Lane determination method and device for backward target, equipment and medium

Abstract

The invention relates to the field of intelligent driving, in particular to a backward target lane determination method, device and equipment and a medium, and the method comprises the steps: determining first driving track information as a lane center line of an own lane according to historical track points of an own vehicle; virtualizing boundary information of the target lane according to the lane center line and the lane width; the target lane is the target lane changed by the vehicle; according to the ordinate of the current position information of each backward target and the boundary abscissa of each backward target determined by the boundary information of the target lane, the probability of each backward target in the target lane is determined, and the probability of the target lane is used for determining the lane where the backward target is located. The method does not depend on forward vision data and lane line parameters, and can virtualize boundary information of a target lane according to historical track points of a vehicle; the probability of the backward target in the target lane is determined through the current position information of each backward target and the boundary information of the target lane, so that the lane where the target is located can be judged in real time.

Description

Technical Field

[0001] The present application relates to the field of intelligent driving, and in particular to a lane determination method, device, equipment and medium for a rearward target. Background Art

[0002] In current vehicle intelligent driving, the sensors mainly configured for L2 functions are front vision, front radar, and corner radar. Most of the rearward sensors are not configured or are only configured with rearward corner radars. For the NOP (Navigate On Pilot) function in L2+, the two rearward corner radars have great limitations in the perception of the rearward environment such as the type of target and lane lines because there is no rearward vision. For example, during high-speed lane changes, it is necessary to know the situation of the target in the rear adjacent lane, and only when safety is ensured can the active lane change request be implemented.

[0003] The current main method for selecting targets in the rear adjacent lane is to store the lane line parameters given by the forward vision. During the vehicle's driving process, the forward visual historical lane line parameters are used as the rear lane line parameters. The lane in which the target is located is located based on the lane line and the position coordinates of the target determined by the rear angle radar, and the dangerous target in the target lane is selected. However, this method is highly dependent on the visual sensor and lane line parameters.

[0004] When the front-view camera is blocked, in strong light, backlight, rain or snow and other bad weather conditions, or when there are no lane lines or the lane lines are of low quality, there is often no lane line parameter output, so it is impossible to accurately locate the lane where the target is located; or, at the moment when the lane line is lost or re-identified after being lost, it is easy to cause errors in the positioning of the target lane, resulting in dangerous lane change requests, causing the driver to be at risk of traffic accidents and endangering driving safety.

[0005] Therefore, how to accurately determine the lane position of the rearward target is a technical problem that needs to be solved urgently in this field. Summary of the invention

[0006] The purpose of this application is to provide a lane determination method, device, equipment and medium for a rearward target, which can accurately determine the lane position of a rearward target.

[0007] In a first aspect, a lane determination method for a rearward target is provided, comprising:

[0008] Determine first driving trajectory information according to the historical trajectory points of the ego vehicle as the lane centerline of the ego lane;

[0009] According to the lane centerline and lane width, the boundary information of the virtual target lane is obtained; the target lane is the target lane for the vehicle to change lanes;

[0010] The probability of each rearward target being in the target lane is determined based on the ordinate of the current position information of each rearward target and the boundary information of the target lane to determine the boundary ordinate of each rearward target, wherein the boundary ordinate of the rearward target includes the left boundary ordinate of the target lane and the right boundary ordinate of the target lane, and the probability of the target lane is used to determine the lane where the rearward target is located.

[0011] In a preferred example, the present application can be further configured as follows: determining the probability of each rearward target being in the target lane according to the ordinate of the current position information of each rearward target and the boundary abscissa of each rearward target determined by the boundary information of the target lane, including:

[0012] Determine, according to multiple position information of each backward target within a sampling period, second driving trajectory information corresponding to each backward target, an average value of the horizontal coordinate, and a standard deviation of the horizontal coordinate;

[0013] Probability estimation is performed according to the second driving trajectory information of each rearward target, the boundary abscissa of each rearward target, the average value of the abscissa and the standard deviation of the abscissa to determine the probability that each rearward target is in the target lane.

[0014] In a preferred example, the present application can be further configured as follows: performing probability estimation based on the second driving trajectory information of each rearward target, the boundary abscissa of each rearward target, the average value of the abscissa, and the standard deviation of the abscissa to determine the probability of each rearward target being in the target lane, including:

[0015] Using a preset model, the probability of each rearward target being in the target lane is determined according to the second driving trajectory information, the boundary abscissa, the average value of the abscissa, and the standard deviation of the abscissa of each rearward target;

[0016] Among them, the preset model is: ,

[0017] q is the probability of the target lane, Y is the second driving trajectory information, Y1 and Y2 are the horizontal coordinates of the right boundary of the target lane and the left boundary of the target lane, Y1 is less than Y2, is the average value, is the standard deviation.

