A vehicle control method and device, electronic equipment and storage medium

Abstract

The present disclosure relates to a vehicle control method and device, electronic equipment and storage medium. The method comprises: performing coordinate system conversion on first radar data and first image data respectively to obtain second radar data and second image data in a preset space coordinate system; performing data processing on the second radar data to obtain radar point cloud information of a target detection object; performing image processing on the second image data to obtain image pixel information of the target detection object; performing data fusion on the radar point cloud information and the image pixel information based on first fusion weights corresponding to the radar point cloud information and the image pixel information respectively to obtain a first fusion result; performing track prediction on the target detection object based on the first fusion result to obtain a first target prediction point; and generating vehicle control information based on the first target prediction point. The embodiments of the present disclosure can improve the accuracy of track prediction of the target detection object, thereby improving the safety of driving.

Description

Technical Field

[0001] This disclosure relates to the field of vehicle technology, and in particular to a vehicle control method, device, electronic device, and storage medium. Background Technology

[0002] Cameras and radar are currently the two most commonly used ranging sensing elements. Cameras monitor objects around a vehicle in real time, and fusing camera data with radar data can improve the accuracy of monitoring surrounding objects. Existing technologies generally make predictions based on radar data and camera data separately, obtaining corresponding prediction results for each, and then fusing the two prediction results to obtain a fused prediction result. This prediction method affects the accuracy of predicting the trajectory of the target object, thereby reducing the safety of vehicle driving. Summary of the Invention

[0003] This disclosure provides a vehicle control method, apparatus, electronic device, and storage medium, which can improve the accuracy of target detection object trajectory prediction, thereby improving driving safety. The technical solution of this disclosure is as follows:

[0004] According to a first aspect of the present disclosure, a vehicle control method is provided, the method comprising:

[0005] The first radar data and the first image data are respectively transformed into a coordinate system to obtain the second radar data in a preset spatial coordinate system and the second image data in the preset spatial coordinate system; the radar signal points in the second radar data are spatially aligned with the image pixels in the second image data; the first radar data and the first image data are data acquired in the same acquisition period.

[0006] The second radar data is processed to obtain radar point cloud information of the target object;

[0007] The second image data is processed to obtain the image pixel information of the target detection object;

[0008] Based on the first fusion weights corresponding to the radar point cloud information and the image pixel information respectively, the radar point cloud information and the image pixel information are fused to obtain a first fusion result; the first fusion weights are determined based on the detection attributes of the target detection object.

[0009] Based on the first fusion result, the trajectory of the target detection object is predicted to obtain the first target prediction point;

[0010] Based on the first target prediction point, vehicle control information is generated.

[0011] Furthermore, before fusing the radar point cloud information and the image pixel information based on the first fusion weights corresponding to the radar point cloud information and the image pixel information respectively to obtain the first fusion result, the method further includes:

[0012] Determine the influence factors of the radar point cloud information and the image pixel information in the current fusion scene;

[0013] Based on the influence factors of the radar point cloud information and the image pixel information in the current fusion scenario, the first fusion weights corresponding to the radar point cloud information and the image pixel information are determined respectively.

[0014] Furthermore, the step of generating vehicle control information based on the first target prediction point includes:

[0015] Based on the radar point cloud information, the trajectory of the target detection object is predicted to obtain the point cloud target prediction points;

[0016] Based on the image pixel information, the trajectory of the target detection object is predicted to obtain pixel target prediction points;

[0017] Based on the second fusion weights corresponding to the point cloud target prediction points and the pixel target prediction points respectively, the point cloud target prediction points and the pixel target prediction points are fused to obtain a second target prediction point; the second fusion weights are determined based on the detection attributes of the target detection object.

[0018] Based on the third fusion weights corresponding to the first target prediction point and the second target prediction point respectively, data fusion is performed on the first target prediction point and the second target prediction point to obtain the target prediction point; the third fusion weight corresponding to the first target prediction point is greater than the third fusion weight corresponding to the second target prediction point;

[0019] The vehicle control information is generated based on the target prediction point.

[0020] Furthermore, before fusing the point cloud target prediction points and the pixel target prediction points based on the second fusion weights corresponding to the point cloud target prediction points and the pixel target prediction points to obtain the second target prediction points, the method further includes:

[0021] Determine the influence factors of the point cloud target prediction points and the pixel target prediction points in the current fusion scene, respectively;

[0022] Based on the influence factors of the point cloud target prediction points in the current fusion scene and the influence factors of the pixel target prediction points in the current fusion scene, the point cloud target prediction points are determined as the second fusion weights corresponding to the pixel target prediction points.

[0023] Furthermore, generating the vehicle control information based on the target prediction point includes:

[0024] Obtain current vehicle status information;

[0025] The vehicle control information is generated based on the target prediction point and the current vehicle status information.

[0026] Furthermore, the first fusion result includes historical trace information of the target detection object;

[0027] The step of predicting the trajectory of the detected target based on the first fusion result to obtain a first target prediction point includes:

[0028] Based on the historical point information of the target detection object, the trajectory of the target detection object is predicted to obtain the predicted trajectory information of the target detection object;

[0029] The first target prediction point is determined based on the predicted flight path information.

[0030] Furthermore, both the first radar data and the first image data include multiple data sets.

[0031] The step of performing coordinate system transformation on the first radar data and the first image data to obtain the second radar data in the preset spatial coordinate system and the second image data in the preset spatial coordinate system includes:

[0032] Each of the multiple first radar data sets is assigned a corresponding associated data set, wherein the associated data set is a first image data set that is adapted to the detection direction of the first radar data set.

[0033] The multiple first radar data and their respective associated data are transformed into coordinate systems to obtain multiple second radar data in a preset spatial coordinate system, and multiple second image data in the preset spatial coordinate system; the radar signal points in the multiple second radar data are spatially aligned with the image pixel points in their respective second image data.

