Car following control method, computer program product and electronic equipment

Abstract

The invention provides a car following control method, a computer program product and electronic equipment, according to the car following control method provided by the invention, target related information of a current car following target of a car can be acquired; if the current car-following target of the car and the historical car-following target of the car belong to the same object and the preset comfortable braking condition of the car is met, smoothing processing can be carried out on the original longitudinal distance between the current car-following target and the car in the target related information; the target longitudinal distance between the current car following target and the car is obtained.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicle control, and particularly relates to a following vehicle control method, a computer program product and an electronic device. BACKGROUND

[0002] With the development of science and technology, the auxiliary driving function of a vehicle is increasingly rich, which constantly promotes the vehicle to be intelligent and comfortable. For example, the auxiliary driving function of the vehicle can combine the surrounding environment information of the vehicle and the running condition information of the vehicle itself, filter out a following target existing on a road ahead of the vehicle, and avoid a collision between the vehicle and the following target by automatically adjusting the driving speed of the vehicle according to the longitudinal distance between the vehicle and the following target, so as to improve the driving safety and convenience. However, due to the influence of sensor noise, target detection error, target fusion processing or other related factors, the detected longitudinal distance between the vehicle and the following target may fluctuate, which easily affects the stability of the braking process of the vehicle, and further affects the experience of the driver and passenger. SUMMARY

[0003] Therefore, the present application provides a following vehicle control method, a computer program product and an electronic device, which can improve the smoothness of the longitudinal distance between the vehicle and the following target used in the following vehicle control, improve the stability of the braking process of the vehicle, and improve the experience of the driver and passenger.

[0004] In one aspect, the present application provides a following vehicle control method, which comprises the following steps.

[0005] obtaining target related information of a current following target of the vehicle;

[0006] if the current following target of the vehicle and a historical following target of the vehicle belong to the same object, and a preset comfortable braking condition of the vehicle is met, performing smoothing processing on an original longitudinal distance between the current following target in the target related information and the vehicle, to obtain a target longitudinal distance between the current following target and the vehicle.

[0007] In another aspect, the present application further provides a computer program product, which stores a computer readable program, and the computer readable program is executed by a controller to realize the steps of the above following vehicle control method.

[0008] In another aspect, the present application further provides an electronic device, which comprises a processor and a memory; wherein the memory stores a computer readable instruction, and the computer readable instruction is adapted to be loaded and executed by the processor to realize the steps of the above following vehicle control method.

[0009] According to the vehicle following control method provided in the present application, target related information of a current vehicle following target of the vehicle can be acquired; if the current vehicle following target of the vehicle and a historical vehicle following target of the vehicle belong to the same object, and a preset comfortable braking condition of the vehicle is met, then the original longitudinal distance between the current vehicle following target in the target related information and the vehicle can be smoothed, so that the vehicle can be controlled to brake according to the target longitudinal distance between the current vehicle following target and the vehicle after the smoothing, which is beneficial to improving the stability of the vehicle braking process and improving the user experience.

[0010] It should be understood that the content described in the summary section is not intended to limit the key or important features of the embodiments of the present application, nor to limit the scope of the present application. Other features of the present application will become apparent through the following description. BRIEF DESCRIPTION OF DRAWINGS

[0011] Figure 1 A flowchart of a vehicle following control method provided in an embodiment of the present application;

[0012] Figure 2 A schematic diagram of a vehicle driving scene provided in an embodiment of the present application;

[0013] Figure 3 A structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0014] In order to make the purposes, technical solutions and advantages of the present application clearer, the technical solutions of the present application will be described clearly and completely below in combination with the embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only some of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of protection of the present application.

[0015] In the description of one or more embodiments of the present application, the term “comprising” and its similar terms shall be understood as open inclusion, i.e. “including but not limited to”. The term “based on” shall be understood as “at least partially based on”. The term “one embodiment” or “the embodiment” shall be understood as “at least one embodiment”. The terms “first”, “second”, etc. can refer to different or same objects.

[0016] The term "at least one" shall be understood as including one and more than one, for example, "at least one of A and B" can cover the cases of "A only," "B only," and "A and B." Further, it is to be understood that the terms "comprising," "including," and "having" can be used interchangeably.

[0017] In the description of one or more embodiments of the application, the term "and / or" should be understood to include one and more than one, for example, "A and / or B" can cover the cases of "A only," "B only," and "A and B." Further, it can include other explicit and implicit definitions, which are not specifically limited.

[0018] Currently, part of the auxiliary driving function of the automobile can combine the existing car-following target in front of the automobile to automatically control the driving of the automobile, thereby improving the driving safety and convenience. However, due to the influence of sensor noise, target detection error, target fusion processing or other related factors, the longitudinal distance between the automobile and the car-following target detected in a short time can fluctuate greatly, thereby when the longitudinal distance between the automobile and the car-following target is combined to brake the automobile, the problem of insufficient braking stability is easy to exist, which affects the experience of the driver and passenger.

