Target screening method and device, storage medium and ACC system or control unit thereof
By employing a target selection method based on an inverted trapezoidal region and a funnel trajectory, the problem of misidentification in target selection within adaptive cruise control systems was solved, achieving higher accuracy and safety.
Patent Information
- Application Number
- CN202411267280.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-10
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2044-09-10
AI Technical Summary
Existing adaptive cruise control systems have issues with target selection, such as misidentifying objects cutting in from the side, slowing down late, or selecting objects that do not intrude, resulting in incorrect braking and lower driving safety.
The target selection method adopts inverted trapezoidal region and funnel trajectory. The distance between the target and the vehicle is determined by sensor detection data, the inverted trapezoidal region type is divided, and the target is selected by cutting into and cutting out of the inverted trapezoidal region. The interpolation curve algorithm and target constraints are combined to perform accurate selection.
It improves the accuracy of target selection and driving safety, avoids misselection and accidental braking, and enhances the performance and safety of the ACC system.
Smart Images

Figure CN118953385A_ABST
Abstract
Description
[Technical field]
[0001] The present invention relates to the technical field of intelligent connected vehicles, and in particular to a target screening method, device, storage medium and an ACC system or a control unit thereof. [Background technology]
[0002] Adaptive Cruise Control (ACC) is an intelligent driving assistance system for automobiles that can automatically adjust the speed of the vehicle to maintain a safe distance based on the speed and distance of the vehicle in front. At present, conventional ACC systems have some problems in target selection, that is, selecting targets based on the nearest principle may lead to misidentification of nearby targets, late deceleration or no intrusion, and may also be selected for false braking. The accuracy of target selection is low, making driving less safe. [Summary of the invention]
[0003] In view of this, embodiments of the present invention provide a target screening method, device, storage medium, and ACC system or its control unit to improve the accuracy of target screening and driving safety.
[0004] On the one hand, an embodiment of the present invention provides a target screening method, comprising:
[0005] Acquire detection data detected by the sensor;
[0006] Determine the distance between the target and the vehicle according to the detection data;
[0007] Determining the type of the inverted trapezoidal area according to the distance between the target and the vehicle;
[0008] Target screening is performed according to the detection data and the type of the inverted trapezoidal area.
[0009] Optionally, determining the distance between the target and the vehicle according to the detection data includes:
[0010] If the distance between the target and the vehicle is within a first threshold range, the target is determined as a close-range target; or,
[0011] If the distance between the target and the vehicle is within a second threshold range, the target is determined as a medium-distance target; or,
[0012] If the distance between the target and the vehicle is within a third threshold range, the target is determined as a long-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, determining the type of the inverted trapezoidal area according to the distance between the target and the vehicle includes:
[0015] If the target is determined to be a close-range target, the type of the inverted trapezoidal area is determined to be a cut-in inverted trapezoidal area; or,
[0016] If the target is determined to be a medium-distance target or a long-distance target, the type of the inverted trapezoidal area is determined to be a cut-out inverted trapezoidal area.
[0017] Optionally, the cut-in inverted trapezoidal area is used to select the target that is closest and second closest to the longitudinal distance of the vehicle in the direction of travel of the vehicle; or, the cut-out inverted trapezoidal area is used to select the target that is closest to the left and right of the vehicle in the direction of travel of the vehicle.
[0018] Optionally, after using the cut-in inverted trapezoidal area to select the target that is closest and second closest to the longitudinal distance of the vehicle in the driving direction of the vehicle, the method further comprises:
[0019] adjusting a first lateral threshold to control the degree of selection of the target according to the longitudinal distance from the ego vehicle in the direction of travel of the ego vehicle and the target type of the target;
[0020] After using the cut-out inverted trapezoidal area to select the target closest to the left and right sides of the vehicle in the direction of travel of the vehicle, the method includes:
[0021] According to the longitudinal distance from the vehicle in the driving direction of the vehicle and the target type of the target, the second lateral threshold is adjusted to control the degree of selection of the target.
[0022] Optionally, the performing target screening according to the detection data and the type of the inverted trapezoidal region includes:
[0023] generating a funnel trajectory according to the detection data and the obtained ego-vehicle predicted trajectory;
[0024] Screening targets according to the funnel track and the type of the inverted trapezoidal area, generating preliminary screening targets and dynamic data of the preliminary screening targets;
[0025] Based on the dynamic data, an interpolation curve algorithm is used to predict and generate a future motion trajectory of the target;
[0026] Targets are screened out from the initial screening targets according to the future motion trajectory of the target and the set target constraints.
[0027] Optionally, generating a funnel trajectory according to the detection data and the acquired ego-vehicle predicted trajectory includes:
[0028] Determine an inverted trapezoidal area according to the detection data;
[0029] generating a funnel trajectory before adjustment according to the inverted trapezoidal area;
[0030] The funnel trajectory before adjustment is adjusted according to the acquired predicted trajectory of the vehicle to generate the funnel trajectory.
