AEB mistaken touch prevention method, device and equipment and computer readable storage medium
By predicting the overlapping area of the vehicle's and the target object's trajectories, the problem of false triggering of AEB in vehicle turning scenarios is solved, improving the accuracy and safety of the system.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- VOYAH AUTOMOBILE TECH CO LTD
- Filing Date
- 2026-01-30
- Publication Date
- 2026-04-28
AI Technical Summary
In situations where a vehicle is turning, traditional AEB systems are prone to misjudgment and triggering, leading to unnecessary emergency braking, affecting driving comfort, and potentially causing secondary accidents.
By predicting the future trajectories of the vehicle and the target object, it determines whether their outlines overlap and calculates the overlap area. AEB is activated only when the overlap area is large enough and time is of the essence.
This improves the accuracy of the AEB system, reduces false alarms in low-risk situations, and ensures that emergency braking is activated only in high-risk collision scenarios, thus guaranteeing safety.
Smart Images
Figure CN121929150A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of vehicle active safety control technology, specifically to an AEB (Autonomous Emergency Braking) anti-accidental activation method, device, equipment, and computer-readable storage medium. Background Technology
[0002] With the development of vehicle intelligence, Automatic Emergency Braking (AEB) has become an important active safety feature. Its core function is to assess the collision risk between the vehicle and obstacles ahead (including other vehicles and pedestrians) in real time, and automatically apply emergency braking when the risk is extremely high to avoid or mitigate a collision.
[0003] However, in turning scenarios, due to the complex relative motion between the vehicle and the target object (such as a pedestrian), traditional risk assessment models based on relative distance and speed are prone to misjudgment. This can lead to situations where there is no actual high risk being misjudged as requiring emergency braking, thus triggering AEB (Autonomous Emergency Braking) falsely. False triggering not only affects driving comfort but may also cause rear-end collisions due to sudden improper braking, resulting in secondary accidents. Summary of the Invention
[0004] This application provides a method, device, equipment, and computer-readable storage medium for preventing accidental AEB activation, which can solve the technical problem that AEB is easily triggered accidentally in vehicle turning scenarios in the prior art.
[0005] In a first aspect, embodiments of this application provide an AEB (Automatic Emergency Braking) method for preventing accidental touches, the AEB method comprising:
[0006] Based on the first motion state parameters of the vehicle at the initial moment and the geometric dimension information of the vehicle, the first prediction information is obtained. The first prediction information includes the motion trajectory of multiple corner points of the first shape used to characterize the shape of the vehicle in the future time period. Based on the second motion state parameters of the target object at the initial moment and the geometric size information of the target object, the second prediction information is obtained. The second prediction information includes the motion trajectory of multiple corner points of the second shape used to characterize the shape of the target object in the future time period. Based on the first prediction information and the second prediction information, it is detected whether there is a target time point, wherein the time difference between the target time point and the initial time is less than a preset time difference, and the overlapping area of the first shape and the second shape at the target time point is greater than a preset area. If a target time point exists, the AEB (Automatic Emergency Braking) system will be activated.
[0007] In conjunction with the first aspect, in one implementation, the future time period includes multiple time points, and obtaining the first prediction information based on the vehicle's first motion state parameters at the initial moment and the vehicle's geometric dimensions includes: Based on the vehicle's first motion state parameters at the initial moment and the circular kinematics model, the coordinates of the vehicle's reference point at each time point are obtained. The first motion state parameters include the vehicle's speed and yaw rate. Based on the vehicle's geometric dimensions and the coordinates of the vehicle's reference point at each time point, the coordinates of multiple corner points representing the first shape of the vehicle's exterior at each time point are obtained.
[0008] In conjunction with the first aspect, in one implementation, obtaining the second prediction information based on the second motion state parameters of the target object at the initial moment and the geometric dimension information of the target object includes: Based on the second motion state parameters of the target object at the initial moment and the linear kinematic model, the coordinates of the target object reference point at each time point are obtained. The second motion state parameters include the target object velocity and the target object acceleration. Based on the geometric dimensions of the target object and the coordinates of the target object's reference point at each time point, the coordinates of multiple corner points of the second shape used to characterize the target object's shape at each time point are obtained.
[0009] In conjunction with the first aspect, in one implementation, detecting the existence of a target time point based on the first prediction information and the second prediction information includes: Based on the first and second prediction information, each time point where the time difference from the initial time is less than a preset time difference is determined. When, the total number of edges that intersect each edge of the second shape with each edge of the first shape. And the number of corner points of the second shape that are located within the first shape. ; like Greater than the first preset value and / or If it is greater than the second preset value, then confirm. The overlapping area of the first shape and the second shape ; like If the area is greater than the preset area, then confirm. The target time point.
