Method for predicting vehicle collision, controller, and storage medium

Abstract

The application discloses a vehicle collision prediction method, a controller and a storage medium. The method comprises the following steps: acquiring motion information of a target pedestrian and a speed of a vehicle, wherein the motion information of the target pedestrian comprises a longitudinal position of the target pedestrian; predicting a collision time according to the motion information of the target pedestrian and the speed of the vehicle; determining a lateral position of the target pedestrian after the collision time and position information of the vehicle after the collision time based on the collision time; determining a dangerous area according to the longitudinal position of the target pedestrian and the position information of the vehicle after the collision time; judging whether the lateral position of the target pedestrian after the collision time is in the dangerous area; and sending an alarm signal and controlling the vehicle to brake in the case that the lateral position of the target pedestrian after the collision time is in the dangerous area. According to the longitudinal position of the target pedestrian and the position information of the vehicle after the collision time, the dangerous area is determined, the range of the dangerous area can be adjusted in real time, and the complex and changeable vehicle driving scene is adapted.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of vehicle auxiliary driving, and particularly relates to a vehicle collision prediction method, a controller and a storage medium. BACKGROUND

[0002] In order to reduce the occurrence of automobile collision accidents and improve traffic safety, automobile manufacturers and suppliers pay more and more attention to passive safety technology and active safety technology of automobiles. At present, domestic researchers have a lot of research on safety distance models and control algorithms. For example, a neural network method is used to study an automobile collision avoidance algorithm, that is, a cooperative warning algorithm based on a fuzzy neural network is proposed, and the algorithm is applied to a forward collision warning system. However, the robustness of the forward collision warning system based on the neural network method is poor. Moreover, the prior art needs to pre-set a dangerous area, and the size of the dangerous area range is usually fixed, which cannot adapt to complex and variable vehicle driving scenes. Therefore, the prior art has the problems of poor robustness and inability to adapt to complex and variable vehicle driving scenes. SUMMARY

[0003] The purpose of the embodiments of the present application is to provide a vehicle collision prediction method, a controller and a storage medium, so as to solve the problems of poor robustness and inability to adapt to complex and variable vehicle driving scenes in the prior art.

[0004] In order to achieve the above-mentioned purpose, the first aspect of the present application provides a vehicle collision prediction method, comprising:

[0005] obtaining motion information of a target pedestrian and a speed of a vehicle, the motion information of the target pedestrian comprising a longitudinal position of the target pedestrian;

[0006] predicting a collision time according to the motion information of the target pedestrian and the speed of the vehicle;

[0007] determining a lateral position of the target pedestrian after the collision time and position information of the vehicle after the collision time based on the collision time;

[0008] determining a dangerous area according to the longitudinal position of the target pedestrian and the position information of the vehicle after the collision time;

[0009] judging whether the lateral position of the target pedestrian after the collision time is in the dangerous area or not;

[0010] in a case where the lateral position of the target pedestrian after the collision time is in the dangerous area, sending an alarm signal and controlling the vehicle to brake.

[0011] In the embodiments of the present application, the dangerous area is determined according to the longitudinal position of the target pedestrian and the position information of the vehicle after the collision time, comprising:

[0012] determining a position interval in which the longitudinal position of the target pedestrian is located;

[0013] The danger zone is determined based on the longitudinal position of the target pedestrian and the vehicle's position after the collision.

[0014] In this embodiment of the application, the motion information of the target pedestrian also includes the longitudinal velocity of the target pedestrian. Predicting the collision time based on the motion information of the target pedestrian and the speed of the vehicle includes:

[0015] The collision time is predicted based on the longitudinal position of the target pedestrian, the longitudinal velocity of the target pedestrian, and the speed of the vehicle.

[0016] In this embodiment of the application, the motion information of the target pedestrian includes the lateral velocity and lateral position of the target pedestrian, and the position information of the vehicle after the collision time includes the lateral position of the vehicle after the collision time. Determining the lateral position of the target pedestrian after the collision time includes:

[0017] Determine the position deviation value, which is the deviation between the lateral position of the vehicle and the lateral position of the target pedestrian after the collision time;

[0018] The lateral position of the target pedestrian after the collision time is determined based on the positional deviation value, the lateral velocity of the target pedestrian, and the collision time.

