Target rejection method and device, equipment, storage medium and vehicle

Abstract

The invention provides a target elimination method and device, equipment, a storage medium and a vehicle, and the method comprises the steps: determining a region of interest located in front of a target vehicle in a lane where the target vehicle is located based on the vehicle state data corresponding to the target vehicle, and judging whether the lane where the target vehicle is located is a curve or not based on the lane data corresponding to the lane where the target vehicle is located. Based on obstacle data corresponding to an obstacle in front of the target vehicle, whether the obstacle is a target stationary obstacle and whether the obstacle is located in the region of interest is judged, and if the lane where the target vehicle is located is a curve, the obstacle is the target stationary obstacle and is located in the region of interest; if yes, the obstacle is removed from a set of all the obstacles serving as candidates of the nearest vehicle target in the path, so that the situation that the roadside static obstacle serves as the nearest vehicle target in the path by mistake can be effectively avoided, the situation that wrong braking or deceleration or even rear-end collision accidents are caused is reduced, and the automatic vehicle following experience of a driver is guaranteed.

Description

Technical Field

[0001] This application relates to the field of autonomous driving technology, specifically to a target elimination method, apparatus, device, storage medium, and vehicle. Background Technology

[0002] With the rapid development of intelligent driving technology, driver assistance functions such as adaptive cruise control (ACC), automatic emergency braking (AEB), and emergency lane keeping assist (ELK) have been increasingly widely used, bringing drivers a more convenient, safe, and comfortable driving experience.

[0003] The ACC function is used to achieve automatic longitudinal following of the vehicle. That is, when the closest in-path vehicle (CIPV) in front of the vehicle decelerates, the vehicle automatically brakes to maintain a safe distance. When the CIPV in front of the vehicle accelerates or changes lanes, the vehicle maintains or automatically accelerates back to the preset cruise speed.

[0004] In certain extreme cases (corner cases), such as curves or situations without lane markings, if there are vehicles parked on the side of the road, the autonomous vehicle may mistakenly identify the parked vehicle as a CIPV target when performing ACC function to automatically follow the vehicle. This may result in incorrect braking or deceleration when the vehicle is close to the parked vehicle, or even a rear-end collision, affecting the driver's experience of automatic following. Summary of the Invention

[0005] Based on the defects and deficiencies of the prior art, this application proposes a target elimination method, apparatus, device, storage medium, and vehicle, which can eliminate stationary obstacles located in the region of interest in front of the target vehicle that can detect the nearest vehicle target in its path from the set of all selected obstacles that are the nearest vehicle targets in the path in a curved scenario. This avoids mistakenly identifying obstacles as the nearest vehicle targets in the path, reduces the occurrence of incorrect braking or deceleration, or even rear-end collisions, and ensures the driver's automated following experience.

[0006] According to a first aspect of the embodiments of this application, a target elimination method is provided, comprising: Based on the vehicle status data corresponding to the target vehicle, determine the region of interest located in front of the target vehicle in the lane where the target vehicle is located; Based on the lane data corresponding to the lane where the target vehicle is located, determine whether the lane where the target vehicle is located is a curve; Based on the obstacle data corresponding to the obstacle in front of the target vehicle, it is determined whether the obstacle is a stationary obstacle and whether the obstacle is located within the region of interest; If the lane where the target vehicle is located is a curve, and the obstacle is a stationary obstacle located within the region of interest, then the obstacle is removed from the target candidate set, which is the set of all obstacles that are candidates for the nearest vehicle target within the path.

[0007] According to a second aspect of the embodiments of this application, a target rejection apparatus is provided, comprising: The determination module is used to determine the region of interest located in front of the target vehicle in the lane where the target vehicle is located, based on the vehicle status data corresponding to the target vehicle. The judgment module is used to determine whether the lane where the target vehicle is located is a curve based on the lane data corresponding to the lane where the target vehicle is located. The judgment module is further configured to determine whether the obstacle is a stationary obstacle and whether the obstacle is located within the region of interest, based on the obstacle data corresponding to the obstacle in front of the target vehicle. The elimination module is used to eliminate the obstacle from the target candidate set if the lane where the target vehicle is located is a curve, the obstacle is a stationary obstacle and is located in the region of interest, and the target candidate set is the set of all obstacles that are candidates for the nearest vehicle target in the path.

[0008] According to a third aspect of the embodiments of this application, an electronic device is provided, including a memory and a processor; The memory is connected to the processor and is used to store programs; The processor is used to implement the target elimination method as described in the first aspect by running a program in the memory.

[0009] According to a fourth aspect of the embodiments of this application, a storage medium is provided, on which a computer program is stored, and when the computer program is run by a processor, it implements the target elimination method as described in the first aspect.

[0010] According to a fifth aspect of the present application, a computer program product is provided, the computer program product including computer program instructions that, when executed by a processor, cause the processor to perform the target elimination method as described in the first aspect.

[0011] According to a sixth aspect of the embodiments of this application, a vehicle is provided, wherein the vehicle is provided with a target rejection device as described in the second aspect, or an electronic device as described in the third aspect.

[0012] In the aforementioned target elimination methods, devices, equipment, storage media, and vehicles, based on the lane data corresponding to the lane where the target vehicle is located, which determines that the lane is a curve, the region of interest in front of the vehicle, determined based on the vehicle state data corresponding to the target vehicle, and whether the obstacle in front of the target vehicle is a stationary obstacle and located within the region of interest, can be used to eliminate stationary obstacles in the target candidate set that are located within the region of interest. This can effectively avoid mistakenly identifying stationary obstacles within the region of interest as the nearest vehicle target in the path, i.e., the following target, in scenarios such as curves, thereby reducing the occurrence of situations where there is no braking or deceleration, or even rear-end collisions. Other methods of identifying stationary obstacles can better ensure the accuracy of stationary obstacle identification in various scenarios. Attached Figure Description

[0013] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of this application. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0014] Figure 1 This is a flowchart illustrating a target elimination method provided in an embodiment of this application.

[0015] Figure 2 This is a schematic diagram of a curve scenario provided in an embodiment of this application.

[0016] Figure 3 This is a schematic diagram of a target elimination process proposed in an embodiment of this application.

[0017] Figure 4 This is a schematic diagram of the structure of a target rejection device proposed in an embodiment of this application.

[0018] Figure 5 This is a schematic diagram of the structure of an electronic device proposed in an embodiment of this application. Detailed Implementation

[0019] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0020] Overview As described in the background section, in certain extreme situations, such as curves or scenarios without lane markings, if other vehicles or obstacles are parked beside the road where the autonomous vehicle is located, the autonomous vehicle may misidentify parked vehicles or obstacles as CIPV targets in front of it when performing ACC (Adaptive Cruise Control) for automated following. This is because existing perception algorithms typically assign an initial velocity to the obstacle and then gradually converge to determine the final speed. During the convergence process, the obstacle may be perceived as moving slowly and with a gradually changing speed, meaning the identified speed of the obstacle is inaccurate. This can lead to the vehicle or obstacle parked beside the road being mistaken for a CIPV target in front of the vehicle, resulting in incorrect braking or deceleration when close to the CIPV target, or even rear-end collisions, thus affecting the driver's automated following experience.