[0010] In conjunction with the first aspect, in one implementation, each time point where the time difference from the initial time is less than a preset time difference is determined. When, the total number of edges that intersect each edge of the second shape with each edge of the first shape. include: For any one of the multiple edges included in the first shape, based on each time point where the time difference from the initial time is less than a preset time difference... At that time, the coordinates of the two corner points corresponding to any one edge and the coordinates of multiple corner points of the second shape are used to detect whether each edge included in the second shape intersects with any one edge; If a target edge intersects with any of the edges, then based on the coordinates of the two corner points corresponding to the edge and the two corner points corresponding to the target edge, it is detected whether the intersection point is located on the target edge and the edge. If the intersection point is located on the target edge and any of the edges, then... The value increases by 1, where The initial value is zero; By repeating this process, we can iterate through all the edges included in the first shape to obtain... Time corresponding The value of .
[0011] In conjunction with the first aspect, in one implementation, each time point where the time difference from the initial time is less than a preset time difference is determined. At that time, the number of corner points of the second shape that are located within the first shape. include: For any corner point among the multiple corner points included in the second shape, based on each time point where the time difference from the initial time is less than a preset time difference... At that time, the coordinates of any corner point and the coordinates of multiple corner points of the first shape are used to detect whether any corner point is within the first shape; If it is within the first shape, then The value increases by 1, where The initial value is zero; By repeating this process, we can iterate through all the corner points included in the second shape to obtain... Time corresponding The value of .
[0012] In conjunction with the first aspect, in one implementation method, it is determined that in When, the overlapping area of the first shape and the second shape include: According to When the coordinates of multiple corner points of the first shape are used, the first bounding rectangle of the first shape is determined. According to When the coordinates of multiple corner points of the second shape are used, the second bounding rectangle of the second shape is determined. The overlapping area is obtained by using the coordinates of the four corner points of the first circumscribed rectangle and the four corner points of the second circumscribed rectangle. .
[0013] Secondly, embodiments of this application provide an AEB (Automatic Emergency Braking) anti-accidental touch device, the AEB anti-accidental touch device comprising: The prediction module is used to obtain first prediction information based on the first motion state parameters of the vehicle at the initial moment and the geometric size information of the vehicle. The first prediction information includes the motion trajectory of multiple corner points of a first shape used to characterize the shape of the vehicle in the future time period. Based on the second motion state parameters of the target object at the initial moment and the geometric size information of the target object, the second prediction information is obtained. The second prediction information includes the motion trajectory of multiple corner points of the second shape used to characterize the shape of the target object in the future time period. The detection module is used to detect whether a target time point exists based on the first prediction information and the second prediction information, wherein the time difference between the target time point and the initial time is less than a preset time difference, and the overlapping area of the first shape and the second shape at the target time point is greater than a preset area. The activation module is used to activate the AEB automatic emergency braking system if a target time point exists.
[0014] Thirdly, embodiments of this application provide an AEB anti-accidental touch device, the AEB anti-accidental touch device including a processor, a memory, and an AEB anti-accidental touch program stored in the memory and executable by the processor, wherein when the AEB anti-accidental touch program is executed by the processor, it implements the steps of the AEB anti-accidental touch method as described in the first aspect.
[0015] Fourthly, embodiments of this application provide a computer-readable storage medium storing an AEB (Avoidance of Errors) anti-accidental touch program, wherein when the AEB anti-accidental touch program is executed by a processor, it implements the steps of the AEB anti-accidental touch method as described in the first aspect.
[0016] The beneficial effects of the technical solutions provided in this application include: In this embodiment, both the vehicle and the target object are considered as entities with specific dimensions, and their trajectories are predicted over a future period. By determining whether the predicted trajectories overlap and further calculating the area of the overlap, the collision risk is upgraded from a binary judgment of "whether it will happen" to a quantitative assessment including "probability of occurrence" and "severity of collision." Ultimately, AEB is activated only when the predicted overlap area is large enough and the collision time is imminent. This filters out a large number of low-risk false alarms caused by slight trajectories overlapping, ensuring that AEB is only activated when the collision certainty is high and the consequences are severe. Attached Figure Description
[0017] Figure 1 This is a flowchart illustrating an embodiment of the AEB anti-accidental touch method of this application; Figure 2This is a schematic diagram of vehicle trajectory prediction in one embodiment; Figure 3 This is a schematic diagram of collision risk identification in one embodiment; Figure 4 This is a schematic projection of the first shape and the second shape in one embodiment; Figure 5 This is a functional module diagram of an embodiment of the AEB anti-accidental touch device of this application; Figure 6 This is a schematic diagram of the hardware structure of the AEB anti-accidental touch device involved in the embodiments of this application. Detailed Implementation
[0018] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present application.
[0019] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.
[0020] Firstly, embodiments of this application provide an AEB (Automatic Electronic Control System) anti-accidental touch method.
