Self-adaptive cruise target screening method, device and equipment, storage medium and vehicle

Abstract

The invention provides a self-adaptive cruise target screening method, device and equipment, a storage medium and a vehicle, and belongs to the technical field of intelligent drive.The method comprises the steps that road environment information and vehicle state information are fitted, and a lane line of a vehicle is obtained; determining candidate angular points based on the distance between at least one angular point of the environment target sensed by the vehicle and the lane line; generating a track line of the vehicle based on the lane line, and obtaining a plurality of track points on the track line according to a preset interval; and by comparing the distances between the candidate angular points and the plurality of track points, screening out a cruise target point from the candidate angular points. Through the mode, the screening process of the cruise target points can be dynamically adjusted, the real-time decision-making capability of the self-adaptive cruise system is improved, and the safety of the self-adaptive cruise system during high-speed driving is ensured.

Description

Technical Field

[0001] This application relates to the field of intelligent driving technology, and in particular, to an adaptive cruise target screening method, device, equipment, storage medium, and vehicle. Background Art

[0002] At present, with the booming development of intelligent transportation systems, autonomous driving and assisted driving technologies are facing unprecedented challenges, especially in complex and changing road environments. As a core component of intelligent vehicles, the efficient and accurate main target screening ability of the adaptive cruise system is the key to ensuring driving safety and driving experience.

[0003] In related technologies, the cruise target point of the target vehicle can be determined by obtaining the positions of each corner point of the target vehicle. However, in the actual driving environment, the positions of each corner point of the target vehicle require a complex calculation process, and the relative positions between the host vehicle and each corner point change with factors such as the vehicle speed and steering angle, which makes the cruise target screening process lack real-time performance, thus possibly resulting in missed reports or false reports of cruise targets.

[0004] Therefore, how to improve the accuracy of cruise target screening while ensuring real-time performance has become a technical problem that needs to be urgently solved by those skilled in the art. Summary of the Invention

[0005] In view of the above problems, this application provides an adaptive cruise target screening method, device, equipment, storage medium, and vehicle that overcome the above problems or at least partially solve the above problems. The technical solutions are as follows: In a first aspect, an embodiment of this application provides an adaptive cruise target screening method, and the method includes: obtaining the lane lines of the host vehicle by fitting road environment information and vehicle state information; determining candidate corner points based on the distances between at least one corner point of the environmental target sensed by the host vehicle and the lane lines; generating a trajectory line of the host vehicle based on the lane lines, and obtaining a plurality of trajectory points on the trajectory line at a preset interval; screening out cruise target points from the candidate corner points by comparing the distances between the candidate corner points and the plurality of trajectory points.

[0006] Optionally, the step of obtaining the lane lines of the host vehicle by fitting road environment information and vehicle state information includes: determining lane line information according to road environment information; obtaining the lane lines of the host vehicle by fitting the lane line information and the vehicle state information. In the embodiments of this application, obtaining known lane line information through road environment information and generating the lane lines of the host vehicle by fitting the lane line information and vehicle state information can reduce the complexity of data processing and improve the response speed of the adaptive cruise system.

[0007] Optionally, determining the lane line information according to the road environment information includes: extracting the lane line information from the road environment information; or, extracting the road contour information from the road environment information and determining the lane line information according to the road contour information. In the embodiments of the present application, for the case where there are lane lines on the road surface, the lane line information is extracted from the road environment information; for the case where there are no lane lines on the road surface, the road contour information is extracted from the road environment information and the lane line information is determined according to the road contour information. The lane line information of the vehicle itself can be obtained whether there are lane lines or not, so that different types of road scenarios can be adapted, thereby improving the stability of cruise target point recognition and reducing the possibility of false alarms or missed reports of cruise target points.

[0008] Optionally, determining the candidate corner points based on the distances between at least one corner point of the environmental target sensed by the vehicle itself and the lane lines includes: determining the position information of at least one corner point of the environmental target in the vehicle coordinate system of the vehicle itself according to the length information, width information and heading angle of the environmental target; determining the distances between the at least one corner point and the lane lines according to the position information of the at least one corner point and the position information of the lane lines; and determining the corner points with distances less than a preset distance threshold among the at least one corner point as candidate corner points. In the embodiments of the present application, by determining the position information of at least one corner point of the environmental target in the vehicle coordinate system of the vehicle itself, the specific position of the environmental target relative to the vehicle itself can be accurately obtained; and then, according to the distances between the at least one corner point and the lane lines, the candidate corner points with distances less than the preset threshold are screened out, so that the adaptive cruise control system can timely discover the environmental targets that may interfere with the lane lines, so as to timely adjust the driving speed of the vehicle itself and ensure the safety of vehicle driving.

[0009] Optionally, screening out the cruise target points from the candidate corner points by comparing the distances between the candidate corner points and the multiple trajectory points includes: starting from the target trajectory point among the multiple trajectory points, sequentially comparing the target distances between the candidate corner points and the multiple trajectory points, where the target trajectory point is the point closest to the vehicle target point among the multiple trajectory points; and screening out the cruise target points from the candidate corner points according to the target distances. In the embodiments of the present application, by starting from the target trajectory point closest to the vehicle target point and sequentially comparing the target distances between each candidate corner point and the trajectory points, the appropriate cruise target points can be screened out from the multiple candidate corner points, which can effectively avoid false alarm problems in the process of selecting cruise target points and improve the driving safety of the vehicle.

[0010] Optionally, the target distance includes a lateral distance and a longitudinal distance; the step of screening the cruise target points from the candidate corner points according to the target distance includes: determining the candidate corner points with a lateral distance less than a preset lateral distance threshold as cruise target points; and / or, determining the candidate corner points with a longitudinal distance less than a preset longitudinal distance threshold as cruise target points. In the embodiments of the present application, by using the lateral distance and / or the longitudinal distance as the screening conditions for the cruise target points, the screening rules for the cruise target points can be determined according to different cruise tasks, so as to adapt to the changing traffic conditions.

[0011] In a second aspect, an adaptive cruise target screening device is provided in an embodiment of the present application. The device includes: a lane line acquisition module, configured to acquire the lane lines of the host vehicle by fitting the road environment information and the vehicle state information; a candidate corner point determination module, configured to determine candidate corner points based on the distances between at least one corner point of the environmental target sensed by the host vehicle and the lane lines; a trajectory point acquisition module, configured to generate a trajectory line of the host vehicle based on the lane lines and acquire a plurality of trajectory points on the trajectory line at a preset interval; a target corner point screening module, configured to screen the cruise target points from the candidate corner points by comparing the distances between the candidate corner points and the plurality of trajectory points.

[0012] In a third aspect, an electronic device is provided in an embodiment of the present application. The electronic device includes a processor and a memory. The memory stores a program or instruction that can run on the processor. When the program or instruction is executed by the processor, the adaptive cruise target screening method described in any one of the above is implemented.

[0013] In a fourth aspect, a computer-readable storage medium is provided in an embodiment of the present application. A program is stored on the computer-readable storage medium. When the program is executed by a processor, the adaptive cruise target screening method described in any one of the above is implemented.

[0014] In a fifth aspect, a vehicle is provided in an embodiment of the present application. The vehicle includes at least one processor. When the at least one processor is executed, the adaptive cruise target screening method described in any one of the above is implemented.

