Vehicle collision prediction methods, readable storage media, program products, and electronic devices

Abstract

This application relates to the field of driving technology, and in particular to a vehicle collision prediction method, a readable storage medium, a program product, and an electronic device. This vehicle collision prediction method can predict the trajectory of a vehicle and a target obstacle over a future period, then determine the relative positions of the vehicle and the target obstacle over that period, and predict the collision situation based on the distances between various target points of the target obstacle and various ends of the vehicle. This enables the prediction of the specific collision time and location between the vehicle and the target obstacle, improving prediction accuracy and thus enhancing driving safety.

Description

Technical Field

[0001] This application relates to the field of driving technology, and in particular to a vehicle collision prediction method, a readable storage medium, a program product, and an electronic device. Background Technology

[0002] During vehicle operation, collision risk can be predicted based on the vehicle's speed and surrounding obstacles (such as other vehicles, pedestrians, traffic equipment, or buildings). However, the accuracy of current collision risk prediction is not high; for example, the prediction of whether a collision will occur and the prediction of when a collision will occur are not accurate enough. Summary of the Invention

[0003] This application provides a vehicle collision prediction method, a readable storage medium, a program product, and an electronic device.

[0004] In a first aspect, embodiments of this application provide a vehicle collision prediction method. The method includes: determining a first predicted trajectory of the target obstacle within a future first time period based on historical motion information of the target obstacle; and determining a second predicted trajectory of the vehicle within the first time period based on historical motion information of the vehicle. Based on the first and second predicted trajectories, determining a first pose information of the target obstacle relative to the vehicle within the first time period. Based on the first pose information, determining first time points and target position information corresponding to multiple target points of the target obstacle, wherein the first time point indicates the time when the distance between the corresponding target point and the target end side of the vehicle is a preset distance, and the target position information indicates the target position information relative to the vehicle when the distance between the corresponding target point and the target end side is a preset distance. Based on the multiple target position information and the position of the target end side, predicting the collision risk between the target end side of the vehicle and the target obstacle.

[0005] By employing the above approach, when determining the collision risk between a target obstacle and the vehicle, multiple target points of the target obstacle and multiple ends of the vehicle are considered. This means that both the size of the vehicle and the target vehicle are taken into account, enabling a more accurate prediction of the location and time of the collision. This facilitates the issuance of accurate warnings to the user, such as prompting them to slow down, yield, avoid the obstacle, or stop to observe, thus ensuring driving safety.

[0006] In one possible implementation of the first aspect above, the target end side of the vehicle includes at least one of the following end sides: a first end side and a second end side opposite to each other in the length direction, and a third end side and a fourth end side opposite to each other in the width direction.

[0007] In one possible implementation of the first aspect described above, the first pose information includes the position of the centroid of the target obstacle in the vehicle coordinate system and the first deflection angle of the reference axis of the target obstacle relative to the first coordinate axis of the vehicle coordinate system. Based on the first pose information, the first time point and target position information corresponding to multiple target points of the target obstacle are determined, including: based on the relative positions of the multiple target points of the target obstacle and the centroid of the target obstacle, the positions of the centroid of the target obstacle in the vehicle coordinate system corresponding to multiple time points within the first time period, and the first deflection angles corresponding to multiple time points within the first time period, a first correspondence relationship is determined between the positions of the multiple target points of the target obstacle in the vehicle coordinate system and time changes within the first time period. Based on the first correspondence relationship, the first time point when the distance between the positions of the multiple target points and the target end side is a preset distance is determined, and the target position information corresponding to the first time point of the multiple target points is determined.

[0008] In one possible implementation of the first aspect described above, predicting the collision risk between the vehicle's target end and a target obstacle based on multiple target location information and the position of the target end includes: determining the first coordinate of each target point in the first coordinate axis of the vehicle coordinate system when the distance between each target point and the target end is a preset distance, wherein the vehicle coordinate system is a Cartesian coordinate system, the projection line segment of the target end in the vehicle coordinate system is parallel to the first coordinate axis, and the distance between the target point and the target end is the distance between the target point and the projection line segment. A first coordinate interval is determined based on the first coordinate of each target point in the first coordinate axis of the vehicle coordinate system, wherein the lower limit of the first coordinate interval is the minimum value of the first coordinate of the target point in the first coordinate axis of the vehicle coordinate system, and the upper limit of the first coordinate interval is the maximum value of the first coordinate of the target point in the first coordinate axis of the vehicle coordinate system. If there is an overlapping area between the first coordinate interval and the second coordinate interval, a collision between the vehicle and the target obstacle is predicted, wherein the second coordinate interval is the coordinate interval corresponding to the first coordinate axis of the projection line segment.

[0009] In some embodiments of this application, whether a collision occurs between a target obstacle and a vehicle can be determined based on a first coordinate interval occupied by multiple target points along a first coordinate axis and a second coordinate interval occupied by the target end of the vehicle along a first coordinate axis. It is understood that if the distance between a target point of the target obstacle and the target end of the vehicle is less than a preset distance, and if the first coordinate interval occupied by the target point and the second coordinate interval occupied by the target end of the vehicle overlap, the paths of the vehicle and the target obstacle may coincide at the first moment, thus posing a risk of collision.

[0010] In one possible implementation of the first aspect above, the method further includes: when there is an overlapping area between the first coordinate interval and the second coordinate interval, determining the collision time between the vehicle and the target obstacle based on the time sequence of each target point at the first moment and the first coordinates corresponding to each target point.

[0011] In some embodiments of this application, the specific collision time between the vehicle and the target obstacle can be determined based on the first moment corresponding to each target point, thus making the determined collision time more accurate. Furthermore, the end of the vehicle collision can also be determined. This allows for more precise avoidance strategies for the driver, or more precise control of the vehicle to avoid obstacles.

[0012] In one possible implementation of the first aspect above, determining the collision time between the vehicle and the target obstacle based on the time sequence of the first moments corresponding to each target point and the first coordinates corresponding to each target point includes: if, among the multiple first moments corresponding to multiple target points, the first coordinate of the target point corresponding to the earliest first moment is in the second coordinate interval, the earliest first moment is taken as the collision time. Otherwise, the collision time is determined based on the first moment and first coordinates corresponding to a first reference point, and the first moment and first coordinates corresponding to a second reference point, wherein the first reference point and the second reference point are determined as follows: multiple first moments are arranged in chronological order, and two adjacent first moments are traversed in chronological order; if the range between the first coordinates of the two target points corresponding to the first two adjacent first moments includes the second coordinate interval, the two target points corresponding to the first two adjacent first moments are respectively taken as the first reference point and the second reference point.

[0013] In some embodiments of this application, the electronic device can also determine the specific collision time between the target obstacle and the vehicle based on the first moment corresponding to each target point. The electronic device controls the vehicle based on the specific collision time (e.g., the process of controlling the vehicle through the vehicle system in autonomous driving), or prompts the user with the specific collision time, thereby avoiding the risk of vehicle collision.

[0014] In one possible implementation of the first aspect above, the preset distance is greater than or equal to 0m and less than or equal to 0.1m.

[0015] Secondly, this application provides an electronic device, including: a memory for storing instructions; and at least one processor for executing the instructions to cause the device to implement the vehicle collision prediction method provided in the first aspect and any possible implementation of the first aspect. The beneficial effects achievable in the second aspect can be referred to the beneficial effects of the vehicle collision prediction method provided in any embodiment of the first aspect, and will not be repeated here.

[0016] Thirdly, this application provides a computer-readable storage medium storing instructions that, when executed by a device, cause a computer to implement the vehicle collision prediction method provided in the first aspect and any possible implementation of the first aspect. The beneficial effects achievable in this third aspect can be found in the beneficial effects of the vehicle collision prediction method provided in any embodiment of the first aspect, and will not be repeated here.

[0017] Fourthly, this application provides a computer program product that stores instructions that, when executed on a device, cause the device to implement the vehicle collision prediction method provided in the first aspect and any possible implementation of the first aspect. The beneficial effects achievable in this fourth aspect can be found in the beneficial effects of the vehicle collision prediction method provided in any embodiment of the first aspect, and will not be repeated here. Attached Figure Description

[0018] Figure 1 A schematic diagram of a vehicle in motion is shown.

[0019] Figure 2 This diagram illustrates the driving paths of the vehicle and the target vehicle in the current coordinate system.

[0020] Figure 3 According to some embodiments of this application, a flowchart of an implementation of a vehicle collision prediction method is shown;

[0021] Figure 4A According to some embodiments of this application, a schematic diagram of a target obstacle in the vehicle coordinate system at the current moment is shown;

[0022] Figure 4B According to some embodiments of this application, a schematic diagram of a target obstacle projected into a vehicle coordinate system is shown;

[0023] Figure 5A According to some embodiments of this application, a schematic diagram is shown with a first end side of the vehicle as the target end side;

[0024] Figure 5B According to some embodiments of this application, a schematic diagram is shown of projecting the first coordinates of multiple target points on a first end side into the same vehicle coordinate system;

[0025] Figure 6A According to some embodiments of this application, a schematic diagram is shown in which the second end side of the vehicle is taken as the target end side;

[0026] Figure 6B According to some embodiments of this application, a schematic diagram is shown of projecting the first coordinates of multiple target points on the second end side into the same vehicle coordinate system;

[0027] Figure 7A According to some embodiments of this application, a schematic diagram is shown in which the third end side of the vehicle is taken as the target end side;

[0028] Figure 7B According to some embodiments of this application, a schematic diagram is shown of projecting the first coordinates of multiple target points on a third end side into the same vehicle coordinate system;

[0029] Figure 8A According to some embodiments of this application, a schematic diagram is shown in which the fourth end side of the vehicle is taken as the target end side;

[0030] Figure 8B According to some embodiments of this application, a schematic diagram is shown of projecting the first coordinates of multiple target points on the fourth end side into the same vehicle coordinate system;

[0031] Figure 9A According to some embodiments of this application, a schematic diagram of solving equations using a linear binary difference method is shown;

[0032] Figure 9B According to some embodiments of this application, a flowchart of an implementation of a linear binary difference method for solving equations is shown;

[0033] Figure 9C According to some embodiments of this application, a schematic diagram of solving equations using Newton's iteration method is shown;

[0034] Figure 10 According to some embodiments of this application, a flowchart of an implementation for determining the collision moment is shown;

[0035] Figure 11 According to some embodiments of this application, a schematic diagram of the structure of an electronic device is shown. Detailed Implementation

[0036] The illustrative embodiments of this application include, but are not limited to, vehicle collision prediction methods, readable storage media, program products, and electronic devices.