[0019] For example, if the difference between the radar target and the visual target detected for a specific object in a certain target detection period is large, a single target among the radar target and the visual target can be taken as the car-following target of the automobile, and the longitudinal distance between the detected car-following target and the automobile is combined to control the braking of the automobile. If the difference between the radar target and the visual target detected for the specific object in the next target detection period is small, the fusion target of the specific object can be generated combining the radar target and the visual target, and the longitudinal distance between the calculated fusion target and the automobile is used to control the braking of the automobile. In the above case and similar cases, although the object that the automobile needs to follow does not change, the longitudinal distance between the automobile and the car-following target obtained in a short time can fluctuate greatly, thereby easily affecting the stability of the braking process of the automobile, and the experience of the driver and passenger at the automobile.

[0020] Based on this, the application provides a following vehicle control method, which can obtain target related information of a current following target of a host vehicle. If the current following target of the host vehicle and a historical following target of the host vehicle belong to the same object, and a preset comfortable braking condition of the host vehicle is met, the original longitudinal distance between the current following target in the target related information and the host vehicle is smoothed, so that the host vehicle can be controlled according to the target longitudinal distance between the current following target and the host vehicle after smoothing, which is beneficial to improve the stability of the vehicle braking process and improve the user experience.

[0021] Please refer to Figure 1 A flowchart of a following vehicle control method provided by the embodiment of the application is shown in FIG. 1. From the perspective of the program, the execution subject of the flowchart can be a program loaded on a radar device, an image acquisition device, a vehicle control device or a vehicle. Alternatively, the execution subject of the flowchart can be the radar device, the image acquisition device, the vehicle control device or the vehicle, or other devices capable of communicating with the radar device, the image acquisition device, the vehicle control device or the vehicle, which is not limited herein.

[0022] The following will be described in detail with reference to the flowchart shown in FIG. 1. The following vehicle control method can specifically include the following steps. Figure 1

[0023] In step S102, target related information of a current following target of a host vehicle is obtained.

[0024] In the embodiment of the application, the current following target of the host vehicle can be an object that needs to be kept at a certain distance and safely followed by the host vehicle when the host vehicle is controlled by a specific auxiliary driving function. The specific auxiliary driving function can include but is not limited to adaptive cruise control (ACC) and extended functions, such as adaptive cruise control function, navigate on autopilot (NOA). The type of the current following target can be various, such as motor vehicle, non-motor vehicle or other types of traffic participants, which is not limited herein.

[0025] In the embodiment of the application, the type of the target related information of the current following target of the host vehicle that can be obtained can also be various, so as to control the host vehicle in combination with the target related information of the current following target. For example, the target related information of the current following target can include but is not limited to at least one of target type information, target unique identification information, original longitudinal distance from the host vehicle, target running condition information and target survival time information, which is not limited herein.

[0026] ​In step S104, if the current following target of the host vehicle and the historical following target of the host vehicle belong to the same object, and the preset comfortable braking condition of the host vehicle is met, then the original longitudinal distance between the current following target in the target related information and the host vehicle is smoothed to obtain a target longitudinal distance between the current following target and the host vehicle.

[0027] In the embodiments of the present application, the target detection and tracking processing can be performed periodically, and the latest following target of the host vehicle can be selected in each target detection and tracking cycle to ensure the real-time, accuracy and rationality of the following target of the host vehicle.

[0028] If the current following target of the host vehicle and the historical following target of the host vehicle belong to the same object, and the longitudinal distance between the host vehicle and the object fluctuates greatly in a short time, the preset comfortable braking condition of the host vehicle can be met. By smoothing the original longitudinal distance between the current following target in the target related information and the host vehicle, the difference between the target longitudinal distance obtained after the smoothing and the historical longitudinal distance between the historical following target and the host vehicle can be less than the difference between the original longitudinal distance and the historical longitudinal distance, so as to slow down the fluctuation of the longitudinal distance between the host vehicle and the object in a short time when the host vehicle follows the object. When the host vehicle is controlled by braking in combination with the target longitudinal distance, the stability of the vehicle braking process can be improved, and the user experience can be improved.

[0029] In the embodiments of the present application, the current following target of the host vehicle and the historical following target of the host vehicle belong to the same object, which means that the current following target and the historical following target are obtained by target detection and tracking processing of the same object at different times, and details are not repeated here.

[0030] Figure 1 The method in the embodiments of the present application can obtain target related information of the current following target of the host vehicle. If the current following target of the host vehicle and the historical following target of the host vehicle belong to the same object, and the preset comfortable braking condition of the host vehicle is met, then the original longitudinal distance between the current following target in the target related information and the host vehicle can be smoothed, so as to control the host vehicle by braking according to the target longitudinal distance between the current following target and the host vehicle obtained after the smoothing, which is beneficial to improve the stability of the vehicle braking process and improve the user experience.