[0015] With the above technical solution, an adaptive cruise target screening method, device, equipment, storage medium and vehicle provided by the present application obtain the lane lines of the host vehicle by fitting the road environment information and the vehicle state information; determine candidate corner points based on the distances between at least one corner point of the environmental target sensed by the host vehicle and the lane lines; generate a trajectory line of the host vehicle based on the lane lines, and obtain a plurality of trajectory points on the trajectory line at a preset interval; screen out cruise target points from the candidate corner points by comparing the distances between the candidate corner points and the plurality of trajectory points. In this way, by fitting the road environment information and the vehicle state information to obtain the lane lines of the host vehicle, and determining candidate corner points based on the distances between at least one corner point of the environmental target and the lane lines, the relative position between the environmental target and the host vehicle can be more accurately located, reducing the possibility of false alarms or missed reports of cruise targets; by comparing the distances between the candidate corner points and the plurality of trajectory points on the trajectory line of the host vehicle and screening out cruise target points from the candidate corner points, the screening process of cruise target points can be dynamically adjusted, improving the real-time decision-making ability of the adaptive cruise system and ensuring the safety of the host vehicle during high-speed driving.

[0016] The above description is only an overview of the technical solution of the present application. In order to be able to understand the technical means of the present application more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features and advantages of the present application more obvious and understandable, the following specifically gives the specific embodiments of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] By reading the following detailed description of the preferred embodiments, various other advantages and benefits will become clear to those of ordinary skill in the art. The drawings are only for the purpose of showing the preferred embodiments and are not considered to be a limitation of the present application. And throughout the drawings, the same reference numerals are used to represent the same components. In the drawings: Figure 1 shows a schematic application scenario diagram of the adaptive cruise target screening method provided by an embodiment of the present application; Figure 2 shows a schematic flow diagram of the adaptive cruise target screening method provided by an embodiment of the present application; Figure 3 shows an example diagram of determining a plurality of trajectory points provided by an embodiment of the present application; Figure 4 shows a schematic flow diagram of the adaptive cruise target screening method provided by another embodiment of the present application; Figure 5 shows a schematic flow diagram of the adaptive cruise target screening method provided by another embodiment of the present application; Figure 6 shows what is provided by an embodiment of the present application; Figure 7Shows a schematic flowchart of an adaptive cruise target screening method provided by another embodiment of the present application; Figure 8 Shows a schematic structural diagram of an adaptive cruise target screening device provided by an embodiment of the present application; Figure 9 Shows a schematic structural diagram of a vehicle provided by an embodiment of the present application. Detailed implementation manners

[0018] Hereinafter, exemplary embodiments of the present application will be described in more detail with reference to the accompanying drawings. Although the exemplary embodiments of the present application are shown in the drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided so that the present application can be more thoroughly understood and the scope of the present application can be fully conveyed to those skilled in the art.

[0019] In the field of intelligent driving, an Adaptive Cruise Control (ACC) is an intelligent driving assistance system based on traditional cruise control. It can automatically adjust the speed of a vehicle to maintain a safe distance from the vehicle ahead on the basis of setting a cruise speed. For example, as Figure 1 shown, the host vehicle 110 is traveling on a highway with a set cruise speed of 100 km / h, and the adaptive cruise system will automatically control the host vehicle 110 to maintain this speed. If a target vehicle 120 in front turns into the lane of the host vehicle, the adaptive cruise system will detect the target vehicle 120 through sensors such as cameras and radars, and calculate and adjust the speed of the host vehicle 110 in real time according to the distance between the target vehicle 120 and the host vehicle 110 to maintain a safe distance from the target vehicle 120. Therefore, accurately calculating the distances between the target vehicles 120 on the main lane ahead and the adjacent left and right lanes and the host vehicle 110 is crucial for the main target screening, which directly affects the selection timing of the main target, the following distance, and the decision-making of speed adjustment.

[0020] In the related ACC target screening method, the main target candidate with the smallest longitudinal distance between the tail contour line of the detection box and the host vehicle can be used as the main target. However, in the actual driving environment, the road conditions are variable. Especially under the condition of dense traffic, the tail contour line of the target vehicle is easily affected by factors such as occlusion and road curves. This makes it easy to misjudge or calculate the distance inaccurately when screening the main target by detecting the longitudinal distance between the tail contour line of the target vehicle and the host vehicle. And by obtaining the position of each corner point of the target vehicle to determine the cruise target point of the target vehicle, since the position of each corner point of the target vehicle requires a complex calculation process, and the relative position between the host vehicle and each corner point will change with factors such as the speed and steering angle of the vehicle, this makes the screening process of the cruise target lack real-time performance, which may lead to missed reports or false reports of the cruise target.

[0021] Based on the above application scenarios, to solve the problem of how to improve the accuracy of cruise target screening while ensuring real-time performance, the embodiments of the present application provide an adaptive cruise target screening method, as Figure 2 shown, Figure 2 FIG. shows a schematic flow chart of the adaptive cruise target screening method provided by the embodiments of the present application. This method can be applied to the controller in the adaptive cruise system. The method 200 includes: Step 201, obtain the lane line of the host vehicle by fitting the road environment information and the vehicle state information.

[0022] Among them, the road environment information in step 201 can be lane line information such as lane line position and shape, traffic sign information such as speed limit signs and turning instructions, or road surface information such as road contours and obstacles; the vehicle state information in step 201 can be information such as speed, acceleration, and steering angle, or the braking state information of the vehicle.

[0023] In this step, the controller in the adaptive cruise system can obtain the road environment information and the vehicle state information through a variety of sensors mounted on the host vehicle 110. For example, capture road images through a camera and identify the color, texture, and edge features of the lane line through image recognition technology; measure the distance and relative speed to environmental targets such as road boundaries and other vehicles through a millimeter-wave radar; construct a three-dimensional point cloud model of the road through a lidar to clearly present the geometric shape of the road; measure the rotation speed of the wheels through a wheel speed sensor and then calculate the driving speed of the vehicle; measure the acceleration of the vehicle through an accelerometer; detect the attitude and steering angle of the vehicle through a gyroscope.

[0024] Adopt a preset fitting algorithm, for example, polynomial fitting, spline curve fitting, etc., and fit the lane lines of the host vehicle 110 according to the acquired road environment information and vehicle state information. For example, for the road image collected by the camera, the Hough transform can be used to detect the edges of the lane lines, and then the least squares method can be used for polynomial fitting in combination with the vehicle state information of the host vehicle 110 to obtain the mathematical expression of the lane lines. Among them, since there are many types and large amounts of data obtained through multiple sensors, before fitting the road environment information and vehicle state information to obtain the lane lines of the host vehicle 110, the acquired road environment information and vehicle state information can also be preprocessed, and the preprocessing includes normalization processing, noise removal, filtering processing, etc., to improve the quality of the data; and then the lane lines of the host vehicle 110 can be obtained by fitting the preprocessed road environment information and vehicle state information.

[0025] In this way, by fitting the road environment information and vehicle state information, the specific position of the lane where the host vehicle 110 is currently located and its lane lines can be accurately obtained, providing accurate lane line information of the host vehicle 110 for the subsequent screening of cruise target points.

[0026] Step 202: Determine candidate corner points based on the distances between at least one corner point of the environmental target perceived by the host vehicle and the lane lines.

[0027] Among them, the environmental target in step 202 can be a vehicle, an obstacle, etc. in the front. There can be one or more environmental targets. For each environmental target, at least one corner point is obtained respectively to be used as a candidate for the cruise target point.

