Vehicle driving control method and device, electronic equipment and storage medium

Abstract

The invention relates to a vehicle driving control method and device, electronic equipment and a storage medium, and the method applied to a cloud server comprises the steps: the cloud server can obtain a plurality of candidate vehicle point locations in a target path in a preset time period, carries out the processing of the plurality of candidate vehicle point locations, and obtains a target vehicle point location; and processing the target vehicle point location according to the time sequence to obtain a target track, associating the target track with the target path, generating an off-line track map packet corresponding to the target track, and sending the off-line track map packet to the vehicle, so that the vehicle performs vehicle driving control on the target path based on the off-line track map packet. By the adoption of the technical scheme, the problems that the intelligent driving function exits at the crossroad, lane selection is unreasonable, and the success rate of getting on and off the ramp is low can be solved, real-time updating of the driving track can be achieved, driving safety and comfort are improved, and the vehicle driving control requirement is met.

Description

Technical Field

[0001] The present disclosure relates to the field of vehicle control technology, and in particular to a vehicle driving control method, device, electronic equipment and storage medium. Background Art

[0002] The driving trajectory used in existing intelligent driving is usually provided by high-precision maps drawn by surveying and mapping vehicles. However, with the increase and change of road infrastructure, the turning trajectory angle is too large, the vehicle tilts, the passengers in the car are uncomfortable, the trajectory enters the unreasonable lane, resulting in reduced driving efficiency and other factors. This can easily lead to the exit of the intelligent driving function at intersections, unreasonable lane selection and low success rate of on and off ramps. In addition, the high-precision map relies on the update speed of the supplier and the update efficiency is slow. Therefore, the driving trajectory provided by the existing high-precision map cannot meet the driving needs of high comfort, high safety and high efficiency. Summary of the invention

[0003] In order to solve the above technical problems or at least partially solve the above technical problems, at least one embodiment of the present disclosure provides a vehicle driving control method, device, electronic device and storage medium.

[0004] In a first aspect, the present disclosure provides a vehicle driving control method, which is applied to a cloud server, comprising:

[0005] Obtain multiple candidate vehicle locations in the target path within a preset time period;

[0006] Processing the multiple candidate vehicle positions to obtain a target vehicle position;

[0007] Processing the target vehicle position according to the time sequence to obtain the target trajectory;

[0008] The target trajectory is associated with the target path, and an offline trajectory map package corresponding to the target trajectory is generated and sent to the vehicle, so that the vehicle performs vehicle driving control on the target path based on the offline trajectory map package.

[0009] In a second aspect, the present disclosure provides a vehicle driving control method, the method being applied to a vehicle, comprising:

[0010] Receiving an offline trajectory map package sent by a cloud server; wherein the cloud server obtains a plurality of candidate vehicle positions in a target path within a preset time period and processes them to obtain a target vehicle position, processes the target vehicle position in a time sequence to obtain a target trajectory, associates the target trajectory with the target path, and generates an offline trajectory map package corresponding to the target trajectory;

[0011] The vehicle driving control is performed on the target path based on the offline trajectory map package.

[0012] In a third aspect, the present disclosure provides a vehicle driving control device, which is applied to a cloud server, comprising:

[0013] A first acquisition module is used to acquire multiple candidate vehicle points in a target path within a preset time period;

[0014] A first processing module is used to process the multiple candidate vehicle positions to obtain a target vehicle position;

[0015] A second processing module is used to process the target vehicle position in time sequence to obtain a target trajectory;

[0016] an associating module, used to associate the target trajectory with the target path;

[0017] A generating and sending module is used to generate an offline track map package corresponding to the target track and send it to the vehicle, so that the vehicle can perform vehicle driving control on the target path based on the offline track map package.

[0018] In a fourth aspect, the present disclosure provides a vehicle driving control device, applied to a charging pile terminal, comprising:

[0019] A receiving module, used for receiving an offline track map package sent by a cloud server; wherein the cloud server obtains a plurality of candidate vehicle positions in a target path within a preset time period and processes them to obtain a target vehicle position, processes the target vehicle position in a time sequence to obtain a target track, associates the target track with the target path, and generates an offline track map package corresponding to the target track;

[0020] A control module is used to control vehicle driving on the target path based on the offline trajectory map package.

[0021] In a fifth aspect, the present disclosure provides an electronic device, including: a processor and a memory;

[0022] The processor is used to execute any of the vehicle driving control methods provided by the embodiments of the present disclosure by calling the program or instruction stored in the memory.

[0023] In a sixth aspect, the present disclosure provides a computer-readable storage medium, which stores a program or instruction, and the program or instruction enables a computer to execute any vehicle driving control method provided by the embodiments of the present disclosure.

[0024] In a seventh aspect, the present disclosure provides a computer program product, which is used to execute any of the vehicle driving control methods provided by the embodiments of the present disclosure.

