Target screening method, device, storage medium and ACC system or control unit thereof

Abstract

Embodiments of the present application provide a target screening method and device, a storage medium and an ACC system or a control unit thereof. The method comprises: acquiring detection data detected by a sensor; determining a distance between a target and a host vehicle according to the detection data; determining a type of an inverted trapezoidal region according to the distance between the target and the host vehicle; and performing target screening according to the detection data and the type of the inverted trapezoidal region. In the technical solution provided by the embodiments of the present application, target screening is performed according to the detection data and the type of the inverted trapezoidal region, thereby improving the accuracy of target screening and the safety of driving.

Description

[0001] The present application relates to the technical field of intelligent networked vehicles, and in particular to a target screening method and device, a storage medium, and an ACC system or a control unit thereof.

[0002] An adaptive cruise control (ACC) system is an intelligent driving assistance system for vehicles that can automatically adjust the speed of the vehicle to maintain a safe distance according to the speed and distance of the vehicle in front. The conventional ACC system currently has some problems in target selection, i.e., selecting a target according to the nearest principle, which may cause a misidentified, late deceleration, or no intrusion but still selected to brake. The accuracy of target screening is low, and the safety of driving is low.

[0003] Therefore, the embodiments of the present application provide a target screening method, device, storage medium, and ACC system or control unit thereof to improve the accuracy of target screening and the safety of driving.

[0004] In one aspect, the embodiments of the present application provide a target screening method, comprising:

[0005] obtaining detection data detected by a sensor;

[0006] determining the distance between the target and the ego vehicle according to the detection data;

[0007] determining the type of the inverted trapezoidal region according to the distance between the target and the ego vehicle;

[0008] screening the target according to the detection data and the type of the inverted trapezoidal region.

[0009] Optionally, the distance between the target and the ego vehicle is determined according to the detection data, comprising:

[0010] if the distance between the target and the ego vehicle is within a first threshold range, the target is determined as a near-distance target; or

[0011] if the distance between the target and the ego vehicle is within a second threshold range, the target is determined as a middle-distance target; or

[0012] if the distance between the target and the ego vehicle is within a third threshold range, the target is determined as a far-distance target.

[0013] The first threshold range is smaller than the second threshold range, and the second threshold range is smaller than the third threshold range.

[0014] ​​​Optionally, the determining the type of the inverted trapezoidal region according to the distance between the target and the ego vehicle comprises:

[0015] If the target is determined as a close-range target, the type of the inverted trapezoidal region is determined as a cut-in inverted trapezoidal region; or,

[0016] If the target is determined as a medium-range target or a long-range target, the type of the inverted trapezoidal region is determined as a cut-out inverted trapezoidal region.

[0017] Optionally, the cut-in inverted trapezoidal region is used to select the target closest to and the second closest to the ego vehicle in the longitudinal direction of the ego vehicle; or, the cut-out inverted trapezoidal region is used to select the target closest to the ego vehicle on the left and the right in the lateral direction of the ego vehicle.

[0018] Optionally, after the cut-in inverted trapezoidal region is used to select the target closest to and the second closest to the ego vehicle in the longitudinal direction of the ego vehicle, the method further comprises:

[0019] According to the longitudinal distance between the ego vehicle and the target in the driving direction of the ego vehicle and the target type of the target, the first lateral threshold is adjusted to control the selection degree of the target.

[0020] After the cut-out inverted trapezoidal region is used to select the target closest to the ego vehicle on the left and the right in the lateral direction of the ego vehicle, the method further comprises:

[0021] According to the longitudinal distance between the ego vehicle and the target in the driving direction of the ego vehicle and the target type of the target, the second lateral threshold is adjusted to control the selection degree of the target.

[0022] Optionally, the target screening according to the detection data and the type of the inverted trapezoidal region comprises:

[0023] A funnel trajectory is generated according to the detection data and the predicted trajectory of the ego vehicle;

[0024] The target is screened according to the funnel trajectory and the type of the inverted trapezoidal region, to generate a preliminary screening target and dynamic data of the preliminary screening target;

[0025] According to the dynamic data, an interpolation curve algorithm is used for prediction to generate a future motion trajectory of the target;

[0026] According to the future motion trajectory of the target and a set target constraint condition, the target is screened from the preliminary screening target.

[0027] Optionally, the generating a funnel trajectory according to the detection data and the predicted trajectory of the ego vehicle comprises:

[0028] An inverted trapezoidal region is determined according to the detection data;

[0029] generate a funnel trajectory before adjustment according to the inverted trapezoidal type region;

[0030] adjust the funnel trajectory before adjustment according to the obtained self-vehicle predicted trajectory, and generate the funnel trajectory.

[0031] In another aspect, an embodiment of the present application provides a target screening device, comprising:

[0032] An acquisition module is configured to acquire detection data detected by a sensor;

[0033] A first determination module is configured to determine a distance between a target and a self-vehicle according to the detection data;

[0034] A second determination module is configured to determine a type of an inverted trapezoidal region according to the distance between the target and the self-vehicle;

[0035] A screening module is configured to perform target screening according to the detection data and the type of the inverted trapezoidal region.

[0036] In another aspect, an embodiment of the present application provides a storage medium, which comprises a stored program, wherein the program controls a device where the storage medium is located to perform the target screening method when the program is running.