[0028] In this step, the controller of the automatic cruise system can sense the environmental targets around the host vehicle 110, such as vehicles, obstacles, etc. in the front, through sensors such as the camera, millimeter-wave radar, lidar, etc. of the host vehicle 110. For each perceived environmental target, at least one of its corner points is extracted. In specific applications, a corner point detection algorithm, such as Harris corner point detection, Shi-Tomasi corner point detection, etc., can be used to detect the corner points of the environmental target from the road image; for 3D point cloud data, the corner points of the environmental target can be determined by analyzing the geometric features of the point cloud. Furthermore, the distances between the corner points of each environmental target and the lane lines obtained in the above step 201 are calculated, and candidate corner points are selected from at least one corner point according to a distance threshold. For example, only the corner points within a certain range from the lane lines are selected as candidate corner points, and the corner points that are too far away are excluded.

[0029] In this way, based on the distance between at least one corner point of the environmental target sensed by the host vehicle and the lane line, candidate corner points can be determined, and candidate corner points within a certain range from the lane line can be screened out, excluding intersection points that are far from the lane line, thereby reducing the computational complexity of cruise target point screening. At the same time, compared with the method in the prior art of determining the relative distance from the host vehicle through the reference point at the rear of the target vehicle, the method provided in this embodiment can more accurately locate the relative position between the environmental target and the host vehicle 110, reducing the possibility of false alarms or missed reports of cruise targets.

[0030] Step 203: Generate a trajectory line of the host vehicle based on the lane line, and obtain multiple trajectory points on the trajectory line at a preset interval.

[0031] Among them, the preset interval in the above step 203 can be set to 0.5 meters, 1 meter, 1.5 meters, etc. The setting of the preset interval can be determined according to actual needs and is not specifically limited here.

[0032] In this step, the controller of the adaptive cruise control system generates a trajectory line of the host vehicle 110 based on the lane line of the host vehicle 110 obtained in the above step 201. For example, if the host vehicle 110 needs to maintain driving in the current lane, the trajectory line can be generated along the center line of the lane line; if the host vehicle 110 needs to perform a lane change operation, a corresponding trajectory line is generated according to the target lane of the lane change and the current lane line. Sprinkle points on the generated trajectory line at a preset interval to obtain multiple trajectory points. The size of the preset interval can be adjusted according to actual needs. The smaller the interval, the denser the trajectory points, and the higher the screening accuracy of subsequent cruise target points, but the computational amount will also increase accordingly.

[0033] In an exemplary embodiment, as Figure 3 shown, taking the environmental target as the target vehicle 120 as an example, the host vehicle 110 and the target vehicle 120 are equivalent to rectangles. Assume that the host vehicle 110 needs to maintain driving in the current lane, generate a trajectory line 310 based on the center line of the lane lines on both sides of the host vehicle 110, and evenly sprinkle 101 points at an equal distance with the target reference point at the front of the host vehicle 110 as the zero point. In specific applications, the target reference point is usually selected as the center of the front bumper of the host vehicle 110.

[0034] In this way, a trajectory line of the host vehicle is generated based on the lane line. This trajectory line can represent the ideal route for the host vehicle 110 to drive along the current lane. By obtaining multiple trajectory points on the trajectory line at a preset interval, the trajectory points represent the expected position points of the host vehicle 110 at future time points, which is beneficial to adjusting the following distance and speed at a specific time point and improving the driving safety of the host vehicle 110.

[0035] Step 204: Screen out cruise target points from the candidate corner points by comparing the distances between the candidate corner points and the multiple trajectory points.

[0036] In this step, the horizontal distance and vertical distance between the candidate corner points and each trajectory point can be used as judgment conditions to screen out the cruise target points. For example, thresholds for the horizontal distance and vertical distance can be set, and the candidate corner point closest to the trajectory point and within the threshold range can be selected as the cruise target point. The method of weighted distance can also be adopted, where different weights are assigned according to the importance of the horizontal distance and vertical distance, the weighted distance is calculated, and the candidate corner point with the minimum weighted distance is selected as the cruise target point.

[0037] In summary, the present application provides an adaptive cruise target screening method. By fitting the road environment information and vehicle state information, the lane line of the host vehicle is obtained; based on the distance between at least one corner point of the environmental target sensed by the host vehicle and the lane line, candidate corner points are determined; a trajectory line of the host vehicle is generated based on the lane line, and multiple trajectory points on the trajectory line are obtained at a preset interval; by comparing the distances between the candidate corner points and the multiple trajectory points, the cruise target points are screened out from the candidate corner points. In this way, compared with the method of determining the cruise target point of the target vehicle by obtaining the position of each corner point of the target vehicle in the prior art, the method provided by the embodiment of the present application fits the road environment information and vehicle state information to obtain the lane line of the host vehicle; the candidate corner points are determined based on the distance between at least one corner point of the environmental target and the lane line, which can more accurately locate the relative position between the environmental target and the host vehicle, reducing the possibility of false alarms or missed alarms of the cruise target; by comparing the distances between the candidate corner points and multiple trajectory points on the trajectory line of the host vehicle, the cruise target points are screened out from the candidate corner points, which can dynamically adjust the screening process of the cruise target points, improve the real-time decision-making ability of the adaptive cruise system, and ensure the safety of the host vehicle during high-speed driving. Moreover, in terms of the response speed of screening the cruise target points, the processing speed of the method provided by the embodiment of the present application is increased by more than 30%, which can meet the real-time requirements under high-speed driving conditions.

[0038] To more clearly illustrate the technical solutions provided by the embodiments of the present application, the following Figures 3 to 7 further describes an adaptive cruise target screening method provided by the present application.

[0039] Since various sensors are usually mounted on the host vehicle 110, lane line information such as lane line position and shape, traffic sign information such as speed limit signs and turning instructions, road surface information such as road contours and obstacles can be obtained through the various sensors. To quickly obtain the lane line of the host vehicle 110, the lane line information can be determined according to the road environment information, and then the lane line of the host vehicle 110 can be obtained by fitting the lane line information and vehicle state information. In a specific embodiment, the embodiment of the present application provides an adaptive cruise target screening method, as Figure 4 shown Figure 4The flowchart of the adaptive cruise target screening method provided by another embodiment of the present application is shown. This method can be applied to the controller in the adaptive cruise system. The method 400 includes: Step 401: Determine lane line information according to road environment information.

[0040] Among them, for the road environment information in step 401, it can be lane line information such as lane line position and shape, it can be traffic sign information such as speed limit signs and turning instructions, or it can be road surface information such as road contour and obstacles.

[0041] In this step, sensors usually installed on the host vehicle 110 are used to collect road environment information. The sensors include cameras, lidar, etc. Furthermore, according to the road environment information, lane line information is determined. For example, road images are collected through a camera, and visual features such as the shape and position of the lane line are extracted from the road images; for another example, a three-dimensional environment map is created by the lidar emitting laser beams and measuring the time of the reflected light to identify the boundary information of the lane line.

[0042] In this way, by determining the lane line information, the position of the host vehicle 110 on the road can be located. At the same time, it is beneficial to quickly fit the lane line of the host vehicle.

[0043] Step 402: Obtain the lane line of the host vehicle by fitting the lane line information and vehicle state information.

[0044] Among them, for the vehicle state information in step 402, it can be information such as speed, acceleration, and steering angle, or it can be the braking state information of the vehicle; this vehicle state information can be obtained through the Controller Area Network (CAN) bus of the host vehicle.

[0045] In this step, the determined lane line information (for example, the coordinate points of the lane line) and vehicle state information (for example, the position, speed, steering wheel angle, etc. of the host vehicle 110) can be converted into a data format suitable for polynomial fitting. Usually, the coordinate points of the lane line are represented as coordinates in a local coordinate system with the host vehicle 110 as the origin. Furthermore, by polynomial fitting the lane line information and vehicle state information, the lane line of the host vehicle is obtained. For example, a fifth-degree polynomial is used to fit the lane line information and vehicle state information to obtain the lane line of the host vehicle. Among them, the general form of the fifth-degree polynomial is: ; Among them, x is the distance along the lane direction, y is the offset perpendicular to the lane direction, a 0, a 1, a 2, a 3,a 4, a 5 are the coefficients of a fifth-degree polynomial.

