A positioning data processing method for unmanned vehicle fleet at a dock

Abstract

The present application provides a method for processing positioning data of an unmanned vehicle fleet at a terminal, including: determining preset task path data of a task vehicle in the unmanned vehicle fleet, sending the data to the corresponding task vehicle and uploading the data to a database; obtaining real-time positioning data and reporting the data to the database; performing deviation correction processing on the real-time positioning data to obtain real-time positioning data after correction, establishing a target index of the real-time positioning data and preset task path data before and after the deviation correction, processing the real-time positioning data and preset task path data before and after the deviation correction, determining abnormal positioning sections and multiple dimensional labels, and uploading the abnormal positioning sections and the corresponding multiple dimensional labels in the database, and using the abnormal positioning sections and the corresponding multiple dimensional labels in the database to determine the preset task path data, thereby optimizing the planning process of the task path and minimizing positioning information abnormalities in the task path.

Description

Technical Field

[0001] The present application relates to the field of unmanned driving, and in particular, to a method for processing positioning data of an unmanned driving fleet at a terminal. Background Art

[0002] With the rapid development of Internet of Things technology, unmanned driving technology has been applied in many fields, such as logistics. In the field of logistics, unmanned driving fleets usually need to send the preset task path data of the task vehicle, and then during the automatic driving process, the vehicle locator of the unmanned driving fleet usually reports the received GPS positioning data at a fixed frequency. The control center controls the task vehicle to avoid obstacles and speed control according to the real-time GPS positioning data, so as to avoid congestion and other problems.

[0003] However, there are usually certain errors in various positioning methods. The vehicle-mounted locator generally communicates with the network through the cellular communication module of the SIM card. When the network signal is weak or there is no signal, it will cause delays or loss of positioning data transmission; there may be various electronic devices around the fixed dock, such as radio communication equipment, radar, etc. These devices may generate electromagnetic interference, affecting the reception and analysis of GPS signals, resulting in missing or abnormal positioning information; buildings, cargo stacking and other obstructions on the dock may block the GPS signal, making it impossible for the vehicle-mounted locator to receive enough satellite signals, resulting in missing or abnormal positioning information. GPS signals may be reflected and refracted multiple times, resulting in errors in signal propagation time, which in turn affects positioning accuracy. The low positioning accuracy of GPS signals has a greater impact on unmanned vehicle fleets, and will affect the detailed path planning of task vehicles in the fleet at the entire fleet level. Summary of the invention

[0004] In view of this, the purpose of this application is to provide a positioning data processing method for a terminal unmanned vehicle fleet, which can batch process the positioning data of the terminal unmanned vehicle fleet, discover abnormal positioning sections, thereby optimizing the planning process of the task path, and minimizing the positioning information anomalies in the task path.

[0005] An embodiment of the present application provides a method for processing positioning data of an unmanned vehicle fleet at a terminal, the method comprising:

[0006] Determine the preset task path data of the task vehicle in the unmanned vehicle fleet, send the preset task path data to the corresponding task vehicle, and upload the preset task path data of the task vehicle to the database;

[0007] Acquire real-time positioning data of the task vehicle in the unmanned vehicle fleet during the driving process according to the corresponding preset task path data, and report the real-time positioning data of the task vehicle to the database;

[0008] The database reads the real-time positioning data of the task vehicles in batches, and performs deviation correction processing on the real-time positioning data to obtain the real-time positioning data after deviation correction;

[0009] The real-time positioning data after deviation correction is updated back to the database, and a target index of the real-time positioning data of the task vehicle, the real-time positioning data after deviation correction, and the preset task path data is established;

[0010] Based on the target index, the real-time positioning data, the real-time positioning data after deviation correction, and the preset task path data of the task vehicle are read, and the real-time positioning data, the real-time positioning data after deviation correction, and the preset task path data of the task vehicle are processed to determine the abnormal positioning section, and determine multiple dimensional labels corresponding to the abnormal positioning section;

[0011] The located abnormal road section and the multiple dimensional tags corresponding to the abnormal corresponding road section are uploaded to the database, and the target index in the database is updated; the located abnormal road section and the corresponding multiple dimensional tags in the database are used to determine the preset task path data of the task vehicle in the unmanned driving fleet.

[0012] In some embodiments, in the positioning data processing method for the unmanned vehicle fleet at the terminal, the database batch reads the real-time positioning data of the task vehicles, and performs deviation correction processing on the real-time positioning data to obtain the corrected real-time positioning data, including:

[0013] The database reads the real-time positioning data of the task vehicles in batches, and cleans the batches of real-time positioning data based on a preset abnormal data processing rule to obtain cleaned real-time positioning data;

[0014] Determine whether there is a missing track point section in the cleaned real-time positioning data, and if so, perform interpolation processing on the missing track point section to obtain real-time positioning data after interpolation processing;

[0015] The real-time positioning data after interpolation processing is processed based on the preset correction algorithm, and the trajectory correction is performed to obtain the real-time positioning data after correction.

[0016] In some embodiments, in the positioning data processing method for the unmanned vehicle fleet at the terminal, the cleaning of the batch of real-time positioning data based on the preset abnormal data processing rules includes: determining whether the trajectory points in the real-time positioning data meet any one of a plurality of preset abnormal data processing rules;

[0017] If yes, the trajectory point is determined to be abnormal data, and the abnormal data is cleaned;

[0018] The plurality of preset abnormal data processing rules include:

[0019] Coordinates that exceed a preset threshold range of preset task path data; the preset threshold range of the preset task path data is determined based on map information of the wharf;

[0020] The track points of the real-time positioning data are repeatedly recorded;

[0021] The track point of the real-time positioning data is located in the restricted area of ​​the dock;

[0022] The moving speed of the task vehicle exceeds a preset speed threshold;

[0023] The change in the moving speed direction of the task vehicle meets the preset direction abnormality condition;

[0024] The distance between consecutive trajectory points in the real-time positioning data exceeds a preset spacing threshold.

