An ACC following target determination method, system, device and vehicle

Abstract

The application discloses an ACC following vehicle target determination method, system, device and vehicle, comprising: detecting a candidate following vehicle target in front of a current vehicle, and obtaining vehicle information of the candidate following vehicle target; obtaining a corresponding first overlap value and road gap information based on a current vehicle width, a first distance and the vehicle information, wherein the first distance is a lateral distance between the current vehicle and a lane line where the current vehicle is located; obtaining a corresponding second overlap value based on the current vehicle width, a second distance and the vehicle information, wherein the second distance is a lateral distance between the current vehicle and the candidate following vehicle target; inputting the first overlap value, the road gap information and the second overlap value into a target screening model, and determining a following vehicle target. The application can accurately determine an ACC following vehicle target, and improve the riding experience of users.

Description

Technical Field

[0001] The present application relates to the field of intelligent driving, and in particular to an ACC following vehicle target determination method, system, device and vehicle. Background Art

[0002] Adaptive Cruise Control (ACC) is an intelligent driver assistance tool that dynamically adjusts vehicle speed based on the driver's preset speed and desired following distance. Utilizing the vehicle's cameras or radar, the ACC system accurately identifies road markings such as lane markings, as well as obstacles such as moving vehicles and pedestrians, and then determines whether there are vehicles ahead in the current lane. Once a vehicle is detected ahead, the ACC system automatically guides the vehicle to follow, maintaining a safe and reliable distance based on a preset time interval. Therefore, accurately identifying the appropriate vehicle to follow is crucial in the ACC system.

[0003] In the existing technology, the ACC system usually relies on the presence of a vehicle traveling directly in the lane ahead as the basis for selecting the vehicle to follow. It fails to fully explore and utilize lane line information, status data of other vehicles, and the vehicle's own status data. As a result, ACC may improperly select the vehicle to follow, thereby affecting the user's riding comfort.

[0004] Application Contents

[0005] The present application provides an ACC following target determination method, system, device and vehicle to accurately determine the ACC following target and improve the user's riding experience.

[0006] In a first aspect, the present application provides an ACC following vehicle target determination method, comprising:

[0007] Detecting a candidate vehicle target ahead of the current vehicle and obtaining vehicle information of the candidate vehicle target;

[0008] Obtaining a corresponding first overlap value and road clearance information based on the current vehicle width, the first distance, and the vehicle information, wherein the first distance is a lateral distance between the current vehicle and a lane line where the current vehicle is located;

[0009] Obtaining a corresponding second overlap value based on the current vehicle width, a second distance, and the vehicle information, wherein the second distance is a lateral distance between the current vehicle and the candidate following target;

[0010] The first overlap value, the road gap information, and the second overlap value are input into a target screening model to determine a vehicle-following target.

[0011] By detecting the candidate following target in front of the current vehicle, the embodiment of the present application can accurately obtain the vehicle information of the candidate following target, facilitating the subsequent calculation of the first overlap value, road gap information, and second overlap value. Based on the current vehicle width, the first distance, and the vehicle information, the overlap between the candidate following target and the lane line, as well as the road gap information between the current vehicle and the lane line, can be accurately determined, facilitating the subsequent determination of the following target. Based on the current vehicle width, the second distance, and the vehicle information, the overlap between the current vehicle and the candidate following target can be accurately determined, facilitating the subsequent determination of the following target. By inputting the first overlap value, the road gap information, and the second overlap value into the target screening model, the following target can be accurately determined by comprehensively considering the overlap between the candidate following target and the lane line, the road gap information between the current vehicle and the lane line, and the overlap between the current vehicle and the candidate following target. Compared with the prior art, the present application can accurately determine the ACC following target, improving the user's riding experience.

[0012] Furthermore, the detecting of the candidate following target ahead of the current vehicle and obtaining the vehicle information of the candidate following target is specifically as follows:

[0013] Detecting a candidate vehicle target ahead of the current vehicle and obtaining initial vehicle information of the candidate vehicle target;

[0014] Perform Kalman filtering on the initial vehicle information to obtain vehicle information of the candidate vehicle-following target.

[0015] In this way, by performing Kalman filtering on the initial vehicle information of the candidate vehicle-following target, noise information in the initial vehicle information can be removed, thereby obtaining effective information for the target screening model to perform vehicle-following determination.

[0016] Furthermore, the initial vehicle information is subjected to Kalman filtering to obtain the vehicle information of the candidate following target, specifically:

[0017] Constructing a corresponding first state vector and a first state covariance matrix based on the initial vehicle information;

[0018] Determine a Kalman gain matrix based on the first state vector and the first state covariance matrix, and obtain a second state vector and a second state covariance matrix based on the Kalman gain matrix;

[0019] Based on the second state vector and the second state covariance matrix, vehicle information of the candidate following target is determined.

