Course angle determination method and device, equipment, medium and product

Abstract

The invention discloses a course angle determination method, device and equipment, a medium and a product, and the method comprises the steps: obtaining the radar information and the driving information of a current vehicle, and determining the current track information based on the radar information and the driving information; determining a first course angle based on the driving information, the current track information and a historical course angle; if the moving target is located on the opposite lane of the current vehicle, determining the lane distance between the current vehicle and the opposite lane, and determining a second course angle based on the lane distance, the historical track of the current vehicle and the driving information; if the current vehicle and the moving target meet the corresponding walking and parking monitoring conditions, determining a third course angle according to the historical track and the driving information of the current vehicle; determining a fourth course angle based on the driving information, the radar information and the current track information; and determining a target course angle from the first course angle, the second course angle, the third course angle and the fourth course angle. According to the technical scheme, accurate calculation of course angles in various scenes is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicles, and in particular, to a method, device, equipment, medium and product for determining a heading angle. Background Art

[0002] The recognition of the dynamic target heading angle is crucial for autonomous driving technology, which can be used to judge the threat level of the target vehicle to the host vehicle, and then issue an early warning or control the vehicle to take emergency evasive action. For a millimeter-wave radar, if the heading angle of the target is calculated inaccurately, it will lead to abnormal radar alarm functions and even affect the accuracy of target tracking, resulting in abnormal multi-sensor fusion results. In addition, compared with lidar, the millimeter-wave radar has insufficient angular resolution and range resolution, and the single-frame detected target point cloud is less, which is not enough to fit the target heading angle through the point cloud shape.

[0003] Currently, the industry usually first judges the driving state of the host vehicle. When the host vehicle is in a high-speed driving state, the heading angle is calculated according to the speed information in the point cloud data; when the host vehicle is not in a high-speed driving state, the historical displacement information in the point cloud data is used to calculate the heading angle, which solves the problem of inaccurate heading angle calculation by a single method. This method can obtain a relatively accurate target heading angle result for normal driving scenarios. However, once the vehicle is in a special driving scenario, the heading angle calculated based on speed or historical displacement still has a large gap with the actual value, and it is still difficult to achieve accurate calculation of the heading angle. Summary of the Invention

[0004] The present invention provides a method, device, equipment, medium and product for determining a heading angle, which realizes accurate calculation of the heading angle in multiple scenarios.

[0005] In a first aspect, an embodiment of the present disclosure provides a method for determining a heading angle, including:

[0006] Obtain the radar information and driving information of the current vehicle, and determine the current track information based on the radar information and the driving information;

[0007] Determine a first heading angle of the moving target relative to the current vehicle based on the driving information, the current track information and the historical heading angle;

[0008] If the moving target is located in the oncoming lane of the current vehicle, determine the lane distance between the current vehicle and the oncoming lane, and determine a second heading angle based on the lane distance, the historical track of the current vehicle and the driving information;

[0009] If the current vehicle and the moving target meet the corresponding start-stop monitoring conditions, determine a third heading angle according to the historical track of the current vehicle and the driving information;

[0010] Determine a fourth heading angle of the moving target relative to the current vehicle based on the driving information, radar information, and the current track information;

[0011] Based on the current driving scenario, determine a target heading angle from the first heading angle, second heading angle, third heading angle, and fourth heading angle.

[0012] In a second aspect, an embodiment of the present disclosure provides a heading angle determination device, including:

[0013] A track information determination unit, configured to obtain radar information and driving information of the current vehicle, and determine current track information based on the radar information and the driving information;

[0014] A first heading angle determination unit, configured to determine a first heading angle of the moving target relative to the current vehicle based on the driving information, the current track information, and the historical heading angle;

[0015] A second heading angle determination unit, configured to, if the moving target is located in the oncoming lane of the current vehicle, determine a lane distance between the current vehicle and the oncoming lane, and determine a second heading angle based on the lane distance, the historical trajectory of the current vehicle, and the driving information;

[0016] A third heading angle determination unit, configured to, if the current vehicle and the moving target meet corresponding stop-and-go monitoring conditions, determine a third heading angle according to the historical trajectory of the current vehicle and the driving information;

[0017] A fourth heading angle determination unit, configured to determine a fourth heading angle of the moving target relative to the current vehicle based on the driving information, radar information, and the current track information;

[0018] A target heading angle determination unit, configured to determine a target heading angle from the first heading angle, second heading angle, third heading angle, and fourth heading angle based on the current driving scenario.

[0019] In a third aspect, an embodiment of the present disclosure provides an electronic device, including:

[0020] At least one processor; and

[0021] A memory communicatively connected to the at least one processor; wherein,

[0022] 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 that the at least one processor can execute a heading angle determination method provided in the first aspect embodiment above.

[0023] Fourthly, an embodiment of the present disclosure provides a computer-readable storage medium storing computer instructions for causing a processor to implement a heading angle determination method provided in the embodiment of the first aspect above when executed.

[0024] Fifthly, an embodiment of the present disclosure provides a computer program product. The computer program product includes a computer program which, when executed by a processor, implements a heading angle determination method provided in the embodiment of the first aspect above.

[0025] A heading angle determination method, apparatus, device, medium and product according to an embodiment of the present invention include obtaining radar information and driving information of a current vehicle, and determining current track information based on the radar information and the driving information; determining a first heading angle of a moving target relative to the current vehicle based on the driving information, the current track information and a historical heading angle; if the moving target is located in an oncoming lane of the current vehicle, determining a lane distance between the current vehicle and the oncoming lane, and determining a second heading angle based on the lane distance, a historical trajectory of the current vehicle and the driving information; if the current vehicle and the moving target meet corresponding stop-and-go monitoring conditions, determining a third heading angle according to the historical trajectory of the current vehicle and the driving information; determining a fourth heading angle of the moving target relative to the current vehicle based on the driving information, radar information and the current track information; and determining a target heading angle from the first heading angle, the second heading angle, the third heading angle and the fourth heading angle based on a current driving scenario. The above technical solution realizes accurate calculation of the heading angle in multiple scenarios.

[0026] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present invention, nor is it used to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention, and those of ordinary skill in the art can obtain other drawings without creative efforts based on these drawings.

[0028] Figure 1 is a flowchart of a heading angle determination method provided in Embodiment 1 of the present invention;

[0029] Figure 2 is a schematic diagram of a radar coordinate system provided in Embodiment 1 of the present invention;

[0030] Figure 3It is a flowchart of a method for determining the heading angle provided in the second embodiment of the present invention;

[0031] Figure 4 It is a schematic flowchart of a process for determining the target heading angle provided in the second embodiment of the present invention;

[0032] Figure 5 It is a schematic structural diagram of a device for determining the heading angle provided in the third embodiment of the present invention;

[0033] Figure 6 It is a schematic structural diagram of an electronic device provided in the fourth embodiment of the present invention. Detailed implementation manners

[0034] In order to enable those skilled in the art to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the protection scope of the present invention.

[0035] It should be noted that the terms "first", "second", and "target" in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and do not have to be used to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of the present invention described here can be implemented in an order different from those illustrated or described here. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units does not have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products, or devices.

[0036] Currently, the method for determining the heading angle adopted in the industry, in the state of low-speed driving, especially in scenarios such as waiting for traffic lights or traffic jams, has a small longitudinal speed and lateral speed, a large variance, and the target heading angle calculated by speed has a large gap with the actual situation. In addition, the historical displacement is short, and it is difficult to calculate an accurate target heading angle through distance. In addition, for oncoming vehicles in the oncoming lane, the radar may not accurately detect the radial distance and speed of the side target points, and it is difficult to obtain an accurate result for the heading angle calculated by the filtered speed or position. Therefore, there is an urgent need for a method for determining the heading angle for multiple scenarios.

[0037] Embodiment 1

[0038] Figure 1The figure is a flowchart of a heading angle determination method provided in the first embodiment of the present invention. This embodiment is applicable to the situation of accurately determining the heading angle in diverse scenarios. This method can be executed by a heading angle determination device, which can be implemented in the form of hardware and / or software.

[0039] As Figure 1 shown, the method includes:

[0040] S101. Obtain the radar information and driving information of the current vehicle, and determine the current trajectory information based on the radar information and the driving information.

