Vehicle emergency braking method, device, computer equipment, readable storage medium and program product

By detecting the relative distance and collision time between vehicles and pedestrians, this technology solves the problem of high computational difficulty in situations with complex pedestrian trajectories, enabling efficient emergency braking and reducing the risk of traffic accidents.

CN119611353BActive Publication Date: 2025-10-28FAW JIEFANG AUTOMOTIVE CO
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202510017888.8
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2025-01-06
Publication Date
2025-10-28
Estimated Expiration
2045-01-06

AI Technical Summary

Technical Problem

Existing automatic emergency braking systems are computationally difficult and inefficient when dealing with complex and diverse pedestrian trajectories, making it difficult to efficiently determine and execute emergency braking.

Method used

By detecting the current road conditions of the vehicle, the relative longitudinal and lateral distances between the vehicle and pedestrians are obtained, the longitudinal and lateral collision times are calculated, it is determined whether a collision will occur, and braking is performed if necessary.

Benefits of technology

It enables efficient and accurate judgment and execution of emergency braking in curved situations, reducing the occurrence of traffic accidents.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119611353B_ABST
    Figure CN119611353B_ABST
Patent Text Reader

Abstract

This application relates to a vehicle emergency braking method, apparatus, computer device, computer-readable storage medium, and computer program product. The method includes: when a pedestrian is detected ahead, determining the road conditions of the road where the vehicle is currently located; if the road conditions are a curve and lane markings exist, acquiring the vehicle speed, the pedestrian's movement speed, the relative lateral distance between the vehicle and the pedestrian, and the relative longitudinal distance; determining the longitudinal collision time and lateral collision time between the vehicle and the pedestrian based on the vehicle speed, the pedestrian's movement speed, the relative longitudinal distance, and the relative lateral distance; determining whether a collision will occur between the vehicle and the pedestrian based on the lateral collision time and the longitudinal collision time; and if a collision is likely, performing braking. This method can efficiently and accurately determine whether a collision with a pedestrian is possible, thereby enabling emergency braking.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This application relates to the field of autonomous driving technology, and in particular to a vehicle emergency braking method, device, computer equipment, computer-readable storage medium, and computer program product. Background Technology

[0002] In recent years, with the continuous development of automotive technology, the number of cars in my country has been increasing year by year, leading to a surge in the number of traffic accidents. Automatic Emergency Braking (AEB), as a key safety technology, has gradually received widespread attention. Studies have shown that vehicles equipped with AEB can effectively reduce the occurrence of traffic accidents.

[0003] Compared to motor vehicles, the trajectories of pedestrians and two-wheeled vehicles are more divergent, diverse, and susceptible to the influence of other obstacles, making them difficult to predict. Typically, calculating a pedestrian's trajectory in a traffic scenario requires considering not only the pedestrian's historical trajectory and kinematic characteristics, but also the surrounding environment (such as obstacles, sidewalks, traffic lights, etc.) and interactions between pedestrians. This not only increases computational complexity but also results in a large amount of computational input, leading to low efficiency in executing Automatic Emergency Braking (AEB). Summary of the Invention

[0004] Therefore, it is necessary to provide a vehicle emergency braking method, device, computer equipment, computer-readable storage medium, and computer program product that can efficiently determine the situation of a collision with a pedestrian and perform emergency braking in order to address the above-mentioned technical problems.

[0005] In a first aspect, this application provides a vehicle emergency braking method, including:

[0006] When a pedestrian is detected ahead, the vehicle's current road conditions are assessed.

[0007] If the road condition is a curve and there are lane lines, then the vehicle speed, pedestrian movement speed, relative lateral distance and relative longitudinal distance between the vehicle and the pedestrian are obtained. Based on the vehicle speed, pedestrian movement speed, relative longitudinal distance and relative lateral distance, the longitudinal collision time and lateral collision time between the vehicle and the pedestrian are determined.

[0008] Based on the lateral collision time and longitudinal collision time, it is determined whether the vehicle will collide with the pedestrian. If a collision is expected, braking is performed.

[0009] In one embodiment, acquiring the vehicle speed, pedestrian movement speed, relative lateral distance between the vehicle and the pedestrian, and relative longitudinal distance includes:

[0010] Obtain the vehicle speed; taking the vehicle's forward direction as the longitudinal direction and the left side of the vehicle as the lateral direction; based on the longitudinal and lateral directions, determine the pedestrian's longitudinal speed, pedestrian's lateral speed, and the longitudinal and lateral distances between the vehicle and the pedestrian; use the longitudinal distance as the relative longitudinal distance; use the pedestrian's longitudinal speed and lateral speed as the pedestrian's movement speed; determine the formula for calculating the relative lateral distance; based on the relative longitudinal distance and the formula for calculating the relative lateral distance, determine the relative lateral distance between the lane line and the pedestrian, which is then used as the relative lateral distance.

[0011] In one embodiment, determining the longitudinal collision time and lateral collision time of the vehicle and pedestrian based on the vehicle speed, the pedestrian movement speed, the relative lateral distance, and the relative longitudinal distance includes:

[0012] Based on the vehicle speed, the pedestrian's longitudinal speed, and the relative longitudinal distance, the longitudinal collision time between the vehicle and the pedestrian is determined; if the longitudinal collision time is greater than a first preset value, the longitudinal collision time between the vehicle and the pedestrian is determined based on the vehicle speed, the pedestrian's longitudinal speed, and the relative longitudinal distance; if the longitudinal collision time is not greater than the first preset value, the lateral collision time between the vehicle and the pedestrian is determined based on the pedestrian's lateral speed and the relative lateral distance.

[0013] In one embodiment, determining the lateral collision time between the vehicle and the pedestrian based on the pedestrian's lateral velocity and the relative lateral distance includes:

[0014] The process involves: acquiring the lane width and vehicle width; determining a minimum lateral distance based on the relative lateral distance and the lane width; determining a maximum lateral distance based on the relative lateral distance and the vehicle width; determining a first lateral collision time based on the minimum lateral distance and the pedestrian's lateral velocity; determining a second lateral collision time based on the relative lateral distance and the pedestrian's lateral velocity; and determining a third lateral collision time based on the maximum lateral distance and the pedestrian's lateral velocity. The first lateral collision time, the second lateral collision time, and the third lateral collision time together constitute the total lateral collision time.

[0015] In one embodiment, determining whether a collision with the pedestrian will occur based on the lateral collision time and the longitudinal collision time includes:

[0016] If the first lateral collision time is greater than the longitudinal collision time, no collision will occur with the pedestrian; if the first lateral collision time is not greater than the longitudinal collision time, and the second lateral collision time is greater than the longitudinal collision time, a first collision event will occur with the pedestrian; if the second lateral collision time plus the first lateral collision time is not greater than the longitudinal collision time, and the third lateral collision time is greater than the longitudinal collision time, a second collision event will occur with the pedestrian; if the third lateral collision time is not greater than the longitudinal collision time, no collision will occur with the pedestrian.