[0046] The least squares method is used to solve for the coefficients of the fifth-degree polynomial. The goal of the least squares method is to minimize the sum of the squares of the errors between the curve fitted by the polynomial and the actual lane line points, and obtain the coefficients of the fifth-degree polynomial. a 0, a 1, a 2, a 3, a 4, a 5. Substitute the coefficients of the fifth-degree polynomial obtained by the solution into the polynomial equation to obtain the lane line equation of the host vehicle. According to the lane line equation, the lane line coordinates at different positions can be calculated, thereby determining the lane line of the host vehicle.

[0047] Step 403: Determine candidate corner points based on the distance between at least one corner point of the environmental target sensed by the host vehicle and the lane line.

[0048] Among them, for the environmental target in step 403, it can be a vehicle, an obstacle, etc. in the front. There can be one or more environmental targets. For each environmental target, at least one corner point is obtained to be used as a candidate for the cruise target point.

[0049] In this step, the controller of the adaptive cruise control system can sense the environmental targets around the host vehicle 110 through sensors such as the camera, millimeter-wave radar, and lidar of the host vehicle 110, such as vehicles, obstacles, etc. in the front. For each sensed environmental target, at least one corner point is extracted. In a specific application, a corner point detection algorithm can be used, such as Harris corner detection, Shi-Tomasi corner detection, etc., to detect the corner points of the environmental target from the road image; for three-dimensional point cloud data, the corner points of the environmental target can be determined by analyzing the geometric features of the point cloud. Furthermore, calculate the distance between the corner points of each environmental target and the lane line obtained in the above step 201, and screen out candidate corner points from at least one corner point according to a distance threshold. For example, only select the corner points within a certain range from the lane line as candidate corner points, and exclude the corner points that are too far away.

[0050] In this way, by determining candidate corner points based on the distance between at least one corner point of the environmental target sensed by the host vehicle and the lane line, candidate corner points within a certain range from the lane line can be screened out, and the intersection points that are far from the lane line can be excluded, thereby reducing the computational complexity of screening cruise target points. At the same time, compared with the method of determining the relative distance from the host vehicle by using the reference point at the rear of the target vehicle in the prior art, the method provided in this embodiment can more accurately locate the relative position between the environmental target and the host vehicle 110, and reduce the possibility of false alarms or missed alarms of the cruise target.

[0051] Step 404: Generate the trajectory line of the host vehicle based on the lane line, and obtain multiple trajectory points on the trajectory line at a preset interval.

[0052] Among them, the preset interval in the above step 404 can be set to 0.5 meters, 1 meter, 1.5 meters, etc. The setting of the preset interval can be determined according to actual needs and will not be specifically limited here.

[0053] In this step, the controller of the adaptive cruise control system generates the trajectory line of the host vehicle 110 based on the lane line of the host vehicle 110 obtained in the above step 402. For example, if the host vehicle 110 needs to keep driving in the current lane, the trajectory line can be generated along the center line of the lane line; if the host vehicle 110 needs to perform a lane change operation, the corresponding trajectory line is generated according to the target lane of the lane change and the current lane line. Sprinkle points on the generated trajectory line at a preset interval to obtain multiple trajectory points. The size of the preset interval can be adjusted according to actual needs. The smaller the interval, the denser the trajectory points, and the higher the screening accuracy of the subsequent cruise target points, but the computational amount will also increase accordingly.

[0054] In this way, the trajectory line of the host vehicle is generated based on the lane line. This trajectory line can represent the ideal route for the host vehicle 110 to drive along the current lane. By obtaining multiple trajectory points on the trajectory line at a preset interval, the expected position points of the host vehicle 110 at future time points are represented by the trajectory points, which is beneficial to adjusting the following distance and speed at a specific time point and improving the driving safety of the host vehicle 110.

[0055] Step 405: Screen out the cruise target points from the candidate corner points by comparing the distances between the candidate corner points and the multiple trajectory points.

[0056] In this step, the lateral distance and longitudinal distance between the candidate corner points and each trajectory point can be used as judgment conditions to screen out the cruise target points. For example, thresholds for the lateral distance and longitudinal distance can be set, and the candidate corner point closest to the trajectory point and within the threshold range is selected as the cruise target point. The method of weighted distance can also be used. Different weights are assigned according to the importance of the lateral distance and longitudinal distance, the weighted distance is calculated, and the candidate corner point with the smallest weighted distance is selected as the cruise target point.

[0057] In summary, the present application provides an adaptive cruise target screening method. According to road environment information, lane line information is determined; by fitting the lane line information and vehicle state information, the lane line of the host vehicle is obtained; based on the distance between at least one corner point of the environmental target sensed by the host vehicle and the lane line, candidate corner points are determined; based on the lane line, a trajectory line of the host vehicle is generated, and multiple trajectory points on the trajectory line are obtained at a preset interval; by comparing the distances between the candidate corner points and the multiple trajectory points, cruise target points are screened out from the candidate corner points. In this way, by obtaining known lane line information through road environment information and generating the lane line of the host vehicle by fitting the lane line information and vehicle state information, the complexity of data processing can be reduced, and the response speed of the adaptive cruise system can be improved; furthermore, based on the distance between at least one corner point of the environmental target and the lane line to determine candidate corner points can more accurately locate the relative position between the environmental target and the host vehicle, reducing the possibility of false alarms or missed reports of cruise targets; by comparing the distances between the candidate corner points and multiple trajectory points on the trajectory line of the host vehicle and screening out cruise target points from the candidate corner points, the screening process of cruise target points can be dynamically adjusted, improving the real-time decision-making ability of the adaptive cruise system and ensuring the safety of the host vehicle during high-speed driving.

[0058] In an embodiment of the present application, as an optional implementation manner, in the above step 401, determining lane line information according to road environment information includes: extracting lane line information from the road environment information; or extracting road contour information from the road environment information and determining lane line information according to the road contour information.

[0059] In this step, for the case where there are lane lines on the road surface (such as highways, urban roads, etc.), the controller of the adaptive cruise system can use sensors such as on-vehicle cameras and lidar to collect road environment information. For example, the camera can obtain image data of the road, and the lidar can obtain three-dimensional point cloud data of the road. The lane lines are identified from the road environment information according to lane line features such as the shape and color of the lane lines. In this way, the position and state of the lane lines can be detected in real time, providing a timely decision-making basis for subsequent cruise target screening.

[0060] For the case where there are no lane lines on the road surface (such as curves, intersections, etc.), the controller of the adaptive cruise system can extract road contour information from the road environment information, and then determine lane line information according to the road contour information. For example, according to rules such as the width of the road and the number of lanes, the position of the lane lines is estimated within the road contour; for another example, machine learning algorithms (such as support vector machines, neural networks, etc.) are used to train the road contour information to predict the position of the lane lines. In specific applications, the road contour information is usually in the shape of a funnel or horn that is wider near and narrower far away, and the shape of the estimated lane lines can be consistent with the shape of the road contour information.

[0061] In this way, for the case where there are lane lines on the road surface, lane line information is extracted from the road environment information; for the case where there are no lane lines on the road surface, road contour information is extracted from the road environment information, and lane line information is determined based on the road contour information. In this way, the lane line information of the host vehicle can be obtained regardless of whether there are lane lines, so that different types of road scenarios can be adapted, thereby improving the stability of cruise target point recognition and reducing the possibility of false alarms or missed reports of cruise target points.

