A method and device for determining a following target

Abstract

The application provides a method and device for determining a following target. The application screens candidate vehicles of at least one scene type from a plurality of target vehicles in front of a host vehicle through a host vehicle driving parameter value and target driving parameter values of the plurality of target vehicles; and determines any candidate vehicle as a tracking target vehicle when the target driving parameter value of the any candidate vehicle meets a preset tracking condition. The tracking target vehicle is determined through the common host vehicle driving parameter value and the target driving parameter value, which improves the commonality of adaptive cruise control, is applicable to multiple scenes and multiple working conditions, improves the balance between comfort and driving safety, saves computing resources, and reduces development costs. The same scene type of candidate vehicles is screened through multiple means, which improves the accuracy of target identification.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of adaptive cruise technology, in particular to a method and device for determining a following target vehicle, a medium and an electronic device. BACKGROUND

[0002] An adaptive cruise control (ACC) is a driving assistance system that adjusts the speed of a vehicle according to the speed and following distance set by the driver. The system constructs a road environment based on perception modules, algorithms, data training, etc., and identifies targets. If there is a first target vehicle and a second target vehicle in front of the ego vehicle, the system can control the ego vehicle to follow the preceding vehicle and maintain a certain safety distance according to the set time distance level.

[0003] However, in some special scenarios, relying solely on perception modules cannot respond to rapidly changing road environments in a timely manner, thereby disrupting the stability of the following target decision and easily causing collisions.

[0004] Therefore, the present application provides a method for determining a following target vehicle to solve the above technical problems. SUMMARY

[0005] The present application aims to provide a method and device for determining a following target vehicle, a medium and an electronic device, which can solve at least one of the above technical problems. The specific scheme is as follows:

[0006] According to the specific embodiments of the present application, in a first aspect, the present application provides a method for determining a following target vehicle, comprising:

[0007] obtaining a self-vehicle driving parameter value and target driving parameter values of a plurality of target vehicles in front of the ego vehicle;

[0008] selecting at least one candidate vehicle of a scene type from the plurality of target vehicles based on the ego vehicle driving parameter value and the target driving parameter values of the plurality of target vehicles;

[0009] When the target driving parameter value of any candidate vehicle meets a preset tracking condition, determining the any candidate vehicle as a tracking target vehicle.

[0010] Optionally, the step of selecting at least one candidate vehicle of a scene type from the plurality of target vehicles based on the ego vehicle driving parameter value and the target driving parameter values of the plurality of target vehicles comprises:

[0011] When the cut-in identifier of any target vehicle is in an active state, and the lateral distance variation value of the any target vehicle and the ego vehicle is less than zero, and the direction of the lateral speed of the any target vehicle is the same as the preset lateral cut-in direction, the any target vehicle is determined as a candidate vehicle of the cut-in type.

[0012] Optionally, the filtering of the candidate vehicle of the at least one scene type from the plurality of target vehicles based on the ego vehicle driving parameter value and the target driving parameter value of the plurality of target vehicles comprises:

[0013] When the longitudinal distance value of any target vehicle and the ego vehicle is less than a preset first longitudinal distance threshold, or the relative longitudinal speed value of the any target vehicle and the ego vehicle is greater than a preset relative longitudinal speed threshold, when the lateral speed value of the any target vehicle is greater than a preset lateral speed threshold, and the lateral distance value of the any target vehicle and the ego vehicle is less than a preset lateral distance threshold, and the overtaking distance value of the any target vehicle crossing a single lane line is greater than a preset overtaking distance threshold, the any target vehicle is determined as a candidate vehicle of the cut-in type.

[0014] Optionally, the filtering of the candidate vehicle of the at least one scene type from the plurality of target vehicles based on the ego vehicle driving parameter value and the target driving parameter value of the plurality of target vehicles comprises:

[0015] When the front vehicle identifier of any target vehicle is in an active state, or the belonging-to-home-lane probability value of the any target vehicle is greater than a preset belonging-to-home-lane probability threshold, or the target distance value of the any target vehicle and the ego vehicle is less than a preset distance threshold, when the lane invasion identifier of the any target vehicle is in an active state, and the sideline gap value of the ego vehicle is less than a preset sideline gap threshold, the any target vehicle is determined as a pending vehicle.

[0016] When the pending vehicle does not satisfy a preset exclusion condition, the pending vehicle is determined as a candidate vehicle of the belonging-to-ego-lane type.

[0017] Optionally, the preset exclusion condition comprises:

[0018] The preset first exclusion condition comprises: the lane change identifier of the pending vehicle is in an active state, and the cut-out identifier of the pending vehicle is in an active state.

[0019] The preset second exclusion condition comprises: the direction of the lateral speed of the pending vehicle is the same as a preset lateral cut-out direction.

[0020] The preset third exclusion condition comprises: when the self-vehicle lane mark of the pending vehicle is in an activated state, and the motion state mark of the pending vehicle is in an activated state, and the lane edge gap value of the pending vehicle is greater than a preset lane edge gap threshold, and the road overlap value of the pending vehicle is less than a preset first road overlap threshold, and the self-vehicle overlap value between the ego vehicle and the pending vehicle is less than a preset first vehicle overlap threshold.

[0021] The preset third exclusion condition comprises: when the self-vehicle lane mark of the pending vehicle is in an activated state, and the motion state mark of the pending vehicle is in a frozen state, and the road overlap value of the pending vehicle is less than a preset second road overlap threshold, and the self-vehicle overlap value between the ego vehicle and the pending vehicle is less than a preset second vehicle overlap threshold, and the lane change mark of the ego vehicle is in a frozen state, and the lane pressure mark of the ego vehicle is in a frozen state.