[0037] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions in the embodiments of this application will be described in detail below with reference to the accompanying drawings and specific implementation methods.

[0038] As shown in the background section, current vehicle collision risk prediction is not very accurate, and the timing of collisions is not precisely predicted.

[0039] The following describes the process of vehicle collision risk prediction.

[0040] For example, Figure 1 A schematic diagram of a vehicle in motion is shown.

[0041] like Figure 1 As shown, while vehicle 01 is traveling on the main road at a T-junction, target vehicle 02 attempts to travel from a side road to the main road. Vehicle 01's onboard equipment can predict its future first travel path r1 based on its speed and historical trajectory. Furthermore, vehicle 01's onboard equipment can also predict target vehicle 02's future second travel path r2 based on its speed and historical trajectory (for example, vehicle 01 can collect environmental information during its journey, obtaining the target vehicle 02's position at multiple times to determine its speed and historical trajectory). Then, the onboard equipment can predict the collision risk between vehicle 01 and target vehicle 02 based on the first travel path r1 and the second travel path r2.

[0042] For example, Figure 2 This diagram illustrates the driving paths of the vehicle and the target vehicle in the current coordinate system.

[0043] In some embodiments, the on-board device can determine a first function f1(t) of the position coordinates of vehicle 01 relative to time in the coordinate system of vehicle 01 at the current moment based on the first driving path r1 of vehicle 01, and a second function f2(t) of the position coordinates of target vehicle 02 relative to time in the coordinate system of vehicle 01 at the current moment based on the second driving path r2 of target vehicle 02. That is, based on the first function f1(t) and any future time tn, the position coordinates of vehicle 01 at time tn relative to vehicle 01 at the current moment can be determined. (Refer to...) Figure 2 The on-board equipment can determine the distances between vehicle 01 and target vehicle 02 over multiple time periods based on the first function f1(t) and the second function f2(t), and judge the collision risk between vehicle 01 and target vehicle 02 based on the distances. For example, the smaller the distance between vehicle 01 and target vehicle 02, the higher the collision risk. When the distance between vehicle 01 and target vehicle 02 is less than a preset value (e.g., a preset value determined based on the length and width of vehicle 01 and the length and width of target vehicle 02), a collision between vehicle 01 and target vehicle 02 is predicted.

[0044] For example, at time tn (time tn is a time after the current time), the coordinates of vehicle 01 in the coordinate system of vehicle 01 at the current time are (0, y1). At time tn, the coordinates of target vehicle 02 in the coordinate system of vehicle 01 at the current time are (0, y2), and y2-y1 is less than a preset value. Therefore, it can be predicted that a collision will occur between vehicle 01 and target vehicle 02, and the on-board equipment can issue warnings such as deceleration.

[0045] It is understandable that in the process of predicting vehicle collision risk, the vehicle and the target vehicle are treated as point masses to determine the vehicle's position. However, vehicles have volume, so collisions may occur at the front, rear, left, or right end of the vehicle during travel. Treating the vehicle as a point mass cannot accurately predict the location of the collision, or the more precise timing of the collision.

[0046] To address the aforementioned issues, this application provides a vehicle collision prediction method. An electronic device (e.g., a vehicle-mounted system or in-vehicle device) can determine a first predicted trajectory of the target obstacle within a future first time period based on the target obstacle's historical motion information, and a second predicted trajectory of the vehicle within the first time period based on the vehicle's historical motion information. Then, based on the first and second predicted trajectories, a first pose information of the target obstacle relative to the vehicle within the first time period is determined. Based on the first pose information, the electronic device can determine the first moment and target position information corresponding to multiple target points (e.g., multiple corner points of the target obstacle) of the target obstacle. The first moment indicates the moment when the distance between the corresponding target point and the target end side of the vehicle (e.g., the front, rear, left, and right sides of the vehicle) is a preset distance. The target position information indicates the target position information relative to the vehicle when the distance between the corresponding target point and the target end side is a preset distance. Then, based on the multiple target position information and the position of the target end side, the collision risk between the target end side of the vehicle and the target obstacle is predicted.

[0047] Using the above method, the vehicle can predict the distances between multiple target points of the target obstacle and the target sides of the vehicle (e.g., front, rear, left, and right sides) over a future period of time, and predict whether a collision will occur between the target point and the vehicle based on the distance between the target point and the target side of the vehicle. For example, when the distance between a target point and the front side is a preset distance (e.g., 0), the position coordinates of the projected line segment corresponding to the target point on the front side also overlap, then the target point has a risk of collision with the front side of the vehicle.

[0048] In the embodiments of this application, when determining the collision risk between the target obstacle and the vehicle, multiple target points of the target obstacle and multiple end sides of the vehicle are considered, that is, the size of the vehicle and the size of the target vehicle are taken into account. Compared with a scheme that treats the target obstacle and the vehicle as separate points, the location and time of the collision between the target obstacle and the vehicle can be predicted more accurately. This facilitates issuing accurate prompts to the user, such as prompting the user to slow down and give way, take evasive action, or stop to observe, ensuring driving safety.

[0049] The vehicle collision prediction method in the embodiments of this application is described below.

[0050] For example, Figure 3 According to some embodiments of this application, a flowchart of an implementation of a vehicle collision prediction method is shown.

[0051] It is understood that the following processes can be performed by electronic devices, which can be in-vehicle devices or servers. In-vehicle devices can be mobile phones, in-vehicle systems, terminals in self-driving vehicles, or wireless terminals in transportation safety.

[0052] like Figure 3 As shown, the process includes:

[0053] S301, based on the historical motion information of the target obstacle, determine the first predicted trajectory of the target obstacle in the first time period in the future, and based on the historical motion information of the vehicle, determine the second predicted trajectory of the vehicle in the first time period.

[0054] In some embodiments of this application, the target obstacle can be an object that may collide with or restrict the vehicle's behavior during its operation. Examples include pedestrians, other vehicles, traffic facilities, buildings, plants, and animals. The electronic device can determine the historical motion information of the target obstacle based on environmental information collected by sensors during the vehicle's operation. For example, the electronic device can determine the position of the target obstacle at multiple moments based on images captured by a camera, thereby calculating the target obstacle's speed, angle relative to the vehicle, and historical motion information such as its path. Then, the electronic device can predict the target obstacle's trajectory within a first time period in the future based on its historical motion information as a first predicted trajectory. Alternatively, the electronic device can directly acquire the vehicle's historical motion information to determine a second predicted trajectory for the vehicle within the first time period in the future.

[0055] It is understandable that, for a moving obstacle, such as other moving vehicles or pedestrians, the first predicted trajectory can be a curve. For a stationary obstacle, such as buildings, plants, or traffic facilities, the first predicted trajectory can be a single coordinate point. Similarly, for a stationary vehicle, the second predicted trajectory can be a single coordinate point; for a moving vehicle, the second predicted trajectory can be a curve.

[0056] In embodiments of this application, the first predicted trajectory may be a function of the position coordinates of the target obstacle in the vehicle's current coordinate system and time, and a function of the angle of the target obstacle relative to the vehicle's current coordinate system and time. In embodiments of this application, the vehicle coordinate system is a Cartesian coordinate system, and both the target obstacle and the vehicle are two-dimensional shapes projected onto the Cartesian coordinate system along the height direction. For example, the projections of the vehicle and other vehicles onto the vehicle coordinate system may be rectangular blocks.

[0057] In this application, the first predicted trajectory can be P target =h(t), where P target This represents the coordinates of the target obstacle in the vehicle coordinate system at the current moment (e.g., x1 for x-coordinate and x1 for y-coordinate) and its azimuth angle φ1. The azimuth angle φ1 can be the angle between the target obstacle's reference axis and the coordinate axes of the vehicle coordinate system (e.g., the x-axis or y-axis). The reference axis can be the straight line corresponding to two reference points of the target obstacle. For example, if the target obstacle is another vehicle, the reference axis can be the straight line from the vehicle's center of mass to the center of its front end.

[0058] Similarly, the second predicted trajectory can be a function of the vehicle's position coordinates and time in the vehicle's current coordinate system, as well as its azimuth angle relative to the vehicle's current coordinate system and time. For example, the second predicted trajectory could be P e =f(t), where P e This represents the vehicle's coordinates in its current coordinate system (e.g., x2 for x, y2 for y) and azimuth angle φ2, where φ2 can be the angle between the vehicle's reference axis and the coordinate axes of the vehicle's coordinate system, such as the x-axis (or y-axis). The reference axis can be the straight line corresponding to two reference points of the vehicle. For example, the reference axis can be the straight line from the vehicle's center of mass to the center of its front end. In other words, at any time t0 within the first time interval, the pose of the target obstacle in the vehicle's current coordinate system (y10, x10, φ10) can be determined based on h(t), and the pose of the vehicle in its current coordinate system (y20, x20, φ20) can be determined based on f(t).