[0062] Since in a complex driving environment, the sensors mounted on the host vehicle 110 can usually identify multiple environmental targets, using the corner points of all environmental targets as candidates for cruise target points will bring a large amount of computation and affect the response speed of the cruise target point screening result. Therefore, the position information of the corner points of the environmental targets in the host vehicle coordinate system can be calculated, and the distance between the corner points and the lane lines of the host vehicle can be determined through this position coordinate. Then, candidate corner points within a certain range of the lane lines can be screened out, and cruise target points can be screened out from the candidate corner points, which can improve the response speed of the cruise target point screening result. In a specific embodiment, the embodiment of the present application provides an adaptive cruise target screening method, as Figure 5 shown Figure 5 FIG. shows a flowchart of an adaptive cruise target screening method provided by another embodiment of the present application. This method can be applied to the controller in the adaptive cruise system. The method 500 includes: Step 501: Obtain the lane lines of the host vehicle by fitting the road environment information and the vehicle state information.

[0063] Among them, the road environment information in step 501 can be lane line information such as lane line position and shape, traffic sign information such as speed limit signs and turning instructions, or road surface information such as road contours and obstacles; the vehicle state information in step 501 can be information such as speed, acceleration, and steering angle, or the braking state information of the vehicle.

[0064] In this step, the controller in the adaptive cruise system can obtain the road environment information and the vehicle state information through a variety of sensors mounted on the host vehicle 110. For example, the road image is captured by a camera, and the color, texture, and edge features of the lane lines are identified through image recognition technology; the distances and relative speeds to environmental targets such as road boundaries and other vehicles are measured by millimeter-wave radar; a three-dimensional point cloud model of the road is constructed by lidar to clearly present the geometric shape of the road; the rotation speed of the wheels is measured by a wheel speed sensor, and then the driving speed of the vehicle is calculated; the acceleration of the vehicle is measured by an accelerometer; the attitude and steering angle of the vehicle are detected by a gyroscope.

[0065] Adopt a preset fitting algorithm, for example, polynomial fitting, spline curve fitting, etc., to fit the lane lines of the host vehicle 110 according to the acquired road environment information and vehicle state information. For example, for the road images collected by the camera, the Hough transform can be used to detect the edges of the lane lines, and then the least squares method can be used for polynomial fitting in combination with the vehicle state information of the host vehicle 110 to obtain the mathematical expression of the lane lines. Among them, since there are many types and large amounts of data obtained through multiple sensors, before fitting the road environment information and vehicle state information to obtain the lane lines of the host vehicle 110, the acquired road environment information and vehicle state information can also be preprocessed, and the preprocessing includes normalization processing, noise removal, filtering processing, etc., to improve the quality of the data; and then the lane lines of the host vehicle 110 can be obtained by fitting the preprocessed road environment information and vehicle state information.

[0066] In this way, by fitting the road environment information and vehicle state information, the specific position of the lane where the host vehicle 110 is currently located and its lane lines can be accurately obtained, providing accurate lane line information of the host vehicle 110 for the subsequent screening of cruise target points.

[0067] Step 502: Determine the position information of at least one corner point of the environmental target in the vehicle coordinate system of the host vehicle according to the length information, width information and heading angle of the environmental target.

[0068] In this step, the length information, width information and heading angle of the environmental target can be measured by sensors such as the radar and camera of the host vehicle 110, and through geometric operations, the position information of at least one corner point of the environmental target in the vehicle coordinate system of the host vehicle can be obtained.

[0069] In an exemplary embodiment, the position coordinates of the four corner points of the target vehicle 120 are calculated respectively with the center zero point of the vehicle coordinate system of the host vehicle 110. As Figure 6 shown, the coordinates of the four corner points are deduced in a left-handed coordinate system, and the formula is as follows: The position coordinate of corner point 1 in the vehicle coordinate system of the host vehicle is: ; The position coordinate of corner point 2 in the vehicle coordinate system of the host vehicle is: ; The position coordinate of corner point 3 in the vehicle coordinate system of the host vehicle is: ; The position coordinate of corner point 4 in the vehicle coordinate system of the host vehicle is: ; Among them, a is the vehicle length of the target vehicle 120,b is the width of the target vehicle 120, Q and is the heading angle of the target vehicle 120.

[0070] In this way, compared with the method in the related art of determining the relative distance from the ego vehicle by using the reference point at the rear of the target vehicle, in the embodiment of the present application, by determining the position information of at least one corner point of the environmental target in the ego vehicle coordinate system, the specific position of the environmental target relative to the ego vehicle can be accurately obtained; compared with the method in the related art of determining the relative distance from the ego vehicle by using the contour of the target vehicle, the method provided in the embodiment of the present application can effectively cope with complex traffic environments and adverse weather conditions, reduce the possibility of false alarms or missed reports of cruise targets, and ensure the safety and comfort of vehicle driving.

[0071] Step 503: Determine the distance between at least one corner point and the lane line according to the position information of at least one corner point and the position information of the lane line; determine the corner points with a distance less than a preset distance threshold among at least one corner point as candidate corner points.

[0072] Among them, the preset distance threshold can be 1 meter, 1.5 meters, 2 meters, etc., and can be specifically adjusted according to actual needs, and no specific limitation is made here.

[0073] Continuing with the above embodiment, for any corner point coordinate and the fitted lane line of the ego vehicle 110 , where the function is a continuously differentiable function, calculate the distance from any corner point to the function curve d , and its calculation formula is: . Thus, it can be determined that the corner points with a distance less than the preset distance threshold among at least one corner point are candidate corner points.

[0074] In this way, according to the distance between at least one corner point and the lane line, candidate corner points with a distance less than the preset threshold are screened out, which can enable the adaptive cruise system to timely discover environmental targets that may interfere with the lane line. For example, when the corner points of environmental targets such as vehicles parked by the roadside and pedestrians suddenly entering the lane approach the lane line, the adaptive cruise system can quickly identify them, and then screen the cruise target points in order to timely adjust the speed of the ego vehicle 110 to ensure the safety of the ego vehicle driving.

[0075] Step 504: Generate a trajectory line of the ego vehicle based on the lane line, and obtain a plurality of trajectory points on the trajectory line at a preset interval.

[0076] Among them, the preset interval in the above step 504 can be set to 0.5 meters, 1 meter, 1.5 meters, etc., and the setting of the preset interval can be determined according to actual needs, and no specific limitation is made here.

[0077] In this step, the controller of the adaptive cruise control system generates a trajectory line of the host vehicle 110 based on the lane lines of the host vehicle obtained in the above step 501. For example, if the host vehicle 110 needs to keep driving in the current lane, the trajectory line can be generated along the center line of the lane lines; if the host vehicle 110 needs to perform a lane change operation, a corresponding trajectory line is generated according to the target lane of the lane change and the current lane lines. Points are scattered on the generated trajectory line at a preset interval to obtain a plurality of trajectory points. The size of the preset interval can be adjusted according to actual requirements. The smaller the interval, the denser the trajectory points, and the higher the screening accuracy of the subsequent cruise target points, but the computational amount will also increase accordingly.

[0078] In this way, a trajectory line of the host vehicle is generated based on the lane lines. This trajectory line can represent the ideal route for the host vehicle 110 to drive along the current lane. By obtaining a plurality of trajectory points on the trajectory line at a preset interval, the expected position points of the host vehicle 110 at future time points are represented by the trajectory points, which is beneficial to adjusting the following distance and speed at a specific time point and improving the driving safety of the host vehicle 110.