[0025] In some embodiments, in the positioning data processing method of the unmanned driving fleet of the terminal, the real-time positioning data of the task vehicle, the real-time positioning data after correction, and the preset task path data are read based on the target index, and the real-time positioning data of the task vehicle, the real-time positioning data after correction, and the preset task path data are processed to determine the abnormal positioning section, and determine the multiple dimensional labels corresponding to the abnormal positioning section; including:

[0026] Connecting the database through a visualization tool, and reading the real-time positioning data of the task vehicle, the real-time positioning data after deviation correction, and the preset task path data based on the target index;

[0027] Processing the real-time positioning data of the task vehicle, the real-time positioning data after deviation correction, and the preset task path data, and determining the comparison results between the real-time positioning data and the real-time positioning data after deviation correction, the real-time positioning data and the preset task path data, and the real-time positioning data after deviation correction and the preset task path data;

[0028] Based on the comparison results, determine the positioning abnormal section where the deviation between the comparison results of the real-time positioning data and the real-time positioning data after deviation correction, the real-time positioning data and the preset task path data, and the real-time positioning data after deviation correction and the preset task path data meets the preset positioning deviation condition;

[0029] Acquire various types of information related to the located abnormal road section, extract multiple dimensional labels corresponding to the located abnormal road section, and determine the weight of each dimensional label; the weight represents the influence of the dimensional label on the located abnormal road section; the various types of information include: the attributes of the task vehicle, weather information, material stacking information, and lane information.

[0030] In some embodiments, in the positioning data processing method for the unmanned vehicle fleet at the terminal, determining the weight of each dimension label includes:

[0031] Obtain the number of abnormal positioning sections of the terminal that have reached a preset number threshold accumulated within a preset time period;

[0032] Performing a first clustering process on the abnormally positioned road sections that have reached a preset number threshold, and aggregating and determining the abnormally positioned road sections at the same location;

[0033] The dimension labels of each abnormally located road section at the same location are obtained, a second clustering process is performed on the obtained dimension labels, and the weights of different dimension labels of the abnormally located road sections at the same location are determined based on the second clustering process results.

[0034] In some embodiments, in the positioning data processing method of the unmanned driving fleet of the terminal, determining the preset task path data of the task vehicle in the unmanned driving fleet includes:

[0035] Determine multiple candidate mission route data based on the departure and destination locations of the mission vehicles in the driverless fleet;

[0036] Obtaining real-time dimension labels of the plurality of candidate task route data;

[0037] Retrieve the located abnormal road section of each candidate task route data based on the target index, and calculate the score of each candidate task route data based on the located abnormal road section, dimension label, weight of the dimension label in the retrieval result of each candidate task route data, and the real-time dimension labels of the multiple candidate task routes;

[0038] The candidate task route data with the highest score is determined as the preset task path data.

[0039] In some embodiments, the positioning data processing method of the unmanned vehicle fleet at the terminal further includes:

[0040] The comparison results between the real-time positioning data and the real-time positioning data after deviation correction, the real-time positioning data and the preset task path, and the real-time positioning data after deviation correction and the preset task path are displayed in the interface of the visualization tool.

[0041] In some embodiments, a positioning data processing device for an unmanned vehicle fleet at a terminal is also provided, the device comprising:

[0042] A first determination module is used to determine the preset task path data of the task vehicle in the unmanned vehicle fleet, send the preset task path data to the corresponding task vehicle, and upload the preset task path data of the task vehicle to the database;

[0043] A reporting module, used to obtain real-time positioning data of the task vehicle in the unmanned vehicle fleet during the driving process according to the corresponding preset task path data, and report the real-time positioning data of the task vehicle to the database;

[0044] A deviation correction module, used to enable the database to batch read the real-time positioning data of the task vehicles, and perform deviation correction processing on the real-time positioning data to obtain the real-time positioning data after deviation correction;

[0045] The first updating module is used to update the real-time positioning data after the deviation correction back to the database, and establish a target index of the real-time positioning data of the task vehicle, the real-time positioning data after the deviation correction, and the preset task path data;

[0046] A second determination module is used to read the real-time positioning data of the task vehicle, the real-time positioning data after deviation correction, and the preset task path data based on the target index, and process the real-time positioning data of the task vehicle, the real-time positioning data after deviation correction, and the preset task path data to determine the abnormal positioning section, and determine multiple dimensional labels corresponding to the abnormal positioning section;

[0047] The second updating module is used to upload the located abnormal road section and the multiple dimensional labels corresponding to the abnormal corresponding road section to the database, and update the target index in the database; the located abnormal road section and the corresponding multiple dimensional labels in the database are used to determine the preset task path data of the task vehicle in the unmanned driving fleet.

[0048] In some embodiments, an electronic device is also provided, including: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate through the bus, and when the machine-readable instructions are executed by the processor, the steps of the positioning data processing method of the terminal unmanned vehicle fleet are executed.

[0049] In some embodiments, a computer-readable storage medium stores a computer program, which, when executed by a processor, executes the steps of the positioning data processing method for the unmanned vehicle fleet at the terminal.

[0050] In an embodiment of the present application, a method for processing positioning data of an unmanned vehicle fleet at a terminal is provided, wherein the method determines preset task path data of a task vehicle in the unmanned vehicle fleet, sends the preset task path data to a corresponding task vehicle, and uploads the preset task path data of the task vehicle to a database; obtains real-time positioning data of the task vehicles in the unmanned vehicle fleet during the driving process according to the corresponding preset task path data, and reports the real-time positioning data of the task vehicles to a database; the database reads the real-time positioning data of the task vehicles in batches, and performs deviation correction processing on the real-time positioning data to obtain the corrected real-time positioning data; the corrected real-time positioning data is updated back to the database, and the real-time positioning data of the task vehicle, the corrected real-time positioning data, and the preset task path data are established. The target index of the database is updated; the real-time positioning data, the real-time positioning data after deviation correction, and the preset task path data of the task vehicle are read based on the target index, and the real-time positioning data, the real-time positioning data after deviation correction, and the preset task path data of the task vehicle are processed to determine the abnormal positioning section, and determine the multiple dimensional tags corresponding to the abnormal positioning section; the abnormal positioning section and the multiple dimensional tags corresponding to the abnormal corresponding section are uploaded to the database, and the target index in the database is updated; the abnormal positioning section and the corresponding multiple dimensional tags in the database are used to determine the preset task path data of the task vehicle in the unmanned driving fleet, so as to minimize the situation where the positioning data is sent and received abnormally when the task vehicle is driving in the preset task path, improve the positioning accuracy, and thus improve the precision of the path planning of the unmanned driving fleet at the terminal. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0052] Figure 1 A method flow chart of the positioning data processing method of the driverless fleet at the terminal according to the embodiment of the present application is shown;