[0037] In another aspect, an embodiment of the present application provides an adaptive cruise control system or a control unit thereof, which comprises a memory and a processor, the memory is configured to store information comprising program instructions, and the processor is configured to control execution of the program instructions, wherein the program instructions are loaded and executed by the processor to implement steps of the target screening method.

[0038] In the technical scheme of the target screening method provided by the embodiment of the present application, the detection data detected by the sensor is acquired, the distance between the target and the self-vehicle is determined according to the detection data, the type of the inverted trapezoidal region is determined according to the distance between the target and the self-vehicle, and the target screening is performed according to the detection data and the type of the inverted trapezoidal region. In the technical scheme provided by the embodiment of the present application, the target screening is performed according to the detection data and the type of the inverted trapezoidal region, which improves the accuracy of the target screening and the safety of driving. BRIEF DESCRIPTION OF DRAWINGS

[0039] In order to more clearly illustrate the technical scheme of the embodiments of the present application, the drawings needed in the embodiments will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0040] Figure 1 A flowchart of a target screening method provided by an embodiment of the present application is shown.

[0041] Figure 2 This is a schematic diagram of cutting into and cutting out an inverted trapezoidal region according to an embodiment of the present invention;

[0042] Figure 3 This is a schematic diagram of the inverted trapezoidal judgment boundary and the inverted trapezoidal judgment boundary provided in an embodiment of the present invention;

[0043] Figure 4 A flowchart for target selection based on detection data and the type of inverted trapezoidal region provided in an embodiment of the present invention;

[0044] Figure 5 This is a schematic diagram of the structure of a target screening device according to an embodiment of the present invention;

[0045] Figure 6 This is a schematic diagram of an ACC system or its control unit provided in an embodiment of the present invention.

Detailed Implementation Methods

[0046] To better understand the technical solution of the present invention, the embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0047] It should be understood that the described embodiments are merely some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0048] The terminology used in the embodiments of this invention is for the purpose of describing particular embodiments only and is not intended to limit the invention. The singular forms “a,” “the,” and “the” as used in the embodiments of this invention and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise.

[0049] It should be understood that the term "and / or" used in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0050] In related technologies, target selection methods have some problems, such as delayed detection of intervening targets, delayed deceleration, or even selection and false braking even without intrusion. These problems are mainly due to inaccurate speed and distance measurement. Furthermore, the ACC system in related technologies uses the nearest-to-the-source principle to select targets, without considering the impact of sensor detection distance on target recognition accuracy and resolution, which may lead to false target selection and false braking.

[0051] To solve the above-mentioned related technical problems, an embodiment of the present application provides a target screening method, which forms an inverted trapezoidal target screening method based on the detection performance of a sensor to solve the target screening problem. An inverted trapezoidal region is used, and a funnel track surrounds the ego vehicle predicted track, that is, the funnel center will be curved according to the direction of the ego vehicle predicted track. This way can effectively solve the problem that the farther the sensor detection distance, the worse the accuracy and resolution of the returned target detection result. Specifically, the nearest and the second nearest targets located in the on-path of the vehicle are selected by cutting into the inverted trapezoidal region, and the left and right adjacent nearest targets are selected by cutting out the inverted trapezoidal region. At the same time, the entering / leaving judgment of the target is realized by using a smaller inner funnel and a larger outer funnel, so that the target is difficult to enter and exit, and the frequent switching of the target is avoided.

[0052] An embodiment of the present application provides a target screening method, which mainly uses the following means:

[0053] 1. Inverted trapezoidal target screening method: according to the detection performance of a sensor, an inverted trapezoidal region is designed for target screening. By surrounding the funnel track around the ego vehicle predicted track, the funnel center is formed according to the direction of the ego vehicle predicted track. The entering / leaving judgment of the target is realized by using a smaller inner funnel and a larger outer funnel, so that the target is difficult to enter and exit.

[0054] Among them, the inner funnel is mainly used for target entering scene, that is, in the process of vehicle driving, when a target object approaches or prepares to enter the vehicle driving path, the inner funnel is responsible for detecting and responding to this situation. Its calculation formula and logic are designed to meet the needs in this specific situation.

[0055] The outer funnel is mainly used for target leaving scene, that is, in the process of vehicle driving, when the target object has exceeded the vehicle and is preparing to leave the vehicle driving path, the outer funnel is responsible for detecting and responding to this situation. Its calculation formula and logic are also designed to meet the needs in this situation.

[0056] In short, the inner funnel and the outer funnel play different roles in the process of vehicle driving. The former focuses on the target that is about to enter the vehicle path, and the latter focuses on the target that has exceeded the vehicle. The design and use of these two funnels are to enhance the safety of vehicle driving and ensure that the vehicle can effectively avoid potential collision risks under various driving conditions.

[0057] 2. Inverted trapezoid cut-in and cut-out: according to the position and distance of the target, the nearest on-path target and the left and right adjacent nearest target are selected using the inverted trapezoid cut-in area and the inverted trapezoid cut-out area. By adjusting the lateral threshold, the selection degree of the target is controlled according to the distance of the target from the longitudinal distance of the ego vehicle, to avoid misselection.

[0058] 3. Constraint selection: in the target judgment process, target selection is performed according to specific constraint conditions. By comprehensively judging the longitudinal distance, lateral distance, speed, etc. of the target, the target is selected by constraint to avoid misselection and false triggering of the brake.