[0020] In this way, by performing Kalman filtering on the initial vehicle information of the candidate vehicle-following target, noise information in the initial vehicle information can be removed, thereby obtaining effective information for the target screening model to perform vehicle-following determination.

[0021] Furthermore, the first overlap value and road clearance information corresponding to the vehicle are obtained based on the current vehicle width, the first distance, and the vehicle information, specifically:

[0022] Obtaining four relative distances between four corner points of the candidate following target and the current vehicle based on the current vehicle width, the first distance, and the vehicle information;

[0023] Determine a relative distance maximum and a relative distance minimum based on the four relative distances;

[0024] The maximum relative distance value is compared with the current vehicle width, and the minimum relative distance value is compared with the current vehicle width to obtain comparison results, and corresponding first overlap values ​​and road gap information are determined based on the comparison results.

[0025] In this way, based on the current vehicle width, the first distance and the vehicle information, the overlap between the candidate following target and the lane line, as well as the road gap information between the current vehicle and the lane line can be accurately grasped, which facilitates the determination of subsequent following targets.

[0026] Furthermore, the determining of the corresponding first overlap value and road gap information based on the comparison result is specifically as follows:

[0027] If the maximum relative distance is less than half the width of the current vehicle, or the minimum relative distance is greater than half the width of the current vehicle, then there is no overlapping area. If the candidate following target is located on the left side of the current vehicle, then the first overlap value is the sum of the maximum relative distance and half the width of the current vehicle. If the candidate following target is located on the right side of the current vehicle, then the first overlap value is the difference between half the width of the current vehicle and the minimum relative distance.

[0028] If the maximum relative distance is greater than or equal to half the current vehicle width, and the minimum relative distance is less than or equal to half the current vehicle width, then the first overlap value is equal to the current vehicle width, and the road clearance information is the maximum lateral distance between the current vehicle and the lane markings on both sides;

[0029] If the minimum relative distance value is greater than half the current vehicle width, the first overlap value is the difference between half the current vehicle width and the minimum relative distance value, and the road clearance information is the distance between the current vehicle and the left lane line minus the minimum relative distance value;

[0030] If the minimum relative distance is less than half the current vehicle width, the first overlap value is the sum of half the current vehicle width and the maximum relative distance, and the road gap information is the distance between the current vehicle and the right lane line minus the maximum relative distance.

[0031] In this way, by comparing the maximum relative distance with the current vehicle width and the minimum relative distance with the current vehicle width, we can accurately grasp the overlap between the candidate following targets and the lane lines in different situations and the road gap information between the current vehicle and the lane lines, which facilitates the determination of subsequent following targets.

[0032] Furthermore, the first overlap value, the road gap information, and the second overlap value are input into a target screening model to determine a vehicle-following target, specifically:

[0033] determining whether the road gap information exceeds a preset gap threshold, and if the road gap information exceeds the preset gap threshold, determining whether risk-free overtaking is possible or whether following is required based on the first overlap value and the second overlap value;

[0034] If both the first overlap value and the second overlap value are smaller than a preset overlap threshold, controlling the current vehicle to perform risk-free overtaking;

[0035] If both the first overlap value and the second overlap value are greater than a preset overlap threshold, the candidate vehicle-following target is taken as the vehicle-following target and the vehicle is followed.

[0036] In this way, by inputting the first overlap value, the road gap information and the second overlap value into the target screening model, the following target can be accurately determined by comprehensively considering the overlap between the candidate following target and the lane line, the road gap information between the current vehicle and the lane line, and the overlap between the current vehicle and the candidate following target.

[0037] Furthermore, the candidate vehicle-following target is used as the vehicle-following target and the vehicle-following is specifically performed as follows:

[0038] When there are several following targets, the following target with the largest second overlap value is followed.

[0039] In this way, by comparing the overlap values ​​between the current vehicle and the candidate following targets and following the following target with the largest second overlap value, the accuracy of the following target can be guaranteed.

[0040] In a second aspect, the present application provides an ACC vehicle following target determination system, comprising: an acquisition module, a first calculation module, a second calculation module, and a determination module;

[0041] The acquisition module is used to detect a candidate vehicle-following target in front of the current vehicle and obtain vehicle information of the candidate vehicle-following target;

[0042] The first calculation module is configured to obtain a corresponding first overlap value and road gap information based on a current vehicle width, a first distance, and the vehicle information, wherein the first distance is a lateral distance between the current vehicle and a lane line where the current vehicle is located;

[0043] The second calculation module is configured to obtain a corresponding second overlap value based on the current vehicle width, a second distance, and the vehicle information, wherein the second distance is a lateral distance between the current vehicle and the candidate following target;

[0044] The determination module is configured to input the first overlap value, the road gap information, and the second overlap value into a target screening model to determine a following target.