[0031] In some possible embodiments, the preset comfortable braking condition can at least include that a preset condition of braking the host vehicle based on the current following target is met, and the difference between the historical longitudinal distance between the historical following target and the host vehicle and the original longitudinal distance reaches a first threshold value.

[0032] In this embodiment of the application, during the process of following the vehicle in conjunction with the current following target, braking control of the vehicle is typically only required when the preset conditions for braking the vehicle based on the current following target are met, taking into account both the current following target's operating status and the vehicle's operating status. This may lead to the possibility of exploiting... Figure 1 The following control method provided in the software controls the vehicle's need for comfort braking. However, if the preset conditions for braking the vehicle based on the current following target are not met, there is usually no need to control the vehicle to brake, and therefore the system will not operate. Figure 1 The following control method provided in the text is used to control the vehicle to perform comfort braking. Therefore, the preset comfort braking conditions may include the satisfaction of preset conditions for braking the vehicle based on the current following target, so as to implement braking when reasonable and necessary. Figure 1 The following vehicle control method provided in the text.

[0033] In practical applications, there can be one or more preset conditions for braking the vehicle based on the current following target. For example, the longitudinal distance between the current following target and the vehicle may be within a specified range, and / or the vehicle's speed may reach a specified speed. The specified range may be from several meters to hundreds of meters, and the specified speed may be from several kilometers to hundreds of kilometers per hour. It is understood that the preset conditions can be set according to actual needs and are not specifically limited thereto.

[0034] In this embodiment, typically, when the vehicle's historical following target and current following target belong to the same object, and the difference between the historical longitudinal distance between the historical following target and the vehicle and the original longitudinal distance between the current following target and the vehicle reaches a first threshold, directly controlling the vehicle's braking based on the original longitudinal distance between the current following target and the vehicle could easily lead to uneven braking during the process of following the same object, thus creating a need for comfort braking. However, if the vehicle's historical following target and current following target belong to different objects, or if the difference between the historical longitudinal distance between the historical following target and the vehicle and the original longitudinal distance between the current following target and the vehicle does not reach the first threshold, then there is generally no need for comfort braking. Therefore, when the vehicle's historical following target and current following target belong to the same object, the preset comfort braking condition may further include: the difference between the historical longitudinal distance between the historical following target and the vehicle and the original longitudinal distance reaches a first threshold, to ensure... Figure 1 The rationality of implementing the following control method provided in the document. The first threshold can range from several meters to tens of meters, without specific limitation.

[0035] In practical applications, the current following target can be a following target of the vehicle selected in a latest target detection and tracking period, and the original longitudinal distance can be a distance between the current following target and the vehicle along a forward direction of the vehicle determined through target detection, tracking, fusion processing, etc. The historical following target can be a following target of the vehicle selected in a period before the latest target detection and tracking period, and the historical longitudinal distance can be a distance between the historical following target and the vehicle along the forward direction of the vehicle used when the vehicle is controlled in the period before the latest target detection and tracking period.

[0036] It can be understood that, if the longitudinal distance between the historical following target and the vehicle is not smoothed in the period before the latest target detection and tracking period, the historical longitudinal distance can be an original distance between the historical following target and the vehicle along the forward direction of the vehicle determined through target detection, tracking, fusion processing, etc.; and if the longitudinal distance between the historical following target and the vehicle is smoothed in the period before the latest target detection and tracking period, the historical longitudinal distance can be a distance obtained by smoothing the original distance, which is beneficial to guarantee the stability of the vehicle braking process.

[0037] In some possible embodiments, the preset comfortable braking condition can further include:

[0038] In the historical following control process of the vehicle, the longitudinal distance between the historical following target and the vehicle is not smoothed; and

[0039] The target types of the current following target and the historical following target are inconsistent, the current following target is in a static state, a motion speed of the current following target is less than a preset speed and a motion probability prediction value of the current following target is less than a preset probability, a difference between the historical longitudinal distance and the original longitudinal distance reaches a second threshold, and at least one of the original longitudinal distance reaching a third threshold and a vehicle speed of the vehicle reaching a fourth threshold is met; the second threshold is greater than the first threshold.

[0040] In the embodiments of the present application, when the vehicle is controlled in combination with the historical following target, it is not necessarily required to control the vehicle to perform comfortable braking, for example, when the object to which the following target of the vehicle belongs changes, the vehicle can not be controlled to perform comfortable braking, or when the fluctuation value of the longitudinal distance between the following target of the vehicle and the vehicle detected in a short time and belonging to the same object is small, the vehicle can not be controlled to perform comfortable braking. Therefore, in the historical following control process of the vehicle, there can be a case that the longitudinal distance between the historical following target and the vehicle is not smoothed.