[0059] Figure 1 A specific implementation is shown, Figure 1 A flowchart of a target screening method provided for an embodiment of the present application is shown in Figure 1 The method comprises:

[0060] Step 102, acquiring detection data detected by a sensor.

[0061] In the embodiment of the present application, each step is executed by an ACC system or a control unit thereof.

[0062] In the embodiment of the present application, the front road environment can be detected by using sensors such as vehicle-mounted cameras, radars or LiDARs. These sensors can detect road information (such as lane line width, left and right lane line distance and / or lane line curvature), measure the longitudinal distance, lateral distance, speed, acceleration, direction and target type (sedan, truck, two-wheeled vehicle) of the front object, and the speed, acceleration, position, etc. of the ego vehicle.

[0063] Step 104, determining the distance between the target and the ego vehicle according to the detection data.

[0064] In the embodiment of the present application, if the distance between the target and the ego vehicle is within a first threshold range, the target is determined as a near-distance target; or, if the distance between the target and the ego vehicle is within a second threshold range, the target is determined as a middle-distance target; or, if the distance between the target and the ego vehicle is within a third threshold range, the target is determined as a far-distance target, wherein the first threshold range is smaller than the second threshold range, and the second threshold range is smaller than the third threshold range. The first threshold range includes a numerical range smaller than a first set distance, the second threshold range includes a numerical range greater than or equal to the first set distance and smaller than a second set distance, and the third threshold range includes a numerical range greater than or equal to the second set distance. The first set distance, the second set distance and the third set distance can be set according to actual conditions. For example, the first set distance is 50 meters, and the second set distance is 100 meters.

[0065] As an alternative, in the process of target screening, the target is first judged according to the detection data of the sensor in terms of distance. The near-distance target (such as within 50 meters from the ego vehicle) is first determined because it has a direct impact on the driving safety of the ego vehicle and needs to be processed in priority. Then, the medium-distance target (such as 50-100 meters from the ego vehicle) and the far-distance target (more than 100 meters) are screened. This order helps the system to process the targets of different distances gradually according to importance and urgency, ensuring safe driving while improving the response speed and accuracy of the system.

[0066] In the embodiment of the application, the distance of the target from the ego vehicle can include a longitudinal distance and a lateral distance. The longitudinal distance refers to the distance of the target from the ego vehicle along the driving direction (i.e. the direction from the front to the rear of the vehicle). In the ACC system, the longitudinal distance is a key factor for judging whether the target vehicle constitutes a potential threat and whether the speed of the ego vehicle needs to be adjusted to maintain a safe distance. The lateral distance refers to the distance of the target from the ego vehicle in the direction of the vehicle width (i.e. perpendicular to the driving direction). The lateral distance is mainly used to judge whether the target vehicle is in the lane of the ego vehicle or in the adjacent lane, and whether the target vehicle has a tendency to cut into the lane of the ego vehicle. For example, a range of longitudinal distance (such as a minimum of 4.2 meters and a maximum of 150 meters) and corresponding lateral distance thresholds under different longitudinal distances can be set. In this way, the screening conditions can be dynamically adjusted according to the real-time position and speed of the target, ensuring that the selected target meets the safety requirements and achieves efficient cruise control.

[0067] Step 106, determining the type of the inverted trapezoidal region according to the distance of the target from the ego vehicle.

[0068] In the embodiment of the application, if the target is determined to be a near-distance target, the type of the inverted trapezoidal region is determined to be a cut-in inverted trapezoidal region; or if the target is determined to be a medium-distance target or a far-distance target, the type of the inverted trapezoidal region is determined to be a cut-out inverted trapezoidal region.

[0069] Figure 2 A schematic diagram of the cut-in inverted trapezoidal region and the cut-out inverted trapezoidal region provided for an embodiment of the application is shown in FIG. 1. Figure 2As shown, ego is the ego car, the top width of the cut-in inverted trapezoidal region is narrow, which means that the lateral tolerance for close-range targets is small. The top width of the cut-out inverted trapezoidal region is wide, allowing greater lateral deviation to accommodate errors that may occur when detecting distant targets. The larger area on the outside is called the cut-out inverted trapezoidal region, which is used to select the left and right nearest targets; the smaller area on the inside is called the cut-in inverted trapezoidal region, which is used to select the on-path nearest and second nearest targets. Cut-in and cut-out are a way of judging selected targets, ensuring that target selection meets safety requirements and avoids misselection. If the target has been selected, the target will continue to be selected and will act until the target crosses the trapezoidal boundary released by the target, and will not act on the target car; if the target has not been selected (has not crossed the trapezoidal boundary selected by the target), the target will not be selected when it enters the buffer zone until it crosses the trapezoidal boundary selected by the target.

[0070] Figure 3 A schematic diagram of a cut-in inverted trapezoidal judgment boundary and a cut-out inverted trapezoidal judgment boundary provided for an embodiment of the present application is shown in FIG. 1. Figure 3 As shown, the cut-in inverted trapezoidal judgment boundary is the boundary of the cut-in inverted trapezoidal region, and the cut-out inverted trapezoidal judgment boundary is the boundary of the cut-out inverted trapezoidal region.

