Lane-changing target prediction method, device, electronic device, and medium

Abstract

The embodiments of the present application disclose a lane-changing target prediction method, device, electronic device, and medium. The method includes: determining a widening distance based on the width of the current target, the width of the detection target, and the safety distance, widening along the center line of the trajectory of the current target based on the widening distance to obtain a first area and a second area with different widening distances; determining the relative position of the detection target and the first area or the second area based on the position of the detection target, and determining a candidate target based on the relative position; determining a lane-changing target from the candidate targets based on the distance of the candidate target from the current target along the center line of the trajectory. Through the technical solution of the embodiments of the present application, the detection target for lane change can be determined in advance, avoiding the current target braking with a large deceleration and the possible collision risk when the detection targets on both sides change lanes at a faster speed, thereby improving the comfort and safety of the system.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving technology, and in particular to a lane change target prediction method, device, electronic device, and medium. Background Art

[0002] Currently, the ODD (Design Operational Domain) of common commercial vehicle adaptive cruise control systems is generally not limited to highways, but also includes national highways and urban roads. Unlike highways, these roads often have unclear or even no lane markings, which greatly complicates the adaptive cruise control system's selection of target vehicles.

[0003] Although traditional commercial vehicle adaptive cruise control systems generally have the function of screening following vehicles in situations without lane lines, they give less consideration to vehicles on both sides of the vehicle that have the potential risk of cutting in when there are no lane lines. As a result, when vehicles on both sides cut in front of the vehicle at a high lateral speed, the adaptive cruise control system of the vehicle cannot identify them in advance, causing the vehicle to brake at a high deceleration, affecting the comfort of the adaptive cruise control system and even posing a collision risk. Summary of the Invention

[0004] The present application provides a lane-changing target prediction method, device, electronic device, and medium. By determining the detection target for lane change in advance, it avoids the current target braking with a large deceleration and the possible risk of collision when the detection targets on both sides change lanes at a relatively fast speed, thereby improving the comfort and safety of the system.

[0005] According to one aspect of the present application, a lane change target prediction method is provided, the method comprising:

[0006] Determine a widening distance according to the width of the current target, the width of the detected target, and the safety distance, and widen along the center line of the trajectory of the current target based on the widening distance to obtain a first area and a second area with different widening distances;

[0007] determining a relative position of the detection target and the first area or the second area according to the position of the detection target, and determining a candidate target according to the relative position;

[0008] A lane-changing target is determined from the candidate targets according to the distance between the candidate targets and the current target along the centerline of the trajectory.

[0009] According to another aspect of the present application, a lane change target prediction device is provided, the device comprising:

[0010] an area determination module, configured to determine a widening distance based on the width of the current target, the width of the detected target, and the safety distance, and to widen the area along the center line of the trajectory of the current target based on the widening distance to obtain a first area and a second area having different widening distances;

[0011] a candidate target determination module, configured to determine a relative position of the detection target and the first area or the second area according to the position of the detection target, and determine a candidate target according to the relative position;

[0012] The lane change target determination module is used to determine the lane change target from the candidate targets based on the distance between the candidate targets and the current target along the trajectory centerline.

[0013] According to another aspect of the present application, an electronic device is provided, the device comprising:

[0014] at least one processor; and

[0015] a memory communicatively connected to at least one processor; wherein,

[0016] The memory stores a computer program that can be executed by at least one processor, and the computer program is executed by at least one processor so that the at least one processor can execute the lane change target prediction method of any embodiment of the present application.

[0017] According to another aspect of the present application, a computer-readable storage medium is provided, which stores computer instructions, and the computer instructions are used to enable a processor to implement the lane change target prediction method of any embodiment of the present application when executed.

[0018] The technical solution of the embodiment of the present application determines the widening distance based on the width of the current target, the width of the detection target, and the safety distance, and widens along the center line of the trajectory of the current target based on the widening distance to obtain a first area and a second area with different widening distances. The area around the current target can be divided into different areas to indicate the possibility of the detection target changing lanes; the relative position of the detection target and the first area or the second area is determined based on the position of the detection target, and the candidate target is determined based on the relative position, so that the candidate target with a greater possibility of changing lanes can be determined; the lane changing target is determined from the candidate targets based on the distance of the candidate target from the current target along the center line of the trajectory. Through the technical solution of the embodiment of the present application, the detection target that is changing lanes can be determined in advance, avoiding the current target braking with a large deceleration and the possible collision risk when the detection targets on both sides change lanes at a faster speed, thereby improving the comfort and safety of the system.