[0018] In a preferred example, the present application can be further configured as follows: determining the probability of each rearward target being in the target lane according to the ordinate of the current position information of each rearward target and the boundary abscissa of each rearward target determined by the boundary information of the target lane, including:

[0019] Determine whether the horizontal coordinate of the current position information of each rearward target is within a preset horizontal coordinate range, wherein the preset horizontal coordinate range is determined based on the horizontal coordinate of the left boundary of the target lane and the horizontal coordinate of the right boundary of the target lane;

[0020] According to the determination result, the probability of each backward target being in the target lane is determined.

[0021] In a preferred example, the present application may be further configured as follows: after determining the probability of each rearward target being in the target lane according to the ordinate of the current position information of each rearward target and the boundary information of the target lane, the boundary abscissa of each rearward target is determined, and further comprising:

[0022] According to the parameter information of each rearward target and the threshold value corresponding to the parameter information, it is determined whether each rearward target is a dangerous target, wherein the parameter information at least includes the probability of the target lane.

[0023] In a preferred example, the present application may be further configured as follows: the parameter information also includes: the heading angle of the rearward target, the longitudinal collision time between the rearward target and the vehicle, and the lateral collision time between the rearward target and the vehicle;

[0024] According to the parameter information of each backward target and the threshold value corresponding to the parameter information, determining whether each backward target is a dangerous target includes:

[0025] For each backward target, if the parameter information satisfies a preset condition, the backward target is determined to be a dangerous target; otherwise, the backward target is determined not to be a dangerous target;

[0026] The preset conditions include: the probability that the rearward target is in the target lane is greater than a preset probability threshold; the heading angle of the rearward target is less than a preset heading angle threshold; the longitudinal collision time between the rearward target and the vehicle is less than a preset longitudinal collision time threshold; the lateral collision time between the rearward target and the vehicle is less than a preset lateral collision time threshold.

[0027] In a preferred example, the present application can be further configured as follows: It also includes: determining the heading angle of the rearward target according to the second driving trajectory information, wherein the second driving trajectory information is trajectory information determined according to multiple position information of the rearward target within a sampling period.

[0028] In a second aspect, a lane determination device for a rearward target is provided, comprising:

[0029] A first determination module is used to determine first driving trajectory information as a lane centerline of the lane according to the historical trajectory points of the vehicle;

[0030] The second determination module is used to virtualize the boundary information of the target lane according to the lane centerline and lane width; the target lane is the target lane for the vehicle to change lanes;

[0031] The third determination module is used to determine the probability of each rearward target being in the target lane based on the longitudinal coordinate of the current position information of each rearward target and the boundary information of the target lane, and the boundary horizontal coordinate of each rearward target includes the left boundary horizontal coordinate of the target lane and the right boundary horizontal coordinate of the target lane. The probability of the target lane is used to determine the lane where the rearward target is located.

[0032] In a third aspect, an electronic device is provided, comprising a memory and a processor, wherein the memory stores a computer program, and the processor executes the lane determination method for a rearward target as described in any one of the first aspects when running the computer program.

[0033] In a fourth aspect, a computer-readable storage medium is provided, wherein at least one program code is stored in the computer-readable storage medium, and the program code is loaded and executed by a processor to implement the lane determination method for a rearward target as described in any one of the first aspects.

[0034] In a fifth aspect, a computer program product is provided, comprising a computer program or instructions, which, when executed by a processor, implements the lane determination method for a rearward target as described in any one of the first aspects.

[0035] In summary, the lane determination method for a rearward target provided by the present application includes the following beneficial technical effects:

[0036] The present application scheme does not rely on forward visual data and lane line parameters, and can virtualize the lane centerline of the ego lane based on the historical trajectory points of the ego vehicle; and virtualize the boundary information of the target lane based on the lane centerline and lane width; further, the boundary horizontal coordinates of each rearward target are determined through the current position information of each rearward target and the boundary information of the target lane, and the probability of each rearward target being in the target lane is determined, so as to judge the lane where the target is located in real time, and improve the recognition rate while ensuring the recognition accuracy.

