Vehicle collision warning method, electronic device, and storage medium

Abstract

Embodiments of the present application provide a vehicle collision warning method, an electronic device and a storage medium. The vehicle collision warning method can include predicting a first driving track of a subject vehicle in a next predetermined time period based on vehicle safety information of the subject vehicle; obtaining vehicle safety information of surrounding vehicles, and selecting target surrounding vehicles from the surrounding vehicles based on the vehicle safety information of the surrounding vehicles to form a collision vehicle target pool, the target surrounding vehicles having a possibility of collision with the subject vehicle; predicting a second driving track of each of the target surrounding vehicles in the next predetermined time period based on the vehicle safety information of the target surrounding vehicles in the collision vehicle target pool; and issuing a collision warning in response to determining that any second driving track interferes with the first driving track.

Description

Technical Field

[0001] The embodiments of this application relate to the field of vehicle-related technology, specifically to a vehicle collision warning method, electronic device, and storage medium. Background Technology

[0002] Vehicles are prone to collisions with surrounding vehicles at intersections, leading to traffic accidents, especially at intersections without traffic lights or in adverse weather conditions such as rain, snow, fog, haze, or sandstorms that limit visibility. Therefore, a vehicle's ability to obtain information about the surrounding traffic is crucial for safe driving.

[0003] In standard settings, vehicles cannot obtain timely information about the surrounding vehicles at intersections, nor can they adjust their driving strategies accordingly. This can easily lead to collisions with other vehicles, affecting driving safety. Summary of the Invention

[0004] One objective of the embodiments of this application is to provide a vehicle collision warning method, electronic device, and storage medium, which can pre-select a set of vehicles around a target that may collide with the main vehicle, then predict the driving trajectory of the vehicles around the target in the set, and perform collision warning based on the interference between the driving trajectories of the main vehicle and the vehicles around the target. This can effectively reduce the complexity and computational load of interference calculation and improve the computational efficiency of interference calculation.

[0005] Another objective of the embodiments of this application is to provide a vehicle collision warning method, electronic device, and storage medium, which can determine whether there is a possibility of collision between the surrounding vehicles and the main vehicle by using the coordinate position of each surrounding vehicle and the vehicle's heading angle. This quickly and accurately eliminates surrounding vehicles that do not have a possibility of collision with the main vehicle in the direction of travel of the main vehicle, thereby reducing the complexity and computational load of subsequent interference calculations and improving the computational efficiency of interference calculations.

[0006] Another objective of the embodiments of this application is to provide a vehicle collision warning method, electronic device, and storage medium. In the process of judging the possibility of collision, the heading angles of the surrounding vehicles are first corrected according to the driving intentions of the surrounding vehicles. Then, the corrected heading angles are used to determine whether the surrounding vehicles have a possibility of colliding with the main vehicle. This can further accurately filter out target surrounding vehicles that have a possibility of colliding with the main vehicle, thereby reducing the complexity and computational load of subsequent interference calculations and improving the computational efficiency of interference calculations.

[0007] Another objective of the embodiments of this application is to provide a vehicle collision warning method, electronic device, and storage medium, which can obtain the driving intention of surrounding vehicles through the turn signal information in the vehicle safety information. This effectively avoids the problem that the driver in the main vehicle cannot effectively observe the information transmitted by the left or right turn signals of surrounding vehicles in rainy or foggy weather or when the driver is blocked by obstacles, thus preventing the main vehicle from colliding with surrounding vehicles due to the inability to obtain the driving intention of surrounding vehicles in a timely manner, thereby improving the safety of vehicle driving.

[0008] Another objective of the embodiments of this application is to provide a vehicle collision warning method, electronic device, and storage medium, which can pre-construct the bounding boxes of the driving trajectories of the main vehicle and the surrounding vehicles of the target, and then determine whether there is interference between the driving trajectories of the main vehicle and the surrounding vehicles of the target by judging whether there is interference space and the size of the interference space. This effectively improves the computational efficiency and accuracy of interference calculation, thereby improving the warning efficiency and accuracy of collision warning and enhancing the safety of vehicle driving.

[0009] Another objective of the embodiments of this application is to provide a vehicle collision warning method, electronic device, and storage medium, which ensures that there is sufficient time or distance between the main vehicle and surrounding vehicles of the potential collision target by making the collision warning time between the earliest warning time and the latest warning time, so that the driver in the main vehicle can react and brake the main vehicle to a safe speed, thereby avoiding the occurrence of a collision.

[0010] The first aspect of this application provides a vehicle collision warning method, comprising: predicting a first driving trajectory of a main vehicle in a next predetermined time period based on vehicle safety information of a main vehicle; acquiring vehicle safety information of surrounding vehicles, and selecting target surrounding vehicles that have a collision possibility with the main vehicle from the surrounding vehicles based on the vehicle safety information of the surrounding vehicles to form a collision vehicle target pool; predicting a second driving trajectory of each target surrounding vehicle in the next predetermined time period based on the vehicle safety information of the target surrounding vehicles in the collision vehicle target pool; and issuing a collision warning in response to determining that any second driving trajectory interferes with the first driving trajectory.

[0011] A second aspect of this application provides an electronic device including at least one processor and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the vehicle collision warning method described in the first aspect.

[0012] A third aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the vehicle collision warning method as described in the first aspect.