[0019] In this embodiment of the application, the lateral position of the target pedestrian after the collision time satisfies formula (1):

[0020] y pre =dy-v y t; (1)

[0021] Among them, y pre Let v be the lateral position of the target pedestrian after the collision time, dy be the position deviation value, and v be the position deviation value. y Let t be the lateral velocity of the target pedestrian, and t be the collision time.

[0022] In this embodiment of the application, determining the positional deviation value includes:

[0023] The position deviation value is determined based on the lateral position of the target pedestrian, the longitudinal position of the target pedestrian, and the turning radius of the vehicle.

[0024] In this embodiment of the application, the positional deviation value satisfies formula (2):

[0025]

[0026] Where dy is the position deviation value, y is the lateral position of the target pedestrian, R is the turning radius of the vehicle, and x is the longitudinal position of the target pedestrian.

[0027] In this embodiment of the application, obtaining the movement information of the target pedestrian includes:

[0028] The motion information of the target pedestrian is acquired through information fusion.

[0029] The second aspect of the present application provides a controller, comprising:

[0030] a memory configured to store instructions; and

[0031] a processor configured to call the instructions from the memory and capable of implementing the above-mentioned vehicle collision prediction method when executing the instructions.

[0032] The third aspect of the present application provides a machine readable storage medium, which stores instructions for causing a machine to execute the above-mentioned vehicle collision prediction method.

[0033] Through the above technical solution, firstly, the motion information of the target pedestrian and the speed of the vehicle are acquired, and the motion information of the target pedestrian includes the longitudinal position of the target pedestrian. Then, the collision time is predicted according to the motion information of the target pedestrian and the speed of the vehicle. Subsequently, the lateral position of the target pedestrian after the collision time and the position information of the vehicle after the collision time are determined based on the collision time. Then, the dangerous area is determined according to the longitudinal position of the target pedestrian and the position information of the vehicle after the collision time, and it is further judged whether the lateral position of the target pedestrian after the collision time is in the dangerous area. Finally, in the case that the lateral position of the target pedestrian after the collision time is in the dangerous area, an alarm signal is sent and the vehicle is controlled to brake. According to the longitudinal position of the target pedestrian and the position information of the vehicle after the collision time, the dangerous area is determined in the present application, which can adjust the range of the dangerous area in real time, adapt to complex and changeable vehicle driving scenes, and improve the robustness.

[0034] Other features and advantages of the present application will be described in detail in the following specific implementation part. BRIEF DESCRIPTION OF DRAWINGS

[0035] The accompanying drawings are included to provide a further understanding of the present application, and constitute a part of the specification, and are used together with the following specific implementation to explain the present application, but do not constitute a limitation on the present application. In the drawings:

[0036] Figure 1 The flow chart of a vehicle collision prediction method according to an embodiment of the present application is schematically shown;

[0037] Figure 2 The schematic diagram of collision prediction in a vehicle left turn scene according to a specific embodiment of the present application is schematically shown;

[0038] Figure 3 The structural block diagram of a controller according to an embodiment of the present application is schematically shown. Detailed Implementation

[0039] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are only for illustration and explanation of the embodiments of this application and are not intended to limit the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0040] It should be noted that if the embodiments of this application involve directional indicators (such as up, down, left, right, front, back, etc.), the directional indicators are only used to explain the relative positional relationship and movement of the components in a certain specific posture (as shown in the figure). If the specific posture changes, the directional indicators will also change accordingly.

[0041] Furthermore, if the embodiments of this application involve descriptions such as "first" or "second," these descriptions are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, features defined with "first" or "second" may explicitly or implicitly include at least one of those features. Additionally, the technical solutions of various embodiments can be combined with each other, but this must be based on the ability of those skilled in the art to implement them. If the combination of technical solutions is contradictory or impossible to implement, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection claimed in this application.