[0037] In addition, the present application also provides a lane determination device, equipment and medium for a rearward target, all of which have the above-mentioned beneficial technical effects. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the embodiments of the present application or the technical solutions of the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0039] Figure 1It is a flowchart of a lane determination method for a rearward target provided in an embodiment of the present application;

[0040] Figure 2 It is a schematic diagram of the virtual lane centerline generated from the lane boundary provided in an embodiment of the present application;

[0041] Figure 3 It is a schematic diagram of generating left and right lane lines of a vehicle provided by an embodiment of the present application;

[0042] Figure 4 is a schematic diagram of position information of a backward target provided by an embodiment of the present application;

[0043] Figure 5 It is a schematic diagram of determining the y value of a boundary point provided in an embodiment of the present application;

[0044] Figure 6 It is a structural schematic diagram of a lane determination device for a rearward target provided in an embodiment of the present application;

[0045] Figure 7 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0046] This specific embodiment is merely an explanation of the present application and is not a limitation of the present application. After reading this specification, those skilled in the art may make modifications to the present embodiment without any creative contribution as needed, but as long as they are within the scope of the present application, they are protected by the patent law.

[0047] It should be noted that in the optional embodiments of the present application, the object information and other related data involved, when the embodiments in the present application are applied to specific products or technologies, need to obtain the permission or consent of the object, and the collection, use and processing of the relevant data need to comply with the relevant laws, regulations and standards of the relevant countries and regions. In other words, if the embodiments of the present application involve data related to the object, it needs to be obtained with the authorization and consent of the object, the authorization and consent of the relevant departments, and in compliance with the relevant laws, regulations and standards of the country and region. If personal information is involved in the embodiments, the acquisition of all personal information needs to obtain the consent of the individual. If sensitive information is involved, the separate consent of the information subject needs to be obtained. The embodiments also need to be implemented with the authorization and consent of the object.

[0048] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0049] In addition, the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article, unless otherwise specified, generally means that the associated objects before and after are in an "or" relationship.

[0050] The present application embodiment provides a lane determination method for a rearward target, such as Figure 1 As shown, the method provided in the embodiment of the present application can be executed by an electronic device, and the electronic device is a server. The server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services. The terminal device can be a smart phone, a tablet computer, a laptop computer, a desktop computer, a vehicle-mounted device, etc., but is not limited thereto. The terminal device and the electronic device can be directly or indirectly connected via wired or wireless communication, which is not limited in the embodiment of the present application. The method includes:

[0051] S101, determining first driving trajectory information according to historical trajectory points of the vehicle as the center line of the lane;

[0052] The embodiment of the present application can be used with or without a visual sensor configured in the rear direction. The embodiment of the present application is not limited to the application scenario, which can be a conventional scenario or a scenario with poor vision.

[0053] Among them, when constructing the surrounding environment of the vehicle, the historical trajectory of the vehicle is used as the center line of the lane of the lane. The electronic device stores the historical trajectory points of the vehicle, stores a trajectory point of the vehicle at every preset distance, and stores a preset number of points in a container, wherein the preset distance is such as 3m, 4m or 5m, etc., which is not limited in the embodiment of the present application, and the preset number is such as 20, 25 or 30, etc., which is not limited in the embodiment of the present application. In order to meet the needs of the vehicle in changing lanes, considering the speed of the target, the farthest point of the historical trajectory point needs to meet a certain distance requirement, which can be customized by the user, and can be specifically set according to the speed limit information of the lane, such as 80m. When the farthest point of the stored centerline point is greater than the distance or the number of stored points is greater than the preset number, the nearest point in the historical trajectory point is deleted.

[0054] Furthermore, the stored historical trajectory points can be preprocessed, such as randomly selecting points that meet the quantity and longest distance requirements from these data points as points for determining the first driving trajectory information; the stored historical trajectory points can also be subjected to operations such as outlier removal to improve the validity of the trajectory points, thereby improving the accuracy of determining the first driving trajectory information.

[0055] According to the stored historical trajectory points, a certain number of selected historical trajectory points are subjected to polynomial curve fitting to obtain a virtual lane centerline trajectory equation. The polynomial may be a cubic polynomial or a quintic polynomial, which is not limited in this embodiment. Taking the cubic polynomial as an example, the obtained first driving trajectory information may be: .

[0056] S102, virtualizing boundary information of a target lane according to the lane centerline and lane width; the target lane is the target lane for the vehicle to change lanes;

[0057] According to the calculated virtual lane center line, the virtual lane center line is offset to the left and right by a certain distance to obtain the boundary of the lane center line. The offset distance is the lane width of the current lane, and the target lane is the left lane or the right lane of the vehicle.

[0058] The process of generating virtual lane boundary lines is as follows: Figure 2 , Figure 3 As shown, Figure 2 is a schematic diagram of a virtual lane centerline generated from a lane boundary provided in an embodiment of the present application, Figure 3 This is a schematic diagram of generating the left and right lane lines of the vehicle provided by the embodiment of the present application, wherein the vehicle is taken as the coordinate origin. The distance offset to the left and right from the lane centerline can be processed according to the actual lane width. For example, if the lane width of the vehicle is 3m, it can be offset to the left by 1.5m to get the left lane boundary, and offset to the right by 1.5m to get the right lane boundary.