[0071] In an embodiment of the present application, the cut-in inverted trapezoidal region is used to select the nearest and second nearest targets in the driving direction of the ego car and the longitudinal distance from the ego car, and the first lateral threshold can be adjusted according to the longitudinal distance in the driving direction of the ego car and the target type of the target to control the degree of selection of the target; or the cut-out inverted trapezoidal region is used to select the left and right nearest targets in the driving direction of the ego car, and the second lateral threshold can be adjusted according to the longitudinal distance in the driving direction of the ego car and the target type of the target to control the degree of selection of the target.

[0072] In an embodiment of the present application, if the speed of the target is similar to that of the ego car and the longitudinal distance is close (e.g., within the cut-in inverted trapezoidal region), the first lateral threshold of the target can be reduced to make it easier to be selected. For targets with similar speeds but far away in the longitudinal direction (e.g., in the cut-out inverted trapezoidal region), the system will increase the second lateral threshold, making it relatively difficult to be selected, thereby avoiding misselection.

[0073] In the embodiments of the present application, the step of "adjusting the first lateral threshold" or "adjusting the second lateral threshold" is obtained by comprehensively judging the longitudinal distance, speed and lateral distance of the target in the process of target screening. The first lateral threshold or the second lateral threshold can be adjusted according to the distance setting table. The distance setting table is used to provide the lateral distance setting reference of the cut-in and cut-out of different target types (such as cars, trucks, and two-wheeled vehicles) at different longitudinal distances. In the actual target screening process, the first lateral threshold or the second lateral threshold can be dynamically adjusted according to the real-time detection data combined with the distance setting table, instead of only looking up a fixed value. This lookup process is to provide a benchmark value or reference range, but the actual adjustment is made according to the real-time situation. Therefore, "adjusting the first lateral threshold" or "adjusting the second lateral threshold" is a process of comprehensively considering multiple factors such as detection data, target type, longitudinal distance, speed and lateral distance. Adjusting the first lateral threshold or the second lateral threshold is to more accurately select the target, avoid misselection and false triggering of the brake, and improve the safety and performance of the system.

[0074] In the embodiments of the present application, Table One is the distance setting table of a car, as shown in the following Table One.

[0075] Table One

[0076]

[0077]

[0078] The cut-in lateral distance refers to the distance between the inner edge of the front wheel and the side of the vehicle body when the vehicle is turning. This parameter affects the stability and maneuverability of the vehicle when turning, as well as the minimum clearance between the wheel and the vehicle body. The cut-out lateral distance refers to the distance between the outer edge of the front wheel and the side of the vehicle body when the vehicle is turning. This parameter also affects the stability and maneuverability of the vehicle, especially at high speeds or during emergency turns.

[0079] Table Two is the distance setting table of a two-wheeled vehicle, as shown in the following Table Two.

[0080] Table Two

[0081]

[0082] Table Three is the distance setting table of a two-wheeled vehicle, as shown in the following Table Three.

[0083] Table Three

[0084]

[0085]

[0086] From the above table, because the sizes of different targets are different, offset compensation based on the calibrated standard lateral distance is needed when selecting the cut-in and cut-out of different targets. The lateral distance of a car type can be used as a standard value, and the distance setting value is as follows: according to the distance between the ego vehicle and the front vehicle, the lateral distance is interpolated, and then the truck risk coefficient is compared, so the distance is larger than that of a car, that is, it is selected earlier; the two-wheeled vehicle is small in size and width, so the distance is smaller than that of a car, and it is selected later.

[0087] In the embodiment of the application, the cut-in inverted trapezoidal region is used to select the target closest and the second closest to the longitudinal distance of the ego vehicle in the driving direction of the ego vehicle, or the cut-out inverted trapezoidal region is used to select the target closest to the left and right adjacent of the ego vehicle in the driving direction of the ego vehicle. The reasons for processing mainly include the following points:

[0088] Safety and priority: that is, the target on the predicted trajectory of the ego vehicle has a direct impact on the driving safety of the ego vehicle, so it is necessary to prioritize the selection and processing of these targets. The cut-in inverted trapezoidal region can accurately identify and process these targets to ensure safe driving.

[0089] Avoiding misselection and misoperation: the left and right adjacent closest target is usually a potential safety threat, such as a vehicle suddenly cutting into the side lane. By using the cut-out inverted trapezoidal region, the target can be identified in time, and the selection can be screened according to factors such as longitudinal distance, speed and lateral distance, to avoid misselection and misoperation, and to improve driving safety.

[0090] Optimizing target selection: by comprehensively considering the distance, speed, lateral distance and other factors of the target, and combining the cut-in inverted trapezoidal region and the cut-out inverted trapezoidal region, the target can be more accurately selected to avoid misselection and misoperation, so as to optimize the target selection process and improve the performance and safety of the ACC system.

[0091] Adapting to different scenarios: in the actual driving process, the road environment in front is complex and variable, and there are many types of targets and scenes. By using the cut-in inverted trapezoidal region and the cut-out inverted trapezoidal region, different scenarios and target types can be adapted to realize more flexible and accurate target selection and processing.

[0092] In summary, the cut-in inverted trapezoidal region or the cut-out inverted trapezoidal region can be determined according to the distance of each detection object, and the target closest and the second closest to the longitudinal distance of the ego vehicle in the driving direction of the ego vehicle and the target closest to the left and right adjacent of the ego vehicle are processed in priority, in order to ensure driving safety, optimize the target selection process and adapt to different scenarios and target types.

[0093] Step 108, target screening according to detection data and type of inverted trapezoidal region.