[0017] In one embodiment, the method further includes:

[0018] If the road condition is a straight road with lane markings, or the steering wheel angle is within a threshold range, then the vehicle speed, pedestrian movement speed, longitudinal collision distance between the vehicle and the pedestrian, and lateral collision distance are obtained; based on the vehicle speed, pedestrian movement speed, longitudinal collision distance, and lateral collision distance, the longitudinal collision time and lateral collision time between the vehicle and the pedestrian are determined.

[0019] Secondly, this application also provides a vehicle emergency braking device, comprising:

[0020] The detection module is used to determine the road conditions of the road where the vehicle is currently located when a pedestrian is detected ahead.

[0021] The time calculation module is used to obtain the vehicle speed, pedestrian movement speed, relative lateral distance and relative longitudinal distance between the vehicle and the pedestrian if the road condition is a curve and there are lane lines. Based on the vehicle speed, the pedestrian movement speed, the relative longitudinal distance and the relative lateral distance, the module determines the lateral collision time and longitudinal collision time between the vehicle and the pedestrian.

[0022] The braking module is used to determine whether the vehicle will collide with the pedestrian based on the lateral collision time and the longitudinal collision time. If a collision is expected, braking is performed.

[0023] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0024] When a pedestrian is detected ahead, the vehicle's current road conditions are assessed.

[0025] If the road condition is a curve and there are lane lines, then the vehicle speed, pedestrian movement speed, relative lateral distance and relative longitudinal distance between the vehicle and the pedestrian are obtained. Based on the vehicle speed, pedestrian movement speed, relative longitudinal distance and relative lateral distance, the longitudinal collision time and lateral collision time between the vehicle and the pedestrian are determined.

[0026] Based on the lateral collision time and longitudinal collision time, it is determined whether the vehicle will collide with the pedestrian. If a collision is expected, braking is performed.

[0027] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the following steps:

[0028] When a pedestrian is detected ahead, the vehicle's current road conditions are assessed.

[0029] If the road condition is a curve and there are lane lines, then the vehicle speed, pedestrian movement speed, relative lateral distance and relative longitudinal distance between the vehicle and the pedestrian are obtained. Based on the vehicle speed, pedestrian movement speed, relative longitudinal distance and relative lateral distance, the longitudinal collision time and lateral collision time between the vehicle and the pedestrian are determined.

[0030] Based on the lateral collision time and longitudinal collision time, it is determined whether the vehicle will collide with the pedestrian. If a collision is expected, braking is performed.

[0031] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, performs the following steps:

[0032] When a pedestrian is detected ahead, the vehicle's current road conditions are assessed.

[0033] If the road condition is a curve and there are lane lines, then the vehicle speed, pedestrian movement speed, relative lateral distance and relative longitudinal distance between the vehicle and the pedestrian are obtained. Based on the vehicle speed, pedestrian movement speed, relative longitudinal distance and relative lateral distance, the longitudinal collision time and lateral collision time between the vehicle and the pedestrian are determined.

[0034] Based on the lateral collision time and longitudinal collision time, it is determined whether the vehicle will collide with the pedestrian. If a collision is expected, braking is performed.

[0035] In the aforementioned vehicle emergency braking method, when a pedestrian is detected ahead, the road conditions of the vehicle's current location are assessed. If the road is a curve and lane markings are present, the vehicle speed, pedestrian speed, relative lateral distance between the vehicle and pedestrian, and relative longitudinal distance are acquired. Based on these parameters, the lateral and longitudinal collision times are determined. The lateral and longitudinal collision times are then used to determine whether a collision will occur. If a collision is expected, braking is initiated. By determining the relative longitudinal and lateral distances between the vehicle and pedestrian on a curve, a highly efficient and accurate assessment of the potential for a collision can be achieved. Attached Figure Description

[0036] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0037] Figure 1 This is a flowchart illustrating a vehicle emergency braking method in one embodiment;

[0038] Figure 2 This is a schematic diagram of an emergency braking method for a vehicle in a curve situation in one embodiment;

[0039] Figure 3 This is a schematic diagram of a vehicle emergency braking method in a straight road condition according to one embodiment;

[0040] Figure 4 This is a flowchart of a vehicle emergency braking method in a straight road condition, as described in one embodiment.

[0041] Figure 5 This is a structural block diagram of a vehicle emergency braking device in one embodiment;

[0042] Figure 6 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0043] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0044] In one embodiment, such as Figure 1As shown, a vehicle emergency braking method is provided. This embodiment illustrates the method applied to a terminal. It is understood that this method can also be applied to a server, and further to a system including both a terminal and a server, and implemented through interaction between the terminal and the server. In this embodiment, the method includes the following steps:

[0045] Step 102: When a pedestrian is detected ahead, determine the road conditions of the road where the vehicle is currently located.

[0046] The detection is carried out using cameras and radar.

[0047] The road conditions include: whether it is a straight road or a curve, whether there are lane lines, and the steering wheel angle and speed.

[0048] For example, when a pedestrian is detected ahead by a camera and radar, the road conditions of the road where the vehicle is currently located can be determined.

[0049] Step 104: If the road condition is a curve and there are lane lines, then obtain the vehicle speed, pedestrian movement speed, relative lateral distance and relative longitudinal distance between the vehicle and the pedestrian, and determine the lateral collision time and longitudinal collision time between the vehicle and the pedestrian based on the vehicle speed, the pedestrian movement speed, the relative longitudinal distance and the relative lateral distance.

[0050] Among them, the vehicle speed is the current vehicle speed, and the pedestrian movement speed, the relative lateral distance between the vehicle and the pedestrian, and the relative longitudinal distance are collected by cameras and radar.

[0051] The longitudinal distance is the vertical distance between the pedestrian and the vehicle, while the lateral distance is the vertical distance between the pedestrian and the vehicle.

[0052] For example, if the road condition is a curve and there are no lane lines, no operation is performed; if the road condition is a curve and there are lane lines, the vehicle speed, pedestrian movement speed, relative lateral distance and relative longitudinal distance between the vehicle and the pedestrian are obtained, and the lateral collision time and longitudinal collision time between the vehicle and the pedestrian are determined based on the vehicle speed, the pedestrian movement speed, the relative longitudinal distance and the relative lateral distance.

[0053] Step 106: Determine whether the vehicle will collide with the pedestrian based on the lateral collision time and longitudinal collision time. If a collision is expected, perform braking.

[0054] Before braking is initiated, a level 1 and level 2 warning will be issued. If a collision still occurs, braking will be initiated.

[0055] For example, it is determined whether a vehicle will collide with a pedestrian based on the lateral collision time and the longitudinal collision time. If a collision is expected, a first-level warning and a second-level warning are issued sequentially. If a collision still occurs after the second-level warning is issued, braking is performed.