[0059] The determination of the adjacent lane boundary of the vehicle is the same as the processing process of the lane width of the vehicle. The left lane boundary of the vehicle can be further offset to the left by 3m to obtain the left boundary line of the left lane, and the right lane of the vehicle can be further offset to the right by 3m to obtain the right boundary line of the right lane.

[0060] Taking the cubic polynomial as an example, four boundary curves of the self-lane, left lane, and right lane can be obtained respectively, that is, the virtual lane model (including lane centerline parameters and the boundaries of each lane), such as: ; ; ; , where d represents the lane width (which can be selected according to the actual lane width), is the boundary information of the left boundary line of the left lane of the vehicle, is the boundary information of the right boundary line of the left lane of the vehicle, that is, the left boundary information of the lane. The boundary information of the left boundary line of the right lane of the vehicle, that is, the right boundary information of the lane; is the boundary information of the right boundary line of the right lane of the vehicle, It is the first trajectory information of the vehicle, i.e., the center line of the lane of the vehicle.

[0061] In an embodiment of the present application, after the target lane is determined, boundary information of the virtual target lane can be generated based on the lane centerline and lane width, and the boundary information includes: left boundary information and right boundary information of the target lane.

[0062] S103, determining the probability of each rearward target being in the target lane according to the ordinate of the current position information of each rearward target and the boundary abscissa of each rearward target determined by the boundary information of the target lane,

[0063] The boundary horizontal coordinates of the rearward target include the left boundary horizontal coordinates of the target lane and the right boundary horizontal coordinates of the target lane. The probability of the target lane is used to determine the lane where the rearward target is located.

[0064] Among them, the rearward target refers to the target that is traveling behind the ego vehicle and may affect the driving path planning. The target can be a vehicle, motorcycle, etc. The current position information of the rearward target refers to the position information obtained by the rearward radar in the same coordinate system as the ego vehicle; the target lane refers to the adjacent lane that the ego vehicle intends to change to; the probability of the rearward target in the target lane is the probability value of the rearward target in the target lane, and the probability value range is [0,1].

[0065] The ordinate of the current position information of each rearward target is substituted into the left boundary information and the right boundary information of the target lane to obtain the left boundary horizontal coordinate of the target lane and the right boundary horizontal coordinate of the target lane as the boundary horizontal coordinate of the rearward target; further, based on the boundary horizontal coordinate of each rearward target, the probability of each rearward target being in the target lane is determined.

[0066] In some embodiments, target lane probability calculation can be implemented in a variety of ways:

[0067] Optionally, the first method matches the interval of the horizontal coordinate of the backward target:

[0068] Determine whether the horizontal coordinate of the current position information of each rearward target is within a preset horizontal coordinate range, and the preset horizontal coordinate range is determined based on the horizontal coordinate of the left boundary of the target lane and the horizontal coordinate of the right boundary of the target lane; determine the probability of each rearward target being in the target lane according to the determination result. Specifically, the preset horizontal coordinate range is [Y1, Y2], where Y1 and Y2 are the horizontal coordinate of the right boundary of the target lane and the horizontal coordinate of the left boundary of the target lane; determine whether the horizontal coordinate of the current position information of the rearward target is within the two horizontal coordinate values, and if so, determine that the probability of the rearward target being in the target lane is 1, otherwise, determine that the probability is 0. When the probability is 1, determine that the rearward target is in the target lane, otherwise determine that the rearward target is not in the target lane.

[0069] Optionally, the second method adopts a probability model method: the corresponding probability value is obtained by integrating the probability density function of the rearward target in the target lane within the boundary range of the target lane.

[0070] It can be seen that the embodiment of the present application does not rely on forward visual data and lane line parameters, and can virtualize the lane centerline of the ego lane based on the historical trajectory points of the ego vehicle; and virtualize the boundary information of the target lane based on the lane centerline and lane width; further, the probability of each rearward target being in the target lane is determined by determining the vertical coordinate of the current position information of each rearward target and the horizontal coordinate of the boundary of the target lane determined by the boundary information of the target lane, so as to facilitate real-time judgment of the lane where the target is located, improve the recognition rate while ensuring the recognition accuracy, and reduce the traffic hazards caused by dangerous lane changes due to missed recognition.

[0071] A possible implementation of the embodiment of the present application is to determine the probability of each rearward target being in the target lane according to the ordinate of the current position information of each rearward target and the boundary abscissa of each rearward target determined by the boundary information of the target lane, including:

[0072] Determine, according to multiple position information of each backward target within a sampling period, second driving trajectory information corresponding to each backward target, an average value of the horizontal coordinate, and a standard deviation of the horizontal coordinate;

[0073] Probability estimation is performed according to the second driving trajectory information of each rearward target, the boundary abscissa of each rearward target, the average value of the abscissa and the standard deviation of the abscissa to determine the probability that each rearward target is in the target lane.