[0022] Optionally, the filtering of the candidate vehicles of at least one scene type from the plurality of target vehicles based on the ego vehicle driving parameter value and the target driving parameter values of the plurality of target vehicles comprises:

[0023] When any target vehicle is determined as the information mark of the tracked target vehicle in the previous frame, and the lane change mark of the ego vehicle is in a frozen state, and the road overlap value of the any target vehicle is greater than a preset first road overlap threshold, the any target vehicle is determined as the candidate vehicle of the separate road overlap type.

[0024] Optionally, the filtering of the candidate vehicles of at least one scene type from the plurality of target vehicles based on the ego vehicle driving parameter value and the target driving parameter values of the plurality of target vehicles comprises:

[0025] When the longitudinal distance value between any target vehicle and the ego vehicle is less than a preset second longitudinal distance threshold, and the road overlap value is greater than a preset second road overlap threshold, and the lane pressure mark of the ego vehicle is in an activated state, the any target vehicle is determined as the candidate vehicle of the separate road overlap type.

[0026] Optionally, the filtering of the candidate vehicles of at least one scene type from the plurality of target vehicles based on the ego vehicle driving parameter value and the target driving parameter values of the plurality of target vehicles comprises:

[0027] When the longitudinal distance value between any target vehicle and the ego vehicle is less than a preset third longitudinal distance threshold, and the any target vehicle is determined as the information mark of the tracked target vehicle in the previous frame, and the self-vehicle overlap value of the any target vehicle is greater than a preset self-vehicle overlap threshold, the any target vehicle is determined as the candidate vehicle of the separate self-vehicle overlap type.

[0028] Optionally, the determining that any candidate vehicle is a tracking target vehicle when a target driving parameter value of the candidate vehicle satisfies a preset tracking condition comprises:

[0029] The determining that any candidate vehicle is a pending tracking target vehicle when a vehicle type of the candidate vehicle satisfies one of a plurality of preset vehicle types, a driving direction of the candidate vehicle is the same as a driving direction of the ego vehicle, and a longitudinal distance value between the candidate vehicle and the ego vehicle is less than or equal to a preset fourth longitudinal distance threshold.

[0030] The determining that a pending tracking target vehicle with a minimum longitudinal distance value from the ego vehicle is the tracking target vehicle.

[0031] According to the specific embodiments of the present application, in a second aspect, the present application provides a vehicle following target determination device, comprising:

[0032] An acquisition unit configured to acquire a driving parameter value of an ego vehicle and target driving parameter values of a plurality of target vehicles in front of the ego vehicle;

[0033] A screening unit configured to screen candidate vehicles of at least one scene type from the plurality of target vehicles based on the driving parameter value of the ego vehicle and the target driving parameter values of the plurality of target vehicles.

[0034] A determination unit configured to determine that any candidate vehicle is a tracking target vehicle when a target driving parameter value of the candidate vehicle satisfies a preset tracking condition.

[0035] Optionally, the screening of the candidate vehicles of at least one scene type from the plurality of target vehicles based on the driving parameter value of the ego vehicle and the target driving parameter values of the plurality of target vehicles comprises:

[0036] The determining that any target vehicle is a cut-in type candidate vehicle when a cut-in identifier of the target vehicle is in an active state, a lateral distance change value between the target vehicle and the ego vehicle is less than zero, and a direction of a lateral speed of the target vehicle is the same as a preset lateral cut-in direction.

[0037] Optionally, the screening of the candidate vehicles of at least one scene type from the plurality of target vehicles based on the driving parameter value of the ego vehicle and the target driving parameter values of the plurality of target vehicles comprises:

[0038] When a longitudinal distance value between any target vehicle and the ego vehicle is less than a preset first longitudinal distance threshold value, or a relative longitudinal speed value between the any target vehicle and the ego vehicle is greater than a preset relative longitudinal speed threshold value, when a lateral speed value of the any target vehicle is greater than a preset lateral speed threshold value, and a lateral distance value between the any target vehicle and the ego vehicle is less than a preset lateral distance threshold value, and an overtaking distance value of the any target vehicle beyond a single-side lane line is greater than a preset overtaking distance threshold value, the any target vehicle is determined as a candidate vehicle of the cut-in type.

[0039] Optionally, the filtering of the candidate vehicle of at least one scene type from the plurality of target vehicles based on the ego vehicle driving parameter value and the target driving parameter value of the plurality of target vehicles comprises:

[0040] When a front vehicle identification of any target vehicle is in an activated state, or a belonging home lane probability value of the any target vehicle is greater than a preset belonging home lane probability threshold value, or a target distance value between the any target vehicle and the ego vehicle is less than a preset distance threshold value, when an encroaching line identification of the any target vehicle is in an activated state, and a side line gap value of the ego vehicle is less than a preset side line gap threshold value, the any target vehicle is determined as a pending vehicle.

[0041] When the pending vehicle does not satisfy a preset exclusion condition, the pending vehicle is determined as a candidate vehicle of the belonging ego lane type.

[0042] Optionally, the preset exclusion condition comprises:

[0043] The preset first exclusion condition comprises that a lane change identification of the pending vehicle is in an activated state, and a cut-out identification of the pending vehicle is in an activated state.

[0044] The preset second exclusion condition comprises that a direction of a lateral speed of the pending vehicle is the same as a preset lateral cut-out direction.

[0045] The preset third exclusion condition comprises that when a self-vehicle lane identification of the pending vehicle is in an activated state, and a motion state identification of the pending vehicle is in an activated state, and a side line gap value of the pending vehicle is greater than a preset side line gap threshold value, and a road overlap value of the pending vehicle is less than a preset first road overlap threshold value, and a self-vehicle overlap value between the ego vehicle and the pending vehicle is less than a preset first vehicle overlap threshold value.

[0046] The preset third exclusion condition comprises that when the self-vehicle lane identification of the pending vehicle is in an activated state, and the motion state identification of the pending vehicle is in a frozen state, and the road overlap value of the pending vehicle is less than a preset second road overlap threshold value, and the self-vehicle overlap value between the ego vehicle and the pending vehicle is less than a preset second vehicle overlap threshold value, and a lane change identification of the ego vehicle is in a frozen state, and an encroaching line identification of the ego vehicle is in a frozen state.