[0021] In one embodiment, reference is made to Figure 1 , Figure 1 This is a flowchart illustrating an embodiment of the AEB (Avoidance of Electronic Touch) method for preventing accidental touches according to this application. Figure 1 As shown, the AEB (Automatic Emergency Braking) anti-accidental touch methods include: Step S10: Based on the first motion state parameters of the vehicle at the initial moment and the geometric dimension information of the vehicle, obtain the first prediction information. The first prediction information includes the motion trajectory of multiple corner points used to characterize the shape of the vehicle in the future time period. Step S20: Based on the second motion state parameters of the target object at the initial moment and the geometric size information of the target object, obtain the second prediction information. The second prediction information includes the motion trajectory of multiple corner points of the second shape used to characterize the shape of the target object in the future time period. In this embodiment, the AEB (Autonomous Emergency Braking) anti-accidental touch method is executed by the vehicle's electronic control unit (ECU) or a dedicated autonomous driving domain controller, which periodically executes steps S10 to S40. The start time of each cycle is the initial time. The future time period refers to a period of time after the initial time, such as 3 seconds. That is, the executing entity repeats steps S10 to S40 in a 3-second cycle. For example, if the initial time is 8:00:00, then the future time period is 8:00:00 to 8:00:03; the next cycle begins at 8:00:03, and if the initial time is 8:00:03, then the future time period is 8:00:03 to 8:00:06, and so on.
[0022] The duration of a future time period can also be determined based on the actual vehicle speed, for example, it may be negatively correlated with the actual vehicle speed. For instance, if the initial time is 8:00:00 and the actual vehicle speed is 15 km / h, then the future time period is 8:00:00~8:00:03; if the next cycle begins at 8:00:03 and the actual vehicle speed is 35 km / h, then the future time period is 8:00:03~8:00:05; and so on.
[0023] In each prediction cycle, both the vehicle and the target object are treated as entities with specific dimensions. Specifically, the vehicle's shape is represented by a first shape based on its external features; and the target object's shape is represented by a second shape based on its external features. The target object refers to traffic participants, such as other vehicles and pedestrians.
[0024] In each prediction cycle, a reference point is selected for both the vehicle and the target object. Based on the kinematic characteristics of the vehicle and the target object, the motion trajectory of the reference point is predicted using the corresponding kinematic model. Based on the vehicle's geometric dimensions, the relative positional relationship between the vehicle's reference point and each corner point of the first shape is determined. Thus, the motion trajectory of each corner point of the first shape is obtained by combining the motion trajectory of the vehicle's reference point. Similarly, based on the target object's geometric dimensions, the relative positional relationship between the target object's reference point and each corner point of the second shape is determined. Thus, the motion trajectory of each corner point of the second shape is obtained by combining the motion trajectory of the target object's reference point.
[0025] The first motion state parameter includes the parameters required for the kinematics model corresponding to the vehicle; similarly, the second motion state parameter includes the parameters required for the kinematics model corresponding to the target object.
[0026] Furthermore, in one embodiment, the future time period includes multiple time points, and step S10 includes: Based on the vehicle's first motion state parameters at the initial moment and the circular kinematics model, the coordinates of the vehicle's reference point at each time point are obtained. The first motion state parameters include the vehicle's speed and yaw rate. Based on the vehicle's geometric dimensions and the coordinates of the vehicle's reference point at each time point, the coordinates of multiple corner points representing the first shape of the vehicle's exterior at each time point are obtained.
[0027] In this embodiment, assuming the future time period is 1.5 seconds, and it is divided into time intervals of 0.05 seconds, the future time period includes 30 time points, denoted as follows: to ,in, The time interval from the initial time is 0.05s. i. To facilitate the explanation of the subsequent calculation process, let , , And so on.
[0028] In the scenario of a vehicle turning, from a kinematic perspective, the vehicle can be considered to be undergoing uniform circular motion. Therefore, based on the vehicle's initial speed... and the yaw rate of the vehicle By combining the circular kinematics model, the coordinates of the vehicle's reference point at each time point are obtained.
[0029] Reference Figure 2 , Figure 2 This is a schematic diagram illustrating the prediction of a vehicle's motion trajectory in one embodiment. For example... Figure 2 As shown, a rectangular coordinate system is established with the center of the rear axle of the vehicle at the initial moment as the origin, the forward direction of the vehicle as the positive X-axis, and the driver's left hand as the positive Y-axis; the center O of the rear axle of the vehicle is taken as the reference point of the vehicle. O' is... From the center of the rear axle of the vehicle, from the initial moment to At what moment, the arc length traveled by the vehicle is The yaw angle is ,but Coordinates of time O' , )for:
[0030]
[0031] exist Figure 2 In the example shown, the first shape used to characterize the vehicle's exterior is a rectangle, meaning it needs to be based on the vehicle's reference point. The coordinates of the moment are combined with the vehicle's geometric dimensions (including the vehicle's length). and vehicle width ), to obtain the four corner points of the rectangle ( Figure 2 Points A, B, C, and D in the middle) The coordinates of time. The conversion process is illustrated below: First, based on Coordinates of time O' , ) and the length of the vehicle, to obtain the center point E of the first shape. Coordinates of time ( , ),in:
[0032]
[0033] Then, the offsets of the four corner points relative to the center point E in the X and Y axes are obtained using the rotation matrix:
[0034]
[0035]
[0036]
[0037]
[0038]
[0039]
[0040]
[0041] in, Let A be the offset of point A relative to center point E in the X-axis direction. This represents the offset of point A relative to the center point E along the Y-axis. Let B be the offset of point B relative to center point E in the X-axis direction. This represents the offset of point B relative to the center point E along the Y-axis. And so on, without further explanation.