[0034] According to a second aspect of the present disclosure, a vehicle control device is provided, the device comprising:

[0035] The calibration module is used to convert the coordinate system of the first radar data and the coordinate system of the first image data into a preset spatial coordinate system to obtain second radar data and second image data. The radar signal points in the second radar data and the image pixels in the second image data are spatially aligned in the preset spatial coordinate system. The first radar data and the first image data are data acquired in the same acquisition cycle.

[0036] The data processing module is used to process the second radar data to obtain radar point cloud information of the target detection object;

[0037] The image processing module is used to perform image processing on the second image data to obtain the image pixel information of the target detection object;

[0038] The fusion module is used to perform a first data fusion on the radar point cloud information and the image pixel information based on the fusion weights corresponding to the radar point cloud information and the image pixel information respectively, to obtain a first fusion result; the first fusion weight is determined based on the detection attributes of the target detection object;

[0039] The trajectory prediction module is used to predict the trajectory of the target detection object based on the first fusion result to obtain a first target prediction point;

[0040] The generation module is used to generate vehicle control information based on the first target prediction point.

[0041] According to a third aspect of the present disclosure, an electronic device is provided, comprising: a processor; and a memory for storing processor-executable instructions; wherein the processor is configured to execute the instructions to implement the vehicle control method as described in any one of the first aspects above.

[0042] According to a fourth aspect of the present disclosure, a computer-readable storage medium is provided, wherein when instructions in the storage medium are executed by a processor of an electronic device, the electronic device is enabled to perform the vehicle control method described in any one of the first aspects of the present disclosure.

[0043] The technical solutions provided by the embodiments of this disclosure have at least the following beneficial effects:

[0044] This disclosure calibrates first radar data and first image data to obtain second radar data and second image data. The first radar data and first image data serve as the raw data acquired by the radar and camera. The first image data and first radar data are converted to the same spatial dimension to facilitate data processing and improve data processing efficiency. The second radar data and second image data are processed separately to obtain radar point cloud information and image pixel information. The first fusion result is based on the detection attributes of the target object, assigning corresponding first fusion weights to the radar point cloud information and image pixel information. Different first fusion weights are assigned based on different detection attributes to improve the flexibility of fusion. The radar point cloud information and image pixel information still retain the original data from the camera and radar, avoiding the loss of original data and improving the accuracy of the first fusion result. This improves the accuracy of trajectory prediction for the target object and further enhances driving safety.

[0045] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0046] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure, and are not intended to unduly limit this disclosure.

[0047] Figure 1 This is a schematic diagram illustrating an application environment according to an exemplary embodiment;

[0048] Figure 2 This is a block diagram illustrating the structure of an existing vehicle control system according to an exemplary embodiment;

[0049] Figure 3 This is a method flow diagram of a vehicle control method according to an exemplary embodiment;

[0050] Figure 4 This is a flowchart illustrating a method for generating vehicle control information according to an exemplary embodiment;

[0051] Figure 5 This is a flowchart illustrating a calibration method according to an exemplary embodiment;

[0052] Figure 6 This is a block diagram of a vehicle control system according to an exemplary embodiment;

[0053] Figure 7 This is a block diagram of a vehicle control device according to an exemplary embodiment;

[0054] Figure 8This is a block diagram illustrating an electronic device for vehicle control according to an exemplary embodiment. Detailed Implementation

[0055] To enable those skilled in the art to better understand the technical solutions of this disclosure, the technical solutions in the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings.

[0056] It should be noted that the terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.

[0057] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for display, data used for analysis, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties.

[0058] Please see Figure 1 , Figure 1 This is a schematic diagram illustrating an application environment according to an exemplary embodiment, such as... Figure 1 As shown, the application environment may include an in-vehicle terminal 100 and a vehicle body processor 200.

[0059] The vehicle-mounted terminal 100 can be used to provide display services to any user. Specifically, the vehicle-mounted terminal 100 can be, but is not limited to, electronic devices such as smartphones, desktop computers, tablets, laptops, smart speakers, digital assistants, augmented reality (AR) / virtual reality (VR) devices, and smart wearable devices, or software running on the aforementioned electronic devices, such as applications. Optionally, the operating system running on the electronic device can be, but is not limited to, Android, iOS, Linux, Windows, etc.

[0060] In an optional embodiment, the vehicle body processor 200 can provide backend services to the vehicle terminal 100, generating data to be displayed by the vehicle terminal 100. Specifically, the vehicle body processor 200 can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms.

[0061] In addition, it should be noted that, Figure 1 The example shown is merely one application environment provided by this disclosure. In practical applications, other application environments may also be included, such as more terminals.

[0062] In the embodiments described in this specification, the vehicle terminal 100 and the vehicle body processor 200 can be directly or indirectly connected via wired or wireless communication, and this disclosure does not impose any restrictions.

[0063] Figure 2 This is a block diagram of a conventional vehicle control system according to an exemplary embodiment. A camera and a millimeter-wave radar in the corresponding detection direction undergo intrinsic parameter calibration. The millimeter-wave radar includes a radar radio frequency front-end for acquiring radar data and a point cloud processing module for processing radar signals. The point cloud processing module processes the radar data to obtain point cloud information, identifies the target object, obtains the point cloud information corresponding to the target object, and performs trajectory prediction based on the point cloud information corresponding to the target object to obtain the predicted point cloud target points. The camera includes an image acquisition module for acquiring image information near the vehicle body, and performs image processing through the image processing module to obtain image data. The system identifies target objects and obtains the corresponding image pixels. Based on the image pixels, it predicts the trajectory of the target object to obtain pixel target prediction points. The millimeter-wave radar and camera send the target point cloud target prediction points and pixel target prediction points to the vehicle processor, respectively. The point cloud target prediction points and pixel target prediction points are fused to obtain the target prediction points. The target prediction points include the coordinate information of the predicted target object in the next acquisition cycle. Based on the target prediction points, vehicle control information is generated, and response strategies are formulated to ensure the safe driving of the vehicle. Therefore, the accuracy of the target prediction points directly affects the driving safety of the vehicle.