[0021] Building on this foundation, the inventors further discovered that, due to limitations in sensor perception capabilities and the complexity and diversity of scenarios, the identification of stationary obstacles is often a challenge in autonomous driving. As end-to-end learning models drive rapid iterations of deep learning algorithms, sensor perception capabilities are continuously improving, and the accuracy of stationary obstacle identification in different scenarios is gradually increasing. However, for certain extreme scenarios, such as curves, the accuracy of stationary obstacle identification remains relatively poor. Based on this, the inventors proposed a method for eliminating stationary obstacles that do not meet the CIPV target requirements in curved scenarios. After determining that the lane corresponding to the target vehicle's lane is a curve based on lane data, the method utilizes the region of interest (ROI) in front of the vehicle, determined by the vehicle state data corresponding to the target vehicle, and whether the obstacle in front of the target vehicle is a stationary obstacle and located within the ROI. This method eliminates stationary obstacles within the ROI from the target candidate set. It effectively avoids mistakenly identifying stationary obstacles within the ROI as the nearest vehicle target (i.e., the vehicle to follow) in curved scenarios, thereby reducing the occurrence of situations where there is no braking or deceleration, or even rear-end collisions. Other methods for identifying stationary obstacles can better ensure the accuracy of stationary obstacle identification in various scenarios.

[0022] Based on the above concept, this specification provides a target elimination method, which will be described exemplarily below with reference to the accompanying drawings.

[0023] Exemplary methods Please see Figure 1 In one exemplary embodiment, a target elimination method is provided, applied to a vehicle. For example... Figure 1 As shown, the target removal method includes steps S101-S104: S101: Based on the vehicle status data corresponding to the target vehicle, determine the region of interest located in front of the target vehicle in the lane where the target vehicle is located.

[0024] Among them, the vehicle status data corresponding to the target vehicle is the vehicle status data of the target vehicle.

[0025] Specifically, vehicle status data includes the vehicle's speed and yaw angle.

[0026] Based on the relationship between the vehicle speed and the speed compensation distance, the speed compensation distance corresponding to the vehicle speed is taken as the target speed compensation distance, and the sum of the preset forward-looking distance and the target speed compensation distance is determined as the longitudinal length of the region of interest, i.e., the region length.

[0027] The preset forward viewing distance can be adjusted based on actual working conditions.

[0028] Based on the road width of the road where the target vehicle is located and the preset lateral expansion margin, the lateral length of the region of interest, i.e., the region width, is determined.

[0029] The preset lateral expansion margin is the lateral safety buffer distance for the road to expand outwards on both the left and right sides, which can be determined based on actual working conditions, taking into account factors such as safety and false detection rate.

[0030] For example, the preset lateral expansion margin can be 0.5m.

[0031] For example, the lateral length of the region is the sum of the road width of the road where the target vehicle is located and two preset lateral extension margins.

[0032] Based on the longitudinal and lateral lengths of the region, the area in front of the target vehicle is defined as the target region.

[0033] For example, the target area is a rectangle, where the length of the target area is the vertical length of the area and the width of the target area is the horizontal length of the area.

[0034] Then, based on the vehicle's yaw angle, the target area is rotated to obtain the region of interest in front of the target vehicle.

[0035] For example, based on the vehicle's yaw angle α, and combined with the coordinates (x, y) of any corner point in the target area, according to x'=x cosα-y sinα and y'=x sinα+y The coordinates (x', y') of any corner point after rotation are obtained by calculating cosα. These corner coordinates are those of the corner point in the vehicle coordinate system. The vehicle coordinate system has its origin at the center of the rear axle of the target vehicle, with the x-axis pointing towards the front of the vehicle and the y-axis pointing towards the rear axle.

[0036] S102: Based on the lane data corresponding to the lane where the target vehicle is located, determine whether the lane where the target vehicle is located is a curve.

[0037] The lane data corresponding to the lane where the target is located includes the curvature of the lane centerline.

[0038] Specifically, the forward-facing camera of the target vehicle captures the lane image corresponding to the lane where the target vehicle is located, and obtains the curvature of the lane centerline obtained by the forward-facing camera recognizing the lane image.

[0039] More specifically, the forward-facing camera identifies the lane boundaries of the lane where the target vehicle is located by recognizing lane images and calculates the curvature of the centerline between the lane boundaries.

[0040] Depending on the specific needs, lane images can also be obtained directly from the forward-facing camera. By recognizing the obtained lane images, the curvature of the lane centerline can be obtained.

[0041] Alternatively, by using a radar positioned in front of the target vehicle, lane point cloud data corresponding to the lane in which the target vehicle is located can be collected, and the curvature of the lane centerline can be obtained by analyzing the lane point cloud data.

[0042] Alternatively, the curvature of the lane centerline can be obtained using multiple sensors, and the curvatures obtained from data acquired by different sensors can be fused to obtain the desired lane centerline curvature. The specific operation of this fusion process can be a weighted summation.

[0043] For example, the sensors include cameras and radar, and may also include other sensors.

[0044] If the curvature of the lane centerline is greater than a preset threshold, the lane containing the target vehicle is determined to be a curve. Conversely, if the curvature of the lane centerline is less than or equal to the preset threshold, the lane containing the target vehicle is determined not to be a curve.

[0045] S103: Based on the obstacle data corresponding to the obstacle in front of the target vehicle, determine whether the obstacle is a stationary obstacle and whether the obstacle is located within the region of interest.

[0046] By acquiring sensor data through cameras, radar, and other sensors, and by analyzing and fusing the sensor data, obstacle data corresponding to obstacles in front of the target vehicle can be obtained, including the speed and position of the obstacles in front of the target vehicle.

[0047] Determining whether an obstacle is a stationary target obstacle based on its speed.

[0048] Specifically, if the speed of an obstacle is greater than or equal to a preset speed threshold, then the obstacle is determined not to be a stationary obstacle. Conversely, if the speed of an obstacle is less than a preset speed threshold, then the obstacle is determined to be a stationary obstacle.

[0049] The location of an obstacle can be represented by its coordinates in the vehicle coordinate system of the target vehicle.

[0050] Specifically, based on the coordinates of the obstacle in the vehicle coordinate system and the coordinate range of the region of interest, it is determined whether the obstacle is located within the region of interest.

[0051] If the coordinates of an obstacle in the vehicle coordinate system are outside the coordinate range of the region of interest, then the obstacle is determined to be outside the region of interest.

[0052] S104: If the target vehicle is in a curved lane and the obstacle is a stationary obstacle located within the region of interest, then the obstacle will be removed from the target candidate set.

[0053] The target candidate set is the set of all obstacles that can be considered as candidates for the nearest vehicle target (i.e., CIPV target) in the path of the target vehicle.

