Vehicle control method and apparatus, device, and storage medium

Abstract

A vehicle control method and apparatus, a device, and a storage medium. The method comprises: scanning, by means of a four-dimensional millimeter-wave radar of a vehicle, an object ahead of the vehicle within a lane line, and extracting a feature parameter of the object and position information of the object, wherein the position information comprises: the height of the object from the road surface and the width of the object from the lane line; on the basis of the feature parameter, determining whether the object is a preset object that triggers vehicle braking; and if the object is the preset object and the position information of the object meets preset conditions, controlling vehicle braking on the basis of a driving parameter of the vehicle, wherein the preset conditions comprise: the height of the object from the road surface is less than or equal to a preset height, and the width of the object from the lane line is less than or equal to a preset width. The method can avoid the problem of a safety accident caused by the inability of a vehicle to brake in time, thereby improving the driving safety.

Description

Vehicle control method, device, equipment and storage medium

[0001] The present application claims priority to the Chinese patent application No. 202411094409.4, filed on August 9, 2024, the content of which is incorporated herein by reference in its entirety. TECHNICAL FIELD

[0002] The present disclosure relates to the field of automotive technology, and in particular, to a vehicle control method, device, equipment and storage medium. BACKGROUND

[0003] With the development of automotive technology, in the current driving process of a vehicle, a front object (also can be referred to as an obstacle or an object) can be recognized by a camera (also can be referred to as a visual sensor) of the vehicle, whether it is an object (such as a four-wheeled vehicle, a two-wheeled vehicle, etc.) that needs to be braked, and when the front object is an object that needs to be braked, the vehicle is controlled to brake to avoid collision with the front object. SUMMARY

[0004] The present disclosure provides a vehicle control method, device, equipment and storage medium, aiming to avoid safety problems caused by the vehicle failing to brake in time, improve the safety of driving, and avoid the problem of frequent braking of the vehicle affecting the user experience.

[0005] In a first aspect, a vehicle control method is provided, which includes: scanning an object in front of a vehicle located in a lane line by a four-dimensional millimeter wave radar of the vehicle, and extracting a characteristic parameter of the object and position information of the object; the characteristic parameter includes at least one of a radar cross section (RCS) or a size of the object; the position information includes a height of the object from a road surface and a width of the object from the lane line; determining whether the object is a preset object that triggers vehicle braking based on the characteristic parameter; if the object is the preset object and the position information of the object meets a preset condition, controlling the vehicle to brake based on a driving parameter of the vehicle; the driving parameter includes at least one of a distance between the object and the vehicle or a driving speed of the vehicle; the preset condition includes that the height of the object from the road surface is less than or equal to a preset height, and the width of the object from the lane line is less than or equal to a preset width.

[0006] In some embodiments, the method further includes: obtaining a risk coefficient corresponding to each of the preset objects; if the object is the preset object, the position information of the object does not meet the preset condition, and the risk coefficient corresponding to the object is less than or equal to a preset risk coefficient, controlling the vehicle to turn until the vehicle passes the object in the lane line; if the object is the preset object, the position information of the object does not meet the preset condition, and the risk coefficient corresponding to the object is greater than the preset risk coefficient, controlling the vehicle to brake based on the driving parameter.

[0007] In some embodiments, determining, based on the characteristic parameters, whether the object is a preset object triggering the vehicle to brake comprises: determining that the object is the preset object if the characteristic parameters of the object satisfy preset thresholds corresponding to each preset object; and determining that the object is not the preset object if at least one of the characteristic parameters of the object does not satisfy a preset threshold corresponding to the preset object.

[0008] In some embodiments, the preset thresholds corresponding to the preset objects are obtained through big data training.

[0009] In some embodiments, controlling the vehicle to brake based on the driving parameters of the vehicle comprises: controlling the vehicle to brake N times based on the driving parameters until the vehicle stops at a target position; the target position is a position separated from the object by a preset distance; and N is an integer greater than 0.

[0010] In some embodiments, controlling the vehicle to brake N times based on the driving parameters comprises: determining, based on the driving parameters, a braking parameter corresponding to each of the N times of braking; the braking parameter comprises at least one of a brake pedal opening degree or a braking time length; and controlling the vehicle to brake N times based on the braking parameter corresponding to each of the N times of braking.

[0011] In some embodiments, if the object is the preset object and the position information of the object satisfies a preset condition, before controlling the vehicle to brake based on the driving parameters of the vehicle, the method further comprises: obtaining a first confidence degree and a second confidence degree; the first confidence degree is a confidence degree of the object scanned by a camera; and the second confidence degree is a confidence degree of the object scanned by a four-dimensional millimeter wave radar; if the first confidence degree is greater than or equal to the second confidence degree, determining, by the camera, whether the object is the preset object; and if the first confidence degree is less than the second confidence degree, determining, by the four-dimensional millimeter wave radar, whether the object is the preset object.

[0012] In a second aspect, a vehicle control device is provided, which comprises a processing module and a determining module; the processing module is configured to scan, by a four-dimensional millimeter wave radar of a vehicle, an object in front of the vehicle within a lane line, and extract characteristic parameters of the object and position information of the object; the characteristic parameters comprise at least one of a radar cross section (RCS) or a size of the object; the position information comprises a height of the object from a road surface and a width of the object from the lane line; the determining module is configured to determine, based on the characteristic parameters, whether the object is a preset object triggering the vehicle to brake; and the processing module is further configured to control the vehicle to brake based on driving parameters of the vehicle if the object is the preset object and the position information of the object satisfies a preset condition; the driving parameters comprise at least one of a distance between the object and the vehicle or a driving speed of the vehicle; and the preset condition comprises that the height of the object from the road surface is less than or equal to a preset height and the width of the object from the lane line is less than or equal to a preset width.

[0013] In some embodiments, the apparatus further comprises a transmission module and a processing module. The transmission module is configured to acquire a respective risk coefficient of each of the preset objects; the processing module is further configured to, if the object is a preset object, the position information of the object does not satisfy the preset condition, and the risk coefficient of the object is less than or equal to a preset risk coefficient, control the vehicle to turn based on the driving parameter until the vehicle drives around the object within the lane line; and the processing module is further configured to, if the object is a preset object, the position information of the object does not satisfy the preset condition, and the risk coefficient of the object is greater than the preset risk coefficient, control the vehicle to brake based on the driving parameter.