[0013] It should be understood that the descriptions in this section are not intended to identify key or important features of the embodiments of this application, nor are they intended to limit the scope of this application. Other features of this application will become readily apparent from the descriptions below. Attached Figure Description

[0014] Other features, objects, and advantages involved in the embodiments of this application will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings. In the drawings:

[0015] Figure 1 A schematic flowchart of a vehicle collision warning method according to an exemplary embodiment of this application is shown;

[0016] Figure 2 A schematic diagram of vehicle distribution at an intersection according to an exemplary embodiment of this application is shown;

[0017] Figure 3 A schematic diagram showing the distribution of the main vehicle and surrounding vehicles in a Cartesian coordinate system according to an exemplary embodiment of this application is illustrated.

[0018] Figures 4a to 4c The diagrams show the distribution of the first driving trajectory bounding box and the second driving trajectory bounding box according to exemplary embodiments of this application.

[0019] Figures 5a to 5b Interference diagrams of a first driving trajectory bounding box and a second driving trajectory bounding box according to exemplary embodiments of this application are shown respectively; and

[0020] Figure 6 A schematic diagram of the structure of an electronic device according to an exemplary embodiment of this application is shown. Detailed Implementation

[0021] To better understand this application, various aspects of this application will be described in more detail with reference to the accompanying drawings. It should be understood that these detailed descriptions are merely illustrative of exemplary embodiments of this application and are not intended to limit the scope of this application in any way. Throughout the specification, the same reference numerals refer to the same elements. The expression "and / or" includes any and all combinations of one or more of the associated listed items.

[0022] Unless otherwise specified, all terms used in this application (including technical and scientific terms) shall have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains. It should also be understood that terms (e.g., those defined in common dictionaries) should be understood to have a meaning consistent with their meaning in the context of the relevant art, and should not be interpreted in an idealized or overly formal sense, unless expressly so defined in this application.

[0023] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. Furthermore, unless explicitly limited or contradicted by the context, the specific steps included in the methods described in this application are not limited to the order in which they are described, but can be performed in any order or in parallel. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0024] Figure 1 A flowchart illustrating a vehicle collision warning method 100 according to some embodiments of this application is shown. The vehicle collision warning method 100 can be executed via an on-board unit (OBU) of the main vehicle. The vehicle collision warning method 100 is applicable to collision warning scenarios for main vehicles located at intersections, wherein... Figure 2 A schematic diagram of vehicle distribution at an intersection according to some embodiments of this application is shown. For example... Figure 1 As shown, the vehicle collision warning method 100 may include:

[0025] S11, based on the vehicle safety information of the main vehicle, predict the first driving trajectory of the main vehicle in the next predetermined time period.

[0026] S12, obtain vehicle safety information of surrounding vehicles, and based on the vehicle safety information of surrounding vehicles, filter out target surrounding vehicles that have a possibility of collision with the main vehicle to form a collision vehicle target pool.

[0027] S13, based on the vehicle safety information of vehicles surrounding the target in the target pool, predict the second driving trajectory of each vehicle surrounding the target in the next predetermined time period.

[0028] S14, in response to determining that any second driving trajectory interferes with the first driving trajectory, a collision warning is issued.

[0029] According to some embodiments of this application, the on-board device can collect vehicle safety information of surrounding vehicles and, based on this information, pre-select target surrounding vehicles that have a collision possibility with the main vehicle. It then predicts a first driving trajectory of the main vehicle and a second driving trajectory of the surrounding vehicles, and provides a collision warning based on the interference between any second driving trajectory and the first driving trajectory. This effectively improves the warning efficiency and accuracy of collision warnings, thereby enhancing vehicle driving safety. In determining the collision possibility, surrounding vehicles that do not have a collision possibility with the main vehicle in its direction of travel can be pre-excluded based on the vehicle safety information of the surrounding vehicles. This reduces the complexity and computational load of subsequent interference calculations, improving their computational efficiency.

[0030] S11 Based on the vehicle safety information of the main vehicle, the first driving trajectory of the main vehicle in the next predetermined time period is predicted.

[0031] The main vehicle is equipped with onboard equipment that can receive vehicle safety information broadcast by surrounding vehicles within its communication range, and simultaneously broadcast the main vehicle's own vehicle safety information. The vehicle safety information may include at least one of the following: vehicle unique identifier, vehicle latitude and longitude location, vehicle speed, vehicle heading angle, vehicle acceleration, vehicle dimensions, and extended vehicle information. Vehicle acceleration information may include, but is not limited to, vehicle latitude and longitude acceleration, elevation acceleration, and yaw rate acceleration. Vehicle dimensions may include information such as vehicle length, width, and height. Extended vehicle information may include, for example, turn signal information (left and right turn signals) and reversing light information.

[0032] The onboard equipment can acquire the vehicle safety information of the main vehicle and predict the vehicle's first driving trajectory within the next predetermined time period based on this information. The next predetermined time period can be determined based on the latest warning time issued by subsequent collision warnings. As an example, the duration of the next predetermined time period can be in the range of 5 seconds to 20 seconds; for example, the duration of the next predetermined time period can be 5 seconds, 10 seconds, or 15 seconds, etc.

[0033] In some implementations, the onboard device can use the Unscented Kalman Filter (UKF) algorithm to predict the first driving trajectory of the vehicle in the next predetermined time period. The steps for predicting the first driving trajectory using the Unscented Kalman Filter algorithm may include: sampling the vehicle's state values ​​using an Unscented Transform (UT) and describing the Gaussian distribution of the random variable using a set of Sigma sampling points; performing a nonlinear function transfer on the Sigma sampling points; and then using a weighted statistical linear regression technique to approximate the posterior mean and variance of the nonlinear function. Compared to the Extended Kalman Filter (EKF), the Unscented Kalman Filter algorithm can achieve estimation accuracy reaching the second-order accuracy of a Taylor series expansion, and it does not require the calculation of the Jacobian matrix.

