Method and related device for dynamic updating of road spectrum in vehicle-cloud cooperation

Abstract

The embodiment of the application provides a kind of vehicle cloud coordination's road spectrum dynamic updating method and related equipment, belong to vehicle automatic control technical field.The scheme uses the first road spectrum information of car end and its information confidence variance, introduce the time attenuation mechanism of confidence variance, reduce the historical cumulative error in subsequent fusion process, secondly, through the conflict detection of current acquisition road spectrum information and historical road spectrum information, if current and historical road spectrum are not conflict, it indicates that road surface does not change significantly, then fusion historical and current road spectrum information quickly determines current road spectrum information, improve the efficiency of road spectrum dynamic updating;If current and historical road spectrum conflict, it indicates that road surface can change significantly, then continuously collect car end road spectrum information to reconstruct current road spectrum information, discard historical data, avoid solidification error, realize the rapid self-healing to real road surface change, improve road spectrum updating accuracy.

Description

Technical Field

[0001] This application relates to the field of vehicle automatic control technology, and in particular to a method and related equipment for dynamic updating of road spectrum in vehicle-cloud collaboration. Background Technology

[0002] Predictive active suspension systems rely on beyond-line-of-sight road elevation information to adjust damping in advance. However, limited by the blind spots of individual vehicle sensors and the limitations of individual vehicle data processing capabilities, a single vehicle cannot independently maintain a long-term road spectrum that includes road elevation data efficiently. Therefore, it is necessary to rely on a cloud platform to aggregate perception data from multiple vehicles to achieve global road spectrum sharing and updates. In addition, the dynamic and variable characteristics of real physical road surfaces place extremely high demands on the real-time performance of road spectrum information.

[0003] Current cloud-based road spectrum dynamic updates are primarily achieved through two technical approaches: one is to replace historical road spectrum information in real time using the latest data collected from a single vehicle. While this method can quickly update the cloud road spectrum, it is prone to introducing anomalous data and causing cloud road spectrum contamination due to the difficulty in removing dynamic inversion errors. The other approach employs a crowdsourced weighted averaging strategy, smoothing single-vehicle noise through multi-vehicle data fusion to improve estimation stability. However, this method assigns high cumulative weights to historical data, and it is difficult to correct historical results in a timely manner with newly collected data, easily leading to error consolidation and an inability to adapt to update lag caused by rapidly changing road spectrum information. Summary of the Invention

[0004] The main objective of this application is to propose a method and related equipment for dynamic updating of road spectrum in vehicle-cloud collaboration, aiming to improve the accuracy of road spectrum and the efficiency of stable dynamic updating.

[0005] To achieve the above objectives, one aspect of this application proposes a method for dynamic updating of road spectrum in vehicle-cloud collaboration, the method comprising the following steps: First road spectrum information is collected from each vehicle terminal; wherein the first road spectrum information carries information confidence variance. Perform temporal-space alignment mapping and statistical analysis on the first path spectrum information collected at the current time step to determine the second path spectrum information in the target space at the current time step and its global total confidence variance. Conflict detection is performed based on the second road spectrum information at the current time step and the historical road spectrum information in the target space to obtain the conflict detection result; wherein, the global total confidence variance of the historical road spectrum information is processed by time decay. If the conflict detection result indicates no conflict, the current road spectrum information is determined based on the historical road spectrum information, its global total confidence variance, and the second road spectrum information. If the conflict detection result indicates that a conflict has occurred, the current road spectrum information is determined based on the first road spectrum information of multiple vehicles in the target space that is continuously collected.

[0006] In some embodiments, the vehicle-mounted device collects the first road spectrum information through the following steps: Select road surface perception data under normal driving conditions, and then perform positioning and coordinate mapping on the road surface perception data to determine the first road spectrum information; The information confidence variance of the first road spectrum information is determined based on the sensor basis variance, positioning quality variance, and vehicle speed deviation penalty variance.

[0007] In some embodiments, before the step of performing conflict detection based on the second road spectrum information at the current time step and the historical road spectrum information in the target space to obtain the conflict detection result, the vehicle-cloud collaborative road spectrum dynamic update method further includes the following steps: Obtain the flag state of the target space; the flag state of the target space is one of the following: monitoring state, active state, and shadow verification state. When the flag state is in the active state, the step of performing conflict detection based on the second road spectrum information of the current time step and the historical road spectrum information in the target space to obtain the conflict detection result is executed.

[0008] In some embodiments, the step of performing conflict detection based on the second path spectrum information and historical path spectrum information at the current time step to obtain a conflict detection result includes the following steps: Calculate the path spectrum deviation between the second path spectrum information and the historical path spectrum information at the current time step; If the road spectrum deviation value is less than the deviation threshold, a non-collision collision detection result is determined; If the deviation value of the road spectrum is greater than or equal to the deviation threshold, the degree of conflict is quantified based on the global total confidence variance of the second road spectrum information and the global total confidence of the historical road spectrum information, and then the conflict detection result is determined based on the degree of conflict.