[0019] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0021] Figure 1 is a flowchart of a lane change target prediction method provided according to Example 1 of the present application;

[0022] Figure 2 is a flow chart of a lane change target prediction method provided according to the second embodiment of the present application;

[0023] Figure 3 This is a schematic diagram of a first area and a second area provided according to the second embodiment of the present application;

[0024] Figure 4 This is a schematic diagram of the relative positions of the preceding vehicle and the vehicle when the center line of the trajectory is non-straight according to the second embodiment of the present application;

[0025] Figure 5 1 is a schematic structural diagram of a lane change target prediction device provided according to the third embodiment of the present application;

[0026] Figure 6 It is a structural diagram of an electronic device that implements a lane change target prediction method provided in Example 4 of the present application. DETAILED DESCRIPTION

[0027] In order to enable those skilled in the art to better understand the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of this application.

[0028] It should be noted that the terms "first", "second", "third", "fourth", "actual", "preset", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0029] Example 1

[0030] Figure 1 This is a flow chart of a lane change target prediction method provided in the first embodiment of the present application. The embodiment of the present application is applicable to the case of predicting vehicles cutting in from both sides. The method can be executed by a lane change target prediction device, which can be implemented in the form of hardware and / or software, and can be configured in an electronic device. Figure 1 As shown, the method includes:

[0031] S110 , determining a widening distance according to the width of the current target, the width of the detected target, and the safety distance, and widening along the center line of the trajectory of the current target based on the widening distance to obtain a first area and a second area with different widening distances.

[0032] The current target refers to the vehicle being driven by the driver, the detected target refers to vehicles that may cut in from either side of the current target, and the safe distance refers to the safe width between vehicles. The width of the current target is a known value, and the safe distance can be set based on the actual scenario. The method for obtaining the width of the detected target may vary, depending on the sensor and algorithm used, such as lidar, camera, ultrasonic sensor, etc. Alternatively, information pre-established in a vehicle database, such as vehicle model and size, can be used to obtain the width of the detected target.

[0033] In an embodiment of the present application, after obtaining the width of the current target, the width of the detection target, and the safety distance, the widening distance can be determined based on the width of the current target, the width of the detection target, and the safety distance. It is understandable that based on the consideration of early warning to prevent the reaction time from being too short, the safety distance can include two different safety widths, and two different widening distances can be determined. When widening along the center line of the trajectory of the current target based on the widening distance, a first area and a second area with different widening distances can be obtained. In this way, the area around the current target can be divided into different areas to indicate the possibility of the detection target changing lanes.

[0034] S120: Determine a relative position between the detection target and the first area or the second area according to the position of the detection target, and determine a candidate target according to the relative position.

[0035] Among them, the candidate target refers to the detection target that is more likely to change lanes.

[0036] In an embodiment of the present application, after obtaining the first area and the second area with different widening distances, the relative position of the detection target and the first area or the second area is determined according to the position of the detection target. Due to different safety widths, the first area and the second area are at different distances from the trajectory centerline of the current target. Specifically, the area close to the trajectory centerline of the current target is determined as the first area, and the area far from the trajectory centerline of the current target is determined as the second area. Then the relative position of the detection target and the first area or the second area includes: the detection target is located outside the first area and the second area, the detection target is located within the second area, and the detection target is located within the first area. It can be understood that the closer the detection target is to the trajectory centerline of the current target, the greater the possibility that the detection target will change lanes. Therefore, the candidate target can be determined based on the relative position of the detection target and the first area or the second area. In this way, the candidate target with a greater possibility of changing lanes can be determined.

[0037] S130 : Determine a lane-changing target from the candidate targets based on the distance between the candidate targets and the current target along the trajectory centerline.

[0038] The distance between the candidate target and the current target along the centerline of the trajectory is calculated based on the Frenet coordinate system. The Frenet coordinate system is a local characterization method for parameterized curves in three-dimensional space. It consists of a normal vector, a tangent vector, and a binormal vector, which together form an orthogonal coordinate system. The tangent vector gives the direction of the curve at that point, the normal vector gives the outward direction of the curve at that point, and the binormal vector is perpendicular to the first two vectors and defines the integrity of the coordinate system. The Frenet coordinate system can help solve some geometric and physical problems of curves.

[0039] In this embodiment of the present application, after determining the distance between a candidate target and the current target along the trajectory centerline based on the Frenet coordinate system, a lane-changing target can be identified from the candidate targets based on this distance. Optionally, if the distance between a candidate target and the current target along the trajectory centerline is less than a preset threshold, the candidate target is identified as a lane-changing target. This allows for the early identification of detected targets for lane changes and for appropriate responses.

[0040] The technical solution of the embodiment of the present application determines the widening distance based on the width of the current target, the width of the detection target, and the safety distance, and widens along the center line of the trajectory of the current target based on the widening distance to obtain a first area and a second area with different widening distances. The area around the current target can be divided into different areas to indicate the possibility of the detection target changing lanes; the relative position of the detection target and the first area or the second area is determined based on the position of the detection target, and the candidate target is determined based on the relative position, so that the detection target with a greater possibility of changing lanes can be determined; the lane-changing target is determined from the candidate targets based on the distance of the candidate target from the current target along the center line of the trajectory. Through the technical solution of the embodiment of the present application, the detection target that is changing lanes can be determined in advance, avoiding the current target braking with a large deceleration and the possible collision risk when the detection targets on both sides change lanes at a faster speed, thereby improving the comfort and safety of the system.