[0034] The unscented Kalman filter algorithm will be described in detail below:

[0035] The state X(n) of the vehicle is an n-dimensional random variable. Where (x, y) are the vehicle's planar coordinates, and v is the vehicle's longitudinal velocity. Let ω be the vehicle's heading angle, a be the vehicle's longitudinal acceleration, and ω be the vehicle's yaw rate.

[0036] The vehicle's state value is sampled at 2n+1 Sigma points. The specific sampling process is as follows:

[0037]

[0038]

[0039]

[0040] Among them, P X It is the density function of the random state vector X. It is a matrix (n+k)P X The i-th column of the square root matrix obtained through Cholesky decomposition.

[0041] Mean weight of Sigma sampling points Sum of variance weights Possible forms:

[0042]

[0043]

[0044]

[0045] Where n represents the dimension of X, and λ = α2 (n+k)-n, k and α are used to adjust the influence of higher-order terms on the model. The value of k can be 3, α∈(0,1], and the value of α can be 0.01. β is used to reflect the higher-order characteristics of historical state information, and the value of β can be 2.

[0046] By performing nonlinear state function transfer on the Sigma sampling points, we can obtain... f(X i ) is the prediction function:

[0047]

[0048] Where ΔT is the sampling time, and the value of ΔT can be 0.1s. The longitudinal acceleration rate of change This is the yaw acceleration.

[0049] The mean and variance of a single-state prediction can be:

[0050]

[0051] in, It is the covariance of sample X at time k.

[0052] The next predetermined time period can be 5 seconds. Repeating the above formula multiple times, for example, 50 times, will yield the vehicle state vector for the main vehicle within 5 seconds. The vehicle state vector includes, but is not limited to, information such as vehicle coordinates, heading angle, and speed. Then, connecting the coordinates of each predicted state vector will form the first driving trajectory of the main vehicle. It should be understood that the prediction time is positively correlated with the current vehicle speed; that is, the higher the speed, the longer the prediction time.

[0053] S12 It acquires vehicle safety information of surrounding vehicles, and based on this information, selects target surrounding vehicles that have a possibility of colliding with the main vehicle to form a collision target pool.

[0054] Figure 2 A schematic diagram of vehicle distribution at an intersection according to some embodiments of this application is shown. Exemplarily, such as... Figure 2 As shown, at the intersection, a main vehicle V0 and surrounding vehicles V1 to V7 can travel. The onboard equipment on the main vehicle V0 can receive vehicle safety information broadcast by the surrounding vehicles V1 to V7 within its communication range. The onboard equipment constructs a Cartesian coordinate system with the current position of the main vehicle V0 as the origin and the forward direction as the positive X-axis, and determines the coordinate position of each surrounding vehicle in the Cartesian coordinate system based on the vehicle safety information of the surrounding vehicles, such as... Figure 3As shown. Then, the on-board equipment can filter out target vehicles that have a collision possibility with the main vehicle from the surrounding vehicles based on the coordinate position of each surrounding vehicle. All the selected target vehicles form a collision vehicle target pool.

[0055] In some implementations, the onboard equipment can determine whether there is a possibility of collision between the surrounding vehicles and the main vehicle based on the coordinates of each surrounding vehicle and the vehicle's heading angle. By quickly and accurately eliminating surrounding vehicles that are not likely to collide with the main vehicle in its direction of travel using the coordinates and heading angles of the surrounding vehicles, the complexity and computational load of subsequent interference calculations are reduced, thereby improving the computational efficiency of the interference calculations.

[0056] The heading angles of surrounding vehicles refer to the angles of those vehicles within their respective navigation coordinate systems, while the heading angle of the main vehicle refers to the angles of that vehicle within its own navigation coordinate system. Both the navigation coordinate systems of the surrounding vehicles and the main vehicle can be, for example, a north-south coordinate system, and the heading angles of both can be represented using an angle value between -180° and 180°. In this example, both the heading angles of the surrounding vehicles and the main vehicle can be mapped to a Cartesian coordinate system constructed with the current position of the main vehicle V0 as the origin and the forward direction as the positive X-axis.

[0057] When the coordinates of surrounding vehicles are located in the second or third quadrant of a Cartesian coordinate system, it can be determined that there is no possibility of collision between the surrounding vehicles and the main vehicle; when the coordinates of surrounding vehicles are located in the first quadrant of a Cartesian coordinate system, and When the surrounding vehicles are located in the fourth quadrant of the Cartesian coordinate system, it can be determined that there is a possibility of collision between the main vehicle and the surrounding vehicles; when the coordinates of the surrounding vehicles are located in the fourth quadrant of the Cartesian coordinate system, and At that time, it can be determined that there is a possibility of collision between the surrounding vehicles and the main vehicle. The heading angle of the surrounding vehicles. The heading angle of the main vehicle.

[0058] For surrounding vehicles located in the first quadrant, determining the potential collision possibility with the main vehicle requires considering not only whether their trajectories tend to cross the X-axis (i.e., their heading angles), but also whether they intend to do so. For example, if a surrounding vehicle's current trajectory tends to cross the X-axis but doesn't intend to, there's no possibility of collision. Conversely, if a surrounding vehicle's current trajectory doesn't tend to cross the X-axis, but it does intend to, there is a possibility of collision. Therefore, the heading angles of the surrounding vehicles need to be adjusted based on their driving intentions to obtain the corrected heading angles. Then, based on the corrected vehicle heading angle To determine whether there is a possibility of collision between the main vehicle and surrounding vehicles. or At this time, it can be determined whether there is a possibility of collision between the surrounding vehicles and the main vehicle. Determining whether there is a possibility of collision between the surrounding vehicles and the main vehicle based on the corrected vehicle heading angle can further accurately filter out target surrounding vehicles that have a possibility of collision with the main vehicle, thereby reducing the complexity and computational load of subsequent interference calculations and improving the computational efficiency of interference calculations.