[0031] On the other hand, an embodiment of the present invention provides a target screening device, comprising:
[0032] An acquisition module, used for acquiring detection data detected by the sensor;
[0033] A first determination module is used to determine the distance between the target and the vehicle according to the detection data;
[0034] A second determination module is used to determine the type of the inverted trapezoidal area according to the distance between the target and the vehicle;
[0035] A screening module is used to screen targets according to the detection data and the type of the inverted trapezoidal area.
[0036] On the other hand, an embodiment of the present invention provides a storage medium, which includes a stored program, wherein when the program is executed, the device where the storage medium is located is controlled to execute the above-mentioned target screening method.
[0037] On the other hand, an embodiment of the present invention provides an adaptive cruise control system or a control unit thereof, comprising a memory and a processor, wherein the memory is used to store information including program instructions, and the processor is used to control the execution of the program instructions, wherein the program instructions implement the steps of the above-mentioned target screening method when loaded and executed by the processor.
[0038] In the technical solution of the target screening method provided by the embodiment of the present invention, detection data detected by the sensor is obtained; the distance between the target and the 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 vehicle; and the target is screened according to the detection data and the type of the inverted trapezoidal area. In the technical solution provided by the embodiment of the present invention, the target is screened according to the detection data and the type of the inverted trapezoidal area, which improves the accuracy of the target screening and the safety of driving.
Brief Description of the Drawings
[0039] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.
[0040] Figure 1 A flow chart of a target screening method provided by one embodiment of the present invention;
[0041] Figure 2 A schematic diagram of cutting into and out of an inverted trapezoidal region provided by an embodiment of the present invention;
[0042] Figure 3 A schematic diagram of a cut-in inverted trapezoidal judgment boundary and a cut-out inverted trapezoidal judgment boundary provided by an embodiment of the present invention;
[0043] Figure 4 A flow chart of performing target screening according to detection data and the type of inverted trapezoidal area provided in one embodiment of the present invention;
[0044] Figure 5 A schematic diagram of the structure of a target screening device provided by one embodiment of the present invention;
[0045] Figure 6 A schematic diagram of an ACC system or a control unit thereof provided in an embodiment of the present invention. [Specific implementation method]
[0046] In order to better understand the technical solution of the present invention, the embodiments of the present invention are described in detail below with reference to the accompanying drawings.
[0047] It should be clear that the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0048] The terms used in the embodiments of the present invention are only for the purpose of describing specific embodiments, and are not intended to limit the present invention. The singular forms "a", "said" and "the" used in the embodiments of the present invention and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings.
[0049] It should be understood that the term "and / or" used 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 generally indicates that the associated objects before and after are in an "or" relationship.
[0050] In the related art, there are some problems with the target screening method, such as late recognition of the target cutting in, late deceleration, or even the selection of the wrong brake even if there is no intrusion. These problems are mainly caused by inaccurate perception, speed measurement and distance measurement. In addition, the ACC system in the related art adopts the nearest principle to select the target, without considering the influence of the sensor detection distance on the target recognition accuracy and resolution, which may lead to the wrong selection of the target and the false triggering of the brake.
[0051] In order to solve the technical problems of the above-mentioned related technologies, an embodiment of the present invention provides a target screening method, which is based on the detection performance of the sensor and solves the target screening problem by forming an inverted trapezoidal target screening method. An inverted trapezoidal area is used, and the funnel trajectory surrounds the predicted trajectory of the vehicle, that is, the center of the funnel will bend accordingly according to the direction of the predicted trajectory of the vehicle. This method can effectively solve the problem that the accuracy and resolution of the returned target detection results are worse when the sensor detection distance is farther. Specifically, the inverted trapezoidal area is cut in to select the nearest and second nearest targets located in the driving area (on-path) of the vehicle, and the inverted trapezoidal area is cut out to select the nearest adjacent targets on the left and right. At the same time, by using a smaller inner funnel (Inner Funnel) and a larger outer funnel (Outer Funnel) to judge the entry / exit of the target, the target is "difficult to enter and exit" and the frequent switching of targets is avoided.
[0052] An embodiment of the present invention provides a target screening method, which mainly adopts the following means:
[0053] 1. Target screening method based on inverted trapezoid: According to the detection performance of the sensor, an inverted trapezoidal area is designed for target screening. The funnel track is formed by surrounding the predicted track of the ego vehicle and bending it accordingly according to the direction of the predicted track of the ego vehicle. A smaller inner funnel and a larger outer funnel are used to judge the entry / exit of the target, so as to achieve the "difficult entry and exit" of the target.
[0054] Among them, the internal funnel is mainly used for target entry scenarios, that is, when a target object approaches or is about to enter the vehicle's driving path during the vehicle's driving process, the internal funnel is responsible for detecting and responding to this situation. Its calculation formula and logic are designed to meet the needs of this specific situation.