[0041] In this embodiment, the current vehicle can be understood as the vehicle where the heading angle determination device integrating the execution of this method is located, that is, the vehicle itself. The radar information can be understood as the information collected by the radar, which is obtained by the radar and at least includes the radar period T and the ranging information monitored by the radar. The driving information can be understood as the information when the current vehicle is driving, at least including the driving speed (Velocity) and the yaw rate (Yawrate). The current trajectory information can be understood as the information related to the trajectory between the current vehicle and the moving target obtained by performing a series of processes by combining the radar information and the driving information, at least including the trajectory number (ID) of the moving target within the monitoring range of the current vehicle, the dynamic and static state (status) of the moving target, the relative speed between the current vehicle and the moving target, the relative distance between the current vehicle and the moving target, and the residence duration (life) of the moving target within the monitoring range of the current vehicle. Among them, the trajectory number can be understood as the identifier of the moving target; the dynamic and static state characterizes the driving state of the moving target, at least including moving, low speed, stop-and-go, and stationary. Among them, moving means that the moving target moves at a normal speed (for example, the moving speed of the moving target is greater than the corresponding speed threshold), low speed means that the moving target moves at a lower speed (for example, the moving speed of the moving target is less than the corresponding speed threshold), stop-and-go means that the moving target changes from moving to stationary, and stationary means that the speed of the moving target is zero; the relative speed includes the longitudinal relative speed Vx and the lateral relative speed Vy between the current vehicle and the moving target; the relative distance includes the longitudinal relative distance X and the lateral relative distance Y between the current vehicle and the moving target; the residence duration represents the duration during which the moving target is perceived by the current vehicle.

[0042] Specifically, obtain the radar data transmitted by the millimeter-wave radar and the driving data of the current vehicle body, perform conventional preprocessing, clustering association, and filtering and tracking processing on the point cloud data such as the radar data and the driving data, and output the current trajectory information. Among them, the coordinate system adopted by the present invention is the radar coordinate system of the radar position set on the current vehicle. Figure 2 The figure is a schematic diagram of a radar coordinate system provided in the first embodiment of the present invention. As Figure 2As shown in the figure, the radar coordinate system takes the center of a single radar as the coordinate origin, with the vertical direction of the radar as the X-axis and the horizontal direction as the Y-axis.

[0043] It can be understood that there is at least one radar installed on the current vehicle. If there is one radar, it is deployed at the front of the vehicle and is a front radar. If there are two radars, they are deployed at the corner positions of the vehicle and are corner radars. The two radars can be any two combinations of the front left corner radar, front right corner radar, rear left corner radar, and rear right corner radar, preferably two rear corner radars. If there are three radars, they are respectively deployed at the front of the vehicle and the corner positions of the vehicle, which is a combination of one front radar and two corner radars. Among them, the two corner radars can still be any two combinations of the front left corner radar, front right corner radar, rear left corner radar, and rear right corner radar, preferably two rear corner radars. If there are four radars, they are respectively deployed at the corner positions of the vehicle, which is a combination of the front left corner radar, front right corner radar, rear left corner radar, and rear right corner radar. If there are five radars, they are respectively deployed at the front of the vehicle and the corner positions of the vehicle, which is a combination of one front radar and four corner radars as shown in Figure 5 the figure.

[0044] S102. Determine the first heading angle of the moving target relative to the current vehicle based on the driving information, current track information, and historical heading angle.

[0045] In this embodiment, the historical heading angle can be understood as the heading angle between the current vehicle and the moving target determined within the historical time, such as the heading angle of the previous frame (target heading angle). The moving target can be understood as the environmental object facing the current vehicle that appears within the monitoring range of the current vehicle and for which the heading angle between the current vehicle and it needs to be calculated. The moving target can be a vehicle, a pedestrian, or other objects. This embodiment does not limit the type of the moving target. There can be multiple moving targets of the same type or different types, and each moving target has its corresponding track number. The first heading angle can be understood as the generalized heading angle between the current vehicle and the moving target in a general scenario calculated based on a conventional method.

[0046] Specifically, the historical heading angles of the moving target calculated within the historical time are all stored for subsequent use. Therefore, when it is determined that the current vehicle is in a moving state based on the driving speed in the driving information, the heading angle of the moving target in this frame relative to the radar coordinate system on the current vehicle is determined based on the relative speed in the current track information. The historical heading angle of the moving target in the previous frame relative to the same radar coordinate system is retrieved, and α-β filtering is performed based on the heading angle calculated in this frame and the historical heading angle of the previous frame to obtain the optimized first heading angle of the moving target relative to the radar coordinate system on the current vehicle.

[0047] It can be understood that the heading angle of the moving target described in the embodiments of the present invention relative to the radar coordinate system on the current vehicle is not limited to a single radar coordinate system, and can be any one radar coordinate system or multiple radar coordinate systems.

[0048] S103. If the moving target is located in the oncoming lane of the current vehicle, determine the lane distance between the current vehicle and the oncoming lane, and determine the second heading angle based on the lane distance, the historical trajectory and the driving information of the current vehicle.

[0049] In this embodiment, the lane distance can be understood as the distance between the current vehicle and the lane where the moving target is located. The historical trajectory can be understood as the driving trajectory of the current vehicle within the historical time, and is determined based on the current track information corresponding to the historical time of the current vehicle. During the driving process of the current vehicle, each frame has its corresponding trajectory point, and the trajectory points of each frame are combined together to form the historical trajectory, which is updated in real time as the vehicle travels. The second heading angle can be understood as the heading angle between the current vehicle and the moving target when the moving target is located in the oncoming lane of the current vehicle. In the oncoming driving scenario, the second heading angle is more accurate than the first heading angle.

[0050] Specifically, if there is an oncoming vehicle target, the radar may not accurately detect the radial distance and speed of the side target points. That is, the lateral relative distance and lateral relative speed in the current track information may not be accurate, and it is difficult to calculate the accurate heading angle through the filtered speed or position. Therefore, if the residence duration of the moving target monitored by the current vehicle and the relative distance between the current vehicle and the moving target meet the corresponding conditions, it is determined that the moving target is in the oncoming lane of the current vehicle; otherwise, it is determined that the moving target is in the non-oncoming lane of the current vehicle, such as the same-direction lane. In the case where it is determined that the moving target is in the oncoming lane of the current vehicle, based on the relative distance between a single moving target and the current vehicle under continuous multi-frame residence durations, or the relative distances between multiple moving targets and the current vehicle under a single-frame residence duration, the lane distance between the current vehicle and the oncoming lane is calculated. Based on the longitudinal relative position in the historical track and the current track information, and the lane distance between the current vehicle and the oncoming lane, the lateral distance between the current vehicle and the lane where the moving target is located is fitted and calculated. Furthermore, based on the calculated lateral distance between the current vehicle and the lane where the moving target is located, and the longitudinal relative distance in the current track information, the second heading angle of the moving target relative to the radar coordinate system on the current vehicle in the oncoming driving scenario is fitted. It can be understood that under the condition of driving on the right side as stipulated, since the oncoming lane must be on the left side of the current vehicle, when the right-side corner radar field of view (FOV) is limited and cannot detect the left-side target, the second heading angle is the heading angle of the moving target relative to the coordinate system of the front left corner radar and / or the rear left corner radar on the current vehicle (it can also be the heading angle of the moving target relative to the coordinate system of the front radar on the current vehicle); otherwise, under the condition of driving on the left side as stipulated, when the left-side corner radar FOV (field of view) is limited and cannot detect the left-side target, the second heading angle is the heading angle of the moving target relative to the coordinate system of the front right corner radar and / or the rear right corner radar on the current vehicle (it can also be the heading angle of the moving target relative to the coordinate system of the front radar on the current vehicle).

[0051] S104. If the current vehicle and the moving target meet the corresponding stop-and-go monitoring conditions, determine the third heading angle according to the historical track and driving information of the current vehicle.