[0053] Figure 2 A flow chart of a method for determining preset task path data of a task vehicle in an unmanned vehicle fleet according to an embodiment of the present application is shown;

[0054] Figure 3 A flow chart of a method for performing deviation correction processing on the real-time positioning data according to an embodiment of the present application is shown;

[0055] Figure 4A flow chart of a method for processing the real-time positioning data of the task vehicle, the real-time positioning data after deviation correction, and the preset task path data according to an embodiment of the present application is shown;

[0056] Figure 5 A schematic diagram of the structure of a positioning data processing device for an unmanned vehicle fleet at a terminal according to an embodiment of the present application is shown;

[0057] Figure 6 A schematic diagram of the structure of an electronic device described in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0058] To make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the drawings in the present application only serve the purpose of explanation and description and are not used to limit the scope of protection of the present application. In addition, it should be understood that the schematic drawings are not drawn in real proportion. The flowchart used in this application shows the operations implemented according to some embodiments of the present application. It should be understood that the operations of the flowchart can be implemented out of sequence, and the steps without logical context can be reversed in order or implemented simultaneously. In addition, those skilled in the art can add one or more other operations to the flowchart under the guidance of the content of the present application, or remove one or more operations from the flowchart.

[0059] In addition, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

[0060] It should be noted that the term "comprising" will be used in the embodiments of the present application to indicate the existence of the features declared thereafter, but does not exclude the addition of other features.

[0061] With the rapid development of Internet of Things technology, unmanned driving technology has been applied in many fields, such as logistics. In the field of logistics, unmanned driving fleets usually need to send the preset task path data of the task vehicle, and then during the automatic driving process, the vehicle locator of the unmanned driving fleet usually reports the received GPS positioning data at a fixed frequency. The control center controls the task vehicle to avoid obstacles and speed control according to the real-time GPS positioning data, so as to avoid congestion and other problems.

[0062] However, there are usually certain errors in various positioning methods. The vehicle-mounted locator generally communicates with the network through the cellular communication module of the SIM card. When the network signal is weak or there is no signal, it will cause delays or loss of positioning data transmission; there may be various electronic devices around the fixed dock, such as radio communication equipment, radar, etc. These devices may generate electromagnetic interference, affecting the reception and analysis of GPS signals, resulting in missing or abnormal positioning information; buildings, cargo stacking and other obstructions on the dock may block the GPS signal, making it impossible for the vehicle-mounted locator to receive enough satellite signals, resulting in missing or abnormal positioning information. GPS signals may be reflected and refracted multiple times, resulting in errors in signal propagation time, which in turn affects positioning accuracy. The low positioning accuracy of GPS signals has a greater impact on unmanned vehicle fleets, and will affect the detailed path planning of task vehicles in the fleet at the entire fleet level.

[0063] Based on this, in an embodiment of the present application, a method for processing positioning data of an unmanned vehicle fleet at a terminal is provided, the method determining preset task path data of a task vehicle in the unmanned vehicle fleet, sending the preset task path data to a corresponding task vehicle, and uploading the preset task path data of the task vehicle to a database; obtaining real-time positioning data of the task vehicles in the unmanned vehicle fleet during the driving process according to the corresponding preset task path data, and reporting the real-time positioning data of the task vehicles to a database; the database batch reads the real-time positioning data of the task vehicles, and performs deviation correction processing on the real-time positioning data to obtain the corrected real-time positioning data; the corrected real-time positioning data is updated back to the database, and the real-time positioning data of the task vehicle, the corrected real-time positioning data, and the preset task path are established. The target index of the data; based on the target index, the real-time positioning data, the real-time positioning data after correction, and the preset task path data of the task vehicle are read, and the real-time positioning data, the real-time positioning data after correction, and the preset task path data of the task vehicle are processed to determine the abnormal positioning section, and determine the multiple dimensional tags corresponding to the abnormal positioning section; upload the abnormal positioning section and the multiple dimensional tags corresponding to the abnormal corresponding section to the database, and update the target index in the database; the abnormal positioning section and the corresponding multiple dimensional tags in the database are used to determine the preset task path data of the task vehicle in the unmanned driving fleet, so as to minimize the abnormal sending and receiving of positioning data when the task vehicle is driving in the preset task path, improve the positioning accuracy, and thus improve the precision of the path planning of the unmanned driving fleet at the terminal.

[0064] Please refer to Figure 1 , Figure 1A method flow chart of a method for processing positioning data of a driverless terminal fleet according to an embodiment of the present application is shown; the positioning data processing method of the driverless terminal fleet comprises the following steps S101-S106:

[0065] S101, determining preset task path data of a task vehicle in the unmanned vehicle fleet, sending the preset task path data to a corresponding task vehicle, and uploading the preset task path data of the task vehicle to a database;

[0066] S102, obtaining real-time positioning data of a task vehicle in the unmanned vehicle fleet during its driving according to the corresponding preset task path data, and reporting the real-time positioning data of the task vehicle to a database;

[0067] S103, the database reads the real-time positioning data of the task vehicles in batches, and performs deviation correction processing on the real-time positioning data to obtain the real-time positioning data after deviation correction;

[0068] S104, updating the real-time positioning data after deviation correction back to the database, and establishing a target index of the real-time positioning data of the task vehicle, the real-time positioning data after deviation correction, and the preset task path data;

[0069] S105, reading the real-time positioning data of the task vehicle, the real-time positioning data after deviation correction, and the preset task path data based on the target index, and processing the real-time positioning data of the task vehicle, the real-time positioning data after deviation correction, and the preset task path data to determine the abnormal positioning section, and determine multiple dimensional labels corresponding to the abnormal positioning section;

[0070] S106. Upload the located abnormal road section and the multiple dimensional tags corresponding to the abnormal corresponding road section to the database, and update the target index in the database; the located abnormal road section and the corresponding multiple dimensional tags in the database are used to determine the preset task path data of the task vehicle in the unmanned driving fleet.

[0071] In the step S101, the preset task path data of the task vehicle in the unmanned vehicle fleet is determined, the preset task path data is sent to the corresponding task vehicle, and the preset task path data of the task vehicle is uploaded to the database.