[0047] Optionally, the filtering out of the candidate vehicles of the at least one scenario type from the plurality of target vehicles based on the self-vehicle driving parameter value and the target driving parameter values of the plurality of target vehicles comprises:

[0048] When any target vehicle is determined as the information identifier of the tracking target vehicle in the previous frame, the lane change identifier of the self-vehicle is in the frozen state, and the road overlap value of the any target vehicle is greater than a preset first road overlap threshold, the any target vehicle is determined as the candidate vehicle of the single road overlap type.

[0049] Optionally, the filtering out of the candidate vehicles of the at least one scenario type from the plurality of target vehicles based on the self-vehicle driving parameter value and the target driving parameter values of the plurality of target vehicles comprises:

[0050] When the longitudinal distance value between any target vehicle and the self-vehicle is less than a preset second longitudinal distance threshold, the road overlap value is greater than a preset second road overlap threshold, and the line pressure identifier of the self-vehicle is in the activated state, the any target vehicle is determined as the candidate vehicle of the single road overlap type.

[0051] Optionally, the filtering out of the candidate vehicles of the at least one scenario type from the plurality of target vehicles based on the self-vehicle driving parameter value and the target driving parameter values of the plurality of target vehicles comprises:

[0052] When the longitudinal distance value between any target vehicle and the self-vehicle is less than a preset third longitudinal distance threshold, the any target vehicle is determined as the information identifier of the tracking target vehicle in the previous frame, and the self-vehicle overlap value of the any target vehicle is greater than a preset self-vehicle overlap threshold, the any target vehicle is determined as the candidate vehicle of the single self-vehicle overlap type.

[0053] Optionally, when the target driving parameter value of any candidate vehicle meets a preset tracking condition, the any candidate vehicle is determined as the tracking target vehicle, comprising:

[0054] When the vehicle type of any candidate vehicle meets one of a plurality of preset vehicle types, the driving direction of the any candidate vehicle is the same as the driving direction of the self-vehicle, and the longitudinal distance value between the any candidate vehicle and the self-vehicle is less than or equal to a preset fourth longitudinal distance threshold, the any candidate vehicle is determined as the pending tracking target vehicle.

[0055] The pending tracking target vehicle with the minimum longitudinal distance value from the self-vehicle is determined as the tracking target vehicle.

[0056] According to the specific embodiments of the present application, in a third aspect, the present application provides a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the method for determining a following target vehicle as claimed in any one of the above.

[0057] According to the specific embodiments of the present application, in a fourth aspect, the present application provides an electronic device comprising: one or more processors; and a storage device storing one or more programs, which, when executed by the one or more processors, cause the one or more processors to implement the method for determining a following target vehicle as claimed in any one of the above.

[0058] Compared with the prior art, the above scheme of the embodiments of the present application has at least the following beneficial effects:

[0059] The present application provides a method, device, medium and electronic device for determining a following target vehicle. The present application screens candidate vehicles of at least one scene type from a plurality of target vehicles in front of a host vehicle by using a host vehicle driving parameter value and target driving parameter values of the plurality of target vehicles; and determines any candidate vehicle as a tracking target vehicle when the target driving parameter value of the any candidate vehicle meets a preset tracking condition. The tracking target vehicle is determined by using a common host vehicle driving parameter value and a target driving parameter value, which improves the commonality of adaptive cruise control, is applicable to multiple scenes and multiple working conditions, improves the balance between comfort and driving safety, saves computing resources, and reduces development costs. The same scene type of candidate vehicles is screened by using multiple means, which improves the accuracy of target identification. BRIEF DESCRIPTION OF DRAWINGS

[0060] Figure 1 A logic diagram of the method for determining a following target vehicle according to the embodiments of the present application is shown;

[0061] Figure 2 A flowchart of the method for determining a following target vehicle according to the embodiments of the present application is shown;

[0062] Figure 3 A unit block diagram of the device for determining a following target vehicle according to the embodiments of the present application is shown. DETAILED DESCRIPTION

[0063] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of protection of the present application.

[0064] The terminology used in the embodiments of this application is for the purpose of describing particular embodiments only and is not intended to limit the application. The singular forms “a,” “said,” and “the” used in the embodiments of this application and the appended claims are also intended to include the plural forms, and “multiple” generally includes at least two unless the context clearly indicates otherwise.

[0065] It should be understood that the term "and / or" used in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0066] It should be understood that although the terms first, second, third, etc., may be used in the embodiments of this application, these descriptions should not be limited to these terms. These terms are only used to distinguish the descriptions. For example, first may also be referred to as second without departing from the scope of the embodiments of this application, and similarly, second may also be referred to as first.

[0067] Depending on the context, the words “if” or “suppose” as used here can be interpreted as “when” or “in response to determination” or “in response to detection.” Similarly, depending on the context, the phrases “if determination” or “if detection (of the stated condition or event)” can be interpreted as “when determination” or “in response to determination” or “when detection (of the stated condition or event)” or “in response to detection (of the stated condition or event).”

[0068] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that an article or device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such an article or device. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the article or device that includes said element.

[0069] It should be noted that any symbols and / or numbers present in the specification that are not marked in the accompanying drawings are not reference numerals.

[0070] The optional embodiments of this application are described in detail below with reference to the accompanying drawings.

[0071] The embodiments provided in this application are embodiments of a method for determining a vehicle following target.

[0072] like Figure 1As shown, the embodiment of the application obtains perception information based on information collected by a monocular camera, combines self-vehicle information and last frame information, and obtains self-vehicle driving parameter values and target driving parameter values of a plurality of target vehicles in front of the self-vehicle according to a road fusion algorithm and a scene processing algorithm. According to a scene type, the self-vehicle driving parameter values and the target driving parameter values of the plurality of target vehicles are judged and processed to obtain candidate vehicles of the cut-in type, the self-lane type, the separate road overlap type, and the separate self-vehicle overlap type. Then, the candidate vehicles are confirmed as target vehicles through vehicle types, longitudinal distance values, and driving directions. Finally, the vehicle with the minimum longitudinal distance value is screened out as a tracking target vehicle.

