Vehicle weak network data correction method and device, electronic equipment and readable storage medium

Abstract

The invention relates to a vehicle weak network data correction method and device, electronic equipment and a readable storage medium. The method comprises the following steps: detecting the network strength of a positioning signal of a vehicle, and generating a correction instruction when the network strength of the positioning signal is lower than a preset threshold value; according to the correction instruction, determining a target roadside device having a spatial overlapping sensing area with the vehicle; acquiring real-time sensing data acquired by the vehicle and reference sensing data acquired by the target roadside equipment, and comparing characteristic parameters of at least one same environment target in the real-time sensing data and the reference sensing data to obtain a deviation value of the characteristic parameters; and when the deviation value of the characteristic parameter exceeds a preset error threshold value, calculating a positioning error vector of the vehicle relative to the target roadside equipment, and performing parameter correction on the vehicle positioning information of the vehicle through the positioning error vector. According to the scheme provided by the invention, the positioning precision of the vehicle in the weak network environment can be improved, the problem of error accumulation in the prediction method is eliminated, and the vehicle driving safety is improved.

Description

Technical Field

[0001] This application relates to the field of intelligent connected transportation technology, and in particular to a method, apparatus, electronic device, and readable storage medium for correcting weak network data of vehicles. Background Technology

[0002] With the development of intelligent connected vehicle technology, vehicle positioning accuracy directly affects driving safety. Currently, vehicle positioning systems mainly rely on onboard satellite positioning signals to calculate pose. However, in weak network environments such as urban canyons and tunnels, positioning signals are weakened due to obstruction or interference, causing vehicles to lose their high-precision positioning capabilities.

[0003] In related technologies, inertial navigation systems (INS) are commonly used to predict vehicle position. However, inferring the current position of a vehicle based on its historical motion state is essentially a prediction rather than a measurement. This can easily lead to the accumulation of errors in vehicle position calculation over time, resulting in inaccurate calculation of the relative pose of environmental targets in global coordinates under weak network conditions, which affects decision-making safety during driving. Summary of the Invention

[0004] To address or partially address the problems existing in related technologies, this application provides a vehicle weak network data correction method, apparatus, electronic device, and readable storage medium, which can improve vehicle positioning accuracy in weak network environments, reduce error accumulation, and improve driving safety.

[0005] The first aspect of this application provides a method for correcting weak network data in vehicles, including: The network strength of the vehicle's positioning signal is detected, and when the network strength of the positioning signal is lower than a preset threshold, a correction command is generated. Based on the correction instruction, a target roadside device with a spatially overlapping sensing area with the vehicle is identified; The system acquires real-time perception data collected by the vehicle and baseline perception data collected by the target roadside equipment, compares the feature parameters of at least one identical environmental target in the real-time perception data and the baseline perception data, and obtains the deviation of the feature parameters. When the deviation of the feature parameter exceeds the preset error threshold, the positioning error vector of the vehicle relative to the target roadside equipment is calculated, and the vehicle positioning information of the vehicle is corrected by the positioning error vector.

[0006] In some implementations, the detection of the network strength of the vehicle's positioning signal, when the network strength of the positioning signal is lower than a preset threshold, generates a correction instruction, including: The first network strength of the vehicle's current location signal is detected; When the first network strength is lower than the first preset strength threshold, the second network strength of the vehicle in an adjacent preset time period is obtained; wherein, the second network strength includes: the minimum strength value or the average strength value of the vehicle positioning signal in an adjacent preset time period; When the strength of the second network is lower than the second preset strength threshold, a correction instruction is generated.

[0007] In some embodiments, before generating a correction instruction when the network strength of the location signal of the detected vehicle is lower than a preset threshold, the method further includes: Obtain the current vehicle location information; The current vehicle location information is matched with the pre-stored signal distribution map information. When the vehicle is determined to have entered a preset signal obstruction area based on the matching result, a network strength detection command is generated so that the vehicle can perform network strength detection according to the network strength detection command.

[0008] In some embodiments, the target roadside device for determining the sensing area that spatially overlaps with the vehicle includes: Based on the vehicle positioning signal, the real-time location information of the vehicle is determined, and a target roadside device that meets the preset conditions is selected from the roadside end devices in the sensing area that has spatial overlap with the vehicle according to the real-time location information of the vehicle. The preset conditions include: meeting preset distance conditions and / or meeting network stability conditions.

[0009] In some implementations, the characteristic parameters include: The coordinates and heading angles of at least one identical environmental target in the vehicle coordinate system and the roadside coordinate system, respectively.

[0010] In some implementations, when the deviation of the feature parameter exceeds a preset error threshold, calculating the positioning error vector of the vehicle relative to the target roadside equipment, and correcting the vehicle positioning information using the positioning error vector, includes: When the deviation of the feature parameter exceeds the preset error threshold, the reference sensing data is used as the standard value, and the vehicle positioning information is iteratively corrected based on the positioning error vector of the vehicle relative to the target roadside equipment until the deviation of the feature parameter converges to less than or equal to the preset error threshold. The positioning error vector includes: vehicle coordinate offset, vehicle heading angle, and vehicle timestamp synchronization error.