[0025] Compared with the prior art, the technical solution provided by the embodiments of the present disclosure has at least the following advantages:

[0026] In the disclosed embodiment, the cloud server can obtain multiple candidate vehicle positions in the target path within a preset time period, process the multiple candidate vehicle positions to obtain the target vehicle position, process the target vehicle position in time sequence to obtain the target trajectory, associate the target trajectory with the target path, and generate an offline trajectory map package corresponding to the target trajectory and send it to the vehicle, so that the vehicle can perform vehicle driving control on the target path based on the offline trajectory map package. Therefore, by analyzing the driving trajectories of a large number of vehicles to determine the target trajectory and provide it to the vehicle for driving control, problems such as the exit of the intelligent driving function at the intersection, unreasonable lane selection, and low success rate of on- and off-ramps can be solved, and the driving trajectory can be updated in real time, improving driving safety and comfort, and meeting vehicle driving control requirements. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0028] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0029] Figure 1A A schematic diagram of the structure of a vehicle driving control system provided by an exemplary embodiment of the present disclosure;

[0030] Figure 1B A flow chart of a vehicle driving control method provided by an exemplary embodiment of the present disclosure;

[0031] Figure 2A An exemplary diagram of a vehicle location provided for an exemplary embodiment of the present disclosure;

[0032] Figure 2B Another example diagram of vehicle position provided for an exemplary embodiment of the present disclosure;

[0033] Figure 2C Another example diagram of vehicle location provided for an exemplary embodiment of the present disclosure;

[0034] Figure 2DAn exemplary diagram of another vehicle position provided for an exemplary embodiment of the present disclosure;

[0035] Figure 3 A schematic flow chart of a vehicle driving control method provided for another exemplary embodiment of the present disclosure;

[0036] Figure 4 A schematic diagram of an interactive process of a vehicle driving control method provided in a specific embodiment of the present disclosure;

[0037] Figure 5 A schematic diagram of the structure of a vehicle driving control device provided by an embodiment of the present disclosure;

[0038] Figure 6 A schematic structural diagram of a vehicle driving control device provided in another embodiment of the present disclosure. DETAILED DESCRIPTION

[0039] In order to more clearly understand the above-mentioned purposes, features and advantages of the present disclosure, the present disclosure is further described in detail below in conjunction with the accompanying drawings and embodiments. It is understandable that the described embodiments are part of the embodiments of the present disclosure, rather than all of the embodiments, and the specific embodiments described herein are only used to explain the present disclosure, rather than to limit the present disclosure. In the absence of conflict, the embodiments of the present disclosure and the features in the embodiments can be combined with each other. Based on the described embodiments of the present disclosure, all other embodiments obtained by ordinary technicians in the field belong to the scope of protection of the present disclosure.

[0040] In the following description, many specific details are set forth to facilitate a full understanding of the present disclosure, but the present disclosure may also be implemented in other ways different from those described herein; it is obvious that the embodiments in the specification are only part of the embodiments of the present disclosure, rather than all of the embodiments.

[0041] The driving trajectory used in existing intelligent driving is usually provided by high-precision maps drawn by surveying and mapping vehicles. However, with the increase and change of road infrastructure, the turning trajectory angle is too large, the vehicle tilts, the passengers in the car are uncomfortable, the trajectory enters the unreasonable lane, resulting in reduced driving efficiency and other factors. This can easily lead to the exit of the intelligent driving function at intersections, unreasonable lane selection and low success rate of on and off ramps. In addition, the high-precision map relies on the update speed of the supplier and the update efficiency is slow. Therefore, the driving trajectory provided by the existing high-precision map cannot meet the high comfort, high safety, high efficiency and personalized driving needs.

[0042] In view of the above problems, the present disclosure provides a vehicle driving control method which can be applied to Figure 1AIn the application environment shown. The vehicle driving control method is applied to a vehicle driving control system. The vehicle driving control includes a cloud server 100 and a vehicle 200. The cloud server 100 and the vehicle 200 are connected in real time for communication. The vehicle 200 can upload positioning, video and other data to the cloud server 100 in real time. The cloud server 100 can process and obtain the vehicle position based on the data uploaded by the vehicle 200. Therefore, the cloud server 100 can obtain multiple candidate vehicle positions in the target path within a preset time period, and process the multiple candidate vehicle positions to obtain the target vehicle position. The target vehicle position is processed in time sequence to obtain the target trajectory, the target trajectory is associated with the target path, and an offline trajectory map package corresponding to the target trajectory is generated and sent to the vehicle 200. The vehicle 200 performs vehicle driving control on the target path based on the offline trajectory map package. Therefore, by analyzing the driving trajectories of a large number of vehicles to determine the target trajectory and provide it to the vehicle for driving control, the problems of intelligent driving function exiting at the intersection, unreasonable lane selection and low success rate of on and off ramps can be solved, and the real-time update of the driving trajectory can be realized, the driving safety and comfort can be improved, and the vehicle driving control requirements can be met.

[0043] The specific implementation methods of the vehicle driving control method, device, electronic device and storage medium disclosed in the present invention are explained in detail below with reference to the accompanying drawings.

[0044] Figure 1B A flow chart of a vehicle driving control method provided for an exemplary embodiment of the present disclosure. The method may be executed by a vehicle driving control device provided for an embodiment of the present disclosure. The vehicle driving control device may be implemented using software and / or hardware and may be integrated in a cloud server.

[0045] like Figure 1B As shown, the vehicle driving control method may include the following steps:

[0046] Step 101, obtaining a plurality of candidate vehicle locations in a target path within a preset time period.