[0042] Figure 1 A flowchart illustrating a vehicle collision prediction method according to an embodiment of this application is shown schematically. Figure 1 As shown in the figure, this application provides a method for predicting vehicle collisions, which may include the following steps:

[0043] Step 101: Obtain the motion information of the target pedestrian and the speed of the vehicle. The motion information of the target pedestrian includes the longitudinal position of the target pedestrian.

[0044] Step 102: Predict the collision time based on the target pedestrian's movement information and the vehicle's speed;

[0045] Step 103: Based on the collision time, determine the lateral position of the target pedestrian and the position information of the vehicle after the collision time;

[0046] Step 104: Determine the danger zone based on the longitudinal position of the target pedestrian and the vehicle's position information after the collision time;

[0047] Step 105, judging whether the lateral position of the target pedestrian after the collision time is in the dangerous area;

[0048] Step 106, in the case that the lateral position of the target pedestrian after the collision time is in the dangerous area, sending an alarm signal and controlling the vehicle braking.

[0049] The prediction method can be applied to the vehicle turning scene, and can be used to predict whether the vehicle will collide with the pedestrian during the turning process.

[0050] In the embodiments of the present application, first, the controller can determine the target pedestrian and obtain the motion information of the target pedestrian. The target pedestrian is a pedestrian who may collide with the vehicle, and can be determined according to the motion information of the pedestrian, the driving direction of the vehicle and the speed of the vehicle. The motion information of the target pedestrian includes the lateral speed, the lateral position, the longitudinal speed and the longitudinal position of the target pedestrian. At the same time, the controller can also obtain the speed of the current vehicle. According to the motion information of the target pedestrian and the speed of the vehicle, the controller can predict the collision time, that is, predict how long the vehicle and the target pedestrian may collide. After determining the collision time, the controller can determine the lateral position of the target pedestrian after the collision time according to the lateral speed of the target pedestrian and the collision time, and determine the position information of the vehicle after the collision time according to the speed of the vehicle and the collision time. Subsequently, the controller can determine the dangerous area according to the longitudinal position of the target pedestrian and the position information of the vehicle after the collision time, and judge whether the lateral position of the target pedestrian after the collision time is in the dangerous area. In the case that the lateral position of the target pedestrian after the collision time is in the dangerous area, the controller sends an alarm signal and controls the vehicle braking. In the case that the lateral position of the target pedestrian after the collision time is not in the dangerous area, the controller does not send an alarm signal, and the vehicle normally drives. In this way, the controller can predict whether the vehicle will collide with the target pedestrian during the turning process, reduce the possibility of accidents, and ensure the safety of the vehicle and the target pedestrian.

[0051] By the technical solution, firstly, the motion information of the target pedestrian and the speed of the vehicle are acquired, the motion information of the target pedestrian includes the longitudinal position of the target pedestrian. Then, the collision time is predicted according to the motion information of the target pedestrian and the speed of the vehicle. Subsequently, the lateral position of the target pedestrian after the collision time and the position information of the vehicle after the collision time are determined based on the collision time. Then, the dangerous area is determined according to the longitudinal position of the target pedestrian and the position information of the vehicle after the collision time, and it is further judged whether the lateral position of the target pedestrian after the collision time is in the dangerous area. Finally, in the case that the lateral position of the target pedestrian after the collision time is in the dangerous area, an alarm signal is sent and the vehicle is controlled to brake. According to the longitudinal position of the target pedestrian and the position information of the vehicle after the collision time, the dangerous area is determined in the application, the range of the dangerous area can be adjusted in real time, the complex and changeable vehicle driving scene is adapted, and the robustness is improved.

[0052] In the embodiment of the application, acquiring the motion information of the target pedestrian can include:

[0053] The motion information of the target pedestrian is acquired through information fusion.

[0054] Specifically, information fusion refers to an information processing process of analyzing and comprehensively processing a plurality of sensor data obtained, so as to determine the motion information of the target pedestrian. In the prediction process of the vehicle collision, the controller can determine the motion information of the target pedestrian through information fusion based on the plurality of sensor data received.