[0011] In some implementations, the parameter correction process includes: The current vehicle positioning information obtained by the vehicle is linearly superimposed with the positioning error vector and then output.

[0012] A second aspect of this application provides a vehicle weak network data correction device, comprising: The correction trigger module is used to detect the network strength of the vehicle's positioning signal, and generate a correction command when the network strength of the positioning signal is lower than a preset threshold. The target determination module is used to determine, according to the correction instruction, the target roadside equipment that has a spatially overlapping sensing area with the vehicle; The deviation calculation module is used to acquire the real-time perception data of the vehicle and the reference perception data collected by the target roadside equipment, compare the feature parameters of at least one identical environmental target in the real-time perception data and the reference perception data, and obtain the deviation of the feature parameters. The parameter correction module is used to calculate the positioning error vector of the vehicle relative to the target roadside equipment when the deviation of the feature parameter exceeds a preset error threshold, and to perform parameter correction on the vehicle positioning information of the vehicle through the positioning error vector.

[0013] A third aspect of this application provides an electronic device, comprising: Processor; and A memory that stores executable code, which, when executed by the processor, causes the processor to perform the method described above.

[0014] A fourth aspect of this application provides a computer-readable storage medium having executable code stored thereon, which, when executed by a processor of an electronic device, causes the processor to perform the method described above.

[0015] The technical solution provided in this application may include the following beneficial effects: The technical solution of this application constructs a positioning error closed-loop correction mechanism based on environmental target feature matching by comparing the real-time comparison of roadside equipment and vehicle perception data when the strength of the vehicle's positioning signal is detected to be lower than a preset threshold. The positioning error vector used to correct the vehicle's positioning information is calculated using the reference perception data of the roadside equipment. The positioning error vector directly corrects the deviation between the vehicle coordinate system and the global coordinate system, thereby improving the positioning accuracy of the vehicle in weak network environments and eliminating the problem of error accumulation in the inertial navigation prediction method. This effectively ensures that the vehicle can maintain accurate global positioning capability even when encountering signal attenuation during driving, thus improving the safety of the driving process.

[0016] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0017] The above and other objects, features and advantages of this application will become more apparent from the more detailed description of exemplary embodiments thereof in conjunction with the accompanying drawings, wherein the same reference numerals generally represent the same components in the exemplary embodiments thereof.

[0018] Figure 1 This is a flowchart illustrating the vehicle weak network data correction method according to an embodiment of this application; Figure 2 This is another schematic flowchart illustrating the vehicle weak network data correction method shown in the embodiments of this application; Figure 3 This is another schematic flowchart illustrating the vehicle weak network data correction method shown in the embodiments of this application; Figure 4 This is a schematic diagram of the structure of the vehicle weak network data correction device shown in the embodiments of this application; Figure 5 This is a schematic diagram of the structure of an electronic device shown in an embodiment of this application. Detailed Implementation

[0019] Embodiments of this application will now be described in more detail with reference to the accompanying drawings. While embodiments of this application are shown in the drawings, it should be understood that this application may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided to make this application more thorough and complete, and to fully convey the scope of this application to those skilled in the art.

[0020] The terminology used in this application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. The singular forms “a,” “the,” and “the” used in this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0021] It should be understood that although the terms "first," "second," "third," etc., may be used in this application to describe various information, this information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, without departing from the scope of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, "multiple" means two or more, unless otherwise explicitly specified.

[0022] In related technologies, inertial navigation systems (INS) are commonly used to predict vehicle position. However, inferring the current position of a vehicle based on its historical motion state is essentially a prediction rather than a measurement. This can easily lead to the accumulation of errors in vehicle position calculation over time, resulting in inaccurate calculation of the relative pose of environmental targets in global coordinates under weak network conditions, which affects decision-making safety during driving.

[0023] To address the aforementioned issues, this application provides a vehicle weak network data correction method, which can improve vehicle positioning accuracy in weak network environments, reduce error accumulation, and enhance the safety of autonomous driving processes.

[0024] The technical solutions of the embodiments of this application are described in detail below with reference to the accompanying drawings.

[0025] Figure 1 This is a flowchart illustrating the vehicle weak network data correction method shown in the embodiments of this application.

[0026] See Figure 1 The vehicle weak network data correction method of this application includes: S110: Detect the network strength of the vehicle's positioning signal. When the network strength of the positioning signal is lower than a preset threshold, generate a correction command.

[0027] In this step, the network strength of the positioning signal obtained by the vehicle through the satellite module is detected. When the network strength of the positioning signal is lower than a preset threshold, it is determined that the vehicle is in a weak network environment, and a correction command is generated to correct the vehicle positioning information obtained by the vehicle.

[0028] The positioning signal can refer to the satellite positioning signal received by the vehicle. The network strength of the positioning signal can be quantified and detected using signal received power or signal-to-noise ratio.