[0052] In this embodiment, the driving and stopping monitoring condition can be understood as the condition for determining the current driving and stopping scenario. The driving and stopping monitoring condition includes: the driving speed in the driving information of the current vehicle is within a set range; a moving target is determined to be a stationary object based on the residence duration and track number in the current track information; the moving target is located in the same-direction lane of the current vehicle. The set range can be understood as the preset vehicle speed range of the vehicle itself, for example, 0 - 3 m / s. The stationary object can be understood as a moving target that the current vehicle can continuously monitor, representing that the moving target persists for multiple frames of residence duration. The driving and stopping scenario is usually a traffic jam scenario or a traffic light scenario. The third course angle can be understood as the course angle between the current vehicle and the moving target in the driving and stopping scenario. In the driving and stopping scenario, the third course angle is more accurate than the first course angle.

[0053] Specifically, for a moving target with low speed, especially in scenarios such as traffic lights or traffic jams, the longitudinal speed and lateral speed of the moving target are small, the variance is large, the course angle calculated by speed has a large gap with the actual situation, and the historical displacement of the moving target in the driving and stopping scenario is short, making it difficult to calculate an accurate course angle through distance. Therefore, if the driving speed in the driving information of the current vehicle is within the set range (the maximum speed is b, the minimum speed is 0) and it is determined that the vehicle speed of the vehicle itself is small enough, if the driving speed a satisfies 0 < a ≤ b, moving targets with dynamic and static states of movement, low speed, and driving and stopping are monitored within a certain distance range (for example, with the center of the vehicle itself as the origin, 6 m in the front, 4 m in the rear, and 3 m on each side left and right); if the driving speed a satisfies a = 0, moving targets with dynamic and static states of movement, low speed, driving and stopping, and stationary are monitored within a certain distance range; if the monitoring result shows that there are multiple moving targets with track numbers (for example, more than 5) around the current vehicle, and the moving targets with the same track number persist for multiple frames of residence duration (for example, more than 20 frames), then these moving targets that persist for multiple frames of residence are determined to be stationary objects; after determining the stationary objects, if these stationary objects are not in the oncoming lane of the current vehicle (which can be determined based on step S103), that is, the moving target is located in the same-direction lane of the current vehicle, it is determined that the driving and stopping monitoring condition is satisfied and the current is a driving and stopping scenario. In the driving and stopping scenario, based on the historical trajectory of the current vehicle and the longitudinal relative distance in the driving information, the optimized lateral relative distance between the current vehicle and the moving target is calculated by fitting, and the third course angle of the moving target relative to the radar coordinate system on the current vehicle is calculated based on the longitudinal relative distance and the optimized lateral relative distance.

[0054] S105. Determine the fourth course angle of the moving target relative to the current vehicle based on the driving information, radar information, and current track information.

[0055] In this embodiment, the fourth course angle can be understood as the course angle in the generalized scenario between the current vehicle and the moving target determined based on the historical position, and the fourth course angle is more accurate than the first course angle.

[0056] Specifically, starting from the first frame when the current vehicle detects a moving target, that is, when the residence time is 1, the lateral relative distance and the longitudinal relative distance between the current vehicle and the moving target at this moment are stored, denoted as anchor point information, and the anchor point information is corrected from the relative distance to the absolute position based on the driving information and the radar information. After that, as the vehicle travels, the real-time displacement between the current vehicle and the moving target also changes. When the real-time displacement meets the corresponding threshold condition, it is determined that the vehicle has effective driving, and the anchor point information is iteratively updated; based on the anchor point information within the historical time (the previous frame), the relative displacement between the current vehicle and the moving target is calculated. When the relative displacement meets the corresponding threshold condition, the fourth heading angle of the moving target relative to the radar coordinate system on the current vehicle is calculated through the relative distance in the current track information and the relative displacement.

[0057] S106. Determine the target heading angle from the first heading angle, the second heading angle, the third heading angle, and the fourth heading angle based on the current driving scenario.

[0058] In this embodiment, the current driving scenario includes an oncoming driving scenario, a stop-and-go scenario, and other scenarios. Among them, the oncoming driving scenario means that the moving target is in the oncoming lane of the current vehicle, and the stop-and-go scenario means the scenario when the current vehicle and the moving target meet the stop-and-go monitoring conditions. In the stop-and-go scenario, the speed of the current vehicle is low enough and multiple moving targets can be continuously monitored. Other scenarios include normal high-speed driving, low-speed driving, and other normal scenarios, including all other driving scenarios except the oncoming driving scenario and the stop-and-go scenario. It can be understood that in the stop-and-go scenario, the moving target is in the same lane as the current vehicle, that is, there is no overlap between the stop-and-go scenario and the oncoming driving scenario.

[0059] Specifically, if the current is in the oncoming driving scenario, the second heading angle is used as the target heading angle; if the current is in the stop-and-go scenario, the third heading angle is used as the target heading angle; if the current is neither in the stop-and-go scenario nor in the oncoming driving scenario, then the heading angle difference between the first heading angle and the fourth heading angle is determined. If the heading angle difference is less than a certain difference threshold, the first heading angle is used as the standard, and the first heading angle is determined as the target heading angle. If the heading angle difference is greater than or equal to the difference threshold, the fourth heading angle is used as the standard, and the fourth heading angle is used as the target heading angle.

[0060] A method for determining a heading angle provided by an embodiment of the present invention includes obtaining radar information and driving information of a current vehicle, and determining current track information based on the radar information and the driving information; determining a first heading angle of a moving target relative to the current vehicle based on the driving information, the current track information, and a historical heading angle; if the moving target is located in an oncoming lane of the current vehicle, determining a lane distance between the current vehicle and the oncoming lane, and determining a second heading angle based on the lane distance, a historical trajectory of the current vehicle, and the driving information; if the current vehicle and the moving target meet corresponding stop-and-go monitoring conditions, determining a third heading angle according to a historical trajectory of the current vehicle and the driving information; determining a fourth heading angle of the moving target relative to the current vehicle based on the driving information, radar information, and the current track information; and determining a target heading angle from the first heading angle, the second heading angle, the third heading angle, and the fourth heading angle based on a current driving scenario. In the above technical solution, a brand-new heading angle perception algorithm for detecting a target using a millimeter-wave radar is used. Based on the heading angle calculated by filtering speed, the target heading angle is assisted and corrected using a historical heading angle, a heading angle calculated based on a historical position, a heading angle calculated based on object lane recognition, and a heading angle calculated based on stop-and-go scenario recognition, realizing accurate calculation of the heading angle in multiple scenarios.

[0061] Embodiment 2

[0062] Figure 3 FIG. is a flowchart of a method for determining a heading angle provided by Embodiment 2 of the present invention. This embodiment is a further optimization of any of the above embodiments and is applicable to the situation of accurately determining the heading angle in diverse scenarios. This method can be executed by a heading angle determination device, and the heading angle determination device can be implemented in the form of hardware and / or software.

[0063] As Figure 3 shown, the method includes:

[0064] S201. Obtain radar information and driving information of a current vehicle, and determine current track information based on the radar information and the driving information.

[0065] S202. For each radar, determine an intermediate heading angle of a moving target relative to the radar in the radar coordinate system based on the driving speed in the driving information and the relative speed in the current track information.

[0066] In this embodiment, the relative speed can be understood as the relative speed difference between the current vehicle and the moving target, including the lateral relative speed and the longitudinal relative speed. The intermediate heading angle can be understood as the heading angle directly calculated based on the relative speed.

[0067] Specifically, each radar has its corresponding coordinate system. For each radar, if the driving speed in the driving information is 0, the intermediate heading angle is determined to be 0°; if the driving speed in the driving information is greater than 0, based on the lateral relative speed Vy and the longitudinal relative speed Vx in the current track information, the intermediate heading angle θ of the moving target relative to the radar on the current vehicle in the corresponding radar coordinate system is calculated through the arctangent function θ Curv = arctan(Vy, Vx). Curv .

[0068] S203. Determine the difference between the historical heading angle and the intermediate heading angle, and determine the first weight of the intermediate heading angle and the second weight of the historical heading angle based on the difference.

[0069] In this embodiment, the first weight can be understood as the weight of the intermediate heading angle, and the second weight can be understood as the weight of the historical heading angle. The first weight and the second weight change with the difference between the historical heading angle and the intermediate heading angle.