[0094] In the embodiment of the present application, after determining the type of the inverted trapezoidal region, the target can be screened according to the longitudinal distance, speed and lateral distance of the target. The main purpose of this screening process is to accurately select the target to be tracked and controlled from a large number of detected objects.

[0095] Figure 4 The flowchart for screening the target according to the detection data and the type of the inverted trapezoidal region provided by an embodiment of the present application is shown in Figure 4 As shown in FIG. 8, step 108 includes:

[0096] Step 1082, determining the inverted trapezoidal region according to the detection data.

[0097] In the embodiment of the present application, the inverted trapezoid is a shape obtained by rotating a trapezoid counterclockwise by 90°.

[0098] Step 1084, generating the funnel trajectory before adjustment according to the inverted trapezoidal region.

[0099] In the embodiment of the present application, the target entering and exiting the trapezoidal region of the inverted trapezoid is metaphorically a funnel shape.

[0100] Step 1086, adjusting the funnel trajectory before adjustment according to the predicted trajectory of the ego vehicle to generate the funnel trajectory.

[0101] In the embodiment of the present application, if the predicted trajectory of the ego vehicle is a straight road, the funnel shape is a fixed angle included angle shape formed with the ego vehicle as the center. If the predicted trajectory of the ego vehicle is a curve (driving trajectory direction), then according to the left turn or right turn, the funnel shape is automatically curved towards the tangent of the curve.

[0102] In the embodiment of the present application, the funnel center refers to the geometric center of the funnel trajectory in the inverted trapezoidal region. The position of the center will be curved according to the predicted trajectory direction. The funnel center is determined after the funnel trajectory is curved according to the predicted trajectory of the ego vehicle. The shape of the funnel trajectory can be adjusted according to the direction of the predicted trajectory of the ego vehicle, so that the funnel center moves along with the curvature of the predicted trajectory of the ego vehicle. The purpose of this step is to make the funnel trajectory more fit the predicted path in actual driving, thereby improving the accuracy and effectiveness of target screening. Specifically, when the predicted trajectory of the ego vehicle changes (such as turning, changing lanes, etc.), the funnel trajectory will adjust its shape and direction accordingly to adapt to the new predicted trajectory, ensuring that the funnel center is always located at the appropriate position of the predicted trajectory. Such design helps to avoid inaccurate target screening or misjudgment problems caused by changes in the predicted trajectory during driving.

[0103] Specifically, the step of "adjusting the shape of the funnel trajectory based on the direction of the ego vehicle predicted trajectory, so that the funnel center moves following the bends of the ego vehicle predicted trajectory" can be described as a key step in the target screening method, which adjusts the funnel shape and funnel center based on the ego vehicle predicted trajectory. To describe or generalize how to generate the funnel trajectory more specifically, it can be broken down into the following steps:

[0104] Probe data collection: Collect ego vehicle driving data through on-board sensors such as cameras, radars, lidars, etc., including speed, acceleration, direction, and possibly predicted path information.

[0105] Ego vehicle predicted trajectory generation: Based on the collected ego vehicle driving data, generate the ego vehicle predicted trajectory through certain algorithms or models. This ego vehicle predicted trajectory may include straight driving, turning, lane changing, etc.

[0106] Funnel center positioning: Before the bend adjustment, the funnel center may be a fixed point or location. However, after introducing the ego vehicle predicted trajectory, the system will determine the position of the funnel center that needs to be adjusted according to the direction of the ego vehicle predicted trajectory.

[0107] Funnel bend adjustment: According to the ego vehicle predicted trajectory, adjust the funnel trajectory. The purpose of this adjustment is to make the center point and trajectory shape of the funnel more consistent with the bends of the ego vehicle predicted trajectory, to ensure that the funnel can accurately cover and screen out targets related to the ego vehicle predicted trajectory.

[0108] Real-time update: With real-time updates of ego vehicle driving data, the funnel center and funnel trajectory need to be continuously adjusted according to new ego vehicle predicted trajectories to maintain accurate screening and tracking of targets. It is more close to how to dynamically generate and adjust the funnel trajectory and funnel center according to the ego vehicle driving data and ego vehicle predicted trajectory in actual driving, so as to ensure accurate and efficient screening of targets related to ego vehicle driving in complex driving environments.

[0109] Step 1088, screen the target according to the funnel trajectory and the type of inverted trapezoidal area, generate the initial screening target and the dynamic data of the initial screening target.

[0110] In the embodiment of the present application, the dynamic data includes speed, acceleration and position.

[0111] Step 1090, according to the dynamic data, use the interpolation curve algorithm to predict the future motion trajectory of the target.

[0112] In the embodiment of the present application, the role of the interpolation curve algorithm in this process is mainly to predict the future motion trajectory of the target based on the dynamic data of the target, to further optimize the selection of the target.

[0113] In the embodiments of the present application, step 1090 specifically includes:

[0114] Interpolation curve selection: According to the characteristics of the collected dynamic data, a suitable interpolation curve algorithm can be selected. Common interpolation curve algorithms include polynomial interpolation, spline interpolation, etc., which can generate smooth and continuous curves based on discrete data points.

[0115] Curve fitting: The collected position of the target (usually time series data) is used as input, and the selected interpolation curve algorithm is used for fitting. During this process, the parameters of the interpolation curve can be adjusted according to the distribution characteristics and dynamic trends of the data, so as to accurately reflect the motion state of the target vehicle as much as possible.