[0059] In embodiments of this application, h(t) may include the x-coordinate of the target obstacle in the vehicle's current coordinate system as a function of time, such as y t (t), a function of the ordinate and time, such as x t (t), and functions of azimuth and time, such as φ t(t). Thus, the coordinates and azimuth of the target obstacle at multiple moments within the first time period can be determined, thereby determining the first predicted trajectory of the target obstacle within the first time period. Similarly, f(t) can include the vehicle's x-coordinate in its current coordinate system as a function of time, such as y e (t), a function of the ordinate and time, such as x e (t), and functions of azimuth and time, such as φ e (t). In this way, the coordinates and azimuth of the vehicle at multiple moments within the first time period can be determined, thereby determining the second predicted trajectory of the vehicle within the first time period.

[0060] S302, based on the first predicted trajectory and the second predicted trajectory, determine the first pose information of the target obstacle relative to the vehicle within the first time period.

[0061] In some embodiments of this application, after the electronic device determines the first predicted trajectory and the second predicted trajectory, it can determine the first pose information of the target obstacle in the vehicle's coordinate system at multiple moments within a future first time period. The first pose information includes the coordinates and azimuth of the target obstacle in the vehicle's coordinate system. That is, each moment within the future first time period corresponds to a vehicle coordinate system, and each vehicle coordinate system includes the first pose information of the target obstacle. It can be understood that since the first pose information of the target obstacle is located in the vehicle coordinate system at the corresponding moment, the positional information in the first pose information can be the relative positional relationship between the target obstacle and the vehicle at the corresponding moment.

[0062] For example, Figure 4A According to some embodiments of this application, a schematic diagram of a target obstacle in the vehicle coordinate system at the current moment is shown. Figure 4B According to some embodiments of this application, a schematic diagram of a target obstacle in the vehicle coordinate system at time t1 is shown.

[0063] Reference Figure 4A and Figure 4B In some embodiments of this application, the target obstacle is exemplified by target vehicle 02. At the current time (e.g., time t0), in the first vehicle coordinate system S of vehicle 01, the coordinates of vehicle 01 are (0,0), and the coordinates of target vehicle 02 are (y,t0). t (t0), x t (t0)). At time t1, the coordinates of vehicle 01 in the first vehicle coordinate system S are (y e (t1), x e (t1)), azimuth angle is φ e (t1). The coordinates of target vehicle 02 are (y... t(t1), x t (t1)). Therefore, the azimuth angle φ of vehicle 01 at time t1 can be used as a basis. e (t1) Determine the second vehicle coordinate system S' of vehicle 01 at time t1. And based on the coordinates of target vehicle 02 at time t1, (y... t (t1), x t (t1)) and the coordinates of vehicle 01 at time t1 are (y e (t1), x e (t1)), determine the coordinates y(t1) and x(t1) of the target vehicle 02 in the second vehicle coordinate system S'.

[0064] The coordinates y(t1) and x(t1) of the target vehicle 02 in the second vehicle coordinate system S' can be determined by referring to the coordinate transformation in equation (1):

[0065] (1)

[0066] Based on equation (1), for any moment within the first time period, the vehicle's azimuth angle φ in the vehicle's current coordinate system is... e (t), vehicle coordinates (y) e (t), x e (t) and the coordinates (y) of the target obstacle. t (t), x t (t). The coordinates x(t) and y(t) of the target obstacle in the vehicle's coordinate system at any given time can be determined. Furthermore, based on the vehicle's azimuth angle φ relative to the vehicle at the current time... e (t), and the azimuth angle φ of the target obstacle relative to the vehicle at the current moment. t (t) can determine the azimuth angle φ(t) relative to the vehicle in the vehicle coordinate system at any time within the first time period. t (t)-φ e (t).

[0067] In embodiments of this application, the first pose information may include the coordinates x(t), y(t) of the target obstacle in the vehicle coordinate system at multiple times within a first time period, as well as the azimuth angle φ(t) in the vehicle coordinate system.

[0068] S303, based on the first pose information, determine the first moment and target position information corresponding to multiple target points of the target obstacle. The first moment indicates the moment when the distance between the corresponding target point and the target end side of the vehicle is a preset distance. The target position information indicates the target position information relative to the vehicle when the distance between the corresponding target point and the target end side is a preset distance.

[0069] In some embodiments, the electronic device can determine the coordinates of multiple target points of the target obstacle in the vehicle coordinate system based on the size and first pose information of the target obstacle. In embodiments of this application, the target points of the target obstacle can be corner points of the target obstacle. A corner point represents the point where two sides of a geometric figure intersect. In embodiments of this application, the target obstacle can be abstracted into a geometric figure to determine its corner points. For example, the target vehicle can be considered as a rectangle, and the four corners of the rectangle can be used as corner points.

[0070] After identifying multiple target points of the target obstacle, multiple first moments can be determined based on the first pose information of the target obstacle relative to the vehicle at multiple moments, where the distance between the multiple target points of the target obstacle and the target end side of the vehicle in the first direction is a preset distance. In the embodiments of this application, the target end side of the vehicle may include at least one of the following: a first end side and a second end side of the vehicle opposite each other in the length direction (e.g., the front and rear ends of the vehicle under normal driving conditions), and a third end side and a fourth end side of the vehicle opposite each other in the width direction (e.g., the left and right ends of the vehicle under normal driving conditions). It can be understood that since the vehicle is a two-dimensional image in the vehicle coordinate system, the first end side, the second end side, the third end side, and the fourth end side of the vehicle are all projected line segments. After determining the target end side, the extension direction of the target end side can be used as the second direction, and then the first direction perpendicular to the second direction can be determined. For example, when the target end side is the first end side of the vehicle, the direction of the projected line segment of the vehicle's width can be used as the second direction, and the length direction of the vehicle can be used as the first direction.

[0071] In some embodiments of this application, the coordinates of the target obstacle in the vehicle coordinate system can be the coordinates of the centroid of the target obstacle in the vehicle coordinate system. The centroid is the coordinate of the position where the mass distribution of the target obstacle is most uniform. In other embodiments, the coordinates of the target obstacle can also be the coordinates of the geometric center of the target obstacle or the coordinates of a specific point. This application does not limit the specific location of the coordinates of the target obstacle.

[0072] In some embodiments of this application, the first pose information includes the position of the centroid of the target obstacle in the vehicle coordinate system, and the azimuth angle of the reference axis of the target obstacle relative to the x-axis (or y1-axis, which can be used as an example of the first coordinate axis) of the vehicle coordinate system (as an example of the first deflection angle).

[0073] Therefore, the electronic device can determine the first correspondence between the positions of multiple target points of the target obstacle in the vehicle coordinate system over time based on the relative positions of multiple target points of the target obstacle and the centroid of the target obstacle, the positions of the centroid of the target obstacle in the vehicle coordinate system at multiple moments within the first time period (e.g., the positions of the centroid at multiple moments can be determined based on x(t) and y(t), and the azimuth angles of the target obstacle relative to the vehicle coordinate system at multiple moments within the first time period (e.g., the azimuth angles at multiple moments can be determined based on φ(t), and the azimuth angle can be used as an example of a deflection angle).

[0074] Then, based on the first correspondence, the electronic device can determine the first moment when the distance between the positions of multiple target points and the target end is a preset distance, and the target position information of the multiple target points at the first moment.

[0075] For example, Figure 5A According to some embodiments of this application, a schematic diagram is shown with a first end side of the vehicle as the target end side. Figure 5B According to some embodiments of this application, a schematic diagram is shown of projecting target position information of multiple target points into the same vehicle coordinate system.

[0076] Reference Figure 5A The target vehicle 02 (as an example of a target obstacle) includes four target points, such as the first target point 021, the second target point 022, the third target point 023, and the fourth target point 024. The target end side of vehicle 01 is the first end side 011, which extends along the Y direction. The distance between the first end side 011 and the origin along the X direction is df, that is, the distance from the front end of vehicle 01 to the center of mass of vehicle 01 is df. The distances of multiple target points along the first direction from the first end side 011 are the distances to the line x = df.

[0077] It can be understood that the relationship between the position and time of the target vehicle 02 in the vehicle coordinate system during the first time period is x(t) and y(t). Then, based on the relative positions of multiple target points of the target vehicle 02 with the centroid of the target vehicle 02, the positions of the centroid of the target vehicle 02 in the vehicle coordinate system at multiple moments during the first time period (determined based on x(t) and y(t)), and the azimuth angles of the target vehicle 02 relative to the vehicle coordinate system at multiple moments during the first time period (determined based on φ(t), the positions of multiple target points of the target vehicle 02 at any moment during the first time period in the vehicle coordinate system can be determined. That is, the target point function of the position and time of the target point in the vehicle coordinate system during the first time period is determined (as an example of the first correspondence). For example, the target point function of the first target point 021 includes x21(t) and y21(t), the target point function of the second target point 022 includes x22(t) and y22(t), the target point function of the third target point 023 includes x23(t) and y23(t), and the target point function of the fourth target point 024 includes x24(t) and y24(t).

