A method for processing map data of a digital map

Abstract

The application discloses a kind of methods for processing map data of digital map, it is related to vehicle system control technical field, including steps: S1, data acquisition and preprocessing;S2, data fusion and analysis;S3, real-time update and maintenance;S4, real-time decision and control;S5, feedback and optimization.The method for processing map data of digital map, compared with completely relying on network transmission to obtain data, it is less affected by network condition, with advanced data transmission protocol and network technology, data can be transmitted in real time in vehicle system, effectively improve the real-time of map data.At the same time, it can quickly, accurately and efficiently process the map data of digital map, based on the process of efficient processing, with incremental updating means, especially suitable for large amount of data, real-time requirement is high, further improve the real-time of map data, so as to improve the map data processing effect of digital map.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicle system control, in particular to a method for processing map data of a digital map. BACKGROUND

[0002] Vehicle system refers to the total of all subsystems inside a car, which work together to enable the car to run normally. Vehicle system covers multiple aspects, including but not limited to power system, transmission system, driving system, braking system, steering system, electrical system, cab system, frame system, and auxiliary driving system, etc., and each subsystem has its specific function and task.

[0003] In modern automobile technology, vehicle system is increasingly closely related to digital map data. Digital map data provides accurate geographic location information for vehicles, enabling vehicles to accurately determine their own position and plan the best driving route. In addition, in combination with positioning systems such as GPS, real-time positioning and navigation functions of vehicles can be realized. During navigation, vehicle system will continuously adjust and optimize the driving route according to map data and real-time traffic information, in order to avoid congested road sections or construction areas, and improve driving efficiency and safety. In addition, vehicle system can also monitor and remind the driving behavior of the driver according to the traffic rule information in the map data, to ensure that the driving behavior complies with the traffic rules, and through in-depth analysis and processing of digital map data, potential dangerous factors (such as sharp turns, steep slopes, intersections, etc.) are identified, and early warning or preventive measures are taken to reduce traffic accidents and improve driving safety.

[0004] However, in actual use, due to the high real-time requirement of vehicle system control on map data, the transmission of map data requires a certain time, especially in poor network conditions, data transmission delay will be further aggravated, and processing and analysis of map data also require time, especially in the case of large data volume and complex processing algorithm, the processing time will be longer, which makes the existing method often have delay when processing map data, so that the real-time requirement of vehicle system control is difficult to meet.

[0005] Therefore, it is urgent to improve this defect, and the present application is to study and improve the existing technology and deficiencies, and to provide a method for processing map data of a digital map. SUMMARY

[0006] The purpose of the present application is to provide a method for processing map data of a digital map to solve the problems raised in the background art.

[0007] To achieve the above object, the present application provides the following technical scheme: a method for processing map data of a digital map, comprising the following steps:

[0008] S1, data acquisition and preprocessing: using sensors (such as GPS, LiDAR, camera, etc.) and real-time traffic data sources, real-time acquisition of road geometry, obstacle position, traffic sign, traffic flow and other key information, and cleaning, denoising, filtering operation on the collected raw data, removing invalid data, repeated data, and repairing missing values, improving data quality and accuracy;

[0009] S2, data fusion and analysis: fuse map data from different sources, use geographic information system (GIS) technology to process (including coordinate conversion, data format conversion, data compression, etc.), analyze (spatial relationship analysis, statistical analysis and modeling of map data) and display (analysis results are displayed in the form of geographic charts, statistical charts, dynamic demonstrations, etc.) geographic information data, real-time analysis of vehicle position, matching vehicle positioning data with map data, and determining the accurate position of the vehicle on the map;

[0010] S3, real-time update and maintenance: establish a real-time update mechanism, automatically acquire new data from the data source, and perform incremental update to ensure the timeliness and accuracy of the map data, and periodically check and repair the map data to ensure the integrity and reliability of the data;

[0011] S4, real-time decision and control: according to the real-time updated map data and vehicle state information, the vehicle system control module makes real-time decisions such as path planning, lane keeping, obstacle avoidance, etc., and converts the decision results into specific control instructions to control the motion state of the vehicle through the actuator, ensuring that the vehicle can maintain a stable motion state under various conditions;

[0012] S5, feedback and optimization: collect feedback information during vehicle operation, such as actual driving trajectory, road condition changes, etc., compare and analyze with map data, and optimize the map data processing method according to the feedback results to improve processing efficiency and accuracy.