[0009] In some embodiments, the step of quantifying the degree of conflict based on the global total confidence variance of the second road spectrum information and the global total confidence of the historical road spectrum information, and then determining the conflict detection result based on the degree of conflict, includes the following steps: The global total confidence variance of the historical road spectrum information is taken in reciprocal and normalized to obtain the historical information confidence level. The global total confidence variance of the second path spectrum information is taken in reciprocal and normalized to obtain the current information confidence level; The degree of conflict is determined based on the historical information trust level and the current information trust level; If the degree of conflict is greater than the conflict threshold and the current information trust level is greater than the trust level threshold, a conflict detection result is determined.

[0010] In some embodiments, determining the current road spectrum information based on the historical road spectrum information, its global total confidence variance, and the second road spectrum information includes the following steps: The inverse of the information confidence variance of each second path spectrum information is used as the fusion weight, and then multiple second path spectrum information are weighted and fused to obtain the third path spectrum information; The reciprocal of the global total confidence variance of the historical road spectrum information is used as the fusion weight, and then the third road spectrum information and the historical road spectrum information are weighted and fused to obtain the current road spectrum information. The global total confidence variance of the current road spectrum information is updated based on the fusion weights of the historical road spectrum information and the fusion weights of each of the second road spectrum information.

[0011] In some embodiments, determining the current road spectrum information based on the continuously collected multi-vehicle first road spectrum information within the target space includes the following steps: Data filtering is performed on the continuously collected first road spectrum information of multiple vehicles in the target space based on the information confidence variance; Multi-vehicle cross-validation is performed on the first road spectrum information that has passed the screening to determine whether multi-vehicle information evidence resonance has been achieved; the multi-vehicle cross-validation includes multi-vehicle consistency verification and conflict verification between multi-vehicle and historical road spectrum information. When multiple vehicle information evidence resonates, the first converged road spectrum information is determined as the current road spectrum information, and the minimum information confidence variance is determined as the global total confidence variance of the current road spectrum information.

[0012] To achieve the above objectives, another aspect of this application proposes a vehicle-cloud collaborative road spectrum dynamic update system, comprising: The first module is used to collect first road spectrum information from each vehicle terminal; wherein the first road spectrum information carries information confidence variance. The second module is used to perform temporal-space alignment mapping and statistical analysis on the first path spectrum information collected at the current time step, and to determine the second path spectrum information in the target space at the current time step and its global total confidence variance. The third module is used to perform conflict detection based on the second road spectrum information at the current time step and the historical road spectrum information in the target space, and obtain the conflict detection result; wherein, the global total confidence variance of the historical road spectrum information is processed by time decay. The fourth module is used to determine the current road spectrum information based on the historical road spectrum information and its global total confidence variance and the second road spectrum information when the conflict detection result indicates that there is no conflict; The fifth module is used to determine the current road spectrum information based on the continuously collected first road spectrum information of multiple vehicles in the target space when the conflict detection result indicates that a conflict has occurred.

[0013] To achieve the above objectives, another aspect of this application provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the above-described method.

[0014] To achieve the above objectives, another aspect of the embodiments of this application proposes a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0015] The embodiments of this application include at least the following beneficial effects: This application provides a method and related equipment for dynamic updating of road spectrum in vehicle-cloud collaboration. This scheme utilizes the first road spectrum information and its information confidence variance on the vehicle side, introduces a time decay mechanism for the confidence variance, reduces historical cumulative errors in the subsequent fusion process, and then detects conflicts between the currently collected road spectrum information and historical road spectrum information. If there is no conflict between the current and historical road spectrum, it indicates that the road surface has not changed significantly. In this case, the historical and current road spectrum information are fused to quickly determine the current road spectrum information, improving the efficiency of dynamic road spectrum updating. If there is a conflict between the current and historical road spectrum, it indicates that the road surface may have changed significantly. In this case, the vehicle-side road spectrum information is continuously collected to reconstruct the current road spectrum information, discarding historical data to avoid fixed errors, achieving rapid self-healing for real road surface changes, and improving the accuracy of road spectrum updating. Attached Figure Description

[0016] Figure 1 This is a flowchart of the vehicle-cloud collaborative road spectrum dynamic update method provided in the embodiments of this application; Figure 2 This is a schematic diagram of the dynamic update process of the target space grid road spectrum provided in the embodiments of this application; Figure 3 This is a schematic diagram of the hardware structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0017] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit it. In the following description, when referring to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with those of this application; they are merely examples of apparatuses and methods consistent with some aspects of the embodiments of this application as detailed in the appended claims.

[0018] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0019] This application provides a method and related equipment for dynamic updating of road spectrum in vehicle-cloud collaboration. This solution not only eliminates the interference of random noise from individual vehicles but also overcomes the defects of error fixation and update lag caused by historical weight overload, achieving a balance between high reliability and high agility in cloud-based road spectrum updates. Furthermore, this high-precision real-time road spectrum can directly serve active suspension pre-control, reducing the probability of chassis misresponse and thus improving vehicle ride smoothness and safety.