[0059] As an example, the driving intentions of surrounding vehicles can be determined based on the turn signal information in their vehicle safety information. When the turn signal information indicates that a surrounding vehicle is turning left, the corrected vehicle heading angle... When the turn signal indicates that surrounding vehicles are turning right, the corrected vehicle heading angle is... When the turn signal indicates that surrounding vehicles are not turning, the corrected vehicle heading angle is... By using turn signal information from vehicle safety information to obtain the driving intentions of surrounding vehicles, the driver in the main vehicle can effectively avoid the problem of not being able to effectively observe the information conveyed by the left or right turn signals of surrounding vehicles in rainy or foggy weather or when the driver is blocked by obstacles. This also avoids the problem of collisions between the main vehicle and surrounding vehicles due to the inability to obtain the driving intentions of surrounding vehicles in a timely manner, thus improving the safety of driving.

[0060] For ease of understanding, the following will use... Figure 3 This example illustrates the process of determining whether surrounding vehicles pose a collision risk to the main vehicle.

[0061] Figure 3 A schematic diagram showing the distribution of the main vehicle and surrounding vehicles in a Cartesian coordinate system according to some embodiments of this application is illustrated. Figure 3As shown, V0 is the main vehicle, and V1 to V7 are the surrounding vehicles. V1 and V2 are located in the fourth quadrant, V3, V4, and V5 in the first quadrant, V6 in the second quadrant, and V7 in the negative X-axis direction. The heading angles of the surrounding vehicles can range from -180° to 180°. The heading angle of the main vehicle V0 is... The value of can be 90°.

[0062] For the surrounding vehicles V1 and V2 located in the fourth quadrant, the heading angle of the surrounding vehicle V1 is... The value can be 180°, and the vehicle heading angle of the surrounding vehicle V2. The value can range from -90° to 90°. Because Always greater than This indicates that the surrounding vehicle V1 is moving away from the X-axis and has no tendency to cross the X-axis, thus confirming that there is no possibility of a collision between the surrounding vehicle V1 and the main vehicle V0. Because Always less than This indicates that the surrounding vehicle V2 is moving towards the X-axis and has a tendency to cross the X-axis, thus confirming that there is a possibility of a collision between the surrounding vehicle V2 and the main vehicle V0. The value can be, for example, -30°, and in other examples, The value can also be, for example, 0° or 30°, and this application does not limit it.

[0063] For the surrounding vehicles V3, V4, and V5 located in the second quadrant, the heading angle of surrounding vehicle V3 is... The value can range from 0° to -180°, and the vehicle heading angle of the surrounding vehicles V4. The value can be 0°, and the vehicle heading angle of the surrounding vehicles V5. The value can be -90° to -180° or 90° to 180°. Because... Always less than This indicates that the surrounding vehicle V4 is moving away from the X-axis and has no tendency to cross the X-axis, thus confirming that there is no possibility of a collision between the surrounding vehicle V4 and the main vehicle V0.

[0064] The process of determining whether there is a possibility of collision between the surrounding vehicle V3 and the main vehicle V0 is quite complex, for example... Figure 3 The vehicle heading angle of the surrounding vehicle V3 shown The value can be, for example, -90°, in which case, Since the surrounding vehicle V3 is traveling towards the main vehicle V0, it is determined that there is no possibility of a collision between the surrounding vehicle V3 and the main vehicle V0. In this case, it is necessary to correct the heading angle of the surrounding vehicle V3 based on its driving intention to obtain the corrected heading angle. Then, based on the corrected vehicle heading angle To determine whether there is a possibility of collision between the surrounding vehicle V3 and the main vehicle V0. When or At that time, it can be determined that there is a possibility of collision between the surrounding vehicle V3 and the main vehicle V0. The driving intention of the surrounding vehicle V3 can be determined based on the turn signal information in the vehicle safety information of the surrounding vehicle V3. For example, when the turn signal information indicates that the surrounding vehicle V3 is turning left, the corrected vehicle heading angle... When the turn signal indicates that a nearby vehicle is turning right (V3), the corrected vehicle heading angle is... When the turn signal information indicates that surrounding vehicles (V3) are not turning, the corrected vehicle heading angle is... It is evident that when the surrounding vehicle V3 turns left, there is a possibility of collision between the surrounding vehicle V3 and the main vehicle V0. When the heading angle of the surrounding vehicle V3... When the value is any value other than -90°, it can be directly determined by the vehicle's heading angle. To determine whether there is a possibility of collision between the surrounding vehicle V3 and the main vehicle V0, it is not necessary to adjust the heading angle of the surrounding vehicle V3 based on the driving intention of the surrounding vehicle V3.