[0064] Figure 3 This is a flowchart illustrating a vehicle control method according to an exemplary embodiment. Figure 2 As shown, the method may include the following steps.

[0065] Step S310: The first radar data and the first image data are respectively transformed into coordinate systems to obtain the second radar data in the preset spatial coordinate system and the second image data in the preset spatial coordinate system; the radar signal points in the second radar data are spatially aligned with the image pixels in the second image data; the first radar data and the first image data are data collected in the same acquisition cycle.

[0066] In this embodiment, the execution entity is the vehicle body processor. It acquires first radar data through radar and first image data through a camera. The radar is a millimeter-wave radar, which includes a radar radio frequency front-end and a computing system. In this embodiment, the computing system in the millimeter-wave radar is removed, and the radar radio frequency front-end is retained. The calculation part is completed by the vehicle body processor. The radar radio frequency front-end is used to collect radar data. The radar data is an analog signal. The radar data is converted into a data signal to obtain the first radar data. The first image data is the image data collected by the camera. The first radar data and the second radar data are transmitted to the vehicle body processor through a high-speed bus. The millimeter-wave radar installed in the vehicle has no computing system, which reduces costs and facilitates the debugging of the millimeter-wave radar.

[0067] Furthermore, the first radar data and the first image data are calibrated. Specifically, spatial and temporal calibration is required for the first radar data and the first image data. Generally, the first radar data is in a polar coordinate system, and the first image data is in a camera coordinate system. Spatial calibration involves converting both the first radar data and the first image data acquired in the same acquisition cycle into a preset spatial coordinate system. All radar signal points in the first radar data are mapped onto the preset spatial coordinate system to obtain the second radar data. Similarly, all image pixels in the first image data are mapped onto the preset spatial coordinate system to obtain the second image data. In the preset spatial coordinate system, the radar signal points and image pixels are aligned, i.e., the radar signal points used to characterize a certain position of the target detection object are aligned. In the spatial coordinate system, image pixels corresponding to the same position of the target detection object can be found. Aligned radar signal points and image pixels represent the same part of the target detection object. The preset spatial coordinate system can be a Cartesian coordinate system. Time calibration is performed by collecting the first radar data and the first image data in the same acquisition cycle. Specifically, the acquisition cycles of the millimeter-wave radar and the camera are not synchronized. Generally, the acquisition cycle of the millimeter-wave radar is longer. The acquisition cycle of the millimeter-wave radar is used as the data calibration cycle. Alternatively, the acquisition cycle of the millimeter-wave radar can be adjusted to a multiple of the acquisition cycle of the camera to facilitate calculation. In this embodiment, the first radar data and the first image data are calibrated based on the vehicle body processor, which can improve the efficiency and accuracy of data calibration.

[0068] Step S320: Process the second radar data to obtain radar point cloud information of the target object;

[0069] The target detection objects can be vehicles, pedestrians, traffic lights, and obstacles around the vehicle that can be sensed by sensors. The second radar data is processed sequentially through range FFT (a fast algorithm for discrete Fourier transform) -> Doppler FFT -> noncoherent accumulation -> target detection -> target measurement (angle, range, and velocity) -> outputting radar point cloud information. This radar point cloud information can characterize multiple detection attributes of the target object, such as the target object's coordinates, distance to the vehicle, and velocity. The angle measurement algorithm typically uses high-resolution spectral estimation, such as spatial isospectral estimation. However, spectral estimation has drawbacks: long computation time and high computational resource consumption, making it unsuitable for the real-time requirements of radar signal processing. Generally, the frame acquisition period for vehicle-mounted millimeter-wave radar is 50ms. In this embodiment, all radar signal processing is unified within the vehicle controller, allowing for centralized computational power in the angle measurement part. The spatial isospectral estimation algorithm can meet the 50ms frame period requirement.

[0070] Step S330: Perform image processing on the second image data to obtain the image pixel information of the target detection object;

[0071] The second image data is processed, and the target detection object is associated with artificial intelligence. A gate is set in the area where the target detection object appears, so as to measure the target detection object and obtain image pixel information. The image pixel information represents multiple detection attributes of the target detection object, such as the distance between the vehicle and the target detection object, the shape, color, coordinates and angle of the target detection object, etc.

[0072] Step S340: Based on the first fusion weights corresponding to the radar point cloud information and the image pixel information respectively, perform data fusion on the radar point cloud information and the image pixel information to obtain the first fusion result; the first fusion weights are determined based on the detection attributes of the target detection object;

[0073] Millimeter-wave radar detection is unaffected by environment and weather, and is more accurate than camera detection in detecting the speed, coordinates, and distance of targets to the vehicle. Cameras, on the other hand, collect image data, which is more accurate in detecting the shape and category of targets. Therefore, based on the detection attributes of the target, a first fusion weight is determined for the information that needs to be emphasized. For example, if the distance between the target and the vehicle needs to be detected, the first fusion weight corresponding to the radar point cloud information is greater than the first fusion weight corresponding to the image pixel information. Data fusion is performed based on their respective first fusion weights to improve the accuracy of the first fusion result. The first fusion result includes the coordinate information of the target in the current acquisition period. If the target is a vehicle in front, the distance between the target and the vehicle can be obtained based on its coordinate information in the current acquisition period. If the current fusion scenario requires detecting the shape of the target, the first fusion weight corresponding to the image pixel information is greater than the first fusion weight corresponding to the radar point cloud information. Data fusion is performed based on their respective first fusion weights to improve the accuracy of the first fusion result, which includes the shape of the target in the current acquisition period.

[0074] Step S350: Based on the first fusion result, predict the trajectory of the target detection object to obtain the first target prediction point;

[0075] The first fusion result includes the coordinate information of the target object in the current acquisition cycle. The trajectory of the target object is predicted to obtain the first target prediction point. The first target prediction point includes the predicted coordinate information of the target object in the next acquisition cycle. Based on the predicted coordinate information, the distance between the target object and its own vehicle in the next acquisition cycle can be predicted.

[0076] Step S360: Generate vehicle control information based on the first target prediction point.