[0020] The vehicle-cloud collaborative road spectrum dynamic update method provided in this application relates to the field of vehicle automatic control technology. This method can be applied to a server or can be software running on a server. The server can be configured as an independent physical server, a server cluster consisting of multiple physical servers, or a distributed system. It can also be configured as a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The server can also be a node server in a blockchain network. The software can be an application implementing the vehicle-cloud collaborative road spectrum dynamic update method, but is not limited to the above forms.

[0021] This application can be used in a wide variety of general-purpose or special-purpose computer system environments or configurations. Examples include: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, programmable consumer electronics, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above systems or devices. This application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific tasks or implement specific abstract data types. This application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0022] Figure 1 This is an optional flowchart of the vehicle-cloud collaborative road spectrum dynamic update method provided in the embodiments of this application. Figure 1 The method may include, but is not limited to, steps S101 to S105.

[0023] S101, collects first road spectrum information from each vehicle terminal; the first road spectrum information carries the information confidence variance; S102, Perform temporal-space alignment mapping and statistical analysis on the first path spectrum information collected at the current time step, and determine the second path spectrum information in the target space at the current time step and its global total confidence variance; S103, perform conflict detection based on the second road spectrum information of the current time step and the historical road spectrum information in the target space to obtain the conflict detection result; wherein, the global total confidence variance of the historical road spectrum information is processed by time decay. S104, if the conflict detection result indicates no conflict, determine the current road spectrum information based on the historical road spectrum information, its global total confidence variance, and the second road spectrum information; S105, if the conflict detection result indicates that a conflict has occurred, determine the current road spectrum information based on the first road spectrum information of multiple vehicles in the continuously collected target space.

[0024] Below, please combine Figure 2 The schematic diagram shown illustrates the dynamic update process of the target space grid road spectrum, which provides a detailed description of the embodiments of this application.

[0025] In step S101 of some embodiments, the information confidence variance characterizes the information reliability of the first road spectrum information; that is, the smaller the information confidence variance, the higher the information reliability. The information confidence variance can be obtained by weighted fusion of sensor basis variance, positioning quality variance, and vehicle speed deviation penalty variance. The road spectrum information in the embodiments of this application includes at least road surface elevation.

[0026] In some embodiments, the vehicle-mounted device of this application can collect first road spectrum information through, but is not limited to, the following steps: S201, Select road surface perception data under normal driving conditions, and then locate and map the road surface perception data to determine the first road spectrum information; S202, determine the information confidence variance of the first road spectrum information based on the sensor basis variance, positioning quality variance and vehicle speed deviation penalty variance.

[0027] In this embodiment, road spectrum features based on vehicle dynamics decoupling are used, and the information confidence variance is calculated to form a multi-source data payload that is sent to the cloud, as detailed below: The vehicle-side performs abnormal condition interception and initial data screening. The vehicle's dynamic state is monitored in real-time by the edge computing unit, and a lightweight random forest algorithm is used to intercept abnormal conditions. When the random forest classifier detects that the vehicle is in a sharp turn, emergency braking, or abrupt lane change, the system outputs an interception flag of 1, and the vehicle automatically discards the road elevation inversion data within that time window, without reporting it.

[0028] ; Adaptive high-precision positioning and coordinate mapping are performed. The vehicle acquires its global absolute geographic coordinates and maps them to (X, Y) coordinates in a local planar coordinate system using a coordinate projection algorithm. To ensure high-precision input of these mapped coordinates, the system adaptively switches the positioning fusion strategy based on the signal quality of the vehicle's environment. The positioning fusion strategy is as follows: When GPS satellite signals are good, an extended Kalman filter algorithm is used. The absolute position provided by GPS is used for observation updates, while the acceleration and angular velocity output by the inertial measurement unit (IMU) are used for time updates. Combined with the RTK differential signal transmitted from roadside base stations, the absolute positioning error is converged and controlled within a safe threshold.

[0029] When a vehicle enters extreme blind zones with severe GPS signal obstruction, such as those with tall buildings or tunnels, a Long Short-Term Memory (LSTM) network is invoked to extract temporal features of the IMU's historical drift error, outputting a compensation term to suppress nonlinear drift caused by IMU integration. A graph convolutional neural network is introduced for group collaborative correction. The current vehicle and neighboring vehicles within the V2X communication range are defined as nodes in the graph network, and the relative spatial features between vehicles are defined as edges. Utilizing the relative positional topology of the neighboring vehicle group, the absolute coordinates of the current vehicle are optimized and collaboratively corrected to improve coordinate mapping accuracy within the blind zone.