[0041] In the embodiment of the present application, the preset comfort braking condition can further include: in the history follow-up control process of the host vehicle, the longitudinal distance between the history follow-up target (i.e. the follow-up target of the host vehicle in the last target detection and tracking period) and the host vehicle is not smoothed, at this time, the preset comfort braking condition is equivalent to the condition required to start the comfort braking function of the running vehicle in the follow-up process.

[0042] Since the longitudinal distance between the current follow-up target and the history follow-up target and the host vehicle is prone to fluctuation when the current follow-up target and the history follow-up target belong to the same object but the target types of the two are inconsistent, at this time, there is usually a comfort braking demand for the host vehicle, so that the preset comfort braking condition can further include the condition that the target types of the current follow-up target and the history follow-up target are inconsistent.

[0043] Since there can be a problem of insufficient accuracy of the original longitudinal distance between the detected current follow-up target and the host vehicle when the current follow-up target is in a stationary state, and / or is about to change from a moving state to a stationary state, and / or the longitudinal distance between the current follow-up target and the host vehicle is far, and / or the vehicle running speed of the host vehicle is large, so that there is also a comfort braking demand for the host vehicle, therefore, the preset comfort braking condition can further include at least one of the current follow-up target being in a stationary state, the motion speed of the current follow-up target being less than a preset speed and the motion probability prediction value of the current follow-up target being less than a preset probability, the original longitudinal distance reaching a third threshold value, and the vehicle running speed of the host vehicle reaching a fourth threshold value.

[0044] The motion probability prediction value of the current follow-up target can be used to reflect the probability that the current follow-up target can continue to be in a moving state. Generally, when the motion probability prediction value of the current follow-up target is less than a preset probability, and the motion speed of the current follow-up target is less than a preset speed, it can be indicated that the current follow-up target is about to change from a moving state to a stationary state. The preset probability can be a small number close to 0, for example, 0.3, 0.1, and the preset speed can be several meters to several kilometers per hour; the third threshold value can be several meters to several hundred meters, and the fourth speed can be several kilometers to several hundred kilometers per hour, which are not limited in particular.

[0045] In addition, by allowing the preset comfort braking condition to further include that the difference between the history longitudinal distance between the history follow-up target and the host vehicle and the original longitudinal distance between the current follow-up target and the host vehicle reaches a second threshold value with a value greater than the first threshold value, the comfort braking function of the running vehicle can be further improved Figure 1 The requirement required to be met when the intermediate scheme is executed is beneficial to guarantee Figure 1The execution rationality and accuracy of the middle scheme. The second threshold value can be several meters to several hundred meters, which can be set according to actual needs, and is not specifically limited.

[0046] In some feasible embodiments, the target type can include at least one of a radar target, a visual target, and a fusion target.

[0047] The radar target can be a target obtained by processing surrounding environment perception data collected by a radar device; the visual target can be a target obtained by processing surrounding environment image data collected by an image collection device; and the fusion target can be a target obtained by processing the surrounding environment perception data collected by the radar device and the surrounding environment image data collected by the image collection device.

[0048] In the embodiments of the present application, radar target detection technology, image target detection technology, target fusion technology, etc. can be used to detect the follow-up target of the vehicle in each cycle. Therefore, the current follow-up target and the historical follow-up target of the vehicle can be any one of a radar target, a visual target, and a fusion target, so that the current follow-up target of the vehicle and the historical follow-up target in the adjacent cycle can belong to different target types.

[0049] In order to facilitate understanding, Figure 2 A schematic diagram of a vehicle driving scene is provided for the embodiments of the present application, which is combined with Figure 2 The follow-up target of the vehicle is exemplified. As shown in Figure 2 The radar target 22, the visual target 23, and / or the fusion target 24 detected for the same specific object can exist in the lane of the vehicle 21, and the target 25 detected for other objects can exist in the adjacent lane of the vehicle. Generally, the follow-up target of the vehicle can be determined from the radar target 22, the visual target 23, and / or the fusion target 24 existing in the lane of the vehicle, so that the target type of the follow-up target of the vehicle can include a radar target, a visual target, or a fusion target. Of course, the follow-up target of the vehicle can also be selected from the adjacent lane of the vehicle, which is not specifically limited.

[0050] In actual application, radar targets and visual targets belonging to the same object can be generated in the same target detection and tracking cycle. If the difference between the radar targets and the visual targets belonging to the same object is large, the longitudinal distance between the radar targets or the visual targets corresponding to the object and the host vehicle can be used for following control; for example, only the longitudinal distance between the visual targets corresponding to the object and the host vehicle can be used for following control. Of course, only the longitudinal distance between the radar targets corresponding to the object and the host vehicle can be used for following control. Alternatively, the minimum value of the longitudinal distances between the radar targets and the visual targets corresponding to the object and the host vehicle can be used for following control, which is beneficial to guarantee the driving safety of the host vehicle. No specific limitation is made in this regard. If the difference between the radar targets and the visual targets belonging to the same object is small, the fusion targets corresponding to the object can be generated by combining the radar targets and the visual targets corresponding to the object, so as to combine the longitudinal distance between the fusion targets and the host vehicle for following control.