[0042] Point A is at Coordinates of time ( , ),in:
[0043]
[0044] Similarly, we can obtain the positions of points B, C, and D. The coordinates at each time point are obtained, that is, the coordinates of multiple corner points used to characterize the first shape of the vehicle's exterior at each time point.
[0045] It should be noted that the use of a rectangle as the primary shape representing the vehicle's exterior is merely illustrative. Depending on the exterior characteristics of different vehicles, an appropriate shape can be flexibly selected as the primary shape.
[0046] Further, in one embodiment, step S20 includes: Based on the second motion state parameters of the target object at the initial moment and the linear kinematic model, the coordinates of the target object reference point at each time point are obtained. The second motion state parameters include the target object velocity and the target object acceleration. Based on the geometric dimensions of the target object and the coordinates of the target object's reference point at each time point, the coordinates of multiple corner points of the second shape used to characterize the target object's shape at each time point are obtained.
[0047] In this embodiment, the motion of the target object is considered as linear motion. First, the coordinates of the target object's reference point at the initial moment are determined ( , (Using the same coordinate system as the vehicle's trajectory prediction), and the lateral velocity of the target object. Longitudinal velocity lateral acceleration and longitudinal acceleration .
[0048] The target reference point is at Coordinates of time ( , ),in:
[0049]
[0050] Based on this, combined The offset of each corner point of the second shape relative to the target reference point at time t is used to obtain the position of each corner point of the second shape at time t. The coordinates of the moment. For the specific process, refer to determining the corner points of the first shape. An example of time coordinates.
[0051] Step S30: Based on the first prediction information and the second prediction information, detect whether there is a target time point, wherein the time difference between the target time point and the initial time is less than a preset time difference, and the overlapping area of the first shape and the second shape at the target time point is greater than a preset area. In this embodiment, the duration of the future time period can be limited so that the time difference between the multiple time points included in the future time period and the initial time is less than a preset time difference.
[0052] As described above, the motion trajectories of multiple corner points of the first shape and multiple corner points of the second shape at each time point in the future time period are predicted. Based on this, the positions of the first and second shapes at each time point in the same coordinate system can be determined, thereby detecting whether the first and second shapes overlap and whether the overlapping area is greater than a preset area.
[0053] Further, in one embodiment, step S30 includes: Step S301: Based on the first prediction information and the second prediction information, determine each time point where the time difference from the initial time is less than a preset time difference. When, the total number of edges that intersect each edge of the second shape with each edge of the first shape. And the number of corner points of the second shape that are located within the first shape. ; In this embodiment, based on the coordinates of the first shape and the corner points of the second shape at each predicted time point, combined with geometric analysis, the following can be determined: The value and The value of .
[0054] Further, in one embodiment, step S301 includes: Step S3011: For any one of the multiple edges included in the first shape, based on each time point where the time difference from the initial time is less than a preset time difference... At that time, the coordinates of the two corner points corresponding to any one edge and the coordinates of multiple corner points of the second shape are used to detect whether each edge included in the second shape intersects with any one edge; In this embodiment, refer to Figure 3 , Figure 3 This is a schematic diagram illustrating collision risk identification in one embodiment. For example... Figure 3 As shown, for ease of explanation, both the first and second shapes are represented by rectangles. The first shape includes four corner points A, B, C, and D, and the second shape includes four corner points a, b, c, and d. When, the coordinates of A, B, C, and D are respectively denoted as ( , ), ( , ), ( , )as well as( , );exist When, the coordinates of a, b, c, and d are respectively denoted as ( , ), ( , ), ( , )as well as( , ).
[0055] like Figure 3 As shown, the first shape includes sides AB, BC, CD and DA, and the second shape includes sides ab, bc, cd and da.
[0056] Taking CD as an example, first check if CD intersects with ab, bc, cd, and da. For example, to check if CD intersects with ab: First calculate the intersection characterization value ,in:
[0057] like Less than If the result is negative, it means that CD does not intersect with ab, and the next round of testing is performed, for example, checking whether CD intersects with bc; if... Not less than This indicates that CD intersects with ab. This is the preset minimum value.