[0014] In some embodiments, the determination module is further configured to determine that the object is a preset object if the characteristic parameter of the object satisfies a preset threshold corresponding to any of the preset objects; and the determination module is further configured to determine that the object is not a preset object if the characteristic parameter of the object does not satisfy the preset threshold corresponding to any of the preset objects.

[0015] In some embodiments, the preset threshold corresponding to each of the preset objects is obtained through big data training.

[0016] In some embodiments, the processing module is further configured to control the vehicle to brake N times based on the driving parameter until the vehicle stops at a target position; the target position is a position separated from the object by a preset distance; and N is an integer greater than 0.

[0017] In some embodiments, the determination module is further configured to determine a respective braking parameter of each of the N times of braking based on the driving parameter; and the braking parameter comprises at least one of a brake pedal opening degree or a braking time length; and the processing module is further configured to control the vehicle to brake N times based on the respective braking parameter of each of the N times of braking.

[0018] In some embodiments, the transmission module is further configured to acquire a first confidence and a second confidence; the first confidence is a confidence of the object scanned by the camera; and the second confidence is a confidence of the object scanned by the four-dimensional millimeter wave radar; the determination module is further configured to determine whether the object is a preset object through the camera if the first confidence is greater than or equal to the second confidence; and the determination module is further configured to determine whether the object is a preset object through the four-dimensional millimeter wave radar if the first confidence is less than the second confidence.

[0019] In a third aspect, an electronic device is provided, comprising: a processor; a memory for storing processor-executable instructions; and the processor is configured to execute the instructions to implement the method of the first aspect and any possible implementation thereof.

[0020] In a fourth aspect, a computer-readable storage medium is provided, which, when instructions in the computer-readable storage medium are executed by a processor of an electronic device, enables the electronic device to perform the method of the first aspect and any possible implementation thereof.

[0021] In a fifth aspect, a vehicle is provided, comprising a vehicle control device configured to implement the method of the first aspect and any possible implementation thereof.

[0022] Some embodiments of the present disclosure provide a vehicle control method, which scans an object in front of a vehicle within a lane line by a four-dimensional millimeter wave radar of the vehicle, and extracts a feature parameter including a radar cross section (RCS) and a size of the object, and position information including a height of the object from a road surface and a width of the object from the lane line. In some embodiments, based on the feature parameter, it is determined that the object is a preset object triggering braking of the vehicle, and the position information of the object satisfies a preset condition that the height of the object from the road surface is less than or equal to a preset height and the width of the object from the lane line is less than or equal to a preset width, to control the vehicle braking based on driving parameters including a distance of the object from the vehicle and a driving speed of the vehicle.

[0023] That is, according to the characteristics of the four-dimensional millimeter wave radar, it is known that the four-dimensional millimeter wave radar is not easily affected by the environment and has a long scanning distance. The radar cross section (RCS) and the size can represent the shape feature of the object, so as to determine whether the object is an object triggering braking of the vehicle. In addition, generally, the closer the distance of the object from the vehicle and the faster the driving speed, the greater the amplitude of the vehicle braking needs to be controlled. Thus, the problem of safety accidents caused by the vehicle being unable to brake in time is avoided, and the safety of driving is improved.

[0024] In addition, according to the height of the obstacle from the road surface and the width of the obstacle from the lane line, the drivable area of the vehicle within the lane line without collision with the obstacle can be determined, so as to control the vehicle braking when the vehicle cannot pass through the drivable area. Thus, the problem of frequent braking of the vehicle caused by directly controlling the vehicle braking is avoided, and the user experience is improved. BRIEF DESCRIPTION OF DRAWINGS

[0025] In order to more clearly illustrate the technical solutions of some embodiments of the present disclosure, the drawings needed in the embodiment description will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present disclosure, and other drawings can also be obtained by those skilled in the art without creative labor.

[0026] FIG. 1 is a schematic diagram of the installation position of a 4D millimeter wave radar and a camera according to some embodiments;

[0027] FIG. 2 is a block diagram of a vehicle control system according to some embodiments;

[0028] FIG. 3 is a flowchart of a vehicle control method according to some embodiments;

[0029] FIG. 4 is a flowchart of a vehicle control method according to some embodiments;

[0030] FIG. 5 is a flowchart of a vehicle control method according to some embodiments;

[0031] FIG. 6 is a flowchart of a vehicle control method according to some embodiments;

[0032] FIG. 7 is a flowchart of a 4D millimeter wave radar and camera fusion for vehicle control according to some embodiments;

[0033] FIG. 8 is a block diagram of a vehicle control device according to some embodiments;

[0034] FIG. 9 is a block diagram of an electronic device according to some embodiments;

[0035] FIG. 10 is a block diagram of a vehicle according to some embodiments. DETAILED DESCRIPTION

[0036] The technical solutions in some embodiments of the present disclosure will be clearly and completely described below with reference to the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, rather than all the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of protection of the present disclosure.

[0037] In the description of the present disclosure, the terms "first", "second" are used only for the purpose of description, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined with "first", "second" can explicitly or implicitly include one or more of the features.

[0038] In the description of the present disclosure, it should be noted that, unless otherwise explicitly specified and limited, the terms "mounting", "connecting", "connecting", "communication" should be understood in a broad sense, for example, it can be fixed connection, or detachable connection, or integral connection. It can be directly connected, or indirectly connected through an intermediate medium, or the communication between the two elements inside. For those of ordinary skill in the art, the meaning of the above terms in the present disclosure can be understood according to the example situation.

[0039] In some embodiments of the disclosure, the term "comprising," "containing" or any other variant thereof is intended to cover a non-exclusive inclusion, such that a process, article, or apparatus that comprises a list of elements does not include only those elements but can also include other elements not expressly listed or inherent to such process, article, or apparatus. Without more limitations, an element defined by the phrase "comprising a... " does not exclude the presence of additional identical elements in the process, article, or apparatus that includes the element.