[0077] Based on the predicted coordinates of the target object in the next detection cycle, vehicle control information is generated as a response strategy for the first target prediction point. Specifically, if the distance between the target object and the vehicle is obtained in the next acquisition cycle based on the first target prediction point, and if the distance is less than a preset distance, it is determined that there is a safety hazard to the vehicle. Based on the vehicle control information, emergency braking is performed to ensure safe driving.

[0078] In this embodiment, the vehicle body processor calibrates the first radar data and the first image data to obtain the second radar data and the second image data. The first radar data and the first image data serve as the raw data collected by the radar and camera. The first image data and the first radar data are converted to the same spatial dimension to facilitate data processing and improve data processing efficiency. The second radar data and the second image data are processed separately to obtain radar point cloud information and image pixel information. The first fusion result is based on the detection attributes of the target object, which are assigned corresponding first fusion weights to the radar point cloud information and the image pixel information. Different first fusion weights are assigned based on different detection attributes to improve the flexibility of fusion. The radar point cloud information and the image pixel information still retain the original data from the camera and radar, avoiding the loss of original data and improving the accuracy of the first fusion result. This improves the accuracy of trajectory prediction for the target object and further enhances driving safety.

[0079] In one implementation, before obtaining the first fusion result by fusing radar point cloud information and image pixel information based on the first fusion weights corresponding to the radar point cloud information and image pixel information respectively, the method further includes:

[0080] Determine the influence factors of radar point cloud information and image pixel information in the current fusion scenario;

[0081] Based on the influence factors of radar point cloud information and image pixel information in the current fusion scenario, the first fusion weights corresponding to radar point cloud information and image pixel information are determined respectively.

[0082] This fusion process is the first fusion in this embodiment. Different fusion scenarios are constructed based on different detection attributes of the target object. Depending on the current detection attributes, the influence factors of radar point cloud information and image pixel information differ in the current fusion scenario. The current fusion scenario is determined based on the current driving state. If the current driving state is following another vehicle, it is necessary to determine the speed of the vehicle in front (the target object) and its distance from the vehicle. Millimeter-wave radar is more accurate in detecting the speed and distance of the target object; therefore, the influence factor of radar point cloud information is higher in the current fusion scenario, meaning the first fusion weight corresponding to radar point cloud information is higher than that of image pixel information. The first fusion weight corresponding to the pixel information is as follows: For example, in the current fusion scenario, the distance between the target detection object and the vehicle is being fused. The radar point cloud information indicates that the distance between the target detection object and the vehicle is 5m, while the image pixel information indicates that the distance is 4.5m. The first fusion weight corresponding to the radar point cloud information is higher, which can be 0.7, while the first fusion weight corresponding to the image pixel information can be 0.3. Based on the first fusion weights corresponding to the radar point cloud information and the image pixel information, the first fusion result is obtained. In the first fusion result, the distance between the target detection object and the vehicle is 0.7×5+0.3×4.5=4.85m.

[0083] Different fusion scenarios can be constructed based on different target detection objects. If the target detection object is a traffic light, that is, color recognition is performed on the target detection object. The camera is more accurate in color recognition than millimeter-wave radar. Therefore, the influence factor of image pixel information is higher in the current fusion scenario. That is, the first fusion weight corresponding to image pixel information is higher than the first fusion weight corresponding to radar point cloud information. For example, if the current detection object is a traffic light and it is necessary to determine whether a vehicle can pass, if the radar point cloud information indicates that the traffic light is currently displaying a yellow light, and the image point cloud information indicates that the traffic light is currently displaying a red light, then for color fusion, it is possible to directly choose between image pixel information and radar point cloud information. There is no need to specifically allocate the first fusion weight. The first fusion weight corresponding to image pixel information is higher, and the first fusion result indicates that the traffic light is currently red.

[0084] Different fusion scenarios can be constructed based on different current environmental information. Current environmental information can be different weather conditions (sunny, rainy, and foggy) or day and night. It's known that current environmental information is determined based on current environmental visibility. When the current environmental visibility is higher than a preset visibility, the first fusion weight corresponding to the image pixel information is higher than the first fusion weight corresponding to the radar point cloud information. Conversely, the first fusion weight corresponding to the radar point cloud information is higher than the first fusion weight corresponding to the image pixel information. For example, when the current environmental visibility is higher than the preset visibility, the first fusion weight corresponding to the image pixel information is determined to be higher. The current fused detection attribute is the shape of the target object. If the radar point cloud information indicates that the shape of the target object is a "triangle"... Image pixel information indicates that the target object is trapezoidal in shape. Since the current environmental visibility is higher than the preset visibility, the first fusion weight corresponding to the image pixel information is higher. Therefore, it can be directly determined that the target object's shape is trapezoidal in the first fusion result. Alternatively, a corresponding first fusion weight can be assigned. For example, if the first fusion weight corresponding to the image pixel information is 0.8, and the first fusion weight corresponding to the radar point cloud information is 0.2, the inconsistencies between the trapezoidal and triangular shapes are weighted. For instance, if the inconsistency is the angle of the target angle, with the trapezoidal angle being 180° and the triangular angle being 60°, the first fusion weight indicates that the target object's shape is triangular, and its target angle is 180° × 0.2 + 60° × 0.8 = 84°.

[0085] Furthermore, the current fusion scenario can be predetermined by human intervention, and the information with higher first fusion weight can be allocated according to the needs. This embodiment can perform multi-faceted fusion based on weather, the detection attributes of the target object, and the object type, which can ensure the fusion accuracy of the first fusion result and make the fusion unaffected by the weather environment.

[0086] In one implementation, Figure 4 This is a flowchart illustrating a method for generating vehicle control information according to an exemplary embodiment; generating vehicle control information based on a first target prediction point includes:

[0087] Step S410: Based on radar point cloud information, predict the trajectory of the target detection object to obtain the target prediction points in the point cloud;

[0088] Step S420: Based on image pixel information, predict the trajectory of the target detection object to obtain the pixel target prediction point;

[0089] Step S430: Based on the second fusion weights corresponding to the point cloud target prediction points and the pixel target prediction points, perform data fusion on the point cloud target prediction points and the pixel target prediction points to obtain the second target prediction points; the second fusion weights are determined based on the detection attributes of the target detection object.