[0029] The preset threshold can be a pre-defined network strength threshold. It should be understood that if the network strength of the positioning signal is lower than the preset threshold, it indicates that the positioning signal acquired by the vehicle in its current environment is weak and delayed, leading to errors in the sensing data due to inaccurate positioning. The preset threshold can be a fixed value or a dynamic value that is dynamically adjusted according to different environmental scenarios.

[0030] The network strength of the vehicle's location signal can be detected according to a preset period. For example, the network strength of the location signal can be sampled every 100 milliseconds.

[0031] S120, based on the correction instruction, identifies the target roadside equipment in the sensing area that spatially overlaps with the vehicle.

[0032] In this step, a correction instruction is obtained, and based on the correction instruction, a target roadside device with a spatially overlapping sensing area with the vehicle is determined from all roadside devices within the range corresponding to the vehicle's location.

[0033] The spatial overlap perception area refers to the perception range within which both the vehicle and roadside equipment can simultaneously detect the same environmental target. It should be understood that the perception range refers to the physical spatial range determined through geofencing technology or coordinate range matching. The vehicle's perception range may be smaller than that of the roadside equipment.

[0034] S130: Acquire real-time perception data collected by the vehicle and reference perception data collected by the target roadside equipment, compare the feature parameters of at least one identical environmental target in the real-time perception data and the reference perception data, and obtain the deviation of the feature parameters.

[0035] In this step, real-time perception data collected by the vehicle and baseline perception data collected by the target roadside equipment are acquired simultaneously. At least one characteristic parameter of the same environmental target is identified from the real-time perception data and the baseline perception data and compared to obtain the deviation of the characteristic parameter.

[0036] It is understandable that roadside equipment is typically operating under stable network conditions, and the perception data collected by roadside equipment can be used as a reference benchmark to correct vehicle positioning information. Real-time perception data and reference perception data can include, but are not limited to, point cloud data, image data, or multi-sensor fusion data collected by sensors such as cameras, LiDAR, and millimeter-wave radar.

[0037] S140, when the deviation of the feature parameters exceeds the preset error threshold, calculate the positioning error vector of the vehicle relative to the target roadside equipment, and perform parameter correction on the vehicle positioning information through the positioning error vector.

[0038] In this step, when the deviation of the feature parameters exceeds the preset error threshold, it is determined that the vehicle is in a weak network environment and the vehicle positioning information has errors. The positioning error vector of the current vehicle relative to the target roadside equipment is detected, and the parameters of the vehicle positioning information obtained by the vehicle are corrected by using the positioning error vector.

[0039] In this embodiment, the vehicle weak network data correction method of this application constructs a positioning error closed-loop correction mechanism based on environmental target feature matching by comparing the real-time comparison of roadside equipment and vehicle perception data when the strength of the vehicle's positioning signal is detected to be lower than a preset threshold. The positioning error vector used to correct the vehicle positioning information is calculated using the reference perception data of the roadside equipment. The deviation between the vehicle coordinate system and the global coordinate system is directly corrected by the positioning error vector, thereby improving the positioning accuracy of the vehicle in a weak network environment and eliminating the problem of error accumulation in the inertial navigation prediction method. This effectively ensures that the vehicle can maintain accurate global positioning capability even when encountering signal attenuation during driving, thus improving the safety of driving.

[0040] Figure 2 This is another schematic flowchart illustrating the vehicle weak network data correction method shown in the embodiments of this application. The embodiments of this application... Figure 1 Based on the embodiments shown, the technical solution of this application will be further described in detail.

[0041] See Figure 2 The vehicle weak network data correction method of this application includes: S210, obtain the current vehicle location information.

[0042] In this step, the vehicle's current location information is obtained in real time through the vehicle positioning system.

[0043] The current vehicle location information may include, but is not limited to, the vehicle's latitude and longitude coordinates, altitude, speed, and direction of travel.

[0044] The vehicle positioning system can be one of the satellite navigation systems such as GPS or BeiDou.

[0045] S220: Match the current vehicle location information with the pre-stored signal distribution map information. When it is determined that the vehicle has entered a preset signal obstruction area based on the matching result, generate a network strength detection command so that the vehicle can perform network strength detection according to the network strength detection command.

[0046] In this step, the current vehicle location information is matched with the signal distribution map information pre-stored on the server. When it is determined that the vehicle has entered a pre-marked preset model occlusion area, a network strength detection command is generated to control the vehicle to perform network strength detection.

[0047] Among them, the preset signal obstruction areas in the pre-stored signal distribution map information can be marked by historical signal strength attenuation records or three-dimensional geographic models.

[0048] The preset signal blocking area is slightly larger than the actual signal blocking area in the real world.

[0049] For example, the pre-stored high-precision map contains geographical information such as road networks, buildings, and tunnels, as well as pre-marked signal obstruction areas. The polygonal geofence within 200 meters in front of the tunnel entrance or the densely built-up area is used as the preset area. When the current vehicle location information shows that the vehicle is about to enter the 200-meter area in front of the tunnel entrance or the densely built-up area, it is determined that the vehicle has entered the preset signal obstruction area.