[0073] The application will be described in detail below. Figure 2 The embodiment of the application will be described in detail.

[0074] In step S201, self-vehicle driving parameter values and target driving parameter values of a plurality of target vehicles in front of the self-vehicle are obtained.

[0075] The target vehicle refers to a vehicle in front of the self-vehicle. The embodiment of the application is to screen out a tracking target vehicle from the plurality of target vehicles so as to perform adaptive cruise on the tracking target vehicle.

[0076] In step S202, candidate vehicles of at least one scene type are screened out from the plurality of target vehicles based on the self-vehicle driving parameter values and the target driving parameter values of the plurality of target vehicles.

[0077] The embodiment of the application can screen out one or more candidate vehicles from the plurality of target vehicles through the self-vehicle driving parameter values and the target driving parameter values of the plurality of target vehicles.

[0078] The coordinate data involved in the embodiment of the application is data of a vehicle body coordinate.

[0079] The scene type includes the cut-in type, the self-lane type, the separate road overlap type, and the separate self-vehicle overlap type. In the second screening, one candidate vehicle of a scene type may be screened out, or a plurality of candidate vehicles of scene types may be screened out. When no candidate vehicle of a scene type is screened out, there is no tracking target vehicle.

[0080] The cut-in type refers to a scene type in which a target vehicle cuts in from a side lane to the self-vehicle.

[0081] The self-lane type refers to a scene type in which a target vehicle is in the same lane as the self-vehicle.

[0082] The separate road overlap type refers to a scene type in which a ratio of a width value of a vehicle to a lane width value.

[0083] The separate vehicle overlap type refers to a scenario type in which a first cross section of the ego vehicle in a vehicle coordinate system forms a plane, and a ratio of an area in which a projection of a second cross section of the front vehicle on the plane overlaps the first cross section to an area of the first cross section.

[0084] In some embodiments, the target driving parameter value at least includes: a cut-in identifier, a lateral distance change value, and a direction of lateral speed.

[0085] Correspondingly, the filtering of the candidate vehicle of at least one scenario type from the plurality of target vehicles based on the ego vehicle driving parameter value and the target driving parameter value of the plurality of target vehicles includes:

[0086] In step S202a, when the cut-in identifier of any target vehicle is in an active state, the lateral distance change value between the any target vehicle and the ego vehicle is less than zero, and the direction of the lateral speed of the any target vehicle is the same as the preset lateral cut-in direction, the any target vehicle is determined as a candidate vehicle of the cut-in type.

[0087] The cut-in identifier is activated by the perception module.

[0088] The lateral distance change value is equal to a difference between a lateral distance value between the target vehicle and the ego vehicle in a current frame and a lateral distance value between the target vehicle and the ego vehicle in a previous frame. When the lateral distance change value between the any target vehicle and the ego vehicle is less than zero, it indicates that the lateral distance between the any target vehicle and the ego vehicle is getting closer and closer.

[0089] Frame, indicating a collection period, and a frame is a collection period.

[0090] The embodiment determines the any target vehicle as a candidate vehicle of the cut-in type by using part of the information provided by the perception module.

[0091] In some embodiments, in some scenarios, the target vehicle invades the lane at a high speed, and the perception module cannot activate the cut-in identifier of the target vehicle in time. Therefore, a solution for the cut-in type is added.

[0092] The target driving parameter value at least includes: a longitudinal distance value, a relative longitudinal speed value, a lateral speed value, a lateral distance value, and an overtaking distance value.

[0093] Correspondingly, the filtering of the candidate vehicle of at least one scenario type from the plurality of target vehicles based on the ego vehicle driving parameter value and the target driving parameter value of the plurality of target vehicles includes:

[0094] Step S202b, when the longitudinal distance value between any target vehicle and the ego vehicle is less than a preset first distance threshold, or the relative longitudinal speed value between the target vehicle and the ego vehicle is greater than a preset relative longitudinal speed threshold, when the lateral speed value of the target vehicle is greater than a preset lateral speed threshold, and the lateral distance value between the target vehicle and the ego vehicle is less than a preset lateral distance threshold, and the exceeding distance value of the target vehicle crossing the single-side lane line is greater than a preset exceeding distance threshold, the target vehicle is determined as a candidate vehicle of the cut-in type.

[0095] The two methods of the cut-in type are used in cooperation with each other, and the identification efficiency of the candidate vehicle of the cut-in type can be improved.

[0096] In some embodiments, the ego vehicle driving parameter value at least includes a side-line clearance value.

[0097] The target driving parameter value at least includes: a front vehicle identification, a belonging-to-self-lane probability value, a target distance value, and an invasion-line identification.

[0098] The side-line clearance value refers to the distance value between the vehicle and the lane side line. The side-line clearance value uses either a left side-line clearance value or a right side-line clearance value. Only one side-line clearance value is used as a calculation standard in one screening.

[0099] The target distance value refers to the distance value between the target vehicle and the ego vehicle.

[0100] Correspondingly, the screening of the candidate vehicle of at least one scene type from the plurality of target vehicles based on the ego vehicle driving parameter value and the target driving parameter value of the plurality of target vehicles includes:

[0101] Step S202c-1, when the front vehicle identification of any target vehicle is in an active state, or the belonging-to-self-lane probability value of the target vehicle is greater than a preset belonging-to-self-lane probability threshold, or the target distance value between the target vehicle and the ego vehicle is less than a preset distance threshold, when the invasion-line identification of the target vehicle is in an active state, and the side-line clearance value of the ego vehicle is less than a preset side-line clearance threshold, the target vehicle is determined as a pending vehicle.