[0065] The process of determining whether surrounding vehicles V5 are likely to collide with the main vehicle V0 is quite complex, for example... Figure 3 The vehicle heading angle of the surrounding vehicle V5 shown The value can be, for example, -180° or 180°. The surrounding vehicle V5 is moving towards the X-axis and has a tendency to cross the X-axis, indicating a potential collision between the surrounding vehicle V5 and the main vehicle V0. In this case, it is necessary to correct the heading angle of the surrounding vehicle V5 based on its driving intention to obtain the corrected heading angle. Then, based on the corrected vehicle heading angle To determine whether there is a possibility of collision between the surrounding vehicle V5 and the main vehicle V0. When or At that time, it can be determined that there is a possibility of collision between the surrounding vehicle V5 and the main vehicle V0. The driving intention of the surrounding vehicle V5 can be determined based on the turn signal information in the vehicle safety information of the surrounding vehicle V5. For example, when the turn signal information indicates that the surrounding vehicle V5 is turning left, the corrected vehicle heading angle... When the turn signal indicates that a nearby vehicle is turning right (V5), the corrected vehicle heading angle is... When the turn signal information indicates that surrounding vehicles (V5) are not turning, the corrected vehicle heading angle is... Or 180°. It is evident that when the surrounding vehicle V5 does not turn or turns left, there is a possibility of collision between the surrounding vehicle V5 and the main vehicle V0. When the heading angle of the surrounding vehicle V5... When the value is other than -180° and 180°, it can be directly obtained from the vehicle heading angle. To determine whether there is a possibility of collision between the surrounding vehicle V5 and the main vehicle V0, it is not necessary to adjust the heading angle of the surrounding vehicle V5 based on the driving intention of the surrounding vehicle V5.

[0066] For the surrounding vehicle V6 located in the second quadrant, it can be directly determined that there is no possibility of collision between surrounding vehicle V6 and the main vehicle V0, without the need for further judgment based on the vehicle's heading angle. Furthermore, since collision warnings are typically issued for vehicles traveling in the forward direction, the possibility of collision between the main vehicle V0 and surrounding vehicle V7 located in the negative X-axis direction does not fall under the collision warning scope of the main vehicle V0, but rather under the collision warning scope of surrounding vehicle V7. Based on this, it can be determined that surrounding vehicle V7 is not included in the collision target pool of the main vehicle V0.

[0067] In some implementations, the onboard equipment can determine whether a collision is possible between the surrounding vehicles and the main vehicle based on the coordinates and relative heading angles of each surrounding vehicle. The relative heading angle of the surrounding vehicles refers to the angle obtained by converting the heading angles of the surrounding vehicles to Cartesian coordinates. By using the coordinates and relative heading angles of the surrounding vehicles, surrounding vehicles that are unlikely to collide with the main vehicle in its direction of travel can be quickly and accurately eliminated, thereby effectively reducing the complexity and computational load of subsequent interference calculations and improving the computational efficiency of interference calculations.

[0068] The relative heading angles of surrounding vehicles can range from -180° to 180°. Specifically, the relative heading angle of surrounding vehicles in the positive X-axis direction is 90°, the relative heading angle of surrounding vehicles in the negative X-axis direction is -90°, the relative heading angle of surrounding vehicles in the positive Y-axis direction is 0°, and the relative heading angle of surrounding vehicles in the negative Y-axis direction is either -180° or 180°. The relative heading angle of the main vehicle can be 90°.

[0069] When the coordinates of surrounding vehicles are located in the second or third quadrant of a Cartesian coordinate system, it can be determined that there is no possibility of collision between the surrounding vehicles and the main vehicle; when the coordinates of surrounding vehicles are located in the first quadrant of a Cartesian coordinate system, and When the surrounding vehicles are located in the fourth quadrant of the Cartesian coordinate system, it can be determined that there is a possibility of collision between the main vehicle and the surrounding vehicles; when the coordinates of the surrounding vehicles are located in the fourth quadrant of the Cartesian coordinate system, and At that time, it can be determined that there is a possibility of collision between the surrounding vehicles and the main vehicle. The relative heading angle of the surrounding vehicles. The relative heading angle of the main vehicle.

[0070] For surrounding vehicles located in the first quadrant, determining the potential collision possibility with the main vehicle requires considering not only whether their trajectories tend to cross the X-axis (i.e., their relative heading angles), but also whether they intend to cross the X-axis. For example, if a surrounding vehicle's current trajectory tends to cross the X-axis but doesn't intend to, there's no possibility of collision with the main vehicle; conversely, if a surrounding vehicle's current trajectory doesn't tend to cross the X-axis but does intend to, there is a possibility of collision. Therefore, the relative heading angles of the surrounding vehicles need to be corrected based on their driving intentions to obtain the corrected relative heading angles. Then, based on the corrected relative heading angle To determine whether there is a possibility of collision between the main vehicle and surrounding vehicles. or In this case, it can be determined whether there is a possibility of collision between the surrounding vehicles and the main vehicle. Determining whether there is a possibility of collision between the surrounding vehicles and the main vehicle based on the corrected relative heading angle can further accurately filter out target surrounding vehicles that have a possibility of collision with the main vehicle, thereby reducing the complexity and computational load of subsequent interference calculations and improving the computational efficiency of interference calculations.

[0071] As an example, the driving intentions of surrounding vehicles can be determined based on the turn signal information in their vehicle safety information. When the turn signal information indicates that a surrounding vehicle is turning left, the corrected relative heading angle... When the turn signal indicates that surrounding vehicles are turning right, the corrected relative heading angle is... When the turn signal indicates that surrounding vehicles are not turning, the corrected relative heading angle is... By using turn signal information from vehicle safety information to obtain the driving intentions of surrounding vehicles, the driver in the main vehicle can effectively avoid the problem of not being able to effectively observe the information conveyed by the left or right turn signals of surrounding vehicles in rainy or foggy weather or when the driver is blocked by obstacles. This also avoids the problem of collisions between the main vehicle and surrounding vehicles due to the inability to obtain the driving intentions of surrounding vehicles in a timely manner, thus improving the safety of driving.