[0047] In the embodiments of the present disclosure, a time period may be pre-set, such as one hour, one day, etc., and the setting may be selected specifically according to the needs of the application scenario; a target path may be pre-set, such as Road A to Road B, Road C to Road D, etc., or multiple paths may be monitored to determine whether preset vehicle driving control conditions are met, and the path that meets the preset vehicle driving control conditions may be used as the target path, thereby further improving the efficiency and effect of driving control; wherein the preset vehicle driving control conditions may include, for example, one or more of the following: function exit due to guide line trajectory reasons when intelligent driving is turned on in the path, function exit due to unreasonable lane selection when intelligent driving is turned on in the path, multiple dragons in the trajectory within a short distance such as X1 meter when the user is driving in the path, and a significant change in the trajectory within a short distance such as X2 meters when the user is driving in the path.

[0048] In the embodiment of the present disclosure, multiple candidate vehicle points refer to multiple location points where multiple vehicles travel on the target path within a preset time period, and the vehicle point refers to the precise coordinates of a vehicle position on the target path, that is, the driving trajectories of a large number of vehicles on the target path can be obtained within the preset time period.

[0049] In the disclosed embodiment, the cloud server processes the to-be-processed positioning data corresponding to each vehicle at each timestamp corresponding to different target paths within a preset time period (such as data collected by IMU (Inertial Measurement Unit), data collected by GPS (Global Positioning System) and data collected by a wheel speed meter, etc.) in advance to obtain candidate vehicle positions corresponding to each vehicle at each timestamp in different target paths, thereby directly acquiring multiple candidate vehicle positions in the target path within the preset time period.

[0050] In the disclosed embodiment, after receiving the vehicle driving control instruction or according to a preset processing cycle, the cloud server obtains multiple candidate vehicle points in the target path within a preset time period.

[0051] Step 102, processing multiple candidate vehicle positions to obtain a target vehicle position.

[0052] In the disclosed embodiment, after the cloud server obtains multiple candidate vehicle positions, it can process the multiple candidate vehicle positions to obtain the target vehicle point.

[0053] As an example, the target center is determined based on the target path, and the offset distance between each candidate vehicle point and the target center is obtained, and the candidate vehicle points corresponding to the offset distance greater than or equal to the preset offset distance threshold are removed, and the candidate vehicle points after the removal are clustered based on the preset clustering algorithm to obtain the target vehicle point.

[0054] As an example, the moving distance between each candidate vehicle point corresponding to the same vehicle identification code is obtained. When the moving distance is less than or equal to a preset moving distance threshold, the candidate vehicle points corresponding to the same vehicle identification code are removed, and the candidate vehicle points after the removal are clustered based on a preset clustering algorithm to obtain the target vehicle point.

[0055] As an example, the target center is determined based on the target path, and the offset distance between each candidate vehicle point and the target center is obtained, and the candidate vehicle points corresponding to the offset distance greater than or equal to a preset offset distance threshold are removed, and the moving distance between each candidate vehicle point corresponding to the same vehicle identification code is obtained. When the moving distance is less than or equal to the preset moving distance threshold, each candidate vehicle point corresponding to the same vehicle identification code is removed, and the candidate vehicle points after the removal are clustered based on a preset clustering algorithm to obtain the target vehicle point.

[0056] Step 103, processing the target vehicle position according to the time sequence to obtain the target trajectory.

[0057] In the disclosed embodiment, after the cloud server obtains the target vehicle position, it can generate a target trajectory based on the target vehicle position. The target trajectory can be understood as the driving trajectory of the vehicle in the target path, such as the target path A1 to A2, which includes three lanes a1, a2 and a3, and the driving trajectory corresponding to lane a1 is used as the target trajectory.

[0058] In the embodiments of the present disclosure, the timing can be understood as a time sequence, such as time from small to large or time from large to small. The specific selection can be based on actual application needs, and the present disclosure does not make any specific limitations.

[0059] In the disclosed embodiment, each target vehicle point has a corresponding target timestamp. The target vehicle points can be connected from small to large according to the target timestamps corresponding to the target vehicle points to obtain the target trajectory, or the target vehicle points can be connected according to preset connection rules such as position direction to obtain the target trajectory.

[0060] Step 104 , associating the target trajectory with the target path, and generating an offline trajectory map package corresponding to the target trajectory and sending it to the vehicle, so that the vehicle performs vehicle driving control on the target path based on the offline trajectory map package.

[0061] In the disclosed embodiment, after the target trajectory is generated, it needs to be matched with the target path in the map before it can be used. Therefore, the latitude and longitude position information of the target trajectory is associated with the latitude and longitude position information of the target path, and an offline trajectory map package corresponding to the target trajectory is generated based on a preset offline map making tool or algorithm.

[0062] It is understandable that the cloud server and the vehicle can communicate in real time. After generating the offline trajectory map package, the cloud server sends the offline trajectory map package to the vehicle, so that the vehicle can drive according to the target trajectory in the offline trajectory map package when performing vehicle driving control on the target path, so as to avoid problems such as the exit of the intelligent driving function at intersections, unreasonable lane selection, and low success rate of on- and off-ramps, thereby improving driving safety and comfort.

[0063] Among them, associating the target trajectory with the target path can be understood as converting the coordinate code of the generated target trajectory to be consistent with the coordinate code of the map road network, matching the target trajectory and the target path according to the coordinate code, placing the representative vehicle points of the target trajectory into the coordinate points of the target path, and drawing the trajectory according to the time distance.