[0102] Step S202c-2, when the pending vehicle does not satisfy a preset exclusion condition, the pending vehicle is determined as a candidate vehicle of the belonging-to-self-lane type.

[0103] In some embodiments, the ego vehicle driving parameter value at least includes a lane-changing identification and a line-pressing identification.

[0104] The target driving parameter value at least includes: a lane-changing identification, a cut-out identification, a lateral speed, a self-lane identification, a motion state identification, a side-line clearance value, a road overlap value, and a self-vehicle overlap value.

[0105] The road overlap value refers to the ratio of the width value of the vehicle to the lane width value.

[0106] The self-vehicle overlap value refers to that a first cross section of the self-vehicle in the vehicle coordinate system forms a plane, and the projection of the second cross section of the front vehicle on the plane overlaps the first cross section.

[0107] Correspondingly, the preset exclusion condition includes:

[0108] The preset first exclusion condition includes that the lane change identifier of the pending vehicle is in an active state, and the cut-out identifier of the pending vehicle is in an active state.

[0109] The preset second exclusion condition includes that the direction of the lateral speed of the pending vehicle is the same as the preset lateral cut-out direction.

[0110] The preset third exclusion condition includes that when the self-vehicle lane identifier of the pending vehicle is in an active state, and the motion state identifier of the pending vehicle is in an active state, and the sideline gap value of the pending vehicle is greater than a preset sideline gap threshold value, and the road overlap value of the pending vehicle is less than a preset first road overlap threshold value, and the self-vehicle overlap value between the self-vehicle and the pending vehicle is less than a preset first vehicle overlap threshold value.

[0111] The preset fourth exclusion condition includes that when the self-vehicle lane identifier of the pending vehicle is in an active state, and the motion state identifier of the pending vehicle is in a frozen state, and the road overlap value of the pending vehicle is less than a preset second road overlap threshold value, and the self-vehicle overlap value between the self-vehicle and the pending vehicle is less than a preset second vehicle overlap threshold value, and the lane change identifier of the self-vehicle is in a frozen state, and the lane pressure identifier of the self-vehicle is in a frozen state.

[0112] The specific embodiment only determines the pending vehicle as a candidate vehicle belonging to the self-lane type when the pending vehicle does not meet the preset first exclusion condition, the preset second exclusion condition, the preset third exclusion condition and the preset fourth exclusion condition. If one of the conditions is met, the pending vehicle is excluded from the candidate vehicle belonging to the self-lane type.

[0113] In some specific embodiments, the self-vehicle driving parameter value at least includes a lane change identifier.

[0114] The target driving parameter value at least includes the information identifier and the road overlap value determined as the tracking target vehicle in the previous frame.

[0115] Correspondingly, the filtering of the candidate vehicle of at least one scene type from the plurality of target vehicles based on the self-vehicle driving parameter value and the target driving parameter value of the plurality of target vehicles includes:

[0116] Step S202d, when any target vehicle has the information identifier of being determined as the tracking target vehicle in the previous frame, the lane change identifier of the ego vehicle is in the frozen state, and the road overlap value of the any target vehicle is greater than the preset first road overlap threshold, the any target vehicle is determined as the candidate vehicle of the single road overlap type.

[0117] In some embodiments, the ego vehicle driving parameter value at least includes the lane-keeping identifier;

[0118] The target driving parameter value at least includes the longitudinal distance value and the road overlap value.

[0119] Correspondingly, the filtering of the candidate vehicle of at least one scene type from the plurality of target vehicles based on the ego vehicle driving parameter value and the target driving parameter value of the plurality of target vehicles includes:

[0120] Step S202e, when the longitudinal distance value of any target vehicle is less than the preset second longitudinal distance threshold, the road overlap value of the any target vehicle is greater than the preset second road overlap threshold, and the lane-keeping identifier of the ego vehicle is in the active state, the any target vehicle is determined as the candidate vehicle of the single road overlap type.

[0121] In some embodiments, the target driving parameter value at least includes: the longitudinal distance value, the information identifier of being determined as the tracking target vehicle in the previous frame, and the ego vehicle overlap value.

[0122] Correspondingly, the filtering of the candidate vehicle of at least one scene type from the plurality of target vehicles based on the ego vehicle driving parameter value and the target driving parameter value of the plurality of target vehicles includes:

[0123] Step S202f, when the longitudinal distance value between any target vehicle and the ego vehicle is less than the preset third longitudinal distance threshold, the any target vehicle has the information identifier of being determined as the tracking target vehicle in the previous frame, and the ego vehicle overlap value of the any target vehicle is greater than the preset ego vehicle overlap threshold, the any target vehicle is determined as the candidate vehicle of the single ego vehicle overlap type.

[0124] Step S203, when the target driving parameter value of any candidate vehicle meets the preset tracking condition, the any candidate vehicle is determined as the tracking target vehicle.

[0125] In some embodiments, the target driving parameter value includes: the vehicle type, the driving direction, and the longitudinal distance value.

[0126] Correspondingly, when the target driving parameter value of any candidate vehicle meets the preset tracking condition, the any candidate vehicle is determined as the tracking target vehicle, including:

[0127] Step S203-1, when the vehicle type of any candidate vehicle satisfies one of the plurality of preset vehicle types, and the driving direction of the any candidate vehicle is the same as the driving direction of the ego vehicle, and the longitudinal distance value between the any candidate vehicle and the ego vehicle is less than or equal to the preset fourth longitudinal distance threshold, the any candidate vehicle is determined as a pending tracking target vehicle.

[0128] The plurality of preset vehicle types include a car type, a truck type, a motorcycle type and a bicycle type. If it is other types, it is excluded.

[0129] The driving direction of the candidate vehicle is the same as the driving direction of the ego vehicle, for example, the ego vehicle is driving forward, the vehicle driving forward in the same lane is the same as the driving direction of the ego vehicle; if the vehicle driving backward in the same lane, it is different from the driving direction of the ego vehicle; the vehicle in the opposite lane is also different from the driving direction of the ego vehicle.