[0051] Since the longitudinal distances between the radar targets, the visual targets and the fusion targets belonging to the same object and the host vehicle often differ, when the current following target of the host vehicle and the historical following target in the adjacent cycle belong to the same object but the types of the targets are inconsistent, it is easy to cause a large fluctuation in the longitudinal distance between the following target used for following control in the adjacent cycle and the host vehicle, thereby affecting the stability of the braking process of the host vehicle.

[0052] In some feasible embodiments, the preset comfortable braking condition can further include that the longitudinal distance between the historical following target and the host vehicle is smoothed in the historical following control process of the host vehicle.

[0053] In the embodiments of the present application, the preset comfortable braking condition can further include that the longitudinal distance between the historical following target (i.e., the following target of the host vehicle in the last target detection and tracking cycle) and the host vehicle is smoothed in the historical following control process of the host vehicle. At this time, the preset comfortable braking condition is equivalent to the condition required to continue to maintain the execution of the vehicle comfortable braking function after the vehicle comfortable braking function is started in the following control process.

[0054] According to the above description, it can be known that the conditions required to start the vehicle comfortable braking function in the following process are more than the conditions required to continue to maintain the execution of the vehicle comfortable braking function, so as to guarantee the rationality and accuracy of the scheme for performing comfortable braking on the vehicle in the following control process in Figure 1 and also help to guarantee the stability and continuity of the execution of the scheme in Figure 1 so as to avoid too frequent start and termination of the operation of the vehicle comfortable braking function, which is beneficial to guarantee the user experience.

[0055] In some possible implementation manners, Figure 1 The method described in the above embodiment can further include:

[0056] If the target unique identifier of the current following target and the target unique identifier of the historical following target have a preset association relationship, it is determined that the current following target and the historical following target belong to the same object. Alternatively,

[0057] If the target unique identifier of the current following target and the target unique identifier of the historical following target have a preset association relationship, and the survival time of the current following target is greater than the survival time of the historical following target, it is determined that the current following target and the historical following target belong to the same object.

[0058] In the embodiments of the present application, the targets of various types obtained through target detection, tracking and fusion processing can generally have their own target unique identifiers, and the target unique identifiers of the same target successfully detected and tracked in different periods can be consistent; and the target unique identifiers of the radar targets, visual targets and fusion targets belonging to the same object detected in the same period can have an association.

[0059] Based on this, if the target types of the current following target and the historical following target are consistent, it can be indicated that the current following target and the historical following target belong to the same object when the target unique identifier of the current following target and the target unique identifier of the historical following target are consistent. If the target types of the current following target and the historical following target are inconsistent, whether the current following target and the historical following target belong to the same object can be identified according to whether the target unique identifier of the current following target and the target unique identifier of the historical following target have an association, which is convenient and fast.

[0060] In actual applications, the radar targets, visual targets and fusion targets can carry specified attribute information to represent whether the targets belong to the same object. When the target types of the current following target and the historical following target are inconsistent, the specified target belonging to the same object as the current following target and having the same target type as the historical following target can be determined according to the specified attribute information of the targets of various types detected in the current period. If the target unique identifier of the specified target is consistent with the target unique identifier of the historical following target, it can be indicated that the target unique identifier of the current following target and the target unique identifier of the historical following target have an association, so that it can be determined that the current following target and the historical following target belong to the same object.

[0061] Alternatively, if a visual target and a radar target are detected for the same object and a fusion target is not generated by combining the visual target and the radar target, only the visual target can be allowed as the following vehicle target of the ego vehicle; and when the fusion target is generated by combining the visual target and the radar target, the target unique identifier of the visual target can be used as the target unique identifier of the fusion target. If the target types of the current following vehicle target and the historical following vehicle target are inconsistent (for example, the historical following vehicle target belongs to a visual target, and the current following vehicle target belongs to a fusion target), the target unique identifier of the current following vehicle target can also be consistent with the target unique identifier of the historical following vehicle target, indicating that there is a correlation between the target unique identifier of the current following vehicle target and the target unique identifier of the historical following vehicle target, so that it can be determined that the current following vehicle target and the historical following vehicle target belong to the same object.