[0050] S230, according to the network strength detection command, detects the network strength of the vehicle's positioning signal, and generates a correction command when the network strength of the positioning signal is lower than a preset threshold.

[0051] S240, based on the correction instruction, identifies the target roadside equipment in a sensing area that spatially overlaps with the vehicle.

[0052] S250: Acquire real-time perception data collected by the vehicle and reference perception data collected by the target roadside equipment, compare the feature parameters of at least one identical environmental target in the real-time perception data and the reference perception data, and obtain the deviation of the feature parameters.

[0053] S260, when the deviation of the feature parameters exceeds the preset error threshold, calculate the positioning error vector of the vehicle relative to the target roadside equipment, and perform parameter correction on the vehicle positioning information through the positioning error vector.

[0054] Steps S230 to S260 are similar to steps S110 to S140. For details, please refer to the previous section on steps S110 to S140. They will not be repeated here.

[0055] In this implementation, the vehicle weak network data correction method of this application pre-marks signal obstruction areas on a pre-stored signal distribution map. Based on the vehicle's positioning information, it actively triggers a network strength detection mechanism before the vehicle enters an area susceptible to signal interference, achieving predictive detection based on the vehicle's geographical location. This effectively avoids the lag of triggering detection only after the vehicle's network signal has weakened, enabling earlier identification of potential weak network environments and reserving sufficient preparation time for subsequent positioning correction strategies. This further improves the positioning accuracy and reliability of the vehicle in complex environments.

[0056] Figure 3 This is another schematic flowchart illustrating the vehicle weak network data correction method shown in the embodiments of this application. The embodiments of this application... Figure 1 Based on the embodiments shown, the technical solution of this application will be further described in detail.

[0057] See Figure 3 The vehicle weak network data correction method of this application includes: S310 detects the first network strength of the vehicle's current location signal.

[0058] In this step, the first network strength corresponding to the vehicle's current location signal is detected in real time.

[0059] The current positioning signal can be a satellite positioning signal obtained by the vehicle's onboard positioning module.

[0060] The first network strength is detected using a real-time sampling method, for example, by collecting the signal strength value every millisecond. In other words, the detection of the first network strength can be continuous.

[0061] S320, when the first network strength is lower than the first preset strength threshold, the second network strength of the vehicle in the adjacent preset time period is obtained; wherein, the second network strength includes: the minimum strength value or the average strength value of the vehicle positioning signal in the adjacent preset time period.

[0062] In this step, when the first network strength is detected to be lower than a preset first strength threshold, a second network strength within a preset time period adjacent to the time when the current first network strength is obtained is triggered. The second network strength may include the minimum or average strength value of the vehicle positioning signal within the adjacent preset time period.

[0063] The adjacent preset time period can be located before or after the moment when the current first network strength is obtained. In other words, after determining that the first network strength is lower than the first preset strength threshold, the positioning signal strength sampling data of the previous preset time period or the positioning signal strength sampling data of the subsequent preset time period can be retrieved. By measuring the positioning signal strength within the preset time period before or after the moment when the current first network strength is obtained, it can be further determined whether the vehicle is in a continuously weak network environment.

[0064] For example, if a preset time period of 10 seconds is set, after detecting that the strength of the first network is lower than the first preset strength threshold, the acquisition of the positioning signal strength data within the previous 10 seconds is immediately triggered. The acquired positioning signal strength data within the previous 10 seconds is then processed to calculate the minimum strength value or the average strength value.

[0065] S330, when the strength of the second network is lower than the second preset strength threshold, a correction instruction is generated.

[0066] In this step, when the second network strength is detected to be lower than the second preset strength threshold, it is determined that the vehicle is in a weak network environment, and a correction command is generated to control the vehicle positioning signal of the vehicle to be corrected.

[0067] It should be understood that the first network strength serves as a preliminary detection condition. When the preliminary detection condition is met, the second network strength within a preset time window is detected and judged. By using a two-level detection and judgment mechanism, the false triggering problem that may be caused by a single instantaneous detection can be effectively avoided. It can effectively distinguish between short-term signal fluctuations and continuous weak network scenarios. Furthermore, by using the joint judgment of dual thresholds and time windows, it can be ensured that the correction command is triggered only under reliable conditions of continuous insufficient network strength, thereby improving the accuracy of the correction process and the efficiency of resource utilization, and reducing unnecessary positioning error correction operations.

[0068] The second preset strength threshold can be slightly higher than the first preset strength threshold. Thus, by using two strength thresholds in different ranges, a stepped triggering condition is formed, and the higher standard of the second detection is used to exclude weak network environments in a critical state. For example, the first preset strength threshold can be set to a specific value within the range of -95dBm to -90dBm, and the second preset strength threshold can be set to a specific value within the range of -90dBm to -85dBm.

[0069] S340, according to the correction instruction, determines the real-time location information of the vehicle based on the vehicle positioning signal, and selects a target roadside device that meets the preset conditions from the roadside end devices in the sensing area that has spatial overlap with the vehicle based on the real-time location information of the vehicle.