[0064] In the vehicle driving control method of the disclosed embodiment, the cloud server can obtain multiple candidate vehicle positions in the target path within a preset time period, process the multiple candidate vehicle positions to obtain the target vehicle position, process the target vehicle position in time sequence to obtain the target trajectory, associate the target trajectory with the target path, and generate an offline trajectory map package corresponding to the target trajectory and send it to the vehicle, so that the vehicle can perform vehicle driving control on the target path based on the offline trajectory map package. Therefore, by analyzing the driving trajectories of a large number of vehicles to determine the target trajectory and provide it to the vehicle for driving control, the problems of intelligent driving function exiting at intersections, unreasonable lane selection, and low success rate of on- and off-ramps can be solved, and the driving trajectory can be updated in real time, improving driving safety and comfort, and meeting vehicle driving control requirements.

[0065] In an optional embodiment of the present disclosure, before obtaining multiple candidate vehicle positions in the target path within a preset time period, the cloud server also includes: obtaining the pending positioning data corresponding to each vehicle at each timestamp in the target path within the preset time period; processing the pending positioning data through a preset positioning processing algorithm to obtain the candidate vehicle position corresponding to each vehicle at each timestamp.

[0066] In the disclosed embodiment, the positioning data to be processed is positioning data in a unified log format, including data collected by the IMU of each vehicle, data collected by the GPS, and data collected by the wheel speed meter. The data collected by the IMU, data collected by the GPS, and data collected by the wheel speed meter of each vehicle at that time point can be queried through the timestamp; the positioning data to be processed can also include video data obtained by a shooting device on the vehicle, such as a camera, and can be processed through a positioning processing algorithm, such as a GPS positioning calculation formula, a camera positioning calculation formula, and a radar positioning calculation formula.

[0067] In the embodiment of the present disclosure, different positioning algorithms can be selected according to the type of positioning data for the to-be-processed positioning data corresponding to each vehicle at each timestamp to perform calculations, so that multiple to-be-processed points corresponding to each vehicle at the same timestamp can be obtained. The multiple to-be-processed points are calculated according to the weights corresponding to different positioning data types to obtain candidate vehicle points corresponding to each vehicle at the same timestamp. Therefore, the candidate vehicle points corresponding to each vehicle at each timestamp can be obtained.

[0068] For example, the positioning data to be processed of vehicle Q at the same timestamp includes data collected by the shooting device and data collected by the GPS. The data collected by the shooting device is calculated according to the camera positioning calculation formula to obtain the point D1 to be processed. The data collected by the GPS is calculated according to the GPS positioning calculation formula to obtain the point D2 to be processed. The weight of the data collected by the shooting device is R1, the weight of the data collected by the GPS is R2, and the result of weighted summation calculation with the point D1 to be processed and the point D2 to be processed is used as the candidate vehicle point corresponding to the vehicle Q at the timestamp.

[0069] In an optional embodiment of the present disclosure, multiple candidate vehicle points are processed to obtain a target vehicle point, including: determining a target center based on a target path, and obtaining an offset distance between each candidate vehicle point and the target center, and removing candidate vehicle points corresponding to offset distances greater than or equal to a preset offset distance threshold; and / or obtaining a moving distance between each candidate vehicle point corresponding to the same vehicle identification code, and removing each candidate vehicle point corresponding to the same vehicle identification code when the moving distance is less than or equal to a preset moving distance threshold; and clustering the removed candidate vehicle points based on a preset clustering algorithm to obtain a target vehicle point.

[0070] In an optional implementation of the present disclosure, the target vehicle points are processed in time sequence to obtain the target trajectory, including: obtaining the target timestamp corresponding to each target vehicle point; connecting the target vehicle points from small to large according to the target timestamp to obtain the target trajectory. In the process of connecting the target vehicle points from small to large according to the target timestamp, if there is a target vehicle point whose time sequence does not conform to the connection direction, such as a back-connection from left to right, it is deleted, so as to further improve the accuracy of the target trajectory, thereby improving the subsequent vehicle driving control accuracy, meeting the user's driving control needs, and improving the user experience.

[0071] In the disclosed embodiment, after the vehicle uploads the positioning data to be processed to the cloud server, the cloud server processes the positioning data to be processed, and can obtain multiple candidate vehicle positions, and processes the multiple candidate vehicle positions to obtain the target vehicle position, and finally performs fitting processing based on the target vehicle position to generate the target trajectory.

[0072] In the disclosed embodiment, the trajectory of the vehicle is preprocessed, and the noise vehicle points are removed to ensure the accuracy of the trajectory. Specifically, the target center is determined based on the target path, and the offset distance between each candidate vehicle point and the target center is obtained, and the candidate vehicle points corresponding to the offset distance greater than or equal to the preset offset distance threshold are removed, wherein the preset offset distance threshold can be selected and set as needed. It can be understood that the target center corresponding to the target path can be set according to the actual scenario. For example, if the target path is a straight two-lane path, the dividing line between the two lanes in the target path can be used as the center line, and the point on the center point can be used as the target center, so that the offset distance between each candidate vehicle point and the nearest target center can be calculated, and the candidate vehicle points corresponding to the offset distance greater than or equal to the preset offset distance threshold are removed. For example, the vehicle point offset caused by signal obstruction due to trees, high-rise buildings, etc. will be relatively large, so the vehicle point offset noise caused by signal obstruction due to trees, high-rise buildings, etc. can be removed to improve the accuracy of the trajectory.