[0074] The second driving trajectory information is polynomial driving trajectory information obtained by fitting multiple position information of the backward target within the sampling period.

[0075] Among them, from the knowledge of statistics, it can be known that the vehicle's choice of which lane to drive is a random event, but the position relative to the vehicle at a certain moment is determined. Moreover, the distribution of lanes at a certain moment can be regarded as a normal distribution. Therefore, in the embodiment of the present application, the probability density of the normal distribution can be used to solve the probability of the rearward target existing in the target lane (left lane, self lane and right lane) at a certain moment.

[0076] The random variable Y (the horizontal coordinate of the backward target) has a mathematical expectation of μ and a standard deviation of The Gaussian distribution of , then its probability density function is: ; The coordinate position of the rearward target obtained by the rearward radar sensor within a certain lane sampling period is , according to the position of the target in the sampling period, calculate the average value and standard deviation of the horizontal coordinate of the backward target in the sampling period , and then obtain the probability density function of the backward target in the sampling period.

[0077] Then, using the preset model, according to the second driving trajectory information of each rearward target, the boundary abscissa, the average value of the abscissa and the standard deviation of the abscissa, the probability of each rearward target being in the target lane is determined;

[0078] Among them, the preset model is: ,

[0079] q is the probability of the target lane, Y is the second driving trajectory information, Y1 and Y2 are the horizontal coordinates of the right boundary of the target lane and the left boundary of the target lane, Y1 is less than Y2, is the average value, is the standard deviation.

[0080] It can be understood that the probability distribution function of the rearward target in the target lane can be obtained by integrating the probability density function of the rearward target in the target lane within the boundary range of the target lane.

[0081] Specifically, according to the ordinate of the rearward target position and the boundary information of the target lane, the horizontal coordinate of the left boundary of the target lane and the horizontal coordinate of the right boundary of the target lane corresponding to the rearward target can be determined; according to the probability density function of the target, the target is integrated in the corresponding lane to obtain the probability q of the rearward target in the target lane.

[0082] It can be seen that in the embodiment of the present application, the judgment of the rearward target in the target lane is quantified and calculated, and the distribution of the rearward target is determined by the probability value, so as to reduce the traffic accident damage caused by the wrong allocation of the rearward target when the visual sensor is used with limited or the lane quality is poor, so as to facilitate the calculation of the probability of the target in the own lane and the adjacent lane based on the virtual lane model of the historical trajectory of the own vehicle, so as to screen the rearward dangerous target of the own vehicle during the active lane change process.

[0083] A possible implementation of the embodiment of the present application further includes, after determining the probability of each rearward target being in the target lane according to the ordinate of the current position information of each rearward target and the boundary information of the target lane, determining the boundary abscissa of each rearward target, and:

[0084] According to the parameter information of each rearward target and the threshold value corresponding to the parameter information, it is determined whether each rearward target is a dangerous target, wherein the parameter information at least includes the probability of the target lane.

[0085] Among them, parameter information refers to multi-dimensional information used for risk assessment, which at least includes the probability of the target lane, and of course can also include: heading angle, longitudinal collision time, lateral collision time, etc.; the threshold corresponding to the parameter information is the threshold corresponding to each dimensional information, which is used to determine the safety of lane changing; the dangerous target refers to the rearward target that has the potential to change lanes to the target lane.

[0086] It can be seen that in the embodiment of the present application, the nature of the backward target (whether it is a dangerous target or a non-dangerous target) is determined by multiple parameters, which effectively reduces the misjudgment rate of a single parameter.

[0087] In a possible implementation of the embodiment of the present application, specifically, the parameter information further includes: a heading angle of the rearward target, a longitudinal collision time between the rearward target and the vehicle, and a lateral collision time between the rearward target and the vehicle;

[0088] According to the parameter information of each backward target and the threshold value corresponding to the parameter information, determining whether each backward target is a dangerous target includes:

[0089] For each backward target, if the parameter information meets the preset conditions, the backward target is determined to be a dangerous target; otherwise, the backward target is determined not to be a dangerous target;

[0090] The preset conditions include: the probability that the rear target is in the target lane is greater than a preset probability threshold; the heading angle of the rear target is less than a preset heading angle threshold; the longitudinal collision time between the rear target and the vehicle is less than a preset longitudinal collision time threshold; the lateral collision time between the rear target and the vehicle is less than a preset lateral collision time threshold.