[0045] By detecting the candidate following target in front of the current vehicle, the embodiment of the present application can accurately obtain the vehicle information of the candidate following target, facilitating the subsequent calculation of the first overlap value, road gap information, and second overlap value. Based on the current vehicle width, the first distance, and the vehicle information, the overlap between the candidate following target and the lane line, as well as the road gap information between the current vehicle and the lane line, can be accurately determined, facilitating the subsequent determination of the following target. Based on the current vehicle width, the second distance, and the vehicle information, the overlap between the current vehicle and the candidate following target can be accurately determined, facilitating the subsequent determination of the following target. By inputting the first overlap value, the road gap information, and the second overlap value into the target screening model, the following target can be accurately determined by comprehensively considering the overlap between the candidate following target and the lane line, the road gap information between the current vehicle and the lane line, and the overlap between the current vehicle and the candidate following target. Compared with the prior art, the present application can accurately determine the ACC following target, improving the user's riding experience.

[0046] In a third aspect, the present application also provides an electronic device comprising a processor and a memory, wherein the memory stores programs or instructions that can be run on the processor, and when the programs or instructions are executed by the processor, the steps of the ACC following target determination method as described in the present application are implemented.

[0047] In a fourth aspect, the present application also provides a vehicle, which is configured to execute the ACC following target determination method as described in the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 This is a flowchart of an embodiment of an ACC vehicle following target determination method provided by the present application;

[0049] Figure 2 is a schematic diagram of a first overlap value determination process provided by the present application;

[0050] Figure 3 is a schematic diagram of the road clearance information determination process provided by this application;

[0051] Figure 4 This is a schematic structural diagram of an embodiment of an ACC vehicle following target determination system provided by the present application;

[0052] Figure 5 This is a hardware structure diagram of the electronic device provided in this application. DETAILED DESCRIPTION

[0053] The following will be combined with the accompanying drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making any creative efforts are within the scope of protection of this application.

[0054] It should be understood that the step numbers used herein are only for convenience of description and are not intended to limit the order in which the steps are executed.

[0055] It should be understood that the terms used in the present specification are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the present specification and the appended claims, the singular forms "a", "an" and "the" are intended to include the plural forms unless the context clearly indicates otherwise.

[0056] The terms “include” and “comprising” indicate the presence of described features, integers, steps, operations, elements and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof.

[0057] The term "and / or" refers to and includes any and all possible combinations of one or more of the associated listed items.

[0058] ACC (Adaptive Cruise Control) is an intelligent driver assistance tool that dynamically adjusts vehicle speed based on the speed and distance set by the driver. This system uses cameras or radar to identify road signs and obstacles, detect the vehicle ahead, and automatically follow it while maintaining a safe distance. Therefore, accurately determining the appropriate vehicle to follow is crucial in ACC systems. Existing technologies rely on the presence of a vehicle directly in the lane ahead as the basis for selecting a vehicle to follow. This fails to fully utilize lane markings, other vehicles, and the vehicle's own data, which can lead to inappropriate following and compromise ride comfort.

[0059] Next, the nouns involved in this application are analyzed:

[0060] Adaptive Cruise Control (ACC), also known as Intelligent Cruise Control (ACC), is a next-generation driver-assistance system developed based on traditional cruise control. The greatest advantage of ACC is that it not only maintains the driver's pre-set speed but also reduces speed and even automatically brakes as needed under specific driving conditions.

[0061] Kalman filtering is an efficient data processing technology that uses linear system state equations to optimally estimate the system state through system input and output observation data.

[0062] Based on this, embodiments of the present application provide an ACC following target determination method, system, device, and vehicle, which can accurately determine the ACC following target and enhance the user's riding experience. The basic principle is to process noisy input and observation signals based on a linear state space representation to obtain an optimal estimate of the system state or true signal. This optimal estimate can be viewed as a filtering process, removing noise to restore the true data.

[0063] An ACC following target determination method, system, device and vehicle provided in the embodiments of the present application are specifically illustrated through the following embodiments. First, an ACC following target determination method in the embodiments of the present application is described.

[0064] An ACC vehicle following target determination method provided in an embodiment of the present application relates to the field of intelligent driving. An ACC vehicle following target determination method provided in an embodiment of the present application can be applied to a terminal, can be applied to a server side, or can be software running in a terminal or a server side. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc.; the server side can be configured as an independent physical server, or as a server cluster or distributed system composed of multiple physical servers, or as a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms; the software can be an application that implements an ACC vehicle following target determination method, etc., but is not limited to the above forms.