[0040] In some embodiments of the disclosure, the word "exemplary" or "for example" is used to mean serving as an example or illustration. Any embodiment or design described as "exemplary" or "for example" should not be construed as being preferred or advantageous over other embodiments or designs. Rather, the use of the word "exemplary" or "for example" is intended to present concepts in a concrete manner.

[0041] In the description of the specification, example features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0042] In the application of vehicle automatic driving, multiple sensors such as cameras, lidar, 3D millimeter wave radar and four-dimensional (4D) millimeter wave radar are usually used to improve the reliability of the automatic driving system.

[0043] At present, when the vehicle is driving, whether the front object (also referred to as object) is an object requiring vehicle braking can be identified through the camera of the vehicle, and when the front object is an object requiring vehicle braking, the distance between the vehicle and the front object is detected through the 3D millimeter wave radar of the vehicle, the vehicle braking is controlled according to the distance between the vehicle and the front object, and the collision between the vehicle and the front object is avoided.

[0044] However, when the vehicle braking is controlled through the camera, the distance of the object is short because the camera is easily affected by the environment (for example, the camera is greatly affected by light intensity, night, rain, snow and other factors), the accuracy of detecting the object is low when the environment is poor, the probability of passing the detection is very low, and only static objects such as four-wheeled vehicles and two-wheeled vehicles can be detected, and the passing probability of detecting adults, children and special-shaped objects is very low. Therefore, the object cannot be accurately identified, and if the vehicle speed is fast, the vehicle may not be able to brake in time, thereby causing a safety accident.

[0045] To solve the above problems, some embodiments of the present disclosure provide a vehicle control method, which can realize autonomous emergency braking (AEB) for a stationary object in a high-speed scene. The 4D millimeter wave radar has the characteristics of detecting a farther distance, all-weather coverage, being less affected by adverse environmental factors, and having a pitch detection capability. The 4D millimeter wave radar scans the object in front of the vehicle and extracts the characteristic parameters of the object, identifies the type of the object, and controls the vehicle braking according to the distance between the object and the vehicle and the driving speed of the vehicle when the object is an object that needs to be braked.

[0046] In addition, when the environment is good, the confidence of the object recognition by the camera is higher than that of the 4D millimeter wave radar. Therefore, while the 4D millimeter wave radar scans the object in front of the vehicle, the camera also scans the object in front of the vehicle, and the confidence of the scanned object by the two is compared. The sensor with higher confidence is used to identify the category of the object. Thus, the 4D millimeter wave radar is used as the main sensor, and the camera is used as the auxiliary sensor. The object is detected and braked through the fusion of the 4D millimeter wave radar and vision, which improves the pass probability of object detection, the robustness of detected objects, and the cost performance.

[0047] In addition, according to the height of the obstacle from the road surface and the width of the obstacle from the lane line, the drivable area of the vehicle in the lane line without collision with the obstacle is determined. When the vehicle cannot pass through the drivable area, the vehicle is controlled to brake, and when the vehicle can pass through the drivable area, the vehicle is controlled to turn and pass through the drivable area. Thus, directly controlling the vehicle to brake can easily cause the vehicle to brake frequently, which affects the user experience. Therefore, some embodiments of the present disclosure have great application value for intelligent driving of a high-speed vehicle.

[0048] As shown in FIG. 1, the 4D millimeter wave radar 11 is located on the bumper of the vehicle 12, for example, at the center of the bumper. The camera 13 is located at the top of the vehicle 12, for example, at the center of the top.

[0049] In an implementation manner, before the vehicle starts to drive, the 4D millimeter wave radar 11 can be manually installed at the center of the bumper of the vehicle 12, and the camera 13 can be manually installed at the center of the top of the vehicle 12, so that the 4D millimeter wave radar 11 and the camera 13 can identify the object in front of the vehicle and brake when the vehicle drives.

[0050] Some embodiments of the present disclosure provide a vehicle control method, which can be applied to a vehicle control system. FIG. 2 is a structural diagram of a vehicle control system according to some embodiments. As shown in FIG. 2, the vehicle control system 20 includes a radar 21, a camera 22, and a processor 23.

[0051] The radar 21 is configured to scan an object in front of the vehicle within a lane line, extract a feature parameter of the object and position information of the object, and determine whether the object is a preset object triggering vehicle braking based on the feature parameter; the camera 22 is configured to scan the object in front of the vehicle, and determine whether the object is the preset object triggering vehicle braking; and the processor 23 is configured to, when the object is the preset object and the position information of the object meets a preset condition, control vehicle braking based on a driving parameter of the vehicle.

[0052] The radar 21 can be a 4D millimeter wave radar or the like positioning device; the camera 22 can be a front-view main camera, a front-view narrow-angle camera, a front-view wide-angle camera or the like video input device. The vehicle control system 20 can be applied to a vehicle.

[0053] FIG. 3 is a flowchart of a vehicle control method according to some embodiments. As shown in FIG. 3, the vehicle control method includes the following steps S201 to S203.

[0054] S201, scanning an object in front of the vehicle within a lane line by a four-dimensional millimeter wave radar of the vehicle, and extracting a feature parameter of the object and position information of the object.

[0055] Here, the feature parameter includes at least one of a radar cross section (RCS) or a size of the object (which can also be referred to as contour information). The position information includes a height of the object from a road surface and a width of the object from a lane line.

[0056] In some embodiments, the 4D millimeter wave radar of the vehicle can scan the object in front of the vehicle to obtain point cloud information of the object in front of the vehicle within the lane line. The point cloud information can be a set of point data of the appearance surface of the object in front of the vehicle. The lane line is the lane line where the vehicle is located.

[0057] Further, the 4D millimeter wave radar can perform filtering processing on the point cloud information of the object in front of the vehicle to remove clutter in the point cloud information, to obtain filtered point cloud information. In some embodiments, according to the filtered point cloud information, the 4D millimeter wave radar can extract the RCS, size of the object in front of the vehicle and position information of the object. The size can include the length and width of the object.