[0070] Specifically, the greater the difference between the adjacent two-frame heading angles of the historical heading angle and the intermediate heading angle, the greater the value of the first weight α of the intermediate heading angle, and the maximum is 1. Among them, the corresponding relationship between the difference of the two-frame heading angles and the first weight and the second weight can be determined based on the actual situation. For example, a difference-weight comparison table is set, and different differences correspond to different weights. Or, the first weight and the second weight are set based on the percentage between the difference degree and 360°. This embodiment does not limit the corresponding manner of the difference and the weight.

[0071] S204. Determine the first heading angle according to the intermediate heading angle, the first weight, the historical heading angle, and the second weight.

[0072] In this embodiment, α-β filtering is performed on the intermediate heading angle and the historical heading angle, and the first heading angle θ is calculated through θ v = α * θ Curv + β * θ Hisv , where α + β = 1. v . In the formula, θ Hisv is the historical heading angle.

[0073] S205. If the moving target is located in the oncoming lane of the current vehicle, determine the lane distance between the current vehicle and the oncoming lane, and determine the second heading angle based on the lane distance, the historical trajectory of the current vehicle, and the driving information.

[0074] S206. If the current vehicle and the moving target meet the corresponding stop-and-go monitoring conditions, determine the third heading angle according to the historical trajectory and the driving information of the current vehicle.

[0075] S207. Determine the fourth course angle of the moving target relative to the current vehicle based on the driving information, radar information, and current track information.

[0076] S208. Determine the target course angle from the first course angle, second course angle, third course angle, and fourth course angle based on the current driving scenario.

[0077] A course angle determination method provided by an embodiment of the present invention includes obtaining the radar information and driving information of the current vehicle, and determining the current track information based on the radar information and driving information; for each radar, determining the intermediate course angle of the moving target relative to the radar in the radar coordinate system based on the driving speed in the driving information and the relative speed in the current track information; determining the difference between the historical course angle and the intermediate course angle, and determining the first weight of the intermediate course angle and the second weight of the historical course angle based on the difference; determining the first course angle according to the intermediate course angle, the first weight, the historical course angle, and the second weight; if the moving target is located in the oncoming lane of the current vehicle, determining the lane distance between the current vehicle and the oncoming lane, and determining the second course angle based on the lane distance, the historical trajectory of the current vehicle, and the driving information; if the current vehicle and the moving target meet the corresponding stop-and-go monitoring conditions, determining the third course angle according to the historical trajectory and driving information of the current vehicle; determining the fourth course angle of the moving target relative to the current vehicle based on the driving information, radar information, and current track information; and determining the target course angle from the first course angle, second course angle, third course angle, and fourth course angle based on the current driving scenario. In the above technical solution, compared with the traditional single-frame course angle calculation, this method can effectively reduce the course angle anomaly caused by the single-frame speed perturbation of the moving target, and can also well take into account the change of the course angle in scenarios such as turning scenarios.

[0078] For the front radar or front corner radar, when a moving target traveling in the opposite direction approaches from a distance, relatively accurate course angle estimation can be obtained by the methods of calculating the course angle based on speed and calculating the course angle based on historical position. However, for the rear corner radar, when a moving target traveling in the opposite direction passes by the side of the vehicle, due to reasons such as the fast movement of the nearby target, the large radar illumination area, and the radial velocity detection being 0 when the radar beam direction is perpendicular to the movement direction of the moving target, it is difficult to calculate the accurate target course angle by the above two traditional methods. Therefore, an embodiment of the present invention provides a method based on oncoming lane recognition to obtain a more accurate course angle estimation.

[0079] As the first alternative embodiment of this embodiment, if the moving target is located in the oncoming lane of the current vehicle, determining the lane distance between the current vehicle and the oncoming lane includes:

[0080] S2051. If the residence duration and relative distance in the current track information meet the first condition and the relative speed meets the second condition, determine that the moving target is in the oncoming lane of the current vehicle.

[0081] In this embodiment, the residence duration can be understood as the duration when the current vehicle detects the existence of the moving target, in terms of frames. The first condition can be understood as the condition for defining whether the moving target is in the oncoming lane of the current vehicle, related to the residence duration and relative distance; the second condition can also be understood as the condition for defining whether the moving target is in the oncoming lane of the current vehicle, related to the relative speed. The first condition includes: when the residence duration is 1, the longitudinal relative distance is less than the corresponding first set distance; when the residence duration is greater than the set number of frames, the longitudinal relative distance is greater than another corresponding second set distance; the lateral relative distance is greater than yet another corresponding third set distance. The second condition includes: the sum value of the longitudinal relative speed and the vehicle's speed relative to the ground is less than the corresponding first set speed, and the absolute value of the lateral relative speed is less than another corresponding second set speed.

[0082] Specifically, taking the regulation of driving on the right as an example, since the oncoming lane can only exist on the left side of the current vehicle, thus, judge the moving target on the left side to determine whether the lane it is in is the oncoming lane of the current vehicle. When the residence duration is 1 and the longitudinal relative distance is less than the corresponding first set distance (for example, 1 m), it is determined that the moving target passes by in front of the current vehicle, reducing the misjudgment caused by lane direction changes; when the residence duration is greater than the set number of frames (for example, 20 frames) and the longitudinal relative distance is greater than the corresponding second set distance (for example, 10 m), it is determined that the moving target is not on the side of the vehicle itself and accurate speed measurement can be achieved; when the lateral relative distance is greater than the corresponding third set distance (for example, 2 m), it is determined that the moving target is on the left side of the current vehicle and not in the same lane. When the sum value of the longitudinal relative speed and the vehicle's speed relative to the ground (Vx + Vehicle) is less than the corresponding first set speed (for example, -10 m / s) and the absolute value of the lateral relative speed is less than the corresponding second set speed (for example, 2 m / s), it can be determined that the moving target is an oncoming vehicle. If both the first condition and the second condition are met, it is determined that this track is real and stable, and the moving target moving in the opposite direction on the left side of the vehicle itself is in the oncoming lane of the current vehicle. If any one of the conditions is not met, it cannot be determined that the moving target is in the oncoming lane of the current vehicle.

[0083] S2052. When the moving target in the oncoming lane of the current vehicle meets the lane distance determination condition, determine the lane distance between the current vehicle and the oncoming lane based on the relative distance in the current track information.

[0084] In this embodiment, the lane distance determination condition can be understood as the condition for determining the distance between the current vehicle and the lane where the moving target is located.

[0085] Specifically, if there are consecutive multi-frame residence durations for moving objects with the same track ID (i.e., the identifier of the moving object), or if there are moving objects with multiple track IDs in a single-frame residence duration (for example, 10 consecutive frames, with at least 4 moving objects in a single frame), it is determined that the current moving object meets the lane distance determination condition. The lateral relative distances in the current track information related to each moving object are statistically analyzed, and the maximum and minimum values of the lateral relative distances are determined from the multiple lateral relative distances. Based on the maximum and minimum values, the lane distance between the current vehicle and the oncoming lane where the moving object is located is determined. The confirmation method of the lane distance can be to take the average value, or to use the minimum value as the standard, or to use the maximum value as the standard. This embodiment does not limit this.

[0086] Based on lane recognition, it is determined whether the moving object is in the same lane or the oncoming lane of the current vehicle, which improves the accuracy of the target heading angle in the same lane and can also solve the problem of inaccurate estimation of the heading angle of the oncoming vehicle in the side face by the rear corner radar. When there are multiple rear oncoming vehicles in the oncoming lane in a single frame or there are moving objects with the same track ID in multiple frames in the oncoming lane, the oncoming lane recognition terminates. When it is determined through the heading angle of the current vehicle that the vehicle performs a lane change operation, the oncoming lane recognition also terminates.

[0087] As the second alternative embodiment of this embodiment, determining the second heading angle based on the lane distance, the historical trajectory, and the driving information of the current vehicle includes:

[0088] S2053. Fit the historical trajectory of the current vehicle to form the trajectory equation of the current vehicle.

[0089] In this embodiment, the trajectory equation can be understood as a third-order curve equation for the current vehicle's travel.

[0090] Specifically, based on the historical trajectory position points of the current vehicle, curve fitting is performed to form the third-order curve equation Y = aX 3 + bX 2 + cX + d of the current vehicle. Here, X is the abscissa position, Y is the ordinate position, and a, b, c, and d are all constant parameters.