[0130] The preset fourth longitudinal distance threshold is an empirical value, for example, the preset fourth longitudinal distance threshold is set to 125m. It can better balance the system comfort and safety. If the longitudinal distance value between any candidate vehicle and the ego vehicle is greater than the preset fourth longitudinal distance threshold, the candidate vehicle is excluded.

[0131] Step S203-2, determining the pending tracking target vehicle with the minimum longitudinal distance value as the tracking target vehicle.

[0132] If there are multiple pending tracking target vehicles, the pending tracking target vehicle with the minimum longitudinal distance value is selected as the tracking target vehicle. Thus, one tracking target vehicle is selected for adaptive cruise.

[0133] In the application, all the preset values are empirical values.

[0134] The embodiment of the application selects candidate vehicles of at least one scene type from a plurality of target vehicles in front of the ego vehicle through the ego vehicle driving parameter value and the target driving parameter value of the plurality of target vehicles. When the target driving parameter value of any candidate vehicle satisfies the preset tracking condition, the any candidate vehicle is determined as a tracking target vehicle. The tracking target vehicle is determined through the common ego vehicle driving parameter value and the target driving parameter value, which improves the universality of adaptive cruise, can be applied to multiple scenes and multiple working conditions, improves the balance between comfort and driving safety, saves computing resources and reduces development cost. Multiple means are used to select candidate vehicles of the same scene type, which improves the accuracy of target identification.

[0135] The application also provides a device embodiment for implementing the method steps of the above embodiments, based on the same name meaning explanation as the above embodiments, with the same technical effects as the above embodiments, which will not be repeated here.

[0136] As Figure 3 shown, the application provides a vehicle following target determination device 300, comprising:

[0137] an acquisition unit, configured to acquire a self-vehicle driving parameter value and target driving parameter values of a plurality of target vehicles in front of the self-vehicle;

[0138] a screening unit, configured to screen candidate vehicles of at least one scenario type from the plurality of target vehicles based on the self-vehicle driving parameter value and the target driving parameter values of the plurality of target vehicles;

[0139] a determination unit, configured to determine any candidate vehicle as a tracking target vehicle when the target driving parameter value of the any candidate vehicle meets a preset tracking condition.

[0140] Optionally, the screening of the candidate vehicles of at least one scenario type from the plurality of target vehicles based on the self-vehicle driving parameter value and the target driving parameter values of the plurality of target vehicles comprises:

[0141] when an any target vehicle has an active cut-in identifier, and a lateral distance variation value between the any target vehicle and the self-vehicle is less than zero, and a direction of a lateral speed of the any target vehicle is the same as a preset lateral cut-in direction, determining the any target vehicle as a candidate vehicle of a cut-in type.

[0142] Optionally, the screening of the candidate vehicles of at least one scenario type from the plurality of target vehicles based on the self-vehicle driving parameter value and the target driving parameter values of the plurality of target vehicles comprises:

[0143] when an any target vehicle has a longitudinal distance value less than a preset first longitudinal distance threshold value, or a relative longitudinal speed value between the any target vehicle and the self-vehicle is greater than a preset relative longitudinal speed threshold value, when a lateral speed value of the any target vehicle is greater than a preset lateral speed threshold value, and a lateral distance value between the any target vehicle and the self-vehicle is less than a preset lateral distance threshold value, and an overtaking distance value of the any target vehicle crossing a single lane line is greater than a preset overtaking distance threshold value, determining the any target vehicle as a candidate vehicle of a cut-in type.

[0144] Optionally, the screening of the candidate vehicles of at least one scenario type from the plurality of target vehicles based on the self-vehicle driving parameter value and the target driving parameter values of the plurality of target vehicles comprises:

[0145] When the front vehicle identification of any target vehicle is in an active state, or the home lane probability value of the any target vehicle is greater than a preset home lane probability threshold value, or the target distance value between the any target vehicle and the ego vehicle is less than a preset distance threshold value, when the lane invasion identification of the any target vehicle is in an active state and the lane edge gap value of the ego vehicle is less than a preset lane edge gap threshold value, the any target vehicle is determined as a pending vehicle.

[0146] When the pending vehicle does not satisfy a preset exclusion condition, the pending vehicle is determined as a candidate vehicle of a home lane type.

[0147] Optionally, the preset exclusion condition comprises:

[0148] The preset first exclusion condition comprises that the lane change identification of the pending vehicle is in an active state and the cut-out identification of the pending vehicle is in an active state.

[0149] The preset second exclusion condition comprises that the direction of the lateral speed of the pending vehicle is the same as a preset lateral cut-out direction.

[0150] The preset third exclusion condition comprises that when the ego lane identification of the pending vehicle is in an active state, the motion state identification of the pending vehicle is in an active state, the lane edge gap value of the pending vehicle is greater than a preset lane edge gap threshold value, the road overlap value of the pending vehicle is less than a preset first road overlap threshold value, and the ego overlap value between the ego vehicle and the pending vehicle is less than a preset first vehicle overlap threshold value.

[0151] The preset third exclusion condition comprises that when the ego lane identification of the pending vehicle is in an active state, the motion state identification of the pending vehicle is in a frozen state, the road overlap value of the pending vehicle is less than a preset second road overlap threshold value, the ego overlap value between the ego vehicle and the pending vehicle is less than a preset second vehicle overlap threshold value, the lane change identification of the ego vehicle is in a frozen state, and the lane invasion identification of the ego vehicle is in a frozen state.

[0152] Optionally, the filtering of the candidate vehicle of at least one scene type from the plurality of target vehicles based on the ego driving parameter value and the target driving parameter value of the plurality of target vehicles comprises:

[0153] When any target vehicle is determined as a tracking target vehicle in a previous frame, the lane change identification of the ego vehicle is in a frozen state, and the road overlap value of the any target vehicle is greater than a preset first road overlap threshold value, the any target vehicle is determined as a candidate vehicle of a separate road overlap type.