[0054] Specifically, the obstacles included in the target candidate set are all obstacles located in front of the vehicle that can be detected by sensors on the vehicle and / or the roadside, such as vehicles, rocks, pedestrians, etc.

[0055] Accordingly, if the lane where the target vehicle is located is not a curve, or the obstacle is not a stationary obstacle, or the obstacle is not in the region of interest, then the obstacle in the target candidate set will not be eliminated.

[0056] In this embodiment, based on the lane data corresponding to the lane where the target vehicle is located, which determines that the lane is a curve, the region of interest in front of the vehicle is determined based on the vehicle state data corresponding to the target vehicle, and whether the obstacle in front of the target vehicle is a stationary obstacle and is located within the region of interest, to eliminate stationary obstacles in the target candidate set that are located within the region of interest. This can effectively avoid mistakenly identifying stationary obstacles within the region of interest as the nearest vehicle target in the path, i.e., the following target, in scenarios such as curves, thereby reducing the occurrence of situations where there is no braking or deceleration, or even rear-end collisions. Using other methods to identify stationary obstacles can better ensure the accuracy of stationary obstacle identification in various scenarios.

[0057] To avoid unnecessary waste of resources, in some embodiments, before performing the above steps S101-S104, it is first determined whether the target vehicle has the driver assistance function enabled. If the target vehicle has the driver assistance function enabled, then the above steps S101-S104 are performed. If the target vehicle has not enabled the driver assistance function, then the above steps S101-S104 are not performed, and the target vehicle is identified as a CIPV target according to the conventional target detection method.

[0058] Specifically, determine whether the ACC function in the driver assistance system is enabled. If it is enabled, perform the above steps; if it is not enabled, do not perform the above steps.

[0059] More specifically, after confirming that the ACC function is enabled, it is determined whether the lane keeping function is enabled. If the lane keeping function is enabled, the above steps are executed; if the lane keeping function is not enabled, the above steps are not executed.

[0060] In this embodiment, since the target vehicle follows the car under the control of its driver when the assisted driving function is not enabled, and the CIPV target is selected by the driver, performing the above steps may cause unnecessary waste of resources. Therefore, performing the above steps only when the assisted driving function is enabled can effectively avoid unnecessary waste of resources.

[0061] To effectively avoid mistakenly identifying stationary roadside obstacles as the nearest vehicle target within the path, in some embodiments, vehicle state data includes the vehicle's speed. Based on the vehicle state data corresponding to the target vehicle, a region of interest located in front of the target vehicle in its lane is determined, including: determining the target's longitudinal length based on the vehicle's speed and the correspondence between vehicle speed and the longitudinal length of the region; determining the target's lateral length based on the vehicle's speed and the correspondence between vehicle speed and the lateral length of the region; and determining the region of interest as an area extending from the front of the vehicle towards the front of the vehicle and gradually decreasing in width based on the target's longitudinal length and lateral length.

[0062] Based on the correspondence between vehicle speed and longitudinal length of the region, the longitudinal length of the region corresponding to the vehicle speed is taken as the target longitudinal length.

[0063] Specifically, the longitudinal length of the target is the total depth of the region of interest along the direction of vehicle travel.

[0064] The relationship between vehicle speed and longitudinal length of the region follows the principle of "larger distance, smaller distance": the greater the vehicle speed, the greater the longitudinal length of the region corresponding to that speed; and the smaller the vehicle speed, the smaller the lateral length of the region corresponding to that speed.

[0065] Based on the correspondence between vehicle speed and the lateral length of the area, the lateral length of the area corresponding to the vehicle speed is taken as the target lateral length.

[0066] Specifically, the target lateral length is the total width of the region of interest at the starting position of the vehicle's front.

[0067] The relationship between vehicle speed and the lateral length of the area follows the principle of "large narrow, small wide". That is, the greater the vehicle speed, the smaller the lateral length of the area corresponding to that vehicle speed, and the smaller the vehicle speed, the larger the lateral length of the area corresponding to that vehicle speed.

[0068] Furthermore, the correspondence between vehicle speed and the longitudinal length of the region, as well as the correspondence between vehicle speed and the lateral length of the region, can be stored in different preset mapping tables. That is, based on the vehicle speed, the target longitudinal length and target lateral length can be obtained by looking up the table.

[0069] Based on the longitudinal and lateral lengths of the target, the region extending from the front of the vehicle towards the front, with its width gradually decreasing until it reaches 0, is identified as the region of interest.

[0070] Specifically, the width of the region of interest gradually shrinks linearly to 0 as the distance from the front of the vehicle in the direction of its extension increases. Of course, depending on the actual needs, the width of the region of interest can also gradually shrink non-linearly to 0 as the distance from the front of the vehicle in the direction of its extension increases.

[0071] That is, according to the predefined shrinkage rules of the region of interest, the region of interest in front of the target vehicle is determined based on the longitudinal length and lateral length of the target.

[0072] For example, in the region of interest, the longitudinal coordinate of the starting position of the vehicle front is the value of the target longitudinal length, and the sum of the absolute values ​​of the coordinates of the lateral endpoints is the value of the target lateral length.

[0073] Alternatively, based on the shape of a predefined region of interest, such as a bullet shape (a combination of rectangle and cone) or a cone shape, the region of interest in front of the target vehicle can be determined according to the longitudinal and lateral lengths of the target.

[0074] In this embodiment, since vehicle speed is a key factor determining vehicle braking distance, driver reaction time, and environmental update frequency, it can serve as an important basis for defining the perception range. Using the target vehicle's own speed as the core variable, the longitudinal and lateral lengths of the target are determined by looking up a table. Based on these two dimensions, the region of interest in front of the target vehicle can be determined, enabling dynamic adjustment of the region of interest in front of the vehicle. Furthermore, since the region of interest extends from the front of the vehicle towards the front and gradually narrows in width, it is the area where CIPV targets may appear. Combining the region of interest allows for focused identification of obstacles in the area where CIPV targets may appear, effectively avoiding the identification of stationary roadside obstacles as CIPV targets.

[0075] To effectively avoid mistakenly identifying stationary roadside obstacles as the nearest vehicle target within the path, in some embodiments, the vehicle state data also includes vehicle steering parameters. After determining the region of interest as an area extending from the front of the vehicle towards the front of the vehicle and gradually decreasing in width based on the target's longitudinal length and lateral length, the method further includes: determining the target offset angle based on the vehicle steering parameters, and adjusting the angle between the longitudinal centerline of the region of interest and the longitudinal direction of the target to the target offset angle.

[0076] That is, after determining the region of interest as the area extending from the front of the vehicle towards the front of the vehicle and gradually decreasing in width, the region of interest is used as the basic region of interest. The longitudinal centerline of the basic region of interest coincides with the longitudinal direction of the vehicle, i.e. the body direction. Then, based on the target offset angle determined by the vehicle steering parameters, the longitudinal centerline or orientation of the basic region of interest is adjusted.