[0030] Perform quantization of multi-source confidence variance. This is done when obtaining road surface elevation inversion values. Subsequently, the vehicle synchronously calculates the information confidence variance of this data, which is quantized by coupling three independent variances, as shown below: ; Among them, the sensor basis variance Determined by vehicle factory calibration or hardware level; positioning quality variance A dynamic mapping relationship is established with the GPS position accuracy factor. When the signal is completely lost, this variance increases exponentially with the loss time t. ,in This serves as the initial positioning error baseline. The exponential growth coefficient; the variance of the vehicle speed deviation penalty. Based on the optimal baseline vehicle speed of the inversion algorithm Current vehicle speed Calculated by the deviation between them ,in This represents the speed-sensitive penalty coefficient. By considering the vehicle's perception hardware conditions, positioning quality, and the deviation between the perceived vehicle speed and the appropriate speed, the reliability of the information confidence variance can be improved.

[0031] Performs packaging and transmission of multi-source data payloads. The vehicle-side data will include a unique vehicle identification number (ID), a high-precision timestamp (ms), local plane abscissa / ordinate coordinates after coordinate transformation, and road surface elevation inversion values. (i.e., first path spectrum information) and information confidence variance The core data payload is packaged and sent to the cloud.

[0032] In step S102 of some embodiments, the spatiotemporal alignment mapping refers to mapping the first road spectrum information to a corresponding spatial network and aligning the first road spectrum information from different vehicle terminals according to a unified time step. Any spatial network is used as the target space for subsequent analysis, and the first road spectrum information at the current time step that falls within the target space is determined as the second road spectrum information. The global total confidence variance of the second road spectrum information refers to the sum of the confidence variances of each second road spectrum information. The spatiotemporal alignment mapping and statistical analysis of the first road spectrum information collected at the current time step are as follows: Spatiotemporal grid mapping and data alignment are performed. The global road network is divided into a fine spatial grid of a preset physical size (e.g., 0.1m * 0.1m). Upon receiving the data payload (i.e., the first road spectrum information) sent by the vehicle, the cloud sets a city base station as the zero coordinate origin and uses a spatial hash algorithm to round and map the local plane horizontal / vertical coordinates (X, Y) in the data packet to the corresponding independent cloud grid. Simultaneously, the cloud sets a fixed time tolerance window (e.g., 10ms) to cluster and align the high-precision timestamps from multiple sources of vehicles falling within the same grid, ensuring strict synchronization of data in both spatial and temporal dimensions. The spatial alignment formula is as follows:

[0033] In the formula, To map the x-coordinate of the grid; This is for mapping the ordinate of the grid.

[0034] In some embodiments, prior to step S103, the vehicle-cloud collaborative road spectrum dynamic update method of this application embodiment may also include, but is not limited to, the following steps: S301, Obtain the flag state of the target space; the flag state of the target space is one of the monitoring state, the active state, and the shadow verification state; the active state indicates that the global total confidence variance converges in time and the convergence value is lower than a preset value; S302, when the flag state is active, perform the step of collision detection based on the second road spectrum information of the current time step and the historical road spectrum information in the target space to obtain the collision detection result.

[0035] In this embodiment, for each spatial network, the following is adopted: Figure 2 The grid lifecycle state machine management mechanism shown here establishes an independent lifecycle state machine for each spatial grid. Based on data convergence and state conflict determination, the grid state is divided into monitoring state, active state, and shadow verification state, as follows: When a vehicle uploads road surface elevation data for the first time on a new road section, the grid is initialized and marked as monitored. The cloud silently records and continuously updates the global total confidence variance of the grid according to the inverse variance fusion rule, without transmitting road spectrum information to vehicles entering the grid from behind.

[0036] When the global total confidence variance converges and falls below the set safe activation threshold, the grid enters the active state. The cloud continuously updates the global total confidence variance of the grid according to the inverse variance fusion rule and transmits road spectrum information to vehicles behind.

[0037] In the active state, collision detection is performed on the spatial network. If the collision detection result indicates a collision, the system enters the shadow verification state. In the shadow verification state, cloud data updates are frozen, parallel shadow branches are established, and cross-validation using multi-vehicle data is performed. After confirmation, the cloud road spectrum is overwritten.

[0038] In this embodiment, conflict detection is performed only when the global total confidence variance of the spatial road spectrum information converges in time and the convergence value is lower than a preset value. This can prevent meaningless conflict detection when the road spectrum information of a new space has just been perceived and the perceived data is too small (i.e., in the monitoring state), thus avoiding the waste of cloud computing resources.

[0039] In step S103 of some embodiments, conflict detection is used to measure the consistency between the second road spectrum information and the historical road spectrum information at the current time step in the target space, in order to determine whether there has been a significant change in road surface elevation. The historical road spectrum information can refer to the road spectrum information fused from multiple vehicles over the previous N time steps, such as the road spectrum information fused from multiple vehicles in the previous time step. The global total confidence variance of the historical road spectrum information needs to undergo time decay management. A dynamic information age preservation mechanism is introduced in the cloud to periodically (e.g., every 24 hours) manage the decay of the global total confidence variance of the data already stored in the grid.