[0072] It should be noted that the database of this application is constantly updated and improved.

[0073] Therefore, please refer to Figure 2 In the embodiment of the present application, determining the preset task path data of the task vehicle in the unmanned vehicle fleet includes the following steps S201-S204:

[0074] S201, determining a plurality of candidate task route data based on the departure position and destination position of the task vehicle in the unmanned vehicle fleet;

[0075] S202, obtaining real-time dimension labels of the plurality of candidate task route data;

[0076] S203, retrieving the located abnormal road section of each candidate task route data based on the target index, and calculating the score of each candidate task route data based on the located abnormal road section, dimension label, weight of the dimension label in the retrieval result of each candidate task route data, and the real-time dimension labels of the multiple candidate task routes;

[0077] S204: Determine the candidate task route data with the highest score as the preset task path data.

[0078] Here, the different candidate task route data may be different routes passed through, or different specific selected lanes. In other words, the task route planned in the embodiment of the present application is specific to the impact of different lanes on the positioning signal.

[0079] The dimension tags include: attributes of the mission vehicle, weather, material stacking, lanes, etc. The attributes of the mission vehicle, weather, logistics, lanes, etc. will indeed affect the positioning accuracy of the vehicle-mounted locator.

[0080] Specifically, different types of vehicles have different structures and heights, which may affect the reception of GPS signals. For example, large trucks, due to their higher bodies, may be more easily blocked by obstacles such as trees and buildings, thus affecting positioning accuracy. The electromagnetic environment inside the vehicle is complex, including electromagnetic radiation generated by the engine, electronic equipment, etc., which may interfere with GPS signals and reduce positioning accuracy. The installation location of the GPS device will also affect its ability to receive signals.

[0081] Severe weather conditions (such as rain, snow, fog, etc.) can weaken the strength of GPS signals, making it more difficult for the locator to receive a strong enough signal to accurately determine the location.

[0082] The materials stacked at the dock have a great impact on the positioning accuracy. For example, large metal or high-density materials are likely to block the GPS signal. In areas where materials are densely stacked, the GPS signal may be seriously interfered with. Metal materials may generate electromagnetic interference. This interference will affect the normal operation of the GPS receiver. The stacking of dock materials may change the local environment, such as topography and landforms. These changes may affect the propagation path and speed of the GPS signal, thereby affecting the positioning accuracy.

[0083] Due to the stacking of materials at the dock, the ground structure is complex, so the positioning accuracy of different lanes may be different.

[0084] Based on this, in an embodiment of the present application, real-time dimensional labels of the multiple candidate task route data are obtained to determine the real-time status of the multiple candidate task route data, so as to determine the route with the highest positioning accuracy in real time.

[0085] In the step S102, the real-time positioning data of the task vehicle in the unmanned vehicle fleet during the driving process according to the corresponding preset task path data is obtained, and the real-time positioning data of the task vehicle is reported to the database.

[0086] The real-time positioning data of the mission vehicle is reported to the database. Specifically, the vehicle-mounted locator usually reports the received GPS positioning data at a fixed frequency, for example, once every second or every 10 seconds. Due to its time series characteristics, high writing frequency and potential massive scale, positioning data usually uses a database that can efficiently process such data, such as the time series database TDengine, InfluxDB, or the column storage database HBase.

[0087] The real-time positioning data includes: longitude and latitude information, timestamp, etc.

[0088] The longitude and latitude information is obtained through the GPS receiver. The GPS system can provide the longitude and latitude coordinates of the vehicle in real time, thereby determining the precise position of the vehicle in the global positioning system.

[0089] The timestamp records the specific time of data collection for subsequent data analysis and processing. The timestamp ensures the timeliness and accuracy of the data.

[0090] In step S103, the database reads the real-time positioning data of the task vehicles in batches, and performs deviation correction processing on the real-time positioning data to obtain the corrected real-time positioning data.

[0091] Please refer to Figure 3 The database batch reads the real-time positioning data of the task vehicles, and performs deviation correction processing on the real-time positioning data to obtain the corrected real-time positioning data, including the following steps S301-S303:

[0092] S301, the database reads the real-time positioning data of the task vehicles in batches, and cleans the batches of real-time positioning data based on a preset abnormal data processing rule to obtain cleaned real-time positioning data;

[0093] S302, determining whether there is a section where track points are missing in the cleaned real-time positioning data, and if so, performing interpolation processing on the section where track points are missing to obtain real-time positioning data after interpolation processing;

[0094] S303: Process the real-time positioning data after interpolation processing based on a preset correction algorithm, perform trajectory correction, and obtain the real-time positioning data after correction.

[0095] The batch of real-time positioning data is cleaned, that is, outliers are removed. Specifically, obviously erroneous positioning points are identified and removed, such as records of abnormally fast speeds and exceeding reasonable geographical ranges.

[0096] Interpolation processing: For parts where data is missing or sparse, linear interpolation, spline interpolation and other methods can be used to supplement the missing trajectory points.

[0097] The real-time positioning data after interpolation processing is processed based on the preset correction algorithm, and the trajectory correction is performed to obtain the real-time positioning data after correction. Specifically, the positioning data after input cleaning and difference processing is combined with the Bayesian filtering algorithm + map matching (Map Matching) and other methods to perform trajectory correction.

[0098] The cleaning of the batch of real-time positioning data based on the preset abnormal data processing rules includes: determining whether the trajectory points in the real-time positioning data meet any one of a plurality of preset abnormal data processing rules;

[0099] If yes, the trajectory point is determined to be abnormal data, and the abnormal data is cleaned;

[0100] The plurality of preset abnormal data processing rules include:

[0101] Coordinates that exceed a preset threshold range of preset task path data; the preset threshold range of the preset task path data is determined based on map information of the wharf;

[0102] The track points of the real-time positioning data are repeatedly recorded;

[0103] The track point of the real-time positioning data is located in the restricted area of ​​the dock;

[0104] The moving speed of the task vehicle exceeds a preset speed threshold;

[0105] The change in the moving speed direction of the task vehicle meets the preset direction abnormality condition;

[0106] The distance between consecutive trajectory points in the real-time positioning data exceeds a preset spacing threshold.

[0107] When the track points of the real-time positioning data are recorded repeatedly, one record is retained.