[0065] The present application can also be used in numerous general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, and the like. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, and the like that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments in which tasks are performed by remote processing devices connected via a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0066] Example 1

[0067] Please refer to Figure 1 , Figure 1 This is a flowchart of an embodiment of an ACC following vehicle target determination method provided by the present application, including steps S101 to S104;

[0068] Step S101, detecting a candidate vehicle target ahead of the current vehicle and obtaining vehicle information of the candidate vehicle target;

[0069] It is understood that the vehicle is the primary execution structure of the ACC following target determination method provided in this application. The vehicle may be equipped with autonomous driving or related technologies. After executing the ACC following target determination method provided in any embodiment of this application, the vehicle may perform subsequent planning (such as speed planning, path planning, etc.) based on the determined following target. For the convenience of subsequent description, the vehicle executing this method will be referred to as the current vehicle.

[0070] It is understandable that the candidate vehicle-following target is a vehicle that may serve as a vehicle-following target (such as the preceding vehicle).

[0071] It can be understood that vehicle information may refer to driving information that can reflect the candidate following target and the vehicle's own information, wherein the driving information may include the speed, heading angle, position, steering angle, etc. of the candidate following target, and the vehicle's own information may be but is not limited to the vehicle width, vehicle length, etc. of the candidate following target.

[0072] In some embodiments, when executing the aforementioned step S101, the following steps include: detecting a candidate vehicle-following target ahead of the current vehicle to obtain initial vehicle information of the candidate vehicle-following target; and performing Kalman filtering on the initial vehicle information to obtain vehicle information of the candidate vehicle-following target. Specifically, the initial vehicle information may be first obtained through onboard sensors, wherein the initial vehicle information includes, but is not limited to, road lane lines, driving information, and vehicle information. After obtaining the initial vehicle information of the candidate vehicle-following target, the initial vehicle information may be subjected to Kalman filtering to remove noise from the initial vehicle information, thereby obtaining the vehicle information of the candidate vehicle-following target.

[0073] In some embodiments, the initial vehicle information is subjected to Kalman filtering to obtain the vehicle information of the candidate vehicle-following target, including: constructing a corresponding first state vector and a first state covariance matrix based on the initial vehicle information; determining a Kalman gain matrix based on the first state vector and the first state covariance matrix, and obtaining a second state vector and a second state covariance matrix based on the Kalman gain matrix; determining the vehicle information of the candidate vehicle-following target based on the second state vector and the second state covariance matrix. Specifically, first, construct a first state vector X and a corresponding first state covariance matrix P based on the initial vehicle information to represent the covariance between the components in the first state vector X; second, define a control vector u k , process noise matrix Q, where the control vector includes control variables such as the vehicle speed and the lateral and longitudinal speeds of the candidate following target, and the first state vector X is transferred and discretized to obtain the first matrix A and the second matrix B, and the prediction formula is used to calculate the Kalman gain matrix K of the first state vector X at the current moment; then, the Kalman gain matrix K is used to update the state vector and covariance matrix through the update formula to obtain the second state vector and the second state covariance matrix Finally, based on the second state vector and the second state covariance matrix Determine vehicle information of the candidate vehicle-following target.

[0074] The Kalman filter prediction formula is specifically:

[0075]

[0076] Where, and are the first state vectors at time k and time k-1 respectively; A and B are the first matrix and the second matrix respectively; u k is the control variable; is the covariance matrix of the first state vector at time k; T represents transpose; Q is the process noise matrix, which is constructed by summarizing the weight coefficients based on the actual vehicle test data, where Q = E[w*w], where E[] is the expected calculation and w is the process noise vector, which is obtained by multiplying and summing each sub-coefficient with each component of the state vector x; K k is the Kalman gain matrix at time k; H is the observation transfer matrix; R is the observation noise, given by the sensor.

[0077] The Kalman filter update formula is specifically:

[0078]

[0079] Where, is the second state vector at time k, that is, the optimal estimate of the state vector; is the second state covariance matrix at time k, that is, the optimal estimate of the covariance matrix; is the first state vector at time k; H is the observation transfer matrix; K k is the Kalman gain matrix at time k; is the covariance matrix of the first state vector at time k; y k are the observed variable values; I is the identity matrix.

[0080] It should be noted that the first matrix A and the second matrix B are both obtained by using the discretization method of the differential equation dX / dt=f(X,u), where X is the first state vector and the specific values ​​of A and B are given according to the actual vehicle calibration.