[0055] The external funnel is mainly used for the target departure scenario, that is, when the target object has surpassed the vehicle and is about to leave the vehicle's path during the vehicle's driving, the external funnel is responsible for detecting and responding to this situation. Its calculation formula and logic are also designed to meet the needs of this situation.
[0056] In short, the inner funnel and the outer funnel play different roles in car driving. The former focuses on the target that is about to enter the vehicle's path, while the latter focuses on the target that has already passed the vehicle. The design and use of these two funnels are to enhance the safety of car driving and ensure that the vehicle can effectively avoid potential collision risks under various driving conditions.
[0057] 2. Cut into the inverted trapezoid and cut out of the inverted trapezoid: According to the position and distance of the target, use the cut into the inverted trapezoid area and cut out of the inverted trapezoid area to select the nearest on-path target and the nearest left and right adjacent targets. By adjusting the lateral threshold, according to the longitudinal distance between the target and the vehicle, the degree of target selection is controlled to avoid misselection.
[0058] 3. Constraint selection: In the process of target judgment, 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 constrained to avoid misselection and mis-triggering of the brakes.
[0059] Figure 1 A specific implementation method is shown. Figure 1 A flow chart of a target screening method provided by one embodiment of the present invention is as follows: Figure 1 As shown, the method includes:
[0060] Step 102: Acquire detection data detected by the sensor.
[0061] In the embodiment of the present invention, each step is executed by the ACC system or its control unit.
[0062] In the embodiment of the present invention, sensors such as vehicle-mounted cameras, radars or laser radar (LiDAR) can be used to detect the road environment ahead. These sensors can detect road information (such as lane width, distance between lanes on the left and right sides and / or lane curvature), measure the longitudinal distance, lateral distance, speed, acceleration, direction and target type (sedan, truck, two-wheeled vehicle) of the object ahead, and the speed, acceleration, position, etc. of the vehicle.
[0063] Step 104: Determine the distance between the target and the vehicle based on the detection data.
[0064] In an embodiment of the present invention, if the distance between the target and the vehicle is within the first threshold range, the target is determined as a short-distance target; or, if the distance between the target and the vehicle is within the second threshold range, the target is determined as a medium-distance target; or, if the distance between the target and the vehicle is within the third threshold range, the target is determined as a long-distance target, wherein the first threshold range is less than the second threshold range, and the second threshold range is less than the third threshold range. The first threshold range includes a numerical range less than the first set distance, the second threshold range includes a numerical range greater than or equal to the first set distance and less than the 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 optional solution, during the target screening process, the distance of the target is first determined based on the detection data of the sensor. Short-distance targets (such as within 50 meters from the vehicle) are determined first because they have a direct impact on the driving safety of the vehicle and need to be processed first. After that, medium-distance targets (such as 50-100 meters from the vehicle) and long-distance targets (more than 100 meters) are screened. This order helps the system gradually process targets of different distances according to their importance and urgency, ensuring safe driving while improving the system's response speed and accuracy.
[0066] In an embodiment of the present invention, the distance between the target and the vehicle may include a longitudinal distance and a lateral distance. The longitudinal distance refers to the distance between the target and the vehicle along the direction of travel (i.e., the direction from the front of the vehicle to the rear of the vehicle). In the ACC system, the longitudinal distance is a key factor in determining whether the target vehicle poses a potential threat and whether the speed of the vehicle needs to be adjusted to maintain a safe distance. The lateral distance refers to the distance between the target and the vehicle in the vehicle width direction (i.e., perpendicular to the direction of travel). The lateral distance is mainly used to determine whether the target vehicle is in the lane where the vehicle is located or in the adjacent lane, and whether the target vehicle has a tendency to cut into the lane of the vehicle. For example, a range of longitudinal distances (such as a minimum of 4.2 meters and a maximum of 150 meters) and corresponding lateral distance thresholds at 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 to ensure that the selected target meets both safety requirements and efficient cruise control.
[0067] Step 106: Determine the type of the inverted trapezoidal area according to the distance between the target and the vehicle.
[0068] In an embodiment of the present invention, if the target is determined to be a close-range target, the type of the inverted trapezoidal area is determined to be a cut-in inverted trapezoidal area; or, if the target is determined to be a medium-range target or a long-range target, the type of the inverted trapezoidal area is determined to be a cut-out inverted trapezoidal area.
[0069] Figure 2 A schematic diagram of cutting into and out of an inverted trapezoidal region provided by an embodiment of the present invention is shown in FIG. Figure 2As shown in the figure, Ego is the ego vehicle, and the top width of the cut-in inverted trapezoidal area is narrow, which means that the lateral tolerance for close-range targets is small. The top width of the cut-out inverted trapezoidal area is wider, allowing a larger lateral deviation to accommodate errors that may occur during long-distance detection. The larger area on the outside is called the cut-out inverted trapezoidal area, which is used to select the nearest left and right adjacent targets; the smaller area on the inside is called the cut-in inverted trapezoidal area, which is used to select the nearest and second nearest targets on-path. Cut-in and cut-out are a way of judging the selected target, ensuring that the target selection meets safety requirements and avoids misselection. If the target has been selected, then the target will still be selected when entering the buffer zone, and will be acted on until the target crosses the trapezoidal boundary of the target release, and then it will not act on the target vehicle; if the target has not been selected (has not crossed the trapezoidal boundary of the target selection), the target will still not be selected when entering the buffer zone, and will not be selected until it crosses the trapezoidal boundary of the target selection.