[0073] Specifically, the moving distance between each candidate vehicle point corresponding to the same vehicle identification code is obtained, and when the moving distance is less than or equal to a preset moving distance threshold, each candidate vehicle point corresponding to the same vehicle identification code is removed; wherein, the preset moving distance threshold can be selected and set as needed, and the vehicle identification code is encrypted data and is only used to identify different vehicles. The movement information of the vehicle can be determined based on the moving distance between each candidate vehicle point of the same vehicle. For example, when the moving distance is less than or equal to the preset moving distance threshold, the vehicle may move slowly or be stationary. In order to ensure the correctness of subsequent processing, each candidate vehicle point corresponding to the same vehicle identification code can be removed, that is, a large number of repeated vehicle points that are creeping or stopped at a low speed are removed.

[0074] It can also be understood that the shape of the trajectory after the above denoising is very close to the actual road, but the GPS accuracy is limited, there is a deviation between the vehicle point and the positioning point, and some position points can be scattered on both sides of the road. And there are many redundant points, therefore, based on the preset clustering algorithm, the candidate vehicle points after the removal process are clustered to obtain the target vehicle point; wherein, the clustering algorithm can be selected and set as needed, such as the hierarchical clustering algorithm and the K-Means algorithm, for example, randomly select k center points from the candidate vehicle points after the removal process, and calculate the distance from each candidate vehicle point to the k center points respectively, classify the candidate vehicle points according to the distance, calculate the midpoint of the same type of data points as the center point position of the class to be updated, and update the center point, repeat the classification, if the sum of the distances between each candidate vehicle point and the center point of the class to which it belongs no longer changes, the algorithm ends, thereby obtaining the target vehicle point; therefore, the redundant candidate vehicle points can be removed by the clustering algorithm to generate the target vehicle point, that is, the representative vehicle point, to ensure the rationality of generating the target trajectory.

[0075] As an example, Figure 2A The denoised points shown in FIG. 1 are candidate vehicle points after the removal process. Figure 2B As shown in the figure, after the redundancy is removed, it can be understood that after obtaining the target vehicle point, the target vehicle point can be connected in ascending order according to the target timestamps corresponding to the target vehicle point to obtain the target trajectory, such as Figure 2C The target trajectory shown is generated by connecting the target vehicle points that meet the time sequence; wherein, the target vehicle points that do not meet the time sequence can be ignored and not connected, so as to further ensure the correctness of the target trajectory.

[0076] It is understandable that after the target trajectory is generated, it needs to be matched with the road network information in the map before it can be used. The matching is performed according to the location of the target trajectory and the location information of the road network, such as Figure 2D The matching results are shown; after the trajectory and road network are matched, an offline trajectory map package of the target trajectory is generated on the cloud server and sent to the vehicle storage controller through 4G / 5G and other networks. After receiving the offline trajectory map package, the vehicle can use the offline trajectory map when driving manually or intelligently. The cloud server analyzes the motion trajectories of a large number of vehicles and calculates a reasonable driving trajectory for use in intelligent driving, etc., thereby improving driving safety and comfort.

[0077] Figure 3A flow chart of a vehicle driving control method provided for another exemplary embodiment of the present disclosure, the method may be executed by a vehicle driving control device provided for an embodiment of the present disclosure, the vehicle driving control device may be implemented using software and / or hardware and may be integrated into a vehicle.

[0078] like Figure 3 As shown, the vehicle driving control method may include the following steps:

[0079] Step 301, receiving an offline trajectory map package sent by a cloud server; wherein the cloud server obtains multiple candidate vehicle positions in a target path within a preset time period for processing to obtain a target vehicle position, processes the target vehicle position in a time sequence to obtain a target trajectory, associates the target trajectory with the target path, and generates an offline trajectory map package corresponding to the target trajectory.

[0080] Step 302 : Controlling vehicle driving on a target path based on the offline trajectory map package.

[0081] In the disclosed embodiment, the vehicle can receive an offline trajectory map package sent by a cloud server, and perform vehicle driving control on a target path based on the offline trajectory map package. The cloud server obtains multiple candidate vehicle positions in a target path within a preset time period for processing to obtain a target vehicle position, processes the target vehicle position in a time sequence to obtain a target trajectory, associates the target trajectory with the target path, and generates an offline trajectory map package corresponding to the target trajectory.

[0082] Specifically, during the driving control process, the vehicle determines whether there is a corresponding offline trajectory map package while driving based on the map. When the corresponding offline trajectory map package exists in the target path, the driving path is planned in real time based on the offline trajectory map package to achieve driving according to the target trajectory, thereby avoiding problems such as the exit of the intelligent driving function at intersections, unreasonable lane selection, and low success rate of on- and off-ramps, thereby improving driving safety and comfort and meeting vehicle driving control needs.

[0083] In the disclosed embodiment, the vehicle uploads the data collected by the IMU, the data collected by the GPS, and the data collected by the wheel speed meter to the cloud server for processing positioning data. The cloud server processes the pending positioning data corresponding to each vehicle at each timestamp corresponding to different target paths in advance within a preset time period, and obtains the candidate vehicle points corresponding to each vehicle at each timestamp in different target paths, so as to directly obtain multiple candidate vehicle points in the target path within the preset time period. After the cloud server obtains the multiple candidate vehicle points, it can process the multiple candidate vehicle points to obtain the target vehicle point, and according to the target vehicle point target trajectory, finally associate the target trajectory with the target path, and generate an offline trajectory map package corresponding to the target trajectory and send it to the vehicle, and the vehicle performs vehicle driving control on the target path based on the offline trajectory map package.