[0058] Step S3012: If there is a target edge that intersects with any of the edges, then based on the coordinates of the two corner points corresponding to the any of the edges and the coordinates of the two corner points corresponding to the target edge, detect whether the intersection point is located on the target edge and the any of the edges. Step S3013: If the intersection point is located on the target edge and any one of the edges, then... The value increases by 1, where The initial value is zero; In this embodiment, based on the above example, if CD intersects with ab, it is necessary to further determine whether the intersection point lies on CD and ab. The method is as follows:
[0059]
[0060] like ,and If the intersection point is determined to be on CD and ab, then... The value increases by 1.
[0061] Similarly, if an intersection of CD and bc is detected, it is necessary to determine whether the intersection point lies on CD and bc. If the intersection point lies on CD and bc, then... The value is increased by 1.
[0062] By repeating this process, we can iterate through all the edges included in the first shape to obtain... Time corresponding The value of .
[0063] Furthermore, in one embodiment, step S301 further includes: For any corner point among the multiple corner points included in the second shape, based on each time point where the time difference from the initial time is less than a preset time difference... At that time, the coordinates of any corner point and the coordinates of multiple corner points of the first shape are used to detect whether any corner point is within the first shape; If it is within the first shape, then The value increases by 1, where The initial value is zero; By repeating this process, we can iterate through all the corner points included in the second shape to obtain... Time corresponding The value of .
[0064] In this embodiment, we continue to refer to... Figure 3 ,like Figure 3 As shown, the second shape includes four points: a, b, c, and d. For example, to determine whether point a is within the first shape, the specific method is as follows:
[0065]
[0066]
[0067]
[0068] like ,and Then point a is determined to be within the first shape, thus making The value increases by 1; if this condition is not met, then point a is determined to be outside the first shape, and therefore no... The value is increased.
[0069] Similarly, the same method is used to determine whether other points (b, c, d) are within the first shape, which will not be elaborated here.
[0070] Step S302, if Greater than the first preset value and / or If it is greater than the second preset value, then confirm. The overlapping area of the first shape and the second shape ; In this embodiment, we continue to refer to... Figure 3 Based on the foregoing explanation, it can be determined that , Assuming the first preset value is 1 and the second preset value is 0, then the following condition is met: Greater than the first preset value and / or If the value is greater than the second preset value, it indicates that the vehicle and the target object are in close proximity. If a collision is possible, the severity of the collision will be further assessed to determine its extent. The overlapping area of the first shape and the second shape Combining Figure 3 In the scenario shown, we can first determine the coordinates of the intersection of DC and ab, and the coordinates of the intersection of DC and bc, and then combine these with the coordinates of point b to obtain the result. The overlapping area of the first shape and the second shape .
[0071] Further, in one embodiment, step S302 includes: According to When the coordinates of multiple corner points of the first shape are used, the first bounding rectangle of the first shape is determined. According to When the coordinates of multiple corner points of the second shape are used, the second bounding rectangle of the second shape is determined. The overlapping area is obtained by using the coordinates of the four corner points of the first circumscribed rectangle and the four corner points of the second circumscribed rectangle. .
[0072] In this embodiment, the first shape is projected onto the X-axis and Y-axis, where the horizontal coordinate of the projection is the maximum value of the horizontal coordinates of multiple corner points of the first shape. and minimum value The ordinate of the projection is the maximum value of the ordinates of multiple corner points of the first shape. and minimum value Then the coordinates of the four corner points of the first circumscribed rectangle are respectively ( ). , ), ( , ), ( , )as well as( , Similarly, the second shape is projected onto the X and Y axes, where the projected x-coordinate is the maximum value of the x-coordinates of multiple corner points of the second shape. and minimum value The ordinate of the projection is the maximum value of the ordinates of multiple corner points of the second shape. and minimum value Then the coordinates of the four corner points of the second circumscribed rectangle are respectively ( ). , ), ( , ), ( , )as well as( , ).
[0073] Reference Figure 4 , Figure 4 This is a schematic projection of the first and second shapes in one embodiment. For example... Figure 4 As shown, the red box represents the first bounding rectangle of the first shape, and the green box represents the second bounding rectangle of the second shape.
[0074] After determining the coordinates of each corner point of the first and second bounding rectangles, the overlapping area can be obtained. The solution process is as follows:
[0075]
[0076]
[0077]
[0078] in, and These represent taking the minimum value and taking the maximum value, respectively.
[0079]
[0080]
[0081]
[0082] At this point, the overlapping area can be obtained. .
[0083] Step S303, if If the area is greater than the preset area, then confirm. The target time point.
[0084] In this embodiment, the preset area is set based on actual needs. If the area is larger than the preset area, it means that... The vehicle will collide with the target object, and the collision area will be relatively large.
[0085] Step S40: If a target time point exists, activate the AEB automatic emergency braking system.
[0086] In this embodiment, based on the above determination, if a target time point exists, it means that the vehicle will collide with the target object in a short period of time, and the collision area is large. In this case, AEB is activated to avoid or mitigate the collision.