[0013] Further, in step S1, the sensors include GPS, LiDAR, camera, laser scanner;

[0014] The GPS determines the position (longitude, latitude and height) and time information of the receiver by receiving signals from satellites, which is used for vehicle positioning and provides real-time geographic position information of the vehicle;

[0015] The LiDAR determines the distance and position of the target by emitting a laser beam and measuring the time it takes to reflect back, and can generate a three-dimensional point cloud map of the surrounding environment, providing high-precision spatial information. LiDAR is used for environmental perception, including measurement of road geometry, accurate detection of obstacle position, identification of vehicles and pedestrians, etc.

[0016] The camera generates images or videos by capturing light, and captures visual information of different ranges according to different resolutions and focal lengths, including identification of traffic signs and signals, lane line detection, tracking of vehicles and pedestrians, etc. It cooperates with image processing and computer vision technology to extract rich visual information, providing important perception capabilities for autonomous driving and intelligent transportation systems.

[0017] The laser scanner measures the geometry of the road surface, including road surface flatness, slope, curvature, etc., by emitting a laser beam and receiving its reflected signal.

[0018] Further, in step S1, the processing operation of the original data includes:

[0019] 1) Data cleaning:

[0020] Missing value processing: For missing sensor data or blank information in the data source, adopt filling strategies (such as using average value, median, mode, etc.) or deletion strategies (if the missing data has little effect on the overall analysis);

[0021] Outlier detection and processing: Use statistical methods (such as Z-score, IQR, etc.) or machine learning algorithms to identify outliers, and choose to retain, correct or delete these outliers according to actual conditions (in traffic data, outliers include sudden changes in speed, unreasonable position information, etc.);

[0022] Data standardization and normalization: Standardize or normalize the data of different sensors and data sources to facilitate comparison and fusion in subsequent analysis;

[0023] 2) Denoising: Use digital filtering (such as low-pass filtering, high-pass filtering, band-pass filtering, etc.), wavelet transform denoising methods to reduce or eliminate noise (such as electromagnetic interference, mechanical vibration, etc.) interference during sensor data acquisition;

[0024] 3) Filtering: By retaining useful components in the signal and suppressing or removing noise components, the signal quality is improved. In real-time traffic data processing, Kalman filtering algorithm is used for smoothing processing to solve the problem of position jitter in GPS data.

[0025] Further, in step S2, the pre-processed map data is transmitted in real time to the vehicle system through a data transmission protocol (such as TCP / IP, UDP, etc.) and network technology (such as 5G, Wi-Fi 6, etc.).

[0026] Further, in step S2, the multi-source data fusion specifically operates as follows: according to the characteristics of the data and the fusion target, a fusion method is selected, and through feature extraction and matching algorithms, the feature points from different data sources are associated to establish geometric and semantic relationships between the data for subsequent fusion processing.

[0027] Further, the fusion method includes model-based fusion, weight-based fusion, and feature-based fusion.

[0028] The model-based fusion integrates map data from different sources by constructing mathematical models. The specific operation steps are as follows: according to the characteristics of the data and the fusion target, a mathematical model (including statistical models, machine learning models, etc.) is selected for construction to describe the internal relationships and laws between the data, then the model is trained using part of the data, and the model is optimized according to the training results, and finally the trained model is used to fuse map data from different sources to obtain fused map data.

[0029] The weight-based fusion realizes fusion by assigning different weights to map data from different sources. The specific operation steps are as follows: by analyzing the accuracy, completeness, timeliness, etc. of the data, the map data from different sources is evaluated to determine its importance and reliability in the fusion process, then according to the data evaluation results, appropriate weights are assigned to the data from different sources, and finally the weighted fusion processing is performed on the map data from different sources according to the assigned weights to obtain the fused map data.

[0030] The feature-based fusion extracts feature information from map data from different sources and performs fusion processing at the feature level. The specific operation steps are as follows: using feature extraction algorithms, key feature information is extracted from map data from different sources, including geographic location, road information, building information, etc., and the extracted feature information is matched to find feature points or feature areas with similarities between different data sources, then through feature weighting, feature selection or feature fusion algorithms, etc., the matched feature information is fused at the feature level, and finally the original map data is reconstructed according to the fused feature information to obtain the fused map data.