[0056] In the aforementioned vehicle emergency braking method, when a pedestrian is detected ahead, the road conditions of the vehicle's current location are assessed. If the road is a curve and lane markings are present, the vehicle speed, pedestrian speed, relative lateral distance between the vehicle and pedestrian, and relative longitudinal distance are acquired. Based on these parameters, the lateral and longitudinal collision times are determined. The lateral and longitudinal collision times are then used to determine whether a collision will occur. If a collision is expected, braking is initiated. By determining the relative longitudinal and lateral distances between the vehicle and pedestrian on a curve, a highly efficient and accurate assessment of the potential for a collision can be achieved.

[0057] In an exemplary embodiment, acquiring the vehicle speed, pedestrian movement speed, relative lateral distance between the vehicle and the pedestrian, and relative longitudinal distance includes:

[0058] Obtain the vehicle speed; take the vehicle's forward direction as the longitudinal direction and the left side of the vehicle as the lateral direction; based on the longitudinal and lateral directions, determine the pedestrian's longitudinal speed, pedestrian's lateral speed, longitudinal distance between the vehicle and the pedestrian, and lateral distance between them; use the longitudinal distance as the relative longitudinal distance; use the pedestrian's longitudinal speed and lateral speed as the pedestrian's movement speed; determine the formula for calculating the relative lateral distance; based on the relative longitudinal distance and the formula for calculating the relative lateral distance, determine the relative lateral distance.

[0059] For example, the vehicle speed at the current moment is obtained, with the vehicle's forward direction as the longitudinal direction and the left side of the vehicle as the lateral direction; based on the longitudinal and lateral directions, the longitudinal velocity of the pedestrian in the longitudinal direction, the lateral velocity of the pedestrian in the lateral direction, the longitudinal distance between the vehicle and the pedestrian, and the lateral distance are determined; the longitudinal distance is used as the relative longitudinal distance; the pedestrian's longitudinal velocity and lateral velocity are used as the pedestrian's movement speed; the formula for calculating the relative lateral distance between the lane line and the pedestrian is determined as follows:

[0060] + ,

[0061] in, It is the distance from the front of the car to the center line of the lane. It is the angle between the front of the car and the center line of the lane. It's curvature. It is the rate of change of curvature; the relative lateral distance is determined based on the relative longitudinal distance and the formula for calculating the relative lateral distance.

[0062] In this embodiment, the obtained lateral distance is the relative lateral distance between the lane line and the pedestrian, rather than the lateral distance between the vehicle itself and the pedestrian. This can prevent large calculation errors in curved situations, which could lead to accidental triggering of emergency braking.

[0063] In an exemplary embodiment, determining the lateral collision time and longitudinal collision time between the vehicle and the pedestrian based on the vehicle speed, the pedestrian's movement speed, the relative lateral distance, and the relative longitudinal distance includes:

[0064] Based on the vehicle speed, the pedestrian's longitudinal speed, and the relative longitudinal distance, the longitudinal collision time between the vehicle and the pedestrian is determined; if the longitudinal collision time is greater than a first preset value, the longitudinal collision time between the vehicle and the pedestrian is determined based on the vehicle speed, the pedestrian's longitudinal speed, and the relative longitudinal distance; if the longitudinal collision time is not greater than the first preset value, the lateral collision time between the vehicle and the pedestrian is determined based on the pedestrian's lateral speed and the relative lateral distance.

[0065] Optionally, the first preset value can be 2.3 seconds.

[0066] For example, the longitudinal collision time between a vehicle and a pedestrian is calculated based on the vehicle speed, the pedestrian's longitudinal speed, and the relative longitudinal distance, using the following formula:

[0067] ,

[0068] in, It is the longitudinal collision time. Relative longitudinal distance, This is the minimum safe distance between vehicles and pedestrians, which can be 2 meters. It is the vehicle speed. This refers to the pedestrian's longitudinal speed. If the longitudinal collision time is greater than 2.3 seconds, the longitudinal collision time between the vehicle and the pedestrian is determined based on the vehicle speed, the pedestrian's longitudinal speed, and the relative longitudinal distance. If the longitudinal collision time is not greater than 2.3 seconds, the lateral collision time between the vehicle and the pedestrian is calculated based on the pedestrian's lateral speed and the relative lateral distance.

[0069] In this embodiment, if the longitudinal collision time is greater than the safe time, it is considered safe and no lateral collision is determined. If the longitudinal collision time is not greater than the safe time, a collision may occur, and then a lateral collision is determined. This allows for an accurate determination of whether a collision event will occur.

[0070] In an exemplary embodiment, determining the lateral collision time between the vehicle and the pedestrian based on the pedestrian's lateral velocity and the relative lateral distance includes:

[0071] The process involves: acquiring the lane width and vehicle width; determining a minimum lateral distance based on the relative lateral distance and the lane width; determining a maximum lateral distance based on the relative lateral distance and the vehicle width; determining a first lateral collision time based on the minimum lateral distance and the pedestrian's lateral velocity; determining a second lateral collision time based on the relative lateral distance and the pedestrian's lateral velocity; and determining a third lateral collision time based on the maximum lateral distance and the pedestrian's lateral velocity. The first lateral collision time, the second lateral collision time, and the third lateral collision time together constitute the total lateral collision time.

[0072] For example, such as Figure 2 As shown, the positive X-axis direction is vertical, and the positive Y-axis direction is horizontal. , and This refers to the longitudinal and lateral distances between vehicles and pedestrians when the vehicle is used as the coordinate system. and These are the pedestrian's longitudinal and lateral velocities. The longitudinal distance... As the relative longitudinal distance AC, the relative lateral distance AE is therefore obtained by the following formula:

[0073] ,

[0074] Get lane line width and vehicle width Based on relative lateral distance AE and lane width The minimum lateral distance AF is determined by the following formula:

[0075] ,

[0076] Based on the relative lateral distance AE and the vehicle width The maximum lateral distance AD ​​is determined by the following formula:

[0077] ,

[0078] Based on the minimum lateral distance AF and the pedestrian's lateral velocity during the AF phase. Determine the time of the first lateral collision. The formula is:

[0079] ,

[0080] in, This is the pedestrian's velocity during the AF phase. It is based on the relative lateral distance AF and the pedestrian's lateral velocity. To determine the second lateral collision time, the pedestrian's lateral velocity in the DF phase should not be directly taken as the lateral velocity relative to the vehicle given by the radar, because pedestrians will instinctively walk in the opposite direction when encountering danger. Therefore, the pedestrian's motion at this time is multifaceted and unpredictable. Differentiate the AD and perform a simple first-order filter to find the pedestrian's instantaneous velocity relative to the lane line. After obtaining the instantaneous velocity, perform a discrete definite integral on the instantaneous velocity and divide it by time to obtain the pedestrian's lateral velocity in the DF phase. The formula is as follows:

[0081] ,

[0082] in, It's exercise time. It is a coefficient. It refers to the instantaneous velocity during the AD phase. It's the time delay, the parameter multiplied by This indicates the value of the parameter in the previous cycle. Calculate the second lateral collision time. The formula is:

[0083] ,

[0084] Based on the maximum lateral distance AD ​​and pedestrian lateral velocity Determine the time of the third lateral collision. The formula is:

[0085] ,

[0086] First lateral collision time Second lateral collision time and third lateral collision time Together, they constitute the lateral collision time.