[0090] Based on the radar point cloud information of the target object in the current acquisition period and the radar point cloud information in historical acquisition periods, the historical point cloud information of the target object can be obtained. Based on the historical point cloud information and the current driving speed of the target object, the trajectory of the target object can be predicted to obtain the predicted point cloud trajectory information. The predicted point cloud trajectory information includes the radar point cloud information of the target object in the next one or more acquisition periods. Based on the predicted point cloud trajectory information, the point cloud target prediction point is obtained. The point cloud target prediction point is the radar point cloud information of the target object in the next acquisition period. Based on this radar point cloud information, the coordinate information of the target object in the next acquisition period, as well as the distance to the vehicle, can be predicted. Similarly, the trajectory of the target object can be predicted based on image pixel information to obtain pixel target prediction points.

[0091] Furthermore, based on the detection attributes of the target object, the second fusion weights corresponding to the point cloud target prediction points and the pixel target prediction points are determined respectively. Data fusion is then performed on the point cloud target prediction points and the pixel target prediction points. This fusion process is the second fusion in this embodiment. Specifically, millimeter-wave radar detection is not affected by the environment or weather, and is more accurate than camera detection in detecting the speed, coordinate position, and distance of the target object from the vehicle. While the camera collects image data, it is more accurate in detecting the shape and object category of the target object. Therefore, based on the detection attributes of the target object, the first fusion weight corresponding to the information that needs to be emphasized is determined. For example, if it is necessary to detect the distance between the target object and the vehicle, the second fusion weight corresponding to the radar point cloud information is greater than the second fusion weight corresponding to the image pixel information. Data fusion is performed based on their respective second fusion weights to improve the accuracy of the second fusion result. The second fusion result includes the coordinate information of the target object in the current acquisition period. For example, if the target object is a vehicle in front, the distance between the target object and the vehicle can be obtained based on the coordinate information of the target object in the current acquisition period.

[0092] In this embodiment, the first fusion process integrates and processes the sensor-sensed data (first radar data and first image data) and outputs a fusion result. This algorithm has high requirements for the timeliness of different types of data and high requirements for data alignment and calibration, so the corresponding data processing results will be more accurate. The vehicle processor can meet the computing power requirements of this embodiment. The second fusion process generates independent information (point cloud target prediction points and pixel prediction points) after the different sensors independently perceive through different algorithms. The two sets of independent information are then fused. The first fusion and the second fusion can be performed simultaneously to improve data processing efficiency.

[0093] Step S440: Based on the third fusion weights corresponding to the first target prediction point and the second target prediction point respectively, perform data fusion on the first target prediction point and the second target prediction point to obtain the target prediction point; the third fusion weight corresponding to the first target prediction point is greater than the third fusion weight corresponding to the second target prediction point.

[0094] Step S450: Generate vehicle control information based on the target prediction point.

[0095] The first target prediction point and the second target prediction point are fused together to form the third fusion in this embodiment. Since the first target prediction point is a prediction result obtained by fusing radar point cloud information and image pixel information, it is more accurate than the second target prediction point. Therefore, in the allocation of the second fusion weight, the third fusion weight corresponding to the first target prediction point is greater than the third fusion weight corresponding to the second target prediction point, so as to improve the accuracy of the target prediction point, thereby enabling the vehicle to make more accurate decisions and improve the accuracy of vehicle control information. This embodiment undergoes three fusions and is not affected by weather, light, or angle, which can avoid false alarms and missed alarms.

[0096] In one implementation, before fusing the point cloud target prediction points and pixel target prediction points based on their respective second fusion weights to obtain the second target prediction points, the method further includes:

[0097] Determine the influence factors of point cloud target prediction points and pixel target prediction points in the current fusion scene;

[0098] Based on the influence factors of point cloud target prediction points and pixel target prediction points in the current fusion scenario, the point cloud target prediction points are determined as the second fusion weights corresponding to the pixel target prediction points.

[0099] The second fusion follows the same principle as the first fusion. The current fusion scenario can be determined based on different detection attributes of the target object, current environmental information, or object category of the target object. As a preferred implementation, the fusion scenario is determined differently in the three fusion processes. For example, if the first fusion determines the current fusion scenario based on the detection attributes of the target object, the second fusion can be based on current environmental information, and the third fusion can be based on the object category of the target object. By performing fusion based on weather, the detection attributes of the target object, and object type, the fusion accuracy of the fusion result can be guaranteed, making the fusion unaffected by weather, lighting, detection attributes, etc., thereby improving the accuracy of the target prediction point and facilitating more accurate trajectory prediction for the target object.

[0100] In one implementation, vehicle control information is generated based on the target prediction point, including:

[0101] Obtain current vehicle status information;

[0102] Based on the target prediction point and the current vehicle status information, vehicle control information is generated.

[0103] The system acquires current vehicle status information, which can be categorized into normal driving status, following status, etc. Normal driving status refers to driving on regular roads, and the corresponding target detection objects can include surrounding vehicles, pedestrians, and traffic lights ahead. When the current vehicle status information includes surrounding vehicles or pedestrians, the corresponding target prediction point includes the predicted coordinates of the target detection object in the next acquisition cycle. It also predicts whether the distance between the target detection object and the vehicle will be less than a preset distance. If it is less than the preset distance, vehicle control information is generated for emergency braking. The target execution module includes an emergency braking module that applies emergency braking based on the vehicle control information. Furthermore, the target execution module can also include a steering module to determine the direction of the target detection object and drive the vehicle to avoid it in the opposite direction. When the target detection object is a traffic light ahead, the target prediction point includes the status information of the traffic light ahead in the next acquisition cycle. If the traffic light ahead is red in the next acquisition cycle, the target execution module responds to the vehicle control information and drives the vehicle to stop.