[0108] The trajectory point of the real-time positioning data is located in the port restricted area. Specifically, if the positioning data shows that the vehicle has passed through the port restricted area (such as water area, inside a building, or a closed area), the data is judged to be invalid.

[0109] The dock restricted area refers to the area in the dock where mission vehicles cannot pass.

[0110] The moving speed of the task vehicle exceeds the preset speed threshold, and the change in the moving speed direction of the task vehicle meets the preset direction abnormality condition, that is, the speed and direction of the task vehicle are checked. If the moving speed of the vehicle or object exceeds the physically possible maximum value, or the direction change is not in line with common sense (such as a sudden large turn), there may be problems with the data and the data is invalid.

[0111] If the distance between consecutive track points in the real-time positioning data exceeds the preset spacing threshold, a track point continuity check is performed. The distance between consecutive positioning points should be reasonable. If there is a jump between two points that is too large or too small, it may be caused by GPS drift or signal interference, and the data is invalid.

[0112] In step S104, the real-time positioning data after deviation correction is updated back to the database, and a target index of the real-time positioning data of the task vehicle, the real-time positioning data after deviation correction, and the preset task path data is established.

[0113] In the subsequent path planning, these data need to be called. Therefore, according to the query requirements, it is necessary to establish appropriate indexes for the real-time positioning data of the task vehicle, the real-time positioning data after correction, and the preset task path data to accelerate subsequent queries and analysis.

[0114] In the embodiment of the present application, when establishing the target index, the road ID index of the wharf is established, and then the timestamp index, vehicle ID index, start / end point index of the preset task path data, etc. are established.

[0115] In the step S105, the real-time positioning data, the real-time positioning data after correction, and the preset task path data of the task vehicle are read based on the target index, and the real-time positioning data, the real-time positioning data after correction, and the preset task path data of the task vehicle are processed to determine the abnormally located road section, and determine multiple dimensional labels corresponding to the abnormally located road section.

[0116] For details, please refer to Figure 4 , Figure 4A flow chart of a method for processing the real-time positioning data of the task vehicle, the real-time positioning data after correction, and the preset task path data according to an embodiment of the present application is shown; specifically, the real-time positioning data of the task vehicle, the real-time positioning data after correction, and the preset task path data are read based on the target index, and the real-time positioning data of the task vehicle, the real-time positioning data after correction, and the preset task path data are processed to determine the abnormal positioning section, and determine multiple dimensional labels corresponding to the abnormal positioning section; the following steps S401-S404 are included:

[0117] S401, connecting to the database through a visualization tool, and reading the real-time positioning data of the task vehicle, the real-time positioning data after deviation correction, and the preset task path data based on the target index;

[0118] S402, processing the real-time positioning data of the task vehicle, the real-time positioning data after deviation correction, and the preset task path data, and determining the comparison results between the real-time positioning data and the real-time positioning data after deviation correction, the real-time positioning data and the preset task path data, and the real-time positioning data after deviation correction and the preset task path data;

[0119] S403, based on the comparison result, determining a positioning abnormal section where the deviation between the comparison results of the real-time positioning data and the real-time positioning data after deviation correction, the real-time positioning data and the preset task path data, and the real-time positioning data after deviation correction and the preset task path data meets the preset positioning deviation condition;

[0120] S404. Acquire various types of information related to the located abnormal road section, extract multiple dimensional labels corresponding to the located abnormal road section, and determine the weight of each dimensional label; the weight represents the influence of the dimensional label on the located abnormal road section; the various types of information include: the attributes of the task vehicle, weather information, material stacking information, and lane information.

[0121] Determine the weight of each dimension label, including:

[0122] Obtain the number of abnormal positioning sections of the terminal that have reached a preset number threshold accumulated within a preset time period;

[0123] Performing a first clustering process on the abnormally positioned road sections that have reached a preset number threshold, and aggregating and determining the abnormally positioned road sections at the same location;

[0124] The dimension labels of each abnormally located road section at the same location are obtained, a second clustering process is performed on the obtained dimension labels, and the weights of different dimension labels of the abnormally located road sections at the same location are determined based on the second clustering process results.

[0125] That is to say, the first clustering process finds the abnormally located road section, section A and section B, at each location from a large amount of various abnormally located road section information.

[0126] The second clustering process is to analyze the reasons affecting the GPS signal accuracy of the abnormal positioning section at each location.

[0127] Specifically, the visualization tool uses Grafana. Grafana integrates the database TDengine to visualize and analyze the positioning data and trajectories, as follows:

[0128] 1) Install the TDengine data source plug-in in the Grafana environment

[0129] 2) Add TDengine data source

[0130] Log in to the Grafana interface and perform the following operations:

[0131] Configuration->Data Sources. Click the "Add data source" button. Select the TDengine plugin from the list. Fill in the connection information, including the address, port, database name, username and password of the TDengine server. Click "Save&Test" to verify that the connection is successful. 3) Create dashboards and queries

[0132] Create a new dashboard or open an existing dashboard. Add a new Panel. In the Query Editor, select the TDengine data source you just added. Write an SQL query based on the structure of the positioning data. For example, the positioning data is stored in a table called location_track and contains timestamp (ts), longitude (longitude) and latitude (latitude) fields. You can write the following query to obtain positioning records within a period of time: In some embodiments, the positioning data processing method of the unmanned vehicle fleet at the terminal, the method also includes:

[0133] The comparison results between the real-time positioning data and the real-time positioning data after deviation correction, the real-time positioning data and the preset task path, and the real-time positioning data after deviation correction and the preset task path are displayed in the interface of the visualization tool.

[0134] In this way, the correction effect and the execution results of the preset task path can be evaluated in an intuitive way.

[0135] In step S106, the located abnormal road section and multiple dimensional tags corresponding to the abnormal corresponding road section are uploaded to the database, and the target index in the database is updated; the located abnormal road section and the corresponding multiple dimensional tags in the database are used to determine the preset task path data of the task vehicle in the unmanned driving fleet.

[0136] In this way, the database described in the embodiments of the present application is becoming more and more complete, and the positioning accuracy prediction of each section of the terminal under various circumstances is becoming more and more accurate, thereby more accurately performing detailed path planning for the task vehicles in the fleet at the entire fleet level.