[0087] In this embodiment, different lateral collision times are determined, which can be used to determine whether a collision will occur and what type of collision will occur, in order to make judgments and take subsequent decisions.

[0088] In an exemplary embodiment, determining whether a collision with the pedestrian will occur based on the lateral collision time and the longitudinal collision time includes:

[0089] If the first lateral collision time is greater than the longitudinal collision time, no collision will occur with the pedestrian; if the first lateral collision time is not greater than the longitudinal collision time, and the second lateral collision time is greater than the longitudinal collision time, a first collision event will occur with the pedestrian; if the second lateral collision time plus the first lateral collision time is not greater than the longitudinal collision time, and the third lateral collision time is greater than the longitudinal collision time, a second collision event will occur with the pedestrian; if the third lateral collision time is not greater than the longitudinal collision time, no collision will occur with the pedestrian.

[0090] For example, if the first lateral collision time Greater than longitudinal collision time If the first lateral collision time is..., then no collision will occur. Not greater than longitudinal collision time And the second lateral collision time Greater than longitudinal collision time If the second lateral collision occurs, the vehicle will collide with the pedestrian during the EF phase. At this point, the driver should be warned to change lanes to the left. Add the first lateral collision time The subsequent time is no greater than the longitudinal collision time. And the third lateral collision time Greater than longitudinal collision time If the third lateral collision occurs during the DE phase, the vehicle will collide with the pedestrian. At this point, the driver should be warned to change lanes to the right. Not greater than longitudinal collision time If the target is not in contact with the target, a collision will not occur.

[0091] In this embodiment, by analyzing the lateral collision time and longitudinal collision time under different conditions, it is possible to accurately determine whether a vehicle will collide with a pedestrian.

[0092] In one exemplary embodiment, the method further includes:

[0093] If the road condition is a straight road with lane markings, or the steering wheel angle is within a threshold range, then the vehicle speed, pedestrian movement speed, longitudinal collision distance between the vehicle and the pedestrian, and lateral collision distance are obtained; based on the vehicle speed, pedestrian movement speed, longitudinal collision distance, and lateral collision distance, the longitudinal collision time and lateral collision time between the vehicle and the pedestrian are determined.

[0094] Optionally, the threshold relationships between vehicle speed (km / h) and steering wheel angle (deg) are as follows: 20 km / h: 35 deg, 30 km / h: 30 deg, 40 km / h: 20 deg, 50 km / h: 20 deg, 60 km / h: 20 deg, 70 km / h: 15 deg, 80 km / h: 15 deg, 90 km / h: 15 deg, 100 km / h: 10 deg. The threshold relationships between vehicle speed (km / h) and steering wheel rotation speed (deg) are as follows: 20 km / h: 60 deg, 30 km / h: 50 deg, 40 km / h: 40 deg, 50 km / h: 40 deg, 60 km / h: 40 deg, 70 km / h: 30 deg, 80 km / h: 30 deg, 90 km / h: 25 deg, 100 km / h: 20 deg. For example, when the vehicle speed is 20 km / h, the steering wheel angle threshold is 35 degrees, and the steering wheel speed is 60 degrees. Here, "deg" is an abbreviation for "degree".

[0095] Optional, such as Figure 3 The diagram shown is for a straight road. The positive X-axis represents the vertical direction, and the positive Y-axis represents the horizontal direction. and This refers to the longitudinal and lateral distances between vehicles and pedestrians when the vehicle is used as the coordinate system. and These are the pedestrian's longitudinal and lateral speeds.

[0096] For example, such as Figure 4 As shown, if the road is straight and lane markings are present, or the steering wheel angle is within a threshold range, the longitudinal and lateral collision distances of the vehicle and pedestrian, the pedestrian lifespan, the pedestrian longitudinal velocity, and the pedestrian lateral velocity are obtained. When the pedestrian lifespan is greater than 0.5 seconds, i.e., the detected presence time exceeds 0.5 seconds, the target pedestrian is considered valid; otherwise, the target pedestrian is ignored. A low-pass filter is used to filter the longitudinal and lateral collision distances, pedestrian longitudinal velocity, and pedestrian lateral velocity of valid target pedestrians. The longitudinal collision time is calculated using the following formula:

[0097] ,

[0098] in, It is the longitudinal collision time. Relative longitudinal distance, This is the minimum safe distance between vehicles and pedestrians, which can be 2 meters. It is the vehicle speed. It is the pedestrian's longitudinal velocity. When When the time is less than 2.3 seconds, the lateral collision time is calculated using the following formula:

[0099] ,

[0100] ,

[0101] in, For vehicle width, It is the time it takes for the pedestrian to walk to the left side of the vehicle. It is the time between when the pedestrian walks to the right side of the vehicle and the moment of impact. Not less than 2.3 seconds, and A collision may occur if the time interval is no more than 2.3 seconds. If a collision is likely, a Level 1 alarm and a Level 2 alarm will be triggered sequentially, each alarm lasting 1.4 seconds. After the second alarm, the lateral displacement will be calculated, and it will be determined whether the lateral displacement exceeds a threshold, using the following formula:

[0102] ,

[0103] in, It is the pedestrian's current position in the horizontal direction. Here, 'a' is the pedestrian's initial position, 'a' is the acceleration, and 't' is the time. Displacement coefficient, when The lateral displacement exceeds a threshold, which will result in a collision, and then emergency braking will be initiated.

[0104] In an exemplary embodiment, a vehicle emergency braking method, when a pedestrian is detected ahead via a camera and radar, determines the road conditions of the road where the vehicle is currently located. If the road condition is a curve and lane markings exist, the current vehicle speed is obtained, with the vehicle's forward direction as the longitudinal direction and the left side of the vehicle as the lateral direction. Based on the longitudinal and lateral directions, the longitudinal velocity of the pedestrian in the longitudinal direction, the lateral velocity of the pedestrian in the lateral direction, the longitudinal distance between the vehicle and the pedestrian, and the lateral distance are determined. The longitudinal distance is used as the relative longitudinal distance; the pedestrian's longitudinal velocity and lateral velocity are used as the pedestrian's movement speed; a formula for calculating the relative lateral distance between the lane markings and the pedestrian is determined, as follows:

[0105] + ,

[0106] in, It is the distance from the front of the car to the center line of the lane. It is the angle between the front of the car and the center line of the lane. It's curvature. It is the rate of change of curvature; the relative lateral distance is determined based on the relative longitudinal distance and the formula for calculating the relative lateral distance. The longitudinal collision time between the vehicle and the pedestrian is calculated based on the vehicle speed, the pedestrian's longitudinal speed, and the relative longitudinal distance, using the following formula:

[0107] ,

[0108] in, It is the longitudinal collision time. Relative longitudinal distance, This is the minimum safe distance between vehicles and pedestrians, which can be 2 meters. It is the vehicle speed. This refers to the pedestrian's longitudinal velocity. If the longitudinal collision time is greater than 2.3 seconds, the longitudinal collision time between the vehicle and the pedestrian is determined based on the vehicle speed, the pedestrian's longitudinal velocity, and the relative longitudinal distance. If the longitudinal collision time is not greater than 2.3 seconds, the lateral collision time between the vehicle and the pedestrian is calculated based on the pedestrian's lateral velocity and the relative lateral distance. The longitudinal distance is used as the relative longitudinal distance AC; therefore, the relative lateral distance AE is obtained by the following formula:

[0109] ,

[0110] Get lane line width and vehicle width Based on relative lateral distance AE and lane width The minimum lateral distance AF is determined by the following formula:

[0111] ,

[0112] Based on the relative lateral distance AE and the vehicle width The maximum lateral distance AD ​​is determined by the following formula:

[0113] ,

[0114] Based on the minimum lateral distance AF and the pedestrian's lateral velocity during the AF phase. Determine the time of the first lateral collision. The formula is:

[0115] ,

[0116] in, This is the pedestrian's velocity during the AF phase. It is based on the relative lateral distance AF and the pedestrian's lateral velocity. To determine the second lateral collision time, the pedestrian's lateral velocity in the DF phase should not be directly taken as the lateral velocity relative to the vehicle given by the radar, because pedestrians will instinctively walk in the opposite direction when encountering danger. Therefore, the pedestrian's motion at this time is multifaceted and unpredictable. Differentiate the AD and perform a simple first-order filter to find the pedestrian's instantaneous velocity relative to the lane line. After obtaining the instantaneous velocity, perform a discrete definite integral on the instantaneous velocity and divide it by time to obtain the pedestrian's lateral velocity in the DF phase. The formula is as follows:

[0117] ,

[0118] in, It's exercise time. It is a coefficient. It refers to the instantaneous velocity during the AD phase. It's the time delay, the parameter multiplied by This indicates the value of the parameter in the previous cycle. Calculate the second lateral collision time. The formula is:

[0119] ,

[0120] Based on maximum lateral distance AD ​​and pedestrian lateral velocity Determine the time of the third lateral collision. The formula is:

[0121] ,

[0122] First lateral collision time Second lateral collision time and third lateral collision time Together, they constitute the lateral collision time. If the first lateral collision time... Greater than longitudinal collision time If the first lateral collision time is..., then no collision will occur. Not greater than longitudinal collision time And the second lateral collision time Greater than longitudinal collision time If the second lateral collision occurs, the vehicle will collide with the pedestrian during the EF phase. At this point, the driver should be warned to change lanes to the left. Add the first lateral collision time The subsequent time is no greater than the longitudinal collision time. And the third lateral collision time Greater than longitudinal collision time If the third lateral collision occurs during the DE phase, the vehicle will collide with the pedestrian. At this point, the driver should be warned to change lanes to the right. Not greater than longitudinal collision time If the road is straight and lane markings are present, or the steering wheel angle is within a threshold range, then the longitudinal and lateral collision distances of the vehicle and pedestrian, the pedestrian lifespan, the pedestrian longitudinal velocity, and the pedestrian lateral velocity are obtained. When the pedestrian lifespan is greater than 0.5 seconds (i.e., the detected presence time exceeds 0.5 seconds), the target pedestrian is considered valid; otherwise, the target pedestrian is ignored. A low-pass filter is used to filter the longitudinal and lateral collision distances, pedestrian longitudinal velocity, and pedestrian lateral velocity of valid target pedestrians. The longitudinal collision time is calculated using the following formula:

[0123] ,

[0124] in, It is the longitudinal collision time. Relative longitudinal distance, This is the minimum safe distance between vehicles and pedestrians, which can be 2 meters. It is the vehicle speed. It is the pedestrian's longitudinal velocity. When When the time is less than 2.3 seconds, the lateral collision time is calculated using the following formula:

[0125] ,

[0126] ,

[0127] in, For vehicle width, It is the time it takes for the pedestrian to walk to the left side of the vehicle. It is the time between when the pedestrian walks to the right side of the vehicle and the moment of impact. Not less than 2.3 seconds, and A collision may occur within 2.3 seconds. If a collision is likely, a Level 1 alarm and a Level 2 alarm will be issued sequentially, each alarm lasting 1.4 seconds. After the second alarm, the lateral displacement will be calculated to determine if a collision will occur. If a collision is likely, emergency braking will be initiated. The method for determining the lateral displacement is as follows:

[0128] ,

[0129] in, It is the pedestrian's current position in the horizontal direction. Here, 'a' is the pedestrian's initial position, 'a' is the acceleration, and 't' is the time. Displacement coefficient, when A collision will occur when the displacement exceeds the lateral movement.

[0130] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0131] In an exemplary embodiment, Figure 5 As shown, a vehicle emergency braking device is provided, including: a detection module, a time calculation module, and a braking module, wherein:

[0132] The detection module is used to determine the road conditions of the road where the vehicle is currently located when a pedestrian is detected ahead.

[0133] The time calculation module is used to obtain the vehicle speed, pedestrian movement speed, relative lateral distance and relative longitudinal distance between the vehicle and the pedestrian if the road condition is a curve and there are lane lines. Based on the vehicle speed, the pedestrian movement speed, the relative longitudinal distance and the relative lateral distance, the module determines the lateral collision time and longitudinal collision time between the vehicle and the pedestrian.

[0134] The braking module is used to determine whether the vehicle will collide with the pedestrian based on the lateral collision time and the longitudinal collision time. If a collision is expected, braking is performed.

[0135] In one embodiment, the time calculation module is further configured to:

[0136] Obtain the vehicle speed; taking the vehicle's forward direction as the longitudinal direction and the left side of the vehicle as the lateral direction; based on the longitudinal and lateral directions, determine the pedestrian's longitudinal speed, pedestrian's lateral speed, and the longitudinal and lateral distances between the vehicle and the pedestrian; use the longitudinal distance as the relative longitudinal distance; use the pedestrian's longitudinal speed and lateral speed as the pedestrian's movement speed; determine the formula for calculating the relative lateral distance; based on the relative longitudinal distance and the formula for calculating the relative lateral distance, determine the relative lateral distance between the lane line and the pedestrian, which is then used as the relative lateral distance.

[0137] In one embodiment, the time calculation module is further configured to:

[0138] Based on the vehicle speed, the pedestrian's longitudinal speed, and the relative longitudinal distance, the longitudinal collision time between the vehicle and the pedestrian is determined; if the longitudinal collision time is greater than a first preset value, the longitudinal collision time between the vehicle and the pedestrian is determined based on the vehicle speed, the pedestrian's longitudinal speed, and the relative longitudinal distance; if the longitudinal collision time is not greater than the first preset value, the lateral collision time between the vehicle and the pedestrian is determined based on the pedestrian's lateral speed and the relative lateral distance.