[0058] According to the filtered point cloud information, first, the 4D millimeter wave radar can perform a first round of feature extraction to extract the size of the object in front of the vehicle, and then the 4D millimeter wave radar can perform a second round of feature extraction to extract the RCS of the object in front of the vehicle.

[0059] In some embodiments, the object in front of the vehicle can be a four-wheeled vehicle, a two-wheeled vehicle, an adult, a child, a special-shaped object, a railing and a road sign, etc.

[0060] S202, determine whether the object is a preset object triggering vehicle braking based on the feature parameter.

[0061] In some embodiments, based on the RCS and size of the object in front of the vehicle, the 4D millimeter wave radar can determine whether the RCS of the object in front of the vehicle is within the preset RCS interval corresponding to the preset object, and whether the size of the object in front of the vehicle is within the preset size interval corresponding to the preset object. In the case that the RCS of an object meets the preset RCS interval corresponding to the preset object and the size meets the preset size interval corresponding to the preset object, the 4D millimeter wave radar can determine that the object is a preset object. In the case that at least one of the following conditions is met: the RCS of an object does not meet the preset RCS interval corresponding to the preset object, or the size does not meet the preset size interval corresponding to the preset object, the 4D millimeter wave radar can determine that the object is not a preset object.

[0062] It should be noted that the RCS and size of different kinds of objects are usually different, so the kind of an object can be identified according to the RCS and size of the object. Some kinds of objects do not need to be braked, such as railings and road signs, etc. These objects usually do not cause traffic accidents. Some kinds of objects need to be braked, such as four-wheeled vehicles, two-wheeled vehicles, adults and children, etc. If these objects are not braked when they are identified, traffic accidents usually occur.

[0063] Some embodiments of the present disclosure can determine that an object is a preset object when the RCS and size of the object meet preset thresholds at the same time. The RCS and size meeting the preset thresholds at the same time indicates that the accuracy of object identification is high, thereby achieving identification of the object in front of the vehicle by the 4D millimeter wave radar while improving the accuracy of identifying the object in front of the vehicle.

[0064] In some embodiments, the preset object can be a four-wheeled vehicle, a two-wheeled vehicle, an adult, a child, etc. which is an object in front of the vehicle that needs to be braked.

[0065] S203, if the object is a preset object and the position information of the object meets a preset condition, control the vehicle to brake based on a driving parameter of the vehicle.

[0066] Here, the driving parameter includes at least one of the distance between the object and the vehicle or the driving speed of the vehicle. The preset condition includes that the height of the object from the road surface is less than or equal to a preset height, and the width of the object from the lane line is less than or equal to a preset width.

[0067] In some embodiments, during the driving of the vehicle, the speed sensor of the vehicle can collect the driving speed of the vehicle, and the 4D millimeter wave radar can collect the distance between the object in front of the vehicle and the vehicle.

[0068] When the 4D millimeter wave radar detects that the object is the preset object and the position information of the object meets the preset condition, the processor of the vehicle can determine the brake pedal opening degree and the brake duration based on the distance between the object and the vehicle and the driving speed of the vehicle. Further, the processor of the vehicle can control the vehicle to brake based on the brake pedal opening degree and the brake duration. The smaller the distance between the object and the vehicle and the greater the driving speed of the vehicle, the greater the determined brake pedal opening degree and the longer the brake duration.

[0069] In some embodiments, the preset height can be any reasonable value such as 1.7m or 1.8m, and the preset width can be any reasonable value such as 1.9m or 2.0m.

[0070] It should be noted that, in general, the height of the vehicle is any value in [1.4m, 1.6m], and the width of the vehicle is any value in [1.6m, 1.8m]. Therefore, the preset height needs to be greater than the height of the vehicle, and the preset width needs to be greater than the width of the vehicle, so as to ensure that the vehicle can drive through the lane line without colliding with obstacles.

[0071] In addition to controlling the vehicle to brake according to whether the object is the preset object and whether the position information of the object meets the preset condition, the vehicle can also be controlled to brake according to the risk coefficient of the object.

[0072] FIG. 4 is a flowchart of a vehicle control method according to some embodiments. As shown in FIG. 4, the method further includes step S301 and step S302 or step S301 and step S303.

[0073] S301, obtain the respective risk coefficients of the preset objects.

[0074] In some embodiments, the processor of the vehicle can obtain the respective risk coefficients of the preset objects. The risk coefficient is the danger degree of the preset object, and the higher the danger degree of the preset object, the greater the risk coefficient of the preset object.

[0075] In some embodiments, in general, adults and children have a high danger degree, so the risk coefficients of adults and children are large. Two-wheeled vehicles and three-wheeled vehicles have a medium danger degree, so the risk coefficients of two-wheeled vehicles and three-wheeled vehicles are medium. Four-wheeled vehicles have a low danger degree, so the risk coefficient of the four-wheeled vehicle is small.

[0076] S302, if the object is the preset object, the position information of the object does not satisfy the preset condition, and the risk coefficient corresponding to the object is less than or equal to the preset risk coefficient, the vehicle is controlled to turn based on the driving parameter until the vehicle passes the object within the lane line.

[0077] In some embodiments, if the object is the preset object, the position information of the object does not satisfy the preset condition, and the risk coefficient corresponding to the object is less than or equal to the preset risk coefficient, the processor of the vehicle can control the vehicle to turn based on the driving parameter until the vehicle passes the object within the lane line. The position information of the object not satisfying the preset condition means that the vehicle can pass the drivable area within the lane line without colliding with the obstacle.

[0078] It should be noted that when the risk coefficient corresponding to the obstacle is small, the vehicle can be controlled to turn to pass the obstacle. Because even if the accuracy of controlling the vehicle to turn is low, the vehicle will not collide with the obstacle, and a serious collision accident will not occur.

[0079] S303, if the object is the preset object, the position information of the object does not satisfy the preset condition, and the risk coefficient corresponding to the object is greater than the preset risk coefficient, the vehicle is controlled to brake based on the driving parameter.

[0080] In some embodiments, if the object is the preset object, the position information of the object does not satisfy the preset condition, and the risk coefficient corresponding to the object is greater than the preset risk coefficient, the processor of the vehicle can control the vehicle to brake based on the driving parameter.