[0070] Figure 3 A schematic diagram of a cut-in inverted trapezoid judgment boundary and a cut-out inverted trapezoid judgment boundary provided by an embodiment of the present invention is shown in FIG. Figure 3 As shown, the inverted trapezoidal cutting-in judgment boundary is the boundary of the inverted trapezoidal cutting-in region, and the inverted trapezoidal cutting-out judgment boundary is the boundary of the inverted trapezoidal cutting-out region.
[0071] In an embodiment of the present invention, the target closest and the second closest to the longitudinal distance of the vehicle in the direction of travel of the vehicle are selected by cutting into the inverted trapezoidal area, and the first lateral threshold is adjusted to control the degree of target selection according to the longitudinal distance from the vehicle in the direction of travel of the vehicle and the target type; or, the target closest to the left and right sides of the vehicle in the direction of travel of the vehicle is selected by cutting out the inverted trapezoidal area, and the second lateral threshold is adjusted to control the degree of target selection according to the longitudinal distance from the vehicle in the direction of travel of the vehicle and the target type.
[0072] In the embodiment of the present invention, if the speed of the target is similar to that of the vehicle and the longitudinal distance is relatively close (such as in the cut-in inverted trapezoidal area), the first lateral threshold of the target can be lowered to make it easier to be selected. For targets with similar speeds but longer longitudinal distances (such as in the cut-out inverted trapezoidal area), the system will increase the second lateral threshold to make it relatively less likely to be selected, thereby avoiding misselection.
[0073] In the embodiment of the present invention, the step of "adjusting the first lateral threshold" or "adjusting the second lateral threshold" is obtained by comprehensive judgment based on factors such as the longitudinal distance, speed and lateral distance of the target during the target screening process. 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 a reference for the lateral distance setting of cutting in and out of different target types (such as cars, trucks, 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 based on the detection data detected in real time and combined with the distance setting table, rather than just looking up a table to obtain a fixed value. This table lookup process is to provide a reference value or reference range, but the actual adjustment is performed according to the real-time situation. Therefore, "adjusting the first lateral threshold" or "adjusting the second lateral threshold" is a process that comprehensively considers 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 select targets more accurately, avoid misselection and mistriggered braking, and improve the safety and performance of the system.
[0074] In the embodiment of the present invention, Table 1 is a distance setting table for a car, as shown in Table 1 below.
[0075] Table 1
[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 handling of the vehicle when turning, as well as the minimum clearance between the wheel and the 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 handling of the vehicle, especially when driving at high speeds or making emergency turns.
[0079] Table 2 is a distance setting table for two-wheeled vehicles, as shown in Table 2 below.
[0080] Table 2
[0081]
[0082] Table 3 is a distance setting table for two-wheeled vehicles, as shown in Table 3 below.
[0083] Table 3
[0084]
[0085]
[0086] As can be seen from the above table, due to the different sizes of different targets, when different targets are cut in and out, it is necessary to perform offset compensation based on the calibrated standard lateral distance. The lateral distance based on the car type can be used as the standard value. The distance setting value is as follows: According to the distance between the vehicle and the front vehicle, the lateral distance is interpolated. Then, the truck has a higher risk factor, so the distance will be larger than that of the car, that is, it will be selected earlier. Since the two-wheeled vehicle has a small target size and width, the distance will be smaller than that of the car and it will be selected later.
[0087] In the embodiment of the present invention, the reasons for using the cut-in inverted trapezoidal area to select the target with the closest and second closest longitudinal distance to the vehicle in the direction of travel of the vehicle; or using the cut-out inverted trapezoidal area to select the target with the closest left and right adjacent distance to the vehicle in the direction of travel of the vehicle for processing are mainly as follows:
[0088] Safety and priority: Targets on the predicted trajectory of the vehicle have a direct impact on the driving safety of the vehicle, so these targets need to be screened and processed first. By cutting into the inverted trapezoidal area, these targets can be accurately identified and processed to ensure safe driving.
[0089] Avoid misselection and misoperation: The nearest targets on the left and right are usually potential safety threats, such as vehicles that suddenly cut in from the side lane. By using the cut-out inverted trapezoidal area, these targets can be identified in a timely manner and screened based on factors such as their longitudinal distance, speed, and lateral distance, avoiding misselection and misoperation and improving driving safety.
[0090] Optimize target selection: By comprehensively considering factors such as the distance, speed, and lateral distance of the target, and combining the judgment method of cutting into and out of the inverted trapezoidal area, the target can be selected more accurately, avoiding misselection and false triggering of brakes, thereby optimizing the target screening process and improving the performance and safety of the ACC system.