[0040] Global total confidence variance stored in the grid Depending on data dwell time It expands exponentially, and its decayed global total confidence variance is expressed as: ; in, This is the global total confidence variance determined for this grid during the multi-vehicle fusion update in the previous time step; This refers to the time since the data has resided in the cloud grid. The dynamic attenuation constant is calculated and generated by the cloud by comprehensively calling road grade information, real-time weather, traffic density and other factors. This represents the global total confidence variance that participates in the fusion calculation of the current time step after time decay management.

[0041] In some embodiments, step S103 may include, but is not limited to, the following steps: S401, Calculate the path spectrum deviation between the second path spectrum information and the historical path spectrum information at the current time step; S402, if the road spectrum deviation value is less than the deviation threshold, determine the non-conflict detection result; S403, when the road spectrum deviation value is greater than or equal to the deviation threshold, the degree of conflict is quantified based on the global total confidence variance of the second road spectrum information and the global total confidence of the historical road spectrum information, and then the conflict detection result is determined based on the degree of conflict.

[0042] Specifically, when the vehicle uploads the first road spectrum information, it can also carry the positioning quality variance. The cloud extracts the positioning quality variance from the data packet uploaded by the vehicle. For data that exceeds the preset horizontal and vertical safety benchmark thresholds (such as RTK signal loss caused by the vehicle entering a tunnel), the cloud directly removes it.

[0043] For legitimate data filtered by location quality, the cloud performs an initial judgment on the deviation between the first road spectrum information and the historical road spectrum information of the active grid. For example, it performs an initial judgment on the deviation between the elevation data of the current time step and the historical average elevation. If the deviation does not reach the severe conflict threshold (i.e., the deviation threshold), a conflict detection result is obtained indicating that the physical road surface has not changed, and then the process of combining historical road spectrum information is entered into the regular steady-state fusion process. If the deviation exceeds the severe conflict threshold, a conflict detection result is determined to indicate that the data is abnormal or the road surface has changed significantly. Then, the degree of conflict is further quantified, and corresponding strategies are taken based on the degree of conflict.

[0044] Considering that most road conditions are relatively stable, this embodiment first quickly determines whether there is a conflict by comparing the road spectrum data before and after. If there is no conflict, it directly enters the process of merging the old and new road spectrum information to improve the efficiency of road spectrum updates. If a conflict is initially suspected, the degree of conflict is quantified and a corresponding strategy is adopted. This can accurately determine when a road spectrum needs to be built based on new data, further improving the accuracy of road spectrum updates and the efficiency of stable dynamic updates.

[0045] In some embodiments, step S403, which involves quantifying the degree of conflict based on the global total confidence variance of the second road spectrum information and the global total confidence of the historical road spectrum information, and then determining the conflict detection result based on the degree of conflict, may include, but is not limited to, the following steps: S501, take the reciprocal of the global total confidence variance of historical road spectrum information and normalize it to obtain the confidence level of historical information; S502, take the reciprocal of the global total confidence variance of the second path spectrum information and normalize it to obtain the current information confidence level; S503, determine the degree of conflict based on the trust level of historical information and the trust level of current information; S504, if the conflict level is greater than the conflict threshold and the current information trust level is greater than the trust level threshold, determine the conflict detection result where a conflict has occurred.

[0046] In this embodiment, for cases where a preliminary determination indicates a suspected conflict, the cloud-based system introduces the DS evidence theory to conduct a multi-source trust game, as detailed below: The overall confidence level of historical road map information in the cloud Global total confidence of the second road spectrum information newly uploaded by the vehicle Taking the reciprocals and normalizing them, we can map them to the degree of confidence in the DS evidence theory, denoted as . Trustworthiness of historical information and current information trust level They are represented as follows: ; ; Based on the aforementioned level of trust, a joint quality allocation matrix for the distributions of new and old data is constructed. Conflict factors in the orthogonal sum calculation are extracted, and the conflict coefficient between the new and old data is quantified. The conflict coefficient is used to measure the degree of conflict: ; The closer the value is to 1, the more intense the contradiction between the elevation reported by the vehicle and the historical elevation in the cloud.

[0047] Based on the conflict coefficient and the current information trust level, the cloud executes the following judgment logic and corresponding road spectrum update strategy: If the conflict coefficient The data is relatively large, but the current information trust level of the new data on the vehicle side is relatively high. The reliability is extremely low, indicating that the conflict is primarily caused by random errors on the vehicle's own end. This low-reliability, poor-quality data set is ignored and discarded, maintaining the road spectrum unchanged.

[0048] If multiple vehicles in different spatial locations simultaneously experience inconsistent conflicts with the cloud within a short period of time, and cannot reach a consensus among themselves, the current road surface is determined to be in an extremely complex state. The cloud then suspends the transmission of road spectrum information to subsequent vehicles entering the area.

[0049] Conflict coefficient Exceeding the threshold for severe conflict, and the current level of information trust. The cloud-based determination indicates that the physical road surface has most likely undergone real changes. Immediately freeze the current grid's data updates and forcibly switch the grid's lifecycle state from the active state to the shadow verification state, i.e., execute step S105.