[0081] It should be noted that when the risk coefficient corresponding to the obstacle is large, the vehicle cannot be controlled to turn to pass the obstacle, and the vehicle needs to be controlled to brake. Because if the accuracy of controlling the vehicle to turn is low, a serious collision accident may occur when the vehicle collides with an adult or a child.

[0082] Some embodiments of the present disclosure can determine whether to pass the obstacle or brake according to the risk coefficient of the obstacle when the vehicle can pass the drivable area within the lane line without colliding with the obstacle. Thus, directly controlling the vehicle to brake to avoid a serious collision accident and to avoid affecting the user experience due to frequent braking of the vehicle.

[0083] As an implementation manner, the step of "controlling the vehicle to brake based on the driving parameter of the vehicle" includes: controlling the vehicle to brake N times based on the driving parameter until the vehicle stops at the target position.

[0084] Here, the target position is a position separated from the object by a preset distance; and N is an integer greater than 0.

[0085] In some embodiments, a preset distance can be set in the processor of the vehicle. Further, the processor of the vehicle can obtain the target position by subtracting the preset distance from the distance between the object and the vehicle. Further, based on the distance between the object and the vehicle and the driving speed of the vehicle, the processor of the vehicle can control the vehicle to brake N times until the vehicle stops at the target position.

[0086] In some embodiments, the preset distance can be 0.5 m, 1 m, or 1.5 m, or any reasonable value.

[0087] As an implementation manner, the step of “controlling the vehicle to brake N times based on the driving parameter” includes: determining a braking parameter corresponding to each braking in the N times of braking based on the driving parameter; and controlling the vehicle to brake N times based on the braking parameter corresponding to each braking in the N times of braking. Here, the braking parameter includes at least one of the brake pedal opening or the braking duration.

[0088] In some embodiments, based on the distance between the object and the vehicle and the driving speed of the vehicle, the processor of the vehicle can determine the brake pedal opening and the braking duration corresponding to the first braking. The smaller the distance between the object and the vehicle, and the greater the driving speed of the vehicle, the greater the brake pedal opening and the longer the braking duration corresponding to the first braking.

[0089] Further, the processor of the vehicle can control the vehicle to brake the first time based on the brake pedal opening and the braking duration corresponding to the first braking, and determine whether the vehicle stops at or before the target position when the first braking ends. If the vehicle does not stop at or before the target position, the processor of the vehicle can obtain the distance between the object and the vehicle and the driving speed of the vehicle. Further, the processor of the vehicle can determine the brake pedal opening and the braking duration corresponding to the second braking based on the distance between the object and the vehicle and the driving speed of the vehicle, to control the vehicle to brake the second time based on the brake pedal opening and the braking duration corresponding to the second braking. If the vehicle stops at or before the target position, the second braking is not performed. In this way, until the vehicle stops at or before the target position. With the increase of the number of braking, the brake pedal opening and the braking duration increase.

[0090] Some embodiments of the present disclosure can control the vehicle to brake multiple times based on different braking parameters when braking is needed, which can avoid the sudden braking causing the driver to feel the jerk of emergency braking, thereby improving the driving experience.

[0091] FIG. 5 is a flowchart of a vehicle control method according to some embodiments. As shown in FIG. 5, the method in step S202 further includes steps S401-S403.

[0092] S401, determine whether the characteristic parameter of the object meets the preset threshold value corresponding to each preset object, if yes, execute S402; if no, execute S403.

[0093] Here, the preset threshold value corresponding to each preset object can be obtained by big data training. The preset threshold value includes a preset RCS interval and a preset size interval. The preset size interval includes a preset length interval and a preset width interval.

[0094] In some embodiments, the processor of the vehicle can obtain the RCS and size of a large number of objects from a database, perform big data training on the RCS and size of the large number of objects, and obtain the preset RCS interval and the preset size interval of each object, including the preset RCS interval and the preset size interval corresponding to each preset object. Further, the processor of the vehicle can determine whether the characteristic parameter of the object meets the preset threshold value corresponding to each preset object.

[0095] It should be noted that the preset RCS interval and the preset size interval need to be trained by artificial intelligence (AI) big data, and only the preset RCS interval and the preset size interval trained by big data are the final accurate values.

[0096] In some embodiments, the processor of the vehicle can obtain the RCS and size of a large number of adults from a database, perform big data training on the RCS of the large number of adults, and obtain the preset RCS interval corresponding to adults, and perform big data training on the size of the large number of adults, and obtain the preset size interval corresponding to adults. The preset RCS interval corresponding to adults can be [-5dBsm, 5dBsm], the preset length interval corresponding to adults can be [1.5m, 2m], and the preset width interval corresponding to adults can be [0.4m, 0.6m].

[0097] S402, if the characteristic parameter of the object meets the preset threshold value corresponding to each preset object, determine that the object is a preset object.

[0098] In some embodiments, if the characteristic parameter of an object is within the preset threshold value corresponding to each preset object, the 4D millimeter wave radar can determine that the object is a preset object.

[0099] In some embodiments, assuming that the RCS of an object is 0dBsm, the length is 1.7m, and the width is 0.5m, the RCS of the object is within [-5dBsm, 5dBsm], the length of the object is within [1.5m, 2m], and the width of the object is within [0.4m, 0.6m], then the object can be determined to be a preset object.

[0100] Some embodiments of the present disclosure can pre-train the RCS range and size range of each object through big data, and then determine whether an object is an object requiring vehicle braking by whether the RCS and size of the object are respectively within the RCS range and size range, thereby improving the accuracy of object recognition.

[0101] S403, if at least one of the characteristic parameters of the object is not within the preset threshold corresponding to the preset object, it is determined that the object is not the preset object.

[0102] If at least one of the characteristic parameters of the object is not within the preset threshold corresponding to the preset object, the 4D millimeter wave radar can determine that the object is not the preset object.

[0103] FIG. 6 is a flowchart of a vehicle control method according to some embodiments. As shown in FIG. 6, before step S203, the method further includes step S501 and step S502 or step S501 and step S503.

[0104] S501, obtaining a first confidence and a second confidence.