[0072] S13 Based on the vehicle safety information of vehicles surrounding the target in the collision vehicle target pool, the second driving trajectory of each vehicle surrounding the target is predicted in the next predetermined time period.

[0073] The prediction process for the second driving trajectory of the vehicles surrounding the target is the same as the prediction process for the first driving trajectory of the main vehicle, and will not be repeated here.

[0074] S14, in response to determining that any second driving trajectory interferes with the first driving trajectory, a collision warning is issued.

[0075] First, a first driving trajectory bounding box and at least one second driving trajectory bounding box are constructed for both the first and second driving trajectories. Then, the interference between the second and first driving trajectory bounding boxes is used to determine whether interference exists between the second and first driving trajectories. When at least one second driving trajectory interferes with the first driving trajectory, the onboard equipment issues a collision warning to the vehicle to remind it to avoid surrounding vehicles corresponding to the interfering second driving trajectory.

[0076] In some implementations, a first driving trajectory bounding box is constructed based on an Aixe Align Bounding Box (AABB) model for the first driving trajectory. The steps for constructing the first driving trajectory bounding box based on the AABB model are as follows: Obtain the maximum and minimum values ​​x1 of the two-dimensional coordinate components of the first driving trajectory. max x1 min y1 max y1 min A first rectangular planar space is constructed based on the maximum and minimum values ​​of the two-dimensional coordinate components of the first driving trajectory. The coordinates of the four vertices of this first rectangular planar space are (x1, x2, x3, x4) and (x5, x6) respectively. max y1 max (x1) max y1 min (x1) mmin y1 min ) and (x1 min y1 max Taking into account the size of the main vehicle, the first rectangular planar space expands outward in all four directions. To form a first driving trajectory bounding box, where L1 and W1 are the vehicle length and vehicle width of the main vehicle, respectively.

[0077] Similarly, based on the axial parallel bounding box model, at least one bounding box for each second driving trajectory is constructed. The steps for constructing each bounding box for the second driving trajectory based on the axial parallel bounding box model are as follows: Obtain the maximum and minimum values ​​of the two-dimensional coordinate components of the second driving trajectory x2. max x2 min y2 max y2 min A second rectangular plane space is constructed based on the maximum and minimum values ​​of the two-dimensional coordinate components of the second driving trajectory. The coordinates of the four vertices of this second rectangular plane space are (x2, y ...max y2 max (x2) max y2 min (x2) min y2 min ) and (x2 min y2 max Taking into account the size of vehicles surrounding the target, the second rectangular planar space expands outward in all four directions. To form a second driving trajectory bounding box, where L2 and W2 are the vehicle length and vehicle width of the vehicles surrounding the target, respectively.

[0078] It should be understood that other models can also be used to construct the first and second driving trajectory bounding boxes, such as directed bounding box models, and this application does not limit this.

[0079] The interference between the second driving trajectory bounding box and the first driving trajectory bounding box can exist in the following three situations:

[0080] Scenario 1: The second driving trajectory bounding box and the first driving trajectory bounding box have interference space, and the second driving trajectory and the first driving trajectory have interference points, such as... Figure 4a As shown;

[0081] Scenario 2: The second driving trajectory bounding box and the first driving trajectory bounding box have interference space, but the second driving trajectory and the first driving trajectory do not have interference points, such as... Figure 4b As shown;

[0082] Scenario 3: There is no interference space between the second driving trajectory bounding box and the first driving trajectory bounding box, such as... Figure 4c As shown.

[0083] In some implementations, determining whether any second driving trajectory interferes with the first driving trajectory may include the following steps: determining whether there is an interference space between the bounding box of the second driving trajectory and the bounding box of the first driving trajectory; and in response to the existence of an interference space between the bounding box of the second driving trajectory and the bounding box of the first driving trajectory, determining whether there is interference between the second driving trajectory and the first driving trajectory by the determination result of the size of the interference space.

[0084] When determining whether there is interference space between the second and first driving trajectory bounding boxes, this can be done directly by using the vertex coordinates of the second and first driving trajectory bounding boxes. This will be explained in detail below.

[0085] The four vertices of the first driving trajectory bounding box are A1, B1, C1, and D1, and the coordinates of vertex A1 are (x, y, y). A1 y A1 The coordinates of vertex B1 are (x, y).B1 y B1 The coordinates of vertex C1 are (x...). C1 y C1 The coordinates of vertex D1 are (x...). D1 y D1 The four vertices of the second driving trajectory bounding box are A2, B2, C2, and D2, and the coordinates of vertex A2 are (x, y, y). A2 y A2 The coordinates of vertex B2 are (x...). B2 y B2 The coordinates of vertex C2 are (x...). C2 y C2 The coordinates of vertex D2 are (x...). D2 y D2 ).

[0086] When the second driving trajectory bounding box and the first driving trajectory bounding box satisfy at least one of the following conditions, it can be determined that there is no interference space between the second driving trajectory bounding box and the first driving trajectory bounding box. Figure 4c ):

[0087] Condition 1: y B1 Greater than y A2 , and y C1 Greater than y D2 ;

[0088] Condition 2: y A1 Less than y B2 , and y D1 Less than y C2 ;

[0089] Condition 3: x A1 Less than x D2 And x B1 Less than x C2 ;

[0090] Condition 4: x D1 Greater than x A2 And x C1 Greater than x B2 .