[0137] Based on the same inventive concept, the embodiment of the present application also provides a positioning data processing device for a terminal unmanned vehicle fleet corresponding to the positioning data processing method for a terminal unmanned vehicle fleet. Since the principle of solving the problem by the device in the embodiment of the present application is similar to the positioning data processing method for the terminal unmanned vehicle fleet in the embodiment of the present application, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be repeated.

[0138] Please refer to Figure 5 , Figure 5 The schematic diagram of the structure of the positioning data processing device of the driverless terminal fleet described in the embodiment of the present application is shown; the device includes:

[0139] The first determination module 501 is used to determine the preset task path data of the task vehicle in the unmanned vehicle fleet, send the preset task path data to the corresponding task vehicle, and upload the preset task path data of the task vehicle to the database;

[0140] The reporting module 502 is used to obtain the real-time positioning data of the task vehicle in the unmanned vehicle fleet during the driving process according to the corresponding preset task path data, and report the real-time positioning data of the task vehicle to the database;

[0141] A deviation correction module 503 is used to enable the database to batch read the real-time positioning data of the task vehicle, and perform deviation correction processing on the real-time positioning data to obtain the real-time positioning data after deviation correction;

[0142] The first updating module 504 is used to update the real-time positioning data after deviation correction back to the database, and establish a target index of the real-time positioning data of the task vehicle, the real-time positioning data after deviation correction, and the preset task path data;

[0143] The second determination module 505 is used to read the real-time positioning data of the task vehicle, the real-time positioning data after correction, and the preset task path data based on the target index, and process the real-time positioning data of the task vehicle, the real-time positioning data after correction, and the preset task path data to determine the abnormal positioning section, and determine multiple dimensional labels corresponding to the abnormal positioning section;

[0144] The second update module 506 is used to upload the located abnormal road section and the multiple dimensional tags corresponding to the abnormal corresponding road section to the database, and update the target index in the database; the located abnormal road section and the corresponding multiple dimensional tags in the database are used to determine the preset task path data of the task vehicle in the unmanned driving fleet.

[0145] In some embodiments, in the positioning data processing device for the unmanned vehicle fleet at the wharf, the deviation correction module, when enabling the database to batch read the real-time positioning data of the task vehicles and performing deviation correction processing on the real-time positioning data to obtain the corrected real-time positioning data, is specifically used to:

[0146] The database reads the real-time positioning data of the task vehicles in batches, and cleans the batches of real-time positioning data based on a preset abnormal data processing rule to obtain cleaned real-time positioning data;

[0147] Determine whether there is a missing track point section in the cleaned real-time positioning data, and if so, perform interpolation processing on the missing track point section to obtain real-time positioning data after interpolation processing;

[0148] The real-time positioning data after interpolation processing is processed based on the preset correction algorithm, and the trajectory correction is performed to obtain the real-time positioning data after correction.

[0149] In some embodiments, in the positioning data processing device of the unmanned vehicle fleet at the wharf, the deviation correction module, when cleaning the batch of real-time positioning data based on the preset abnormal data processing rules, is specifically used to: determine whether the trajectory point in the real-time positioning data satisfies any one of a plurality of preset abnormal data processing rules;

[0150] If yes, the trajectory point is determined to be abnormal data, and the abnormal data is cleaned;

[0151] The plurality of preset abnormal data processing rules include:

[0152] Coordinates that exceed a preset threshold range of preset task path data; the preset threshold range of the preset task path data is determined based on map information of the wharf;

[0153] The track points of the real-time positioning data are repeatedly recorded;

[0154] The track point of the real-time positioning data is located in the restricted area of ​​the dock;

[0155] The moving speed of the task vehicle exceeds a preset speed threshold;

[0156] The change in the moving speed direction of the task vehicle meets the preset direction abnormality condition;

[0157] The distance between consecutive trajectory points in the real-time positioning data exceeds a preset spacing threshold.

[0158] In some embodiments, in the positioning data processing device of the unmanned driving fleet of the terminal, the second determination module, when reading the real-time positioning data of the task vehicle, the real-time positioning data after correction, and the preset task path data based on the target index, and processing the real-time positioning data of the task vehicle, the real-time positioning data after correction, and the preset task path data, determines the abnormal positioning section, and determines multiple dimensional labels corresponding to the abnormal positioning section, is specifically used to:

[0159] Connecting the database through a visualization tool, and reading the real-time positioning data of the task vehicle, the real-time positioning data after deviation correction, and the preset task path data based on the target index;

[0160] Processing the real-time positioning data of the task vehicle, the real-time positioning data after deviation correction, and the preset task path data, and determining the comparison results between the real-time positioning data and the real-time positioning data after deviation correction, the real-time positioning data and the preset task path data, and the real-time positioning data after deviation correction and the preset task path data;

[0161] Based on the comparison results, determine the positioning abnormal section where the deviation between the comparison results of the real-time positioning data and the real-time positioning data after deviation correction, the real-time positioning data and the preset task path data, and the real-time positioning data after deviation correction and the preset task path data meets the preset positioning deviation condition;

[0162] Acquire various types of information related to the located abnormal road section, extract multiple dimensional labels corresponding to the located abnormal road section, and determine the weight of each dimensional label; the weight represents the influence of the dimensional label on the located abnormal road section; the various types of information include: the attributes of the task vehicle, weather information, material stacking information, and lane information.

[0163] In some embodiments, in the positioning data processing device for the unmanned vehicle fleet at the terminal, the second determination module, when determining the weight of each dimensional label, is specifically used to:

[0164] Obtain the number of abnormal positioning sections of the terminal that have reached a preset number threshold accumulated within a preset time period;

[0165] Performing a first clustering process on the abnormally positioned road sections that have reached a preset number threshold, and aggregating and determining the abnormally positioned road sections at the same location;

[0166] The dimension labels of each abnormally located road section at the same location are obtained, a second clustering process is performed on the obtained dimension labels, and the weights of different dimension labels of the abnormally located road sections at the same location are determined based on the second clustering process results.