[0079] Step 505: Screen out the cruise target points from the candidate corner points by comparing the distances between the candidate corner points and the plurality of trajectory points.

[0080] In this step, the lateral distance and the longitudinal distance between the candidate corner points and each trajectory point can be used as judgment conditions to screen out the cruise target points. For example, thresholds for the lateral distance and the longitudinal distance can be set, and the candidate corner point that is the closest to the trajectory point and within the threshold range is selected as the cruise target point. The method of weighted distance can also be adopted. Different weights are assigned according to the importance of the lateral distance and the longitudinal distance, the weighted distance is calculated, and the candidate corner point with the smallest weighted distance is selected as the cruise target point.

[0081] In summary, the present application provides an adaptive cruise target screening method. By fitting the road environment information and vehicle state information, the lane line of the host vehicle is obtained; according to the length information, width information and heading angle of the environmental target, the position information of at least one corner point of the environmental target in the vehicle coordinate system of the host vehicle is determined; according to the position information of at least one corner point and the position information of the lane line, the distance between at least one corner point and the lane line is determined; the corner points with a distance less than a preset distance threshold among at least one corner point are determined as candidate corner points; a trajectory line of the host vehicle is generated based on the lane line, and a plurality of trajectory points on the trajectory line are obtained at a preset interval; by comparing the distances between the candidate corner points and the plurality of trajectory points, the cruise target points are screened out from the candidate corner points. In this way, by fitting the road environment information and vehicle state information, the lane line of the host vehicle is obtained; according to the length information, width information and heading angle of the environmental target, the position information of at least one corner point of the environmental target in the vehicle coordinate system of the host vehicle is determined; according to the position information of at least one corner point and the position information of the lane line, the distance between at least one corner point and the lane line is determined, so that the adaptive cruise system can timely detect environmental targets that may interfere with the lane line; and then by comparing the distances between the candidate corner points and the plurality of trajectory points on the trajectory line of the host vehicle, the cruise target points are screened out from the candidate corner points, so as to timely adjust the driving speed of the host vehicle and ensure the safety of vehicle driving.

[0082] In a complex driving environment, the adaptive cruise system often faces the situation of multiple candidate corner points. Usually, the system will select the candidate corner point closest to the trajectory line of the host vehicle as the cruise target point. However, the point closest to the trajectory line is not necessarily the corner point that needs to be tracked, and it may be a corner point located at the rear end of the environmental target, resulting in a false alarm problem for the cruise target point. To address this problem, starting from the target trajectory point closest to the target point of the host vehicle, the target distances between each candidate corner point and the trajectory point are compared in turn, so as to screen out a suitable cruise target point from multiple candidate corner points, thereby effectively avoiding the false alarm problem in the process of selecting the cruise target point. In a specific embodiment, the embodiment of the present application provides an adaptive cruise target screening method, as Figure 7 shown Figure 7 FIG. shows a schematic flowchart of an adaptive cruise target screening method provided by another embodiment of the present application. This method can be applied to the controller in the adaptive cruise system. The method 700 includes: Step 701, by fitting the road environment information and vehicle state information, obtain the lane line of the host vehicle.

[0083] Among them, the road environment information in step 701 can be lane line information such as lane line position and shape, traffic sign information such as speed limit signs and turning instructions, or road surface information such as road contour and obstacles; the vehicle state information in step 701 can be information such as speed, acceleration, and steering angle, or the braking state information of the vehicle.

[0084] In this step, the controller in the adaptive cruise control system can obtain the road environment information and vehicle state information through a variety of sensors mounted on the vehicle 110. For example, it can capture road images through a camera and identify the color, texture, and edge features of the lane lines through image recognition technology; measure the distance and relative speed to environmental targets such as road boundaries and other vehicles through millimeter-wave radar; construct a three-dimensional point cloud model of the road through lidar to clearly present the geometric shape of the road; measure the rotational speed of the wheels through wheel speed sensors and then calculate the driving speed of the vehicle; measure the acceleration of the vehicle through an accelerometer; and detect the attitude and steering angle of the vehicle through a gyroscope.

[0085] Adopt a preset fitting algorithm, such as polynomial fitting, spline curve fitting, etc., to fit the lane lines of the vehicle 110 based on the obtained road environment information and vehicle state information. For example, for the road images collected by the camera, the Hough transform can be used to detect the edges of the lane lines, and then the least squares method can be used for polynomial fitting in combination with the vehicle state information of the vehicle 110 to obtain the mathematical expression of the lane lines. Among them, since there are many types and large amounts of data obtained through multiple sensors, before fitting the road environment information and vehicle state information to obtain the lane lines of the vehicle 110, the obtained road environment information and vehicle state information can also be preprocessed, and the preprocessing includes normalization processing, noise removal, filtering processing, etc., to improve the quality of the data; and then the lane lines of the vehicle 110 can be obtained by fitting the preprocessed road environment information and vehicle state information.

[0086] In this way, by fitting the road environment information and vehicle state information, the specific position of the lane where the vehicle 110 is currently located and its lane lines can be accurately obtained, providing accurate lane line information of the vehicle 110 for the subsequent screening of cruise target points.

[0087] Step 702: Determine candidate corner points based on the distance between at least one corner point of the environmental target perceived by the vehicle itself and the lane line.

[0088] Among them, the environmental target in step 702 can be a vehicle, an obstacle, etc. in front, and there can be one or more environmental targets. For each environmental target, at least one corner point is obtained respectively to be used as a candidate for the cruise target point.

[0089] In this step, the controller of the adaptive cruise control system can sense the environmental targets around the host vehicle 110 through sensors such as the camera, millimeter-wave radar, and lidar of the host vehicle 110, such as the vehicle and obstacles ahead. For each sensed environmental target, at least one corner point is extracted. In specific applications, corner point detection algorithms such as Harris corner detection and Shi-Tomasi corner detection can be used to detect the corner points of the environmental target from the road image; for 3D point cloud data, the corner points of the environmental target can be determined by analyzing the geometric features of the point cloud. Furthermore, the distance between the corner points of each environmental target and the lane lines obtained in the above step 701 is calculated, and candidate corner points are screened out from at least one corner point according to a distance threshold. For example, only the corner points within a certain range from the lane lines are selected as candidate corner points, and the corner points that are too far away are excluded.

[0090] In this way, based on the distance between at least one corner point of the environmental target sensed by the host vehicle and the lane lines, candidate corner points are determined, and the candidate corner points within a certain range from the lane lines can be screened out, and the intersection points that are far from the lane lines are excluded, thereby reducing the computational complexity of cruise target point screening. At the same time, compared with the method of determining the relative distance from the host vehicle by using the reference point at the rear of the target vehicle in the prior art, the method provided in this embodiment can more accurately locate the relative position between the environmental target and the host vehicle 110, and reduce the possibility of false alarms or missed detections of cruise targets.

[0091] Step 703: Generate a trajectory line of the host vehicle based on the lane lines, and obtain multiple trajectory points on the trajectory line at a preset interval.

[0092] Among them, the preset interval in the above step 703 can be set to 0.5 meters, 1 meter, 1.5 meters, etc. The setting of the preset interval can be determined according to actual needs and will not be specifically limited here.