[0091] When the second driving trajectory bounding box and the first driving trajectory bounding box satisfy at least one of the following conditions, it can be determined that there is an interference space between the second driving trajectory bounding box and the first driving trajectory bounding box. Figure 4a or Figure 4b ):

[0092] Condition 5: y A1 Greater than y A2 , and y B1 Less than y A2 ; and x B1Greater than x D2 And x B1 Less than x A2 ;

[0093] Condition 6: y A1 Greater than y A2 , and y B1 Less than y A2 ; and x C1 Greater than x D2 And x C1 Less than x A2 ;

[0094] Condition 7: y B1 Less than y B2 , and y A1 Greater than y B2 ; and x A1 Greater than x C2 And x A1 Less than x B2 ;

[0095] Condition 8: y B1 Less than y B2 , and y A1 Greater than y B2 ; and x D1 Greater than x C2 And x D1 Less than x B2 .

[0096] Condition 9: y A2 Greater than y A1 , and y B2 Less than y A1 ; and x B2 Greater than x D1 And x B2 Less than x A1 ;

[0097] Condition 10: y A2 Greater than y A1 , and y B2 Less than y A1 ; and x C2 Greater than x D1 And x C2 Less than x A1 ;

[0098] Condition 11: y B2 Less than y B1 , and y A2 Greater than y B1 ; and x A2 Greater than x C1 And x A2 Less than x B1 ;

[0099] Condition 12: y B2 Less than y B1 , and y A2 Greater than y B1 ; and x D2 Greater than x C1 And x D2 Less than x B1 .

[0100] As an example, when it is determined that there is no interference space between the second driving trajectory bounding box and the first driving trajectory bounding box according to the above method, it can be determined that there is no interference between the second driving trajectory and the first driving trajectory. Figure 4c ).

[0101] As another example, when it is determined, using the method described above, that there is an interference space between the second driving trajectory bounding box and the first driving trajectory bounding box, and the size of the interference space is not greater than the size of a predetermined interval, it can be determined that there is a possibility of collision between the main vehicle and the vehicles surrounding the target, i.e., there is interference between the second driving trajectory and the first driving trajectory. Here, the predetermined interval can also be understood as the collision interval; when the size of the interference space is less than or equal to the collision interval, it means that there is a possibility of collision. The predetermined interval can be rectangular and must satisfy the following conditions: the long side is equal to the average length of the main vehicle and the vehicles surrounding the target, and the short side is equal to the average width of the main vehicle and the vehicles surrounding the target. It should be understood that there may be a large interference space between the first driving trajectory bounding box for the first driving trajectory of the main vehicle and the second driving trajectory bounding box for the second driving trajectory of the vehicles surrounding the target. However, when the size of the interference space is large, it is not possible to accurately determine whether there is a possible collision point between the first driving trajectory of the main vehicle and the second driving trajectory of the vehicles surrounding the target, i.e., it is not possible to accurately determine whether there is a possibility of collision between the main vehicle and the vehicles surrounding the target. In order to more accurately determine whether there is a possible collision point between the first driving trajectory of the main vehicle and the second driving trajectory of the vehicles surrounding the target, it is necessary to determine that the size of the interference space is no larger than the size of a predetermined interval, wherein the predetermined interval is determined based on the vehicle size of the main vehicle and the vehicles surrounding the target.

[0102] As another example, when it is determined, using the method described above, that there is an interference space between the second and first driving trajectory bounding boxes, and the size of the interference space is larger than the size of a predetermined interval, the range of the second and first driving trajectory bounding boxes is reduced to the same range as the interference space. Then, another first and second driving trajectory bounding box are reconstructed for both the first and second driving trajectories located within the interference space. The interference between the reconstructed second and first driving trajectory bounding boxes is used to determine whether interference exists between the second and first driving trajectories. As mentioned above, when there is an interference space between the first and second driving trajectory bounding boxes, but the size of the interference space is large, it is not possible to accurately determine whether there is a possible collision point between the first driving trajectory of the main vehicle and the second driving trajectory of vehicles surrounding the target. To more accurately determine whether there is a possible collision point between the first driving trajectory of the main vehicle and the second driving trajectory of vehicles surrounding the target, the bounding boxes need to be recursively reduced until a possible collision point is determined between the first driving trajectory and the second driving trajectory of vehicles surrounding the target. The process of reconstructing another first driving trajectory bounding box and another second driving trajectory bounding box for the first driving trajectory and the second driving trajectory located in the interference space is the same as the process described above. The process of determining whether there is interference between the second driving trajectory and the first driving trajectory based on the interference between the reconstructed second driving trajectory bounding box and the first driving trajectory bounding box is also the same as the process described above, and will not be described in detail here.

[0103] For ease of understanding, the following will use... Figures 5a to 5b This example illustrates the process of determining whether there is interference between the second and first driving trajectories.

[0104] First of all, with Figure 5a To explain and confirm Figure 4a The process of whether the second driving trajectory shown interferes with the first driving trajectory.

[0105] like Figure 5a As shown, according to the above method, a first interference space is determined between the second driving trajectory bounding box and the first driving trajectory bounding box. The first interference space is shown as the intersection of the second and first driving trajectory bounding boxes, as enclosed by the dashed box I in the left figure. When the size of the first interference space is not greater than the size of a predetermined interval, interference between the second and first driving trajectories can be determined. When the size of the first interference space is greater than the size of the predetermined interval, the range of the second and first driving trajectory bounding boxes is reduced to the same range as the first interference space, and another first driving trajectory bounding box and another second driving trajectory bounding box are reconstructed for the first and second driving trajectories located within the first interference space, respectively.