[0062] Similarly, if a visual target and a radar target are detected for the same object and a fusion target is not generated by combining the visual target and the radar target, only the radar target can be allowed as the following vehicle target of the ego vehicle; and when the fusion target is generated by combining the visual target and the radar target, the target unique identifier of the radar target can be used as the target unique identifier of the fusion target. If the target types of the current following vehicle target and the historical following vehicle target are inconsistent (for example, the historical following vehicle target belongs to a radar target, and the current following vehicle target belongs to a fusion target), the target unique identifier of the current following vehicle target can also be consistent with the target unique identifier of the historical following vehicle target, indicating that there is a correlation between the target unique identifier of the current following vehicle target and the target unique identifier of the historical following vehicle target, so that it can be determined that the current following vehicle target and the historical following vehicle target belong to the same object.

[0063] Of course, when the target types of the current following vehicle target and the historical following vehicle target are inconsistent, other ways can also be used to represent and determine whether there is a correlation between the target unique identifier of the current following vehicle target and the target unique identifier of the historical following vehicle target, and further identify whether they belong to the same object. For example, when the overlap rate of the regions where the current following vehicle target and the historical following vehicle target are located reaches a preset overlap rate, and the running speed, running acceleration, and motion direction of the two are consistent, it can be determined that there is a correlation between the target unique identifier of the current following vehicle target and the target unique identifier of the historical following vehicle target, and further that the current following vehicle target and the historical following vehicle target belong to the same object. This is not specifically limited.

[0064] In the embodiments of the present application, each type of target obtained through target detection, tracking and fusion processing can generally have a respective survival time, wherein the survival time of a radar target and a visual target can include the number or length of periods experienced from the period in which the target was first detected to the current period. The survival time of a fusion target can be the survival time of a radar target or a visual target relied on for generating the fusion target.

[0065] Based on this, if the current following target and the historical following target belong to the same object, the survival time of the current following target can generally be greater than the survival time of the historical following target, so that when the target unique identifier of the current following target and the target unique identifier of the historical following target have a preset association relationship, and the survival time of the current following target is greater than the survival time of the historical following target, it is determined again that the current following target and the historical following target belong to the same object, which is beneficial to improving the accuracy of the identification result of whether they belong to the same object.

[0066] In some possible implementation manners, Figure 1 The method described in the above embodiment, can further include:

[0067] If the current following target of the vehicle and the historical following target of the vehicle belong to different objects, the vehicle is controlled to brake according to the original longitudinal distance between the current following target in the target related information and the vehicle.

[0068] In the embodiments of the present application, when the current following target of the vehicle and the historical following target of the vehicle belong to different objects, it can be indicated that the following object of the vehicle has changed. At this time, it is generally normal for the longitudinal distance between the following target used for controlling the vehicle to brake and the vehicle to have a large fluctuation, and the driver can generally understand the braking instability phenomenon of the vehicle caused by the change of the following object, so that the original longitudinal distance between the current following target and the vehicle can be directly used to control the vehicle to brake without smoothing the original longitudinal distance between the current following target and the vehicle, which is beneficial to ensuring the accuracy of the following control result of the vehicle.

[0069] It can be understood that when the original longitudinal distance between the current following target and the vehicle is used to control the vehicle to brake, control instructions for increasing, decreasing or maintaining the braking torque required to be generated by the vehicle can be generated, or the vehicle can not be controlled to generate braking torque, so that control instructions for controlling the vehicle to generate braking torque are not generated, which is not limited in detail.

[0070] In some possible implementation manners, Figure 1 The method described in the above embodiment, can further include:

[0071] If the current following target of the host vehicle and the historical following target of the host vehicle belong to the same object, and the preset comfort braking condition of the host vehicle is not satisfied, the host vehicle is controlled according to the original longitudinal distance between the current following target in the target related information and the host vehicle.

[0072] In the embodiments of the present application, when the current following target of the host vehicle and the historical following target of the host vehicle belong to the same object, the preset comfort braking condition of the host vehicle may not be satisfied. At this time, the original longitudinal distance between the current following target and the host vehicle can be directly used for brake control of the host vehicle without smoothing, which is beneficial to guarantee the accuracy of the following control result of the host vehicle.

[0073] It can be understood that when the original longitudinal distance between the current following target and the host vehicle is used for brake control of the host vehicle, control instructions for increasing, decreasing or maintaining the brake torque required to be generated by the host vehicle can be generated, or the host vehicle can not be controlled to generate brake torque, so that control instructions for controlling the host vehicle to generate brake torque are not generated, which is not limited.

[0074] In some possible implementation manners, Figure 1 The method in the above method can further include:

[0075] generating brake control instructions for the host vehicle according to the target longitudinal distance between the current following target and the host vehicle. Or,

[0076] sending the target longitudinal distance between the current following target and the host vehicle to a target controller; the target controller is used for brake control of the host vehicle according to the target longitudinal distance.

[0077] In the embodiments of the present application, when the host vehicle is controlled according to the target longitudinal distance between the current following target and the host vehicle, the brake control instructions for the host vehicle can be directly generated by Figure 1 the execution subject of the method in the above method according to the target longitudinal distance, or the target longitudinal distance can be sent by Figure 1 the execution subject of the method in the above method to a target controller, so that brake control instructions for the host vehicle are generated by other controllers according to the target longitudinal distance, which is good in flexibility, and is not limited.