[0081] It should be noted that the vehicle-mounted sensors include but are not limited to cameras, radars, LiDAR and other sensors on the vehicle.

[0082] In this way, by performing Kalman filtering on the initial vehicle information of the candidate vehicle-following target, noise information in the initial vehicle information can be removed, thereby obtaining effective information for the target screening model to perform vehicle-following determination.

[0083] Step S102, obtaining a corresponding first overlap value and road clearance information based on the current vehicle width, a first distance, and the vehicle information, wherein the first distance is a lateral distance between the current vehicle and the lane line where the current vehicle is located;

[0084] It is understandable that after obtaining the vehicle information, it is also necessary to obtain the current vehicle width W. At the same time, the center of the vehicle is set as the origin of the coordinate system, and the lateral distance between the current vehicle and the lane line where the current vehicle is located is determined according to the rule of negative on the left and positive on the right, that is, the first distance a. The schematic diagram of the first overlap value determination process is shown as follows: Figure 2 shown.

[0085] In some embodiments, when executing the aforementioned step S102, it includes: obtaining four relative distances between the four corner points of the candidate following target and the current vehicle based on the current vehicle width, the first distance and the vehicle information; determining a relative distance maximum and a relative distance minimum based on the four relative distances; comparing the relative distance maximum with the current vehicle width and the relative distance minimum with the current vehicle width, respectively, to obtain comparison results, and determining corresponding first overlap values ​​and road gap information based on the comparison results. Specifically, first, the candidate following target has four corner points, marked as corner point 1, corner point 2, corner point 3 and corner point 4, and the relative distances between the four corner points and the center of the current vehicle are calculated, where the relative distance of corner point 1 is: a+l*sin(θ)+(-0.5*W_obj)*cos(θ); the relative distance of corner point 2 is: a+l*sin(θ)+0.5*W_obj*cos(θ); the relative distance of corner point 3 is: a+(-0.5*W_obj)*cos(θ); the relative distance of corner point 4 is: a+0.5*W_o bj*cos(θ), where a is the first distance, θ is the heading angle, and W_obj is the candidate following target width. Then, by comparing the four relative distances, the relative distance maximum d_max and relative distance minimum d_min, i.e., corner point 4 and corner point 1, are found. Finally, the relative distance maximum d_max is compared with the current vehicle width W, and the relative distance minimum d_min is compared with the current vehicle width W to obtain comparison results. Based on the comparison results, the corresponding first overlap value and road gap information are determined.

[0086] In some embodiments, the corresponding first overlap value and road gap information are determined based on the comparison result, including: if the maximum relative distance d_max is less than half the current vehicle width W, or the minimum relative distance d_min is greater than half the current vehicle width W, then there is no overlapping area; if the candidate following target is located on the left side of the current vehicle, then the first overlap value is the sum of the maximum relative distance d_max and half the current vehicle width W; if the candidate following target is located on the right side of the current vehicle, then the first overlap value is the difference between half the current vehicle width W and the minimum relative distance d_min. That is, if d_max<-W / 2 or d_min>W / 2, it means that the candidate following target has not entered the lane of the current vehicle and there is no overlapping area. At this time, if the candidate following target is located on the left side of the current vehicle, the first overlap value is overlap_r=d_max+W / 2; if the candidate following target is located on the right side of the current vehicle, the first overlap value is overlap_h=W / 2-d_min, and there is no road gap.

[0087] In some embodiments, the corresponding first overlap value and road gap information are determined based on the comparison result, including: if the relative distance maximum value d_max is greater than or equal to half of the current vehicle width W, and the relative distance minimum value d_min is less than or equal to half of the current vehicle width W, then the first overlap value is equal to the current vehicle width W, and the road gap information is the maximum lateral distance between the current vehicle and the lane lines on both sides, that is, d_min<=-W / 2and d_max>W / 2, then it means that the candidate following target has completely entered the lane of the current vehicle and is considered to be completely overlapped, then the first overlap value is overlap_r=W. At this time, since the candidate following target has completely entered the lane of the current vehicle, there are gaps on both sides. The schematic diagram of the road gap information determination process is shown as follows: Figure 3 As shown in the figure, it can be seen that the maximum gap information between the left and right sides can be used as the road clearance information, that is, lat_clearance = max(max(lat_clearance_left,0),max(lat_clearance_right,0)), where lat_clearance_left is the road clearance on the left and lat_clearance_right is the road clearance on the right.