[0055] Figure 2 A schematic diagram of collision prediction in a vehicle left-turn scene according to an embodiment of the application is schematically shown. As shown in the figure, Figure 2 Taking the vehicle left-turn scene as an example, a coordinate system is established with the front direction of the vehicle as the longitudinal positive direction and the left side of the vehicle as the lateral positive direction, x is the longitudinal position of the target pedestrian, y is the lateral position of the target pedestrian, v y is the lateral speed of the target pedestrian, and v is the speed of the vehicle, and dy is the position deviation value. In the embodiment of the application, the motion information of the target pedestrian further includes the longitudinal speed of the target pedestrian, and step 102, predicting the collision time according to the motion information of the target pedestrian and the speed of the vehicle, can include:

[0056] The collision time is predicted according to the longitudinal position of the target pedestrian, the longitudinal speed of the target pedestrian and the speed of the vehicle.

[0057] Specifically, the controller can predict the collision time according to the motion information of the target pedestrian and the speed of the vehicle. The motion information of the target pedestrian includes the longitudinal speed of the target pedestrian. The controller can predict the collision time according to the longitudinal position of the target pedestrian, the longitudinal speed of the target pedestrian and the speed of the vehicle. The collision time satisfies formula (3):

[0058]

[0059] Where t is the collision time, x is the longitudinal position of the target pedestrian, and v is the vehicle speed. x The longitudinal velocity of the target pedestrian is used. This allows the controller to predict the potential collision time between the vehicle and the target pedestrian.

[0060] In this embodiment of the application, step 104, determining the danger zone based on the longitudinal position of the target pedestrian and the vehicle's position information after the collision time, may include:

[0061] Determine the longitudinal position range of the target pedestrian;

[0062] The danger zone is determined based on the longitudinal position of the target pedestrian and the vehicle's position after the collision.

[0063] Specifically, the closer the pedestrian's longitudinal position is to the vehicle, the greater the probability of a collision is considered, thus a larger danger zone is set. Conversely, the farther the pedestrian's longitudinal position is from the vehicle, the lower the probability of a collision is considered, thus a smaller danger zone is set. Therefore, the controller can determine the range of the pedestrian's longitudinal position, which can be set according to actual conditions. Based on this range, the controller can determine the width of the danger zone. Furthermore, since the danger zone's position updates as the vehicle moves, it is necessary to combine the vehicle's position information after the collision time to determine the specific location of the danger zone. In one example, multiple position ranges can be pre-determined, such as a first position range, a second position range, and a third position range, where the first position range is 1 to 2 meters. When the distance between the pedestrian's longitudinal position and the vehicle is detected to be 1.5 meters, the pedestrian's longitudinal position is considered to be within the first position range, and the width of the danger zone can be set to 2 meters. In this way, the controller can determine the width and location of the danger zone.

[0064] like Figure 2 As shown in the embodiments of this application, determining the positional deviation value may include:

[0065] The position deviation value is determined based on the lateral position of the target pedestrian, the longitudinal position of the target pedestrian, and the turning radius of the vehicle.

[0066] Specifically, the controller can determine the position deviation value. The controller can acquire the target pedestrian's motion information, including the pedestrian's lateral and longitudinal positions. Furthermore, the controller can acquire the vehicle's turning radius. By combining the pedestrian's lateral and longitudinal positions with the vehicle's turning radius, the position deviation value can be further determined.

[0067] In the embodiment of the present application, the position deviation value can satisfy formula (2):

[0068]

[0069] wherein dy is the position deviation value, y is the lateral position of the target pedestrian, R is the turning radius of the vehicle, and x is the longitudinal position of the target pedestrian.

[0070] Specifically, the controller can determine the position deviation value. The controller can obtain the motion information of the target pedestrian, wherein the motion information of the target pedestrian includes the lateral position of the target pedestrian and the longitudinal position of the target pedestrian. And the controller can obtain the turning radius of the vehicle. In combination with the lateral position of the target pedestrian, the longitudinal position of the target pedestrian and the turning radius of the vehicle, the position deviation value can be further determined. Wherein the turning radius of the vehicle satisfies formula (4):

[0071]

[0072] wherein R is the turning radius of the vehicle, v is the speed of the vehicle, and ω is the yaw rate.