[0091] S2054. Determine the reference lateral relative distance according to the longitudinal relative distance in the driving information and the trajectory equation.

[0092] In this embodiment, the reference lateral relative distance can be understood as the lateral relative distance fitted based on the longitudinal relative distance and the trajectory equation. Compared with the lateral relative distance in the current track information, the fitted reference lateral relative distance is more accurate.

[0093] Specifically, substitute the longitudinal relative distance in the driving information into the trajectory equation of the current vehicle to fit and obtain the reference lateral relative distance.

[0094] S2055. Determine the first lateral relative distance based on the reference lateral relative distance and the lane distance, and determine the second heading angle of the moving target relative to the current vehicle based on the longitudinal relative distance and the first lateral relative distance.

[0095] In this embodiment, the first lateral relative distance can be understood as a more specific lateral relative distance between the current vehicle and the moving target considering the factors of lane distance and measurement distance.

[0096] Specifically, calculate the sum of the reference lateral relative distance and the lane distance to obtain the first lateral relative distance. Based on the longitudinal relative distance X and the first lateral relative distance Y, through θ Road = arctan(Y, X) to calculate the second heading angle θ of the moving target relative to the corresponding radar coordinate system on the current vehicle Road .

[0097] The above technical solution can effectively solve the problem of inaccurate calculation of the lateral heading angle of an oncoming vehicle target on the side of the vehicle.

[0098] As the third alternative embodiment of this embodiment, if the current vehicle and the moving target meet the corresponding stop-and-go monitoring conditions, determine the third heading angle according to the historical trajectory and driving information of the current vehicle, including:

[0099] S2061. If the current vehicle and the moving target meet the corresponding stop-and-go monitoring conditions, fit the historical trajectory of the current vehicle to form the trajectory equation of the current vehicle.

[0100] Specifically, if the current vehicle and the moving target meet the corresponding stop-and-go monitoring conditions, based on the same fitting method as in step S2053, fit the third-order curve equation according to the historical trajectory of the current vehicle as the trajectory equation of the current vehicle.

[0101] S2062. Determine the second lateral relative distance according to the longitudinal relative distance and the trajectory equation in the driving information, and determine the third heading angle of the moving target relative to the current vehicle based on the longitudinal relative distance and the second lateral relative distance.

[0102] In this embodiment, the second lateral relative distance can be understood as the lateral relative distance fitted based on the longitudinal relative distance and the trajectory equation. Compared with the lateral relative distance in the current track information, the fitted second lateral relative distance is more accurate.

[0103] Specifically, substitute the longitudinal relative distance in the driving information into the trajectory equation of the current vehicle to fit and obtain the second lateral relative distance. Based on the longitudinal relative distance X and the second lateral relative distance Y, through θ SceneThe third heading angle θ of the moving target relative to the current vehicle radar coordinate system is calculated by = arctan(Y,X). Scene .

[0104] It can be understood that when the driving speed of the current vehicle is greater than the maximum speed corresponding to the set range (for example, 3 m / s), it is determined that the current does not meet the start-stop monitoring condition, the recognition of the start-stop scenario is terminated, and the calculation of the third heading angle ends.

[0105] Based on the heading angle fitting of the start-stop scenario, it well avoids the problem of incorrect heading angle calculation caused by small Vx and Vy or inaccurate detection when a low-speed moving target does not have sufficiently far historical positions to assist in correcting the heading angle.

[0106] As the fourth alternative embodiment of this embodiment, determining the fourth heading angle of the moving target relative to the current vehicle based on the driving information, radar information, and current track information includes:

[0107] S2071. If the residence duration in the current track information meets the set trigger condition, determine the first anchor point information and the second anchor point information of the current vehicle, and store the first anchor point information and the second anchor point information.

[0108] In this embodiment, the set trigger condition can be understood as the trigger condition for calculating the fourth heading angle. The first anchor point information can be understood as a type of vehicle position information, which is the distance between the current vehicle and the moving target, focusing on historical moments; the second anchor point information can also be understood as a type of vehicle position information, which is the distance between the current vehicle and the moving target, focusing on the current moment; when the residence duration is 1, the first anchor point information and the second anchor point information are the same.

[0109] Specifically, if the residence duration in the current track information is 1, indicating that the moving target enters the detection range of the current vehicle, it is determined that the current meets the set trigger condition, record the first anchor point information (X1, Y1) and the second anchor point information (X2, Y2) of the current vehicle. When the first anchor point information and the second anchor point information are recorded for the first time, X1 = X2, Y1 = Y2, both X1 and X2 can be the longitudinal relative distance X in the current track information, and both Y1 and Y2 can be the lateral relative distance Y in the current track information. After determining the first anchor point information and the second anchor point information, store the first anchor point information and the second anchor point information for backup, which is used for subsequent iterative assignment.

[0110] S2072. Correct the first anchor point information and the second anchor point information according to the driving information and the radar information to obtain the corrected first anchor point information and the second anchor point information.

[0111] In this embodiment, since the first anchor point information and the second anchor point information are relative distances with the center of the rear axle of the vehicle as the coordinate origin, it is necessary to perform motion compensation on X1 in the first anchor point information according to the driving speed Velocity and the heading angular velocity Yawrate in the driving information, as well as the corresponding radar monitoring period T in the radar information, through X1 = (X1 + (-Velocity * T)) * cos(-Yawrate * T) - Y1 * sin(-Yawrate * T), and perform motion compensation on Y1 in the first anchor point information through Y1 = (X1 + (-Velocity * T)) * sin(-Yawrate * T) + Y1 * cos(-Yawrate * T)sin(-Yawrate * T) to obtain the corrected first anchor point information, so as to maintain the accuracy of the historical positions X1 and Y1; similarly, perform the same motion compensation on X2 and Y2 in the second anchor point information in the same way to obtain the corrected second anchor point information.

[0112] S2073. Determine the first lateral displacement and the first longitudinal displacement of the moving target relative to the current vehicle according to the corrected first anchor point information and the relative distance in the current track information. If any of the first lateral displacement and the first longitudinal displacement satisfies the first displacement condition, determine the fourth heading angle of the moving target relative to the current vehicle according to the relative distance and the first anchor point information.

[0113] In this embodiment, the first lateral displacement can be understood as the lateral displacement between the current vehicle and the moving target, which is the difference between the lateral relative distance and the abscissa in the first anchor point information. The first longitudinal displacement can be understood as the longitudinal displacement between the current vehicle and the moving target, which is the difference between the longitudinal relative distance and the ordinate in the first anchor point information. The first displacement condition can be understood as the trigger condition for specifically calculating the fourth heading angle.

[0114] Specifically, according to the first anchor point information (X1, Y1), the longitudinal relative distance X, and the lateral relative distance Y, through X dis1 = |X - X1|, the first longitudinal displacement X dis1 is calculated, and through Y dis1 = |Y - Y1|, the first lateral displacement Y dis1 is calculated. If any of the first lateral displacement and the second longitudinal displacement satisfies the corresponding first displacement threshold (for example, 3 m), the motion direction θ Curd = arctan(Y - Y1, X - X1) is fitted through the arctangent function to calculate the fourth heading angle θ of the moving target relative to the radar coordinate system of the current vehicle Curd .

[0115] S2074. Determine the second lateral displacement, second longitudinal displacement, and total displacement of the moving target relative to the current vehicle based on the corrected second anchor point information and the relative distance. If any of the second lateral displacement, second longitudinal displacement, and total displacement meets the second displacement condition, assign the second anchor point information to the first anchor point information, assign the relative distance to the second anchor point information, and return to re - execute the determination of the fourth course angle.

[0116] In this embodiment, the second lateral displacement can be understood as the lateral displacement between the current vehicle and the moving target, which is the difference between the lateral relative distance and the abscissa in the second anchor point information; the second longitudinal displacement can be understood as the longitudinal displacement between the current vehicle and the moving target, which is the difference between the longitudinal relative distance and the ordinate in the second anchor point information; the total displacement can be understood as the total displacement between the current vehicle and the moving target, which is calculated based on the second lateral displacement and the second longitudinal displacement. The second displacement condition can be understood as the trigger condition for performing iterative updates of the first anchor point information and the second anchor point information.