[0093] In this step, the controller of the adaptive cruise control system generates a trajectory line of the host vehicle 110 based on the lane lines of the host vehicle 110 obtained in the above step 701. For example, if the host vehicle 110 needs to keep driving in the current lane, the trajectory line can be generated along the center line of the lane line; if the host vehicle 110 needs to perform a lane change operation, the corresponding trajectory line is generated according to the target lane of the lane change and the current lane line. Points are scattered on the generated trajectory line at a preset interval to obtain multiple trajectory points. The size of the preset interval can be adjusted according to actual needs. The smaller the interval, the denser the trajectory points, and the higher the screening accuracy of subsequent cruise target points, but the computational amount will also increase accordingly.

[0094] In this way, a trajectory line of the host vehicle is generated based on the lane line. This trajectory line can represent the ideal route for the host vehicle 110 to travel along the current lane. By obtaining multiple trajectory points on the trajectory line at a preset interval, the expected position points of the host vehicle 110 at future time points are represented by the trajectory points, which is conducive to adjusting the following distance and speed at a specific time point and improving the driving safety of the host vehicle 110.

[0095] Step 704: Starting from the target trajectory point among the multiple trajectory points, sequentially compare the target distances between the candidate corner points and the multiple trajectory points; according to the target distances, screen out the cruise target points from the candidate corner points.

[0096] Among them, the target trajectory point in step 704 is the point among the multiple trajectory points that is closest to the host vehicle target point. In specific applications, the center point of the front bumper of the host vehicle 110 is usually determined as the host vehicle target point.

[0097] In this step, first, the controller in the adaptive cruise control system generates multiple trajectory points, such as trajectory point 0, trajectory point 1, trajectory point 2,..., trajectory point 100. Starting from the target trajectory point among the multiple trajectory points, for example, trajectory point 0, sequentially compare the target distances between the candidate corner points and trajectory point 0, trajectory point 1, trajectory point 2,..., trajectory point 100. According to the target distances and a preset screening rule, screen out the cruise target points from the candidate corner points. For example, select the candidate corner point closest to the target trajectory point as the cruise target point, or select the candidate corner points within a certain specific range of distances as the cruise target points.

[0098] In an optional implementation manner in the embodiments of the present application, the target distances in the above step 704 include lateral distances and longitudinal distances; in the above step 704, screening out the cruise target points from the candidate corner points according to the target distances includes: Determine the candidate corner points with a lateral distance less than a preset lateral distance threshold as the cruise target points; and / or, determine the candidate corner points with a longitudinal distance less than a preset longitudinal distance threshold as the cruise target points.

[0099] Among them, the preset lateral distance threshold for this step can be set to 0.5 meters, 0.8 meters, 1 meter, etc., and the preset lateral distance can be adjusted according to actual needs and is not specifically limited herein; the preset longitudinal distance threshold can be set to 1 meter, 2 meters, 5 meters, etc., and the preset longitudinal distance can be adjusted according to actual needs and is not specifically limited herein.

[0100] In this way, by using the lateral distance and / or the longitudinal distance as the screening conditions for the cruise target points, the screening rules for the cruise target points can be determined according to different cruise tasks, so as to adapt to the changing traffic conditions.

[0101] In summary, the present application provides an adaptive cruise target screening method. By fitting the road environment information and vehicle state information, the lane lines of the host vehicle are obtained. According to the length information, width information, and heading angle of the environmental target, the position information of at least one corner point of the environmental target in the vehicle coordinate system of the host vehicle is determined. According to the position information of at least one corner point and the position information of the lane lines, the distance between at least one corner point and the lane lines is determined. The corner points with a distance less than a preset distance threshold among at least one corner point are determined as candidate corner points. A trajectory line of the host vehicle is generated based on the lane lines, and multiple trajectory points on the trajectory line are obtained at a preset interval. Starting from the target trajectory point among the multiple trajectory points, the target distances between the candidate corner points and the multiple trajectory points are compared in sequence. According to the target distances, the cruise target points are screened out from the candidate corner points. In this way, by starting from the target trajectory point closest to the target point of the host vehicle and comparing the target distances between each candidate corner point and the trajectory points in sequence to screen out appropriate cruise target points from multiple candidate corner points, the false alarm problem in the process of selecting cruise target points can be effectively avoided, and the driving safety of the vehicle is improved.

[0102] In addition, as Figure 8 shown, Figure 8 FIG. shows a schematic structural diagram of an adaptive cruise target screening device provided by an embodiment of the present application. The device 800 includes: A lane line acquisition module 801, configured to obtain the lane lines of the host vehicle by fitting the road environment information and vehicle state information; A candidate corner point determination module 802, configured to determine candidate corner points based on the distance between at least one corner point of an environmental target sensed by the host vehicle and the lane lines; A trajectory point acquisition module 803, configured to generate a trajectory line of the host vehicle based on the lane lines and obtain multiple trajectory points on the trajectory line at a preset interval; A target corner point screening module 804, configured to screen out cruise target points from the candidate corner points by comparing the distances between the candidate corner points and the multiple trajectory points.

[0103] In a specific embodiment, when the lane line acquisition module 801 is configured to obtain the lane lines of the host vehicle by fitting the road environment information and vehicle state information, it is specifically configured to: Determine lane line information according to the road environment information; Obtain the lane lines of the host vehicle by fitting the lane line information and the vehicle state information.

[0104] In a specific embodiment, when the lane line acquisition module 801 is configured to determine lane line information according to the road environment information, it is specifically configured to: Extract lane line information from the road environment information; or, Extract road contour information from road environment information, and determine lane line information according to the road contour information.

[0105] In a specific embodiment, when the candidate corner point determination module 802 is used to determine candidate corner points based on the distance between at least one corner point of an environmental target sensed by the vehicle itself and the lane line, it is specifically configured to: Determine the position information of at least one corner point of the environmental target in the vehicle coordinate system of the vehicle itself according to the length information, width information, and heading angle of the environmental target; Determine the distance between the at least one corner point and the lane line according to the position information of the at least one corner point and the position information of the lane line; Determine the corner points with a distance less than a preset distance threshold among the at least one corner point as candidate corner points.

[0106] In a specific embodiment, when the target corner point screening module 804 is used to screen cruise target points from the candidate corner points by comparing the distances between the candidate corner points and the multiple trajectory points, it is specifically configured to: Starting from the target trajectory point among the multiple trajectory points, sequentially compare the target distances between the candidate corner points and the multiple trajectory points, where the target trajectory point is the point closest to the vehicle target point among the multiple trajectory points; Screen cruise target points from the candidate corner points according to the target distances.

[0107] In a specific embodiment, the target distance includes a lateral distance and a longitudinal distance; when the target corner point screening module 804 is used to screen cruise target points from the candidate corner points according to the target distances, it is specifically configured to: Determine the candidate corner points with a lateral distance less than a preset lateral distance threshold as cruise target points; and / or, Determine the candidate corner points with a longitudinal distance less than a preset longitudinal distance threshold as cruise target points.

[0108] Regarding the device in the above embodiments, the specific manners in which each unit performs operations have been described in detail in the embodiments related to the method, and will not be elaborated herein.

[0109] An embodiment of the present application provides an adaptive cruise target screening device, including a lane line acquisition module, a candidate corner determination module, a trajectory point acquisition module, and a target corner screening module; the lane line acquisition module obtains the lane line of the host vehicle by fitting the road environment information and the vehicle state information; the candidate corner determination module determines candidate corners based on the distance between at least one corner of the environmental target perceived by the host vehicle and the lane line; the trajectory point acquisition module generates a trajectory line of the host vehicle based on the lane line and obtains a plurality of trajectory points on the trajectory line at a preset interval; the target corner screening module screens out cruise target points from the candidate corners by comparing the distances between the candidate corners and the plurality of trajectory points. In this way, by fitting the road environment information and the vehicle state information, the lane line of the host vehicle is obtained; the candidate corners are determined based on the distance between at least one corner of the environmental target and the lane line, which can more accurately locate the relative position between the environmental target and the host vehicle and reduce the possibility of false alarms or missed reports of cruise targets; by comparing the distances between the candidate corners and the plurality of trajectory points on the trajectory line of the host vehicle and screening out cruise target points from the candidate corners, the screening process of the cruise target points can be dynamically adjusted, improving the real-time decision-making ability of the adaptive cruise system and ensuring the safety of the host vehicle during high-speed driving.