[0087] In this embodiment, both the vehicle and the target object are considered as entities with specific dimensions, and their trajectories are predicted over a future period. By determining whether the predicted trajectories overlap and further calculating the area of the overlap, the collision risk is upgraded from a binary judgment of "whether it will happen" to a quantitative assessment including "probability of occurrence" and "severity of collision." Ultimately, AEB is activated only when the predicted overlap area is large enough and the collision time is imminent. This filters out a large number of low-risk false alarms caused by slight trajectories overlapping, ensuring that AEB is only activated when the collision certainty is high and the consequences are severe.
[0088] Secondly, embodiments of this application also provide an AEB anti-accidental touch device.
[0089] In one embodiment, reference is made to Figure 5 , Figure 5 This is a functional module diagram of an embodiment of the AEB anti-accidental touch device of this application. Figure 5 As shown, the AEB anti-accidental touch device includes: The prediction module 10 is used to obtain first prediction information based on the first motion state parameters of the vehicle at the initial moment and the geometric size information of the vehicle. The first prediction information includes the motion trajectory of multiple corner points of a first shape used to characterize the shape of the vehicle in the future time period. Based on the second motion state parameters of the target object at the initial moment and the geometric size information of the target object, the second prediction information is obtained. The second prediction information includes the motion trajectory of multiple corner points of the second shape used to characterize the shape of the target object in the future time period. The detection module 20 is used to detect whether a target time point exists based on the first prediction information and the second prediction information, wherein the time difference between the target time point and the initial time is less than a preset time difference, and the overlapping area of the first shape and the second shape at the target time point is greater than a preset area. Activation module 30 is used to activate the AEB automatic emergency braking system if a target time point exists.
[0090] Furthermore, in one embodiment, the future time period includes multiple time points, and the prediction module 10 is used to: Based on the vehicle's first motion state parameters at the initial moment and the circular kinematics model, the coordinates of the vehicle's reference point at each time point are obtained. The first motion state parameters include the vehicle's speed and yaw rate. Based on the vehicle's geometric dimensions and the coordinates of the vehicle's reference point at each time point, the coordinates of multiple corner points representing the first shape of the vehicle's exterior at each time point are obtained.
[0091] Furthermore, in one embodiment, the prediction module 10 is used for: Based on the second motion state parameters of the target object at the initial moment and the linear kinematic model, the coordinates of the target object reference point at each time point are obtained. The second motion state parameters include the target object velocity and the target object acceleration. Based on the geometric dimensions of the target object and the coordinates of the target object's reference point at each time point, the coordinates of multiple corner points of the second shape used to characterize the target object's shape at each time point are obtained.
[0092] Furthermore, in one embodiment, the detection module 20 is used for: Based on the first and second prediction information, each time point where the time difference from the initial time is less than a preset time difference is determined. When, the total number of edges that intersect each edge of the second shape with each edge of the first shape. And the number of corner points of the second shape that are located within the first shape. ; like Greater than the first preset value and / or If it is greater than the second preset value, then confirm. The overlapping area of the first shape and the second shape ; like If the area is greater than the preset area, then confirm. The target time point.
[0093] Furthermore, in one embodiment, the detection module 20 is used for: For any one of the multiple edges included in the first shape, based on each time point where the time difference from the initial time is less than a preset time difference... At that time, the coordinates of the two corner points corresponding to any one edge and the coordinates of multiple corner points of the second shape are used to detect whether each edge included in the second shape intersects with any one edge; If a target edge intersects with any of the edges, then based on the coordinates of the two corner points corresponding to the edge and the two corner points corresponding to the target edge, it is detected whether the intersection point is located on the target edge and the edge. If the intersection point is located on the target edge and any of the edges, then... The value increases by 1, where The initial value is zero; By repeating this process, we can iterate through all the edges included in the first shape to obtain... Time corresponding The value of .
[0094] Furthermore, in one embodiment, the detection module 20 is used for: For any corner point among the multiple corner points included in the second shape, based on each time point where the time difference from the initial time is less than a preset time difference... At that time, the coordinates of any corner point and the coordinates of multiple corner points of the first shape are used to detect whether any corner point is within the first shape; If it is within the first shape, then The value increases by 1, where The initial value is zero; By repeating this process, we can iterate through all the corner points included in the second shape to obtain... Time corresponding The value of .
[0095] Furthermore, in one embodiment, the detection module 20 is used for: According to When the coordinates of multiple corner points of the first shape are used, the first bounding rectangle of the first shape is determined. According to When the coordinates of multiple corner points of the second shape are used, the second bounding rectangle of the second shape is determined. The overlapping area is obtained by using the coordinates of the four corner points of the first circumscribed rectangle and the four corner points of the second circumscribed rectangle. .