[0091] In the embodiment of the present application, the selection of dangerous targets mainly considers some parameters of the rearward dangerous targets in the target lane, mainly including the following:

[0092] 1. The probability of the rearward target being in the target lane. The probability of the rearward target being in the target lane needs to be greater than a preset probability threshold, such as 0.8.

[0093] 2. The heading angle of the rearward target needs to be less than a preset heading angle threshold, such as 0.78 rad. If the heading angle is too large, it is considered that the rearward target will cut out of the target lane and there is no risk of collision. The heading angle of the rearward target is determined based on the second driving trajectory information, and the second driving trajectory information is trajectory information determined based on multiple position information of the rearward target within the sampling period.

[0094] 3. The longitudinal collision time between the rearward target and the vehicle is less than a preset longitudinal collision time threshold, such as 2s.

[0095] 4. The lateral collision time between the rearward target and the ego vehicle is less than the preset lateral collision time threshold, such as 1.5s. Consider a target with the same longitudinal speed as the ego vehicle but very close lateral distance, such as the phenomenon of running head-to-head.

[0096] Targets that meet the above four conditions at the same time are considered to be dangerous targets behind during active lane change.

[0097] It can be seen that in the embodiment of the present application, the probability of the rearward target being in the target lane, the heading angle of the rearward target, the longitudinal collision time between the rearward target and the own vehicle, and the lateral collision time between the rearward target and the own vehicle are used as the basis for judging the danger of the rearward target, and the danger situation of the rearward target can be accurately determined.

[0098] Based on any of the above embodiments, the embodiments of the present application provide a specific main calculation process for screening rearward targets, including: the first step: using the historical trajectory line of the vehicle as the virtual lane centerline, based on the virtual lane centerline, virtualizing the left and right boundaries of the lane, and based on the left and right boundaries of the lane, respectively virtualizing the left and right boundaries of the left lane and the right and left boundaries of the right lane. The second step: based on the coordinate distribution of the rearward target, calculate its probability density function, based on the lane boundary value calculated in the first step, calculate the probability distribution of the target in the three lanes respectively, after obtaining the probability of the target in the three lanes, according to the probability maximum principle, assign the target by lane. The third step: select the dangerous target in the target lane where the vehicle needs to change lanes. The selection of the dangerous target mainly considers the probability of being in the target lane, the longitudinal collision time between the target and the vehicle, the lateral collision time between the target and the vehicle, and the heading angle of the target.

[0099] Specifically, 1. Virtual lane model: According to the historical trajectory points of the vehicle, the first driving trajectory information is determined as the lane centerline of the vehicle; according to the lane centerline and lane width, the boundary information of the virtual target lane is obtained. Based on this, four boundary curves of the vehicle lane, left lane, and right lane can be obtained, that is, the virtual lane model (including lane centerline parameters and the boundaries of each lane), such as: ; ; ; .

[0100] 2. Backward target probability calculation: The probability density function is , y is the second driving trajectory information; Figure 4 , assuming that the backward target is at point F (current position information), according to the coordinates of the target The boundary curve obtained in the above step can be respectively substituted into the curve according to the longitudinal coordinate x of the backward target. and curve Get the boundary coordinate y of the left lane. Similarly, when the rearward target is in other lanes, the calculation of its boundary is the same as the calculation of the rearward target F.

[0101] Based on the calculated lane boundary, the probability density function of the rearward target is used to integrate the rearward target in the lane to obtain the probability of the rearward target being in the lane. Figure 5 ,get:

[0102] ; ; ;in, Represent the lane boundaries of each lane respectively.

[0103] 3. Selection of rearward dangerous targets during active lane change:

[0104] The selection of dangerous targets mainly considers some parameters of the rearward dangerous targets in the target lane, and then determines whether each rearward target is a dangerous target based on the parameter information of each rearward target and the threshold corresponding to the parameter information.

[0105] A device provided in an embodiment of the present application is introduced below. The device described below and the method described above can be referred to each other. The device of this embodiment is set in an electronic device. Figure 6 , Figure 6 It is a structural block diagram of a device of one embodiment of the present application, comprising:

[0106] A first determination module 210 is used to determine first driving trajectory information as a lane centerline of the lane according to the historical trajectory points of the vehicle;

[0107] The second determination module 220 is used to virtualize the boundary information of the target lane according to the lane centerline and lane width; the target lane is the target lane for the vehicle to change lanes;

[0108] The third determination module 230 is used to determine the probability of each rearward target being in the target lane based on the longitudinal coordinate of the current position information of each rearward target and the boundary information of the target lane, and the boundary horizontal coordinate of each rearward target includes the left boundary horizontal coordinate of the target lane and the right boundary horizontal coordinate of the target lane. The probability of the target lane is used to determine the lane where the rearward target is located.