[0105] Here, the first confidence is the confidence of the object scanned by the camera, and the second confidence is the confidence of the object scanned by the 4D millimeter wave radar. The confidence can be the definition or completeness. The confidence of the object scanned by the camera can be the confidence of the image information obtained by the camera scanning the object in front. The confidence of the object scanned by the 4D millimeter wave radar can be the confidence of the point cloud information obtained by the 4D millimeter wave radar scanning the object in front.

[0106] In some embodiments, the 4D millimeter wave radar of the vehicle scans the object in front of the vehicle to obtain point cloud information of the object in front of the vehicle, and the camera of the vehicle scans the object in front of the vehicle to obtain image information of the object in front of the vehicle. Further, the camera of the vehicle can convert the image information into a coordinate system corresponding to the point cloud information to obtain a confidence corresponding to the image information (i.e., the second confidence) and a confidence corresponding to the point cloud information (i.e., the first confidence).

[0107] It should be noted that the detection distance of the camera will change with the change of the environment. In the daytime and in the environment with a wide field of view, the 4D millimeter wave radar and the camera can sometimes scan the object in front of the vehicle at the same time. However, due to the influence of the characteristics of the camera itself, the confidence of the object scanned by the camera is usually different, which is affected by the distance between the object in front of the vehicle and the vehicle and the environmental conditions. When the object in front of the vehicle is close and the environmental conditions are good, the confidence of the camera is high, which is usually higher than the confidence of the 4D millimeter wave radar. When the object in front of the vehicle is far away and the environmental conditions are poor, the confidence of the camera is low, which is usually lower than the confidence of the 4D millimeter wave radar. The confidence of the 4D millimeter wave radar is usually not affected by the distance between the object in front of the vehicle and the vehicle and the environmental conditions.

[0108] S502, in a case where the first confidence is greater than or equal to the second confidence, determining, by the camera, whether the object is the preset object.

[0109] In some embodiments, in a case where the first confidence is greater than or equal to the second confidence, the camera can compare the image information of an object with historical image information of a plurality of objects stored in a database, obtain the similarity between the image information of the object and each historical image information, and in a case where the similarity between the image information of the object and certain historical image information is greater than a preset similarity, determine whether the object corresponding to the historical image information is the preset object. If the object corresponding to the historical image information is the preset object, it is determined that the object is the preset object. If the object corresponding to the historical image information is not the preset object, it is determined that the object is not the preset object.

[0110] S503, in a case where the first confidence is less than the second confidence, determining, by the 4D millimeter wave radar, whether the object is the preset object.

[0111] It should be noted that the higher the confidence of the object scanned by the sensor, the higher the definition of the object scanned by the sensor, and the higher the accuracy of the object identified by the sensor.

[0112] Some embodiments of the present disclosure can simultaneously scan the object by the 4D millimeter wave radar and the camera, and select the sensor with higher confidence to identify the object, thereby realizing the fusion of the 4D millimeter wave radar and the camera and improving the accuracy of identifying the object.

[0113] In some embodiments, FIG. 7 is a flowchart of vehicle control by 4D millimeter wave radar and camera fusion according to some embodiments. As shown in FIG. 7, the method comprises:

[0114] S601, scanning the object by the 4D millimeter wave radar to obtain the point cloud information of the object, and simultaneously scanning the object by the camera to obtain the image information of the object.

[0115] S602, fuse the point cloud information of the object and the image information of the object (i.e., convert the image information of the object into the coordinate system corresponding to the point cloud information of the object), and calculate the confidence of the object in the 4D millimeter wave radar scanning and the confidence of the object in the camera scanning.

[0116] S603, select the sensor with higher confidence from the 4D millimeter wave radar and the camera, and identify whether the object is an object that needs to be braked.

[0117] S604, when it is identified that the object is an object that needs to be braked, calculate the braking parameters corresponding to the first braking based on the distance between the vehicle and the object and the driving speed of the vehicle.

[0118] S605, perform the first braking based on the braking parameters corresponding to the first braking.

[0119] S606, when the first braking ends, determine whether the vehicle stops before or while driving to the target position, if so, perform S607, if not, perform S608.

[0120] S607, stop braking.

[0121] If the vehicle stops before or while driving to the target position, stop braking.

[0122] S608, calculate the braking parameters corresponding to the second braking based on the distance between the vehicle and the object and the driving speed of the vehicle, and perform the second braking based on the braking parameters corresponding to the second braking.

[0123] If the vehicle does not stop before or while driving to the target position, calculate the braking parameters corresponding to the second braking based on the distance between the vehicle and the object and the driving speed of the vehicle, and perform the second braking based on the braking parameters corresponding to the second braking.

[0124] S609, when the second braking ends, determine whether the vehicle stops before or while driving to the target position.

[0125] In this way, until the vehicle stops before or while driving to the target position.

[0126] The above describes the solutions provided by some embodiments of the present disclosure from the method aspect. To implement the above functions, the vehicle control device or the electronic device comprises hardware structures and / or software modules corresponding to each function. Those skilled in the art should easily realize that, in combination with the units and algorithm steps of each example described in the embodiments disclosed herein, the present disclosure can be implemented in the form of hardware or a combination of hardware and computer software. Whether a certain function is implemented in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present disclosure.

[0127] Some embodiments of the present disclosure can divide the functional modules of the vehicle control device or the electronic device according to the above method. For example, the vehicle control device or the electronic device can comprise functional modules corresponding to each function division, or two or more functions can be integrated into one processing module. The above integrated module can be implemented in the form of hardware or software functional module. It should be noted that the division of modules in some embodiments of the present disclosure is illustrative, and is only a logical function division. Actual implementation can have another division manner.

[0128] FIG. 8 is a block diagram of a vehicle control device according to some embodiments. Referring to FIG. 8, the vehicle control device 110 comprises a processing module 1101 and a determination module 1102.

[0129] The processing module 1101 is configured to scan an object in front of a vehicle located in a lane line by a four-dimensional millimeter wave radar of the vehicle, and extract a feature parameter of the object and position information of the object; the feature parameter comprises at least one of a radar cross section (RCS) or a size; and the position information comprises a height of the object from a road surface and a width of the object from the lane line.