[0077] The vehicle steering parameters include the vehicle steering wheel angle, vehicle yaw angle, and / or vehicle turn signal status. Additionally, the target offset angle is the angle by which the region of interest rotates relative to the vehicle's longitudinal axis.

[0078] Specifically, an offset angle is determined based on each parameter in the vehicle steering parameters, and the offset angles corresponding to each parameter are weighted and summed to obtain the target offset angle.

[0079] The weights of the offset angles corresponding to each parameter can be determined based on the degree of influence of each parameter on the orientation of the region of interest.

[0080] More specifically, the vehicle's turn signal status includes both left and right turn signals being off, only the left turn signal being on, and only the right turn signal being on.

[0081] There is a correspondence between the vehicle's turn signal status and the offset angle. Based on this correspondence, the offset angle corresponding to the vehicle's turn signal status is determined. For example, when both left and right turn signals are off, the corresponding offset angle is 0; when only the left turn signal is on, the corresponding offset angle is a first preset offset angle, such as 3°; when only the right turn signal is on, the corresponding offset angle is a second preset offset angle, such as -3°. The sign of the offset angle does not represent magnitude. A positive offset angle for the region of interest indicates that the region of interest is biased to the left of the vehicle on the side furthest from the front of the vehicle; a negative offset angle indicates that the region of interest is biased to the right of the vehicle on the side furthest from the front of the vehicle.

[0082] The vehicle steering parameters specifically include the vehicle yaw angle over a period of time, or the yaw angle at the previous moment. The product of the change in the vehicle yaw angle and the scaling factor is taken as the offset angle corresponding to the vehicle yaw angle.

[0083] The scaling factor, which is less than or equal to 1, is used to map the change in the vehicle's yaw angle to the corresponding offset angle, and can be filtered to avoid jitter. The scaling factor can be determined based on the vehicle's speed.

[0084] Depending on the specific circumstances, the product of the difference between the lane heading angle and the vehicle's yaw angle and the scaling factor can also be used as the offset angle corresponding to the vehicle's yaw angle.

[0085] Based on the vehicle's steering wheel angle and the correspondence between the vehicle's steering wheel angle and the deflection angle, the offset angle corresponding to the vehicle's steering wheel angle is determined by looking up tables and other methods.

[0086] Alternatively, based on the vehicle's steering wheel angle and speed, the heading change angle of the target vehicle within a preset time period after the current moment is estimated, and the offset angle corresponding to the vehicle's steering wheel angle is determined based on the estimated heading change angle.

[0087] For example, the preset time period is, for example, 1 second.

[0088] The heading change angle is the angle of change in the longitudinal direction (direction of the vehicle) of the target vehicle.

[0089] Specifically, the model can be used to estimate the rate of change of the heading angle of the target vehicle based on the steering wheel angle and the vehicle speed, and then the heading angle can be determined by combining it with a preset time period.

[0090] That is, by inputting the steering wheel angle and speed of the vehicle into the model for estimation, the corresponding heading angle change rate of the target vehicle can be obtained. Then, the product of the duration of the preset time period and the heading angle change rate is determined as the heading angle change of the target vehicle within the preset time period after the current moment.

[0091] The aforementioned model can be a steady-state steering model. A steady-state steering model is a simplified mathematical model of a vehicle reaching a stable and balanced circular motion state under constant steering wheel angle and constant vehicle speed input.

[0092] Here, the steady-state steering model can predict the rate of change of the target vehicle's heading angle using a function that characterizes the mapping relationship between the vehicle's steering wheel angle, vehicle speed, and the rate of change of heading angle.

[0093] Then, the estimated heading change angle can be directly determined as the offset angle corresponding to the steering wheel angle of the vehicle.

[0094] Alternatively, the estimated heading change angle can be scaled, and the scaled heading change angle can be determined as the offset angle corresponding to the steering wheel angle of the vehicle. The scaling factor used in the scaling process can be the same as or different from the scaling factor used in the yaw angle processing described above.

[0095] Finally, the target offset angle is obtained by weighted summation of the steering wheel angle, yaw angle, and / or the offset angle corresponding to the vehicle's turn signal status.

[0096] In this embodiment, after determining the basic region of interest based on the vehicle speed, the orientation of the region of interest is dynamically deflected by combining the target offset angle determined by the vehicle's steering parameters, so that its longitudinal centerline is aligned with the actual or expected heading of the vehicle. This more accurately covers the driving path of the target vehicle and the area where CIPV targets may appear, thereby optimizing the identification of non-CIPV targets and effectively avoiding the identification of roadside stationary obstacles as CIPV targets.

[0097] To achieve accurate judgment of curved scenarios, in some embodiments, it is determined whether the lane where the target vehicle is located is a curve based on the lane data corresponding to the lane where the target vehicle is located. This includes: determining whether the lane where the target vehicle is located has lane lines based on the lane data corresponding to the lane where the target vehicle is located; if the lane where the target vehicle is located has lane lines, then determining whether the lane where the target vehicle is located is a curve based on the lane data; if the lane where the target vehicle is located does not have lane lines, then determining whether the lane where the target vehicle is located is a curve based on the vehicle steering parameters corresponding to the target vehicle.

[0098] Lane data is obtained by recognizing lane images captured by a forward-facing camera. This recognition operation can be performed by the forward-facing camera or by other devices located in or communicating with the vehicle.

[0099] Specifically, data is collected from the lane where the target vehicle is located using various sensors, such as cameras and radar sensors. The lane data corresponding to the data collected from various sensors are then fused to obtain the lane data corresponding to the lane where the target vehicle is located.

[0100] The lane data includes information about whether lane lines are present. This information includes whether lane lines are present or absent.

[0101] If both the lane data collected by the camera and the lane data collected by the radar sensor indicate the presence of lane lines, then the lane where the target vehicle is located has lane lines. If at least one of the lane data collected by the camera and the radar sensor indicates the absence of lane lines, then the lane where the target vehicle is located has no lane lines.

[0102] Alternatively, fusion processing can also refer to weighted summation.

[0103] For example, the presence or absence of lane lines in the lane data is represented by different values, such as 0 indicating the presence of lane lines and 1 indicating the absence of lane lines. If the values ​​of the presence or absence of lane lines in the lane data corresponding to data collected by different sensors are weighted and summed, and the resulting value is greater than a preset value, then it is determined that the lane in which the target vehicle is located has lane lines.

[0104] Depending on the specific circumstances, the fusion process may involve more complex algorithmic calculations, as detailed in existing technologies.

[0105] If the lane data obtained at the end shows "no lane line", then the lane where the target vehicle is located is determined to have no lane line. If the lane data obtained at the end shows "lane line", then the lane where the target vehicle is located is determined to have a lane line.

[0106] Alternatively, the lane data may include information about the presence or absence of lane lines, specifically whether a left lane line or a right lane line exists. The method for determining the presence or absence of left and right lane lines is similar to the method described above and will not be elaborated upon here.