[0078] In some possible implementation manners, the smoothing processing on the original longitudinal distance between the current following target in the target related information and the host vehicle to obtain the target longitudinal distance between the current following target and the host vehicle can include:

[0079] determine the target longitudinal distance between the current following target and the vehicle from the range of the historical longitudinal distance between the historical following target and the vehicle to the original longitudinal distance.

[0080] In the embodiments of the present application, by letting the target longitudinal distance between the current following target and the vehicle obtained after the smoothing processing be located in the range of [the historical longitudinal distance, the original longitudinal distance] or [the original longitudinal distance, the historical longitudinal distance], the fluctuation of the longitudinal distance between the following target and the vehicle used for the braking control of the vehicle in a short time can be reduced to a certain extent, thereby facilitating the improvement of the stability of the vehicle braking process and the improvement of the user experience.

[0081] In some possible implementation manners, the determination of the target longitudinal distance between the current following target and the vehicle from the range of the historical longitudinal distance between the historical following target and the vehicle to the original longitudinal distance can include:

[0082] If the historical longitudinal distance is greater than the original longitudinal distance, the difference between the historical longitudinal distance and the target difference value is determined as the target longitudinal distance between the current following target and the vehicle.

[0083] If the historical longitudinal distance is less than the original longitudinal distance, the sum of the historical longitudinal distance and the target difference value is determined as the target longitudinal distance between the current following target and the vehicle.

[0084] The target difference value is the product of the absolute value of the difference between the historical longitudinal distance and the original longitudinal distance and a preset weight, and the preset weight is a value greater than 0 and less than 1.

[0085] In the embodiments of the present application, by taking the product of the absolute value of the difference between the historical longitudinal distance and the original longitudinal distance and a preset weight as the target difference value, and determining the difference between the historical longitudinal distance and the target difference value as the target longitudinal distance between the current following target and the vehicle when the historical longitudinal distance is greater than the original longitudinal distance, and determining the sum of the historical longitudinal distance and the target difference value as the target longitudinal distance between the current following target and the vehicle when the historical longitudinal distance is less than the original longitudinal distance, the effectiveness and stability of the smoothing processing result of the longitudinal distance between the vehicle and the following target used for the braking control of the vehicle can be guaranteed, thereby facilitating the improvement of the stability of the vehicle braking process and the improvement of the user experience. It can be understood that other principles or schemes can also be used to smooth the original longitudinal distance between the current following target and the vehicle, which is not limited in particular.

[0086] In some possible implementation manners, Figure 1The follow vehicle control method provided in the embodiments and the follow vehicle control method can be applied to at least one of an adaptive cruise control (ACC) function and a traffic jam assist (TJA) function, and of course, can be applied to other vehicle auxiliary functions related to follow vehicle control, without specific limitation. By executing the follow vehicle control method in the above vehicle auxiliary function running process Figure 3 The method provided in the embodiments and the method are beneficial to improving the stability of the vehicle braking process and improving the user experience.

[0087] The application further provides a computer program product, which has a computer readable program stored thereon, and the computer readable program can implement the steps of the follow vehicle control method of at least some of the above embodiments when executed by a controller. For details, refer to the specific description in the above embodiments, which will not be repeated here.

[0088] The application further provides a computer program product, which has a computer readable program stored thereon, and the computer readable program can implement the steps of the follow vehicle control method of at least some of the above embodiments when executed by a controller. For details, refer to the specific description in the above embodiments, which will not be repeated here. Figure 3 As shown in FIG. 1, the electronic device includes a radar device 1, an image acquisition device 2, a domain controller 3, and a vehicle controller 4. ​ At the hardware level, the electronic device can include a processor 31 and a memory 35, and of course, can also include an internal bus 32, a network interface 33, a memory 34, and other hardware required by the business. The processor 31 can read the corresponding computer program from the memory 35 into the memory and then run to implement the steps of the follow vehicle control method of at least some of the above embodiments. For details, refer to the specific description in the above embodiments, which will not be repeated here.

[0089] In some possible implementations, the electronic device can include at least one of a radar device, an image acquisition device, and a domain controller, and of course, the electronic device can also include other kinds of vehicle controllers or devices, without specific limitation.

[0090] Finally, each of the embodiments in the application is described in a progressive manner, and the same and similar parts between the embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments. Especially, the computer program product and the electronic device are basically similar to the method embodiments, so the description is relatively simple, and the relevant parts can refer to the part of the method embodiments.

[0091] The above only describes the embodiments of the application and is not intended to limit the application. The application can have various changes and modifications for those skilled in the art. Any modification, equivalent replacement, improvement, etc. within the spirit and principle of the application shall be included in the scope of the claims of the application.