[0078] Exemplarily, in some embodiments of this application, the preset distance can be from 0m to 0.1m. Taking 0m as an example, the vertical distance from multiple target points to the first end 011 is essentially the X-axis coordinate of the multiple target points, df. That is, for the first target point 021, the first time t11 is the time x21(t) - df = 0. In other words, t11 obtained by solving x21(t) - df = 0 is the first time t11 of the first target point 021. After obtaining the first time t11, t11 can be substituted into y21(t) to obtain y21(t11) = y11, where y11 is the first coordinate of the first target point on the y-axis (as an example of the first coordinate axis). In some embodiments, the target position information can be coordinate information, such as (y11, df). (Refer to...) Figure 5A , Figure 5A This is a schematic diagram showing the position of target vehicle 02 in the vehicle coordinate system of vehicle 01 at time t11. Here, R represents the travel path of target vehicle 02 relative to vehicle 01 during the first time period. For example, during the first time period, vehicle 01 remains stationary, and target vehicle 02 travels along trajectory R with its azimuth angle remaining constant.

[0079] It can be understood that the above process yields the first time point t11 ​​and the corresponding first coordinate y11 for the first target point 021. Similarly, the first time point t12 for the second target point 022 can be determined by solving for the time x22(t) - df = 0. Substituting t12 into y22(t) yields the first coordinate y22(t12) = y12 for the second target point 022, thus determining the coordinates of the second target point 022 as (y12, df) (as an example of target position information). The first time point t13 for the third target point 023 can be determined by solving for the time x23(t) - df = 0. Substituting t13 into y23(t) yields the first coordinate y23(t13) = y13 for the third target point 023 along the second direction, thus determining the coordinates of the third target point 023 as (y13, df) (as an example of target position information). The first time point t14 of the fourth target point 024 is determined by solving for the moment x24(t) - df = 0. Then, t14 is substituted into y24(t) to obtain the first coordinate of the fourth target point y24(t14) = y14, thus determining the coordinates of the fourth target point 024 as (y14, df) (as an example of target location information). Then, refer to... Figure 5B This allows the first coordinates at multiple moments to be projected onto the same vehicle coordinate system. In this way, the positional relationship between the first coordinates of multiple target points and vehicle 01 can be easily determined.

[0080] Similarly, refer to Figure 6A and Figure 6B The target end is designated as the second end. This allows us to determine the first time point and first coordinates when the distance between multiple target points and the second end point of vehicle 01 is a preset distance. For example, when the distance between the first target point 021 and the second end point of vehicle 01 is the preset distance, solving x21(t) + dr = 0 determines the first time point as t21. Based on y21(t21), the first coordinate is determined as y21, which is then (y21, dr), where dr is the distance between the second end point and the centroid of vehicle 01. Similarly, the first time point when the distance between the second target point 022 and the second end point of vehicle 01 is the preset distance is t22, and the first coordinate is y22, with coordinates (y22, dr). The first time point when the distance between the third target point 023 and the second end point of vehicle 01 is the preset distance is t23, and the first coordinate is y23, with coordinates (y23, dr). The distance between the fourth target point 024 and the second end of vehicle 01 is the preset distance. The first moment is t24, the first coordinate is y24, and the coordinates are (y24, dr).

[0081] Reference Figure 7A and Figure 7BThe target end is the third end, which allows us to determine the first time point and first coordinate when the distance between multiple target points and the third end point of vehicle 01 is a preset distance. For example, when the distance between the second target point 022 and the second end point of vehicle 01 is a preset distance, solving y22(t) + 0.5w = 0 determines the first time point as t31. Based on x22(t31), the first coordinate is determined as x31, and the first coordinate axis is the x-axis, with coordinates (-0.5w, x31), where w is the width of vehicle 01. Similarly, the first time point when the distance between the first target point 021 and the second end point of vehicle 01 is a preset distance is t32, and the first coordinate is x32, with coordinates (-0.5w, x32). The first time point when the distance between the fourth target point 024 and the second end point of vehicle 01 is a preset distance is t33, and the first coordinate is x33, with coordinates (-0.5w, x33). The distance between the third target point 023 and the second end of vehicle 01 is the preset distance. The first moment is t34, the first coordinate is x34, and the coordinates are (-0.5w, x34).

[0082] Reference Figure 8A and Figure 8B The target end is designated as the fourth end. This allows us to determine the first time point and first coordinates when the distance between multiple target points and the fourth end point of vehicle 01 is a preset distance. For example, when the distance between the second target point 022 and the second end point of vehicle 01 is a preset distance, solving y22(t) - 0.5w = 0 determines the first time point as t41. Based on x22(t41), the first coordinate is determined as x41, with coordinates (0.5w, x41), where w is the width of vehicle 01. Similarly, the first time point when the distance between the first target point 021 and the second end point of vehicle 01 is a preset distance is t42, and the first coordinate is x42, with coordinates (0.5w, x42). The first time point when the distance between the fourth target point 024 and the second end point of vehicle 01 is a preset distance is t43, and the first coordinate is x43, with coordinates (0.5w, x43). The distance between the third target point 023 and the second end of vehicle 01 is the preset distance. The first moment is t44, the first coordinate is x44, and the coordinates are (0.5w, x44).

[0083] In summary, the target location information and first coordinates of multiple target points at different ends of vehicle 01 at multiple first moments can be determined.

[0084] In embodiments of this application, the process of solving the equations for multiple target points and the target end with a preset distance can first be solved using a linear binary difference method. For example, Figure 9A According to some embodiments of this application, a schematic diagram of solving equations using a linear binary difference method is shown. Figure 9B According to some embodiments of this application, a flowchart of an implementation of a linear binary difference method for solving equations is shown.

[0085] The bisection method is a numerical method for finding solutions to equations that result in zero. It is applicable to functions that are continuous and monotonic within a given interval. Its core idea is to gradually approach the root of the equation by continuously narrowing the interval.

[0086] Reference Figure 9A In the embodiments of this application, taking the solution of x21(t)-df=0 as an example, Figure 9A The function curve of x21(t)-df is shown, where the horizontal axis is time t and the vertical axis is the distance x between the first target point 021 of the target vehicle and the first end side 011 (e.g., the front end side) of the vehicle 01. In the embodiments of this application, the first time period can be a time period from 0s to 3s, and the interval from 0s to 3s can be selected as the initial interval based on the bisection method.

[0087] For example, substituting t=0 and t=3 into x21(t)-df, we can determine that x is -4m and 8m respectively. The different signs of -4m and 8m indicate that there exists a solution x21(t)-df=0 between 0s and 3s. Then, the initial interval is divided. For example, the intersection of the straight line formed by the points corresponding to 0s and 3s on the x21(t)-df curve and the t-axis is selected, and it is determined whether the absolute value of the corresponding value on the x21(t)-df curve at that time is less than or equal to a preset distance. For example, refer to... Figure 9A The intersection of the straight line l1 corresponding to times 0s and 3s on the curve x21(t)-df with the t-axis corresponds to time 1s (this time can be determined by the equation of the straight line formed by the two points when the distance is equal to 0). Substituting t=1 into x21(t)-df, the solution x is -1.9m. The absolute value of -1.9m is greater than the preset distance (for example, take the preset distance as 0.1m), and -1.9m and 8m have different signs, so the solution of x21(t)-df=0 is in the interval between 1s and 3s.

[0088] Divide the interval from 1s to 3s into two parts. Select the time 1.375s corresponding to the intersection of the line formed by the points corresponding to 1s and 3s on the curve x21(t)-df with the t-axis. Substitute this time into x21(t)-df and solve for x, obtaining x = -0.8m. Since -0.8m and 8m have different signs, and the absolute value of -0.8m is greater than a predetermined distance, we can determine that the solution for x21(t)-df = 0 lies in the interval from 1.375s to 3s.

[0089] Divide the interval from 1.375s to 3s into two parts. Select the point on the curve x21(t)-df corresponding to the point at 1.375s and the point at 3s corresponding to the point at the intersection of the line with the t-axis. Substitute this point (1.53s) into x21(t)-df and solve for x. The result is x = -0.28m. Since -0.28m and 8m have different signs, and the absolute value of -0.28m is greater than a predetermined distance, we can determine that the solution for x21(t)-df = 0 lies within the interval from 1.53s to 3s.

[0090] Divide the interval from 1.53s to 3s into two parts. Select the point on the curve x21(t)-df corresponding to the point at 1.53s and the point at 3s corresponding to the point at 1.58s, and substitute this point into x21(t)-df to obtain x = -0.09m. Since -0.09m and -0.4m have different signs, but the absolute value of -0.09m is less than a preset distance, t = 1.58s can be taken as the first time t11 when the distance between the first target point 021 and the first end side 011 of vehicle 01 is less than the preset distance.

[0091] Below, refer to Figure 9B Taking h(t) as x21(t)-df as an example, the solution process of the bisection method can be referred to Figure 9B The process involves several steps, including those executed by electronic devices.

[0092] S901, obtain the value h(t1) of function h(t) at the first endpoint t1.

[0093] In some embodiments of this application, the initial endpoint of the first endpoint t1 is the start time of the first time period, and the first endpoint t1 may be updated during the calculation process.

[0094] S902, obtain the value h(t2) ​​of the function h(t) at the second endpoint t2.

[0095] In some embodiments of this application, the initial endpoint of the second endpoint t2 is the end time of the first time period, and the second endpoint t2 may be updated during the calculation process.

[0096] It is understandable that the above S901 and S902 processes are not in any particular order.

[0097] S903, determine whether h(t1) and h(t2) ​​have the same sign.

[0098] If the judgment result is yes, then h(t) has no solution, or h(t) is not monotonic between t1 and t2. In this case, the bisection method is no longer used to solve the problem.

[0099] If the judgment result is negative, then execute S904 to determine the intersection point tm of the straight line formed by the points of t1 and t2 on h(t1) and the time axis, and calculate h(tm).

[0100] S904, determine the intersection point tm of the straight line formed by the points of t1 and t2 on h(t1) with the time axis, and calculate h(tm).

[0101] S905, determine whether the absolute value of h(tm) is less than the preset distance.