[0107] Specifically, if the lane data obtained in the final result shows that there is no lane line on the left and no lane line on the right, then it is determined that the lane where the target vehicle is located has no lane line. If the lane data obtained in the final result shows that there is a lane line on the left and / or a lane line on the right, then it is determined that the lane where the target vehicle is located has a lane line.

[0108] Specifically, lane data includes the curvature of the lane centerline. There are lane lines in the lane where the target vehicle is located. Based on the lane data, when determining whether the lane where the target vehicle is located is a curve, the curvature of the lane centerline is determined to be greater than a preset threshold.

[0109] Specifically, the vehicle steering parameters include the vehicle steering wheel angle. When there are no lane lines in the lane where the target vehicle is located, based on the vehicle steering parameters corresponding to the target vehicle, such as the vehicle steering wheel angle, it is determined whether the lane where the target vehicle is located is a curve. If the vehicle steering wheel angle is greater than a preset angle threshold, then the lane where the target vehicle is located is determined to be a curve.

[0110] More specifically, if the steering wheel angle of the vehicle is greater than a preset angle threshold and continues for a preset duration, then the lane where the target vehicle is located is determined to be a curve.

[0111] Accordingly, if the steering wheel angle of the vehicle is less than or equal to a preset steering angle threshold, or if the duration of the steering wheel angle of the vehicle being greater than the preset steering angle threshold is less than a preset duration, then it is determined that the lane where the target vehicle is located is not a curve.

[0112] For example, if the left lane line of the current lane (the lane where the target vehicle is located) output by the forward-view camera does not exist, the right lane line of the current lane output by the forward-view camera does not exist, and the turning angle of the vehicle direction is greater than the preset turning angle threshold w1, and continues for a preset duration, then the current scene is determined to be a curve scene, that is, the lane where the target vehicle is located is a curve; otherwise, the current scene is not a curve scene, that is, the lane where the target vehicle is located is not a curve.

[0113] For example, a curve scenario can be as follows: Figure 2 As shown, the road in which the target vehicle travels contains two lanes, which are two-way lanes. s1 is the left boundary of the lane in which the target vehicle is located, s2 is the right boundary of the lane in which the target vehicle is located, s3 is the travel path of the target vehicle, the rectangles on both sides of the two-way lane are roadside obstacles, and the arrow extending from the front of the target vehicle is the longitudinal centerline direction of the region of interest in front of the target vehicle.

[0114] In this embodiment, depending on whether there are lane lines in the lane where the target vehicle is located, different methods are used to determine whether the lane where the target vehicle is located is a curve. This can achieve accurate determination of whether the lane where the target vehicle is located is a curve regardless of whether there are lane lines, thereby effectively improving the reliability of the system.

[0115] To ensure the accuracy of curve scene recognition, in some embodiments, lane data includes the quality value, length, and / or curvature of the lane line in the lane where the target vehicle is located. The quality value characterizes the clarity of the lane line. Based on the lane data, determining whether the lane where the target vehicle is located is a curve includes: determining whether the quality value of the lane line in the lane where the target vehicle is located is greater than a preset quality threshold; if the quality value of the lane line in the lane where the target vehicle is located is greater than the preset quality threshold, then determining whether the lane where the target vehicle is located is a curve based on the preset length range in which the length of the lane line falls and whether the curvature of the lane line is a preset curvature corresponding to the preset length range.

[0116] That is, based on whether the quality value of the lane line is greater than a preset quality threshold, the preset length range in which the length of the lane line in the lane where the target vehicle is located is located, and the relationship between the curvature of the lane line and the preset curvature of the lane line corresponding to the preset length range, it is determined whether the lane where the target vehicle is located is a curve.

[0117] The lane lines can refer to either the left lane line or the right lane line.

[0118] For example, the quality value of the lane markings can range from, for instance, an integer from 0 to 100. The higher the quality value, the clearer the lane markings. In other words, the quality value is positively correlated with the clarity of the lane markings.

[0119] Specifically, if the mass value of the lane line in the lane where the target vehicle is located is greater than a preset mass threshold, then based on the preset length range in which the length of the lane line in the lane where the target vehicle is located is located, and the relationship between the curvature of the lane line and the preset curvature of the lane line corresponding to the preset length range, it is determined whether the lane where the target vehicle is located is a curve.

[0120] There can be multiple preset length intervals, such as a first preset length interval and a second preset length interval. Correspondingly, there can be multiple preset curvatures, such as a first preset curvature and a second preset curvature. There is a one-to-one correspondence between different preset length intervals and different preset curvatures.

[0121] Accordingly, if the quality of the lane line in the lane where the target vehicle is located is less than or equal to a preset quality threshold, then it is determined that the lane where the target vehicle is located is not a curve.

[0122] More specifically, if the length of the lane line of the lane where the target vehicle is located is within a first preset length range, and the curvature of the lane line of the lane where the target vehicle is located is equal to the first preset curvature of the lane line corresponding to the first preset length range, then the lane where the target vehicle is located is determined to be a curve.

[0123] If the length of the lane line of the lane where the target vehicle is located is within the second preset length range, and the curvature of the lane line of the lane where the target vehicle is located is equal to the second preset curvature of the lane line corresponding to the second preset length range, then the lane where the target vehicle is located is determined to be a curve.

[0124] Accordingly, if the length of the lane line in the lane where the target vehicle is located is within a first preset length range, and the curvature of the lane line in the lane where the target vehicle is located is not equal to the first preset curvature of the lane line corresponding to the first preset length range, then it is determined that the lane where the target vehicle is located is not a curve. Alternatively, if the length of the lane line in the lane where the target vehicle is located is not within the first preset length range, and the curvature of the lane line in the lane where the target vehicle is located is equal to the first preset curvature of the lane line corresponding to the first preset length range, then it is determined that the lane where the target vehicle is located is not a curve.

[0125] Wherein, the first preset length interval is smaller than the second preset length interval, and correspondingly, the first preset curvature is smaller than the second preset curvature.

[0126] In addition, the first preset curvature can specifically refer to a range of preset values ​​centered on the first preset curvature. Similarly, the second preset curvature can specifically refer to a range of preset values ​​centered on the second preset curvature.

[0127] For example, taking the left lane line as an example, if the left lane line of the current lane is present as output by the forward-view camera, and the mass of the left lane line of the current lane output by the forward-view camera is greater than a certain value q1 (e.g., 0.5), if the length of the left lane line of the current lane output by the forward-view camera is less than a certain value l1, and the curvature of the left lane line of the current lane output by the forward-view camera is equal to a certain value c1, then the lane where the target vehicle is located is determined to be a curve; if the length of the left lane line of the current lane output by the forward-view camera is greater than a certain value l1 but less than a certain value l2, and the mass ... q1 (e.g., 0.5), then the lane where the target vehicle is located is determined to be a curve. If the curvature of the left lane line is equal to a certain value c2, then the lane where the target vehicle is located is determined to be a curve; if the length of the left lane line output by the forward-view camera is greater than a certain value l2 and less than a certain value l3, and the curvature of the left lane line output by the forward-view camera is equal to a certain value c3, then the lane where the target vehicle is located is determined to be a curve; if the length of the left lane line output by the forward-view camera is greater than a certain value l3 and less than a certain value l4, and the curvature of the left lane line output by the forward-view camera is equal to a certain value c4, then the lane where the target vehicle is located is determined to be a curve.