[0091] Adapt to different scenarios: In actual driving, the road environment ahead is complex and changeable, with various types of targets and scenarios. By using the judgment method of cutting into and out of the inverted trapezoidal area, it can adapt to different scenarios and target types, and achieve more flexible and accurate target screening and processing.
[0092] In summary, the method of cutting into or out of the inverted trapezoidal area can be determined according to the distance of each detected object, and priority is given to the targets that are closest and second closest to the longitudinal distance of the vehicle in the direction of travel and the targets that are closest to the left and right. This is to ensure driving safety, optimize the target selection process and adapt to different scenarios and target types.
[0093] Step 108: Target screening is performed according to the detection data and the type of the inverted trapezoidal area.
[0094] In the embodiment of the present invention, after the type of the inverted trapezoidal area is determined, screening can be performed based on the longitudinal distance, speed and lateral distance of the target. The main purpose of this screening process is to accurately select the target that needs to be tracked and controlled from a large number of detection objects.
[0095] Figure 4 A flowchart of performing target screening according to detection data and the type of inverted trapezoidal area provided in one embodiment of the present invention, such as Figure 4 As shown, step 108 includes:
[0096] Step 1082: Determine the inverted trapezoidal area based on the detection data.
[0097] In the embodiment of the present invention, the inverted trapezoid is a shape obtained by rotating the trapezoid 90° counterclockwise.
[0098] Step 1084: Generate the funnel trajectory before adjustment according to the inverted trapezoidal area.
[0099] In the embodiment of the present invention, the target of the inverted trapezoidal driving entering and exiting the trapezoidal area is likened to a funnel shape.
[0100] Step 1086: Adjust the funnel trajectory before adjustment according to the acquired predicted trajectory of the vehicle to generate a funnel trajectory.
[0101] In the embodiment of the present invention, if the predicted trajectory of the vehicle is a straight road, the funnel shape is a fixed angle shape formed with the vehicle as the center; if the predicted trajectory of the vehicle is a curve (driving trajectory direction), then according to the left turn or the right turn, the funnel shape direction automatically bends according to the tangent of the curve.
[0102] In an embodiment of the present invention, the funnel center refers to the geometric center of the funnel trajectory in the inverted trapezoidal area, and the center position will be bent accordingly according to the predicted trajectory direction. The funnel center is determined after the funnel trajectory is bent according to the predicted trajectory of the vehicle. The shape of the funnel trajectory can be adjusted according to the direction of the predicted trajectory of the vehicle, so that the funnel center moves along the bend of the predicted trajectory of the vehicle. The purpose of this step is to make the funnel trajectory more consistent with the predicted path in actual driving, thereby improving the accuracy and effectiveness of target screening. Specifically, when the predicted trajectory of the 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 a design helps to avoid inaccurate or misjudgment problems in target screening due to changes in the predicted trajectory during driving.
[0103] Specifically, the step of "adjusting the shape of the funnel trajectory according to the direction of the ego vehicle predicted trajectory so that the center of the funnel moves along the bend of the ego vehicle predicted trajectory" can be described as a key step in the target screening method, which adjusts the funnel shape and the center of the funnel based on the ego vehicle predicted trajectory. In order to describe or generally explain how to generate the funnel trajectory in more detail, it can be decomposed into the following steps:
[0104] Detection data collection: Collect vehicle driving data through on-board sensors (such as cameras, radars, lidars, etc.), including information such as speed, acceleration, direction, and possible predicted paths.
[0105] E-vehicle predicted trajectory generation: Based on the collected ego-vehicle driving data, the ego-vehicle predicted trajectory is generated through a certain algorithm or model. This ego-vehicle predicted trajectory may include straight-line driving, turning, lane changing, and other situations.
[0106] Funnel center positioning: Before the bending adjustment, the funnel center may be a fixed point or position. However, after the introduction of the ego vehicle predicted trajectory, the system will determine the position where the funnel center needs to be adjusted based on the direction of the ego vehicle predicted trajectory.
[0107] Funnel curvature adjustment: The funnel trajectory is adjusted according to the predicted trajectory of the ego vehicle. The purpose of this adjustment is to make the center point and trajectory shape of the funnel more consistent with the curvature of the predicted trajectory of the ego vehicle, so as to ensure that the funnel can accurately cover and filter out targets related to the predicted trajectory of the ego vehicle.
[0108] Real-time update: With the real-time update of the ego vehicle driving data, the funnel center and funnel trajectory need to be constantly adjusted according to the new ego vehicle predicted trajectory to maintain accurate screening and tracking of targets. It is closer 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, thereby ensuring that targets related to ego vehicle driving can be accurately and efficiently screened in complex driving environments.
[0109] Step 1088: Screen the targets according to the funnel trajectory and the type of the inverted trapezoidal area, and generate preliminary screening targets and dynamic data of the preliminary screening targets.
[0110] In the embodiment of the present invention, the dynamic data includes velocity, acceleration and position.