[0116] Prediction of the future motion trajectory of the target: After the interpolation curve fitting is completed, the position of the target at a certain time in the future can be predicted according to the current detection data of the target and the trend of the curve. This process usually needs to consider factors such as time step, prediction accuracy, etc., to ensure the reliability and practicality of the prediction results.

[0117] Trajectory output: According to the future motion trajectory of the target, corresponding control decisions are made.

[0118] Step 1092, according to the future motion trajectory of the target and the set target constraint condition, the target is selected from the preliminary screening target.

[0119] In the embodiments of the present application, the target constraint condition can be set according to the actual situation, for example, the target constraint condition can include the following conditions:

[0120] Lateral distance and longitudinal distance: The relative position of the target's lateral distance and longitudinal distance to the ego vehicle can be used for screening. For example, for the target corresponding to the cut-in inverted trapezoidal area, a longitudinal minimum distance (such as 4.2 meters) and a longitudinal maximum distance (such as 150 meters) can be set to ensure that only the target with appropriate distance on the predicted trajectory of the ego vehicle is selected. At the same time, the lateral threshold can be dynamically adjusted according to the lateral position of the target (i.e. the relative position to the ego vehicle lane) and the distance of the longitudinal distance, so as to control the degree of selection of the target.

[0121] Target type: The target type of the front target (such as car, truck, two-wheeled vehicle, etc.) can be identified, and different target types can be screened according to their characteristics and potential danger levels. For example, since trucks are usually larger and heavier than cars, a wider lateral threshold and a longer longitudinal distance threshold can be set for trucks to identify and select them as potential tracking targets earlier. On the contrary, for smaller two-wheeled vehicles, a narrower lateral threshold and a closer longitudinal distance threshold can be set to avoid misselection.

[0122] Speed: Speed is also an important factor to consider when screening targets. The speed difference between the front target and the ego vehicle can be compared, and the targets can be screened according to the proximity of the speed. For example, if the speed of the target is similar to that of the ego vehicle, and the longitudinal distance is moderate, the lateral threshold of the target can be reduced, so that it is easier to be selected as the tracking target. On the contrary, if the speed of the target is too fast or too slow, and the speed difference with the ego vehicle is large, the lateral threshold can be increased or excluded from the screening range.

[0123] In summary, the above three aspects can be comprehensively judged according to multiple target constraint conditions such as lateral distance, longitudinal distance, target type and speed, to further screen the front target, so as to ensure that the selected target meets the requirements of safe driving, and improves the performance and comfort of the ACC system. The specific logic may differ depending on the vehicle model, sensor performance and system design.

[0124] In the technical scheme provided by the embodiment of the application, the detection data detected by the sensor is acquired; the distance between the target and the ego vehicle is determined according to the detection data; the type of the inverted trapezoidal area is determined according to the distance between the target and the ego vehicle; and the target is screened according to the detection data and the type of the inverted trapezoidal area. In the technical scheme provided by the embodiment of the application, the target is screened according to the detection data and the type of the inverted trapezoidal area, which improves the accuracy of target screening and the safety of driving.

[0125] In the technical scheme provided by the embodiment of the application, the direction of the predicted trajectory of the ego vehicle and the detection performance of the sensor can be used to screen the target in the target selection process, so as to avoid misselecting the target and triggering the brake, and improve the performance and safety of the ACC system.

[0126] In the technical scheme provided by the embodiment of the application, the inverted trapezoidal target screening method is introduced, and the target is more accurately screened according to the sensor detection performance and the future motion trajectory of the target. The funnel trajectory can be bent according to the direction of the predicted motion trajectory, so as to avoid the problems of misselecting the target and frequently switching the target.

[0127] In the technical scheme provided by the embodiment of the application, a smaller "inner funnel" and a larger "outer funnel" are used for target entry / exit judgment. This design can realize the "difficult entry and difficult exit" of the target, avoid the problems of misselecting the target and triggering the brake due to inaccurate sensing, speed measurement and distance measurement, and improve the accuracy of target screening.

[0128] The technical scheme provided by the embodiment of the present application considers the comprehensive factors of longitudinal distance, speed and lateral distance for cutting into a target. Under the same speed of a target vehicle, the closer the longitudinal distance of a target is, the smaller the lateral threshold is, and the target is more likely to be selected, so as to reflect the ability of identifying a cutting-in target. Under the same speed, the farther the target is, the larger the lateral threshold is, and the target is less likely to be selected, so as to avoid the situation of misselection.

[0129] An embodiment of the present application provides a target screening device. Figure 5 A structural schematic diagram of the target screening device provided by an embodiment of the present application is shown in the figure, and the device comprises an acquisition module 11, a first determination module 12, a second determination module 13 and a screening module 14. Figure 5 The acquisition module 11 is used for acquiring detection data detected by a sensor.

[0130] The first determination module 12 is used for determining the distance between a target and a vehicle according to the detection data.

[0131] The second determination module 13 is used for determining the type of an inverted trapezoidal area according to the distance between the target and the vehicle.

[0132] The screening module 14 is used for screening a target according to the detection data and the type of the inverted trapezoidal area.

[0133] In the embodiment of the present application, the first determination module 12 is specifically used for determining the target as a near-distance target if the distance between the target and the vehicle is located in a first threshold range, or determining the target as a middle-distance target if the distance between the target and the vehicle is located in a second threshold range, or determining the target as a far-distance target if the distance between the target and the vehicle is located in a third threshold range; the first threshold range is smaller than the second threshold range, and the second threshold range is smaller than the third threshold range.

