed to step d;

[0061] Step d: If the distance between the current magnetic tag and the magnetic tag on the previous sequence is less than a certain threshold, discard the tags in parallel; if the distance between the current magnetic tag and the magnetic tag on the previous sequence is greater than or equal to a certain threshold, or less than or equal to a certain threshold, proceed to step e.

[0062] Step e: Determine the degree of deviation of the current mark's lateral deviation relative to the lateral deviation of the previous magnetic mark and the lateral deviation of the magnetic mark two years prior; if yes, the mark is in the magnetic mark sequence on the line, and the magnetic mark sequence number is incremented by 1; if no, the mark is not in the magnetic mark sequence on the line, and is discarded.

[0063] If the local longitudinal position is not determined, proceed to step f;

[0064] Step f: Combining Figure 2 Determine whether the most recent magnetic markers satisfy the local error correction coding; if yes, find the marker sequence number based on the local error correction coding value; if not, proceed to step g.

[0065] Step g: Determine whether the mileage at the time of the most recent received RTK data is greater than the mileage at the time of the most recent received RFID data; if yes, proceed to step h; if no, proceed to step i.

[0066] Step h: Determine whether the difference between the mileage at the time of the most recent RTK data reception and the current mileage is less than a certain threshold, and whether the current magnetic marker sequence size is greater than or equal to a certain fixed distance; if yes, set the vehicle's initial position to the magnetic marker sequence number determined by the RTK data, set the range to half of a certain fixed distance, and then proceed to step j; if no, it means that not enough data has been obtained to determine the longitudinal position.

[0067] Step i: Determine whether the difference between the mileage at the time of the most recent RFID data reception and the current mileage is less than a certain threshold, and whether the current magnetic tag sequence size is greater than or equal to a certain fixed distance; if yes, set the initial position of the sliding window to the magnetic tag sequence number determined according to the RFID data, set the sliding range to half of a certain fixed distance, and then proceed to step j; if no, it means that not enough data has been obtained to determine the longitudinal position.

[0068] Step j: Starting from the current magnetic marker, extract all magnetic marker sequences with a certain index size; use the magnetic marker sequence matching algorithm to determine the vehicle's position on the magnetic marker sequence based on the vehicle's approximate longitudinal position, historical magnetic marker sequences, and on-line magnetic marker sequences.

[0069] Step k: If the magnetic tag sequence that satisfies the above two conditions is unique, then the magnetic tag sequence is determined.

[0070] Preferably, in step a above, the step of maintaining the magnetic tag sequence is:

[0071] Combination Figure 3 As shown, after receiving a new magnetic tag, it checks whether the distance from the previous frame is insufficient to drop a tag; if so, the sequence is cleared and a new sequence is created; if not, a connection is established for the current magnetic tag, and then the process proceeds to the next step.

[0072] Determine if the previous sequence consists of two elements; if so, normalize and connect the previous sequence; otherwise, delete the older sequence and recursively output the sequence.

[0073] This embodiment detects the magnetic field of magnetic markers along the vehicle's travel direction, utilizes the magnetic field polarity to obtain a local magnetic marker sequence, thereby accurately determining the specific location of an individual magnetic marker and its longitudinal relative position to the vehicle, achieving local longitudinal positioning of the vehicle. Since the positions of the magnetic markers on the road are fixed, the vehicle's position within the complete road can be determined by acquiring the longitudinal distribution of the magnetic field of the magnetic markers.

[0074] Step (4), vehicle lateral positioning;

[0075] a. The vehicle directly measures the distance between itself and the center lane line through a camera. This positioning information can provide deviation information for the automatic lateral control of the vehicle during driving.

[0076] b. Since the direction and magnitude of the magnetic field at various points in the space near the magnetic marker are mutually exclusive, the vehicle can determine the lateral distance of the vehicle relative to the fixed magnetic marker by collecting the spatial magnetic field distribution information when passing the magnetic marker, and finally obtain the magnitude of the vehicle's lateral deviation.