[0031] Further, in step S2, the specific operation of vehicle position resolution and map matching: obtain the real-time position information of the vehicle through GPS or other positioning technology, and convert it to coordinates in the coordinate system of the map. Then, match the vehicle position data with the map data, and determine the accurate position of the vehicle on the map through steps such as error area selection, road selection set creation, angle filtering, and distance calculation.

[0032] The specific steps of matching vehicle positioning data with map data are as follows:

[0033] Error area selection: Since there may be errors in GPS signals or other sensor data, a reasonable error area must be defined to search for possible matching roads within this area.

[0034] Road selection set creation: Extract all candidate roads in the area from the map database to form a road selection set.

[0035] Angle filtering: Calculate and compare the angle between the vehicle's driving direction and the candidate road direction to exclude roads with large angles and further narrow the range of the road selection set.

[0036] Distance calculation: Further calculate the distance between the vehicle's position and the remaining candidate roads to determine the final matching road.

[0037] Matching data update: Update the vehicle position data using the matching result to ensure that the vehicle's display on the map is consistent with its actual position.

[0038] Further, in step S3, incremental update only processes the data that has changed since the last update when performing data update operations, without repeating the update of data that has not changed or has already been updated. The specific operation of incremental update is as follows:

[0039] Log tracking: Use database logs (such as MySQL's binlog), event sources (such as Kafka), or data version control mechanisms to track data changes.

[0040] Difference detection: Compare the data snapshot at the last synchronization with the current data to determine the changed parts.

[0041] Only update the changed data: Only write the changed data to the target database or data warehouse.

[0042] Further, in step S4, the real-time decision algorithm specifically includes:

[0043] Path planning algorithm: responsible for generating an optimal driving path according to the current position and target position of the vehicle, combining map information and traffic rules, and the path planning algorithm includes global path planning (generating a drivable area and a reference driving path based on known map information, combining local environmental information and real-time feedback information of the vehicle, and the global path planning algorithm is usually based on graph search, heuristic search (such as A algorithm) or sampling method (such as RRT algorithm)), local path planning (based on global path planning, considering real-time environmental changes and vehicle dynamics, local path adjustment is carried out; local path planning algorithms such as artificial potential field method, dynamic window method and model predictive control, etc.);

[0044] Lane keeping algorithm: used to ensure that the vehicle can stably drive in the lane it is in, avoiding lane deviation, and the lane keeping algorithm includes: vision-based lane keeping (using a camera to capture lane line information, identifying lane lines through image processing technology, and calculating steering wheel angle according to the relative position between the vehicle and the lane line to achieve lane keeping), model prediction-based lane keeping (predicting the future driving trajectory of the vehicle through the vehicle dynamics model, and adjusting the control parameters to ensure that the vehicle remains in the lane in combination with the lane line information);

[0045] Obstacle avoidance algorithm: responsible for making timely decisions when obstacles are detected to avoid collisions with obstacles, and the obstacle avoidance algorithm uses radar, LiDAR, camera and other sensors to detect obstacles around the vehicle, and evaluates the collision risk according to the position, speed, size and other information of the obstacles, then formulates an obstacle avoidance strategy according to the risk evaluation result, such as deceleration, lane change, emergency braking, etc., after decision making, local path planning is carried out to generate a driving path that avoids obstacles.

[0046] Further, in step S5, the map data processing method is optimized and specifically includes:

[0047] Data updating and correction: updating map data in a timely manner according to feedback results, including road information, road condition information, traffic facilities, etc., correcting data errors or omissions found;

[0048] Algorithm optimization: optimizing map data processing algorithms for problems found in data analysis, for example, improving path planning algorithms to improve accuracy; optimizing road condition prediction algorithms to more accurately reflect real-time road conditions, and introducing machine learning and deep learning technologies to improve the intelligent level of map data processing and road condition prediction;

[0049] Quality control and evaluation: establish a quality control system to monitor and evaluate the processing process of map data, regularly evaluate the accuracy and usability of map data to ensure that the quality of map data meets user needs;

[0050] User participation and feedback mechanism: Establish a user participation mechanism to encourage users to actively provide feedback on road conditions and map issues, and improve the feedback processing process to ensure that user feedback is responded to and processed in a timely manner.