[0070] In this step, after obtaining the correction instruction, the real-time location information of the vehicle in the pre-stored high-precision map is obtained through the vehicle positioning signal. Based on the real-time location information, the target roadside device that meets the preset conditions is selected from the candidate roadside device set that currently overlaps with the vehicle in the sensing area.

[0071] The preset conditions include meeting preset distance conditions and / or meeting network stability conditions. It should be understood that a roadside end that meets the preset conditions can meet only the preset distance conditions, only the network stability conditions, or both the preset distance conditions and the network stability conditions.

[0072] The preset distance condition is used to select the roadside device with the optimal effective communication range. For example, the first roadside device located within a fan-shaped area directly in front of the vehicle and less than 150 meters away from the vehicle is selected as the target roadside device.

[0073] Among them, the network stability condition is used to select the roadside device with the best network conditions. For example, the first roadside device with an average communication signal strength with the vehicle over the past 5 seconds that is higher than -80dBm and an instantaneous fluctuation amplitude that does not exceed 10dBm is selected as the target roadside device.

[0074] The preset conditions can be dynamically set based on the distribution density of roadside equipment. For example, in areas with dense roadside equipment deployment, only network stability needs to be met, while in areas with sparse roadside equipment deployment, both distance and network stability conditions need to be met. In this way, by flexibly combining the screening conditions, different environmental characteristics can be adapted. For example, network stability can be prioritized in areas with severe signal obstruction, while distance factors are given more attention in open areas. This allows for the optimal matching of roadside equipment with vehicles in complex and variable weak network environments.

[0075] Among them, the roadside end equipment that has a spatially overlapping sensing area with the vehicle can be roadside equipment within a certain range around the vehicle.

[0076] For example, based on the real-time location information of the vehicle in a pre-stored high-precision map and the relative positional relationship between the vehicle and each roadside device, roadside devices with relative positional distances between them that are within a pre-set distance value are selected as candidate roadside devices for areas with spatial overlap in perception.

[0077] S350: Acquire real-time perception data collected by the vehicle and reference perception data collected by the target roadside equipment, compare the feature parameters of at least one identical environmental target in the real-time perception data and the reference perception data, and obtain the deviation of the feature parameters.

[0078] In this step, real-time perception data collected by the vehicle and baseline perception data collected by the target roadside equipment are acquired simultaneously. At least one characteristic parameter of the same environmental target is identified from the real-time perception data and the baseline perception data and compared to obtain the deviation of the characteristic parameter.

[0079] The feature parameters may include the coordinate positions and heading angles of at least one identical environmental target in both the vehicle coordinate system and the roadside coordinate system. It should be understood that the vehicle coordinate system and the roadside coordinate system use different spatial reference bases. The vehicle coordinate system is a three-dimensional Cartesian coordinate system with the vehicle's center of mass as the origin, while the roadside coordinate system is a global coordinate system with the target roadside equipment as the origin. The coordinate positions of the identical environmental targets can be extracted from raw point cloud data from millimeter-wave radar or lidar, and the heading angle can be identified from image data using target detection algorithms.

[0080] As an example, a roadside traffic sign can be selected as a common environmental target. In the vehicle coordinate system, the coordinate position of the traffic sign can be represented as (x1, y1, z1), with a heading angle of θ1. In the roadside coordinate system, the coordinate position of the same traffic sign can be represented as (x2, y2, z2), with a heading angle of θ2. By comparing these two sets of data, the positional and directional deviations of the vehicle relative to the roadside equipment can be calculated. Furthermore, multiple environmental targets can be selected for comparison, such as simultaneously selecting the same streetlight, the same building corner, and the same road sign as common environmental targets. By comparing the feature parameters of multiple common environmental targets and taking the average as the deviation of the final output feature parameters, the accuracy of correcting vehicle positioning information can be improved.

[0081] The deviation of the characteristic parameters can be calculated using Euclidean distance or the absolute value of the angle difference.

[0082] In obtaining the deviation of the feature parameters, the coordinate positions and heading angles of at least one identical environmental target in the vehicle coordinate system and the roadside coordinate system can be converted to the same preset coordinate system for comparison.

[0083] For example, the coordinates of the front and rear axle center points of an environmental target are obtained in the vehicle coordinate system, and the coordinates of the geometric center point of the same target are obtained in the roadside coordinate system. A coordinate transformation matrix is ​​then used to convert the coordinates in the vehicle coordinate system into projected coordinates in the global coordinate system, and a three-dimensional comparison is performed with the global coordinates collected by the roadside equipment in the lateral, longitudinal, and vertical directions. Another example is the calculation of angular deviations by unifying the heading angles in the vehicle coordinate system and the roadside coordinate system to the same rotating reference frame.

[0084] S360: When the deviation of the feature parameters exceeds the preset error threshold, the reference sensing data is used as the standard value, and the vehicle positioning information is iteratively corrected based on the positioning error vector of the vehicle relative to the target roadside equipment until the deviation of the feature parameters converges to less than or equal to the preset error threshold.