[0104] Furthermore, when the current vehicle status is following, the corresponding target detection object can include the vehicle in front. Based on the target prediction point, the driving speed of the vehicle in front and the distance between the vehicle and the vehicle can be determined. The corresponding target execution module can include a speed control module. Based on the vehicle control information, the speed control module keeps the driving speed of the vehicle and the vehicle in front consistent and ensures that the distance between the vehicle and the vehicle in front is greater than a preset distance. On highways, the threshold of the preset distance can be increased to maintain the distance between vehicles and ensure safe driving on highways.

[0105] Furthermore, the target prediction point can be displayed on the in-vehicle terminal to remind the driver to take timely action.

[0106] In one implementation, the first fusion result includes historical trace information of the target detected object;

[0107] Based on the first fusion result, the trajectory of the detected target is predicted to obtain the first target prediction point, including:

[0108] Based on the historical point information of the target detection object, the trajectory of the target detection object is predicted to obtain the predicted trajectory information of the target detection object.

[0109] The first target prediction point is determined based on the predicted flight path information.

[0110] This embodiment can save the historical coordinate information of the target detection object in the historical detection cycle. The historical coordinate information is connected sequentially according to the time sequence to form the historical point information of the target detection object. Based on the historical point information and the status information of the target detection object, the trajectory is predicted to obtain the predicted trajectory information. The predicted trajectory information includes at least the coordinate information or status information of the target detection object in the next one or more collection cycles. If the target detection object is a vehicle in front, the predicted trajectory information includes the predicted coordinate information of the vehicle in front in the next collection cycle. Based on the coordinate information, the distance between the target detection object and the vehicle is determined. If the distance is less than a preset distance, it is determined that there is a safety hazard to the vehicle, and emergency braking is performed based on the vehicle control information to ensure safe driving. If the target detection object is a traffic light, the predicted trajectory information includes the predicted color of the traffic light in the next collection cycle, thereby determining whether to pass through the intersection and avoiding the situation where the street light color changes when the vehicle is in the intersection, affecting driving safety.

[0111] In one implementation, Figure 5 This is a flowchart illustrating a calibration method according to an exemplary embodiment, wherein the number of first radar data and first image data both include multiples;

[0112] The first radar data and the first image data are transformed into different coordinate systems to obtain second radar data in a preset spatial coordinate system and second image data in a preset spatial coordinate system, including:

[0113] Step S510: Determine the associated data corresponding to each of the multiple first radar data, wherein the associated data is the first image data that is adapted to the detection direction of the first radar data;

[0114] Step S520: Perform coordinate system transformation on the multiple first radar data and their respective associated data to obtain multiple second radar data in the preset spatial coordinate system and multiple second image data in the preset spatial coordinate system; the radar signal points in the multiple second radar data are spatially aligned with the image pixel points in their respective second image data.

[0115] A typical vehicle is equipped with multiple millimeter-wave radars and cameras based on various detection directions. By setting the installation positions and angles of the millimeter-wave radars and cameras, extrinsic parameter calibration is performed to ensure that the same detection direction is detected by both the millimeter-wave radars and cameras. The vehicle body sensors receive multiple first radar data and first image data, and perform intrinsic parameter calibration. Each first radar data corresponds to associated data, which is first image data adapted to the detection direction of the first radar data. Adaptation means that the first image data includes at least the target detection object from the first radar data; that is, the first radar data includes target detection. In the context of multiple first image data sets, any first image data that can detect a target object is considered as associated data of the first radar data. Therefore, there can be multiple associated data sets. Similarly, associated data can be matched based on the first image data. The associated data is first radar data that is compatible with the detection direction of the first image data. The vehicle body processor has high processing power and can simultaneously calibrate multiple first radar data sets and their corresponding associated data, improving calibration efficiency. The same target object is detected by the camera and millimeter-wave radar based on multiple detection directions, improving the accuracy of calibration and thus enhancing the reliability of the target prediction point.

[0116] Figure 8This is a block diagram of a vehicle control system according to an exemplary embodiment. In this embodiment, the camera transmits the first image information it acquires to the vehicle body processor via a high-speed bus, and the millimeter-wave radar transmits the first radar data it acquires to the vehicle body processor via a high-speed bus. Data calibration and data processing are performed in the vehicle body processor. Specifically, the calibration module in the vehicle body processor performs time and spatial calibration on the first image data and the first radar data to obtain second image data and second radar data. The image pixels in the second image data can be aligned with the radar signal points in the second radar data in a preset spatial coordinate system. In the image processing module, target detection is performed. The system identifies objects and associates them with the target detection objects in the second image data to obtain image pixel information. This image pixel information includes the target object's color, shape, speed, object category, and coordinate information corresponding to historical acquisition periods. In the point cloud processing module, the target object is processed sequentially as follows: distance FFT (a fast algorithm for discrete Fourier transform) -> Doppler FFT -> noncoherent accumulation -> target detection -> target measurement (angle measurement, range measurement, velocity measurement) -> outputting radar point cloud information. This radar point cloud information includes the target object's coordinate information corresponding to historical acquisition periods, its distance from the target vehicle in the current acquisition period, and the target object's shape. The radar point cloud information and image pixel information are fused in the first fusion module to obtain the first fusion result. The first fusion result can accurately represent the coordinate information of the target detection object in the historical acquisition cycle. Based on the first fusion result, trajectory prediction is performed to obtain the predicted trajectory information. In the predicted trajectory information, the first target prediction point is determined. The first target prediction point includes the coordinate information of the target detection object obtained in the first fusion in the next acquisition cycle. This is the first fusion, which fuses the detection attributes of the target detection object. The trajectory prediction is performed based on the image pixel information to obtain the image target prediction point. The trajectory prediction is performed based on the radar point cloud information. The first target prediction point is obtained by measuring and fusing the target prediction point in the image with the target prediction point in the point cloud. This is the second fusion. The second fusion is based on the current environmental information. The first target prediction point is fused with the second target prediction point to obtain the target prediction point. This is the third fusion. In this embodiment, the target prediction point is obtained through three fusions, taking into account the detection attributes of the target prediction object and the current environmental information. That is, the target prediction point is not affected by the weather. In any environment, the accuracy of the target prediction point can be guaranteed, thereby generating vehicle control information, driving the target execution module to execute, and making timely response strategies to ensure the safe driving of the vehicle.