[0109] In a preferred example, the present application may be further configured as: a third determination module 230, for:

[0110] Determine, according to multiple position information of each backward target within a sampling period, second driving trajectory information corresponding to each backward target, an average value of the horizontal coordinate, and a standard deviation of the horizontal coordinate;

[0111] Probability estimation is performed according to the second driving trajectory information of each rearward target, the boundary abscissa of each rearward target, the average value of the abscissa and the standard deviation of the abscissa to determine the probability that each rearward target is in the target lane.

[0112] In a preferred example, the present application may be further configured as: a third determination module 230, for:

[0113] Using a preset model, the probability of each rearward target being in the target lane is determined according to the second driving trajectory information, the boundary abscissa, the average value of the abscissa, and the standard deviation of the abscissa of each rearward target;

[0114] Among them, the preset model is: ,

[0115] q is the probability of the target lane, Y is the second driving trajectory information, Y1 and Y2 are the horizontal coordinates of the right boundary of the target lane and the left boundary of the target lane, Y1 is less than Y2, is the average value, is the standard deviation.

[0116] In a preferred example, the present application may be further configured as: a third determination module 230, for:

[0117] Determine whether the horizontal coordinate of the current position information of each rearward target is within a preset horizontal coordinate range, wherein the preset horizontal coordinate range is determined based on the horizontal coordinate of the left boundary of the target lane and the horizontal coordinate of the right boundary of the target lane;

[0118] According to the determination result, the probability of each backward target being in the target lane is determined.

[0119] In a preferred example, the present application can be further configured as follows:

[0120] The fourth determination module is used to determine whether each rearward target is a dangerous target according to parameter information of each rearward target and a threshold value corresponding to the parameter information, wherein the parameter information at least includes the probability of the target lane.

[0121] In a preferred example, the present application can be further configured as follows: the parameter information also includes: the heading angle of the rearward target, the longitudinal collision time between the rearward target and the vehicle, and the lateral collision time between the rearward target and the vehicle;

[0122] The fourth determination module is used for:

[0123] For each backward target, if the parameter information meets the preset conditions, the backward target is determined to be a dangerous target; otherwise, the backward target is determined not to be a dangerous target;

[0124] The preset conditions include: the probability that the rear target is in the target lane is greater than a preset probability threshold; the heading angle of the rear target is less than a preset heading angle threshold; the longitudinal collision time between the rear target and the vehicle is less than a preset longitudinal collision time threshold; the lateral collision time between the rear target and the vehicle is less than a preset lateral collision time threshold.

[0125] In a preferred example, the present application can be further configured as follows:

[0126] The heading angle determination module is used to determine the heading angle of the backward target according to the second driving trajectory information, where the second driving trajectory information is trajectory information determined according to multiple position information of the backward target within a sampling period.

[0127] An electronic device is provided in an embodiment of the present application, such as Figure 7 As shown, Figure 7 The electronic device 300 shown includes: at least one processor 301 ( Figure 7 301 and memory 303. The processor 301 and memory 303 are connected, such as through a bus 302. Optionally, the electronic device 300 may further include a transceiver 304. It should be noted that in actual applications, the transceiver 304 is not limited to one, and the structure of the electronic device 300 does not constitute a limitation on the embodiments of the present application.

[0128] The processor 301 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. The processor 301 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0129] The bus 302 may include a path to transmit information between the above components. The bus 302 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 302 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 7 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0130] The memory 303 may be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compressed optical disk, laser disk, optical disk, digital versatile disk, Blu-ray disk, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0131] The memory 303 is used to store the application code for executing the solution of the present application, and the execution is controlled by the processor 301. The processor 301 is used to execute the application code stored in the memory 303 to implement the contents shown in the above method embodiment.

[0132] Figure 7 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0133] An embodiment of the present application provides a computer-readable storage medium, in which at least one program code is stored. When the computer-readable storage medium is run on a computer, the computer can execute the corresponding content of the aforementioned method embodiment.

[0134] An embodiment of the present application provides a computer program product, including a computer program or instructions, which implement the corresponding contents of the aforementioned method embodiment when the computer program or instructions are executed by a processor.

[0135] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0136] The above are only some implementation methods of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A lane determination method for a rearward target, characterized in that: include: Determine first driving trajectory information according to the historical trajectory points of the ego vehicle as the lane centerline of the ego lane; The boundary information of the virtual target lane is obtained based on the lane centerline and lane width; The target lane is the target lane for the vehicle to change lanes; The probability of each rearward target being in the target lane is determined based on the ordinate of the current position information of each rearward target and the boundary information of the target lane to determine the boundary ordinate of each rearward target, wherein the boundary ordinate of the rearward target includes the left boundary ordinate of the target lane and the right boundary ordinate of the target lane, and the probability of the target lane is used to determine the lane where the rearward target is located.