[0111] Step 1090: Based on the dynamic data, an interpolation curve algorithm is used to make predictions and generate the future motion trajectory of the target.
[0112] In the embodiment of the present invention, 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, so as to further optimize the selection of the target.
[0113] In the embodiment of the present invention, 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. These algorithms can generate smooth continuous curves based on discrete data points.
[0115] Curve fitting: The collected target positions (usually time series data) are used as input and fitted using the selected interpolation curve algorithm. In this process, the parameters of the interpolation curve can be adjusted according to the distribution characteristics and dynamic change trends of the data to reflect the movement state of the target vehicle as accurately as possible.
[0116] Prediction of the target's future motion trajectory: After the interpolation curve fitting is completed, the target's position at a certain moment in the future can be predicted based on the current target detection data and the trend of the curve. This process usually needs to consider factors such as time step and prediction accuracy to ensure the reliability and practicality of the prediction results.
[0117] Trajectory output: Make corresponding control decisions based on the future motion trajectory of the target.
[0118] Step 1092: Filter out targets from the initial screening targets based on the target's future motion trajectory and the set target constraints.
[0119] In the embodiment of the present invention, the target constraint conditions can be set according to the actual situation. For example, the target constraint conditions may include the following conditions:
[0120] Lateral distance and longitudinal distance: Filtering can be performed based on the lateral distance and longitudinal distance of the target relative to the vehicle's position. For example, for targets corresponding to the cut-in inverted trapezoidal area, a minimum longitudinal distance (such as 4.2 meters) and a maximum longitudinal distance (such as 150 meters) can be set to ensure that only targets that are on the predicted trajectory of the vehicle and at a moderate distance are filtered out. At the same time, the lateral threshold is dynamically adjusted based on the target's lateral position (i.e., relative position to the vehicle's lane) and longitudinal distance to control the degree of target selection.
[0121] Target type: The target type of the target ahead (such as cars, trucks, two-wheelers, etc.) can be identified and screened according to the characteristics and potential danger level of different target types. For example, since trucks are usually larger and heavier than cars, a wider lateral threshold and a farther longitudinal distance threshold can be set for them to identify and select trucks as potential tracking targets earlier. On the contrary, for smaller two-wheelers, 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. You can compare the speed difference between the target in front and the ego vehicle, and screen based on the speed proximity. For example, if the target's speed is similar to the ego vehicle and the longitudinal distance is moderate, you can lower the lateral threshold of the target to make it easier to be selected as a tracking target. On the contrary, if the target's speed is too fast or too slow, and the speed difference is large with the ego vehicle, you can increase the lateral threshold or exclude it from the screening range.
[0123] Combining the above three aspects, a comprehensive judgment can be made based on multiple target constraints such as lateral distance, longitudinal distance, target type and speed, and the target ahead can be further screened to ensure that the selected target not only meets the requirements of safe driving, but also improves the performance and comfort of the ACC system. The specific logic may vary depending on the vehicle model, sensor performance and system design.
[0124] In the technical solution provided by the embodiment of the present invention, detection data detected by the sensor is obtained; the distance between the target and the 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 vehicle; and the target is screened according to the detection data and the type of the inverted trapezoidal area. In the technical solution provided by the embodiment of the present invention, the target is screened according to the detection data and the type of the inverted trapezoidal area, thereby improving the accuracy of target screening and driving safety.
[0125] In the technical solution provided by the embodiment of the present invention, screening can be performed during the target selection process according to the direction of the predicted trajectory of the vehicle and the detection performance of the sensor, thereby avoiding misselection of targets and mis-triggering of brakes, thereby improving the performance and safety of the ACC system.
[0126] In the technical solution provided by the embodiment of the present invention, by introducing an inverted trapezoidal target screening method, targets are screened more accurately according to the sensor detection performance and the target's future motion trajectory. The funnel trajectory can be bent accordingly according to the direction of the predicted motion trajectory, thereby avoiding the problem of misselecting targets and frequently switching targets.
[0127] In the technical solution provided by the embodiment of the present invention, a smaller "internal funnel" and a larger "external funnel" are used to judge the entry / exit of the target. This design can achieve "difficult entry and exit" of the target, avoid the problem of misselection of the target and mis-triggering of the brake due to inaccurate perception, speed measurement and distance measurement, thereby improving the accuracy of target screening.
[0128] In the technical solution provided by the embodiment of the present invention, the comprehensive factors of longitudinal distance, speed and lateral distance are considered for screening the cut-in target. When the target vehicle has the same speed, the closer the longitudinal distance is, the smaller the lateral threshold is, and the easier it is to be selected, so as to reflect the ability to identify the cut-in target. When the target is far away at the same speed, the larger the lateral threshold is, and the less likely it is to be selected, so as to avoid the situation of misselection.
[0129] An embodiment of the present invention provides a target screening device. Figure 5 A schematic diagram of a target screening device provided by an embodiment of the present invention is shown in FIG. Figure 5 As shown, the device includes: an acquisition module 11, a first determination module 12, a second determination module 13 and a screening module 14.