[0051] This invention provides a method for processing map data from digital maps, which has the following advantages:

[0052] This invention's data acquisition methods include not only sensors but also real-time traffic data sources. Some data comes directly from devices and systems integrated into the vehicle itself. Compared to relying entirely on network transmission, it is less affected by network conditions. Combined with advanced data transmission protocols and network technologies, it enables real-time data transmission within vehicle systems, effectively improving the real-time performance of map data. Furthermore, this invention can process digital map data quickly, accurately, and efficiently. Based on this efficient processing flow, and with incremental update methods, it is particularly suitable for situations with large data volumes and high real-time requirements, further enhancing the real-time performance of map data and thus improving the overall map data processing effectiveness. Attached Figure Description

[0053] Figure 1 This is a flowchart illustrating the steps of a method for processing map data from a digital map according to the present invention. Detailed Implementation

[0054] The embodiments of the present invention will be described in further detail below with reference to the accompanying drawings and examples. The following examples are for illustrative purposes only and should not be construed as limiting the scope of the invention.

[0055] like Figure 1 As shown, a method for processing map data for digital maps includes the following steps:

[0056] S1. Data Acquisition and Preprocessing:

[0057] By utilizing sensors (such as GPS, LiDAR, cameras, etc.) and real-time traffic data sources (vehicle sensor data, road infrastructure sensor data, public transportation system data, mobile application and user data, third-party data sources), key information such as road geometry, obstacle location, traffic signs, and traffic flow can be acquired in real time. The collected raw data is then cleaned, denoised, and filtered to remove invalid and duplicate data and repair missing values, thereby improving data quality and accuracy.

[0058] In this embodiment, the sensors include GPS, LiDAR, cameras, laser scanners, etc. GPS determines the receiver's location (longitude, latitude, and altitude) and time information by receiving signals from satellites, used for vehicle positioning, and provides real-time geographical location information. LiDAR determines the distance and location of targets by emitting laser beams and measuring the time it takes for them to reflect back, and can generate a 3D point cloud map of the surrounding environment, providing high-precision spatial information. LiDAR is used for environmental perception, including measuring road geometry, accurately detecting obstacle locations, and identifying vehicles and pedestrians. Cameras generate images or videos by capturing light, and capture different ranges of visual information based on different resolutions and focal lengths, including the recognition of traffic signs and signals, lane detection, and tracking of vehicles and pedestrians. Combined with image processing and computer vision technologies, rich visual information is extracted, providing crucial perception capabilities for autonomous driving and intelligent transportation systems. Laser scanners measure the geometry of the road surface, including road surface smoothness, slope, and curvature, by emitting laser beams and receiving their reflected signals.

[0059] In this embodiment, the processing operations for the raw data include:

[0060] 1) Data cleaning:

[0061] Missing value handling: For missing sensor data or blank information in the data source, adopt strategies such as filling (e.g., using the mean, median, mode, etc.) or deleting (if the missing data has little impact on the overall analysis);

[0062] Outlier detection and handling: Statistical methods (such as Z-score, IQR, etc.) or machine learning algorithms are used to identify outliers, and these outliers are selected to be retained, corrected or deleted according to the actual situation (in traffic data, outliers include sudden speed changes, unreasonable location information, etc.).

[0063] Data standardization and normalization: Standardize or normalize data from different sensors and data sources to facilitate comparison and fusion in subsequent analysis;

[0064] 2) Noise reduction: Digital filtering (such as low-pass filtering, high-pass filtering, band-pass filtering, etc.) and wavelet transform are used to reduce or eliminate noise interference (such as electromagnetic interference, mechanical vibration, etc.) on sensor data during the acquisition process.

[0065] 3) Filtering: By preserving useful components in the signal while suppressing or removing noise components, signal quality can be improved. In real-time traffic data processing, the Kalman filter algorithm is used to smooth the position jitter problem in GPS data.

[0066] S2. Data Fusion and Analysis:

[0067] The preprocessed map data is transmitted to the vehicle system in real time via data transmission protocols (such as TCP / IP, UDP, etc.) and network technologies (such as 5G, Wi-Fi 6, etc.). Map data from different sources are fused and processed using Geographic Information System (GIS) technology (including coordinate transformation, data format conversion, data compression, etc.), analyzed (spatial relationship analysis, statistical analysis, and modeling of map data, such as calculating the distance between vehicles and roads, analyzing vehicle driving trajectories, predicting traffic flow, etc.), and displayed (the analysis results are displayed intuitively in the form of geographic charts, statistical charts, dynamic demonstrations, etc., such as displaying vehicle location, driving trajectory, and surrounding road information on the map in real time, and displaying traffic flow and congestion through statistical charts, etc.). The vehicle location is parsed in real time, and the vehicle positioning data is matched with the map data to determine the vehicle's accurate location on the map.