[0050] In step S104 of some embodiments, if the road spectrum deviation value is less than the deviation threshold, it can be considered that no conflict has occurred. At this time, the current road spectrum information is determined based on the historical road spectrum information, its global total confidence variance, and the second road spectrum information. The historical road spectrum information and the second road spectrum information can be implemented based on the inverse variance weighted fusion method.

[0051] In some embodiments, the step S104, which determines the current road spectrum information based on historical road spectrum information, its global total confidence variance, and the second road spectrum information, may include, but is not limited to, the following steps: S601, the reciprocal of the information confidence variance of each second path spectrum information is used as the fusion weight, and then multiple second path spectrum information are weighted and fused to obtain the third path spectrum information; S602, the reciprocal of the global total confidence variance of historical road spectrum information is used as the fusion weight, and then the third road spectrum information and historical road spectrum information are weighted and fused to obtain the current road spectrum information; S603, based on the fusion weights of historical road spectrum information and the fusion weights of each second road spectrum information, update the global total confidence variance of the current road spectrum information.

[0052] Specifically, if the new data is determined to be legitimate and without serious conflicts, an inverse variance weighted fusion method is used to fuse historical road spectrum information and second road spectrum information based on the historical and current confidence variances to obtain the current road spectrum information. The total confidence variance of the second road spectrum information reported by the vehicle The reciprocal of the elevation is used as the inversion value. The fusion weight.

[0053] For the received number Road surface elevation data for each vehicle, latest average elevation within the cloud grid. The fusion formula is: ; In the formula, This is the average historical elevation of this grid in the cloud-based road spectrum (i.e., historical road spectrum information). The global total confidence variance of historical road spectrum information after time decay management; and These are the road surface elevation inversion value (i.e., the second road spectrum information) and the information confidence variance of the newly reported vehicle i.

[0054] Synchronously update the global variance of this grid: ; For batch processing scenarios where multiple vehicles simultaneously report within the same time tolerance window (e.g., within 10ms), the grid global elevation mean is used. The update is extended to the following formula, and the fused current road spectrum information is obtained through the following formula: ; The global total confidence variance of this grid is updated synchronously to obtain the global total confidence variance of the current road spectrum information: ; Store the current state and complete the first step. After fusing data from all vehicles or the current batch, the system will calculate the latest average elevation value of the grid. With converged global variance Store the route map in the cloud.

[0055] The prior parameters are updated and the loop is closed. When the data uploaded in the next time step is received, the cloud extracts the current road spectrum information (i.e. the fused elevation mean) and the global total confidence variance stored in the current time step. After time decay management, they are used as the prior historical road spectrum information and the global total confidence variance for the fusion calculation in the next time step, respectively, thus forming a closed loop and realizing the continuous rolling update of road spectrum data in the cloud.

[0056] In step S105 of some embodiments, if it is determined that the road surface has actually changed (i.e., a real conflict has occurred) based on the degree of conflict and the current information trust level, the historical road spectrum information is no longer fused. Instead, the current road spectrum information is reconstructed based on the multi-vehicle first road spectrum information in the continuously collected target space, that is, the parallel shadow branch cross-verification and overwrite process is executed.

[0057] In some embodiments, the step S105 of determining the current road spectrum information based on the multi-vehicle first road spectrum information in the continuously collected target space may include, but is not limited to, the following steps: S701, based on the information confidence variance, performs data filtering on the first road spectrum information of multiple vehicles in the continuously collected target space; S702, perform multi-vehicle cross-validation on the first road spectrum information that has passed the screening to determine whether multi-vehicle information evidence resonance has been achieved; multi-vehicle cross-validation includes multi-vehicle consistency verification and conflict verification between multi-vehicle and historical road spectrum information. S703, when multi-vehicle information evidence resonance is achieved, determines the first converged road spectrum information as the current road spectrum information, and determines the minimum information confidence variance as the global total confidence variance of the current road spectrum information.

[0058] In this embodiment, the parallel shadow branch cross-validation and overwrite process is as follows: The spatial grid (i.e., the target space) switches to the shadow verification state, and the cloud-based roadmap opens a shadow elevation branch parallel to the roadmap grid in the background. The old elevation average in the roadmap grid is forcibly frozen and updated, and the cloud suspends the transmission of roadmap information to vehicles about to enter the grid.

[0059] The system collects road spectrum elevation and variance data from multiple subsequent vehicles that have passed through the grid. Within the shadow branch, it initiates an evidence quality game. During the multi-source data fusion process, the vehicle evidence with the smallest variance quickly absorbs inferior opinions with larger variances. When multiple independent vehicles without spatiotemporal correlation report high-confidence elevation data that corroborate each other, and all conflict with the historical elevation mean in the road spectrum grid but consistently point to the current elevation of the shadow branch, cross-vehicle evidence resonance is formed.