[0041] Example 2

[0042] Figure 2 This is a flow chart of a lane change target prediction method provided in the second embodiment of the present application. The present embodiment is optimized based on the above embodiment. For solutions not fully described in the present embodiment, please refer to the above embodiment. Figure 2 As shown, the method of the embodiment of the present application specifically includes the following steps:

[0043] S210 , determining a widening distance according to the width of the current target, the width of the detected target, and the safety distance, and widening along the center line of the trajectory of the current target based on the widening distance to obtain a first area and a second area with different widening distances.

[0044] In an embodiment of the present application, after determining the widening distance based on the width of the current target, the width of the detected target and the safety distance, widening can be performed along the center line of the trajectory of the current target based on the widening distance to obtain a first area and a second area with different widening distances.

[0045] Specifically, widening is performed along the center line of the trajectory of the current target based on the widening distance to obtain a first area and a second area with different widening distances, including:

[0046] Determine the safe movement length along the center line of the current target trajectory based on the current target's movement speed and load;

[0047] Within the safe motion length range, widening is performed along the center line of the trajectory of the current target based on the widening distance to obtain a first area and a second area with different widening distances.

[0048] It is understandable that the comfort and safety of the current target will only be affected when the detection target changes lanes from both sides within the preset distance of the current target. Changing lanes from both sides outside the preset distance of the current target will have no effect on the current target. Therefore, before widening along the center line of the trajectory of the current target based on the widening distance, it is necessary to determine the preset distance of the widened area in the direction of the center line of the trajectory of the current target. The preset distance is the safe movement length of the current target along the center line of the current target trajectory. The safe movement length of the current target along the center line of the current target trajectory is determined by the movement speed and load of the current target. The greater the movement speed and load, the greater the inertia of the current target, and the greater the safe movement length required.

[0049] Specifically, based on the current target's movement speed and load, the safe movement length along the centerline of the current target trajectory is determined, including:

[0050] If the current target's movement speed and / or load is zero, the safe movement length is determined to be a preset constant value;

[0051] If the load and movement speed of the current target are both non-zero, it is determined that the safe movement length is positively correlated with the movement speed and load, respectively.

[0052] In the embodiment of the present application, when determining the safe motion length along the centerline of the current target trajectory based on the current target's motion speed and load, two situations can be considered: when the motion speed and / or load is zero, and when both the current target's load and motion speed are non-zero. If the current target's motion speed and / or load is zero, the safe motion length is a preset constant value, which can be set based on actual conditions. If both the current target's load and motion speed are non-zero, when one value is fixed, the safe motion length is positively correlated with the other.

[0053] For example, Table 1 below shows the relationship between the safe movement length and the current target's movement speed and load. As shown in Table 1, when the movement speed and / or load are zero, the safe movement length is a preset constant value of 40. However, when both the load and the movement speed are non-zero, and one value is fixed, the safe movement length is positively correlated with the other. For example, when the load is 10 tons, the safe movement length increases with increasing movement speed. Other situations not listed in the table can be handled accordingly using the principle of linear interpolation.

[0054] Table 1 Relationship between safe movement length and current target movement speed and load

[0055]

[0056] After determining the safe movement length along the centerline of the current target trajectory, the widening distance can be applied along the centerline of the current target trajectory within the safe movement length, resulting in a first region and a second region with different widening distances. The different widening distances are caused by different safe widths, and are designed to provide early warning to prevent premature reaction times.

[0057] Specifically, within the safe motion length range, widening is performed along the center line of the current target's trajectory based on the widening distance to obtain a first area and a second area with different widening distances, including:

[0058] The width of the current target is used as the widening distance of the safe motion length range from the farthest end of the current target. The sum of the width of the current target, the width of the detection target, and the first safe width is used as the widening distance of the safe motion length range from the nearest end of the current target. The first area is widened along the center line of the current target's trajectory;

[0059] The width of the current target is used as the widening distance of the safe motion length range from the farthest end of the current target, and the sum of the width of the current target, the width of the detected target and the second safe width is used as the widening distance of the safe motion length range from the nearest end of the current target. The widening is performed along the center line of the trajectory of the current target to obtain the widened area, and the first area is removed from the widened area to obtain the second area; wherein, the first safe width is smaller than the second safe width.

[0060] In the embodiment of the present application, when the first area is obtained by widening along the center line of the current target's trajectory, a pentagonal area is obtained, and the center line of the current target's trajectory passes through the vertex at the bottom of the pentagonal area and is perpendicular to the edge at the top of the pentagonal area, and the pentagonal area is symmetrical about the center line of the current target's trajectory. It can be understood that the length of the edge at the top of the pentagonal area is the width of the current target, the distance between the two vertices symmetrical about the center line of the current target's trajectory below is the sum of the width of the current target, the width of the detected target, and the first safe width, the distance from the bottom vertex to the top edge is the safe motion length, and the angle between the two edges symmetrical about the center line of the current target's trajectory below represents the maximum sensing range of the sensor.