[0085] In this step, when the deviation of the feature parameters exceeds the preset error threshold, it is determined that the vehicle positioning information needs to be corrected. The initial positioning error vector of the vehicle relative to the target roadside equipment is calculated, and this error vector is applied to the current positioning information of the vehicle to obtain the corrected vehicle positioning information. Based on the corrected vehicle positioning information and the reference perception data, the deviation of the feature parameters is recalculated. If the deviation still exceeds the preset error threshold, the above calculation and correction process is repeated for iterative correction until the deviation of the feature parameters converges to less than or equal to the preset error threshold.

[0086] The positioning error vector includes: vehicle coordinate offset, vehicle heading angle, and vehicle timestamp synchronization error. The vehicle coordinate offset represents the vehicle's position deviation in the global coordinate system; the vehicle heading angle represents the vehicle's orientation deviation in the global coordinate system; and the vehicle timestamp synchronization error represents the time synchronization error between the vehicle and roadside equipment. By correcting the vehicle using these types of positioning error vectors, the correction process simultaneously addresses parameters in three dimensions: spatial pose, attitude angle, and time synchronization error. This ensures that the corrected vehicle positioning information meets the accuracy requirements of driving decisions in terms of spatiotemporal consistency, thereby improving the safety and reliability of the driving system.

[0087] As an example, suppose the initial positioning error vector has a vehicle coordinate offset of (2m, 1m), a vehicle heading angle deviation of 5 degrees, and a timestamp synchronization error of 0.1 seconds. After the first iteration correction, the deviation of the feature parameters may decrease but still exceed the preset error threshold, which may result in a new positioning error vector, such as a vehicle coordinate offset of (0.5m, 0.3m), a vehicle heading angle deviation of 2 degrees, and a timestamp synchronization error of 0.03 seconds. Then, the iteration correction continues until the deviation of the feature parameters finally converges to within the preset error threshold.

[0088] It should be understood that simply correcting the positioning error vector acquired in a single instance may result in incomplete error compensation and an inability to eliminate the cumulative effect of positioning errors. This application, by introducing an iterative correction mechanism and combining it with the collaborative compensation of multi-dimensional error vectors, can systematically improve the accuracy of vehicle positioning information. The parameter correction process includes linearly superimposing the current vehicle positioning information acquired by the vehicle with the positioning error vector and then outputting the result.

[0089] The linear superposition operation is limited to algebraic operations, allowing direct addition of each component of the error vector with the corresponding component of the vehicle positioning information. For example, when the error vector contains coordinate offsets Δx and Δy, the corrected coordinate values ​​are generated using x'=x+Δx and y'=y+Δy. Thus, this operation does not require establishing nonlinear equations or performing iterative convergence calculations, and the number of operations can be effectively controlled within a fixed number; for example, only one addition operation is performed for each coordinate axis.

[0090] The timing of superimposing the error vector and positioning information can be configured to be performed in real time. That is, the superposition is performed immediately after the latest positioning error vector is obtained, so that the delay of the corrected positioning information does not exceed a single calculation cycle.

[0091] When the network signal recovers, the overlay operation can be configured to terminate automatically, at which point the vehicle positioning information is directly output as raw data. For example, if the network strength threshold is detected to reach a preset termination correction threshold, such as when the signal strength recovers to above -90dBm, the input channel of the error vector is stopped. This allows the system to quickly switch back to the raw positioning data output mode, thereby meeting the real-time and stability requirements of the driving system while maintaining positioning accuracy. In this embodiment, the vehicle weak network data correction method of this application sets up a multi-dimensional screening mechanism to select roadside equipment that meets preset conditions, so as to realize adaptive optimization of equipment matching strategy by combining environmental characteristics, thereby effectively improving the quality of the benchmark data provided by the roadside equipment for vehicle correction; and introduces an iterative correction and error vector collaborative compensation mechanism, using benchmark perception data as an objective reference for closed-loop pose correction, which can systematically eliminate the risk of vehicle's own perception error accumulation, so that the deviation of feature parameters converges to within the threshold, thereby effectively improving the vehicle positioning accuracy and driving decision reliability in weak network environment.

[0092] Corresponding to the aforementioned application function implementation method embodiments, this application also provides a vehicle weak network data correction device, electronic device, and corresponding embodiments.

[0093] Figure 4 This is a schematic diagram of the structure of a vehicle weak network data correction device shown in an embodiment of this application.

[0094] See Figure 4 The vehicle weak network data correction device 400 of this application includes: a correction trigger module 410, a target determination module 420, a deviation calculation module 430, and a parameter correction module 440.

[0095] The correction trigger module 410 is used to detect the network strength of the vehicle's positioning signal. When the network strength of the positioning signal is lower than a preset threshold, a correction command is generated.