[0077] When a vehicle collects information about the distribution of the spatial magnetic field as it passes a magnetic marker using a positioning sensor, it is affected by the ambient magnetic field, in addition to the magnetic field of the magnetic marker. In this embodiment, the positioning sensor includes 16 arrayed magnetic sensing units. Each magnetic sensing unit detects the magnitude and direction of the magnetic field at its location. By taking multiple measurements of the positioning sensor and obtaining the average value of each magnetic sensing unit, the average value of all magnetic sensing units is subtracted from the value of each magnetic sensing unit as the deviation. This deviation is subtracted from each subsequent data obtained by the positioning sensor to eliminate the influence of the surrounding environment.

[0078] In the calculation process of the positioning sensor, determining the presence of a magnetic marker is crucial. Further data processing is only necessary if a magnetic marker is detected. First, the presence of a magnetic marker under each positioning sensor is checked, and the consistency of each sensor is compared. The closer the magnetic marker is to the positioning sensor, the worse the consistency. In practical applications, the presence of a magnetic marker can be determined by checking if the standard deviation of the consistency data exceeds a certain value. By analyzing the trend of the standard deviation, the relationship between the distance between the magnetic marker and the positioning sensor can be determined. Finally, the lateral distance between the magnetic marker and the positioning sensor is detected. Once the distance between the magnetic marker and the positioning sensor is obtained, the relative distance between the vehicle and the magnetic marker can be determined, achieving lateral positioning of the vehicle.

[0079] This invention addresses the problems of low accuracy, high cost, and difficulty in engineering application of current vehicle positioning methods. As can be seen from this embodiment, the advantages of this invention are:

[0080] (1) For vehicles using electromagnetic tags for longitudinal positioning, this longitudinal positioning method based on RFID data can ensure that the vehicle can enter the road with magnetic tags before entering the road with magnetic tags; and after entering the road with magnetic tags, the magnetic tags on the magnetic tag sequence can be quickly extracted.

[0081] (2) Relying solely on magnetic tag coding for vehicle longitudinal positioning has several drawbacks: the vehicle needs to pass over a coded magnetic tag before its specific location can be determined. This means that the vehicle cannot determine its exact location on the map before obtaining longitudinal positioning information, i.e., it cannot obtain the environmental conditions at that location, which will have a certain impact on the vehicle's lateral and longitudinal control. This invention utilizes RFID and RTK to solve this problem. The principle of this technology is to use non-contact data communication between the reader and the tag, using the reader to read the location information stored in the tag installed on the ground. RTK technology mainly utilizes a combination of GPS and data transmission technology to determine the vehicle's latitude and longitude in a short time through real-time calculation, so as to facilitate high-precision positioning. The combination of these two methods allows the vehicle to obtain longitudinal position information through the tag before passing over the magnetic tag;

[0082] (3) Based on the characteristics of RFID, RTK and magnetic tag coding, this invention avoids positioning blind spots and improves positioning stability and accuracy when the vehicle is in motion.

[0083] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A vehicle positioning method based on multi-source information fusion, characterized in that, Includes the following steps: 1) Install RTK equipment, including RTK mobile station, RTK base station and RTK antenna; RTK antennas are installed at the front and rear of the vehicle, an RTK mobile station is installed in the middle of the vehicle, and an RTK base station is installed on the ground to obtain the vehicle's latitude and longitude coordinates. 2) Deploy electromagnetic markers, including magnetic markers and RFID tags; Magnetic tags and RFID tags are arranged on the line in an array-like distribution. The magnetic tags are encoded by expanding the sequence of magnetic tags according to their N / S polarity in a binary encoding manner. The magnetic tag encoding includes local error correction coding and padding segments. 3) Generate local error correction codes based on the arrangement of electromagnetic markers; The magnetic markers on the line are encoded. The local error correction coding sequence is the same on different road segments. Multiple consecutive magnetic marker sequence data form a local error correction code. The local error correction code is determined based on the obtained magnetic marker sequence data. Code padding is set between the local error correction codes of each road segment. It also includes the following steps: Vehicle longitudinal positioning; After receiving magnetic tag sequence data, RFID data, or RTK data, the vehicle records its current mileage and determines its longitudinal position based on this data. a. When the vehicle receives magnetic tag sequence data, it maintains the magnetic tag sequence by counting, determines the local error correction code based on the magnetic tag sequence, and determines the longitudinal position of the vehicle based on the local error correction code and the magnetic tag sequence. b. When the vehicle receives RTK data, first determine the latitude and longitude of the vehicle's location based on the RTK data, then determine the nearest magnetic marker sequence based on the latitude and longitude and the local error correction code, and finally determine the longitudinal position of the vehicle based on the RTK latitude and longitude data and the local error correction code. c. When the vehicle receives RFID data, it first determines the EPC number of the RFID tag at its location based on the RFID data, then determines the nearest magnetic tag sequence based on the EPC number and the local error correction code, and finally determines the longitudinal position of the vehicle based on the magnetic tag sequence. After the vehicle receives the magnetic tag sequence data and maintains the magnetic tag sequence, it determines whether it can match the local error correction code. If not, after judging the mileage threshold and preconditions, the magnetic tag sequence matching algorithm is used to perform local error correction coding matching based on the most recently received RTK data and the most recently received RFID data. If so, the approximate longitudinal position of the vehicle is determined, and the vehicle's longitudinal location on the global road is finally determined by matching the historical magnetic marker sequence with the line magnetic marker sequence.