[0139] In one embodiment, the time calculation module is further configured to:

[0140] The process involves: acquiring the lane width and vehicle width; determining a minimum lateral distance based on the relative lateral distance and the lane width; determining a maximum lateral distance based on the relative lateral distance and the vehicle width; determining a first lateral collision time based on the minimum lateral distance and the pedestrian's lateral velocity; determining a second lateral collision time based on the relative lateral distance and the pedestrian's lateral velocity; and determining a third lateral collision time based on the maximum lateral distance and the pedestrian's lateral velocity. The first lateral collision time, the second lateral collision time, and the third lateral collision time together constitute the total lateral collision time.

[0141] In one embodiment, the braking module is further configured to:

[0142] If the first lateral collision time is greater than the longitudinal collision time, no collision will occur with the pedestrian; if the first lateral collision time is not greater than the longitudinal collision time, and the second lateral collision time is greater than the longitudinal collision time, a first collision event will occur with the pedestrian; if the second lateral collision time plus the first lateral collision time is not greater than the longitudinal collision time, and the third lateral collision time is greater than the longitudinal collision time, a second collision event will occur with the pedestrian; if the third lateral collision time is not greater than the longitudinal collision time, no collision will occur with the pedestrian.

[0143] In one embodiment, the time calculation module is further configured to:

[0144] If the road condition is a straight road with lane markings, or the steering wheel angle is within a threshold range, then the vehicle speed, pedestrian movement speed, longitudinal collision distance between the vehicle and the pedestrian, and lateral collision distance are obtained; based on the vehicle speed, pedestrian movement speed, longitudinal collision distance, and lateral collision distance, the longitudinal collision time and lateral collision time between the vehicle and the pedestrian are determined.

[0145] The various modules in the aforementioned vehicle emergency braking device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0146] In one exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 6 As shown, this computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores longitudinal and lateral collision times. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When executed by the processor, the computer program implements a vehicle emergency braking method.

[0147] Those skilled in the art will understand that Figure 6 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0148] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0149] When a pedestrian is detected ahead, the vehicle's current road conditions are assessed.

[0150] If the road condition is a curve and there are lane lines, then the vehicle speed, pedestrian movement speed, relative lateral distance and relative longitudinal distance between the vehicle and the pedestrian are obtained. Based on the vehicle speed, pedestrian movement speed, relative longitudinal distance and relative lateral distance, the longitudinal collision time and lateral collision time between the vehicle and the pedestrian are determined.

[0151] Based on the lateral collision time and longitudinal collision time, it is determined whether the vehicle will collide with the pedestrian. If a collision is expected, braking is performed.

[0152] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0153] Obtain the vehicle speed; taking the vehicle's forward direction as the longitudinal direction and the left side of the vehicle as the lateral direction; based on the longitudinal and lateral directions, determine the pedestrian's longitudinal speed, pedestrian's lateral speed, and the longitudinal and lateral distances between the vehicle and the pedestrian; use the longitudinal distance as the relative longitudinal distance; use the pedestrian's longitudinal speed and lateral speed as the pedestrian's movement speed; determine the formula for calculating the relative lateral distance; based on the relative longitudinal distance and the formula for calculating the relative lateral distance, determine the relative lateral distance between the lane line and the pedestrian, which is then used as the relative lateral distance.

[0154] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0155] Based on the vehicle speed, the pedestrian's longitudinal speed, and the relative longitudinal distance, the longitudinal collision time between the vehicle and the pedestrian is determined; if the longitudinal collision time is greater than a first preset value, the longitudinal collision time between the vehicle and the pedestrian is determined based on the vehicle speed, the pedestrian's longitudinal speed, and the relative longitudinal distance; if the longitudinal collision time is not greater than the first preset value, the lateral collision time between the vehicle and the pedestrian is determined based on the pedestrian's lateral speed and the relative lateral distance.

[0156] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0157] The process involves: acquiring the lane width and vehicle width; determining a minimum lateral distance based on the relative lateral distance and the lane width; determining a maximum lateral distance based on the relative lateral distance and the vehicle width; determining a first lateral collision time based on the minimum lateral distance and the pedestrian's lateral velocity; determining a second lateral collision time based on the relative lateral distance and the pedestrian's lateral velocity; and determining a third lateral collision time based on the maximum lateral distance and the pedestrian's lateral velocity. The first lateral collision time, the second lateral collision time, and the third lateral collision time together constitute the total lateral collision time.

[0158] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0159] If the first lateral collision time is greater than the longitudinal collision time, no collision will occur with the pedestrian; if the first lateral collision time is not greater than the longitudinal collision time, and the second lateral collision time is greater than the longitudinal collision time, a first collision event will occur with the pedestrian; if the second lateral collision time plus the first lateral collision time is not greater than the longitudinal collision time, and the third lateral collision time is greater than the longitudinal collision time, a second collision event will occur with the pedestrian; if the third lateral collision time is not greater than the longitudinal collision time, no collision will occur with the pedestrian.

[0160] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0161] If the road condition is a straight road with lane markings, or the steering wheel angle is within a threshold range, then the vehicle speed, pedestrian movement speed, longitudinal collision distance between the vehicle and the pedestrian, and lateral collision distance are obtained; based on the vehicle speed, pedestrian movement speed, longitudinal collision distance, and lateral collision distance, the longitudinal collision time and lateral collision time between the vehicle and the pedestrian are determined.

[0162] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0163] When a pedestrian is detected ahead, the vehicle's current road conditions are assessed.

[0164] If the road condition is a curve and there are lane lines, then the vehicle speed, pedestrian movement speed, relative lateral distance and relative longitudinal distance between the vehicle and the pedestrian are obtained. Based on the vehicle speed, pedestrian movement speed, relative longitudinal distance and relative lateral distance, the longitudinal collision time and lateral collision time between the vehicle and the pedestrian are determined.

[0165] Based on the lateral collision time and longitudinal collision time, it is determined whether the vehicle will collide with the pedestrian. If a collision is expected, braking is performed.

[0166] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0167] Obtain the vehicle speed; taking the vehicle's forward direction as the longitudinal direction and the left side of the vehicle as the lateral direction; based on the longitudinal and lateral directions, determine the pedestrian's longitudinal speed, pedestrian's lateral speed, and the longitudinal and lateral distances between the vehicle and the pedestrian; use the longitudinal distance as the relative longitudinal distance; use the pedestrian's longitudinal speed and lateral speed as the pedestrian's movement speed; determine the formula for calculating the relative lateral distance; based on the relative longitudinal distance and the formula for calculating the relative lateral distance, determine the relative lateral distance between the lane line and the pedestrian, which is then used as the relative lateral distance.

[0168] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0169] Based on the vehicle speed, the pedestrian's longitudinal speed, and the relative longitudinal distance, the longitudinal collision time between the vehicle and the pedestrian is determined; if the longitudinal collision time is greater than a first preset value, the longitudinal collision time between the vehicle and the pedestrian is determined based on the vehicle speed, the pedestrian's longitudinal speed, and the relative longitudinal distance; if the longitudinal collision time is not greater than the first preset value, the lateral collision time between the vehicle and the pedestrian is determined based on the pedestrian's lateral speed and the relative lateral distance.