[0117] Since the vehicle is in a moving state and its position is changing at any time, therefore, as the vehicle travels, the first anchor point information and the second anchor point information need to be iteratively updated correspondingly. Specifically, according to the second anchor point information (X2, Y2), the longitudinal relative distance X, and the lateral relative distance Y, through X dis2 = |X - X2| to calculate the second longitudinal displacement, through Y dis2 = |Y - Y2| to calculate the second lateral displacement, and through to calculate the total displacement. If any of the second lateral displacement, second longitudinal displacement, and total displacement meets the corresponding second displacement threshold (for example, 5m), assign X2 and Y2 in the current second anchor point information to X1 and Y1 in the first anchor point information respectively, and assign the longitudinal relative distance X and the lateral relative distance Y in the current track information to X2 and Y2 in the second anchor point information respectively, so as to realize the iterative update of the first anchor point information and the second anchor point information.

[0118] Furthermore, it further includes:

[0119] a. If the relative speed in the current track information meets the round - trip movement condition, determine the third anchor point information of the moving target.

[0120] In this embodiment, the round - trip movement condition can be understood as the condition for determining whether the moving target has round - trip movements such as U - turns. The third anchor point information can be understood as the position information of the moving target, which is the absolute position coordinate point information of the moving target.

[0121] To prevent the fourth heading angle calculated from the historical position (the first anchor point information) from being incorrect due to the target moving back and forth, an anomaly monitoring mechanism is introduced. Specifically, if the absolute value |Vy| of the lateral relative velocity Vy in the current track information is less than a certain velocity threshold, or the absolute value |Vx| of the longitudinal relative velocity Vx is less than this velocity threshold, it is determined that the current meets the conditions for moving back and forth, and the third anchor point information of the moving target is determined based on the radar information.

[0122] b. Determine the third lateral displacement and the third longitudinal displacement of the current vehicle relative to the moving target according to the third anchor point information and the relative distance. If any of the third lateral displacement and the third longitudinal displacement meets the third displacement condition, it is determined that the moving target has a U-turn behavior, and the fourth heading angle is set to invalid.

[0123] In this embodiment, the third lateral displacement can be understood as the lateral displacement between the current vehicle and the moving target, which is the difference between the lateral relative distance and the abscissa in the third anchor point information; the third longitudinal displacement can be understood as the longitudinal displacement between the current vehicle and the moving target, which is the difference between the longitudinal relative distance and the ordinate in the third anchor point information. The third displacement condition can be understood as the condition for confirming whether the moving target has a U-turn behavior.

[0124] Specifically, according to the third anchor point information (X3, Y3), the longitudinal relative distance X, and the lateral relative distance Y, through X dis3 = |X - X3| to calculate the third longitudinal distance X dis3 , through Y dis3 = |Y - Y3| to calculate the third lateral distance. If any of the third lateral displacement and the third longitudinal displacement meets the corresponding third displacement threshold (for example, 0.5 m), and satisfies |X3 – X1| < X dis1 , it is determined that the moving target may have a U-turn behavior, and the fourth heading angle is set to invalid.

[0125] c. If the third displacement condition is met for a continuously set number of times, clear the first anchor point information and the second anchor point information.

[0126] In this embodiment, the set number of times can be understood as a preset continuous number threshold, for example, 3 times.

[0127] Specifically, when it is determined that the moving target may have a U-turn behavior, the heading angle is no longer calculated using the historical position (the first anchor point information), the count is incremented by one, and after re-recording the third anchor point information (X3, Y3), the judgment described in step b is repeated. When the third displacement condition is met for a continuously set number of times (for example, 3 times), it is determined that the moving target has a U-turn behavior, and all historical position information is cleared, that is, all the stored first anchor point information and second anchor point information is cleared.

[0128] Calculate the fourth heading angle based on the historical position. By recording the information of two anchor points, the historical relative distance of the moving target can be well utilized to fit the moving direction. By introducing a historical position anomaly monitoring mechanism, it can be timely determined whether the moving target has a round-trip movement, avoiding obtaining an incorrect heading angle through incorrect historical position calculation. And this mechanism has a redundant design, which can avoid wrongly exiting the historical position calculation and correction strategy due to the unstable jitter of target detection. When the threshold is set appropriately, a target heading angle with high precision can be obtained, solving the problem of inaccurate heading angle estimation for low-speed targets.

[0129] Figure 4 It is a schematic flowchart of a process for determining a target heading angle provided in the second embodiment of the present invention. As Figure 4 shown, first determine the radar information, driving information of the current vehicle, and the current track information of the current vehicle relative to the moving target in advance, and then determine the first heading angle, second heading angle, third heading angle, and fourth heading angle based on the above information. Specifically, determine the first heading angle based on the driving information and α-β filtering; then determine the second heading angle based on lane recognition. If the moving target is in the oncoming lane of the current vehicle, fit the second heading angle and determine the second heading angle as the target heading angle. Otherwise, perform a stop-and-go scenario recognition; determine the third heading angle based on the recognition of the stop-and-go scenario. If the current is in a stop-and-go scenario, fit the third heading angle and determine the third heading angle as the target heading angle. Otherwise, perform the determination of the fourth heading angle based on the historical position, calculate multiple displacements and determine whether the corresponding displacement conditions are met. When the displacement conditions are met, fit the fourth heading angle, and select the most optimal one from the first heading angle and the fourth heading angle as the target heading angle. Determine the most matching and accurate target heading angle from each heading angle.

[0130] As the fifth optional embodiment of this embodiment, determining the target heading angle from the first heading angle, second heading angle, third heading angle, and fourth heading angle based on the current driving scenario includes:

[0131] S2081. If the current driving scenario is an oncoming driving scenario, determine the second heading angle as the target heading angle.

[0132] In this embodiment, the current driving scenario can be understood as the driving scenario of the current vehicle and the moving target at the current moment. The oncoming driving scenario can be understood as the scenario where the moving target is driving in the oncoming lane of the current vehicle.

[0133] Specifically, if the current driving scenario is an oncoming driving scenario and the moving target is in the oncoming lane of the current vehicle, then determine the second heading angle θ Road as the target heading angle. Otherwise, determine whether the current driving scenario is a stop-and-go scenario, and perform step S2082.

[0134] S2082. If the current driving scenario is a stop-and-go scenario, determine the third heading angle as the target heading angle.

[0135] In this embodiment, the stop-and-go scenario can be understood as a scenario where the current vehicle and the moving target are in a state such as waiting for a red light or being stuck in traffic.

[0136] Specifically, if the current driving scenario is a stop-and-go scenario and the current vehicle and the moving target meet the stop-and-go monitoring conditions, determine the third heading angle θ Scene as the target heading angle. Otherwise, execute step S2083.

[0137] S2083. If the current is in other scenarios except the oncoming driving scenario and the stop-and-go scenario, determine the heading angle difference between the first heading angle and the fourth heading angle.

[0138] In this embodiment, the heading angle difference can be understood as the difference between the first heading angle and the fourth heading angle.

[0139] Specifically, if the current driving scenario is neither the oncoming driving scenario nor the stop-and-go scenario, calculate the heading angle difference between the first heading angle θ v and the fourth heading angle θ Curd .

[0140] S2084. If the heading angle difference is less than the difference threshold, determine the first heading angle as the target heading angle; otherwise, determine the fourth heading angle as the target heading angle.

[0141] In this embodiment, the difference threshold can be understood as the maximum preset heading angle difference.

[0142] Specifically, if the heading angle difference is less than the difference threshold (for example, 30°), determine the first heading angle θ v as the target heading angle. If the heading angle difference is greater than or equal to the difference threshold, take the fourth heading angle as the standard and determine the fourth heading angle θ Curd as the target heading angle.