[0088] In some embodiments, determining corresponding first overlap values and road clearance information based on the comparison results includes: when the minimum relative distance d_min is greater than half of the current vehicle width W, the first overlap value is the difference between half of the current vehicle width W and the minimum relative distance, and the road clearance information is the distance between the current vehicle and the left lane line minus the minimum relative distance; that is, when d_min > -W / 2, it indicates that the candidate following vehicle target invades the current vehicle's lane from the right. Therefore, the first overlap value is overlap_r = W / 2 - d_min, and at this time, the road clearance information, the lateral distance to the left lane line, is also lat_clearance = offset_l - d_min.

[0089] In some embodiments, determining corresponding first overlap values and road clearance information based on the comparison results includes: when the minimum relative distance d_min is less than half of the current vehicle width W, the first overlap value is the sum of half of the current vehicle width W and the maximum relative distance, and the road clearance information is the distance between the current vehicle and the right lane line minus the maximum relative distance; that is, when d_min < W / 2, it indicates that the candidate following vehicle target invades the current vehicle's lane from the left. The first overlap value is overlap_r = W / 2 + d_max, and at this time, the road clearance information, the lateral distance to the right lane line, is also lat_clearance = offset_r - d_max.

[0090] In this way, by comparing the maximum relative distance with the current vehicle width and the minimum relative distance with the current vehicle width, the overlap situation between the candidate following vehicle target and the lane line and the road clearance information between the current vehicle and the lane line in different situations can be accurately grasped, facilitating the determination of the following vehicle target subsequently.

[0091] Step S103: Obtain corresponding second overlap values based on the current vehicle width, the second distance, and the vehicle information, where the second distance is the lateral distance between the current vehicle and the candidate following vehicle target.

[0092] It can be understood that the center of the host vehicle needs to be set as the origin of the coordinate system, and the lateral distance between the current vehicle and the candidate following vehicle target, that is, the second distance b, is determined following the rule of negative on the left and positive on the right. Then, based on the current vehicle width W, the second distance b, and the vehicle information, the second overlap value overlap_h is calculated according to a method similar to that in step S102. Since step S102 has been elaborated in detail, it will not be repeated here.

[0093] Step S104: input the first overlap value, the road gap information, and the second overlap value into a target screening model to determine a following target.

[0094] It can be understood that after obtaining the first overlap value overlap_r, the road gap information lat_clearance and the second overlap value overlap_h, it is necessary to determine whether the road gap information lat_clearance exceeds the preset gap threshold. If the road gap information exceeds the preset gap threshold, then based on the first overlap value overlap_r and the second overlap value overlap_h, it is determined whether risk-free overtaking is possible or whether following is required; if the first overlap value overlap_r and the second overlap value overlap_h are both less than the preset overlap threshold, the current vehicle is controlled to perform risk-free overtaking; if the first overlap value overlap_r and the second overlap value overlap_h are both greater than the preset overlap threshold, the candidate following target is used as the following target and following is performed.

[0095] It should be noted that both the preset gap threshold and the preset overlap threshold can be set freely.

[0096] In this way, by inputting the first overlap value, the road gap information and the second overlap value into the target screening model, the following target can be accurately determined by comprehensively considering the overlap between the candidate following target and the lane line, the road gap information between the current vehicle and the lane line, and the overlap between the current vehicle and the candidate following target.

[0097] In some embodiments, taking the candidate following target as the following target and following the target includes: when there are multiple following targets, following the following target with the largest second overlap value overlap_h.

[0098] In this way, by comparing the overlap values ​​between the current vehicle and the candidate following targets and following the following target with the largest second overlap value, the accuracy of the following target can be guaranteed.

[0099] By detecting the candidate following target in front of the current vehicle, the embodiment of the present application can accurately obtain the vehicle information of the candidate following target, facilitating the subsequent calculation of the first overlap value, road gap information, and second overlap value. Based on the current vehicle width, the first distance, and the vehicle information, the overlap between the candidate following target and the lane line, as well as the road gap information between the current vehicle and the lane line, can be accurately determined, facilitating the subsequent determination of the following target. Based on the current vehicle width, the second distance, and the vehicle information, the overlap between the current vehicle and the candidate following target can be accurately determined, facilitating the subsequent determination of the following target. By inputting the first overlap value, the road gap information, and the second overlap value into the target screening model, the following target can be accurately determined by comprehensively considering the overlap between the candidate following target and the lane line, the road gap information between the current vehicle and the lane line, and the overlap between the current vehicle and the candidate following target. Compared with the prior art, the present application can accurately determine the ACC following target, improving the user's riding experience.