[0068] In this embodiment, the specific operation of multi-source data fusion is as follows: based on the characteristics of the data and the fusion objective, a fusion method is selected, and feature points from different data sources are associated through feature extraction and matching algorithms to establish geometric and semantic relationships between the data for subsequent fusion processing; the fusion methods include model-based fusion, weight-based fusion, and feature-based fusion;

[0069] The model-based fusion integrates map data from different sources by constructing a mathematical model. This method involves a deep understanding and analysis of the data in order to establish an accurate mathematical model to describe the relationships between the data. The specific steps are as follows: Based on the characteristics of the data and the fusion goal, a mathematical model (including statistical models, machine learning models, etc.) is selected and constructed to describe the inherent relationships and patterns between the data. Then, a portion of the data is used to train the model, and the model is optimized based on the training results to improve its accuracy and generalization ability. Finally, the trained model is used to fuse map data from different sources to obtain the fused map data.

[0070] The weight-based fusion achieves fusion by assigning different weights to map data from different sources. These weights reflect the importance and reliability of different data sources in the fusion process. The specific steps are as follows: by analyzing the accuracy, completeness, and timeliness of the data, the map data from different sources are evaluated to determine their importance and reliability in the fusion process. Then, based on the data evaluation results, corresponding weights are assigned to the data from different sources. The magnitude of the weight reflects the degree of contribution of the data to the fusion result. Finally, the map data from different sources are weighted and fused according to the assigned weights to obtain the fused map data.

[0071] The feature-based fusion method extracts feature information from map data from different sources and performs fusion processing at the feature level. This method can fully utilize the feature information of the data to improve the accuracy and reliability of the fusion results. The specific operation steps are as follows: a feature extraction algorithm is used to extract key feature information from map data from different sources, including geographical location, road information, building information, etc., and the extracted feature information is matched to find similar feature points or feature regions between different data sources. Then, the matched feature information is fused at the feature level through feature weighting, feature selection, or feature fusion algorithms. Finally, the original map data is reconstructed based on the fused feature information to obtain the fused map data.

[0072] In this embodiment, the specific operations for vehicle location parsing and map matching are as follows: Real-time vehicle location information is obtained through GPS or other positioning technologies, converted into coordinates in a map coordinate system, and then the vehicle location data is matched with map data to determine the vehicle's accurate location on the map. The specific steps for matching vehicle location data with map data are as follows:

[0073] Error region selection (due to potential errors in GPS signals or other sensor data, a reasonable error region must be defined to search for possible matching roads within this region): The error region is defined according to a probability criterion, meaning that the error region must contain the vehicle's actual location with a certain probability. The size of the error region is determined comprehensively based on the accuracy of the GPS signal, the performance of the sensor, and environmental factors (such as urban canyons, tall buildings blocking the view, etc.). If the error region is too large, it will increase the capacity of the road selection set and consume more computation time; if it is too small, it may miss the correct matching roads.

[0074] Creating the road selection set (extracting all candidate roads in the area from the map database to form the road selection set): using road data in the map database, all possible roads are retrieved within the error area, and the retrieved roads are filtered according to certain rules (such as road type, direction of travel, etc.) to form the final road selection set;

[0075] Angle filtering (an effective method to further narrow down the road selection set by calculating and comparing the angle between the vehicle's current direction of travel and the candidate road direction, eliminating roads with excessively large angles): Calculate the angle between the vehicle's current direction of travel and the candidate road direction, set an angle threshold (such as 15°, 30°, etc.), and exclude roads with angles greater than the threshold from the road selection set;

[0076] Distance calculation (further calculate the distance between the vehicle position and the remaining candidate roads to determine the final matching road): Considering the characteristics of map data and computational efficiency, Euclidean distance, Manhattan distance and other distance calculation methods are selected to calculate the shortest distance between the vehicle position and each candidate road, and the road with the smallest distance is selected as the final matching road;

[0077] Matching data update (updating vehicle location data using matching results to ensure that the vehicle's display on the map matches its actual location): The matched road coordinates are used as the vehicle's current location coordinates. As the vehicle moves and the GPS signal is updated, the matching process is repeated continuously to achieve dynamic updates of the vehicle's location.