[0143] Embodiment III

[0144] Figure 5 is a schematic structural diagram of a heading angle determination device provided in Embodiment III of the present invention. As Figure 5 shown, the device includes:

[0145] A track information determination unit 31, configured to obtain the radar information and driving information of the current vehicle, and determine the current track information based on the radar information and the driving information;

[0146] A first heading angle determination unit 32, configured to determine the first heading angle of the moving target relative to the current vehicle based on the driving information, the current track information, and the historical heading angle;

[0147] The second heading angle determination unit 33 is configured to determine the lane distance between the current vehicle and the oncoming lane if the moving target is in the oncoming lane of the current vehicle, and determine the second heading angle based on the lane distance, the historical trajectory of the current vehicle, and the driving information;

[0148] The third heading angle determination unit 34 is configured to determine the third heading angle according to the historical trajectory of the current vehicle and the driving information if the current vehicle and the moving target meet the corresponding stop-and-go monitoring conditions;

[0149] The fourth heading angle determination unit 35 is configured to determine the fourth heading angle of the moving target relative to the current vehicle based on the driving information, the radar information, and the current track information;

[0150] The target heading angle determination unit 36 is configured to determine the target heading angle from the first heading angle, the second heading angle, the third heading angle, and the fourth heading angle based on the current driving scenario.

[0151] The heading angle determination device adopted in this technical solution realizes the accurate determination of the target heading angle in various scenarios.

[0152] Optionally, at least one radar is provided on the current vehicle, and the first heading angle determination unit 32 is specifically configured to:

[0153] For each radar, determine the intermediate heading angle of the moving target relative to the radar in the radar coordinate system based on the driving speed in the driving information and the relative speed in the current track information;

[0154] Determine the difference between the historical heading angle and the intermediate heading angle, and determine the first weight of the intermediate heading angle and the second weight of the historical heading angle based on the difference;

[0155] Determine the first heading angle according to the intermediate heading angle, the first weight, the historical heading angle, and the second weight.

[0156] Optionally, the second heading angle determination unit 33 is specifically configured to:

[0157] If the residence time and the relative distance in the current track information meet the first condition and the relative speed meets the second condition, determine that the moving target is in the oncoming lane of the current vehicle;

[0158] When the moving target in the oncoming lane of the current vehicle meets the lane distance determination condition, determine the lane distance between the current vehicle and the oncoming lane based on the relative distance in the current track information.

[0159] Optionally, the second heading angle determination unit 33 is specifically configured to:

[0160] Fit a trajectory equation of the current vehicle based on the historical trajectory of the current vehicle;

[0161] Determine a reference lateral relative distance according to the longitudinal relative distance in the driving information and the trajectory equation;

[0162] Determine a first lateral relative distance according to the reference lateral relative distance and the lane distance, and determine a second heading angle of the moving target relative to the current vehicle based on the longitudinal relative distance and the first lateral relative distance.

[0163] Optionally, the stop-go monitoring condition includes: the driving speed in the driving information of the current vehicle is within a set range; determining that the moving target is a stationary object based on the residence duration and the track number in the current track information; the moving target is located in the same lane as the current vehicle;

[0164] Optionally, the third heading angle determination unit 34 is specifically configured to:

[0165] If the current vehicle and the moving target meet the corresponding stop-go monitoring condition, fit a trajectory equation of the current vehicle based on the historical trajectory of the current vehicle;

[0166] Determine a second lateral relative distance according to the longitudinal relative distance in the driving information and the trajectory equation, and determine a third heading angle of the moving target relative to the current vehicle based on the longitudinal relative distance and the second lateral relative distance.

[0167] Optionally, the fourth heading angle determination unit 35 is specifically configured to:

[0168] If the residence duration in the current track information meets the set trigger condition, determine first anchor point information and second anchor point information of the moving target relative to the current vehicle, and store the first anchor point information and the second anchor point information;

[0169] Correct the first anchor point information and the second anchor point information according to the driving information and the radar information to obtain corrected first anchor point information and second anchor point information;

[0170] Determine a first lateral displacement and a first longitudinal displacement of the moving target relative to the current vehicle according to the corrected first anchor point information and the relative distance in the current track information. If any of the first lateral displacement and the first longitudinal displacement meets the first displacement condition, determine a fourth heading angle of the moving target relative to the current vehicle according to the relative distance and the first anchor point information;

[0171] Determine the second lateral displacement, the second longitudinal displacement, and the total displacement of the moving target relative to the current vehicle according to the corrected second anchor point information and the relative distance. If any of the second lateral displacement, the second longitudinal displacement, and the total displacement satisfies the second displacement condition, assign the second anchor point information to the first anchor point information, assign the relative distance to the second anchor point information, and return to re - execute the determination of the fourth heading angle.

[0172] Optionally, the fourth heading angle determination unit 35 is further configured to:

[0173] If the relative speed in the current track information satisfies the round - trip movement condition, determine the third anchor point information of the moving target;

[0174] Determine the third lateral displacement and the third longitudinal displacement of the moving target relative to the current vehicle according to the third anchor point information and the relative distance. If any of the third lateral displacement and the third longitudinal displacement satisfies the third displacement condition, determine that the moving target has a U - turn behavior, and set the fourth heading angle to invalid;

[0175] If the continuous setting times satisfy the third displacement condition, clear the first anchor point information and the second anchor point information.

[0176] Optionally, the target heading angle determination unit 36 is specifically configured to:

[0177] If the moving target is located in the oncoming lane of the current vehicle, determine that the current driving scenario is an oncoming driving scenario, and determine the second heading angle as the target heading angle;

[0178] If the current vehicle and the moving target meet the corresponding stop - and - go monitoring conditions, determine that the current driving scenario is a stop - and - go scenario, and determine the third heading angle as the target heading angle;

[0179] If the current is in other scenarios except the oncoming driving scenario and the stop - and - go scenario, determine the heading angle difference between the first heading angle and the fourth heading angle;

[0180] If the heading angle difference is less than the difference threshold, determine the first heading angle as the target heading angle; otherwise, determine the fourth heading angle as the target heading angle.

[0181] The heading angle determination device provided by the embodiments of the present invention can execute the heading angle determination method provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the method.

[0182] Embodiment 4

[0183] Figure 6FIG. 0 is a schematic structural diagram of an electronic device provided in Embodiment 4 of the present invention. The electronic device is intended to represent various forms of digital computers, such as, a laptop computer, a desktop computer, a workbench, a personal digital assistant, a server, a blade server, a mainframe computer, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as, a personal digital processor, a cellular phone, a smart phone, a wearable device (such as a helmet, glasses, a watch, etc.) and other similar computing devices. The electronic device can also be a vehicle with processing and computing capabilities. The components shown herein, their connections and relationships, and their functions are only examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0184] As Figure 6 shown, the electronic device 40 includes at least one processor 41, and a memory communicatively connected to the at least one processor 41, such as a read-only memory (ROM) 42, a random access memory (RAM) 43, etc. The memory stores a computer program executable by the at least one processor. The processor 41 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 42 or the computer program loaded from the storage unit 48 into the random access memory (RAM) 43. In the RAM 43, various programs and data required for the operation of the electronic device 40 can also be stored. The processor 41, the ROM 42, and the RAM 43 are connected to each other via a bus 44. An input / output (I / O) interface 45 is also connected to the bus 44.

[0185] Multiple components in the electronic device 40 are connected to the I / O interface 45, including: an input unit 46, such as a keyboard, a mouse, etc.; an output unit 47, such as various types of displays, speakers, etc.; a storage unit 48, such as a magnetic disk, an optical disk, etc.; and a communication unit 49, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 49 allows the electronic device 40 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0186] The processor 41 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the processor 41 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The processor 41 executes the various methods and processes described above, such as the heading angle determination method.

[0187] In some embodiments, the heading angle determination method may be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as storage unit 48. In some embodiments, part or all of the computer program may be loaded and / or installed onto the electronic device 40 via the ROM 42 and / or the communication unit 49. When the computer program is loaded into the RAM 43 and executed by the processor 41, one or more steps of the heading angle determination method described above may be performed. Alternatively, in other embodiments, the processor 41 may be configured to execute the heading angle determination method by any other suitable means (e.g., by means of firmware).

[0188] The various embodiments of the systems and techniques described above in this document may be implemented in digital electronic circuitry, integrated circuit systems, field-programmable gate arrays (FPGA), application specific integrated circuits (ASIC), application specific standard products (ASSP), systems-on-chip (SOC), complex programmable logic devices (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include: being implemented in one or more computer programs that may be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a special-purpose or general-purpose programmable processor that receives data and instructions from a storage system, at least one input device, and at least one output device, and transmits the data and instructions to the storage system, the at least one input device, and the at least one output device.