[0128] The preset curvature corresponding to different lane lengths can be calibrated based on a large amount of historical data.

[0129] In this embodiment, low-quality lane lines have poor clarity, and the reliability of their length and curvature is also poor. When the lane line quality is high, combining the length and curvature of the lane lines can more accurately determine whether the target vehicle's lane is a curve. Based on this, removing stationary obstacles in the region of interest can effectively avoid interference from roadside stationary obstacles and ensure the accuracy of CIPV target recognition. In the curved scenario with low-quality lane lines, executing the subsequent logic to remove stationary obstacles in the region of interest within the curve may result in the mistaken removal of stationary obstacles in the vehicle's travel path, causing the target vehicle to fail to brake or decelerate in time, thus leading to a safety accident.

[0130] In some embodiments, obstacle data includes the sensor type corresponding to the obstacle, the obstacle type, the obstacle's motion state, and / or the obstacle's longitudinal velocity. Based on the obstacle data corresponding to the obstacle in front of the target vehicle, determining whether the obstacle is a target stationary obstacle includes: if the sensor type corresponding to the obstacle is a first sensor type, then determining whether the obstacle is a target stationary obstacle based on the obstacle type, the obstacle's motion state, and the obstacle's longitudinal velocity; if the sensor type corresponding to the obstacle is a second sensor type, then determining whether the obstacle is a target stationary obstacle based on the obstacle type and the obstacle's motion state.

[0131] The sensor type corresponding to the obstacle represents the type of sensor used to detect the obstacle.

[0132] Specifically, the sensor types corresponding to the obstacles are the first sensor type and the second sensor type.

[0133] For example, the first sensor type is a combination of multiple sensor types, including visual sensors and laser sensors, such as cameras and radar. The obstacle sensor type is the first sensor type indicating that the sensors detecting the obstacle include cameras and radar.

[0134] For example, the second sensor type is a single vision sensor, such as a camera, and the obstacle sensor type is a second sensor type that indicates that the sensor that detected the obstacle includes a camera.

[0135] Since single-vision sensors have poor accuracy in perceiving vehicle speed, and motion status is obtained by summarizing data from multiple aspects, when the sensor type corresponding to the obstacle is a camera, the longitudinal speed of the obstacle is not considered. Based on the obstacle type and motion status, it is possible to determine whether the obstacle is a stationary obstacle, which can better ensure the accuracy of the judgment.

[0136] Specifically, obstacle types include vehicles and non-vehicles.

[0137] When determining whether an obstacle is a stationary obstacle based on its type, motion state, and longitudinal velocity, the system first determines whether the obstacle is a vehicle. If the obstacle is a vehicle, it then determines whether it is a stationary obstacle based on its motion state and longitudinal velocity. If the obstacle is not a vehicle, it is determined that the obstacle is not a stationary obstacle.

[0138] When determining whether an obstacle is a target stationary obstacle based on its type and motion state, the system first determines whether the obstacle is a vehicle. If the obstacle is a vehicle, the system then determines whether it is a target stationary obstacle based on its motion state. If the obstacle is not a vehicle, the system determines that the obstacle is not a target stationary obstacle or ignores it.

[0139] Since CIPV targets the following targets when the target vehicle performs ACC function, non-vehicle obstacles generally cannot be used as following targets and will not be mistakenly identified as CIPV targets. Therefore, only vehicle obstacles are further judged, and non-vehicle obstacles are identified as non-target stationary obstacles or ignored. This can reduce unnecessary waste of resources and ensure that the target vehicle can smoothly navigate the corner.

[0140] Specifically, the motion state of an obstacle includes both stationary and non-stationary states.

[0141] When determining whether an obstacle is a target stationary obstacle based on its motion state and longitudinal velocity, if the obstacle's motion state is stationary, then the longitudinal velocity of the obstacle determines whether the obstacle is a target stationary obstacle. If the obstacle's motion state is not stationary, then the obstacle is determined not to be a target stationary obstacle.

[0142] Specifically, if the longitudinal velocity of an obstacle is greater than a preset longitudinal velocity threshold, the obstacle is determined to be a target stationary obstacle; if the longitudinal velocity of an obstacle is less than or equal to the preset longitudinal velocity threshold, the obstacle is determined to be a target stationary obstacle.

[0143] Since the motion state of the obstacle is determined by combining data from multiple sensors, and the longitudinal velocity of the obstacle corresponding to the first sensor type can be determined relatively accurately, based on these two factors, it is possible to accurately determine whether the obstacle is a stationary target obstacle, so as to accurately perform subsequent removal operations.

[0144] For example, if the fusion type (i.e., the sensor type mentioned above) corresponding to the obstacle in front of the vehicle is camera + radar, the obstacle type is a vehicle such as a truck or car, the obstacle's motion state is stationary, and the obstacle's longitudinal velocity v x Less than or equal to a certain value v limIf the condition is met, the obstacle is determined to be a stationary obstacle. Otherwise, the obstacle is not a stationary obstacle.

[0145] If the obstacle in front of the vehicle corresponds to a camera in the fusion type, the obstacle type is a vehicle such as a truck or car, and the obstacle's motion state is stationary, then the obstacle is determined to be a stationary obstacle. Otherwise, the obstacle is not a stationary obstacle.

[0146] In this embodiment, different data are used to determine whether an obstacle is a target obstacle based on different sensor types. That is, a method of using differentiated judgment logic based on different sensor types can be adopted to achieve hierarchical identification of stationary target obstacles that match the sensor capabilities, maximize the utilization value of perception information, ensure the accuracy of target stationary obstacle identification, and remove obstacles from the set of all obstacles that are candidates for the nearest vehicle target in the path. This effectively avoids mistakenly identifying roadside stationary obstacles as the nearest vehicle target in the path, reduces the occurrence of incorrect braking or deceleration, or even rear-end collisions, and ensures the driver's automated following experience.

[0147] It is understood that the term "self-vehicle" in this manual refers to the "target vehicle," for example, the speed of the self-vehicle is the speed of the target vehicle.

[0148] Furthermore, the judgment logic based on multiple conditions described in the embodiments of this application can evaluate each condition sequentially, in parallel, or in combination thereof during specific implementation. Any evaluation order or execution method that can realize the logical relationship described falls within the protection scope of this application.

[0149] For example, such as Figure 3 As shown, the process includes: The first step is to determine whether the driver assistance function is activated. If the driver assistance function is activated, proceed to the next step. If the driver assistance function is not activated, the process will end.

[0150] When the driver assistance functions are activated, the ACC (Adaptive Cruise Control) function is activated. If the lane keeping assist (LKA) function is activated, the vehicle is controlled to stay along the center line of the road through the lateral control function. If the LKA function is not activated, the driver controls the steering wheel to keep the vehicle along the center line of the road. The lateral control function is the core of the LKA function.