[0096] The functions of each module in the AEB anti-accidental touch device correspond to the steps in the AEB anti-accidental touch method embodiment, and their functions and implementation processes will not be described in detail here.
[0097] Thirdly, this application provides an AEB anti-accidental touch device, which can be an electronic control unit (ECU) or an autonomous driving domain controller or other device with data processing functions.
[0098] Reference Figure 6 , Figure 6 This is a schematic diagram of the hardware structure of the AEB (Automatic Emergency Braking) anti-accidental touch device involved in the embodiments of this application. In the embodiments of this application, the AEB anti-accidental touch device may include a processor, a memory, a communication interface, and a communication bus.
[0099] The communication bus can be of any type and is used to interconnect the processor, memory, and communication interface.
[0100] The communication interface includes input / output (I / O) interfaces, physical interfaces, and logical interfaces used for interconnecting internal components of the AEB (Automatic Emergency Braking) anti-misoperation device, as well as interfaces used for interconnecting the AEB anti-misoperation device with other devices (such as other computing devices or user equipment). Physical interfaces can be Ethernet interfaces, fiber optic interfaces, ATM interfaces, etc.; user equipment can be displays, keyboards, etc.
[0101] Memory can be various types of storage media, such as random access memory (RAM), read-only memory (ROM), non-volatile RAM (NVRAM), flash memory, optical storage, hard disk, programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), etc.
[0102] The processor can be a general-purpose processor, which can call the AEB anti-mistouch program stored in the memory and execute the AEB anti-mistouch method provided in the embodiments of this application. For example, the general-purpose processor can be a central processing unit (CPU). The method executed when the AEB anti-mistouch program is called can be referred to in the various embodiments of the AEB anti-mistouch method of this application, and will not be repeated here.
[0103] Those skilled in the art will understand that Figure 6 The hardware structure shown does not constitute a limitation of this application and may include more or fewer components than shown, or combine certain components, or have different component arrangements.
[0104] Fourthly, embodiments of this application also provide a computer-readable storage medium.
[0105] The present application has a computer-readable storage medium storing an AEB anti-accidental touch program, wherein when the AEB anti-accidental touch program is executed by a processor, it implements the steps of the AEB anti-accidental touch method as described above.
[0106] The method implemented when the AEB anti-accidental touch procedure is executed can be referred to in various embodiments of the AEB anti-accidental touch method of this application, and will not be repeated here.
[0107] It should be noted that the sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.
[0108] The terms "comprising" and "having," and any variations thereof, in the specification, claims, and accompanying drawings of this application are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to such process, method, product, or apparatus. The terms "first," "second," and "third," etc., are used to distinguish different objects, etc., and do not indicate a sequence, nor do they limit "first," "second," and "third" to different types.
[0109] In the description of the embodiments of this application, terms such as "exemplary," "for example," or "for instance" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as "exemplary," "for example," or "for instance" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of terms such as "exemplary," "for example," or "for instance" is intended to present the relevant concepts in a concrete manner.
[0110] In the description of the embodiments of this application, unless otherwise stated, " / " means "or". For example, A / B can mean A or B. The "and / or" in the text is merely a description of the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist simultaneously, and B exists alone. In addition, in the description of the embodiments of this application, "multiple" means two or more.
[0111] In some processes described in the embodiments of this application, multiple operations or steps are included in a specific order. However, it should be understood that these operations or steps may not be executed in the order they appear in the embodiments of this application, or they may be executed in parallel. The sequence number of the operation is only used to distinguish different operations, and the sequence number itself does not represent any execution order. In addition, these processes may include more or fewer operations, and these operations or steps may be executed sequentially or in parallel, and these operations or steps may be combined.
[0112] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes several instructions to cause a terminal device to execute the methods described in the various embodiments of this application.
[0113] The above are merely preferred embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.
Claims
1. A method for preventing accidental touches by auto-traffic alert (AEB), characterized in that, The AEB anti-accidental touch method includes: Based on the first motion state parameters of the vehicle at the initial moment and the geometric dimension information of the vehicle, the first prediction information is obtained. The first prediction information includes the motion trajectory of multiple corner points of the first shape used to characterize the shape of the vehicle in the future time period. Based on the second motion state parameters of the target object at the initial moment and the geometric size information of the target object, the second prediction information is obtained. The second prediction information includes the motion trajectory of multiple corner points of the second shape used to characterize the shape of the target object in the future time period. Based on the first prediction information and the second prediction information, it is detected whether there is a target time point, wherein the time difference between the target time point and the initial time is less than a preset time difference, and the overlapping area of the first shape and the second shape at the target time point is greater than a preset area. If a target time point exists, the AEB (Automatic Emergency Braking) system will be activated.