[0134] In the embodiment of the present application, the second determination module 13 is specifically used for determining the type of the inverted trapezoidal area as a cutting-in inverted trapezoidal area if the target is determined as a near-distance target, or determining the type of the inverted trapezoidal area as a cutting-out inverted trapezoidal area if the target is determined as a middle-distance target or a far-distance target.

[0135] In the embodiment of the present application, the cutting-in inverted trapezoidal area is used to select the target closest to and the target next closest to the vehicle in the driving direction of the vehicle in the longitudinal distance; or the cutting-out inverted trapezoidal area is used to select the target closest to the vehicle on the left and the target closest to the vehicle on the right in the lateral distance.

[0136] In the embodiment of the present application, the cutting-in inverted trapezoidal area is used to select the target closest to and the target next closest to the vehicle in the driving direction of the vehicle in the longitudinal distance; or the cutting-out inverted trapezoidal area is used to select the target closest to the vehicle on the left and the target closest to the vehicle on the right in the lateral distance.

[0137] In the embodiment of the present application, the second determining module 13 is specifically configured to adjust the first lateral threshold to control the selection degree of the target according to the longitudinal distance from the ego vehicle in the driving direction of the ego vehicle and the target type of the target; and adjust the second lateral threshold to control the selection degree of the target according to the longitudinal distance from the ego vehicle in the driving direction of the ego vehicle and the target type of the target.

[0138] In the embodiment of the present application, the screening module 14 is specifically configured to generate a funnel trajectory according to the detection data and the predicted trajectory of the ego vehicle; screen the target according to the funnel trajectory and the type of the inverted trapezoidal region to generate the primary screening target and the dynamic data of the primary screening target; predict the future motion trajectory of the target by using an interpolation curve algorithm according to the dynamic data; and screen the target from the primary screening target according to the future motion trajectory of the target and the set target constraint condition.

[0139] In the embodiment of the present application, the screening module 14 is specifically configured to determine the inverted trapezoidal region according to the detection data; generate the funnel trajectory before adjustment according to the inverted trapezoidal region; and generate the funnel trajectory by adjusting the funnel trajectory before adjustment according to the predicted trajectory of the ego vehicle.

[0140] In the technical scheme provided by the embodiment of the present application, the detection data detected by the sensor is acquired; the distance between the target and the ego vehicle is determined according to the detection data; the type of the inverted trapezoidal region is determined according to the distance between the target and the ego vehicle; and the target is screened according to the detection data and the type of the inverted trapezoidal region. In the technical scheme provided by the embodiment of the present application, the target is screened according to the detection data and the type of the inverted trapezoidal region, which improves the accuracy of target screening and the safety of driving.

[0141] The target screening device provided by the embodiment of the present application can be used to implement the target screening method in the above Figure 1 The specific description can be referred to the embodiments of the target screening method described above, which will not be described herein.

[0142] The embodiment of the present application provides a storage medium, which includes a stored program, wherein when the program is running, the device where the storage medium is located is controlled to perform each step of the embodiments of the target screening method described above, and the specific description can be referred to the embodiments of the target screening method described above.

[0143] The embodiment of the present application provides an ACC system or a control unit thereof, which includes a memory and a processor, the memory is used to store information including program instructions, and the processor is used to control the execution of the program instructions, the program instructions are loaded and executed by the processor to realize each step of the embodiments of the target screening method described above, and the specific description can be referred to the embodiments of the target screening method described above.

[0144] Figure 6 A schematic diagram of an ACC system or a control unit thereof provided by the embodiment of the present application is shown in FIG. 1.Figure 6 As shown, the ACC system or the control unit 20 of the embodiment includes a processor 21, a memory 22, and a computer program 23 stored in the memory 22 and executable on the processor 21, which, when executed by the processor 21, implements the application to the target screening method in the embodiment. For the sake of brevity, the functions of the computer program 23 to the models / cells in the target screening device in the embodiment will not be repeated here. Alternatively, the computer program 23, when executed by the processor 21, implements the functions of the models / cells in the target screening device in the embodiment. For the sake of brevity, the functions of the computer program 23 to the models / cells in the target screening device in the embodiment will not be repeated here.

[0145] The ACC system or the control unit 20 includes, but is not limited to, the processor 21 and the memory 22. Those skilled in the art can understand that the ACC system or the control unit 20 can include more or fewer components, or combine certain components, or include different components, such as input / output devices, network access devices, buses, etc. Figure 6 The ACC system or the control unit 20 is only an example and does not limit the ACC system or the control unit 20, which can include more or fewer components than shown, or combine certain components, or include different components, such as input / output devices, network access devices, buses, etc.

[0146] The processor 21 can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0147] The memory 22 can be an internal storage unit of the ACC system or the control unit 20, such as a hard disk or a memory of the ACC system or the control unit 20. The memory 22 can also be an external storage device of the ACC system or the control unit 20, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. Further, the memory 22 can include both internal storage units and external storage devices of the ACC system or the control unit 20. The memory 22 is used to store computer programs and other programs and data required by the ACC system or the control unit. The memory 22 can also be used to temporarily store data that has been output or will be output.

[0148] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described system, device and unit can refer to the corresponding processes in the foregoing method embodiments, which will not be repeated here.