[0151] The second step is scene judgment, which involves determining whether the current scene is a curve scene based on whether there are lane lines on the road, combined with the steering wheel angle of the vehicle or road information.

[0152] Specifically, for roads with lane markings, the system determines whether the current scene is a curve based on road information obtained by recognizing images captured by the vehicle's forward-facing camera, including information such as road curvature, lane length, lane quality, and lane position. For roads without lane markings, the system determines whether the current scene is a curve based on the angle of the vehicle's steering wheel.

[0153] In addition, for roads without lane markings, if the road curvature is small and the steering wheel angle of the vehicle is within the corresponding turning angle threshold, it is impossible to determine whether the current scene is a curve scene. The system will directly enter the no-recognition judgment stage, that is, end the current process and use other target detection algorithms in the existing technology to identify the target vehicle.

[0154] The third step is obstacle detection, which involves using the vehicle's forward-facing camera and radar to comprehensively identify obstacles on the road edge and determine whether the obstacle is a stationary obstacle.

[0155] The fourth step is to determine the vehicle's status, which includes information such as vehicle speed, steering wheel angle, and whether the turn signals are on. The status of the turn signals can be replaced by the vehicle's yaw angle, which more accurately represents the vehicle's steering state. Alternatively, in addition to vehicle speed, steering wheel angle, and whether the turn signals are on, the vehicle status can also include the vehicle's yaw angle.

[0156] The fifth step is CIPV target selection, which involves dynamically adjusting the lateral distance threshold for CIPV target selection based on the vehicle's speed, determining the longitudinal distance threshold for CIPV target selection based on lane line information, and selecting a CIPV target based on the lateral and longitudinal distance thresholds.

[0157] Wherein, lateral distance refers to the absolute value of the lateral coordinate of the obstacle in the vehicle coordinate system, and longitudinal distance refers to the absolute value of the longitudinal coordinate of the obstacle in the vehicle coordinate system.

[0158] Specifically, lane line information includes lane line quality parameters. If the lane line quality is poor, such as no lane line being identified, a blurred lane line, or a short lane line, the longitudinal distance threshold is calibrated according to the principle of "nearer distance, larger distance" (or "farer distance, smaller distance"). For an explanation of the "nearer distance, larger distance" principle, please refer to the above content; it will not be repeated here.

[0159] Specifically, if, in a curve scenario, the position of a stationary obstacle in the vehicle coordinate system is within the range of the vehicle coordinate system corresponding to the calibrated lateral distance threshold and longitudinal distance threshold, then the stationary obstacle will not be selected as a CIPV target.

[0160] It is understandable that the second, third and fourth steps mentioned above can be performed in parallel for CIPV target selection in the fifth step.

[0161] Exemplary device like Figure 4 As shown in the figure, this application embodiment also provides a target rejection device, including a determination module 401, a judgment module 402 and a rejection module 403.

[0162] in, The determination module 401 is used to determine the region of interest located in front of the target vehicle in the lane where the target vehicle is located, based on the vehicle status data corresponding to the target vehicle. The judgment module 402 is used to determine whether the lane where the target vehicle is located is a curve based on the lane data corresponding to the lane where the target vehicle is located; and to determine whether the obstacle is a stationary obstacle and whether the obstacle is located within the region of interest based on the obstacle data corresponding to the obstacle in front of the target vehicle. The elimination module 403 is used to eliminate the obstacle from the target candidate set if the lane where the target vehicle is located is a curve, the obstacle is a stationary obstacle and is located in the region of interest, and the target candidate set is the set of all obstacles that are candidates for the nearest vehicle target in the path.

[0163] The target elimination device provided in this embodiment belongs to the same application concept as the target elimination method provided in the above embodiments of this application. It can execute the method provided in any of the above embodiments of this application and has the corresponding functional modules and beneficial effects of the method. Technical details not described in detail in this embodiment can be found in the specific processing content of the target elimination method provided in the above embodiments of this application, and will not be repeated here.

[0164] The functions implemented by the determination module 401, the judgment module 402, and the elimination module 403 can be implemented by the same or different processors calling software, and this application embodiment does not limit this.

[0165] Exemplary electronic devices Another embodiment of this application also provides an electronic device, see [link to relevant documentation] Figure 5 As shown, the electronic device includes a memory 500 and a processor 510.

[0166] The memory 500 is connected to the processor 510 and is used to store programs; The processor 510 is configured to implement the target elimination method disclosed in any of the above embodiments by running the program stored in the memory 500.

[0167] Specifically, the electronic device may also include: a bus, a communication interface 520, an input device 530, and an output device 540.

[0168] The processor 510, memory 500, communication interface 520, input device 530, and output device 540 are interconnected via a bus. Among them: A bus can include a pathway for transmitting information between various components of a computer system.

[0169] The processor 510 can be a general-purpose processor, such as a general-purpose central processing unit (CPU), a microprocessor, etc., or an application-specific integrated circuit (ASIC), or one or more integrated circuits used to control the execution of the program of the present application. It can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), an off-the-shelf programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0170] The processor 510 may include a main processor, as well as a baseband chip, modem, etc.

[0171] The memory 500 stores a program for executing the technical solution of this application, and may also store an operating system and other critical business functions. Specifically, the program may include program code, which includes computer operation instructions. More specifically, the memory 500 may include read-only memory (ROM), other types of static storage devices capable of storing static information and instructions, random access memory (RAM), other types of dynamic storage devices capable of storing information and instructions, disk storage, flash memory, etc.

[0172] Input device 530 may include a device for receiving user input data and information, such as a keyboard, mouse, camera, scanner, light pen, voice input device, touch screen, pedometer, or gravity sensor.

[0173] Output device 540 may include devices that allow information to be output to a user, such as a display screen, printer, speaker, etc.

[0174] The communication interface 520 may include a device that uses any transceiver to communicate with other devices or communication networks, such as Ethernet, Radio Access Network (RAN), Wireless Local Area Network (WLAN), etc.

[0175] The processor 510 executes the program stored in the memory 500 and calls other devices, which can be used to implement the various steps of any of the target elimination methods provided in the above embodiments of this application.

[0176] Those skilled in the art will understand that Figure 5The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the electronic device to which the present application is applied. The specific electronic device may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements.

[0177] This application also proposes a chip, which includes a processor and a data interface. The processor reads and runs a program stored in a memory through the data interface to execute the target elimination method described in any of the above embodiments. For details of the processing and its beneficial effects, please refer to the above embodiments of the target elimination method.

[0178] This application also provides a vehicle equipped with the aforementioned electronic equipment or target removal device.

[0179] In addition to the methods and apparatus described above, embodiments of this application provide a computer program product comprising computer program instructions that, when executed by a processor, cause the processor to perform the steps of the target elimination methods according to various embodiments of this application as described in the "Exemplary Methods" section of this specification.