[0170] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0171] The process involves: acquiring the lane width and vehicle width; determining a minimum lateral distance based on the relative lateral distance and the lane width; determining a maximum lateral distance based on the relative lateral distance and the vehicle width; determining a first lateral collision time based on the minimum lateral distance and the pedestrian's lateral velocity; determining a second lateral collision time based on the relative lateral distance and the pedestrian's lateral velocity; and determining a third lateral collision time based on the maximum lateral distance and the pedestrian's lateral velocity. The first lateral collision time, the second lateral collision time, and the third lateral collision time together constitute the total lateral collision time.

[0172] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0173] If the first lateral collision time is greater than the longitudinal collision time, no collision will occur with the pedestrian; if the first lateral collision time is not greater than the longitudinal collision time, and the second lateral collision time is greater than the longitudinal collision time, a first collision event will occur with the pedestrian; if the second lateral collision time plus the first lateral collision time is not greater than the longitudinal collision time, and the third lateral collision time is greater than the longitudinal collision time, a second collision event will occur with the pedestrian; if the third lateral collision time is not greater than the longitudinal collision time, no collision will occur with the pedestrian.

[0174] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0175] If the road condition is a straight road with lane markings, or the steering wheel angle is within a threshold range, then the vehicle speed, pedestrian movement speed, longitudinal collision distance between the vehicle and the pedestrian, and lateral collision distance are obtained; based on the vehicle speed, pedestrian movement speed, longitudinal collision distance, and lateral collision distance, the longitudinal collision time and lateral collision time between the vehicle and the pedestrian are determined.

[0176] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps:

[0177] When a pedestrian is detected ahead, the vehicle's current road conditions are assessed.

[0178] If the road condition is a curve and there are lane lines, then the vehicle speed, pedestrian movement speed, relative lateral distance and relative longitudinal distance between the vehicle and the pedestrian are obtained. Based on the vehicle speed, pedestrian movement speed, relative longitudinal distance and relative lateral distance, the longitudinal collision time and lateral collision time between the vehicle and the pedestrian are determined.

[0179] Based on the lateral collision time and longitudinal collision time, it is determined whether the vehicle will collide with the pedestrian. If a collision is expected, braking is performed.

[0180] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0181] Obtain the vehicle speed; taking the vehicle's forward direction as the longitudinal direction and the left side of the vehicle as the lateral direction; based on the longitudinal and lateral directions, determine the pedestrian's longitudinal speed, pedestrian's lateral speed, and the longitudinal and lateral distances between the vehicle and the pedestrian; use the longitudinal distance as the relative longitudinal distance; use the pedestrian's longitudinal speed and lateral speed as the pedestrian's movement speed; determine the formula for calculating the relative lateral distance; based on the relative longitudinal distance and the formula for calculating the relative lateral distance, determine the relative lateral distance between the lane line and the pedestrian, which is then used as the relative lateral distance.

[0182] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0183] Based on the vehicle speed, the pedestrian's longitudinal speed, and the relative longitudinal distance, the longitudinal collision time between the vehicle and the pedestrian is determined; if the longitudinal collision time is greater than a first preset value, the longitudinal collision time between the vehicle and the pedestrian is determined based on the vehicle speed, the pedestrian's longitudinal speed, and the relative longitudinal distance; if the longitudinal collision time is not greater than the first preset value, the lateral collision time between the vehicle and the pedestrian is determined based on the pedestrian's lateral speed and the relative lateral distance.

[0184] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0185] The process involves: acquiring the lane width and vehicle width; determining a minimum lateral distance based on the relative lateral distance and the lane width; determining a maximum lateral distance based on the relative lateral distance and the vehicle width; determining a first lateral collision time based on the minimum lateral distance and the pedestrian's lateral velocity; determining a second lateral collision time based on the relative lateral distance and the pedestrian's lateral velocity; and determining a third lateral collision time based on the maximum lateral distance and the pedestrian's lateral velocity. The first lateral collision time, the second lateral collision time, and the third lateral collision time together constitute the total lateral collision time.

[0186] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0187] If the first lateral collision time is greater than the longitudinal collision time, no collision will occur with the pedestrian; if the first lateral collision time is not greater than the longitudinal collision time, and the second lateral collision time is greater than the longitudinal collision time, a first collision event will occur with the pedestrian; if the second lateral collision time plus the first lateral collision time is not greater than the longitudinal collision time, and the third lateral collision time is greater than the longitudinal collision time, a second collision event will occur with the pedestrian; if the third lateral collision time is not greater than the longitudinal collision time, no collision will occur with the pedestrian.

[0188] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0189] If the road condition is a straight road with lane markings, or the steering wheel angle is within a threshold range, then the vehicle speed, pedestrian movement speed, longitudinal collision distance between the vehicle and the pedestrian, and lateral collision distance are obtained; based on the vehicle speed, pedestrian movement speed, longitudinal collision distance, and lateral collision distance, the longitudinal collision time and lateral collision time between the vehicle and the pedestrian are determined.

[0190] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0191] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0192] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A vehicle emergency braking method, characterized in that, The method includes: When a pedestrian is detected ahead, the vehicle's current road conditions are assessed. If the road condition is a curve and lane markings exist, then the vehicle speed is obtained; the vehicle's direction of travel is taken as the positive X-axis, and the direction perpendicular to the X-axis and pointing to the left of the vehicle's front is taken as the positive Y-axis. The positive X-axis is the longitudinal direction, and the positive Y-axis is the lateral direction; based on the longitudinal and lateral directions, the pedestrian's longitudinal speed, pedestrian's lateral speed, and the longitudinal and lateral distances between the vehicle and the pedestrian are determined; the longitudinal distance is taken as the relative longitudinal distance; the pedestrian's longitudinal speed and lateral speed are taken as the pedestrian's movement speed; a formula for calculating the relative lateral distance is determined; based on the relative longitudinal distance... Using the formula for calculating the relative lateral distance, the relative lateral distance between the lane line and the pedestrian is determined as the relative lateral distance; based on the vehicle speed, the pedestrian's longitudinal speed, and the relative longitudinal distance, the longitudinal collision time between the vehicle and the pedestrian is determined; if the longitudinal collision time is greater than a first preset value, the system returns to determining the longitudinal collision time between the vehicle and the pedestrian based on the vehicle speed, the pedestrian's longitudinal speed, and the relative longitudinal distance; if the longitudinal collision time is not greater than the first preset value, the lateral collision time between the vehicle and the pedestrian is determined based on the pedestrian's lateral speed and the relative lateral distance. Based on the lateral collision time and longitudinal collision time, it is determined whether the vehicle will collide with the pedestrian. If a collision is expected, braking is performed. The determination of the relative lateral distance between the lane line and the pedestrian, based on the relative longitudinal distance and the formula for calculating the relative lateral distance, includes: Let the pedestrian's location be point A, and the curve where the vehicle is located be the target lane. Starting from pedestrian point A, draw a ray along the positive Y-axis, and mark the point of collision on that ray as point E. AE represents the relative lateral distance. Draw another ray along the opposite X-axis, and mark the point on the Y-axis where that ray lands as point C. AC represents the relative longitudinal distance between the pedestrian and vehicle during the collision. The formula for calculating the lateral distance AE is as follows: ; Determining the lateral collision time between the vehicle and the pedestrian based on the pedestrian's lateral velocity and the relative lateral distance includes: Let the pedestrian's location be point A, and the curve where the vehicle is located be the target lane. Starting from pedestrian point A, draw a ray along the positive Y-axis. The point on the target lane line closest to the pedestrian is designated as point F. AF represents the minimum lateral distance for a collision between the pedestrian and the vehicle. With the vehicle at point E, the intersection of the ray and the side of the vehicle furthest from the pedestrian (the vehicle's left side) is designated as point D. AD represents the maximum lateral distance for a collision between the pedestrian and the vehicle. Obtain the lane width. and vehicle width Based on relative lateral distance AE and lane width The minimum lateral distance AF between pedestrians and vehicles is determined by the following formula: , Based on the relative lateral distance AE and the vehicle width The maximum lateral distance AD ​​is determined by the following formula: ; Based on the minimum lateral distance AF and the pedestrian's lateral velocity during the AF phase. Determine the time of the first lateral collision. The formula is: , in, It is the pedestrian's velocity during the AF phase; based on the relative lateral distance AF and the pedestrian's lateral velocity. Determine the second lateral collision time; the pedestrian's lateral velocity during the DF phase. , the formula is as follows: , in, It's exercise time. It is a coefficient. It refers to the instantaneous velocity during the AD phase. It is the time delay, instantaneous velocity multiplied by Represent the instantaneous velocity value during the previous cycle; calculate the second lateral collision time. The formula is: , Based on maximum lateral distance AD ​​and pedestrian lateral velocity Determine the time of the third lateral collision. The formula is: , First lateral collision time Second lateral collision time and third lateral collision time Together, they constitute the lateral collision time.