2. The vehicle positioning method based on multi-source information fusion according to claim 1, characterized in that, It also includes the following steps: Vehicle lateral positioning; After receiving camera data and magnetic tag sequence data, the vehicle's lateral position is determined based on this data; a. The vehicle's lateral deviation is obtained by directly measuring the distance between the vehicle and the center lane line through a camera; b. By collecting information on the distribution of the spatial magnetic field when the vehicle passes the magnetic marker, the lateral distance of the vehicle relative to the fixed magnetic marker is determined, and the magnitude of the lateral deviation of the vehicle is finally obtained.

3. The vehicle positioning method based on multi-source information fusion according to claim 2, characterized in that: The vehicle acquires local error correction codes through sensors, and then obtains longitudinal positioning information based on the local error correction code data, RTK data, and RFID data. The positioning information is used to assist in the longitudinal control of the vehicle.

4. The vehicle positioning method based on multi-source information fusion according to claim 2, characterized in that: After the vehicle passes through a complete magnetic marker, the encoded segment data of the magnetic marker is obtained through reverse decoding, thereby updating the local error correction code; the longitudinal position of the vehicle in the local error correction code is obtained through longitudinal integration between magnetic markers; then, the longitudinal position of the vehicle is updated in an incremental manner every time it passes through a magnetic marker position.

5. The vehicle positioning method based on multi-source information fusion according to claim 4, characterized in that: The local error correction code consists of 16 magnetic tags, and the codes formed by any four consecutive magnetic tags in the local error correction code are all different. When a vehicle passes through a local error correction code, the initial longitudinal position of the vehicle is determined by comparing the received RFID data or RTK data with the local error correction code.

6. The vehicle positioning method based on multi-source information fusion according to claim 5, characterized in that: The magnetic markers of the filled segments all have the same polarity.

7. The vehicle positioning method based on multi-source information fusion according to claim 1, characterized in that: When a vehicle collects information on the distribution of the spatial magnetic field as it passes a magnetic marker using a positioning sensor, the magnetic sensor is affected by the ambient magnetic field other than that of the magnetic marker. The electromagnetic positioning sensor includes multiple magnetic sensing units. By repeatedly measuring the magnetic field at the location of each magnetic sensing unit and obtaining the average magnetic field value of each magnetic sensing unit, the average magnetic field value of each magnetic sensing unit is subtracted from the average magnetic field value of all magnetic sensing units as the deviation. This deviation is then subtracted from each magnetic field data obtained by the subsequent electromagnetic positioning sensor to eliminate the influence of the surrounding environment.

8. A vehicle positioning method based on multi-source information fusion according to claim 7, characterized in that: When a vehicle receives magnetic field data from a magnetic marker via a positioning sensor, data consistency is calculated by determining the standard deviation of the magnetic field data for each frame. If the standard deviation of the magnetic field data is less than or equal to a certain value, it is determined that the vehicle has passed the corresponding magnetic marker.

9. A vehicle positioning method based on multi-source information fusion according to claim 1, characterized in that: The magnetic markers and RFID tags are arranged in one or more rows at fixed intervals in the center of the line.

Images