[0189] The computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The computer programs may be executed entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine, or entirely on the remote machine or server.

[0190] In the context of the present invention, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer-readable storage medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, the computer-readable storage medium can be a machine-readable signal medium. More specific examples of the machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, 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 disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0191] For providing 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 a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the electronic device. Other kinds 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, speech input, or tactile input).

[0192] The systems and techniques described herein can be implemented in a computing system that includes backend 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 frontend components (e.g., a user computer having a graphical user interface or a web browser through which the user can interact with an implementation of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend 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: local area network (LAN), wide area network (WAN), blockchain network, and the Internet.

[0193] A computing system may include a client and a server. The client and the server are generally far from each other and usually interact via a communication network. The client-server relationship is created by computer programs running on respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system, solving the defects of difficult management and weak business scalability existing in traditional physical hosts and VPS services.

[0194] It should be understood that various forms of the processes shown above can be used, with steps reordered, added, or deleted. For example, the steps recited in the present invention can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved, and no limitation is made herein.

[0195] The above specific embodiments do not constitute a limitation on the protection scope of the present invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for determining the heading angle, characterized in that Including: Obtain the radar information and driving information of the current vehicle, and determine the current track information based on the radar information and the driving information; Determine the first heading angle of the moving target relative to the current vehicle based on the driving information, the current track information, and the historical heading angle; If the moving target is in the oncoming lane of the current vehicle, determine the lane distance between the current vehicle and the oncoming lane, and determine the second heading angle based on the lane distance, the historical track of the current vehicle, and the driving information; If the current vehicle and the moving target meet the corresponding stop-and-go monitoring conditions, determine the third heading angle according to the historical track of the current vehicle and the driving information; Determine the fourth heading angle of the moving target relative to the current vehicle based on the driving information, radar information, and the current track information; Determine the target heading angle from the first heading angle, the second heading angle, the third heading angle, and the fourth heading angle based on the current driving scenario.

2. The method according to claim 1, characterized in that At least one radar is provided on the current vehicle. Correspondingly, the determining the first heading angle of the moving target relative to the current vehicle based on the driving information, the current track information, and the historical heading angle includes: For each radar, determine the intermediate heading angle of the moving target relative to the radar in the radar coordinate system based on the driving speed in the driving information and the relative speed in the current track information; Determine the difference between the historical heading angle and the intermediate heading angle, and determine the first weight of the intermediate heading angle and the second weight of the historical heading angle based on the difference; Determine the first heading angle according to the intermediate heading angle, the first weight, the historical heading angle, and the second weight.

3. The method according to claim 1, wherein The if the moving target is in the oncoming lane of the current vehicle, determining the lane distance between the current vehicle and the oncoming lane includes: If the residence duration and relative distance in the current track information meet the first condition and the relative speed meets the second condition, determine that the moving target is in the oncoming lane of the current vehicle; When the moving target in the oncoming lane of the current vehicle meets the lane distance determination condition, determine the lane distance between the current vehicle and the oncoming lane based on the relative distance in the current track information.

4. The method according to claim 1, wherein The determining the second heading angle based on the lane distance, the historical track of the current vehicle, and the driving information includes: Fit the historical track of the current vehicle to form the track equation of the current vehicle; Determine the reference lateral relative distance according to the longitudinal relative distance in the driving information and the track equation; Determine the first lateral relative distance according to the reference lateral relative distance and the lane distance, and determine the second heading angle of the moving target relative to the current vehicle based on the longitudinal relative distance and the first lateral relative distance.

5. The method according to claim 1, wherein The stop-and-go monitoring conditions include: the driving speed in the driving information of the current vehicle is within a set range; determining that the moving target is a stationary object based on the residence duration and track number in the current track information; the moving target is in the same lane as the current vehicle; Correspondingly, if the current vehicle and the moving target meet the corresponding stop-and-go monitoring conditions, determining a third heading angle according to the historical trajectory of the current vehicle and the driving information includes: If the current vehicle and the moving target meet the corresponding stop-and-go monitoring conditions, fitting the historical trajectory of the current vehicle to form a trajectory equation of the current vehicle; Determining a second lateral relative distance according to the longitudinal relative distance in the driving information and the trajectory equation, and determining a third heading angle of the moving target relative to the current vehicle based on the longitudinal relative distance and the second lateral relative distance.

6. The method according to claim 1, wherein Determining a fourth heading angle of the moving target relative to the current vehicle based on the driving information, radar information, and the current track information includes: If the residence duration in the current track information meets a set trigger condition, determining first anchor point information and second anchor point information of the moving target relative to the current vehicle, and storing the first anchor point information and the second anchor point information; Correcting the first anchor point information and the second anchor point information according to the driving information and the radar information to obtain corrected first anchor point information and second anchor point information; Determining a first lateral displacement and a first longitudinal displacement of the moving target relative to the current vehicle according to the corrected first anchor point information and the relative distance in the current track information. If any of the first lateral displacement and the first longitudinal displacement meets a first displacement condition, determining a fourth heading angle of the moving target relative to the current vehicle according to the relative distance and the first anchor point information; Determining a second lateral displacement, a second longitudinal displacement, and a total displacement of the moving target relative to the current vehicle according to the corrected second anchor point information and the relative distance. If any of the second lateral displacement, the second longitudinal displacement, and the total displacement meets a second displacement condition, assigning the second anchor point information to the first anchor point information, assigning the relative distance to the second anchor point information, and returning to re-execute the determination of the fourth heading angle.

7. The method according to claim 6, characterized in that, It further includes: If the relative speed in the current track information meets a round-trip movement condition, determining third anchor point information of the moving target; Determining a third lateral displacement and a third longitudinal displacement of the moving target relative to the current vehicle according to the third anchor point information and the relative distance. If any of the third lateral displacement and the third longitudinal displacement meets a third displacement condition, determining that the moving target has a U-turn behavior and setting the fourth heading angle to invalid; If the third displacement condition is met for a continuous set number of times, clearing the first anchor point information and the second anchor point information.

8. The method according to claim 1, wherein Determining a target heading angle from the first heading angle, the second heading angle, the third heading angle, and the fourth heading angle based on the current driving scenario includes: If the moving target is located in the oncoming lane of the current vehicle, determining that the current driving scenario is an oncoming driving scenario and determining the second heading angle as the target heading angle; If the current vehicle and the moving target meet the corresponding stop-and-go monitoring conditions, determining that the current driving scenario is a stop-and-go scenario and determining the third heading angle as the target heading angle; If the current is in other scenarios except the oncoming driving scenario and the stop-and-go scenario, determine the heading angle difference between the first heading angle and the fourth heading angle; If the heading angle difference is less than the difference threshold, determine the first heading angle as the target heading angle; otherwise, determine the fourth heading angle as the target heading angle.

9. A heading angle determination device, characterized in that, Comprising: A trajectory information determination unit, configured to obtain radar information and driving information of the current vehicle, and determine the current trajectory information based on the radar information and the driving information; A first heading angle determination unit, configured to determine a first heading angle of a moving target relative to the current vehicle based on the driving information, the current trajectory information, and the historical heading angle; A second heading angle determination unit, configured to, if the moving target is located in the oncoming lane of the current vehicle, determine the lane distance between the current vehicle and the oncoming lane, and determine a second heading angle based on the lane distance, the historical trajectory of the current vehicle, and the driving information; A third heading angle determination unit, configured to, if the current vehicle and the moving target meet the corresponding stop-and-go monitoring conditions, determine a third heading angle according to the historical trajectory of the current vehicle and the driving information; A fourth heading angle determination unit, configured to determine a fourth heading angle of the moving target relative to the current vehicle based on the driving information, radar information, and the current trajectory information; A target heading angle determination unit, configured to determine a target heading angle from the first heading angle, the second heading angle, the third heading angle, and the fourth heading angle based on the current driving scenario.

10. An electronic device, characterized in that, Comprising: 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 that the at least one processor can execute a heading angle determination method according to any one of claims 1-8.

11. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing a processor to implement a heading angle determination method according to any one of claims 1-8 when executed.

12. A computer program product, characterized in that, The computer program product includes a computer program that implements a heading angle determination method according to any one of claims 1-8 when executed by a processor.

Images