[0078] S3, Real-time updates and maintenance:

[0079] A real-time update mechanism is established to automatically retrieve new data from data sources and perform incremental updates, ensuring the timeliness and accuracy of map data. Simultaneously, map data is periodically verified and repaired to ensure its integrity and reliability. Incremental updates only process data that has changed since the last update, avoiding duplicate updates of unchanged or already updated data. The specific operations of incremental updates are as follows:

[0080] Log tracing: Use database logs (such as MySQL's binlog), event sources (such as Kafka), or data version control mechanisms to track data changes;

[0081] Difference detection: Compare the data snapshot from the last synchronization with the current data to identify the changed parts;

[0082] Update only changed data: Only write changed data to the target database or data warehouse;

[0083] In this embodiment, the process for establishing a real-time update mechanism is as follows:

[0084] Data source identification: Identify the types of data that need to be updated in real time, such as traffic conditions, POI information, road changes, etc., and identify reliable data sources. If an API interface is used as the data source, it is necessary to establish a cooperative relationship with the data provider and obtain the necessary API access permissions and keys.

[0085] Data Acquisition: Use programming languages ​​(such as Python, Java, etc.) to write automated scripts to retrieve data from data sources periodically or in real time. The scripts should be able to handle network requests, parse data formats (such as JSON, XML), and use caching technologies (such as Redis, Memcached) to store recently acquired data.

[0086] Data processing and incremental update: Design an incremental detection mechanism, such as using timestamps, version numbers, or hash values, to determine whether the data has changed. For data that has changed, perform an incremental update operation to add the new data to the map database and update the relevant indexes and caches.

[0087] In this embodiment, the map data verification and repair process is as follows:

[0088] Establish a regular verification mechanism to conduct a comprehensive check on map data. The verification content includes, but is not limited to, road network connectivity, POI information accuracy, and address matching correctness.

[0089] Data repair: For issues that can be automatically identified and repaired by algorithms (such as format errors, data redundancy, etc.), corresponding repair scripts are developed for processing; for issues that require manual judgment and repair (such as incorrect POI locations, newly added roads not being marked, etc.), an issue feedback and repair process is established, and a dedicated team handles them;

[0090] Set the cycle: Based on the update frequency and importance of the map data, set a reasonable verification and repair cycle; for example, real-time traffic information can be set to be verified once an hour, while static road and POI information can be verified once a day or once a week.

[0091] S4. Real-time Decision-Making and Control:

[0092] Based on real-time updated map data and vehicle status information, the vehicle system control module makes real-time decisions, such as path planning, lane keeping, and obstacle avoidance, and converts the decision results into specific control commands. Through actuators, the vehicle's motion state is controlled to ensure that the vehicle can maintain a stable motion state under various conditions.

[0093] In this embodiment, the real-time decision-making algorithm specifically includes:

[0094] Path planning algorithms are responsible for generating an optimal driving route based on the vehicle's current and target locations, combined with map information and traffic rules. Path planning algorithms include global path planning (generating drivable areas and reference routes based on known map information, combined with local environmental information and real-time vehicle feedback; global path planning algorithms are typically based on graph search, heuristic search (such as A algorithm), or sampling methods (such as RRT algorithm)) and local path planning (adjusting local paths based on real-time environmental changes and vehicle dynamics characteristics; local path planning algorithms include artificial potential field methods, dynamic window methods, and model predictive control).

[0095] Lane keeping algorithms are used to ensure that vehicles can drive stably within their lanes and avoid deviating from the lane. Lane keeping algorithms include: vision-based lane keeping (using cameras to capture lane line information, identifying lane lines through image processing technology, and calculating the steering wheel angle based on the relative position between the vehicle and the lane lines to achieve lane keeping) and model prediction-based lane keeping (predicting the future driving trajectory of the vehicle through vehicle dynamics models, and adjusting control parameters in conjunction with lane line information to ensure that the vehicle stays within the lane).

[0096] Obstacle avoidance algorithm: It is responsible for making timely decisions when an obstacle is detected to avoid collision with the obstacle. The obstacle avoidance algorithm uses sensors such as radar, lidar (LiDAR), and cameras to detect obstacles around the vehicle and assesses the collision risk based on information such as the position, speed, and size of the obstacle. Then, based on the risk assessment results, it formulates obstacle avoidance strategies, such as deceleration, lane changing, and emergency braking. After the decision is made, local path planning is performed to generate a driving path that avoids the obstacle.