[0130] The acquisition module 11 is used to acquire detection data detected by the sensor.
[0131] The first determination module 12 is used to determine the distance between the target and the vehicle according to the detection data.
[0132] The second determination module 13 is used to determine the type of the inverted trapezoidal area according to the distance between the target and the vehicle.
[0133] The screening module 14 is used to screen targets according to the detection data and the type of the inverted trapezoidal region.
[0134] In an embodiment of the present invention, the first determination module 12 is specifically used to determine the target as a short-range target if the distance between the target and the vehicle is within a first threshold range; or, if the distance between the target and the vehicle is within a second threshold range, determine the target as a medium-range target; or, if the distance between the target and the vehicle is within a third threshold range, determine the target as 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.
[0135] In an embodiment of the present invention, the second determination module 13 is specifically used to determine the type of the inverted trapezoidal area as a cut-in inverted trapezoidal area if the target is determined to be a close-range target; or, if the target is determined to be a medium-range target or a long-range target, determine the type of the inverted trapezoidal area as a cut-out inverted trapezoidal area.
[0136] In an embodiment of the present invention, the cut-in inverted trapezoidal area is used to select the target that is closest and second closest to the longitudinal distance of the vehicle in the direction of travel of the vehicle; or, the cut-out inverted trapezoidal area is used to select the target that is closest to the left and right of the vehicle in the direction of travel of the vehicle.
[0137] In an embodiment of the present invention, the second determination module 13 is specifically used to adjust the first lateral threshold to control the degree of selection of the target according to the longitudinal distance from the vehicle in the direction of travel of the vehicle and the target type of the target; and adjust the second lateral threshold to control the degree of selection of the target according to the longitudinal distance from the vehicle in the direction of travel of the vehicle and the target type of the target.
[0138] In an embodiment of the present invention, the screening module 14 is specifically used to generate a funnel trajectory based on the detection data and the acquired predicted trajectory of the vehicle; screen the targets according to the types of the funnel trajectory and the inverted trapezoidal area to generate preliminary screening targets and dynamic data of the preliminary screening targets; use the interpolation curve algorithm to predict based on the dynamic data to generate the future motion trajectory of the target; and screen out the target from the preliminary screening targets based on the future motion trajectory of the target and the set target constraints.
[0139] In the embodiment of the present invention, the screening module 14 is specifically used to determine the inverted trapezoidal area according to the detection data; generate the pre-adjusted funnel trajectory according to the inverted trapezoidal area; and adjust the pre-adjusted funnel trajectory according to the acquired vehicle predicted trajectory to generate the funnel trajectory.
[0140] In the technical solution provided by the embodiment of the present invention, detection data detected by the sensor is obtained; the distance between the target and the 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 vehicle; and the target is screened according to the detection data and the type of the inverted trapezoidal area. In the technical solution provided by the embodiment of the present invention, the target is screened according to the detection data and the type of the inverted trapezoidal area, thereby improving the accuracy of target screening and driving safety.
[0141] The target screening device provided in this embodiment can be used to achieve the above Figure 1 For the target screening method in, the specific description can be found in the above-mentioned embodiment of the target screening method, which will not be repeated here.
[0142] An embodiment of the present invention 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 execute the steps of the embodiment of the above-mentioned target screening method. For a specific description, please refer to the embodiment of the above-mentioned target screening method.
[0143] An embodiment of the present invention provides an ACC system or a control unit thereof, including a memory and a processor, wherein the memory is used to store information including program instructions, and the processor is used to control the execution of the program instructions. When the program instructions are loaded and executed by the processor, the steps of the embodiment of the above-mentioned target screening method are implemented. For a specific description, please refer to the embodiment of the above-mentioned target screening method.
[0144] Figure 6 Schematic diagram of an ACC system or its control unit provided by an embodiment of the present invention. Figure 6 As shown, the ACC system or its control unit 20 of this embodiment includes: a processor 21, a memory 22, and a computer program 23 stored in the memory 22 and executable on the processor 21. When the computer program 23 is executed by the processor 21, the target screening method applied in the embodiment is implemented. To avoid repetition, it is not described one by one here. Alternatively, when the computer program is executed by the processor 21, the functions of each model / unit in the target screening device applied in the embodiment are implemented. To avoid repetition, it is not described one by one here.
[0145] The ACC system or its control unit 20 includes, but is not limited to, a processor 21 and a memory 22. Those skilled in the art will appreciate that Figure 6 It is only an example of the ACC system or its control unit 20 and does not constitute a limitation of the ACC system or its control unit 20. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the ACC system or its control unit may also include input and output devices, network access devices, buses, etc.
[0146] The processor 21 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.