[0084] In the vehicle driving control method of the disclosed embodiment, the vehicle receives an offline trajectory map package sent by a cloud server; wherein the cloud server obtains multiple candidate vehicle positions in the target path within a preset time period for processing to obtain the target vehicle position, and processes the target vehicle position in a time sequence to obtain the target trajectory, and associates the target trajectory with the target path, and generates an offline trajectory map package corresponding to the target trajectory, and performs vehicle driving control on the target path based on the offline trajectory map package. By adopting the above technical solution, the cloud server analyzes the driving trajectories of a large number of vehicles to determine the target trajectory and provide it to the vehicle for driving control, which can solve the problems of intelligent driving function exiting at intersections, unreasonable lane selection, and low success rate of on- and off-ramps, and can realize real-time updating of the driving trajectory, improve driving safety and comfort, and meet vehicle driving control requirements.

[0085] In an optional embodiment of the present disclosure, the inertial measurement unit IMU, the global positioning system GPS and the wheel speed meter of the vehicle are controlled to collect the first data, the second data and the third data according to a preset collection frequency; the first data, the second data and the third data are processed according to a preset format to obtain the data to be processed in the target format; the shooting equipment of the vehicle is controlled to collect the video data within the target distance range according to the collection frequency, and the video data is pre-processed to obtain the target video data; the data to be processed and the target video data are associated with the vehicle identification code corresponding to the vehicle as the positioning data to be processed and uploaded to the cloud server.

[0086] In the disclosed embodiment, the pre-set collection frequency can be set as needed, the preset format can be selected according to actual data, such as a unified log format, and the target distance range can also be selected and set as needed.

[0087] Specifically, the vehicle collects data generated by the vehicle bus / data in real time, including IMU, GPS, wheel speed meter, shooting equipment such as camera, etc. Among them, IMU, GPS and wheel speed meter can provide vehicle positioning information, and camera can provide perception results of static environment and dynamic target. In order to ensure the correctness of data and generated trajectory, the collection frequency is greater than or equal to 40HZ, for example. When collecting data, the controllers from IMU, GPS, wheel speed meter and camera need to keep time synchronization to avoid data time misalignment. After data collection, the data collected by IMU, GPS and wheel speed meter need to be processed in a unified log format. The data collected by IMU, GPS and wheel speed meter at that time point can be queried through the timestamp. The camera does not process the video data in a unified format. When uploading data, the data involving vehicle privacy and the privacy of the surrounding area of ​​the vehicle during collection needs to be desensitized, that is, when uploading text data, the vehicle identification code is one-way encrypted, and the specific vehicle cannot be decrypted by reverse decoding. When uploading video data, elements such as faces and license plates are coded to further improve data security.

[0088] In some embodiments, the video data is analyzed to obtain the driving information of adjacent vehicles, and the acquisition frequency is adjusted based on the driving information of adjacent vehicles.

[0089] In the embodiments of the present disclosure, the vehicle positions of adjacent vehicles within a certain distance range can be acquired through video data, so that the vehicle positions of adjacent vehicles can be determined according to the driving information of the adjacent vehicles, such as having the same driving trajectory as the own vehicle, according to the relative distance, thereby providing more vehicle position information, reducing the collection of samples, that is, adjusting the collection frequency, thereby improving data processing efficiency while ensuring the correctness of the target trajectory.

[0090] As an example scenario, Figure 4 As shown, step 4.1 controls the vehicle's inertial measurement unit IMU, global positioning system GPS, and wheel speed meter to collect data and process them in a unified log format, and controls the camera to shoot video data; step 4.2 uploads the data to the cloud server; step 4.3 the cloud server performs fitting based on the data uploaded by the vehicle to obtain a target trajectory; step 4.4 the cloud server associates the target trajectory with the target path, and generates an offline trajectory map package corresponding to the target trajectory; step 4.5 the cloud server sends the offline trajectory map package to the vehicle; step 4.6 the vehicle performs vehicle driving control on the target path based on the offline trajectory map package.

[0091] Specifically, in the intelligent driving function, the driving behaviors and data of intelligent driving and users are collected, and the data is desensitized in the vehicle and uploaded to the cloud server. Through big data cleaning, extraction, analysis, and storage, the user's driving behavior is mined through big data technology to obtain a more comfortable and reasonable driving trajectory, which is then sent to the vehicle for user use. That is, the driving trajectories of multiple moving vehicles are fitted through an algorithm to generate a trajectory (target trajectory), and the trajectory is associated with road or lane information, and the trajectory is marked as an empirical trajectory (without affecting the trajectories of other maps). An offline trajectory map package is made on the cloud server and sent to the vehicle for use by the intelligent driving and human driving systems. The empirical trajectory can solve the problems of intelligent driving function exiting at intersections, unreasonable lane selection, and low success rate of on- and off-ramps, thereby improving the safety and comfort of intelligent driving and human driving.

[0092] Therefore, through the vehicle intelligent driving perception data and the cloud server analyzing the movement trajectories of a large number of users through algorithms, a reasonable driving trajectory is calculated for intelligent driving use, that is, data collection from the vehicle side, cloud data mining and distribution to the vehicle side, the whole link is completed automatically, without human intervention, and has a wide range of applications; that is to say, through perception and user driving behavior data, the vehicle points that affect comfort, safety, efficiency, etc. are automatically mined, and a trajectory that conforms to the driving habits of most users is assigned. The data update efficiency is high, and the fastest update can be achieved in the next second, and no manual review is required.