[0097] In terms of implementing decision-making algorithms, autonomous driving systems typically combine multiple algorithms to cope with complex driving environments, as follows:

[0098] PID control algorithm: used for speed control, position tracking, etc., to make the vehicle travel along the expected trajectory by adjusting control parameters;

[0099] Fuzzy control algorithms have advantages in processing fuzzy or uncertain input information and can be used for obstacle avoidance decisions, driving mode switching, etc.

[0100] Model Predictive Control (MPC): Considering the vehicle's dynamic characteristics and future state, it generates optimal control commands through prediction and optimization, and is suitable for local path planning and obstacle avoidance control.

[0101] Deep learning algorithms, such as convolutional neural networks (CNN) and recurrent neural networks (RNN), can be used for obstacle detection, behavior prediction, and driving decisions.

[0102] S5, Feedback and Optimization:

[0103] Collect feedback information during vehicle operation, such as actual driving trajectory and road condition changes, compare and analyze it with map data, and optimize map data processing methods based on feedback results to improve processing efficiency and accuracy.

[0104] In this embodiment, the optimization of the map data processing method specifically includes:

[0105] Data updates and corrections: Update map data promptly based on feedback, including road information, traffic conditions, and transportation facilities; and correct any data errors or omissions found.

[0106] Algorithm optimization: To address the problems discovered during data analysis, optimize map data processing algorithms. For example, improve route planning algorithms to enhance accuracy; optimize traffic prediction algorithms to more accurately reflect real-time traffic conditions; and introduce machine learning and deep learning technologies to improve the intelligence level of map data processing and traffic prediction.

[0107] Quality Control and Evaluation: Establish a quality control system to monitor and evaluate the map data processing process, and regularly evaluate the accuracy and usability of the map data to ensure that the quality of the map data meets user needs;

[0108] User participation and feedback mechanism: Establish a user participation mechanism to encourage users to actively provide feedback on road conditions and map issues, and improve the feedback processing process to ensure that user feedback is responded to and processed in a timely manner.

[0109] The embodiments of the present invention are given for illustrative and descriptive purposes only, and are not intended to be exhaustive or to limit the invention to the forms disclosed. Many modifications and variations will be apparent to those skilled in the art. The embodiments were chosen and described in order to better illustrate the principles and practical application of the invention, and to enable those skilled in the art to understand the invention and to design various embodiments with various modifications suitable for a particular purpose.

Claims

1. A method for processing map data from digital maps, characterized in that, Includes the following steps: S1. Data Acquisition and Preprocessing: Using sensors and real-time traffic data sources, key road information is acquired in real time, including real-time road geometry, obstacle locations, traffic signs, and traffic flow. The acquired raw data is then cleaned, denoised, and filtered. S2. Data Fusion and Analysis: The map data from different sources is fused together, and the geographic information data is processed, analyzed and displayed using geographic information system technology. The vehicle location is analyzed in real time, and the vehicle location data is matched with the map data to determine the vehicle's accurate location on the map. In step S2, the preprocessed map data is transmitted to the vehicle system in real time through data transmission protocols and network technology. S3. Real-time update and maintenance: Establish a real-time update mechanism to automatically obtain new data from traffic data sources and perform incremental updates, while regularly verifying and repairing map data; S4. Real-time decision-making and control: Based on real-time updated map data and vehicle status information, the vehicle system control module makes real-time decisions and converts the decision results into specific control commands, which control the vehicle's motion state through actuators. S5. Feedback and Optimization: Collect feedback information during vehicle operation, compare and analyze it with map data, and optimize the map data processing method based on the feedback results.

2. The method for processing map data of digital maps according to claim 1, characterized in that, In step S1, the sensors include GPS, LiDAR, camera, and laser scanner; The GPS determines the receiver's location and time information by receiving signals from satellites, which is used for vehicle positioning and provides real-time geographical location information of the vehicle. The LiDAR determines the distance and position of a target by emitting a laser beam and measuring the time it takes for it to reflect back. It can also generate a three-dimensional point cloud map of the surrounding environment, providing high-precision spatial information. LiDAR is used for environmental perception. The camera generates images or videos by capturing light, and captures visual information of different ranges according to different resolutions and focal lengths. Combined with image processing and computer vision technology, it extracts rich visual information. The laser scanner measures the geometry of the road surface, including road surface smoothness, slope, and curvature, by emitting a laser beam and receiving its reflected signal.