[0180] The computer program product can be written in any combination of one or more programming languages ​​to perform the operations of the embodiments of this application. The programming languages ​​include object-oriented programming languages ​​such as Java and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0181] Furthermore, embodiments of this application also propose a storage medium storing a computer program that is executed by a processor in the target elimination methods according to various embodiments of this application described in the "Exemplary Methods" section above.

[0182] The basic principles of the present invention have been described above with reference to specific embodiments. However, it should be noted that the advantages, benefits, and effects mentioned in the present invention are merely examples and not limitations, and should not be considered as essential features of each embodiment of the present invention. Furthermore, the specific details disclosed above are for illustrative and facilitative purposes only, and are not limitations. These details do not limit the present invention to the necessity of employing the aforementioned specific details.

[0183] The block diagrams of devices, apparatuses, devices, and systems involved in this invention are merely illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As those skilled in the art will recognize, these devices, apparatuses, devices, and systems can be connected, arranged, and configured in any manner. Words such as “comprising,” “including,” “having,” etc., are open-ended terms meaning “including but not limited to,” and are used interchangeably with them. The terms “or” and “and” as used herein refer to the terms “and / or,” and are used interchangeably with them unless the context clearly indicates otherwise. The term “such as” as used herein refers to the phrase “such as but not limited to,” and is used interchangeably with it.

[0184] It should also be noted that in the apparatus, device, and method of the present invention, the components or steps can be disassembled and / or recombined. These disassemblies and / or recombinations should be considered as equivalent solutions of the present invention.

[0185] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the invention. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein can be applied to other aspects without departing from the scope of the invention. Therefore, the invention is not intended to be limited to the aspects shown herein, but rather to be carried out within the widest scope consistent with the principles and novel features disclosed herein.

[0186] It should be understood that the qualifying terms "first", "second", "third", "fourth", "fifth" and "sixth" used in the description of the embodiments of the present invention are only used to more clearly illustrate the technical solutions and are not intended to limit the scope of protection of the present invention.

[0187] The above description has been given for purposes of illustration and description. Furthermore, this description is not intended to limit the embodiments of the invention to the forms disclosed herein. Although numerous exemplary aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations therein.

Claims

1. A target elimination method, characterized in that, The method includes: Based on the vehicle status data corresponding to the target vehicle, determine the region of interest located in front of the target vehicle in the lane where the target vehicle is located; Based on the lane data corresponding to the lane where the target vehicle is located, determine whether the lane where the target vehicle is located is a curve; Based on the obstacle data corresponding to the obstacle in front of the target vehicle, it is determined whether the obstacle is a stationary obstacle and whether the obstacle is located within the region of interest; If the lane where the target vehicle is located is a curve, and the obstacle is a stationary obstacle located within the region of interest, then the obstacle is removed from the target candidate set, which is the set of all obstacles that are candidates for the nearest vehicle target within the path.

2. The target elimination method according to claim 1, characterized in that, The vehicle status data includes the vehicle's speed; determining the region of interest in front of the target vehicle within its lane, based on the target vehicle's status data, includes: Based on the vehicle speed and the correspondence between vehicle speed and the longitudinal length of the area, the target longitudinal length is determined; The target lateral length is determined based on the vehicle speed and the correspondence between the vehicle speed and the lateral length of the area; Based on the target's longitudinal length and lateral length, the region extending from the front of the vehicle towards the front of the vehicle, with its width gradually decreasing, is determined as the region of interest.

3. The target elimination method according to claim 2, characterized in that, The vehicle state data also includes vehicle steering parameters. After determining the region of interest as an area extending from the front of the vehicle towards the front and gradually decreasing in width, based on the target longitudinal length and the target lateral length, the method further includes: The target offset angle is determined based on the vehicle's steering parameters; The angle between the longitudinal centerline of the region of interest and the longitudinal direction of the target vehicle is adjusted to the target offset angle.

4. The target elimination method according to claim 1, characterized in that, The step of determining whether the lane where the target vehicle is located is a curve based on the lane data corresponding to the lane where the target vehicle is located includes: Based on the lane data corresponding to the lane where the target vehicle is located, determine whether there are lane lines in the lane where the target vehicle is located. If the lane where the target vehicle is located has lane markings, then based on the lane data, it is determined whether the lane where the target vehicle is located is a curve; If the lane where the target vehicle is located has no lane markings, then based on the vehicle's steering parameters, it is determined whether the lane where the target vehicle is located is a curve.

5. The target elimination method according to claim 4, characterized in that, The lane data includes the quality value, length, and / or curvature of the lane lines in the lane where the target vehicle is located. The quality value characterizes the clarity of the lane lines. The step of determining whether the lane where the target vehicle is located is a curve based on the lane data includes: Determine whether the mass value of the lane line in the lane where the target vehicle is located is greater than a preset mass threshold; If the mass value of the lane line in the lane where the target vehicle is located is greater than the preset mass threshold, then based on the preset length range in which the length of the lane line is located, and whether the curvature of the lane line is a preset curvature corresponding to the preset length range, it is determined whether the lane where the target vehicle is located is a curve.

6. The target elimination method according to claim 1, characterized in that, The obstacle data includes the sensor type corresponding to the obstacle, the obstacle type, the obstacle's motion state, and / or the obstacle's longitudinal velocity. The step of determining whether an obstacle is a stationary obstacle based on the obstacle data corresponding to the obstacle in front of the target vehicle includes: If the sensor type corresponding to the obstacle is the first sensor type, then based on the obstacle type, the motion state of the obstacle and the longitudinal velocity of the obstacle, it is determined whether the obstacle is a target stationary obstacle; If the sensor type corresponding to the obstacle is the second sensor type, then based on the obstacle type and the obstacle's motion state, it is determined whether the obstacle is a target stationary obstacle.

7. A target rejection device, characterized in that, The device includes: The determination module is used to determine the region of interest located in front of the target vehicle in the lane where the target vehicle is located, based on the vehicle status data corresponding to the target vehicle. The judgment module is used to determine whether the lane where the target vehicle is located is a curve based on the lane data corresponding to the lane where the target vehicle is located. The judgment module is further configured to determine whether the obstacle is a stationary obstacle and whether the obstacle is located within the region of interest, based on the obstacle data corresponding to the obstacle in front of the target vehicle. The elimination module is used to eliminate the obstacle from the target candidate set if the lane where the target vehicle is located is a curve, the obstacle is a stationary obstacle and is located in the region of interest, and the target candidate set is the set of all obstacles that are candidates for the nearest vehicle target in the path.

8. An electronic device, characterized in that, Including memory and processor; The memory is connected to the processor and is used to store programs; The processor is configured to implement the target elimination method as described in any one of claims 1 to 6 by running a program in the memory.

9. A storage medium, characterized in that, The storage medium stores a computer program, which, when executed by a processor, implements the target elimination method as described in any one of claims 1 to 6.

10. A vehicle, characterized in that, The vehicle is equipped with the target rejection device as described in claim 7 or the electronic device as described in claim 8.

Images