[0093] It is understandable that during the actual driving of the vehicle, unreasonable guide line trajectories can be automatically identified. For example, when the intelligent driving is turned on, the function is exited due to the guide line trajectory, and when the user is driving, the trajectory changes drastically within a short distance, etc., it is determined that an unreasonable trajectory exists. Therefore, the data collected by the vehicle is used to automatically identify takeover risk scenarios such as on and off ramps, ramp driving, etc., and the takeover risk points and trajectories caused by the trajectory are automatically analyzed and the trajectory is corrected. In other words, a reasonable driving trajectory is calculated for users to use, solving the problem of reduced comfort caused by unreasonable guide line trajectories.

[0094] In order to implement the above embodiments, the present disclosure also provides a vehicle driving control device, which can be implemented by software and / or hardware and can be integrated in a cloud server.

[0095] Figure 5 A schematic diagram of the structure of a vehicle driving control device provided by an embodiment of the present disclosure is shown in FIG. Figure 5 As shown, the vehicle driving control device 50 may include: a first acquisition module 510, a first processing module 520, a second processing module 530, an association module 540 and a generation and sending module 550.

[0096] The first acquisition module 510 is used to acquire multiple candidate vehicle locations in the target path within a preset time period;

[0097] A first processing module 520 is used to process the multiple candidate vehicle positions to obtain a target vehicle position;

[0098] The second processing module 530 is used to process the target vehicle position in time sequence to obtain a target trajectory;

[0099] An association module 540, configured to associate the target trajectory with the target path;

[0100] The generating and sending module 550 is used to generate an offline trajectory map package corresponding to the target trajectory and send it to the vehicle, so that the vehicle can perform vehicle driving control on the target path based on the offline trajectory map package.

[0101] Optionally, the device further comprises:

[0102] A second acquisition module is used to acquire the to-be-processed positioning data corresponding to each vehicle at each timestamp in the target path within the preset time period;

[0103] The third processing module is used to process the positioning data to be processed by a preset positioning processing algorithm to obtain the candidate vehicle points corresponding to each vehicle at each timestamp.

[0104] Optionally, the first processing module 520 is specifically configured to:

[0105] Determine the target center based on the target path, obtain the offset distance between each candidate vehicle point and the target center, and remove the candidate vehicle points corresponding to the offset distance greater than or equal to a preset offset distance threshold; and / or,

[0106] Obtaining the moving distance between each candidate vehicle point corresponding to the same vehicle identification code, and when the moving distance is less than or equal to a preset moving distance threshold, removing each candidate vehicle point corresponding to the same vehicle identification code;

[0107] The candidate vehicle locations after the removal process are clustered based on a preset clustering algorithm to obtain the target vehicle location.

[0108] Optionally, the second processing module 530 is specifically configured to:

[0109] Obtaining a target timestamp corresponding to each target vehicle position;

[0110] The target vehicle points are connected from small to large according to the target timestamps to obtain the target trajectory.

[0111] The vehicle driving control device applicable to the cloud server provided in the embodiment of the present disclosure can execute the vehicle driving control method applied to the cloud server provided in the embodiment of the present disclosure, and has the functional modules and beneficial effects corresponding to the execution method. The contents not fully described in the embodiment of the device of the present disclosure can refer to the description in any method embodiment of the present disclosure.

[0112] In order to implement the above embodiments, the present disclosure also provides a vehicle driving control device, which can be implemented by software and / or hardware and can be integrated in a charging pile terminal.

[0113] Figure 6 A schematic diagram of the structure of a vehicle driving control device provided by another embodiment of the present disclosure is shown in FIG. Figure 6 As shown, the vehicle driving control device 60 may include: a receiving module 610 and a control module 620 .

[0114] The receiving module 610 is used to receive an offline track map package sent by a cloud server; wherein the cloud server obtains a plurality of candidate vehicle positions in a target path within a preset time period and processes them to obtain a target vehicle position, processes the target vehicle position in a time sequence to obtain a target track, associates the target track with the target path, and generates an offline track map package corresponding to the target track;

[0115] The control module 620 is used to control the vehicle driving on the target path based on the offline trajectory map package.

[0116] Optionally, the vehicle driving control device 60 further includes:

[0117] A first acquisition module, used for controlling an inertial measurement unit IMU, a global positioning system GPS and a wheel speed meter of the vehicle to acquire first data, second data and third data according to a preset acquisition frequency;

[0118] a fourth processing module, configured to process the first data, the second data and the third data according to a preset format to obtain data to be processed in a target format;

[0119] A second acquisition module is used to control the camera of the vehicle to acquire video data within a target distance range according to the acquisition frequency, and pre-process the video data to obtain target video data;

[0120] The uploading module is used to associate the data to be processed and the target video data as the positioning data to be processed with the vehicle identification code corresponding to the vehicle and then upload them to the cloud server.

[0121] Optionally, the device further comprises:

[0122] An analysis and acquisition module, used to analyze the video data and acquire driving information of adjacent vehicles;

[0123] An adjustment module is used to adjust the collection frequency based on the adjacent vehicle driving information.

[0124] The vehicle driving control device applicable to the charging pile terminal provided in the embodiment of the present disclosure can execute the vehicle driving control method applied to the charging pile terminal provided in the embodiment of the present disclosure, and has the functional modules and beneficial effects corresponding to the execution method. The contents not fully described in the embodiment of the device of the present disclosure can refer to the description in any method embodiment of the present disclosure.