[0061] Similarly, when widening the widened area along the centerline of the current target's trajectory, the resulting area is also a pentagonal area. However, the distance between the two vertices of the pentagon below the widened area, which are symmetrical about the current target's trajectory centerline, is equal to the sum of the current target's width, the width of the detected target, and the second safety width. If the first safety width is smaller than the second safety width, the widened area is a larger pentagonal area that contains the pentagonal area of ​​the first area. After removing the first area from the larger pentagonal area, the second area is obtained.

[0062] For example, Figure 3 A schematic diagram of the first and second regions is shown. As shown in the figure, the width of the current target is D, the safe motion length is L, the width of the detected target is D0, the first safe width is d1, and the second safe width is d2. The sum of the width of the current target, the width of the detected target, and the first safe width is D1 = D + D0 + d1, and the sum of the width of the current target, the width of the detected target, and the second safe width is D2 = D + D0 + d2. If d2 is greater than d1, then D2 is greater than D1. The small pentagonal region in the figure is the first region, and the large pentagonal region is the widened region. The remaining area in the widened region excluding the first region is the second region.

[0063] S220: If the detection target is determined to be located in the first area according to the position of the detection target, the detection target is determined to be a candidate target.

[0064] In an embodiment of the present application, if the detection target is determined to be located in the first area based on the position of the detection target, it means that the detection target is very close to the center line of the trajectory of the current target. Optionally, the detection target can be directly determined as a candidate target. However, in actual driving scenarios, due to the influence of various factors, it is not ruled out that the detection target only accidentally enters the first area of ​​the current target. Therefore, a preset time threshold for the detection target to enter the first area of ​​the current target can be set in advance. When the time for the detection target to enter the first area of ​​the current target exceeds the preset time threshold, the detection target is determined to be a candidate target. In this way, accidental factors can be eliminated and the accuracy of candidate target determination can be increased.

[0065] Exemplarily, a preset time threshold T1 is set for the detection target to enter the first area of ​​the current target. When the time t1 of the detection target entering the first area of ​​the current target is greater than T1, the detection target is determined to be a candidate target.

[0066] S230: If it is determined that the detection target is located in the second area according to the position of the detection target, determine whether the detection target is a candidate target according to the relative position of the detection target and the first area.

[0067] In an embodiment of the present application, if the detection target is determined to be within the second area based on the position of the detection target, it means that the detection target is not very close to the center line of the trajectory of the current target. At this time, it can be determined whether the detection target is a candidate target based on the relative position of the detection target and the first area.

[0068] Specifically, determining whether the detected target is a candidate target according to the relative position of the detected target and the first area includes:

[0069] Determining a probability of the detection target being cut into based on a relative distance between the detection target and an edge of the first region; wherein the cut-in probability is inversely proportional to the relative distance, and the edge of the first region is an edge on the same side of the trajectory centerline as the detection target;

[0070] determining a probability change rate according to a cut-in probability determined by relative distances between the detection target and the edge of the first area detected at different times;

[0071] If the probability change rate is greater than the preset change rate threshold and the duration is greater than the preset duration, the detected target is determined to be a candidate target.

[0072] In an embodiment of the present application, the probability of the detection target being cut in can be determined based on the relative distance between the detection target and the edge of the first area, where the edge of the first area and the detection target are located on the same side of the center line of the trajectory, such as on the left. It can be understood that the smaller the relative distance, the greater the probability of the detection target being cut in, that is, the probability of cutting in is inversely proportional to the relative distance. Furthermore, the relative distance between the detection target and the edge of the first area can be continuously obtained within a certain period of time, and the probability of the detection target being cut in can be determined, and the probability of cutting in during this period can be derived to obtain the probability change rate. Optionally, when the probability change rate is greater than a preset change rate threshold, the detection target is determined to be a candidate target. Similarly, based on the consideration of excluding accidental factors, the detection target can be determined to be a candidate target when the probability change rate is greater than the preset change rate threshold for a duration greater than a preset duration.

[0073] The process of determining the relative position of the detection target and the first area includes:

[0074] If the trajectory centerline is a straight line, determine the lateral deviation distance of the detection target from the trajectory centerline and the edge distance of the first edge point of the first area from the trajectory centerline based on the position of the detection target, and determine the relative position based on the lateral deviation distance and the edge distance; wherein the first edge point is an edge point among the edge points of the first area that is at a preset distance from the current target and is located on the same side of the trajectory centerline as the detection target; the preset distance is the component of the distance between the detection target and the current target along the trajectory centerline direction;

[0075] If the trajectory centerline is non-straight, the lateral deviation distance of the detection target from the trajectory centerline and the edge distance of the second edge point of the first area from the trajectory centerline are determined according to the position of the detection target and the trajectory equation of the trajectory centerline, and the relative position is determined according to the lateral deviation distance and the edge distance; wherein the second edge point is the intersection of the reference straight line and the edge of the first area, which is on the same side of the trajectory centerline as the detection target, and the reference straight line is a straight line passing through the detection target and perpendicular to the trajectory centerline.