[0073] As shown in Figure 2 In the embodiment of the present application, the motion information of the target pedestrian includes the lateral speed of the target pedestrian and the lateral position of the target pedestrian, the position information of the vehicle after the collision time includes the lateral position of the vehicle after the collision time, and the determination of the lateral position of the target pedestrian after the collision time can include:

[0074] determining the position deviation value, the position deviation value being the deviation value of the lateral position of the vehicle after the collision time and the lateral position of the target pedestrian;

[0075] determining the lateral position of the target pedestrian after the collision time according to the position deviation value, the lateral speed of the target pedestrian and the collision time.

[0076] Specifically, the controller can predict the lateral position of the target pedestrian after the collision time. The controller needs to determine the position deviation value first. The position deviation value is the deviation value of the lateral position of the vehicle after the collision time and the lateral position of the target pedestrian. Then the lateral position of the target pedestrian after the collision time can be determined according to the position deviation value, the lateral speed of the target pedestrian and the collision time. In this way, the lateral position of the target pedestrian after the collision time can be determined, so that the controller can subsequently determine whether the lateral position of the target pedestrian after the collision time is in the dangerous area.

[0077] In the embodiment of the present application, the lateral position of the target pedestrian after the collision time can satisfy formula (1):

[0078] y pre = dy-vy t; (1)

[0079] wherein y pre is the lateral position of the target pedestrian after the collision time, dy is the position deviation value, v y is the lateral speed of the target pedestrian, and t is the collision time.

[0080] Specifically, the controller can determine the lateral position of the target pedestrian after the collision time according to the position deviation value, the lateral speed of the target pedestrian, and the collision time. In this way, the controller can subsequently determine whether the lateral position of the target pedestrian after the collision time is in the dangerous region.

[0081] In addition, according to the motion information of the target pedestrian, the controller can also determine the motion scenario of the target pedestrian. Table 1 schematically shows a motion scenario of a target pedestrian according to an embodiment of the present application. As shown in Table 1, the motion scenario of the target pedestrian can be distinguished according to the lateral speed v y , the lateral position y, the longitudinal speed v x , and the longitudinal position x of the target pedestrian. In this way, the alarm signal can be more accurate.

[0082] Table 1

[0083] Position of target pedestrian Speed of target pedestrian Motion scenario of target pedestrian x > 0, y < 0 v y >0, v x =0]]> Right side cross x > 0, y > 0 v y <0,v x =0]]> Left side cross x > 0, y < 0 v y <0,v x =0]]> Right side away x > 0, y > 0 v y >0, v x =0]]> Left side away x>0 v y = 0, v x = 0]]> Stationary x > 0, y < 0 v y >0, v x >0]]> Right side against vehicle cross x > 0, y > 0 v y <0, v x >0]]> Left side against vehicle cross x > 0, y < 0 v y >0, v x <0]] Right side with vehicle cross x > 0, y > 0 v y <0,v x <0]]> Left side with vehicle cross

[0084] Figure 3 A structural block diagram of a controller according to an embodiment of the present application is schematically shown. As shown in FIG. 3, the controller according to an embodiment of the present application can include: Figure 3 a memory 310 configured to store instructions; and

[0085] a processor 320 configured to call the instructions from the memory 310 and capable of implementing the above-mentioned vehicle collision prediction method when executing the instructions.

[0086] Specifically, in the embodiment of the present application, the processor 320 can be configured to:

[0087] obtain motion information of a target pedestrian and a speed of a vehicle, the motion information of the target pedestrian including a longitudinal position of the target pedestrian;

[0088] predict a collision time according to the motion information of the target pedestrian and the speed of the vehicle;

[0089] determine a lateral position of the target pedestrian after the collision time and position information of the vehicle after the collision time based on the collision time;

[0090] determine a dangerous region according to the longitudinal position of the target pedestrian and the position information of the vehicle after the collision time;

[0091] determine a dangerous region according to the longitudinal position of the target pedestrian and the position information of the vehicle after the collision time;

[0092] determine whether the lateral position of the target pedestrian after the collision time is in the dangerous area;

[0093] in a case where the lateral position of the target pedestrian after the collision time is in the dangerous area, send an alarm signal and control vehicle braking.