2. The lane determination method for a rearward target according to claim 1, characterized in that: Determining the probability of each rearward target being in the target lane according to the ordinate of the current position information of each rearward target and the boundary abscissa of each rearward target determined by the boundary information of the target lane, including: Determine, according to multiple position information of each backward target within a sampling period, second driving trajectory information corresponding to each backward target, an average value of the horizontal coordinate, and a standard deviation of the horizontal coordinate; Probability estimation is performed according to the second driving trajectory information of each rearward target, the boundary abscissa of each rearward target, the average value of the abscissa and the standard deviation of the abscissa to determine the probability that each rearward target is in the target lane.

3. The lane determination method for a rearward target according to claim 2, characterized in that: Probability estimation is performed according to the second driving trajectory information of each rearward target, the boundary abscissa of each rearward target, the average value of the abscissa, and the standard deviation of the abscissa to determine the probability of each rearward target being in the target lane, including: Using a preset model, the probability of each rearward target being in the target lane is determined according to the second driving trajectory information, the boundary abscissa, the average value of the abscissa, and the standard deviation of the abscissa of each rearward target; Among them, the preset model is: , q is the probability of the target lane, Y is the second driving trajectory information, Y1 and Y2 are the horizontal coordinates of the right boundary of the target lane and the left boundary of the target lane, Y1 is less than Y2, is the average value, is the standard deviation.

4. The lane determination method for a rearward target according to claim 1, characterized in that: Determining the probability of each rearward target being in the target lane according to the ordinate of the current position information of each rearward target and the boundary abscissa of each rearward target determined by the boundary information of the target lane, including: Determine whether the horizontal coordinate of the current position information of each rearward target is within a preset horizontal coordinate range, wherein the preset horizontal coordinate range is determined based on the horizontal coordinate of the left boundary of the target lane and the horizontal coordinate of the right boundary of the target lane; According to the determination result, the probability of each backward target being in the target lane is determined.

5. The lane determination method for a rearward target according to any one of claims 1 to 4, characterized in that: After determining the boundary abscissa of each rearward target according to the ordinate of the current position information of each rearward target and the boundary information of the target lane, and determining the probability of each rearward target being in the target lane, the method further includes: According to the parameter information of each rearward target and the threshold value corresponding to the parameter information, it is determined whether each rearward target is a dangerous target, wherein the parameter information at least includes the probability of the target lane.

6. The lane determination method for a rearward target according to claim 5, characterized in that: The parameter information also includes: the heading angle of the rearward target, the longitudinal collision time between the rearward target and the vehicle, and the lateral collision time between the rearward target and the vehicle; According to the parameter information of each backward target and the threshold value corresponding to the parameter information, determining whether each backward target is a dangerous target includes: For each backward target, if the parameter information satisfies a preset condition, the backward target is determined to be a dangerous target; otherwise, the backward target is determined not to be a dangerous target; The preset conditions include: the probability that the rearward target is in the target lane is greater than a preset probability threshold; the heading angle of the rearward target is less than a preset heading angle threshold; the longitudinal collision time between the rearward target and the vehicle is less than a preset longitudinal collision time threshold; the lateral collision time between the rearward target and the vehicle is less than a preset lateral collision time threshold.

7. The lane determination method for a rearward target according to claim 5, characterized in that: Also includes: The heading angle of the backward target is determined according to the second driving trajectory information, where the second driving trajectory information is trajectory information determined according to a plurality of position information of the backward target within a sampling period.

8. A lane determination device for a rearward target, characterized in that: include: A first determination module is used to determine first driving trajectory information as a lane centerline of the lane according to the historical trajectory points of the vehicle; The second determination module is used to virtualize the boundary information of the target lane according to the lane centerline and lane width; The target lane is the target lane for the vehicle to change lanes; The third determination module is used to determine the probability of each rearward target being in the target lane based on the longitudinal coordinate of the current position information of each rearward target and the boundary information of the target lane, and the boundary horizontal coordinate of each rearward target includes the left boundary horizontal coordinate of the target lane and the right boundary horizontal coordinate of the target lane. The probability of the target lane is used to determine the lane where the rearward target is located.

9. An electronic device, characterized in that: The electronic device includes a memory and a processor, wherein a computer program is stored in the memory, and the processor executes the lane determination method for a rearward target according to any one of claims 1 to 7 when running the computer program.

10. A computer-readable storage medium, characterized in that: At least one program code is stored in the computer-readable storage medium, and the program code is loaded and executed by the processor to implement the lane determination method for a rearward target as described in any one of claims 1 to 7.

Images