[0100] Example 2

[0101] Please refer to Figure 4 , Figure 4 This is a structural diagram of an embodiment of an ACC vehicle following target determination system provided by the present application; it includes: an acquisition module 100, a first calculation module 200, a second calculation module 300 and a determination module 500;

[0102] The acquisition module 100 is used to detect a candidate vehicle-following target in front of the current vehicle and obtain vehicle information of the candidate vehicle-following target;

[0103] The first calculation module 200 is configured to obtain a corresponding first overlap value and road gap information based on a current vehicle width, a first distance, and the vehicle information, wherein the first distance is a lateral distance between the current vehicle and a lane line where the current vehicle is located;

[0104] The second calculation module 300 is configured to obtain a corresponding second overlap value based on the current vehicle width, a second distance, and the vehicle information, wherein the second distance is a lateral distance between the current vehicle and the candidate following target;

[0105] The determination module 500 is configured to input the first overlap value, the road gap information, and the second overlap value into a target screening model to determine a following target.

[0106] Since the information interaction, execution process, and other contents between the modules in the above-mentioned ACC following target determination system are based on the same concept as the embodiment of the ACC following target determination method in the first aspect of the present invention, the technical effects achieved are basically the same. For specific contents, please refer to the description in the first embodiment of the method of the present invention, and no further details will be given here.

[0107] The apparatus embodiments described above are merely illustrative, wherein the modules described as separate components may or may not be physically separate, i.e., they may be located in one location or distributed across multiple network elements. Some or all of these elements may be selected based on actual needs to achieve the objectives of the methods of this embodiment.

[0108] See also Figure 5 , Figure 5 The hardware structure of an electronic device according to another embodiment is shown. The electronic device includes:

[0109] The present application also provides an electronic device including a processor and a memory, wherein the memory stores programs or instructions that can be run on the processor, and when the program or instructions are executed by the processor, the steps of the ACC following target determination method as described in the present application are implemented.

[0110] The processor 501 may be implemented as a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application.

[0111] The memory 502 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 502 can store an operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 502 and is called by the processor 501 to execute the large model-based dialogue risk assessment method of the embodiments of this application.

[0112] Input / output interface 503, used to implement information input and output;

[0113] Communication interface 504, used to implement communication interaction between this device and other devices, which can be achieved through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WiFi, Bluetooth, etc.);

[0114] Bus 505 , which transmits information between various components of the device (e.g., processor 501 , memory 502 , input / output interface 503 , and communication interface 504 );

[0115] The processor 501 , the memory 502 , the input / output interface 503 and the communication interface 504 are connected to each other in communication within the device via a bus 505 .

[0116] The present application also provides a vehicle, which is configured to execute the ACC following target determination method as described in the present application.

[0117] Those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing related hardware through a computer program. The program can be stored in a computer-monitorable storage medium, and when executed, the program can include the processes in the above-described method embodiments. The storage medium can be a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0118] The specific embodiments described above further illustrate the purpose, technical solutions and beneficial effects of the present application in detail. It should be understood that the above description is only a specific embodiment of the present application and is not intended to limit the scope of protection of the present application.

[0119] It is particularly pointed out that for those skilled in the art, any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of this application should be included in the scope of protection of this application.

Claims

1. A method for determining a vehicle following target in an ACC system, characterized in that: include: Detecting a candidate vehicle target ahead of the current vehicle and obtaining vehicle information of the candidate vehicle target; Obtaining a corresponding first overlap value and road clearance information based on the current vehicle width, the first distance, and the vehicle information, wherein the first distance is a lateral distance between the current vehicle and a lane line where the current vehicle is located; Obtaining a corresponding second overlap value based on the current vehicle width, a second distance, and the vehicle information, wherein the second distance is a lateral distance between the current vehicle and the candidate following target; Inputting the first overlap value, the road gap information, and the second overlap value into a target screening model to determine a vehicle-following target; The obtaining of the corresponding first overlap value and road gap information based on the current vehicle width, the first distance, and the vehicle information specifically comprises: obtaining four relative distances between four corner points of the candidate following target and the current vehicle based on the current vehicle width, the first distance, and the vehicle information; determining a relative distance maximum value and a relative distance minimum value based on the four relative distances; comparing the relative distance maximum value with the current vehicle width and the relative distance minimum value with the current vehicle width to obtain comparison results, and determining the corresponding first overlap value and road gap information based on the comparison results. The first overlap value, the road gap information, and the second overlap value are input into a target screening model to determine a following target. Specifically, the following steps are as follows: determining whether the road gap information exceeds a preset gap threshold; if so, determining whether risk-free overtaking is possible or whether following is required based on the first overlap value and the second overlap value; if both the first overlap value and the second overlap value are less than the preset overlap threshold, controlling the current vehicle to perform risk-free overtaking; and if both the first overlap value and the second overlap value are greater than the preset overlap threshold, using the candidate following target as the following target and performing following.