[0130] The determination module 1102 is configured to determine whether the object is a preset object triggering vehicle braking based on the feature parameter.

[0131] The processing module 1101 is further configured to control vehicle braking based on a driving parameter of the vehicle if the object is the preset object and the position information of the object satisfies a preset condition; the driving parameter comprises at least one of a distance between the object and the vehicle or a driving speed of the vehicle; and the preset condition comprises that the height of the object from the road surface is less than or equal to a preset height, and the width of the object from the lane line is less than or equal to a preset width.

[0132] In some embodiments, the vehicle control apparatus 110 further comprises a transmission module 1103; the transmission module 1103 is configured to obtain a risk coefficient corresponding to each of the preset objects; the processing module 1101 is further configured to, if the object is a preset object, the position information of the object does not satisfy the preset condition, and the risk coefficient corresponding to the object is less than or equal to a preset risk coefficient, control the vehicle to turn based on the driving parameter until the vehicle drives around the object within the lane line; or the processing module 1101 is further configured to, if the object is a preset object, the position information of the object does not satisfy the preset condition, and the risk coefficient corresponding to the object is greater than the preset risk coefficient, control the vehicle to brake based on the driving parameter.

[0133] In some embodiments, the determination module 1102 is further configured to determine whether the characteristic parameter of the object satisfies a preset threshold corresponding to each of the preset objects; the determination module 1102 is further configured to determine that the object is a preset object if the characteristic parameter of the object satisfies the preset threshold corresponding to each of the preset objects; and the determination module 1102 is further configured to determine that the object is not a preset object if at least one of the characteristic parameters of the object does not satisfy the preset threshold corresponding to the preset object.

[0134] In some embodiments, the preset threshold corresponding to each of the preset objects is obtained through big data training.

[0135] In some embodiments, the processing module 1101 is further configured to control the vehicle to brake N times based on the driving parameter until the vehicle stops at a target position; the target position is a position separated from the object by a preset distance; and N is an integer greater than 0.

[0136] In some embodiments, the determination module 1102 is further configured to determine a braking parameter corresponding to each of the N times of braking based on the driving parameter; the braking parameter comprises at least one of a brake pedal opening or a braking time length; and the processing module 1101 is further configured to control the vehicle to brake N times based on the braking parameter corresponding to each of the N times of braking.

[0137] In some embodiments, the transmission module 1103 is further configured to obtain a first confidence and a second confidence; the first confidence is a confidence of the object scanned by the camera; and the second confidence is a confidence of the object scanned by the four-dimensional millimeter wave radar; the determination module 1102 is further configured to determine whether the object is a preset object through the camera if the first confidence is greater than or equal to the second confidence; and the determination module 1102 is further configured to determine whether the object is a preset object through the four-dimensional millimeter wave radar if the first confidence is less than the second confidence.

[0138] FIG. 9 is a block diagram of an electronic device according to some embodiments. As shown in FIG. 9, the electronic device 130 comprises, but is not limited to, a processor 1301 and a memory 1302.

[0139] Here, the memory 1302 is configured to store executable instructions of the processor 1301. It can be understood that the processor 1301 is configured to execute the instructions to implement the vehicle control method in the above embodiments.

[0140] It should be noted that those skilled in the art can understand that the electronic device structure shown in FIG. 9 does not constitute a limitation on the electronic device, and the electronic device can include more or fewer components than those shown in FIG. 9, or combine certain components, or different component arrangements.

[0141] The processor 1301 is the control center of the electronic device, which connects all parts of the electronic device through various interfaces and lines, executes software programs and / or modules stored in the memory 1302, and calls data stored in the memory 1302, to perform various functions of the electronic device and process data, thereby overall monitoring the electronic device. The processor 1301 can include one or more processing modules. In some embodiments, the processor 1301 can integrate an application processor and a modem processor, where the application processor mainly processes the operating system, user interface, and application programs, etc., and the modem processor mainly processes wireless communication. It can be understood that the above-mentioned modem processor can also not be integrated into the processor 1301.

[0142] The memory 1302 can be used to store software programs and various data. The memory 1302 can mainly include a program storage area and a data storage area, where the program storage area can store operating systems, application programs required by at least one functional module (such as acquisition unit, determination module, processing unit, etc.), etc. In addition, the memory 1302 can include a high-speed random access memory, and can also include a non-volatile memory, for example, at least one magnetic disk storage device, flash memory device, or other volatile solid-state memory device.

[0143] In some embodiments, a computer readable storage medium including instructions executable by the processor 1301 of the electronic device 130 to implement the vehicle control method in the above embodiments is also provided.

[0144] In actual implementation, the functions of the processing module 1101, the determination module 1102, and the transmission module 1103 in FIG. 8 can all be implemented by the processor 1301 in FIG. 9 calling the computer program stored in the memory 1302. The execution process can refer to the description of the vehicle control method part in the above embodiments, which will not be described here.

[0145] In some embodiments, the computer readable storage medium can be a non-transitory computer readable storage medium, for example, the non-transitory computer readable storage medium can be a read-only memory (ROM), a random access memory (RAM), a Compact Disc Read-Only Memory (CD-ROM), a magnetic tape, a floppy disk, and an optical data storage device, etc.

[0146] In some embodiments, as shown in FIG. 10, some embodiments of the present disclosure further provide a vehicle 1 comprising a vehicle control device 110, an electronic device 130, and a computer readable storage medium, which can complete the vehicle control method in the above embodiments through the vehicle control device.

[0147] In some embodiments, some embodiments of the present disclosure further provide a computer program product comprising one or more instructions executable by the processor 1301 of the electronic device to complete the vehicle control method in the above embodiments.

[0148] It should be noted that the instructions in the above computer readable storage medium or the one or more instructions in the computer program product are executed by the processor of the electronic device to realize each process of the above vehicle control method embodiments, and can achieve the same technical effects as the above vehicle control method. To avoid repetition, it will not be described here.

[0149] Through the description of the above embodiments, those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above division of each functional module is taken as an example for illustration, and in actual application, the above functions can be completed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete the full classification part or part of the functions described above.