[0167] In some embodiments, in the positioning data processing device for the unmanned driving fleet of the terminal, the second determination module and the first determination module, when determining the preset task path data of the task vehicle in the unmanned driving fleet, are specifically used to:

[0168] Determine multiple candidate mission route data based on the departure and destination locations of the mission vehicles in the driverless fleet;

[0169] Obtaining real-time dimension labels of the plurality of candidate task route data;

[0170] Retrieve the located abnormal road section of each candidate task route data based on the target index, and calculate the score of each candidate task route data based on the located abnormal road section, dimension label, weight of the dimension label in the retrieval result of each candidate task route data, and the real-time dimension labels of the multiple candidate task routes;

[0171] The candidate task route data with the highest score is determined as the preset task path data.

[0172] In some embodiments, the positioning data processing device for the unmanned vehicle fleet at the terminal further includes:

[0173] The display module is used to display the comparison results between the real-time positioning data and the real-time positioning data after correction, the real-time positioning data and the preset task path, and the real-time positioning data after correction and the preset task path in the interface of the visualization tool.

[0174] Based on the same inventive concept, an electronic device corresponding to the positioning data processing method for the unmanned vehicle fleet at the terminal is also provided in the embodiment of the present application. Since the principle of solving the problem by the electronic device in the embodiment of the present application is similar to the positioning data processing method for the unmanned vehicle fleet at the terminal in the embodiment of the present application, the implementation of the electronic device can refer to the implementation of the method, and the repeated parts will not be repeated.

[0175] Please refer to Figure 6 , Figure 6A schematic diagram of the structure of the electronic device described in an embodiment of the present application is shown; the electronic device 600 includes: a processor 602, a memory 601 and a bus, the memory 601 stores machine-readable instructions executable by the processor 602, and when the electronic device 600 is running, the processor 602 communicates with the memory 601 through the bus, and when the machine-readable instructions are executed by the processor 602, the steps of the positioning data processing method for the unmanned terminal fleet are executed.

[0176] Based on the same inventive concept, a computer-readable storage medium corresponding to a positioning data processing method for a driverless fleet at a terminal is also provided in an embodiment of the present application. Since the principle of solving the problem by the computer-readable storage medium in the embodiment of the present application is similar to the positioning data processing method for a driverless fleet at a terminal in the embodiment of the present application, the implementation of the computer-readable storage medium can refer to the implementation of the method, and the repeated parts will not be repeated.

[0177] A computer-readable storage medium stores a computer program, which, when executed by a processor, executes the steps of the positioning data processing method for a driverless terminal fleet.

[0178] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, the specific working process of the system and device described above can refer to the corresponding process in the method embodiment, and will not be repeated in this application. In the several embodiments provided in this application, it should be understood that the disclosed system, device and method can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation. For example, multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.

[0179] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0180] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0181] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium that is executable by a processor. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a platform server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard drives, ROM, RAM, magnetic disks, or optical disks.

[0182] The above are only specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for processing positioning data of an unmanned vehicle fleet at a terminal, characterized in that: The method comprises: Determine the preset task path data of the task vehicle in the unmanned vehicle fleet, send the preset task path data to the corresponding task vehicle, and upload the preset task path data of the task vehicle to the database; Acquire real-time positioning data of the task vehicle in the unmanned vehicle fleet during the driving process according to the corresponding preset task path data, and report the real-time positioning data of the task vehicle to the database; The database reads the real-time positioning data of the task vehicles in batches, and performs deviation correction processing on the real-time positioning data to obtain the real-time positioning data after deviation correction; The real-time positioning data after deviation correction is updated back to the database, and a target index of the real-time positioning data of the task vehicle, the real-time positioning data after deviation correction, and the preset task path data is established; Based on the target index, the real-time positioning data, the real-time positioning data after deviation correction, and the preset task path data of the task vehicle are read, and the real-time positioning data, the real-time positioning data after deviation correction, and the preset task path data of the task vehicle are processed to determine the abnormal positioning section, and determine multiple dimensional labels corresponding to the abnormal positioning section; The abnormal road section located and the multiple dimensional tags corresponding to the abnormal corresponding road section are uploaded to the database, and the target index in the database is updated; the abnormal road section located and the corresponding multiple dimensional tags in the database are used to determine the preset task path data of the task vehicle in the unmanned driving fleet; The method comprises: reading the real-time positioning data of the task vehicle, the real-time positioning data after deviation correction, and the preset task path data based on the target index, and processing the real-time positioning data of the task vehicle, the real-time positioning data after deviation correction, and the preset task path data to determine the abnormal positioning section, and determine multiple dimensional labels corresponding to the abnormal positioning section; comprising: Connecting the database through a visualization tool, and reading the real-time positioning data of the task vehicle, the real-time positioning data after deviation correction, and the preset task path data based on the target index; Processing the real-time positioning data of the task vehicle, the real-time positioning data after deviation correction, and the preset task path data, and determining the comparison results between the real-time positioning data and the real-time positioning data after deviation correction, the real-time positioning data and the preset task path data, and the real-time positioning data after deviation correction and the preset task path data; Based on the comparison results, determine the positioning abnormal section where the deviation between the comparison results of the real-time positioning data and the real-time positioning data after deviation correction, the real-time positioning data and the preset task path data, and the real-time positioning data after deviation correction and the preset task path data meets the preset positioning deviation condition; Acquire various types of information related to the abnormally located road section, extract multiple dimensional labels corresponding to the abnormally located road section, and determine the weight of each dimensional label; the weight represents the degree of influence of the dimensional label on the abnormally located road section; the various types of information include: the attributes of the task vehicle, weather information, material stacking information, and lane information; Determining the weight of each dimension label includes: Obtain the number of abnormal positioning sections of the terminal that have reached a preset number threshold accumulated within a preset time period; Performing a first clustering process on the abnormally positioned road sections that have reached a preset number threshold, and aggregating and determining the abnormally positioned road sections at the same location; Obtaining the dimensional labels of each abnormally positioned road section at the same location, performing a second clustering process on the obtained dimensional labels, and determining the weights of different dimensional labels of the abnormally positioned road sections at the same location based on the second clustering process results; The step of determining preset task path data of a task vehicle in the unmanned vehicle fleet includes: Determine multiple candidate mission route data based on the departure and destination locations of the mission vehicles in the driverless fleet; Obtaining real-time dimension labels of the plurality of candidate task route data; Retrieve the located abnormal road section of each candidate task route data based on the target index, and calculate the score of each candidate task route data based on the located abnormal road section, dimension label, weight of the dimension label in the retrieval result of each candidate task route data, and the real-time dimension labels of the plurality of candidate task route data; The candidate task route data with the highest score is determined as the preset task path data.