[0102] If the judgment result is yes, then execute S909 and take tm as the first moment.

[0103] If the result is negative, then execute S906 to determine whether h(tm) and h(t1) have the same sign.

[0104] S906, determine whether h(tm) and h(t1) have the same sign.

[0105] If the judgment result is yes, then execute S907 and set tm as t1.

[0106] If the judgment result is negative, then execute S908 and set tm as t2.

[0107] S907 uses tm as t1.

[0108] In some embodiments of this application, if h(tm) and h(t1) have the same sign, it means that h(tm) and h(t2) ​​have opposite signs (h(t1) and h(t2) ​​have opposite signs). The solution of h(t)=0 is between tm and t2. Then tm can be used as t1 to execute S904 again, determine the intersection point tm of the straight line formed by the points of t1 and t2 on h(t1) and the time axis, and calculate h(tm).

[0109] S908 uses tm as t2.

[0110] In some embodiments of this application, if h(tm) and h(t1) do not have the same sign, it means that the solution of h(t)=0 is between t1 and tm. Then tm can be used as t2 to execute S904 again, determine the intersection point tm of the straight line formed by the points of t1 and t2 on h(t1) and the time axis, and calculate h(tm).

[0111] S909 uses time as its first moment.

[0112] In some embodiments of this application, if the absolute value of h(tm) is less than a preset distance, then time tm can be taken as the solution for h(t) = 0. Therefore, time tm can be considered the first time point.

[0113] In some embodiments of this application, if the electronic device determines that there is no solution for h(t) by the bisection method (e.g., h(t) is not monotonic or h(t) will not be less than a preset distance in the region of the first time period), then it can continue to solve for h(t) = 0 by the Newton iteration method.

[0114] Newton's iteration method is an efficient numerical method for solving equations that result in zero. It quickly converges to the root of the equation by utilizing the Taylor expansion of the function and tangent approximation.

[0115] For example, when solving for h(t) = 0, an initial point can be chosen, and then a Taylor expansion of h(t) can be performed at the initial point. For example, if the initial point is time t01, then h(t) ≈ h(t01) + h'(t01)(t-t01), where h'(t01) is the value of the first derivative of the function h(t) at time t01. Letting h(t1) + h'(t1)(t-t1) = 0, we can obtain t = t1 - h(t1) / h'(t1). Then, t1 - h(t1) / h'(t1) can be used as the next prediction point, and the time of the next prediction point can be t02, thereby determining whether the absolute value of h(t02) is less than a preset distance. If it is not less than the preset distance, the Taylor expansion is continued; if it is less than the preset distance, the solution is complete.

[0116] It is understandable that the solution process of Newton's iteration method is essentially to draw the tangent line of the function at the initial point, and the intersection of the tangent line and the t-axis is the next prediction point. This process is repeated until convergence.

[0117] For example, Figure 9C According to some embodiments of this application, a schematic diagram of solving equations using Newton's iterative method is shown.

[0118] Reference Figure 9C The initial point can be selected as 0s, h(0) is -4m, and the absolute value is greater than the preset distance of 0.1m, then the position of the second point needs to be predicted.

[0119] Reference Figure 9C The position of the second point is 2.7s, h(2.7) = 6.5m. Its absolute value is greater than the preset distance of 0.1m, so the position of the next point is predicted.

[0120] Reference Figure 9C The position of the third point is 2.15s, h(2.15) = 2.1m. Its absolute value is greater than the preset distance of 0.1m, so the position of the next point is predicted.

[0121] Reference Figure 9C The position of the fourth point is 1.68s, h(1.68) = 0.11m. Its absolute value is greater than the preset distance of 0.1m, so the position of the next point is predicted.

[0122] Reference Figure 9C The position of the fifth point is 1.6s, h(1.6) = 0.05m, and its absolute value is less than the preset distance of 0.1m, so 1.6s can be taken as the first moment.

[0123] It is understood that the above-described process of solving the equation is merely an example. In other embodiments, the equation can be solved in other ways. The embodiments of this application do not limit the process of solving the equation.

[0124] It is understood that in the embodiments of this application, there may be a situation where there is no solution during the process of solving the equation. When there is no solution, it means that the corresponding target point will not contact the target end side of the vehicle.

[0125] In other embodiments, during the process of solving the equation, there may be multiple solutions where the distance between a target point and the target end is less than a preset distance. In this case, the earliest solution can be selected, or the second moment when the distance between the centroid of the target obstacle and the target end is less than the preset distance can be calculated, and the solution closest to the second moment can be taken as the first moment of the target point.

[0126] S304 predicts the collision risk between the vehicle's target side and the target obstacle based on multiple target location information and the target end position.

[0127] In some embodiments of this application, after determining the first moment corresponding to multiple target points and the target position information of multiple target points, the collision risk between the target end of the vehicle and the target obstacle can be predicted based on the target position information and the size of the vehicle.

[0128] For example, based on multiple target location information, the first coordinate of each target point in the first coordinate axis of the vehicle coordinate system can be determined when the distance between each target point and the target end is a preset distance. Here, the vehicle coordinate system is a plane rectangular coordinate system, the projection line segment of the target end in the vehicle coordinate system is parallel to the first coordinate axis, and the distance between the target point and the target end is the distance between the target point and the projection line segment.

[0129] For example, refer to Figure 5A The first end side 011 of the target end side is vehicle 01, the first coordinate axis is the y-axis, the first coordinate of the first target point 021 is y11, the first coordinate of the second target point 022 is y12, the first coordinate of the third target point 023 is y13, and the first coordinate of the fourth target point 024 is y14.

[0130] In embodiments of this application, the electronic device can determine a first coordinate interval based on the first coordinate of each target point in the first coordinate axis of the vehicle coordinate system. The lower limit of the first coordinate interval is the minimum value of the first coordinate of each target point in the first coordinate axis of the vehicle coordinate system, and the upper limit of the first coordinate interval is the maximum value of the first coordinate of each target point in the first coordinate axis of the vehicle coordinate system. If there is an overlapping area between the first coordinate interval and the second coordinate interval, a collision between the vehicle and the target obstacle is predicted. The second coordinate interval is the coordinate interval of the first coordinate axis corresponding to the projected line segment on the target end side.

[0131] For example, refer to Figure 5B The first coordinate interval is [y11, y13]. The second coordinate interval is [-0.5w, 0.5w].

[0132] Specifically, refer to Figure 5B When the first end side 011 of vehicle 01 is taken as the target end side, the target position information (y11, df) and (y13, df) of the first target point 021 and the third target point 023 are located at the same position, and the target position information (y12, df) and (y14, df) of the second target point 022 and the fourth target point 024 are located at the same position. With the first coordinate axis being the y-axis, the minimum value of the first coordinate is determined to be y11 (y13), the maximum value of the first coordinate is y12 (y14), and the range of the first coordinate is between y11 (y13) and y12 (y14). Continue referring to... Figure 5B When the target end is the first end 011, the first coordinate axis is the y-axis. The second coordinate interval is the range of the projected line segment of the vehicle's width, that is, the interval from -0.5w to 0.5w in the y-axis direction. Since there is an overlap between the range of y11 (y13) and y12 (y14) and the range from -0.5w to 0.5w, it can be determined that there is a collision risk between the target vehicle 02 and the first end 011 of the vehicle 01. In some embodiments of this application, if the electronic device determines that there is a collision risk between the target vehicle 02 and the vehicle 01, it can also determine, based on the first coordinate interval (e.g., based on the positions of y11 (y13) and y12 (y14), how much the vehicle 01 should shift to the left or right to avoid colliding with the target vehicle 02.

[0133] Similarly, refer to Figure 6BWhen the second end side 012 of vehicle 01 is taken as the target end side, the target position information (y21, dr) and (y23, dr) of the first target point 021 and the third target point 023 are located at the same position, and the target position information (y22, dr) and (y24, dr) of the second target point 022 and the fourth target point 024 are located at the same position. With the first coordinate axis being the y-axis, the minimum value of the first coordinate is determined to be y21 (y23), the maximum value is y22 (y24), and the range of the first coordinate is between y21 (y23) and y22 (y24). Continue referring to... Figure 6B When the target end is the second end 012, the first coordinate axis is the y-axis. The second coordinate interval is the range of the projected line segment of the vehicle's width, that is, the interval from -0.5w to 0.5w in the y-axis direction. Since the range between y21 (y23) and y22 (y24) does not overlap with the range from -0.5w to 0.5w, it can be determined that there is no collision risk between the target vehicle 02 and the second end 012 of vehicle 01. In some embodiments of this application, if the electronic device predicts that the target vehicle 02 and vehicle 01 will not collide, the degree of collision risk can also be determined by the distance between the first and second coordinate intervals to provide a collision risk warning to the user.

[0134] Reference Figure 7B When the third end side 013 of vehicle 01 is taken as the target end side, the target position information (-0.5w, x32) and (-0.5w, x34) of the first target point 021 and the third target point 023 are located at the same position, and the target position information (-0.5w, x31) and (-0.5w, x33) of the second target point 022 and the fourth target point 024 are located at the same position. With the first coordinate axis being the x-axis, the minimum value of the first coordinate is determined to be x31 (x33), the maximum value of the first coordinate is x32 (x34), and the range of the first coordinate is between x31 (x33) and x32 (x34). Continue referring to... Figure 7B When the target end is the third end 013, the first coordinate axis is the x-axis. The second coordinate interval is the range of the projected line segment of the vehicle's length, that is, the range from -dr to df in the x-axis direction. There is an overlapping area between the range of x31 (x33) and x32 (x34) and the range from -dr to df, so it can be determined that there is a collision risk between the target vehicle 02 and the third end 013 of vehicle 01.