[0147] The memory 22 may be an internal storage unit of the ACC system or its control unit 20, such as a hard disk or memory of the ACC system or its control unit 20. The memory 22 may also be an external storage device of the ACC system or its control unit 20, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the ACC system or its control unit 20. Furthermore, the memory 22 may also include both an internal storage unit and an external storage device of the ACC system or its control unit 20. The memory 22 is used to store computer programs and other programs and data required by the ACC system or its control unit. The memory 22 may also be used to temporarily store data that has been output or is to 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 systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.
[0149] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.
[0150] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0151] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional units.
[0152] The above-mentioned integrated unit implemented in the form of a software functional unit can be stored in a computer-readable storage medium. The above-mentioned software functional unit is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor (Processor) to perform some steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), disk or optical disk and other media that can store program codes.
[0153] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.
Claims
1. A target screening method, characterized in that: include: Acquire detection data detected by the sensor; Determine the distance between the target and the vehicle according to the detection data; Determining the type of the inverted trapezoidal area according to the distance between the target and the vehicle; Target screening is performed according to the detection data and the type of the inverted trapezoidal area.
2. The method according to claim 1, characterized in that Determining the distance between the target and the vehicle according to the detection data includes: If the distance between the target and the vehicle is within a first threshold range, the target is determined as a close-range target; or, If the distance between the target and the vehicle is within a second threshold range, the target is determined as a medium-distance target; or, If the distance between the target and the vehicle is within a third threshold range, the target is determined as a long-distance 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 according to claim 2, characterized in that Determining the type of the inverted trapezoidal area according to the distance between the target and the vehicle includes: If the target is determined to be a close-range target, the type of the inverted trapezoidal area is determined to be a cut-in inverted trapezoidal area; or, If the target is determined to be a medium-distance target or a long-distance target, the type of the inverted trapezoidal area is determined to be a cut-out inverted trapezoidal area.
4. The method according to claim 3, characterized in that: The cut-in inverted trapezoidal area is used to select the target that is closest and second closest to the longitudinal distance of the vehicle in the direction of travel of the vehicle; or, the cut-out inverted trapezoidal area is used to select the target that is closest to the left and right of the vehicle in the direction of travel of the vehicle.
5. The method according to claim 4, characterized in that After using the cut-in inverted trapezoidal area to select the target that is closest and the target that is second closest to the longitudinal distance of the vehicle in the direction of travel of the vehicle, the method includes: adjusting a first lateral threshold to control the degree of selection of the target according to the longitudinal distance from the ego vehicle in the direction of travel of the ego vehicle and the target type of the target; After using the cut-out inverted trapezoidal area to select the target closest to the left and right sides of the vehicle in the direction of travel of the vehicle, the method includes: According to the longitudinal distance from the vehicle in the driving direction of the vehicle and the target type of the target, the second lateral threshold is adjusted to control the degree of selection of the target.
6. The method according to claim 1, characterized in that The target screening according to the detection data and the type of the inverted trapezoidal area includes: generating a funnel trajectory according to the detection data and the obtained ego-vehicle predicted trajectory; Screening targets according to the funnel track and the type of the inverted trapezoidal area, generating preliminary screening targets and dynamic data of the preliminary screening targets; Based on the dynamic data, an interpolation curve algorithm is used to predict and generate a future motion trajectory of the target; Targets are screened out from the initial screening targets according to the future motion trajectory of the target and the set target constraints.
7. The method according to claim 6, characterized in that Generating a funnel trajectory according to the detection data and the acquired ego-vehicle predicted trajectory includes: Determine an inverted trapezoidal area according to the detection data; generating a funnel trajectory before adjustment according to the inverted trapezoidal area; The funnel trajectory before adjustment is adjusted according to the acquired predicted trajectory of the vehicle to generate the funnel trajectory.
8. A target screening device, characterized in that: include: An acquisition module, used for acquiring detection data detected by the sensor; A first determination module is used to determine the distance between the target and the vehicle according to the detection data; A second determination module is used to determine the type of the inverted trapezoidal area according to the distance between the target and the vehicle; A screening module is used to screen targets according to the detection data and the type of the inverted trapezoidal area.
9. A storage medium, characterized in that: The storage medium includes a stored program, wherein when the program is executed, the device where the storage medium is located is controlled to execute the target screening method according to any one of claims 1 to 7.
10. An adaptive cruise control system or a control unit thereof, comprising a memory and a processor, wherein the memory is used to store information including program instructions, and the processor is used to control the execution of the program instructions, characterized in that: When the program instructions are loaded and executed by the processor, the steps of the target screening method described in any one of claims 1 to 7 are implemented.
Citation Information
Patent Citations
Vehicle motion relationship determination method and device
CN111968395A
Self-adaptive cruise target selection method and device and computer equipment
CN112009473A
Unmanned vehicle environment cognition and decision control method and system, and vehicle
CN112455439A
Surrounding vehicle track prediction method and device, vehicle and storage medium
CN114291116A
Tracking target determination method and device, electronic equipment and storage medium
CN114643988A
Cited By
Target screening method and apparatus, storage medium, and ACC system or control unit thereof
WO2026056210A1