[0076] In the actual driving process, there are various road conditions including straight roads and other than straight roads. Therefore, when determining the relative position of the detection target and the first area, it is necessary to determine it according to whether the center line of the trajectory of the current target is a straight line or not. In an embodiment of the present application, the center line of the trajectory of the current target is judged to be a straight line or a non-straight line based on the yaw angular velocity of the current target and whether the driver turns the steering wheel. For example, when the driver does not turn the steering wheel and the yaw angular velocity of the current target exceeds the set curve threshold and lasts for a certain time, the center line of the trajectory is judged to be a non-straight line. When the driver does not turn the steering wheel and the yaw angular velocity of the current target is less than the set curve threshold and lasts for a certain time, the center line of the trajectory is judged to be a straight line. The curve threshold can be obtained by actual vehicle calibration. Because there is a case where the center line of the trajectory is non-straight line, the Frenet coordinate system is introduced here for the convenience of calculation.

[0077] When the center line of the trajectory is a straight line, the relative horizontal and vertical distances between the detection target and the current target can be obtained by the sensor of the current target, wherein the relative horizontal distance between the detection target and the current target is the lateral distance between the detection target and the center line of the trajectory. The first edge point and the detection target are located on the same side of the center line of the trajectory, and its relative longitudinal distance to the current target is a preset distance. The preset distance is the component of the distance between the detection target and the current target along the direction of the center line of the trajectory, that is, the relative longitudinal distance between the detection target and the current target. The edge distance of the first edge point from the center line of the trajectory can be calculated from the preset distance. After obtaining the lateral distance and the edge distance, the relative position can be determined based on the lateral distance and the edge distance. Optionally, the lateral distance and the edge distance can be subtracted to obtain the relative distance between the detection target and the edge of the first area.

[0078] When the trajectory centerline is a non-straight line, the relative horizontal and vertical distances between the detection target and the current target can also be obtained by the sensor of the current target. However, in this case, the trajectory equation of the trajectory centerline needs to be determined first, and then the lateral distance of the detection target from the trajectory centerline is determined based on the position of the detection target and the trajectory equation of the trajectory centerline. The second edge point and the detection target are located on the same side of the trajectory centerline. It is the intersection of the reference straight line passing through the detection target and perpendicular to the trajectory centerline and the edge of the first area. When calculating the edge distance between the second edge point of the first area and the trajectory centerline, the trajectory equation of the trajectory centerline can be converted into the Frenet coordinate system. At this time, the trajectory centerline becomes a straight line. The edge distance between the second edge point and the trajectory centerline can be calculated based on the calculation method of the edge distance between the first edge point and the trajectory centerline, and the relative position can be determined based on the lateral distance and the edge distance.

[0079] For example, when the trajectory centerline is a straight line, as Figure 3 As shown, the relative horizontal and vertical distances between the detection target and the current target are obtained based on the sensor of the current target. The relative horizontal distance is the lateral distance between the detection target and the center line of the trajectory. L1 is calculated by combining the sensor's perception range angle with D1. Through the principle of similar triangles, the edge distance from the first edge point of the first area to the center line of the trajectory can be calculated based on the relative longitudinal distance between the detection target and the current target, D1 and L1. The absolute value of the difference between the edge distance and the lateral distance is the relative distance between the detection target and the edge of the first area. The smaller the relative distance, the greater the probability ρ of the detection target point to cut in, and vice versa. The value range of ρ is 0% to 100%. At the same time, at a certain time T ρ1 Derivative of ρ is obtained to obtain the change rate of the cut-in probability ρ'. When ρ' is greater than the preset change rate threshold ρ0 and the duration t ρ1 >T ρ1 , the detected target is determined to be a candidate target.

[0080] For example, when the trajectory centerline is non-straight, the yaw angular velocity of the current target can be used to predict the current target's driving trajectory. First, the yaw angular velocity ω of the current target is Kalman filtered, and then the current turning radius R is calculated according to the current target's motion speed V: R = V / ω, thereby obtaining the current curve curvature K: K = 1 / R, and then the curvature K is derived to obtain the curvature change rate K'. Finally, the current target's driving trajectory is fitted to obtain the trajectory centerline equation of the current target: f(x) = KX 2 +K'X 3 .