[0135] Reference Figure 8BWhen the fourth end side 014 of vehicle 01 is taken as the target end side, the target position information (0.5w, x42) and (0.5w, x44) of the first target point 021 and the third target point 023 are located at the same position, and the target position information (0.5w, x41) and (0.5w, x43) of the second target point 022 and the fourth target point 024 are located at the same position. With the first coordinate axis being the x-axis, the minimum value of the first coordinate is determined to be x41 (x43), the maximum value is x42 (x44), and the range of the first coordinate is between x41 (x43) and x42 (x44). Continue referring to... Figure 7B When the target end is the fourth end 014, the first coordinate axis is the x-axis. The second coordinate interval is the range of the projected line segment of the vehicle's length, that is, the range from -dr to df in the x-axis direction. There is an overlapping area between the range of x41 (x43) and x42 (x44) and the range from -dr to df, so it can be determined that there is a collision risk between the target vehicle 02 and the fourth end 014 of vehicle 01.

[0136] The above method can determine the specific time and location of collisions between multiple target points of the target obstacle and the vehicle, thereby improving the accuracy of predicting whether a collision will occur between the vehicle and the target obstacle.

[0137] It is understood that after determining that there is an overlapping area between the first coordinate interval and the second coordinate interval of the target end of the vehicle in the second direction, it can be determined that there is a risk of collision between the target obstacle and the vehicle. Therefore, in some embodiments of this application, the collision time between the target obstacle and the vehicle can be further determined.

[0138] It is understandable that during the above judgment process, collisions could occur at multiple ends of the target obstacle and the vehicle. However, under normal circumstances, the target obstacle will at most collide with two adjacent ends of the vehicle. Therefore, after determining the ends of the collision, the collision time between the vehicle and the target obstacle can be determined based on the time sequence of the first moment corresponding to each target point and the first coordinates corresponding to each target point.

[0139] For example, if the first coordinate of the target point corresponding to the earliest first moment among multiple first moments is in the second coordinate interval, the earliest first moment among the first moments is taken as the collision moment.

[0140] For example, when the target end is the fourth end, the corresponding second coordinate interval is the range between -dr and df. (Refer to...) Figure 8A and Figure 8BIt can be determined that t41 is the earliest of the multiple first moments, and the first coordinate x41 of the second target point 022 corresponding to t41 is within the second coordinate interval. Therefore, the collision time of the fourth end of the target vehicle 02 and the vehicle 01 is determined to be the first moment t41 of the second target point 022.

[0141] In some embodiments of this application, if the first coordinate of the target point corresponding to the earliest first time among a plurality of first times is not in the second coordinate interval, the collision time can be determined based on the first time and first coordinate corresponding to the first reference point and the second reference point.

[0142] In some embodiments of this application, multiple first moments can be arranged in chronological order, and two adjacent first moments can be traversed in chronological order. When the range between the first coordinates of the two target points corresponding to the two adjacent first moments of the first group includes the second coordinate interval, the two target points corresponding to the two adjacent first moments of the first group are respectively used as the first reference point and the second reference point.

[0143] For example, refer to Figure 7A and Figure 7B When the target end is the third end, the corresponding second coordinate interval is the range between -dr and df. It can be determined that the first time t31 corresponding to the second target point 022 is the earliest first time among the first times corresponding to multiple target points, and the second target point 022 is not located within the second coordinate interval [-dr, df]. Therefore, it is necessary to determine the second set of target points.

[0144] Understandable, continue to refer to Figure 7A and Figure 7B Among multiple target points, the first time t31 of the second target point 022 and the first time t32 of the first target point 021 are the two earliest adjacent first times in chronological order. Therefore, the first times t31 and t32 can be traversed earliest. It can be understood that the interval [x32, x31] between the first coordinates x31 of the second target point 022 and x32 of the first target point 021 overlaps with the second coordinate interval [-dr, df]. Therefore, the first times t31 and t32 can be considered as the first pair of adjacent first times. The second target points 022 and 021 corresponding to the first times t31 and t32, respectively, can serve as the first reference point and the second reference point, so that the collision time can be determined based on the first coordinates and first times of the first and second reference points.

[0145] Similarly, the first time t32 of the first target point 021 and the first time t33 of the fourth target point 024 are adjacent times. Furthermore, the interval [x32, x33] between the first coordinate x32 of the first target point 021 and the first coordinate x33 of the fourth target point 024 overlaps with the second coordinate interval [-dr, df]. However, the electronic device will not first traverse the first times t32 and t33 according to the time sequence. Therefore, the first times t32 and t33 do not belong to the first group of two adjacent first times. The following describes the process of determining the specific time of collision between the target obstacle and the vehicle from the first times corresponding to multiple target points on the target side in the embodiments of this application.

[0146] In some embodiments of this application, the first moments of multiple target points of the target obstacle can be ordered in chronological order. For example, to determine the collision moment of multiple target points of target vehicle 02 and the first end side 011 of vehicle 01, refer to... Figure 5A and Figure 5B The time sequence of the first moments is t11, t12, t13, and t14. Let t(i) represent the i-th first moment in the time sequence from earliest to latest, where i is 1, 2, 3, or 4. For example, when i=1, t(i) is t11, and the first coordinate of the target point corresponding to t(i) is y11. When i=2, t(i) is t12, and the first coordinate of the target point corresponding to t(i) is y12. When i=3, t(i) is t13, and the first coordinate of the target point corresponding to t(i) is y13. When i=4, t(i) is t14, and the first coordinate of the target point corresponding to t(i) is y14.

[0147] For example, Figure 10 According to some embodiments of this application, a flowchart of an implementation for determining the collision moment is shown.

[0148] The following processes can all be executed by electronic devices.

[0149] Reference Figure 10 The process includes:

[0150] S1001, set the initial value of i to 1.

[0151] It is understood that in the embodiments of this application, i starts from 1 and cycles, so i can be set to 1. In other embodiments, the initial value of i can also be set to other values. This application does not limit the initial value of i.

[0152] S1002, determine whether the first coordinate corresponding to t(i) is located in the second coordinate interval.

[0153] If the judgment result is yes, then execute S1008 and take t(i) as the collision time.

[0154] If the result is negative, then execute S1003 to determine whether the first coordinate corresponding to t(i+1) is located in the second coordinate interval.

[0155] S1003, determine whether the first coordinate corresponding to t(i+1) is located in the second coordinate interval.

[0156] It is understandable that if the first coordinate corresponding to t(i) is not located in the second coordinate interval, it is also possible to determine whether the first coordinate corresponding to t(i+1) is located in the second coordinate interval.

[0157] If the judgment result is yes, then execute S1009 to determine the collision time based on the first coordinates corresponding to t(i) and t(i+1).

[0158] If the judgment result is negative, then execute S1004 to determine whether the range between the first coordinate corresponding to t(i) and the first coordinate corresponding to t(i+1) overlaps with the second coordinate interval.

[0159] S1004, determine whether the range between the first coordinates corresponding to t(i) and the first coordinates corresponding to t(i+1) overlaps with the second coordinate interval.

[0160] It is understandable that if neither the first coordinate corresponding to t(i) nor the first coordinate corresponding to t(i+1) is within the second coordinate interval, then it can be determined whether the range between the first coordinate corresponding to t(i) and the first coordinate corresponding to t(i+1) overlaps with the second coordinate interval.

[0161] If the judgment result is yes, then execute S1005 to determine the collision time based on the first coordinates corresponding to t(i) and t(i+1).

[0162] If the judgment result is negative, then execute S1006 and set i = i + 1.

[0163] S1005, determine the collision time based on the first coordinates corresponding to t(i) and t(i+1).

[0164] It can be understood that if the range between the first coordinates corresponding to t(i) and the first coordinates corresponding to t(i+1) overlaps with the second coordinate interval, and the first coordinates corresponding to t(i) and t(i+1) are not within the second coordinate interval, then the target points corresponding to t(i) and t(i+1) can be determined as the second set of target points. Specifically, the target point corresponding to t(i) can be used as the first reference point, and the target point corresponding to t(i+1) can be used as the second reference point.

[0165] In some embodiments of this application, if the first coordinate of the target point corresponding to t(i) is less than the lower limit of the second coordinate interval, and the first coordinate of the target point corresponding to t(i+1) is greater than the upper limit of the second coordinate interval, then the collision time can be determined according to the following equation (2):

[0166] TCC=((y12+0.5w)×t(i)-(y11+0.5w)×t(i+1)) / (y12-y11) (2)

[0167] Where TCC is the collision time, t(i) is the i-th first moment in chronological order, and t(i+1) is the (i+1)-th first moment in chronological order. y11 is the first coordinate of the target point corresponding to t(i), y12 is the first coordinate of the target point corresponding to t(i+1), and w is the width of vehicle 01.

[0168] It can be understood that when the first coordinate of the target point corresponding to t(i) is less than the lower limit of the second coordinate interval, and the first coordinate of the target point corresponding to t(i+1) is greater than the upper limit of the second coordinate interval, the collision time between target vehicle 02 and vehicle 01 can be regarded as the collision at the lower limit endpoint of the second coordinate interval between target vehicle 02 and vehicle 01 (when the first end side 011 is taken as the target end side, the lower limit endpoint is -0.5w). That is, the specific collision time is between t(i) and t(i+1), and within the short period between t(i) and t(i+1), target vehicle 02 can be regarded as moving at a constant speed relative to vehicle 01. Then, the distance that target vehicle 02 moves from the first coordinate of the target point corresponding to time t(i) to the lower limit endpoint of the second coordinate interval is -0.5w-y11, and the movement time is TCC-t(i). The distance from the lower limit endpoint of the second coordinate interval to the first coordinate of the target point corresponding to t(i+1) is y12-(-0.5w), and the movement time is t(i+1)-TCC. Since the target vehicle 02 is considered to be moving at a constant speed relative to vehicle 01, then (y12-(-0.5w)) / (t(i+1)-TCC) = (-0.5w-y11) / (TCC-t(i)). Therefore, formula (2) can be determined based on this formula.