[0117] This embodiment also provides a vehicle control device. Figure 7This is a block diagram of a vehicle control device according to an exemplary embodiment, the device being capable of implementing all the above-described method steps, the device comprising:

[0118] The calibration module 710 is used to convert the coordinate system of the first radar data and the coordinate system of the first image data into a preset spatial coordinate system to obtain the second radar data and the second image data. The radar signal points in the second radar data and the image pixels in the second image data are spatially aligned in the preset spatial coordinate system. The first radar data and the first image data are data acquired in the same acquisition cycle.

[0119] Data processing module 720 is used to process the second radar data to obtain radar point cloud information of the target detection object;

[0120] Image processing module 730 is used to perform image processing on the second image data to obtain image pixel information of the target detection object;

[0121] The fusion module 740 is used to perform a first data fusion on radar point cloud information and image pixel information based on the fusion weights corresponding to radar point cloud information and image pixel information respectively, to obtain a first fusion result; the first fusion weights are determined based on the detection attributes of the target detection object.

[0122] The trajectory prediction module 750 is used to predict the trajectory of the target detection object based on the first fusion result, and obtain the first target prediction point;

[0123] The generation module 760 is used to generate vehicle control information based on the first target prediction point.

[0124] The vehicle control unit also includes,

[0125] The first determining module is used to determine the influence factors of radar point cloud information and image pixel information in the current fusion scenario, respectively.

[0126] The second determining module is used to determine the first fusion weights corresponding to radar point cloud information and image pixel information respectively, based on the influence factors of radar point cloud information and image pixel information in the current fusion scenario.

[0127] Module 760 is generated, including:

[0128] The point cloud target prediction point generation module is used to predict the trajectory of the target detection object based on radar point cloud information and obtain the point cloud target prediction points.

[0129] The pixel target prediction point generation module is used to predict the trajectory of the target detection object based on the image pixel information to obtain pixel target prediction points.

[0130] The first fusion module is used to perform data fusion on the point cloud target prediction points and the pixel target prediction points based on the second fusion weights corresponding to the point cloud target prediction points and the pixel target prediction points respectively, so as to obtain the second target prediction points; the second fusion weights are determined based on the detection attributes of the target detection object.

[0131] The second fusion module is used to perform data fusion on the first target prediction point and the second target prediction point based on the third fusion weights corresponding to the first target prediction point and the second target prediction point, so as to obtain the target prediction point; the third fusion weight corresponding to the first target prediction point is greater than the third fusion weight corresponding to the second target prediction point.

[0132] The first generation module is used to generate vehicle control information based on the target prediction point.

[0133] The vehicle control unit also includes,

[0134] The third determination module is used to determine the influence factors of point cloud target prediction points and pixel target prediction points in the current fusion scene, respectively.

[0135] The fourth determination module is used to determine the second fusion weights corresponding to the point cloud target prediction points and the pixel target prediction points based on the influence factors of the point cloud target prediction points in the current fusion scene and the influence factors of the pixel target prediction points in the current fusion scene.

[0136] The first generation module includes:

[0137] The acquisition module is used to acquire current vehicle status information;

[0138] The second generation module is used to generate vehicle control information based on the target prediction point and the current vehicle status information.

[0139] The generation module 760 also includes:

[0140] The predicted trajectory information generation module is used to predict the trajectory of the target detection object based on the historical point information of the target detection object, and obtain the predicted trajectory information of the target detection object; the first fusion result includes the historical point information of the target detection object;

[0141] The fifth determination module is used to determine the first target prediction point based on the predicted trajectory information.

[0142] The calibration module 710 also includes:

[0143] The sixth determining module is used to determine the associated data corresponding to each of the multiple first radar data. The associated data is the first image data that is adapted to the detection direction of the first radar data. The number of first radar data and first image data includes multiple data.

[0144] The coordinate system transformation module is used to transform the coordinate systems of multiple first radar data and their corresponding associated data to obtain multiple second radar data in a preset spatial coordinate system and multiple second image data in a preset spatial coordinate system; the radar signal points in the multiple second radar data are spatially aligned with the image pixel points in their respective second image data.

[0145] It should be noted that the apparatus provided in the above embodiments is only illustrated by the division of the above functional modules when implementing its functions. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the apparatus and method embodiments provided in the above embodiments belong to the same concept, and the specific implementation process can be found in the method embodiments, which will not be repeated here.

[0146] Figure 8 This is a block diagram illustrating an electronic device for vehicle control according to an exemplary embodiment. The electronic device may be a terminal, and its internal structure diagram may be as follows: Figure 8 As shown, the electronic device includes a processor, memory, network interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The network interface is used to communicate with external terminals via a network connection. When the computer program is executed by the processor, it implements a vehicle control method. The display screen can be a liquid crystal display (LCD) or an e-ink display. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad mounted on the device's casing, or an external keyboard, touchpad, or mouse.

[0147] Those skilled in the art will understand that Figure 8 The structure shown is merely a block diagram of a portion of the structure related to the present disclosure and does not constitute a limitation on the electronic device to which the present disclosure is applied. A specific electronic device may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0148] In an exemplary embodiment, an electronic device is also provided, including: a processor; and a memory for storing processor-executable instructions; wherein the processor is configured to execute the instructions to implement the vehicle control method as described in the embodiments of this disclosure.

[0149] In an exemplary embodiment, a computer-readable storage medium is also provided, wherein instructions in the storage medium, when executed by a processor of an electronic device, enable the electronic device to perform the vehicle control method of the present disclosure embodiments.