[0081] Figure 4The diagram shows the relative positions of the preceding vehicle and the vehicle when the trajectory centerline is non-straight. The preceding vehicle is the detection target, and the vehicle is the current target. After obtaining the trajectory centerline equation of the current target, the lateral deviation distance of the detection target from the trajectory centerline can be calculated. First, the trajectory centerline equation of the current target is differentiated to calculate the slope equation of the trajectory centerline of the current target: f′(x)=2KX+3K'X 2 .like Figure 4 As shown in the figure, BD is the lateral deviation distance of the target vehicle. The thicker dotted line in the figure is the center line of the current target trajectory. From the relationship in the figure, we can know that the lateral deviation distance solution expression is: BD = (AB–AC) cosβ, where AB is the lateral relative distance between the detected target and the current target, AC can be obtained from the trajectory equation of the current target trajectory centerline: AC = f(OA), and the angle β is the intersection of the tangent of the trajectory centerline at point D and the horizontal axis. According to the figure, we can see that point D and point C are close, so the tangent angle of point C can be used to replace the tangent angle β of point D. The horizontal coordinate of point C is the relative longitudinal distance OA between the detected target and the current target, so it can be obtained according to the slope equation of the vehicle trajectory centerline: tanβ = f′(OA). In this way, the lateral deviation distance of the detection target from the center line of the trajectory can be calculated. Afterwards, the trajectory equation of the center line of the trajectory can be converted into the Frenet coordinate system. At this time, the center line of the trajectory becomes a straight line. The edge distance of the second edge point from the center line of the trajectory is calculated according to the edge distance calculation method of the first edge point from the center line of the trajectory, and the relative position is determined according to the lateral deviation distance and the edge distance. The smaller the relative distance, the greater the probability ρ of the detection target point, and vice versa. The value range of ρ is 0% to 100%. At the same time, at a certain time T ρ1 Derivative of ρ is obtained to obtain the change rate of the cut-in probability ρ'. When ρ' is greater than the preset change rate threshold ρ0 and the duration t ρ1 >T ρ1 , the detected target is determined to be a candidate target.

[0082] S240: Select the candidate target with the shortest distance from the current target along the center line of the trajectory as the lane change target.

[0083] In this embodiment of the present application, after determining the distance between the candidate target and the current target along the trajectory centerline based on the Frenet coordinate system, the lane change target can be determined from the candidate targets based on the distance between the candidate target and the current target along the trajectory centerline. Specifically, the candidate target with the smallest distance from the current target along the trajectory centerline is selected as the lane change target. This allows the detection target to be identified in advance and appropriate response can be implemented.

[0084] The technical solution of the embodiment of the present application determines the widening distance based on the width of the current target, the width of the detection target, and the safety distance. Based on the widening distance, the current target is widened along the center line of the trajectory to obtain a first area and a second area with different widening distances. The area around the current target can be divided into different areas to indicate the possibility of the detection target changing lanes. If the detection target is determined to be within the first area based on the position of the detection target, the detection target is determined to be a candidate target, and the detection target with a high possibility of changing lanes can be determined. If the detection target is determined to be within the second area based on the position of the detection target, whether the detection target is a candidate target is determined based on the relative position of the detection target and the first area. The candidate target with the smallest distance from the current target along the center line of the trajectory is used as the lane changing target. Through the technical solution of the embodiment of the present application, the detection target that is changing lanes can be determined in advance to avoid the current target braking with a large deceleration and the possible collision risk when the detection targets on both sides change lanes at a faster speed, thereby improving the comfort and safety of the system.

[0085] Example 3

[0086] Figure 5 This is a schematic diagram of the structure of a lane change target prediction device provided in the third embodiment of the present application. The device can execute the lane change target prediction method provided in any embodiment of the present application and has the corresponding functional modules and beneficial effects of the execution method. Figure 5 As shown, the device includes:

[0087] An area determination module 310 is configured to determine a widening distance based on the width of the current target, the width of the detected target, and the safety distance, and to widen the area along the center line of the trajectory of the current target based on the widening distance to obtain a first area and a second area having different widening distances;

[0088] a candidate target determination module 320, configured to determine a relative position between the detection target and the first area or the second area according to the position of the detection target, and determine a candidate target according to the relative position;

[0089] The lane change target determination module 330 is configured to determine a lane change target from the candidate targets based on the distance between the candidate targets and the current target along the centerline of the trajectory.

[0090] In the embodiment of the present application, the region determination module 310 includes:

[0091] A safe motion length determination unit, configured to determine a safe motion length along the center line of the current target trajectory according to the current target's motion speed and load;

[0092] The area determination unit is used to widen the trajectory center line of the current target based on the widening distance within the safe movement length range to obtain a first area and a second area with different widening distances.

[0093] Optionally, the safety movement length determination unit includes:

[0094] a first safety movement length determination subunit, configured to determine the safety movement length to be a preset constant value if the movement speed and / or load of the current target is zero;

[0095] The second safe movement length determination subunit is used to determine that the safe movement length is positively correlated with the movement speed and the load respectively if the load and movement speed of the current target are not zero.