[0094] Further, the processor 320 can be further configured to:

[0095] determine a position interval in which the longitudinal position of the target pedestrian is located;

[0096] determine the dangerous area according to the position interval in which the longitudinal position of the target pedestrian is located and the position information of the vehicle after the collision time.

[0097] Further, the processor 320 can be further configured to:

[0098] predict the collision time according to the longitudinal position of the target pedestrian, the longitudinal speed of the target pedestrian and the speed of the vehicle.

[0099] Further, the processor 320 can be further configured to:

[0100] determine a position deviation value, the position deviation value being a deviation value of the lateral position of the vehicle after the collision time and the lateral position of the target pedestrian;

[0101] determine the lateral position of the target pedestrian after the collision time according to the position deviation value, the lateral speed of the target pedestrian and the collision time.

[0102] In the embodiments of the present application, the lateral position of the target pedestrian after the collision time satisfies formula (1):

[0103] y pre = dy-v y t; (1)

[0104] wherein y pre is the lateral position of the target pedestrian after the collision time, dy is the position deviation value, v y is the lateral speed of the target pedestrian, and t is the collision time.

[0105] Further, the processor 320 can be further configured to:

[0106] determine the position deviation value according to the lateral position of the target pedestrian, the longitudinal position of the target pedestrian and the turning radius of the vehicle.

[0107] In the embodiments of the present application, the position deviation value satisfies formula (2):

[0108]

[0109] wherein dy is a position deviation value, y is a lateral position of the target pedestrian, R is a turning radius of the vehicle, and x is a longitudinal position of the target pedestrian.

[0110] Further, the processor 320 can be further configured to:

[0111] acquire the motion information of the target pedestrian through information fusion.

[0112] Through the technical solution described above, firstly, the motion information of the target pedestrian and the speed of the vehicle are acquired, and the motion information of the target pedestrian includes the longitudinal position of the target pedestrian. Then, the collision time is predicted according to the motion information of the target pedestrian and the speed of the vehicle. Subsequently, the lateral position of the target pedestrian after the collision time and the position information of the vehicle after the collision time are determined based on the collision time. Then, the dangerous area is determined according to the longitudinal position of the target pedestrian and the position information of the vehicle after the collision time, and it is further judged whether the lateral position of the target pedestrian after the collision time is in the dangerous area. Finally, in the case that the lateral position of the target pedestrian after the collision time is in the dangerous area, an alarm signal is sent and the vehicle is controlled to brake. According to the longitudinal position of the target pedestrian and the position information of the vehicle after the collision time, the dangerous area is determined in the present application, which can adjust the range of the dangerous area in real time, adapt to complex and changeable vehicle driving scenes, and improve the robustness.

[0113] The embodiment of the present application also provides a machine readable storage medium, which stores instructions for causing a machine to execute the vehicle collision prediction method described above.

[0114] Those skilled in the art should understand that embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can adopt a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can adopt a computer program product in the form of being implemented on one or more computer usable storage media containing computer usable program codes (including but not limited to disk storage, CD-ROM, optical storage, etc.).

[0115] The present application is described with reference to flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of the flows and / or blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to produce a machine, so that the instructions executed by the computer or other programmable data processing devices produce a device for implementing the functions described in the flowcharts and / or block diagrams. Figure 1 one flow or multiple flows and / or blocks Figure 1an apparatus to perform each block or blocks of the flow or flows and / or steps of the function(s) specified in the block or blocks.

[0116] These computer program instructions can also be stored in a computer- readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the flow Figure 1 an apparatus to perform each block or blocks of the flow or flows and / or steps of the function(s) specified in the block or blocks. Figure 1 an apparatus to perform each block or blocks of the flow or flows and / or steps of the function(s) specified in the block or blocks.

[0117] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the flow Figure 1 an apparatus to perform each block or blocks of the flow or flows and / or steps of the function(s) specified in the block or blocks. Figure 1 an apparatus to perform each block or blocks of the flow or flows and / or steps of the function(s) specified in the block or blocks.