[0060] When N consecutive high-confidence vehicles pass anomaly filtering and location drift verification, and their reported data all converge to the shadow elevation, or when the cumulative global total confidence variance within the shadow branch decreases to the minimum confirmation threshold, the cloud system determines that multiple vehicles have reached a consensus. It then extracts the converged elevation mean and minimum information confidence variance from the shadow branch and directly and losslessly overwrites and replaces the outdated data in the road spectrum grid. After overwriting, the bypass shadow branch is immediately destroyed, and the state of the spatial grid is restored from the shadow verification state to the active state. The cloud resumes transmitting road spectrum information to vehicles approaching the grid, completing the closed-loop dynamic self-healing of the cloud road spectrum.

[0061] This embodiment introduces a lightweight filtering and total confidence quantification mechanism on the vehicle side, and a spatiotemporal grid decay and shadow mode state machine mechanism on the cloud side. When a serious conflict is detected in high-confidence physical data, the cloud road spectrum grid update is actively frozen and a parallel shadow branch is established in the bypass. Non-destructive confirmation is performed through multi-vehicle cross-verification based on DS evidence theory, achieving rapid self-healing of real road surface changes without compromising the original safety benchmark, while removing noise interference.

[0062] This application also provides a vehicle-cloud collaborative road spectrum dynamic update system, including: The first module is used to collect first road spectrum information from each vehicle terminal; the first road spectrum information carries the information confidence variance. The second module is used to perform temporal-space alignment mapping and statistical analysis on the first path spectrum information collected at the current time step, and to determine the second path spectrum information in the target space at the current time step and its global total confidence variance. The third module is used to perform conflict detection based on the second road spectrum information at the current time step and the historical road spectrum information in the target space, and obtain the conflict detection result; wherein, the global total confidence variance of the historical road spectrum information is processed by time decay. The fourth module is used to determine the current road spectrum information based on historical road spectrum information, its global total confidence variance, and the second road spectrum information when the conflict detection result indicates no conflict. The fifth module is used to determine the current road spectrum information based on the first road spectrum information of multiple vehicles in the continuously collected target space when the collision detection result indicates that a collision has occurred.

[0063] It is understood that the methods described in the above method embodiments are applicable to this system embodiment. The specific functions implemented in this system embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0064] This application also provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the above-described method. This electronic device can be any smart terminal, including tablet computers, in-vehicle computers, etc.

[0065] It is understood that the content of the above method embodiments is applicable to this device embodiment. The specific functions implemented by this device embodiment are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0066] Please see Figure 3 , Figure 3 The hardware structure of an electronic device according to another embodiment is illustrated. The electronic device includes: The processor 901 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this application. The memory 902 can be implemented as a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 902 can store the operating system and other applications. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 902 and is called and executed by the processor 901. The 903 input / output interface is used to implement information input and output. The communication interface 904 is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.). Bus 905 transmits information between various components of the device (e.g., processor 901, memory 902, input / output interface 903, and communication interface 904); The processor 901, memory 902, input / output interface 903, and communication interface 904 are connected to each other within the device via bus 905.

[0067] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method.

[0068] It is understood that the content of the above method embodiments is applicable to this storage medium embodiment. The specific functions implemented in this storage medium embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0069] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0070] It is understood that the content of the above method embodiments is applicable to the embodiments of this program product. The specific functions implemented by the embodiments of this program product are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0071] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0072] The embodiments described in this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided by the embodiments of this application. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems.

[0073] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of this application, and may include more or fewer steps than shown, or combine certain steps, or different steps.

[0074] The system embodiments described above are merely illustrative. The modules described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0075] Those skilled in the art will understand that all or some of the steps in the methods disclosed above, as well as the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, or suitable combinations thereof.

[0076] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or modules is not necessarily limited to those steps or modules explicitly listed, but may include other steps or modules not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0077] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0078] In the embodiments provided in this application, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative; for instance, the division of modules described above is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0079] The modules described above as separate components may or may not be physically separate. The components shown as modules may or may not be physical modules; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0080] Furthermore, the functional modules in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The integrated modules described above can be implemented in hardware or as software functional modules.

[0081] If the integrated module is implemented as a software functional module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes multiple instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing programs, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0082] The preferred embodiments of the present application have been described above with reference to the accompanying drawings, but this does not limit the scope of the claims of the present application. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and substance of the embodiments of the present application shall be within the scope of the claims of the present application.

Claims

1. A method for dynamic updating of road spectrum in vehicle-cloud collaboration, characterized in that, The method includes the following steps: First road spectrum information is collected from each vehicle terminal; wherein the first road spectrum information carries information confidence variance. Perform temporal-space alignment mapping and statistical analysis on the first path spectrum information collected at the current time step to determine the second path spectrum information in the target space at the current time step and its global total confidence variance. Conflict detection is performed based on the second road spectrum information at the current time step and the historical road spectrum information in the target space to obtain the conflict detection result; wherein, the global total confidence variance of the historical road spectrum information is processed by time decay. If the conflict detection result indicates no conflict, the current road spectrum information is determined based on the historical road spectrum information, its global total confidence variance, and the second road spectrum information. If the conflict detection result indicates that a conflict has occurred, the current road spectrum information is determined based on the first road spectrum information of multiple vehicles in the target space that is continuously collected.