[0096] Optionally, the region determination unit includes:

[0097] A first region determination subunit is configured to use the width of the current target as the widening distance of the safe motion length range from the farthest end of the current target, and use the sum of the width of the current target, the width of the detection target, and the first safe width as the widening distance of the safe motion length range from the nearest end of the current target, and widen the range along the center line of the trajectory of the current target to obtain a first region;

[0098] The second area determination subunit is used to take the width of the current target as the widening distance of the safe movement length range from the farthest end of the current target, and take the sum of the width of the current target, the width of the detection target and the second safe width as the widening distance of the safe movement length range from the nearest end of the current target, widen along the center line of the trajectory of the current target to obtain a widened area, and remove the first area from the widened area to obtain a second area; wherein the first safe width is smaller than the second safe width.

[0099] In the embodiment of the present application, the candidate target determination module 320 includes:

[0100] a first region candidate target determining unit, configured to determine the detection target as a candidate target if it is determined based on the position of the detection target that the detection target is located within the first region;

[0101] The second area candidate target determining unit is configured to determine whether the detection target is a candidate target based on a relative position between the detection target and the first area if the detection target is determined to be located in the second area based on the position of the detection target.

[0102] Optionally, the second area candidate target determination unit includes:

[0103] a cut-in probability determination subunit, configured to determine a cut-in probability of the detection target based on a relative distance between the detection target and an edge of the first area; wherein the cut-in probability is inversely proportional to the relative distance, and the edge of the first area is an edge located on the same side of the trajectory centerline as the detection target;

[0104] a probability change rate determining subunit, configured to determine a probability change rate according to a cut-in probability determined by a relative distance between a detection target detected at different times and an edge of the first area;

[0105] The candidate target determination subunit is used to determine that the detected target is a candidate target if the probability change rate is greater than a preset change rate threshold and the duration is greater than a preset duration.

[0106] Optionally, the second area candidate target determination unit includes:

[0107] a first relative position determination subunit for determining, if the trajectory centerline is a straight line, a lateral deviation distance of the detection target from the trajectory centerline and an edge distance of a first edge point of the first area from the trajectory centerline based on the position of the detection target, and determining the relative position based on the lateral deviation distance and the edge distance; wherein the first edge point is an edge point among the edge points of the first area that is at a preset distance from the current target and is located on the same side of the trajectory centerline as the detection target; and the preset distance is a component of the distance between the detection target and the current target along the trajectory centerline;

[0108] The second relative position determination subunit is used to determine the lateral deviation distance of the detection target from the trajectory centerline and the edge distance of the second edge point of the first area from the trajectory centerline based on the position of the detection target and the trajectory equation of the trajectory centerline if the trajectory centerline is non-straight, and determine the relative position based on the lateral deviation distance and the edge distance; wherein the second edge point is the intersection of the reference straight line and the edge of the first area, which is on the same side of the trajectory centerline as the detection target, and the reference straight line is a straight line passing through the detection target and perpendicular to the trajectory centerline.

[0109] In the embodiment of the present application, the lane change target determination module 330 includes:

[0110] The lane-changing target determining unit is configured to select the candidate target with the smallest distance from the current target along the center line of the trajectory as the lane-changing target.

[0111] A lane change target prediction device provided in an embodiment of the present application can execute a lane change target prediction method provided in any embodiment of the present application, and has functional modules and beneficial effects corresponding to the execution method.

[0112] Example 4

[0113] Figure 6 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present application is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present application described and / or required herein.

[0114] like Figure 6 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., which is communicatively connected to the at least one processor 11. The memory stores a computer program that can be executed by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. Various programs and data required for the operation of the electronic device 10 can also be stored in the RAM 13. The processor 11, ROM 12, and RAM 13 are connected to each other via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0115] Multiple components in the electronic device 10 are connected to the I / O interface 15, including an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0116] The processor 11 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any other suitable processor, controller, or microcontroller. The processor 11 executes the various methods and processes described above, such as the lane change target prediction method.

[0117] In some embodiments, the lane change target prediction method may be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the lane change target prediction method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to execute the lane change target prediction method in any other suitable manner (e.g., via firmware).

[0118] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0119] Computer programs for implementing the methods of the present application can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable lane change target prediction device, such that, when executed by the processor, the computer programs implement the functions / operations specified in the flowcharts and / or block diagrams. The computer programs can be executed entirely on the machine, partially on the machine, as a standalone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0120] In the context of the present application, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. A computer-readable storage medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. A more specific example of a machine-readable storage medium can include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0121] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0122] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0123] A computing system may include clients and servers. The clients and servers are typically remote from each other and typically interact via a communication network. This client-server relationship arises through computer programs running on the respective computers, creating a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host. This server is a hosting product within the cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosting and VPS services.

[0124] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this application can be performed in parallel, sequentially, or in a different order, as long as the desired information of the technical solution of this application can be achieved. This document is not limited here.

[0125] The above specific embodiments do not constitute a limitation on the scope of protection of this application. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application shall be included within the scope of protection of this application.