[0118] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0119] The memory can include non-persistent memory and / or volatile memory, such as random access memory (RAM) and / or cache memory. The memory can also include non-volatile memory, such as read-only memory (ROM), electrically programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), flash memory, or a combination of non-volatile memories. The memory is an example of computer-readable media.

[0120] Computer-readable media includes permanent and non-permanent, removable and non-removable media implemented in any method or technology for storage of information such as computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD), or other optical storage, magnetic cassettes, magnetic tapes, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible to a computing device. According to the definition herein, computer-readable media does not include transitory media, such as modulated data signals and carrier waves.

[0121] It should also be noted that the terms "comprising", "comprises" or other variations thereof are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can also include other elements not expressly listed or inherent to such process, method, article, or apparatus.

[0122] The above embodiments are only used to illustrate the present application, but not to limit it. Instead of the above, various modifications and changes can be made to the application by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the application shall fall into the scope of the claims of the application.

Claims

1. A method of predicting a vehicle collision, characterized by, The method comprises: obtaining motion information of a target pedestrian and a speed of a vehicle, the motion information of the target pedestrian comprising a longitudinal position of the target pedestrian; predicting a collision time according to the motion information of the target pedestrian and the speed of the vehicle; determining a lateral position of the target pedestrian after the collision time and position information of the vehicle after the collision time based on the collision time; determining a dangerous area according to the longitudinal position of the target pedestrian and the position information of the vehicle after the collision time; judging whether the lateral position of the target pedestrian after the collision time is in the dangerous area; in a case where the lateral position of the target pedestrian after the collision time is in the dangerous area, sending an alarm signal and controlling the vehicle to brake; wherein the determining of the dangerous area according to the longitudinal position of the target pedestrian and the position information of the vehicle after the collision time comprises: determining a position interval in which the longitudinal position of the target pedestrian is located; and determining the dangerous area according to the position interval in which the longitudinal position of the target pedestrian is located and the position information of the vehicle after the collision time.

2. The prediction method of claim 1, wherein, The motion information of the target pedestrian further comprises a longitudinal speed of the target pedestrian, and the predicting of the collision time according to the motion information of the target pedestrian and the speed of the vehicle comprises: predicting the collision time according to the longitudinal position of the target pedestrian, the longitudinal speed of the target pedestrian and the speed of the vehicle.

3. The prediction method of claim 1, wherein, The motion information of the target pedestrian comprises a lateral speed of the target pedestrian and a lateral position of the target pedestrian, and the position information of the vehicle after the collision time comprises a lateral position of the vehicle after the collision time, and the determining of the lateral position of the target pedestrian after the collision time comprises: determining a position deviation value, the position deviation value being a deviation value of the lateral position of the vehicle after the collision time and the lateral position of the target pedestrian; determining the lateral position of the target pedestrian after the collision time according to the position deviation value, the lateral speed of the target pedestrian and the collision time.

4. The prediction method of claim 3, wherein, The lateral position of the target pedestrian after the collision time satisfies formula (1): ； （1） wherein, is a lateral position of the target pedestrian after a time to collision, is the position offset value, is a lateral velocity of the target pedestrian, is the time to collision.

5. The prediction method of claim 3, wherein, The determining of the position deviation value comprises: determining the position deviation value according to the lateral position of the target pedestrian, the longitudinal position of the target pedestrian and a turning radius of the vehicle.

6. The prediction method of claim 5, wherein, The position deviation value satisfies formula (2): ；（2） wherein, is the position offset value, is the lateral position of the target pedestrian, is the turning radius of the vehicle, is the longitudinal position of the target pedestrian.

7. The prediction method of claim 1, wherein, The obtaining of the motion information of the target pedestrian comprises: obtaining the motion information of the target pedestrian through information fusion.

8. A controller characterized by comprising: The method comprises: a memory configured to store instructions; and a processor configured to call the instructions from the memory and capable of realizing the method for predicting a vehicle collision according to any one of claims 1 to 7 when executing the instructions.

9. A machine-readable storage medium, characterized in that, The machine-readable storage medium stores instructions for causing a machine to execute the method for predicting a vehicle collision according to any one of claims 1 to 7.

Images