[0110] Figure 9 It is a schematic structural diagram of a vehicle provided by an embodiment of the present application.

[0111] Exemplarily, as Figure 9 shown, the vehicle 900 includes: a memory 901 and a processor 902. Among them, an executable program code 9011 is stored in the memory 901, and the processor 902 is used to call and execute the executable program code 9011 to execute the adaptive cruise target screening method.

[0112] In this embodiment, the vehicle can be divided into functional modules according to the above method examples. For example, each functional module can be corresponded, or two or more functions can be integrated into one processing module. The above integrated module can be implemented in the form of hardware. It should be noted that the division of modules in this embodiment is illustrative, only a logical function division, and there may be other division methods in actual implementation.

[0113] In the case of dividing each functional module according to each corresponding function, the vehicle 700 can include: a lane line acquisition module, a candidate corner determination module, a trajectory point acquisition module, a target corner screening module, etc. It should be noted that all relevant contents of each step involved in the above method embodiment can be cited in the function description of the corresponding functional module, and will not be repeated here.

[0114] The vehicle provided in this embodiment is used to execute the above-mentioned adaptive cruise target screening method, so the same effects as the above implementation method can be achieved.

[0115] In the case of adopting integrated units, the vehicle may include a processing module and a storage module. Among them, the processing module can be used to control and manage the actions of the vehicle. The storage module can be used to support the vehicle to execute mutual program codes and data, etc.

[0116] Among them, the processing module can be a processor or a controller, which can implement or execute various exemplary logic blocks, modules, and circuits described in connection with the disclosure of the present application. The processor can also be a combination that realizes computing functions. For example, it includes a combination of one or more microprocessors, a combination of digital signal processing (DSP) and a microprocessor, etc. The storage module can be a memory.

[0117] This embodiment also provides a computer-readable storage medium. Computer program codes are stored in the computer-readable storage medium (including but not limited to disk memories, CD-ROMs, optical memories, etc.). When the computer program codes run on a computer, the computer is enabled to execute the above-mentioned relevant method steps to implement an adaptive cruise target screening method provided in the above embodiment.

[0118] This embodiment also provides a computer program product. When the computer program product runs on a computer, the computer is enabled to execute the above-mentioned relevant steps to implement an adaptive cruise target screening method provided in the above embodiment.

[0119] Among them, the beneficial effects of the above embodiment can refer to the beneficial effects in the corresponding method provided above, which will not be elaborated here.

[0120] Through the description of the above embodiments, those skilled in the art can understand that for the convenience and conciseness of description, only the above-mentioned division of each functional module is used as an example. In actual applications, the above functions can be allocated to different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above.

[0121] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of modules or units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of devices or units can be in electrical, mechanical or other forms.

[0122] In the description of the present application, it should be understood that if terms such as "upper", "lower", "front", "rear", "left" and "right" are used to indicate the orientation or positional relationship, it is based on the orientation or positional relationship shown in the drawings. It is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the indicated position or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it should not be construed as a limitation of the present application.

[0123] It should be noted that in this text, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. It should also be noted that the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or also includes elements inherent in such a process, method, commodity or device. Without further limitation, the element defined by the statement "including one..." does not exclude the existence of another identical element in the process, method, commodity or device including the element.

[0124] The above are only the embodiments of the present application and are not used to limit the present application. For those skilled in the art, various changes and modifications can be made to the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present application shall be included within the scope of the claims of the present application.

Claims

1. An adaptive cruise target screening method, characterized in that, The method includes: Obtaining the lane lines of the host vehicle by fitting the road environment information and the vehicle state information; Determining candidate corner points based on the distances between at least one corner point of the environmental target sensed by the host vehicle and the lane lines; Generating a trajectory line of the host vehicle based on the lane lines, and obtaining a plurality of trajectory points on the trajectory line at a preset interval; Screening out cruise target points from the candidate corner points by comparing the distances between the candidate corner points and the plurality of trajectory points.

2. The adaptive cruise target screening method according to claim 1, wherein The step of obtaining the lane lines of the host vehicle by fitting the road environment information and the vehicle state information includes: Determining lane line information according to the road environment information; Obtaining the lane lines of the host vehicle by fitting the lane line information and the vehicle state information.

3. The adaptive cruise target screening method according to claim 2, wherein The step of determining lane line information according to the road environment information includes: Extracting lane line information from the road environment information; or Extracting road contour information from the road environment information, and determining lane line information according to the road contour information.

4. The adaptive cruise target screening method according to claim 1, characterized in that The step of determining candidate corner points based on the distances between at least one corner point of the environmental target sensed by the host vehicle and the lane lines includes: Determining the position information of at least one corner point of the environmental target in the vehicle coordinate system of the host vehicle according to the length information, width information and heading angle of the environmental target; Determining the distances between the at least one corner point and the lane lines according to the position information of the at least one corner point and the position information of the lane lines; Determining the corner points with distances less than a preset distance threshold among the at least one corner point as candidate corner points.

5. The adaptive cruise target screening method according to any one of claims 1 to 4, characterized in that The step of screening out cruise target points from the candidate corner points by comparing the distances between the candidate corner points and the plurality of trajectory points includes: Starting from the target trajectory point among the plurality of trajectory points, sequentially comparing the target distances between the candidate corner points and the plurality of trajectory points, where the target trajectory point is the point closest to the target point of the host vehicle among the plurality of trajectory points; Screening out cruise target points from the candidate corner points according to the target distances.

6. The adaptive cruise target screening method according to claim 5, characterized in that The target distances include lateral distances and longitudinal distances; the step of screening out cruise target points from the candidate corner points according to the target distances includes: Determining the candidate corner points with lateral distances less than a preset lateral distance threshold as cruise target points; and / or Determining the candidate corner points with longitudinal distances less than a preset longitudinal distance threshold as cruise target points.

7. An adaptive cruise target screening device, characterized in that, The device includes: A lane line acquisition module, configured to obtain the lane lines of the host vehicle by fitting the road environment information and the vehicle state information; A candidate corner point determination module, configured to determine candidate corner points based on the distances between at least one corner point of the environmental target sensed by the host vehicle and the lane lines; A trajectory point acquisition module, configured to generate a trajectory line of the host vehicle based on the lane lines, and obtain a plurality of trajectory points on the trajectory line at a preset interval; A target corner point screening module, configured to screen out cruise target points from the candidate corner points by comparing the distances between the candidate corner points and the plurality of trajectory points.

8. An electronic device, characterized in that, The electronic device includes a processor and a memory, and the memory stores programs or instructions that can run on the processor. When the programs or instructions are executed by the processor, the adaptive cruise target screening method described in any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium, characterized in that, Programs or instructions are stored on the computer-readable storage medium, and when the programs or instructions are executed by a processor, the adaptive cruise target screening method described in any one of claims 1 to 6 is implemented.

10. A vehicle, characterized in that, The vehicle includes at least one processor, and when the at least one processor is executed, the adaptive cruise target screening method described in any one of claims 1 to 6 is implemented.

Images