[0125] The embodiments of the present disclosure also provide an electronic device including a processor and a memory; the processor calls a program or instruction stored in the memory to execute the steps of the various embodiments of the vehicle driving control method described above, which will not be repeated here to avoid repeated description.

[0126] The embodiments of the present disclosure also provide a computer-readable storage medium, which is non-transitory and stores programs or instructions. The programs or instructions enable a computer to execute the steps of the embodiments of the vehicle driving control method described above. To avoid repeated description, they will not be repeated here.

[0127] The embodiments of the present disclosure also provide a computer program product, which is used to execute the steps of the embodiments of the aforementioned vehicle driving control method.

[0128] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0129] The above description is only a specific embodiment of the present disclosure, so that those skilled in the art can understand or implement the present disclosure. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present disclosure. Therefore, the present disclosure will not be limited to the embodiments described herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A vehicle driving control method, characterized in that: The method is applied to a cloud server and includes: Obtain multiple candidate vehicle locations in the target path within a preset time period; Processing the multiple candidate vehicle positions to obtain a target vehicle position; Processing the target vehicle position according to the time sequence to obtain the target trajectory; The target trajectory is associated with the target path, and an offline trajectory map package corresponding to the target trajectory is generated and sent to the vehicle, so that the vehicle performs vehicle driving control on the target path based on the offline trajectory map package.

2. The method according to claim 1, characterized in that The method, before acquiring a plurality of candidate vehicle locations in the target path within a preset time period, further includes: Obtaining the to-be-processed positioning data corresponding to each vehicle at each timestamp in the target path within the preset time period; The positioning data to be processed is processed by a preset positioning processing algorithm to obtain the candidate vehicle points corresponding to each vehicle at each timestamp.

3. The method according to claim 1, characterized in that The processing of the plurality of candidate vehicle positions to obtain the target vehicle position includes: Determine the target center based on the target path, obtain the offset distance between each candidate vehicle point and the target center, and remove the candidate vehicle points corresponding to the offset distance greater than or equal to a preset offset distance threshold; and / or, Obtaining the moving distance between each candidate vehicle point corresponding to the same vehicle identification code, and when the moving distance is less than or equal to a preset moving distance threshold, removing each candidate vehicle point corresponding to the same vehicle identification code; The candidate vehicle locations after the removal process are clustered based on a preset clustering algorithm to obtain the target vehicle location.

4. The method according to claim 1, characterized in that: The step of processing the target vehicle position in time sequence to obtain a target trajectory includes: Obtaining a target timestamp corresponding to each target vehicle position; The target vehicle points are connected from small to large according to the target timestamps to obtain the target trajectory.

5. A vehicle driving control method, characterized in that: The method is applied to a vehicle and comprises: Receiving an offline trajectory map package sent by a cloud server; wherein the cloud server obtains a plurality of candidate vehicle positions in a target path within a preset time period and processes them to obtain a target vehicle position, processes the target vehicle position in a time sequence to obtain a target trajectory, associates the target trajectory with the target path, and generates an offline trajectory map package corresponding to the target trajectory; The vehicle driving control is performed on the target path based on the offline trajectory map package.

6. The method according to claim 5, characterized in that The method further comprises: Controlling the inertial measurement unit IMU, the global positioning system GPS and the wheel speed meter of the vehicle to collect the first data, the second data and the third data according to a preset collection frequency; Processing the first data, the second data and the third data according to a preset format to obtain data to be processed in a target format; Controlling the camera of the vehicle to collect video data within a target distance range at the collection frequency, and preprocessing the video data to obtain target video data; The data to be processed and the target video data are associated with the vehicle identification code corresponding to the vehicle as the positioning data to be processed and then uploaded to the cloud server.

7. The method according to claim 6, characterized in that The method further comprises: Analyzing the video data to obtain driving information of adjacent vehicles; The collection frequency is adjusted based on the adjacent vehicle driving information.

8. A vehicle driving control device, characterized in that: Applied to a cloud server, the device comprises: A first acquisition module is used to acquire multiple candidate vehicle points in a target path within a preset time period; A first processing module is used to process the multiple candidate vehicle positions to obtain a target vehicle position; A second processing module is used to process the target vehicle position in time sequence to obtain a target trajectory; an associating module, used to associate the target trajectory with the target path; A generating and sending module is used to generate an offline track map package corresponding to the target track and send it to the vehicle, so that the vehicle can perform vehicle driving control on the target path based on the offline track map package.

9. A vehicle driving control device, characterized in that: Applied to a charging pile terminal, the device comprises: A receiving module, used for receiving an offline track map package sent by a cloud server; wherein the cloud server obtains a plurality of candidate vehicle positions in a target path within a preset time period and processes them to obtain a target vehicle position, processes the target vehicle position in a time sequence to obtain a target track, associates the target track with the target path, and generates an offline track map package corresponding to the target track; A control module is used to control vehicle driving on the target path based on the offline trajectory map package.

10. An electronic device, characterized in that: include: Processor and memory; The processor is used to execute the vehicle driving control method as described in any one of claims 1 to 7 by calling the program or instruction stored in the memory.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a program or an instruction, which enables a computer to execute the vehicle driving control method according to any one of claims 1 to 7.

Images