[0096] In some implementations, the correction trigger module 410 can detect the first network strength of the vehicle's current positioning signal; when the first network strength is lower than a first preset strength threshold, it can obtain the second network strength of the vehicle in an adjacent preset time period; wherein, the second network strength includes: the minimum strength value or the average strength value of the vehicle positioning signal in an adjacent preset time period; when the second network strength is lower than a second preset strength threshold, it can generate a correction command.

[0097] In some implementations, before generating a correction instruction when the network strength of the vehicle's positioning signal is lower than a preset threshold, the correction trigger module 410 can also obtain the current vehicle positioning information; match the current vehicle positioning information with the pre-stored signal distribution map information; and when it is determined that the vehicle has entered a preset signal obstruction area based on the matching result, generate a network strength detection instruction so that the vehicle can perform network strength detection according to the network strength detection instruction.

[0098] The target determination module 420 is used to determine the target roadside equipment in the sensing area that overlaps with the vehicle, based on the correction instructions.

[0099] In some implementations, the target determination module 420 can determine the real-time location information of the vehicle based on the vehicle positioning signal, and select a target roadside device that meets preset conditions from the roadside end devices in the sensing area that has spatial overlap with the vehicle based on the real-time location information of the vehicle; wherein, the preset conditions include: meeting preset distance conditions and / or meeting network stability conditions.

[0100] The deviation calculation module 430 is used to acquire real-time perception data of the vehicle and reference perception data collected by the target roadside equipment, compare the feature parameters of at least one identical environmental target in the real-time perception data and the reference perception data, and obtain the deviation of the feature parameters.

[0101] In some implementations, the characteristic parameters include: the coordinate positions and heading angles of at least one identical environmental target in the vehicle coordinate system and the roadside coordinate system, respectively.

[0102] The parameter correction module 440 is used to calculate the positioning error vector of the vehicle relative to the target roadside equipment when the deviation of the feature parameters exceeds the preset error threshold, and to perform parameter correction on the vehicle positioning information through the positioning error vector.

[0103] In some implementations, the parameter correction module 440 can use the reference sensing data as a standard value and iteratively correct the vehicle positioning information based on the positioning error vector of the vehicle relative to the target roadside equipment when the deviation of the feature parameters exceeds the preset error threshold, until the deviation of the feature parameters converges to less than or equal to the preset error threshold; wherein, the positioning error vector includes: vehicle coordinate offset, vehicle heading angle, and vehicle timestamp synchronization error.

[0104] In some implementations, the parameter correction process includes linearly superimposing the current vehicle positioning information acquired by the vehicle with the positioning error vector and then outputting the result.

[0105] In this embodiment, the vehicle weak network data correction device of this application constructs a positioning error closed-loop correction mechanism based on environmental target feature matching by comparing the real-time comparison of roadside equipment and vehicle perception data when the strength of the vehicle's positioning signal is detected to be lower than a preset threshold. The positioning error vector used to correct the vehicle's positioning information is calculated using the reference perception data of the roadside equipment. The deviation between the vehicle coordinate system and the global coordinate system is directly corrected by the positioning error vector, thereby improving the positioning accuracy of the vehicle in a weak network environment and eliminating the problem of error accumulation in the inertial navigation prediction method. This effectively ensures that the vehicle can maintain accurate global positioning capability even when the signal attenuates during driving, thus improving the safety of driving.

[0106] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated further here.

[0107] Figure 5 This is a schematic diagram of the structure of an electronic device shown in an embodiment of this application.

[0108] See Figure 5 The electronic device 1000 includes a memory 1010 and a processor 1020.

[0109] The processor 1020 can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor.

[0110] Memory 1010 may include various types of storage units, such as system memory, read-only memory (ROM), and permanent storage devices. ROM may store static data or instructions required by processor 1020 or other modules of the computer. Permanent storage devices may be read-write storage devices. Permanent storage devices may be non-volatile storage devices that retain stored instructions and data even when the computer is powered off. In some embodiments, permanent storage devices use mass storage devices (e.g., magnetic or optical disks, flash memory) as permanent storage devices. In other embodiments, permanent storage devices may be removable storage devices (e.g., floppy disks, optical drives). System memory may be a read-write storage device or a volatile read-write storage device, such as dynamic random access memory. System memory may store some or all of the instructions and data required by the processor during operation. Furthermore, memory 1010 may include any combination of computer-readable storage media, including various types of semiconductor memory chips (e.g., DRAM, SRAM, SDRAM, flash memory, programmable read-only memory), and disks and / or optical disks may also be used. In some embodiments, the memory 1010 may include a removable storage device that is readable and / or writable, such as a laser disc (CD), a read-only digital multifunction optical disc (e.g., DVD-ROM, dual-layer DVD-ROM), a read-only Blu-ray disc, an ultra-high density optical disc, a flash memory card (e.g., SD card, mini SD card, Micro-SD card, etc.), a magnetic floppy disk, etc. Computer-readable storage media do not contain carrier waves or transient electronic signals transmitted wirelessly or via wired connections.

[0111] The memory 1010 stores executable code, which, when processed by the processor 1020, can cause the processor 1020 to execute part or all of the methods described above.