3. The method for processing map data of digital maps according to claim 1, characterized in that, In step S1, the processing operations for the raw data include: 1) Data cleaning: Missing value handling: For missing sensor data or blank information in the data source, adopt strategies of filling or deleting; Outlier detection and handling: Identify outliers using statistical methods or machine learning algorithms, and select whether to retain, correct, or delete outliers based on the actual situation; Data standardization and normalization: Standardizing or normalizing data from different sensors and data sources; 2) Noise reduction: Digital filtering and wavelet transform are used to reduce or eliminate noise interference to sensor data during the acquisition process; 3) Filtering: By preserving useful components in the signal while suppressing or removing noise components, signal quality can be improved. In real-time traffic data processing, the Kalman filter algorithm is used to smooth the position jitter problem in GPS data.

4. The method for processing map data of digital maps according to claim 1, characterized in that, In step S2, the specific operation of multi-source data fusion is as follows: based on the characteristics of the data and the fusion objective, a fusion method is selected, and feature points from different data sources are associated through feature extraction and matching algorithms to establish geometric and semantic relationships between the data for subsequent fusion processing.

5. A method for processing map data of a digital map according to claim 4, characterized in that, The fusion methods include model-based fusion, weight-based fusion, and feature-based fusion. Model-based fusion integrates map data from different sources by constructing a mathematical model. Weight-based fusion achieves fusion by assigning different weights to map data from different sources. Feature-based fusion extracts feature information from map data from different sources and performs fusion processing at the feature level.

6. The method for processing map data of a digital map according to claim 1, characterized in that, In step S2, the specific operations of vehicle location parsing and map matching are as follows: real-time location information of the vehicle is obtained through GPS or other positioning technologies and converted into coordinates in the map coordinate system. Then, the vehicle location data is matched with the map data. Through error region selection, road selection set creation, angle filtering, distance calculation and matching data update, the accurate location of the vehicle on the map is determined.

7. The method for processing map data of a digital map according to claim 1, characterized in that, In step S3, incremental updates only process the data that has changed since the last update, without repeatedly updating data that has not changed or has already been updated. The specific operations of incremental updates are as follows: Log tracing: Using database logs, event sources, or data version control mechanisms to track data changes; Difference detection: Compare the data snapshot from the last synchronization with the current data to identify the changed parts; Update only changed data: Only write changed data to the target database or data warehouse.

8. The method for processing map data of a digital map according to claim 1, characterized in that, In step S4, the real-time decision-making algorithm specifically includes: Path planning algorithm: It is responsible for generating an optimal driving route based on the vehicle's current location and target location, combined with map information and traffic rules. The path planning algorithm includes global path planning and local path planning. Lane keeping algorithms are used to ensure that vehicles can drive stably within their lanes and avoid deviating from the lane. Lane keeping algorithms include vision-based lane keeping and model prediction-based lane keeping. Obstacle avoidance algorithm: It is responsible for making timely decisions when an obstacle is detected to avoid collision with the obstacle. The obstacle avoidance algorithm uses sensors to detect obstacles around the vehicle and assesses the collision risk based on information such as the position, speed and size of the obstacle. Then, based on the risk assessment results, it formulates obstacle avoidance strategies, including deceleration, lane changing and emergency braking. After the decision is made, local path planning is performed to generate a driving path that avoids the obstacle.

9. A method for processing map data of a digital map according to claim 1, characterized in that, In step S5, the optimization of the map data processing method specifically includes: Data updates and corrections: Update map data promptly based on feedback results, and correct any data errors or omissions found. Algorithm optimization: To address the problems discovered during data analysis, we will optimize the map data processing algorithm, introduce machine learning and deep learning technologies, and improve the intelligence level of map data processing and traffic prediction. Quality Control and Evaluation: Establish a quality control system to monitor and evaluate the map data processing process, and regularly evaluate the accuracy and usability of the map data to ensure that the quality of the map data meets user needs; User participation and feedback mechanism: Establish a user participation mechanism to encourage users to actively provide feedback on road conditions and map issues, and improve the feedback processing process to ensure that user feedback is responded to and processed in a timely manner.

Images