Claims

1. A lane change target prediction method, characterized in that: The method comprises: Determine a widening distance according to the width of the current target, the width of the detected target, and the safety distance, and widen along the center line of the trajectory of the current target based on the widening distance to obtain a first area and a second area with different widening distances; determining a relative position of the detection target and the first area or the second area according to the position of the detection target, and determining a candidate target according to the relative position; A lane-changing target is determined from the candidate targets based on the distance between the candidate targets and the current target along the centerline of the trajectory.

2. The method according to claim 1, characterized in that Based on the widening distance, widening is performed along the center line of the current target trajectory to obtain a first area and a second area with different widening distances, including: Determine the safe movement length along the center line of the current target trajectory based on the current target's movement speed and load; Within the safe motion length range, widening is performed along the center line of the trajectory of the current target based on the widening distance to obtain a first area and a second area with different widening distances.

3. The method according to claim 2, characterized in that Based on the current target's speed and load, determine the safe movement length along the centerline of the current target trajectory, including: If the current target's movement speed and / or load is zero, the safe movement length is determined to be a preset constant value; If the load and movement speed of the current target are both non-zero, it is determined that the safe movement length is positively correlated with the movement speed and load, respectively.

4. The method according to claim 2, characterized in that Within the safe motion length range, widening is performed along the center line of the current target trajectory based on the widening distance, resulting in a first area and a second area with different widening distances, including: Using the width of the current target as the widening distance of the safe motion length range from the farthest end of the current target, and using the sum of the width of the current target, the width of the detection target, and the first safe width as the widening distance of the safe motion length range from the nearest end of the current target, widening is performed along the center line of the trajectory of the current target to obtain a first area; The width of the current target is used as the widening distance of the safe movement length range from the farthest end of the current target, and the sum of the width of the current target, the width of the detection target and the second safe width is used as the widening distance of the safe movement length range from the nearest end of the current target. The widening is performed along the center line of the trajectory of the current target to obtain a widened area, and the first area is removed from the widened area to obtain a second area; wherein the first safe width is smaller than the second safe width.

5. The method according to claim 1, characterized in that Determining a relative position of the detection target and the first area or the second area according to the position of the detection target, and determining a candidate target according to the relative position, including: If it is determined according to the position of the detection target that the detection target is located in the first area, then determining the detection target as a candidate target; If it is determined that the detection target is located in the second area according to the position of the detection target, whether the detection target is a candidate target is determined according to the relative position of the detection target and the first area.

6. The method according to claim 5, characterized in that Determining whether the detected target is a candidate target according to a relative position between the detected target and the first area includes: Determining a penetration probability of the detection target based on a relative distance between the detection target and an edge of the first area; wherein the penetration probability is inversely proportional to the relative distance, and the edge of the first area is an edge located on the same side of the trajectory centerline as the detection target; determining a probability change rate according to a penetration probability determined by relative distances between a detection target and an edge of the first area detected at different times; If the probability change rate is greater than the preset change rate threshold and the duration is greater than the preset duration, the detected target is determined to be a candidate target.

7. The method according to claim 5, characterized in that The process of determining the relative position of the detection target and the first area includes: If the trajectory centerline is a straight line, determine the lateral deviation distance of the detection target from the trajectory centerline and the edge distance of the first edge point of the first area from the trajectory centerline based on the position of the detection target, and determine the relative position based on the lateral deviation distance and the edge distance; wherein the first edge point is an edge point among the edge points of the first area that is at a preset distance from the current target and is located on the same side of the trajectory centerline as the detection target; the preset distance is the component of the distance between the detection target and the current target along the trajectory centerline direction; If the trajectory centerline is a non-straight line, the lateral deviation distance of the detection target from the trajectory centerline and the edge distance of the second edge point of the first area from the trajectory centerline are determined based on the position of the detection target and the trajectory equation of the trajectory centerline, and the relative position is determined based on the lateral deviation distance and the edge distance; wherein the second edge point is the intersection of the reference straight line and the edge of the first area, which is on the same side of the trajectory centerline as the detection target, and the reference straight line is a straight line passing through the detection target and perpendicular to the trajectory centerline.

8. The method according to claim 1, characterized in that Determining a lane change target from the candidate targets based on a distance between the candidate targets and the current target along a trajectory centerline includes: The candidate target with the smallest distance from the current target along the center line of the trajectory is used as the lane change target.

9. A lane change target prediction device, characterized in that: include: an area determination module, configured to determine a widening distance based on the width of the current target, the width of the detected target, and the safety distance, and to widen the area along the center line of the trajectory of the current target based on the widening distance to obtain a first area and a second area having different widening distances; a candidate target determination module, configured to determine a relative position of the detection target and the first area or the second area according to the position of the detection target, and determine a candidate target according to the relative position; The lane change target determination module is used to determine the lane change target from the candidate targets based on the distance between the candidate targets and the current target along the trajectory centerline.

10. An electronic device, characterized in that: The device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so as to enable the at least one processor to execute the lane change target prediction method according to any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the lane change target prediction method according to any one of claims 1 to 8 when executed.

Images