Claims

1. A car-following control method, comprising: obtaining target-related information of a current car-following target of a host vehicle; if the current car-following target of the host vehicle and a historical car-following target of the host vehicle belong to a same object, and a preset comfortable braking condition of the host vehicle is met, performing smoothing processing on an original longitudinal distance between the current car-following target and the host vehicle in the target-related information, to obtain a target longitudinal distance between the current car-following target and the host vehicle.

2. The method of claim 1, the predetermined comfort braking condition comprising at least: a preset condition for braking the host vehicle based on the current car-following target is met, and a difference between a historical longitudinal distance between the historical car-following target and the host vehicle and the original longitudinal distance reaches a first threshold. 3.The method of claim 2, wherein the preset comfortable braking condition further comprises: during a historical car-following control process of the host vehicle, no smoothing processing is performed on a longitudinal distance between the historical car-following target and the host vehicle; and the target type of the current car-following target is inconsistent with that of the historical car-following target, the current car-following target is in a static state, a motion speed of the current car-following target is less than a preset speed and a motion probability prediction value of the current car-following target is less than a preset probability, the difference between the historical longitudinal distance and the original longitudinal distance reaches a second threshold, and at least one of the original longitudinal distance reaching a third threshold and a vehicle traveling speed of the host vehicle reaching a fourth threshold is met; wherein the second threshold is greater than the first threshold. a radar target, a vision target, and a fusion target; 4. The method of claim 3, the target type comprising: wherein the radar target is obtained by processing surrounding environment perception data collected by a radar device, the vision target is obtained by processing surrounding environment image data collected by an image collection device, and the fusion target is obtained by processing the surrounding environment perception data collected by the radar device and the surrounding environment image data collected by the image collection device. during the historical car-following control process of the host vehicle, smoothing processing is performed on the longitudinal distance between the historical car-following target and the host vehicle.

5. The method of claim 2, the predetermined comfort braking condition further comprising: 6.The method of claim 1, further comprising: if a target unique identifier of the current car-following target and a target unique identifier of the historical car-following target have a preset association relationship, it is determined that the current car-following target and the historical car-following target belong to a same object; or if the target unique identifier of the current car-following target and the target unique identifier of the historical car-following target have the preset association relationship, and a survival time of the current car-following target is greater than a survival time of the historical car-following target, it is determined that the current car-following target and the historical car-following target belong to the same object. 7.The method of claim 1, further comprising: if the current car-following target of the host vehicle and the historical car-following target of the host vehicle belong to different objects, performing braking control on the host vehicle according to the original longitudinal distance between the current car-following target and the host vehicle in the target-related information. 8.The method of claim 1, further comprising: ​ ​ If the current following target of the vehicle and the historical following target of the vehicle belong to the same object, and the preset comfortable braking condition of the vehicle is not met, the vehicle is controlled according to the original longitudinal distance between the current following target in the target related information and the vehicle.

9. The method of claim 1, further comprising: generating a braking control instruction for the vehicle according to the target longitudinal distance between the current following target and the vehicle; or, sending the target longitudinal distance between the current following target and the vehicle to a target controller, wherein the target controller is configured to control the vehicle according to the target longitudinal distance.

10. The method of any one of claims 1-9, wherein the smoothing processing on the original longitudinal distance between the current following target in the target related information and the vehicle to obtain the target longitudinal distance between the current following target and the vehicle comprises: determining the target longitudinal distance between the current following target and the vehicle from a range of the historical longitudinal distance between the historical following target and the vehicle to the original longitudinal distance.

11. The method of claim 10, wherein the determining the target longitudinal distance between the current following target and the vehicle from the range of the historical longitudinal distance between the historical following target and the vehicle to the original longitudinal distance comprises: if the historical longitudinal distance is greater than the original longitudinal distance, determining a difference between the historical longitudinal distance and a target difference value as the target longitudinal distance between the current following target and the vehicle; if the historical longitudinal distance is less than the original longitudinal distance, determining a sum of the historical longitudinal distance and the target difference value as the target longitudinal distance between the current following target and the vehicle; wherein the target difference value is a product of an absolute value of a difference between the historical longitudinal distance and the original longitudinal distance and a preset weight, and the preset weight is a value greater than 0 and less than 1.

12. The method of claim 1, wherein the following control method is applied to at least one of an adaptive cruise function and a traffic jam assist function.

13. A computer program product having a computer readable program stored thereon, wherein the computer readable program, when executed by a controller, implements the steps of the method of any one of claims 1-12.

14. An electronic device comprising: a processor and a memory, wherein the memory stores computer readable instructions adapted to be loaded and executed by the processor to implement the steps of the method of any one of claims 1-12.

15. The electronic device of claim 14, the electronic device comprising: at least one of a radar device, an image acquisition device, and a domain controller.

Images