2. The method according to claim 1, characterized in that, The determination of whether a collision will occur with the pedestrian based on the lateral collision time and the longitudinal collision time includes: If the first lateral collision time is greater than the longitudinal collision time, then no collision will occur with the pedestrian; If the first lateral collision time is not greater than the longitudinal collision time, and the second lateral collision time is greater than the longitudinal collision time, then a first collision event will occur with the pedestrian. If the second lateral collision time plus the first lateral collision time is not greater than the longitudinal collision time, and the third lateral collision time is greater than the longitudinal collision time, then a second collision event will occur with the pedestrian. If the third lateral collision time is not greater than the longitudinal collision time, then a collision with a pedestrian will not occur.

3. A vehicle emergency braking device, characterized in that, The device includes: The detection module is used to determine the road conditions of the road where the vehicle is currently located when a pedestrian is detected ahead. The time calculation module is used to obtain vehicle speed if the road condition is a curve and lane markings exist; taking the vehicle's travel direction as the positive X-axis, and the direction perpendicular to the X-axis and pointing to the left of the vehicle's front as the positive Y-axis, the positive X-axis is the longitudinal direction, and the positive Y-axis is the lateral direction; based on the longitudinal and lateral directions, it determines the pedestrian's longitudinal speed, pedestrian's lateral speed, and the longitudinal and lateral distances between the vehicle and the pedestrian; it uses the longitudinal distance as the relative longitudinal distance; it uses the pedestrian's longitudinal speed and lateral speed as the pedestrian's movement speed; it determines the formula for calculating the relative lateral distance; and based on the relative... The longitudinal distance and the formula for calculating the relative lateral distance are used to determine the relative lateral distance between the lane line and the pedestrian, which is then used as the relative lateral distance. Based on the vehicle speed, the pedestrian's longitudinal speed, and the relative longitudinal distance, the longitudinal collision time between the vehicle and the pedestrian is determined. If the longitudinal collision time is greater than a first preset value, the system returns to determining the longitudinal collision time between the vehicle and the pedestrian based on the vehicle speed, the pedestrian's longitudinal speed, and the relative longitudinal distance. If the longitudinal collision time is not greater than the first preset value, the lateral collision time between the vehicle and the pedestrian is determined based on the pedestrian's lateral speed and the relative lateral distance. The braking module is used to determine whether the vehicle will collide with the pedestrian based on the lateral collision time and the longitudinal collision time. If a collision is expected, braking is performed. The determination of the relative lateral distance between the lane line and the pedestrian, based on the relative longitudinal distance and the formula for calculating the relative lateral distance, includes: Let the pedestrian's location be point A, and the curve where the vehicle is located be the target lane. Starting from pedestrian point A, draw a ray along the positive Y-axis, and mark the point of collision on that ray as point E. AE represents the relative lateral distance. Draw another ray along the opposite X-axis, and mark the point on the Y-axis where that ray lands as point C. AC represents the relative longitudinal distance between the pedestrian and vehicle during the collision. The formula for calculating the lateral distance AE is as follows: ; in, It is the distance from the front of the car to the center line of the lane. It is the angle between the front of the car and the center line of the lane. It's curvature. It is the rate of change of curvature; Determining the lateral collision time between the vehicle and the pedestrian based on the pedestrian's lateral velocity and the relative lateral distance includes: Let the pedestrian's location be point A, and the curve where the vehicle is located be the target lane. Starting from pedestrian point A, draw a ray along the positive Y-axis. The point on the target lane line closest to the pedestrian is designated as point F. AF represents the minimum lateral distance for a collision between the pedestrian and the vehicle. With the vehicle at point E, the intersection of the ray and the side of the vehicle furthest from the pedestrian (the vehicle's left side) is designated as point D. AD represents the maximum lateral distance for a collision between the pedestrian and the vehicle. Obtain the lane width. and vehicle width Based on relative lateral distance AE and lane width The minimum lateral distance AF between pedestrians and vehicles is determined by the following formula: , Based on the relative lateral distance AE and the vehicle width The maximum lateral distance AD ​​is determined by the following formula: ; Based on the minimum lateral distance AF and the pedestrian's lateral velocity during the AF phase. Determine the time of the first lateral collision. The formula is: , in, It is the pedestrian's velocity during the AF phase; based on the relative lateral distance AF and the pedestrian's lateral velocity. Determine the second lateral collision time; the pedestrian's lateral velocity during the DF phase. , the formula is as follows: , in, It's exercise time. It is a coefficient. It refers to the instantaneous velocity during the AD phase. It is the time delay, instantaneous velocity multiplied by Represent the instantaneous velocity value during the previous cycle; calculate the second lateral collision time. The formula is: , Based on maximum lateral distance AD ​​and pedestrian lateral velocity Determine the time of the third lateral collision. The formula is: , First lateral collision time Second lateral collision time and third lateral collision time Together, they constitute the lateral collision time.

4. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 2.

5. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 2.

6. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 2.

Citation Information

Patent Citations

  • Vehicle collision prediction method, controller and storage medium

    CN116343524A

  • Collision avoidance support device and collision avoidance support method

    JP2014093040A