[0150] In an exemplary embodiment, a computer program product containing instructions is also provided, which, when run on a computer, causes the computer to perform the vehicle control method of the present disclosure embodiments.

[0151] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. This computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM), etc.

[0152] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the following claims.

[0153] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.

Claims

1. A vehicle control method, characterized in that, The method includes: The first radar data and the first image data are respectively transformed into a coordinate system to obtain the second radar data in a preset spatial coordinate system and the second image data in the preset spatial coordinate system; the radar signal points in the second radar data are spatially aligned with the image pixels in the second image data; the first radar data and the first image data are data acquired in the same acquisition period. The second radar data is processed to obtain radar point cloud information of the target object; The second image data is processed to obtain the image pixel information of the target detection object; Based on the first fusion weights corresponding to the radar point cloud information and the image pixel information respectively, the radar point cloud information and the image pixel information are fused to obtain a first fusion result; the first fusion weights are determined based on the detection attributes of the target detection object. Based on the first fusion result, the trajectory of the target detection object is predicted to obtain the first target prediction point; Based on the radar point cloud information, the trajectory of the target detection object is predicted to obtain the point cloud target prediction points; Based on the image pixel information, the trajectory of the target detection object is predicted to obtain pixel target prediction points; Based on the second fusion weights corresponding to the point cloud target prediction points and the pixel target prediction points respectively, the point cloud target prediction points and the pixel target prediction points are fused to obtain a second target prediction point; the second fusion weights are determined based on the detection attributes of the target detection object. Based on the third fusion weights corresponding to the first target prediction point and the second target prediction point respectively, data fusion is performed on the first target prediction point and the second target prediction point to obtain the target prediction point; the third fusion weight corresponding to the first target prediction point is greater than the third fusion weight corresponding to the second target prediction point; The vehicle control information is generated based on the target prediction point.

2. The method according to claim 1, characterized in that, Before fusing the radar point cloud information and the image pixel information based on the first fusion weights corresponding to the radar point cloud information and the image pixel information respectively to obtain the first fusion result, the method further includes: Determine the influence factors of the radar point cloud information and the image pixel information in the current fusion scene; Based on the influence factors of the radar point cloud information and the image pixel information in the current fusion scenario, the first fusion weights corresponding to the radar point cloud information and the image pixel information are determined respectively.

3. The method according to claim 1, characterized in that, Before fusing the point cloud target prediction points and the pixel target prediction points based on the second fusion weights corresponding to the point cloud target prediction points and the pixel target prediction points to obtain the second target prediction points, the method further includes: Determine the influence factors of the point cloud target prediction points and the pixel target prediction points in the current fusion scene, respectively; Based on the influence factors of the point cloud target prediction points in the current fusion scene and the influence factors of the pixel target prediction points in the current fusion scene, the point cloud target prediction points are determined as the second fusion weights corresponding to the pixel target prediction points.

4. The method according to claim 1, characterized in that, The process of generating the vehicle control information based on the target prediction point includes: Obtain current vehicle status information; The vehicle control information is generated based on the target prediction point and the current vehicle status information.

5. The method according to claim 1, characterized in that, The first fusion result includes the historical trace information of the target detection object; The step of predicting the trajectory of the detected target based on the first fusion result to obtain a first target prediction point includes: Based on the historical point information of the target detection object, the trajectory of the target detection object is predicted to obtain the predicted trajectory information of the target detection object; The first target prediction point is determined based on the predicted flight path information.

6. The method according to claim 1, characterized in that, Both the first radar data and the first image data include multiple data sets. The step of performing coordinate system transformation on the first radar data and the first image data to obtain the second radar data in the preset spatial coordinate system and the second image data in the preset spatial coordinate system includes: Each of the multiple first radar data sets is assigned a corresponding associated data set, wherein the associated data set is a first image data set that is adapted to the detection direction of the first radar data set. The multiple first radar data and their respective associated data are transformed into coordinate systems to obtain multiple second radar data in a preset spatial coordinate system, and multiple second image data in the preset spatial coordinate system; the radar signal points in the multiple second radar data are spatially aligned with the image pixel points in their respective second image data.

7. A vehicle control device, characterized in that, The device includes: The calibration module is used to perform coordinate system transformation on the first radar data and the first image data respectively to obtain the second radar data in the preset spatial coordinate system and the second image data in the preset spatial coordinate system; the radar signal points in the second radar data are spatially aligned with the image pixels in the second image data; the first radar data and the first image data are data acquired in the same acquisition cycle; the data processing module is used to process the second radar data to obtain the radar point cloud information of the target detection object; The image processing module is used to perform image processing on the second image data to obtain the image pixel information of the target detection object; The fusion module is used to perform data fusion on the radar point cloud information and the image pixel information based on the first fusion weights corresponding to the radar point cloud information and the image pixel information respectively, to obtain a first fusion result; the first fusion weights are determined based on the detection attributes of the target detection object; The trajectory prediction module is used to predict the trajectory of the target detection object based on the first fusion result to obtain a first target prediction point; The generation module is used to predict the trajectory of the target detection object based on the radar point cloud information to obtain point cloud target prediction points; predict the trajectory of the target detection object based on the image pixel information to obtain pixel target prediction points; fuse the point cloud target prediction points and the pixel target prediction points based on the second fusion weights corresponding to the point cloud target prediction points and the pixel target prediction points to obtain a second target prediction point; the second fusion weights are determined based on the detection attributes of the target detection object; fuse the first target prediction point and the second target prediction point based on the third fusion weights corresponding to the first target prediction point and the second target prediction point to obtain a target prediction point; the third fusion weight corresponding to the first target prediction point is greater than the third fusion weight corresponding to the second target prediction point; and generate the vehicle control information based on the target prediction points.

8. An electronic device, characterized in that, include: processor; Memory used to store the processor's executable instructions; The processor is configured to execute the instructions to implement the vehicle control method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, When the instructions in the storage medium are executed by the processor of the electronic device, the electronic device is able to perform the vehicle control method as described in any one of claims 1 to 6.

Images