2. The method for dynamic updating of road spectrum in vehicle-cloud collaboration according to claim 1, characterized in that, The vehicle-mounted device collects the first road spectrum information through the following steps: Select road surface perception data under normal driving conditions, and then perform positioning and coordinate mapping on the road surface perception data to determine the first road spectrum information; The information confidence variance of the first road spectrum information is determined based on the sensor basis variance, positioning quality variance, and vehicle speed deviation penalty variance.

3. The method for dynamic updating of road spectrum in vehicle-cloud collaboration according to claim 1, characterized in that, Before the step of performing conflict detection based on the second road spectrum information at the current time step and the historical road spectrum information in the target space to obtain the conflict detection result, the vehicle-cloud collaborative road spectrum dynamic update method further includes the following steps: Obtain the flag state of the target space; the flag state of the target space is one of the following: monitoring state, active state, and shadow verification state. When the flag state is in the active state, the step of performing conflict detection based on the second road spectrum information of the current time step and the historical road spectrum information in the target space to obtain the conflict detection result is executed.

4. The method for dynamic updating of road spectrum in vehicle-cloud collaboration according to claim 2, characterized in that, The process of performing conflict detection based on the second path spectrum information and historical path spectrum information at the current time step to obtain conflict detection results includes the following steps: Calculate the path spectrum deviation between the second path spectrum information and the historical path spectrum information at the current time step; If the road spectrum deviation value is less than the deviation threshold, a non-collision collision detection result is determined; If the deviation value of the road spectrum is greater than or equal to the deviation threshold, the degree of conflict is quantified based on the global total confidence variance of the second road spectrum information and the global total confidence of the historical road spectrum information, and then the conflict detection result is determined based on the degree of conflict.

5. The method for dynamic updating of road spectrum in vehicle-cloud collaboration according to claim 4, characterized in that, The step of quantifying the degree of conflict based on the global total confidence variance of the second road spectrum information and the global total confidence of the historical road spectrum information, and then determining the conflict detection result based on the degree of conflict, includes the following steps: The global total confidence variance of the historical road spectrum information is taken in reciprocal and normalized to obtain the historical information confidence level. The global total confidence variance of the second path spectrum information is taken in reciprocal and normalized to obtain the current information confidence level; The degree of conflict is determined based on the historical information trust level and the current information trust level; If the degree of conflict is greater than the conflict threshold and the current information trust level is greater than the trust level threshold, a conflict detection result is determined.

6. The method for dynamic updating of road spectrum in vehicle-cloud collaboration according to claim 1, characterized in that, The step of determining the current road spectrum information based on the historical road spectrum information, its global total confidence variance, and the second road spectrum information includes the following steps: The inverse of the information confidence variance of each second path spectrum information is used as the fusion weight, and then multiple second path spectrum information are weighted and fused to obtain the third path spectrum information; The reciprocal of the global total confidence variance of the historical road spectrum information is used as the fusion weight, and then the third road spectrum information and the historical road spectrum information are weighted and fused to obtain the current road spectrum information. The global total confidence variance of the current road spectrum information is updated based on the fusion weights of the historical road spectrum information and the fusion weights of each of the second road spectrum information.

7. The method for dynamic updating of road spectrum in vehicle-cloud collaboration according to claim 1, characterized in that, The step of determining the current road spectrum information based on the continuously collected first road spectrum information of multiple vehicles in the target space includes the following steps: Data filtering is performed on the continuously collected first road spectrum information of multiple vehicles in the target space based on the information confidence variance; Multi-vehicle cross-validation is performed on the first road spectrum information that has passed the screening to determine whether multi-vehicle information evidence resonance has been achieved; the multi-vehicle cross-validation includes multi-vehicle consistency verification and conflict verification between multi-vehicle and historical road spectrum information. When multiple vehicle information evidence resonates, the first converged road spectrum information is determined as the current road spectrum information, and the minimum information confidence variance is determined as the global total confidence variance of the current road spectrum information.

8. A vehicle-cloud collaborative road spectrum dynamic update system, characterized in that, include: The first module is used to collect first road spectrum information from each vehicle. The first road spectrum information carries the information confidence variance; The second module is used to perform temporal-space alignment mapping and statistical analysis on the first path spectrum information collected at the current time step, and to determine the second path spectrum information in the target space at the current time step and its global total confidence variance. The third module is used to perform conflict detection based on the second road spectrum information at the current time step and the historical road spectrum information in the target space, and obtain the conflict detection result; wherein, the global total confidence variance of the historical road spectrum information is processed by time decay. The fourth module is used to determine the current road spectrum information based on the historical road spectrum information and its global total confidence variance and the second road spectrum information when the conflict detection result indicates that there is no conflict; The fifth module is used to determine the current road spectrum information based on the continuously collected first road spectrum information of multiple vehicles in the target space when the conflict detection result indicates that a conflict has occurred.

9. An electronic device, characterized in that, The electronic device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the method according to any one of claims 1 to 7.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1 to 7.

Images