[0149] In several embodiments provided by the present application, it should be understood that the disclosed system, device and method can be implemented by other manners. For example, the above-described device embodiments are only schematic, for example, the division of the units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interfaces, devices or units, and can be electrical, mechanical or other forms.

[0150] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, that is, can be located in one place, or can be distributed on a plurality of network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0151] In addition, each functional unit in each embodiment of the present application can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of hardware plus software functional unit.

[0152] The integrated unit realized in the form of software functional unit can be stored in a computer readable storage medium. The software functional unit stored in a storage medium includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to execute part of the steps of the method described in each embodiment of the present application. The foregoing storage medium includes a variety of program code storage media such as a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0153] The above only describes the preferred embodiments of the present application and is not intended to limit the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method of target screening, characterized by, The method comprises the following steps: obtaining detection data detected by a sensor; determining the distance between a target and the ego vehicle according to the detection data; determining the type of the inverted trapezoidal region according to the distance between the target and the ego vehicle; screening the target according to the detection data and the type of the inverted trapezoidal region; the step of determining the type of the inverted trapezoidal region according to the distance between the target and the ego vehicle comprises: if the target is determined to be a close-range target, the type of the inverted trapezoidal region is determined to be a cut-in inverted trapezoidal region, and the closest and the second closest targets to the ego vehicle in the driving direction of the ego vehicle are selected by using the cut-in inverted trapezoidal region; or, if the target is determined to be a medium-range target or a long-range target, the type of the inverted trapezoidal region is determined to be a cut-out inverted trapezoidal region, and the left and right closest targets to the ego vehicle in the driving direction of the ego vehicle are selected by using the cut-out inverted trapezoidal region, wherein the top width of the cut-in inverted trapezoidal region is smaller than the top width of the cut-out inverted trapezoidal region.

2. The method of claim 1, wherein, the step of determining the distance between the target and the ego vehicle according to the detection data comprises: if the distance between the target and the ego vehicle is within a first threshold range, the target is determined to be a close-range target; or, if the distance between the target and the ego vehicle is within a second threshold range, the target is determined to be a medium-range target; or, if the distance between the target and the ego vehicle is within a third threshold range, the target is determined to be a long-range target. The first threshold range is smaller than the second threshold range, and the second threshold range is smaller than the third threshold range.

3. The method of claim 1, wherein, after the step of selecting the closest and the second closest targets to the ego vehicle in the driving direction of the ego vehicle by using the cut-in inverted trapezoidal region, the method further comprises the following steps: adjusting a first lateral threshold according to the longitudinal distance between the ego vehicle and the target in the driving direction of the ego vehicle and the target type of the target to control the selection degree of the target; after the step of selecting the left and right closest targets to the ego vehicle in the driving direction of the ego vehicle by using the cut-out inverted trapezoidal region, the method further comprises the following steps: adjusting a second lateral threshold according to the longitudinal distance between the ego vehicle and the target in the driving direction of the ego vehicle and the target type of the target to control the selection degree of the target.

4. The method of claim 1, wherein, the step of screening the target according to the detection data and the type of the inverted trapezoidal region comprises: generating a funnel trajectory according to the detection data and the predicted trajectory of the ego vehicle; screening the target according to the funnel trajectory and the type of the inverted trapezoidal region to generate primary screening targets and dynamic data of the primary screening targets; predicting the future motion trajectory of the target by using an interpolation curve algorithm according to the dynamic data to generate the future motion trajectory of the target; screening the target from the primary screening targets according to the future motion trajectory of the target and a set target constraint condition.

5. The method of claim 4, wherein, the step of generating the funnel trajectory according to the detection data and the predicted trajectory of the ego vehicle comprises: determining an inverted trapezoidal region according to the detection data; generating an unadjusted funnel trajectory according to the inverted trapezoidal region; adjusting the unadjusted funnel trajectory according to the predicted trajectory of the ego vehicle to generate the funnel trajectory.

6. A target screening device, characterized by, The method comprises the following steps: an obtaining module, configured to obtain detection data detected by a sensor; a first determining module, configured to determine the distance between a target and the ego vehicle according to the detection data; A second determining module is configured to determine the type of the inverted trapezoidal region according to the distance between the target and the ego vehicle; A screening module is configured to screen the target according to the detection data and the type of the inverted trapezoidal region; The second determining module is specifically configured to: if the target is determined as a close-range target, determine the type of the inverted trapezoidal region as a cut-in inverted trapezoidal region, and select the target closest to and the second closest to the ego vehicle in the longitudinal direction of the ego vehicle using the cut-in inverted trapezoidal region; or if the target is determined as a medium-range target or a far-range target, determine the type of the inverted trapezoidal region as a cut-out inverted trapezoidal region, and select the target closest to the ego vehicle in the left and right directions using the cut-out inverted trapezoidal region, wherein the top width of the cut-in inverted trapezoidal region is smaller than the top width of the cut-out inverted trapezoidal region.

7. A storage medium, characterized by The storage medium comprises a stored program, wherein the program controls the device where the storage medium is located to execute the target screening method in any one of claims 1 to 5 when the program is running.

8. An adaptive cruise control system comprising a memory for storing information including program instructions and a processor for controlling execution of the program instructions, characterized in that, The program instructions are loaded and executed by the processor to implement the steps of the target screening method in any one of claims 1 to 5.

Images