2. The positioning data processing method of the unmanned vehicle fleet at the terminal according to claim 1 is characterized in that: The database batch reads the real-time positioning data of the task vehicle, and performs deviation correction processing on the real-time positioning data to obtain the real-time positioning data after deviation correction, including: The database reads the real-time positioning data of the task vehicles in batches, and cleans the batches of real-time positioning data based on a preset abnormal data processing rule to obtain cleaned real-time positioning data; Determine whether there is a missing track point section in the cleaned real-time positioning data, and if so, perform interpolation processing on the missing track point section to obtain real-time positioning data after interpolation processing; The real-time positioning data after interpolation processing is processed based on the preset correction algorithm, and the trajectory correction is performed to obtain the real-time positioning data after correction.

3. The positioning data processing method for the unmanned vehicle fleet at a terminal according to claim 2, characterized in that: The cleaning of the batch of real-time positioning data based on the preset abnormal data processing rules includes: determining whether the trajectory points in the real-time positioning data meet any one of a plurality of preset abnormal data processing rules; If yes, the trajectory point is determined to be abnormal data, and the abnormal data is cleaned; The plurality of preset abnormal data processing rules include: Coordinates that exceed a preset threshold range of preset task path data; the preset threshold range of the preset task path data is determined based on map information of the wharf; The track points of the real-time positioning data are repeatedly recorded; The track point of the real-time positioning data is located in the restricted area of ​​the dock; The moving speed of the task vehicle exceeds a preset speed threshold; The change in the moving speed direction of the task vehicle meets the preset direction abnormality condition; The distance between consecutive trajectory points in the real-time positioning data exceeds a preset distance threshold.

4. The method for processing positioning data of a driverless terminal fleet according to claim 1, characterized in that: The method further comprises: The comparison results between the real-time positioning data and the real-time positioning data after deviation correction, the real-time positioning data and the preset task path, and the real-time positioning data after deviation correction and the preset task path are displayed in the interface of the visualization tool.

5. A positioning data processing device for an unmanned vehicle fleet at a terminal, characterized in that: The device comprises: A first determination module is used to determine the preset task path data of the task vehicle in the unmanned vehicle fleet, send the preset task path data to the corresponding task vehicle, and upload the preset task path data of the task vehicle to the database; A reporting module, used to obtain real-time positioning data of the task vehicle in the unmanned vehicle fleet during the driving process according to the corresponding preset task path data, and report the real-time positioning data of the task vehicle to the database; A deviation correction module, used to enable the database to batch read the real-time positioning data of the task vehicles, and perform deviation correction processing on the real-time positioning data to obtain the real-time positioning data after deviation correction; The first updating module is used to update the real-time positioning data after the deviation correction back to the database, and establish a target index of the real-time positioning data of the task vehicle, the real-time positioning data after the deviation correction, and the preset task path data; A second determination module is used to read the real-time positioning data of the task vehicle, the real-time positioning data after deviation correction, and the preset task path data based on the target index, and process the real-time positioning data of the task vehicle, the real-time positioning data after deviation correction, and the preset task path data to determine the abnormal positioning section, and determine multiple dimensional labels corresponding to the abnormal positioning section; A second updating module is used to upload the located abnormal road section and the multiple dimensional tags corresponding to the abnormal corresponding road section to the database, and update the target index in the database; the located abnormal road section and the corresponding multiple dimensional tags in the database are used to determine the preset task path data of the task vehicle in the unmanned driving fleet; The method comprises: reading the real-time positioning data of the task vehicle, the real-time positioning data after deviation correction, and the preset task path data based on the target index, and processing the real-time positioning data of the task vehicle, the real-time positioning data after deviation correction, and the preset task path data to determine the abnormal positioning section, and determine multiple dimensional labels corresponding to the abnormal positioning section; comprising: Connecting the database through a visualization tool, and reading the real-time positioning data of the task vehicle, the real-time positioning data after deviation correction, and the preset task path data based on the target index; Processing the real-time positioning data of the task vehicle, the real-time positioning data after deviation correction, and the preset task path data, and determining the comparison results between the real-time positioning data and the real-time positioning data after deviation correction, the real-time positioning data and the preset task path data, and the real-time positioning data after deviation correction and the preset task path data; Based on the comparison results, determine the positioning abnormal section where the deviation between the comparison results of the real-time positioning data and the real-time positioning data after deviation correction, the real-time positioning data and the preset task path data, and the real-time positioning data after deviation correction and the preset task path data meets the preset positioning deviation condition; Acquire various types of information related to the abnormally located road section, extract multiple dimensional labels corresponding to the abnormally located road section, and determine the weight of each dimensional label; the weight represents the degree of influence of the dimensional label on the abnormally located road section; the various types of information include: the attributes of the task vehicle, weather information, material stacking information, and lane information; Determining the weight of each dimension label includes: Obtain the number of abnormal positioning sections of the terminal that have reached a preset number threshold accumulated within a preset time period; Performing a first clustering process on the abnormally positioned road sections that have reached a preset number threshold, and aggregating and determining the abnormally positioned road sections at the same location; Obtaining the dimensional labels of each abnormally positioned road section at the same location, performing a second clustering process on the obtained dimensional labels, and determining the weights of different dimensional labels of the abnormally positioned road sections at the same location based on the second clustering process results; The step of determining preset task path data of a task vehicle in the unmanned vehicle fleet includes: Determine multiple candidate mission route data based on the departure and destination locations of the mission vehicles in the driverless fleet; Obtaining real-time dimension labels of the plurality of candidate task route data; Retrieve the located abnormal road section of each candidate task route data based on the target index, and calculate the score of each candidate task route data based on the located abnormal road section, dimension label, weight of the dimension label in the retrieval result of each candidate task route data, and the real-time dimension labels of the plurality of candidate task route data; The candidate task route data with the highest score is determined as the preset task path data.

6. An electronic device, characterized in that: include: A processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor. When the electronic device is running, the processor communicates with the memory via the bus. When the machine-readable instructions are executed by the processor, the steps of the positioning data processing method for the driverless terminal fleet are performed as described in any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which, when executed by a processor, executes the steps of the method for processing positioning data of an unmanned terminal fleet as described in any one of claims 1 to 4.

Images