[0169] In some embodiments of this application, if the first coordinate of the target point corresponding to t(i) is greater than the upper limit of the second coordinate interval, and the first coordinate of the target point corresponding to t(i+1) is less than the lower limit of the second coordinate interval, then the collision time can be determined according to the following equation (3):

[0170] TCC=((0.5w-y12)×t(i)-(0.5w-y11)×t(i+1)) / (y11-y12) (3)

[0171] Where TCC is the collision time, t(i) is the i-th first moment in chronological order, and t(i+1) is the (i+1)-th first moment in chronological order. y11 is the first coordinate of the target point corresponding to t(i), y12 is the first coordinate of the target point corresponding to t(i+1), and w is the width of vehicle 01.

[0172] It can be understood that when the first coordinate of the target point corresponding to t(i) is greater than the upper limit of the second coordinate interval, and the first coordinate of the target point corresponding to t(i+1) is less than the lower limit of the second coordinate interval, the collision time between target vehicle 02 and vehicle 01 can be regarded as the collision at the upper limit of the second coordinate interval between target vehicle 02 and vehicle 01 (when the first end side 011 is taken as the target end side, the upper limit is 0.5w). That is, the specific collision time is between t(i) and t(i+1), and during the short period between t(i) and t(i+1), target vehicle 02 can be regarded as moving at a constant speed relative to vehicle 01. Then, the distance from the first coordinate of the target point corresponding to t(i) to the upper limit of the second coordinate interval is y11-0.5w, and the movement time is TCC-t(i). The distance from the upper limit of the second coordinate interval to the first coordinate of the target point corresponding to t(i+1) is 0.5w-y12, and the movement time is t(i+1)-TCC. And since the target vehicle 02 is considered to be moving at a constant speed relative to vehicle 01, then (0.5w-y12) / (t(i+1)-TCC)=(y11-0.5w) / (TCC-t(i)). Therefore, the above formula (3) can be determined based on this formula.

[0173] It is understandable that when the third end side 013 or the fourth end side 014 is the target end side, the process of determining the collision time can refer to the example when the first end side 011 is the target end side.

[0174] Thus, the collision time TCC of the first end side 011 of the target vehicle 02 and vehicle 01 can be determined.

[0175] S1006, let i = i + 1.

[0176] It is understandable that if the collision time cannot be determined based on the current i at the first moment, the next iteration can be performed.

[0177] S1007, determine whether i is greater than or equal to the number of target points.

[0178] It is understood that in the embodiments of this application, the number of target points is 4. In other embodiments, the number of target points may be more or less. It is understood that if i is greater than the number of target points, but the collision moment has not been determined, it indicates a problem with the data, and the iteration process can be terminated. If i is equal to the number of target points, then in the next process, it is necessary to determine the first moment corresponding to i+1. Since i is already the number of target points, there is no (i+1)th first moment, and the iteration needs to be terminated.

[0179] If the judgment result is yes, then the iteration ends.

[0180] If the result is negative, then execute S1003 to determine whether the first coordinate corresponding to t(i+1) is located in the second coordinate interval.

[0181] S1008, where t(i) is taken as the collision time.

[0182] In some embodiments of this application, t(i) is used as the collision time of the current target side only when i=1 and the first coordinate of the target point corresponding to t(i) is determined to be located in the second coordinate interval.

[0183] For example, if the first coordinate of the target point corresponding to t(2) is located in the second coordinate interval, then t(i+1), i.e., the first coordinate of the target point corresponding to t(2) is located in the second coordinate interval, is determined at i=1, and the process S1009 will be executed. If the first coordinate of the target point corresponding to t(3) is located in the second coordinate interval, then it can be determined at i=2 that the first coordinate of the target point corresponding to t(2) is not located in the second coordinate interval. Therefore, it is possible to determine t(i+1), i.e., to determine whether the first coordinate of the target point corresponding to t(3) is located in the second coordinate interval. Then the process S1009 will still be executed.

[0184] S1009, determine the collision time based on the first coordinates corresponding to t(i) and t(i+1).

[0185] In some embodiments of this application, if t(i) is not within the second coordinate interval, and t(i+1) is within the second coordinate interval, then the target points corresponding to t(i+1) and t(i) can be used as the second group of target points. It can be understood that if the first coordinate of the target point corresponding to t(i) is not within the second coordinate interval, and the first coordinate of the target point corresponding to t(i+1) is within the second coordinate interval, then it can be determined that the ranges of the first coordinates of the target points corresponding to t(i) and t(i+1) overlap with the second coordinate interval. Therefore, t(i+1) and t(i) belong to two adjacent first moments in the first group. Therefore, the target points corresponding to t(i+1) and t(i) can be used as the first reference point and the second reference point, respectively, to calculate the collision moment.

[0186] In some embodiments of this application, if the first coordinate of the target point corresponding to t(i) is less than the lower limit of the second coordinate interval, the collision time can be determined according to equation (2). If the first coordinate of the target point corresponding to t(i) is greater than the upper limit of the second coordinate interval, the collision time can be determined according to equation (3). In this way, the collision time TCC of the first end side 011 of the target vehicle 02 and the vehicle 01 can be determined.

[0187] Understandably, the above process can determine the specific moment of collision between the target obstacle and the target end of the vehicle, thus enabling more accurate collision risk avoidance. For example, it can prompt adjustments to the vehicle's direction or slow down, thereby improving driving safety.

[0188] In some embodiments of this application, the electronic device can also determine the specific collision side of the target obstacle and the vehicle based on the collision times of multiple target side sides. For example, the side side corresponding to the earliest collision time among the collision times of the first side side, the collision times of the third side side, and the collision times of the fourth side side can be determined as the finally predicted side side that will collide with the target obstacle.

[0189] Through the above-described scheme, the vehicle in this embodiment can better assess and make decisions when facing active safety issues (such as automatic emergency braking (AEB) and emergency lane keeping (ELK)), ensuring positive function triggering and avoiding false triggering. Furthermore, this embodiment uses a function of position and time to represent the position of the vehicle and the target obstacle at any given time in the future. Compared to collision detection at discrete time points, this avoids the problem of missed collision detection due to excessively sparse sampling time, thereby improving the accuracy of collision prediction.

[0190] The electronic devices involved in the above embodiments are described below.

[0191] For example, Figure 11 According to some embodiments of this application, a schematic diagram of the structure of an electronic device 100 is shown.

[0192] The electronic device 100 may be an in-vehicle device as described in the foregoing embodiments, and the electronic device 100 is used to implement the vehicle collision prediction method provided in the foregoing embodiments.

[0193] like Figure 11 As shown, the electronic device 100 includes one or more processors 101, system memory 102, non-volatile memory (NVM) 103, communication interface 104, input / output device 105, and system control logic unit 106 for coupling the processor 101, system memory 102, non-volatile memory 103, communication interface 104, and input / output (I / O) device 105. Wherein:

[0194] Processor 101 may include one or more processing units, such as a central processing unit (CPU), graphics processing unit (GPU), digital signal processor (DSP), microprocessor (MCU), artificial intelligence (AI) processor, field programmable gate array (FPGA), neural network processing unit (NPU), etc. The processing module or circuit may include one or more single-core or multi-core processors. In some embodiments, the CPU may be used to optimize a neural network model to be run. For example, in some embodiments of this application, the electronic device 100 can predict the trajectory of a target obstacle using a neural network model, and the NPU can be used to run the neural network model to be run.

[0195] System memory 102 is volatile memory, such as random-access memory (RAM), double data rate synchronous dynamic random access memory (DDR SDRAM), etc. System memory is used for temporary storage of data and / or instructions. For example, in some embodiments, system memory 102 can be used to store data provided in the foregoing embodiments, such as sensor data, image data, or video data, and can also be used to store instructions for the vehicle collision prediction methods provided in the foregoing embodiments.

[0196] The non-volatile memory 103 may include one or more tangible, non-transitory computer-readable media for storing data and / or instructions. In some embodiments, the non-volatile memory 103 may include any suitable non-volatile memory and / or any suitable non-volatile storage device, such as a hard disk drive (HDD), compact disc (CD), digital versatile disc (DVD), solid-state drive (SSD), etc. In some embodiments, the non-volatile memory 103 may also be a removable storage medium, such as secure digital (SD) storage. In other embodiments, the non-volatile memory 103 may be used to store instructions for the vehicle collision prediction methods provided in the foregoing embodiments.

[0197] Specifically, system memory 102 and non-volatile memory 103 may each include a temporary copy and a permanent copy of instruction 107. Instruction 107 may include, when executed by at least one of processors 101, causing electronic device 100 to implement the vehicle collision prediction method provided in the embodiments of this application.

[0198] The communication interface 104 may include a transceiver for providing a wired or wireless communication interface for the electronic device 100, thereby enabling communication with any other suitable device via one or more networks. In some embodiments, the communication interface 104 may be integrated into other components of the electronic device 100, for example, the communication interface 104 may be integrated into the processor 101. In some embodiments, the electronic device 100 may communicate with other devices through the communication interface 104, for example, the electronic device 100 may obtain relevant data from other devices through the communication interface 104.

[0199] Input / output (I / O) device 105 can be an input device such as a keyboard or mouse, and an output device such as a monitor. Users can interact with electronic device 100 through input / output (I / O) device 105.