2. The ACC following vehicle target determination method according to claim 1, characterized in that: The detecting of the candidate following target ahead of the current vehicle and obtaining the vehicle information of the candidate following target is specifically as follows: Detecting a candidate vehicle target ahead of the current vehicle and obtaining initial vehicle information of the candidate vehicle target; Perform Kalman filtering on the initial vehicle information to obtain vehicle information of the candidate vehicle-following target.

3. The ACC following vehicle target determination method according to claim 2, characterized in that: The Kalman filter processing is performed on the initial vehicle information to obtain the vehicle information of the candidate vehicle-following target, specifically: Constructing a corresponding first state vector and a first state covariance matrix based on the initial vehicle information; Determine a Kalman gain matrix based on the first state vector and the first state covariance matrix, and obtain a second state vector and a second state covariance matrix based on the Kalman gain matrix; Based on the second state vector and the second state covariance matrix, vehicle information of the candidate following target is determined.

4. The ACC following vehicle target determination method according to claim 1, characterized in that: The determining of the corresponding first overlap value and road gap information based on the comparison result is specifically as follows: If the maximum relative distance is less than half the width of the current vehicle, or the minimum relative distance is greater than half the width of the current vehicle, then there is no overlapping area. If the candidate following target is located on the left side of the current vehicle, then the first overlap value is the sum of the maximum relative distance and half the width of the current vehicle. If the candidate following target is located on the right side of the current vehicle, then the first overlap value is the difference between half the width of the current vehicle and the minimum relative distance. If the maximum relative distance is greater than or equal to half the current vehicle width, and the minimum relative distance is less than or equal to half the current vehicle width, then the first overlap value is equal to the current vehicle width, and the road clearance information is the maximum lateral distance between the current vehicle and the lane markings on both sides; If the minimum relative distance value is greater than half the current vehicle width, the first overlap value is the difference between half the current vehicle width and the minimum relative distance value, and the road clearance information is the distance between the current vehicle and the left lane line minus the minimum relative distance value; If the minimum relative distance is less than half the current vehicle width, the first overlap value is the sum of half the current vehicle width and the maximum relative distance, and the road gap information is the distance between the current vehicle and the right lane line minus the maximum relative distance.

5. The ACC following vehicle target determination method according to claim 1, characterized in that: The method of taking the candidate vehicle-following target as the vehicle-following target and following the vehicle is specifically as follows: When there are several following targets, the following target with the largest second overlap value is followed.

6. An ACC following vehicle target determination system, characterized in that: include: an acquisition module, a first calculation module, a second calculation module, and a determination module; The acquisition module is used to detect a candidate vehicle-following target in front of the current vehicle and obtain vehicle information of the candidate vehicle-following target; The first calculation module is configured to obtain a corresponding first overlap value and road gap information based on a current vehicle width, a first distance, and the vehicle information, wherein the first distance is a lateral distance between the current vehicle and a lane line where the current vehicle is located; The second calculation module is configured to obtain a corresponding second overlap value based on the current vehicle width, a second distance, and the vehicle information, wherein the second distance is a lateral distance between the current vehicle and the candidate following target; The determining module is configured to input the first overlap value, the road gap information, and the second overlap value into a target screening model to determine a following target; The obtaining of the corresponding first overlap value and road gap information based on the current vehicle width, the first distance, and the vehicle information specifically comprises: obtaining four relative distances between four corner points of the candidate following target and the current vehicle based on the current vehicle width, the first distance, and the vehicle information; determining a relative distance maximum value and a relative distance minimum value based on the four relative distances; comparing the relative distance maximum value with the current vehicle width and the relative distance minimum value with the current vehicle width to obtain comparison results, and determining the corresponding first overlap value and road gap information based on the comparison results. The first overlap value, the road gap information, and the second overlap value are input into a target screening model to determine a following target. Specifically, the following steps are as follows: determining whether the road gap information exceeds a preset gap threshold; if so, determining whether risk-free overtaking is possible or whether following is required based on the first overlap value and the second overlap value; if both the first overlap value and the second overlap value are less than the preset overlap threshold, controlling the current vehicle to perform risk-free overtaking; and if both the first overlap value and the second overlap value are greater than the preset overlap threshold, using the candidate following target as the following target and performing following.

7. An electronic device, characterized in that: The method comprises a processor and a memory, wherein the memory stores a program or instruction that can be run on the processor, and when the program or instruction is executed by the processor, the steps of the ACC following target determination method as described in any one of claims 1 to 5 are implemented.

8. A vehicle, characterized in that: The vehicle is configured to execute the ACC following target determination method according to any one of claims 1 to 5.

Images