[0150] In several embodiments provided by the present disclosure, it should be understood that the disclosed apparatus and method can be implemented by other ways. For example, the above-described apparatus embodiments are only schematic, for example, the division of the modules or units is only a logical function division, and there can be another division way in actual implementation, for example, a plurality of units or components can be combined or integrated into another device, or some features can be ignored or not executed. In addition, the displayed or discussed mutual coupling or direct coupling or communication connection can be indirect coupling or communication connection through some interfaces, devices or units, and can be electrical, mechanical or other forms.

[0151] The units described as separate components may or may not be physically separate, and the components displayed as units may be a physical unit or multiple physical units, that is, may be located in one place, or also can be distributed to multiple different places. Part or all of the classified units can be selected according to actual needs to achieve the purpose of the embodiment of the present embodiment.

[0152] In addition, each functional unit in various embodiments of the present disclosure can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0153] If the integrated unit is realized in the form of a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on such understanding, the technical solutions of some embodiments of the present disclosure or the part of the related technology that contributes essentially or the whole classification or part of the technical solutions can be embodied in the form of a software product, which is stored in a storage medium and includes a plurality of instructions for making a device (which can be a single-chip microcomputer, a chip, etc.) or a processor execute the whole classification or part of the steps of the method of various embodiments of the present disclosure. The foregoing storage medium includes: a U disk, a mobile hard disk, a ROM, a RAM, a magnetic disk or an optical disk and various program code storage media.

[0154] The above is only a specific embodiment of the present disclosure, but the protection scope of the present disclosure is not limited thereto, and any person skilled in the art can easily think of changes or replacements within the technical range disclosed by the present disclosure, which should be covered within the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be subject to the protection scope of the claims.

Claims

1. A vehicle control method, comprising: scanning, by a four-dimensional millimeter wave radar of a vehicle, an object in front of the vehicle within a lane line, and extracting a characteristic parameter of the object and position information of the object; wherein the characteristic parameter comprises at least one of a radar cross section (RCS) or a size of the object, and the position information comprises a height of the object from a road surface and a width of the object from the lane line; determining, based on the characteristic parameter, whether the object is a preset object triggering braking of the vehicle; if the object is the preset object and the position information of the object satisfies a preset condition, controlling, based on a driving parameter of the vehicle, the vehicle to brake; wherein the driving parameter comprises at least one of a distance between the object and the vehicle or a driving speed of the vehicle, and the preset condition comprises that the height of the object from the road surface is less than or equal to a preset height and the width of the object from the lane line is less than or equal to a preset width. 2.The method of claim 1, further comprising: obtaining a risk coefficient corresponding to each of the preset objects; if the object is the preset object, the position information of the object does not satisfy the preset condition, and the risk coefficient corresponding to the object is less than or equal to a preset risk coefficient, controlling, based on the driving parameter, the vehicle to turn until the vehicle passes the object within the lane line; if the object is the preset object, the position information of the object does not satisfy the preset condition, and the risk coefficient corresponding to the object is greater than the preset risk coefficient, controlling, based on the driving parameter, the vehicle to brake.

3. The method of claim 1, wherein, The determining, based on the characteristic parameter, whether the object is the preset object triggering braking of the vehicle comprises: if the characteristic parameter of the object satisfies a preset threshold corresponding to each of the preset objects, determining that the object is the preset object; if at least one of the characteristic parameters of the object does not satisfy the preset threshold corresponding to the preset object, determining that the object is not the preset object.

4. The method of claim 3, wherein, The preset threshold corresponding to each of the preset objects is obtained by big data training.

5. The method of claim 1, wherein, The controlling, based on the driving parameter of the vehicle, the vehicle to brake comprises: controlling, based on the driving parameter, the vehicle to brake N times until the vehicle stops at a target position; wherein the target position is a position separated from the object by a preset distance, and N is an integer greater than 0.

6. The method of claim 5, wherein, The controlling, based on the driving parameter, the vehicle to brake N times comprises: determining, based on the driving parameter, a braking parameter corresponding to each of the N times of braking; the braking parameter comprises at least one of a brake pedal opening or a braking time length; controlling, based on the braking parameter corresponding to each of the N times of braking, the vehicle to brake the N times.

7. The method of claim 1, wherein, Before the if the object is the preset object and the position information of the object satisfies a preset condition, controlling, based on a driving parameter of the vehicle, the vehicle to brake, the method further comprises: obtaining a first confidence and a second confidence; wherein the first confidence is a confidence of the object scanned by a camera; and the second confidence is a confidence of the object scanned by the four-dimensional millimeter wave radar; if the first confidence is greater than or equal to the second confidence, determining whether the object is the preset object by the camera; if the first confidence is less than the second confidence, determining whether the object is the preset object by the four-dimensional millimeter wave radar.

8. A vehicle control apparatus, comprising: a processing module configured to scan an object in front of a vehicle within a lane line by a four-dimensional millimeter wave radar of the vehicle, and extract a feature parameter of the object and position information of the object; the feature parameter comprises at least one of a radar cross section (RCS) or a size of the object; the position information comprises a height of the object from a road surface and a width of the object from the lane line; and a determination module configured to determine whether the object is a preset object triggering vehicle braking based on the feature parameter; the processing module is further configured to, if the object is the preset object and the position information of the object satisfies a preset condition, control the vehicle to brake based on a driving parameter of the vehicle; the driving parameter comprises at least one of a distance of the object from the vehicle or a driving speed of the vehicle; and the preset condition comprises that the height of the object from the road surface is less than or equal to a preset height, and the width of the object from the lane line is less than or equal to a preset width.

9. An electronic device comprising: a processor; and a memory for storing processor-executable instructions; wherein the processor is configured to execute the instructions to implement the method according to any one of claims 1 to 7.

10. A computer readable storage medium, wherein, When the computer-executable instructions stored in the computer-readable storage medium are executed by the processor of the electronic device, the electronic device can perform the method according to any one of claims 1 to 7.

11. A vehicle comprising the apparatus according to claim 8, the vehicle being configured to implement the method according to any one of claims 1 to 7.

Images