2. The AEB anti-accidental touch method as described in claim 1, characterized in that, The future time period includes multiple time points. The first prediction information obtained based on the vehicle's first motion state parameters at the initial moment and the vehicle's geometric dimensions includes: Based on the vehicle's first motion state parameters at the initial moment and the circular kinematics model, the coordinates of the vehicle's reference point at each time point are obtained. The first motion state parameters include the vehicle's speed and yaw rate. Based on the vehicle's geometric dimensions and the coordinates of the vehicle's reference point at each time point, the coordinates of multiple corner points representing the first shape of the vehicle's exterior at each time point are obtained.
3. The AEB anti-accidental touch method as described in claim 2, characterized in that, The process of obtaining the second prediction information based on the second motion state parameters of the target object at the initial moment and the geometric dimension information of the target object includes: Based on the second motion state parameters of the target object at the initial moment and the linear kinematic model, the coordinates of the target object reference point at each time point are obtained. The second motion state parameters include the target object velocity and the target object acceleration. Based on the geometric dimensions of the target object and the coordinates of the target object's reference point at each time point, the coordinates of multiple corner points of the second shape used to characterize the target object's shape at each time point are obtained.
4. The AEB anti-accidental touch method as described in claim 3, characterized in that, Based on the first and second prediction information, detecting the existence of a target time point includes: Based on the first and second prediction information, each time point where the time difference from the initial time is less than a preset time difference is determined. When, the total number of edges that intersect each edge of the second shape with each edge of the first shape. And the number of corner points of the second shape that are located within the first shape. ; like Greater than the first preset value and / or If it is greater than the second preset value, then confirm. The overlapping area of the first shape and the second shape ; like If the area is greater than the preset area, then confirm. The target time point.
5. The AEB anti-accidental touch method as described in claim 4, characterized in that, Determine each time point where the time difference from the initial time is less than a preset time difference. When, the total number of edges that intersect each edge of the second shape with each edge of the first shape. include: For any one of the multiple edges included in the first shape, based on each time point where the time difference from the initial time is less than a preset time difference... At that time, the coordinates of the two corner points corresponding to any one edge and the coordinates of multiple corner points of the second shape are used to detect whether each edge included in the second shape intersects with any one edge; If a target edge intersects with any of the edges, then based on the coordinates of the two corner points corresponding to the edge and the two corner points corresponding to the target edge, it is detected whether the intersection point is located on the target edge and the edge. If the intersection point is located on the target edge and any of the edges, then... The value increases by 1, where The initial value is zero; By repeating this process, we can iterate through all the edges included in the first shape to obtain... Time corresponding The value of .
6. The AEB anti-accidental touch method as described in claim 4, characterized in that, Determine each time point where the time difference from the initial time is less than a preset time difference. At that time, the number of corner points of the second shape that are located within the first shape. include: For any corner point among the multiple corner points included in the second shape, based on each time point where the time difference from the initial time is less than a preset time difference... At that time, the coordinates of any corner point and the coordinates of multiple corner points of the first shape are used to detect whether any corner point is within the first shape; If it is within the first shape, then The value increases by 1, where The initial value is zero; By repeating this process, we can iterate through all the corner points included in the second shape to obtain... Time corresponding The value of .
7. The AEB anti-accidental touch method as described in claim 4, characterized in that, Determined at When, the overlapping area of the first shape and the second shape include: According to When the coordinates of multiple corner points of the first shape are used, the first bounding rectangle of the first shape is determined. According to When the coordinates of multiple corner points of the second shape are used, the second bounding rectangle of the second shape is determined. The overlapping area is obtained by using the coordinates of the four corner points of the first circumscribed rectangle and the four corner points of the second circumscribed rectangle. .
8. An AEB (Automatic Emergency Braking) anti-accidental touch device, characterized in that, The AEB anti-accidental touch device includes: The prediction module is used to obtain first prediction information based on the first motion state parameters of the vehicle at the initial moment and the geometric size information of the vehicle. The first prediction information includes the motion trajectory of multiple corner points of a first shape used to characterize the shape of the vehicle in the future time period. Based on the second motion state parameters of the target object at the initial moment and the geometric size information of the target object, the second prediction information is obtained. The second prediction information includes the motion trajectory of multiple corner points of the second shape used to characterize the shape of the target object in the future time period. The detection module is used to detect whether a target time point exists based on the first prediction information and the second prediction information, wherein the time difference between the target time point and the initial time is less than a preset time difference, and the overlapping area of the first shape and the second shape at the target time point is greater than a preset area. The activation module is used to activate the AEB automatic emergency braking system if a target time point exists.
9. An AEB (Automatic Emergency Braking) anti-accidental touch device, characterized in that, The AEB anti-accidental touch device includes a processor, a memory, and an AEB anti-accidental touch program stored in the memory and executable by the processor, wherein when the AEB anti-accidental touch program is executed by the processor, it implements the steps of the AEB anti-accidental touch method as described in any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores an AEB anti-accidental touch program, wherein when the AEB anti-accidental touch program is executed by a processor, it implements the steps of the AEB anti-accidental touch method as described in any one of claims 1 to 7.