[0154] Optionally, the filtering of the candidate vehicles of at least one scene type from the plurality of target vehicles based on the ego vehicle driving parameter value and the target driving parameter values of the plurality of target vehicles comprises:

[0155] When the longitudinal distance value between any target vehicle and the ego vehicle is less than a preset second longitudinal distance threshold, the road overlap value is greater than a preset second road overlap threshold, and the lane-keeping identifier of the ego vehicle is in the active state, the any target vehicle is determined as a candidate vehicle of the separate road overlap type.

[0156] Optionally, the filtering of the candidate vehicles of at least one scene type from the plurality of target vehicles based on the ego vehicle driving parameter value and the target driving parameter values of the plurality of target vehicles comprises:

[0157] When the longitudinal distance value between any target vehicle and the ego vehicle is less than a preset third longitudinal distance threshold, the information identifier of the any target vehicle is determined as the tracking target vehicle in the previous frame, and the ego vehicle overlap value of the any target vehicle is greater than a preset ego vehicle overlap threshold, the any target vehicle is determined as a candidate vehicle of the separate ego vehicle overlap type.

[0158] Optionally, the determining of the any candidate vehicle as the tracking target vehicle when the target driving parameter value of the any candidate vehicle meets a preset tracking condition comprises:

[0159] When the vehicle type of any candidate vehicle meets one of a plurality of preset vehicle types, the driving direction of the any candidate vehicle is the same as the driving direction of the ego vehicle, and the longitudinal distance value between the any candidate vehicle and the ego vehicle is less than or equal to a preset fourth longitudinal distance threshold, the any candidate vehicle is determined as the pending tracking target vehicle;

[0160] The pending tracking target vehicle with the minimum longitudinal distance value from the ego vehicle is determined as the tracking target vehicle.

[0161] The embodiments of the present application filter the candidate vehicles of at least one scene type from the plurality of target vehicles in front of the ego vehicle based on the ego vehicle driving parameter value and the target driving parameter values of the plurality of target vehicles; and determine the any candidate vehicle as the tracking target vehicle when the target driving parameter value of the any candidate vehicle meets a preset tracking condition. The tracking target vehicle is determined based on the common ego vehicle driving parameter value and the target driving parameter value, which improves the commonality of the adaptive cruise, is applicable to multiple scenes and multiple working conditions, improves the balance between comfort and driving safety, saves the computing resources, and reduces the development cost. The same scene type of candidate vehicles is filtered by multiple means, which improves the accuracy of target identification.

[0162] Embodiment 3

[0163] The embodiment provides an electronic device, the electronic device comprises at least one processor and a memory connected with the at least one processor; wherein the memory stores instructions executable by the one processor; the instructions are executed by the at least one processor to enable the at least one processor to perform the method steps as described in the above embodiment.

[0164] Embodiment 4

[0165] The embodiment of the present application provides a non-volatile computer storage medium, the computer storage medium stores computer executable instructions, and the computer executable instructions can execute the method steps as described in the above embodiment.

[0166] Finally, it should be noted that: the embodiments in the specification are described in a progressive manner, and each embodiment focuses on the difference from other embodiments, and the same or similar parts of each embodiment can be referred to. For the system or device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the related parts are described in the method part.

[0167] The above embodiments are only used to illustrate the technical solutions of the present application, but not limit the present application; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that the technical solutions recorded in the foregoing embodiments can be modified, or some technical features can be replaced by equivalents; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method of determining a following target, characterized by, The method comprises: obtaining a self-vehicle driving parameter value and target driving parameter values of a plurality of target vehicles in front of the self-vehicle; screening candidate vehicles of at least one scenario type from the plurality of target vehicles based on the self-vehicle driving parameter value and the target driving parameter values of the plurality of target vehicles; when the target driving parameter value of any candidate vehicle meets a preset tracking condition, determining the any candidate vehicle as a tracking target vehicle; wherein the screening of the candidate vehicles of at least one scenario type from the plurality of target vehicles based on the self-vehicle driving parameter value and the target driving parameter values of the plurality of target vehicles comprises: when a front vehicle identifier of any target vehicle is in an active state, or a belonging-to-self-lane probability value of the any target vehicle is greater than a preset belonging-to-self-lane probability threshold value, or a target distance value between the any target vehicle and the self-vehicle is less than a preset distance threshold value, when an encroaching line identifier of the any target vehicle is in an active state and a side line gap value of the self-vehicle is less than a preset side line gap threshold value, determining the any target vehicle as a pending vehicle; when the pending vehicle does not meet a preset exclusion condition, determining the pending vehicle as a candidate vehicle of a belonging-to-self-lane type; the preset exclusion condition comprises: a preset first exclusion condition comprises that a lane changing identifier of the pending vehicle is in an active state and a cut-out identifier of the pending vehicle is in an active state; a preset second exclusion condition comprises that a direction of a lateral speed of the pending vehicle is the same as a preset lateral cut-out direction; a preset third exclusion condition comprises that when a self-vehicle lane identifier of the pending vehicle is in an active state, a motion state identifier of the pending vehicle is in an active state, a side line gap value of the pending vehicle is greater than a preset side line gap threshold value, a road overlap value of the pending vehicle is less than a preset first road overlap threshold value, and a self-vehicle overlap value between the self-vehicle and the pending vehicle is less than a preset first vehicle overlap threshold value; a preset fourth exclusion condition comprises that when the self-vehicle lane identifier of the pending vehicle is in an active state, the motion state identifier of the pending vehicle is in a frozen state, the road overlap value of the pending vehicle is less than a preset second road overlap threshold value, the self-vehicle overlap value between the self-vehicle and the pending vehicle is less than a preset second vehicle overlap threshold value, a lane changing identifier of the self-vehicle is in a frozen state, and a pressure line identifier of the self-vehicle is in a frozen state.