[0200] The system control logic unit 106 may include any suitable interface controller to provide any suitable interface to other modules of the electronic device 100. For example, in some embodiments, the system control logic unit 106 may include one or more memory controllers to provide an interface to the system memory 102 and the non-volatile memory 103.

[0201] In some embodiments, at least one of the processors 101 may be packaged together with the logic of one or more controllers for the system control logic unit 106 to form a system in package (SiP). In other embodiments, at least one of the processors 101 may also be integrated on the same chip with the logic of one or more controllers for the system control logic unit 106 to form a system-on-chip (SoC).

[0202] Understandable. Figure 11 The structure of the electronic device 100 shown is only one example; in other embodiments, the electronic device 100 may include more... Figure 11 It can have more or fewer components, or combine some components, or split some components, or arrange the components differently. Figure 11 The components can be implemented in hardware, software, or a combination of both.

[0203] It is understood that electronic device 100 can be any device configured on the vehicle, including but not limited to mobile phones, in-vehicle systems, terminals in self-driving vehicles, wireless terminals in transportation safety, terminals in smart cities, and so on.

[0204] This application also provides a program product that stores instructions. When these instructions are executed on an electronic device, the electronic device can implement the vehicle collision prediction method provided in the foregoing embodiments.

[0205] This application also provides a readable storage medium storing one or more programs, which, when executed by an electronic device, enable the electronic device to implement the vehicle collision prediction method provided in the foregoing embodiments.

[0206] Various embodiments of the mechanisms disclosed in this application can be implemented in hardware, software, firmware, or combinations of these implementation methods. Embodiments of this application can be implemented as computer programs or program code executable on a programmable system, the programmable system including at least one processor, a storage system (including volatile and non-volatile memory and / or storage elements), at least one input device, and at least one output device.

[0207] Program code can be applied to input instructions to execute the functions described in this application and generate output information. The output information can be applied to one or more output devices in a known manner. For the purposes of this application, the processing system includes any system having a processor such as, for example, a digital signal processor, a microcontroller, an application-specific integrated circuit, or a microprocessor.

[0208] The program code can be implemented using a high-level procedural language or an object-oriented programming language to communicate with the processing system. Assembly language or machine language can also be used when needed. In fact, the mechanisms described in this application are not limited to any particular programming language. In either case, the language can be a compiled language or an interpreted language.

[0209] In some cases, the disclosed embodiments may be implemented in hardware, firmware, software, or any combination thereof. The disclosed embodiments may also be implemented as instructions carried on or stored thereon by one or more transient or non-transitory machine-readable (e.g., computer-readable) storage media, which may be read and executed by one or more processors. For example, the instructions may be distributed via a network or through other computer-readable media. Therefore, machine-readable media can include any mechanism for storing or transmitting information in a machine-readable (e.g., computer-readable) form, including but not limited to floppy disks, optical disks, CD-ROMs, compact disc-read-only memory (CD-ROMs), magneto-optical disks, read-only memory (ROM), random-access memory (RAM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), magnetic cards or optical cards, flash memory, or tangible machine-readable storage for transmitting information (e.g., carrier waves, infrared signals, digital signals, etc.) using the Internet in the form of electrical, optical, acoustic, or other forms of propagation signals. Therefore, machine-readable media includes any type of machine-readable medium suitable for storing or transmitting electronic instructions or information in a machine-readable (e.g., computer-readable) form.

[0210] In the accompanying drawings, some structural or methodological features may be shown in a specific arrangement and / or order. However, it should be understood that such a specific arrangement and / or order may not be necessary. Rather, in some embodiments, these features may be arranged in a manner and / or order different from that shown in the illustrative drawings. Furthermore, the inclusion of structural or methodological features in a particular figure does not imply that such features are required in all embodiments, and in some embodiments, these features may be omitted or may be combined with other features.

[0211] It should be noted that all units / modules mentioned in the device embodiments of this application are logical units / modules. Physically, a logical unit / module can be a physical unit / module, a part of a physical unit / module, or a combination of multiple physical units / modules. The physical implementation of these logical units / modules themselves is not the most important factor; the combination of functions implemented by these logical units / modules is the key to solving the technical problems proposed in this application. Furthermore, to highlight the innovative aspects of this application, the above-described device embodiments of this application have not introduced units / modules that are not closely related to solving the technical problems proposed in this application. This does not mean that the above-described device embodiments do not contain other units / modules.

[0212] It should be noted that in the examples and description of this application, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one" does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0213] Although this application has been illustrated and described with reference to certain preferred embodiments thereof, those skilled in the art will understand that various changes in form and detail may be made thereto without departing from the scope of this application.

Claims

1. A vehicle collision prediction method characterized by, The method comprises: determining a first predicted trajectory of the target obstacle in a first time period in the future based on historical motion information of the target obstacle, and determining a second predicted trajectory of the vehicle in the first time period based on historical motion information of the vehicle; determining first pose information of the target obstacle relative to the vehicle in the first time period based on the first predicted trajectory and the second predicted trajectory; determining, based on the first pose information, first time instants and target position information corresponding to a plurality of target points of the target obstacle respectively, the first time instant indicating a time instant when a distance of the corresponding target point to a target end side of the vehicle is a preset distance, and the target position information indicating a target position of the corresponding target point relative to the vehicle when the distance of the corresponding target point to the target end side is the preset distance, the projection line segment of the target end side in the vehicle coordinate system being parallel to a first coordinate axis in the vehicle coordinate system; determining, based on the plurality of target position information, a first coordinate of each of the target points in the first coordinate axis in the vehicle coordinate system when the distance of each of the target points to the target end side is the preset distance; determining a first coordinate interval based on the first coordinate of each of the target points in the first coordinate axis in the vehicle coordinate system; predicting that the vehicle and the target obstacle will collide when there is an overlapping region between the first coordinate interval and a second coordinate interval indicated by the target end side of the vehicle.

2. The vehicle collision prediction method according to claim 1, characterized by, The target end side of the vehicle comprises at least one of the following end sides: a first end side and a second end side opposite in the length direction of the vehicle, and a third end side and a fourth end side opposite in the width direction of the vehicle.

3. The vehicle collision prediction method according to claim 1 or 2, characterized by, The first pose information comprises a position of a center of mass of the target obstacle in the vehicle coordinate system and a first deflection angle of a reference axis of the target obstacle relative to a first coordinate axis of the vehicle coordinate system. The determining, based on the first pose information, of the first time instants and the target position information corresponding to the plurality of target points of the target obstacle respectively comprises: determining, based on relative positions of the plurality of target points of the target obstacle to the center of mass of the target obstacle, positions of the center of mass of the target obstacle in the vehicle coordinate system corresponding to a plurality of time instants in the first time period, and the first deflection angles corresponding to the plurality of time instants in the first time period, a first correspondence relationship between positions of the plurality of target points of the target obstacle in the vehicle coordinate system and time in the first time period; determining, based on the first correspondence relationship, the first time instants when the positions of the plurality of target points are respectively a preset distance from the target end side, and the target position information corresponding to the first time instants of the plurality of target points respectively.

4. The vehicle collision prediction method according to claim 1 or 2, characterized by, The vehicle coordinate system is a planar rectangular coordinate system, and the distance of the target point to the target end side is the distance of the target point to the projection line segment; a lower limit value of the first coordinate interval is a minimum value of the first coordinate of the target point in the first coordinate axis in the vehicle coordinate system, and an upper limit value of the first coordinate interval is a maximum value of the first coordinate of the target point in the first coordinate axis in the vehicle coordinate system. The second coordinate interval is a coordinate interval corresponding to the first coordinate axis of the projection line segment.

5. The vehicle collision prediction method of claim 4, wherein The method further comprises: In the case that there is an overlapping area between the first coordinate interval and the second coordinate interval, determining a collision time of the vehicle and the target obstacle according to a time sequence of first time instants corresponding to each of the target points and the first coordinates corresponding to each of the target points.

6. The vehicle collision prediction method of claim 5, wherein Determining the collision time of the vehicle and the target obstacle according to the time sequence of first time instants corresponding to each of the target points and the first coordinates corresponding to each of the target points comprises: In the case that the first coordinate of the target point corresponding to the earliest first time instant among the plurality of first time instants corresponding to the plurality of target points is in the second coordinate interval, taking the earliest first time instant as the collision time; Otherwise, determining the collision time based on the first time instant and the first coordinate corresponding to a first reference point and the first time instant and the first coordinate corresponding to a second reference point; The first reference point and the second reference point are determined according to the following manner: arranging the plurality of first time instants in time sequence and starting to traverse two adjacent first time instants in time sequence; In the case that a range between the first coordinates of the two target points corresponding to the first group of two adjacent first time instants includes the second coordinate interval, taking the two target points corresponding to the first group of two adjacent first time instants as the first reference point and the second reference point respectively.

7. The vehicle crash prediction method according to any one of claims 1, 2, 5, 6, characterized in that, The preset distance is greater than or equal to 0 m and less than or equal to 0.1 m.

8. An electronic device, comprising: Comprise: a memory for storing instructions; at least one processor for executing the instructions to cause the electronic device to implement the vehicle collision prediction method of any one of claims 1 to 7.

9. A computer-readable storage medium, characterized in that, The readable storage medium has instructions stored thereon, and the instructions, when executed on a computer, cause the computer to perform the vehicle collision prediction method of any one of claims 1 to 7.

10. A computer program product, characterised in that, The computer program product has instructions stored thereon, and the instructions, when executed on a device, cause the device to perform the vehicle collision prediction method of any one of claims 1 to 7.

Images