[0112] Furthermore, the method according to this application can also be implemented as a computer program or computer program product, which includes computer program code instructions for performing some or all of the steps in the method described above.

[0113] Alternatively, this application may be implemented as a computer-readable storage medium (or a non-transitory machine-readable storage medium or a machine-readable storage medium) storing executable code (or computer program or computer instruction code) thereon, which, when executed by a processor of an electronic device (or server, etc.), causes the processor to perform part or all of the steps of the methods described above according to this application.

[0114] The various embodiments of this application have been described above. These descriptions are exemplary and not exhaustive, nor are they limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen to best explain the principles, practical application, or improvement of the technology in the market, or to enable others skilled in the art to understand the embodiments disclosed herein.

Claims

1. A method for correcting weak network data in vehicles, characterized in that, include: The network strength of the vehicle's positioning signal is detected, and when the network strength of the positioning signal is lower than a preset threshold, a correction command is generated. Based on the correction instruction, a target roadside device with a spatially overlapping sensing area with the vehicle is identified; The system acquires real-time perception data collected by the vehicle and baseline perception data collected by the target roadside equipment, compares the feature parameters of at least one identical environmental target in the real-time perception data and the baseline perception data, and obtains the deviation of the feature parameters. When the deviation of the feature parameter exceeds the preset error threshold, the positioning error vector of the vehicle relative to the target roadside equipment is calculated, and the vehicle positioning information of the vehicle is corrected by the positioning error vector.

2. The method according to claim 1, characterized in that, The network strength of the vehicle's positioning signal is detected. When the network strength of the positioning signal is lower than a preset threshold, a correction instruction is generated, including: The first network strength of the vehicle's current location signal is detected; When the first network strength is lower than the first preset strength threshold, the second network strength of the vehicle in an adjacent preset time period is obtained; wherein, the second network strength includes: the minimum strength value or the average strength value of the vehicle positioning signal in an adjacent preset time period; When the strength of the second network is lower than the second preset strength threshold, a correction instruction is generated.

3. The method according to claim 1 or 2, characterized in that, Before generating a correction instruction when the network strength of the location signal of the detected vehicle is lower than a preset threshold, the method further includes: Obtain the current vehicle location information; The current vehicle location information is matched with the pre-stored signal distribution map information. When the vehicle is determined to have entered a preset signal obstruction area based on the matching result, a network strength detection command is generated so that the vehicle can perform network strength detection according to the network strength detection command.

4. The method according to claim 1, characterized in that, The target roadside device for determining the sensing area that spatially overlaps with the vehicle includes: Based on the vehicle positioning signal, the real-time location information of the vehicle is determined, and a target roadside device that meets the preset conditions is selected from the roadside end devices in the sensing area that has spatial overlap with the vehicle according to the real-time location information of the vehicle. The preset conditions include: meeting preset distance conditions and / or meeting network stability conditions.

5. The method according to claim 1, characterized in that, The feature parameters include: The coordinates and heading angles of at least one identical environmental target in the vehicle coordinate system and the roadside coordinate system, respectively.

6. The method according to claim 1, characterized in that, When the deviation of the feature parameter exceeds a preset error threshold, the positioning error vector of the vehicle relative to the target roadside equipment is calculated, and the vehicle positioning information is corrected using the positioning error vector, including: When the deviation of the feature parameter exceeds the preset error threshold, the reference sensing data is used as the standard value, and the vehicle positioning information is iteratively corrected based on the positioning error vector of the vehicle relative to the target roadside equipment until the deviation of the feature parameter converges to less than or equal to the preset error threshold. The positioning error vector includes: vehicle coordinate offset, vehicle heading angle, and vehicle timestamp synchronization error.

7. The method according to claim 1, characterized in that, The parameter correction process includes: The current vehicle positioning information obtained by the vehicle is linearly superimposed with the positioning error vector and then output.

8. A vehicle weak network data correction device, characterized in that, include: The correction trigger module is used to detect the network strength of the vehicle's positioning signal, and generate a correction command when the network strength of the positioning signal is lower than a preset threshold. The target determination module is used to determine, according to the correction instruction, the target roadside equipment that has a spatially overlapping sensing area with the vehicle; The deviation calculation module is used to acquire the real-time perception data of the vehicle and the reference perception data collected by the target roadside equipment, compare the feature parameters of at least one identical environmental target in the real-time perception data and the reference perception data, and obtain the deviation of the feature parameters. The parameter correction module is used to calculate the positioning error vector of the vehicle relative to the target roadside equipment when the deviation of the feature parameter exceeds a preset error threshold, and to perform parameter correction on the vehicle positioning information of the vehicle through the positioning error vector.

9. An electronic device, characterized in that, include: processor; as well as A memory having executable code stored thereon, which, when executed by the processor, causes the processor to perform the method as described in any one of claims 1-7.

10. A computer-readable storage medium having executable code stored thereon, characterized in that: When the executable code is executed by the processor of the electronic device, the processor performs the method as described in any one of claims 1-7.

Images