2. The method of claim 1, wherein, the screening of the candidate vehicles of at least one scenario type from the plurality of target vehicles based on the self-vehicle driving parameter value and the target driving parameter values of the plurality of target vehicles comprises: when a cut-in identifier of any target vehicle is in an active state, a lateral distance change value between the any target vehicle and the self-vehicle is less than zero, and a direction of a lateral speed of the any target vehicle is the same as a preset lateral cut-in direction, determining the any target vehicle as a cut-in type candidate vehicle.

3. The method of claim 1, wherein, the screening of the candidate vehicles of at least one scenario type from the plurality of target vehicles based on the self-vehicle driving parameter value and the target driving parameter values of the plurality of target vehicles comprises: When the longitudinal distance value between any target vehicle and the ego vehicle is less than a preset first longitudinal distance threshold, or the relative longitudinal speed value between the any target vehicle and the ego vehicle is greater than a preset relative longitudinal speed threshold, when the lateral speed value of the any target vehicle is greater than a preset lateral speed threshold, and the lateral distance value between the any target vehicle and the ego vehicle is less than a preset lateral distance threshold, and the overtaking distance value of the any target vehicle beyond the single-side lane line is greater than a preset overtaking distance threshold, the any target vehicle is determined as a candidate vehicle of the cut-in type.

4. The method of claim 1, wherein, The filtering of the candidate vehicles of at least one scene type from the multiple target vehicles based on the ego vehicle driving parameter value and the target driving parameter values of the multiple target vehicles comprises: When any target vehicle is determined as the information identifier of the tracked target vehicle in the previous frame, and the lane change identifier of the ego vehicle is in the frozen state, and the road overlap value of the any target vehicle is greater than a preset first road overlap threshold, the any target vehicle is determined as a candidate vehicle of the single road overlap type.

5. The method of claim 1, wherein, The filtering of the candidate vehicles of at least one scene type from the multiple target vehicles based on the ego vehicle driving parameter value and the target driving parameter values of the multiple target vehicles comprises: When the longitudinal distance value between any target vehicle and the ego vehicle is less than a preset second longitudinal distance threshold, and the road overlap value is greater than a preset second road overlap threshold, and the line pressure identifier of the ego vehicle is in the active state, the any target vehicle is determined as a candidate vehicle of the single road overlap type.

6. The method of claim 1, wherein, The filtering of the candidate vehicles of at least one scene type from the multiple target vehicles based on the ego vehicle driving parameter value and the target driving parameter values of the multiple target vehicles comprises: When the longitudinal distance value between any target vehicle and the ego vehicle is less than a preset third longitudinal distance threshold, and the any target vehicle is determined as the information identifier of the tracked target vehicle in the previous frame, and the ego vehicle overlap value of the any target vehicle is greater than a preset ego vehicle overlap threshold, the any target vehicle is determined as a candidate vehicle of the single ego vehicle overlap type.

7. The method of claim 1, wherein, The determination of the any candidate vehicle as the tracked target vehicle when the target driving parameter value of the any candidate vehicle meets the preset tracking condition comprises: When the vehicle type of any candidate vehicle meets one of the multiple preset vehicle types, and the driving direction of the any candidate vehicle is the same as the driving direction of the ego vehicle, and the longitudinal distance value between the any candidate vehicle and the ego vehicle is less than or equal to a preset fourth longitudinal distance threshold, the any candidate vehicle is determined as the pending tracked target vehicle; The pending tracked target vehicle with the minimum longitudinal distance value from the ego vehicle is determined as the tracked target vehicle.

8. A device for determining a following target, characterized in that The method comprises: an acquisition unit configured to acquire an ego vehicle driving parameter value and target driving parameter values of multiple target vehicles in front of the ego vehicle; a filtering unit configured to filter candidate vehicles of at least one scene type from the multiple target vehicles based on the ego vehicle driving parameter value and the target driving parameter values of the multiple target vehicles; a determination unit configured to determine any candidate vehicle as a tracked target vehicle when the target driving parameter value of the any candidate vehicle meets a preset tracking condition. The filtering of the candidate vehicles of at least one scene type from the plurality of target vehicles based on the self-vehicle driving parameter value and the target driving parameter value of the plurality of target vehicles comprises: When the front vehicle identifier of any target vehicle is in an active state, or the home lane probability value of the any target vehicle is greater than a preset home lane probability threshold value, or the target distance value between the any target vehicle and the ego vehicle is less than a preset distance threshold value, when the lane invasion identifier of the any target vehicle is in an active state and the lane edge gap value of the ego vehicle is less than a preset lane edge gap threshold value, the any target vehicle is determined as a pending vehicle; When the pending vehicle does not satisfy a preset exclusion condition, the pending vehicle is determined as a candidate vehicle of the home lane type; The preset exclusion condition comprises: The preset first exclusion condition comprises that the lane change identifier of the pending vehicle is in an active state and the cut-out identifier of the pending vehicle is in an active state; The preset second exclusion condition comprises that the direction of the lateral speed of the pending vehicle is the same as a preset lateral cut-out direction; The preset third exclusion condition comprises that when the ego lane identifier of the pending vehicle is in an active state, the motion state identifier of the pending vehicle is in an active state, the lane edge gap value of the pending vehicle is greater than a preset lane edge gap threshold value, the road overlap value of the pending vehicle is less than a preset first road overlap threshold value, and the ego overlap value between the ego vehicle and the pending vehicle is less than a preset first vehicle overlap threshold value; The preset fourth exclusion condition comprises that when the ego lane identifier of the pending vehicle is in an active state, the motion state identifier of the pending vehicle is in a frozen state, the road overlap value of the pending vehicle is less than a preset second road overlap threshold value, the ego overlap value between the ego vehicle and the pending vehicle is less than a preset second vehicle overlap threshold value, the lane change identifier of the ego vehicle is in a frozen state, and the lane invasion identifier of the ego vehicle is in a frozen state.

Images