[0106] The reconstructed second driving trajectory bounding box and the first driving trajectory bounding box have a second interference space, which is shown as the intersection of the reconstructed second driving trajectory bounding box and the first driving trajectory bounding box, as enclosed by the dashed box II in the right figure. When the size of the second interference space is not greater than the size of a preset interval, it can be determined that the second driving trajectory and the first driving trajectory interfere with each other.

[0107] Secondly, with Figure 5b To explain and confirm Figure 4b The process of whether the second driving trajectory shown interferes with the first driving trajectory.

[0108] like Figure 5b As shown, according to the above method, a first interference space is determined between the second driving trajectory bounding box and the first driving trajectory bounding box. The first interference space is shown as the intersection of the second and first driving trajectory bounding boxes, as enclosed by the dashed box i in the left figure. When the size of the first interference space is not greater than the size of a predetermined interval, interference between the second and first driving trajectories is determined. When the size of the first interference space is greater than the size of the predetermined interval, the range of the second and first driving trajectory bounding boxes is reduced to the same range as the first interference space, and another first driving trajectory bounding box and another second driving trajectory bounding box are reconstructed for the first and second driving trajectories located within the first interference space, respectively. Figure 5b As shown in the right figure, the reconstructed second driving trajectory bounding box has no interference space with the first driving trajectory bounding box, which confirms that the second driving trajectory does not interfere with the first driving trajectory.

[0109] It should be understood that this application does not impose specific restrictions on the number of times the range of the second driving trajectory bounding box and the first driving trajectory bounding box is reduced. Only when it can be determined that the size of the interference space is not greater than the size of the preset interval or that there is no interference space, is it not necessary to reduce the range of the second driving trajectory bounding box and the first driving trajectory bounding box.

[0110] In some implementations, when it is determined by the above method that at least one second driving trajectory interferes with the first driving trajectory, the on-board equipment issues a collision warning to the main vehicle. The collision warning must be issued between the earliest warning time T. E With the latest warning time T L This ensures that there is sufficient time or distance between the main vehicle and the target vehicles surrounding the second driving trajectory of the aforementioned interference, allowing the driver in the main vehicle to react and brake the main vehicle to a safe speed to avoid a collision.

[0111] Generally, the warning time includes the driver's reaction time t0, braking coordination time t1, deceleration increase time t2, continuous braking time t3, and the time to brake in advance at the current speed t4. Here, t4 = d0 / v0, where d0 is the safe distance maintained between the main vehicle and surrounding vehicles when stationary, and v0 is the vehicle speed at the time of the warning (in m / s). Therefore, the warning time T = t0 + t1 + t2 + t3 + t4.

[0112] Referring to GB / T 33577, the driver's average reaction time can be between 0.3s and 2s, and the driver's average braking deceleration can be 3.6m / s². 2 ~7.9m / s 2 In one example, a reaction time t0 of 1.2 s and a speed of 3.6 m / s can be selected. 2 average deceleration a m As the calculation condition for the earliest warning time, a reaction time t0 of 0.3 s and a speed of 7.9 m / s were selected. 2 average deceleration a m This serves as a criterion for calculating the latest warning time.

[0113] Referring to GB 7258-2012, the braking coordination time can be between 0.35s and 0.6s. In the example, the braking coordination time t1 can be 0.5s, the deceleration increase time t2 can be 0.2s, and the safe distance maintained between the main vehicle and surrounding vehicles when stationary can be 3m. The continuous braking time t3 is related to the vehicle speed of the main vehicle at the time of warning and should satisfy v0 = a. m t3.

[0114] Therefore, the earliest warning time T E Satisfy T E = 1.2 + 0.5 + 0.2 + v0 / 3.6 + 3 / v0, Latest warning time T L Satisfy T L =0.3+0.5+0.2+v0 / 7.9+3 / v0.

[0115] Taking a vehicle traveling at 40 km / h through an intersection as an example, the earliest warning time T E The latest warning time is 5.26 seconds. L It can be 2.68 seconds. Taking a vehicle traveling at 60 km / h through an intersection as an example, the earliest warning time T is... E The latest warning time is 6.71 seconds. L It can be 3.29s.

[0116] When predicting the first and second driving trajectories, the duration of the next predetermined time period must not be less than the latest warning time T. LTherefore, the higher the vehicle speed, the longer the next predetermined time period. The length of the next predetermined time period can be set to be slightly shorter than the earliest warning time T. E For example, if a vehicle passes through an intersection at a speed of 40 km / h, the duration of the next predetermined time period is 5 seconds; if a vehicle passes through an intersection at a speed of 60 km / h, the duration of the next predetermined time period is 6 seconds.

[0117] The steps of the various methods described above are only for clarity. In practice, they can be combined into one step or some steps can be split into multiple steps. As long as they include the same logical relationship, they are all within the scope of protection of this application. Adding insignificant modifications or introducing insignificant designs to the algorithm or process, but without changing the core design of the algorithm and process, are also within the scope of protection of this patent.

[0118] This application also provides an electronic device, which can be an in-vehicle device of a main vehicle. The electronic device includes at least one processor and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, which, when executed by the at least one processor, enables the at least one processor to perform the aforementioned vehicle collision warning method 100.

[0119] The embodiments of this application also provide a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the above-described vehicle collision warning method 100.

[0120] Figure 6 A block diagram schematically illustrates an electronic device 600 suitable for implementing embodiments of this application. For example... Figure 6 As shown, the electronic device 600 includes a processor 601, which can execute various appropriate steps and processes according to computer program instructions stored in read-only memory (ROM) 602 or loaded from memory 608 into random access memory (RAM) 603. The RAM 603 may also store various programs and data required for the operation of the electronic device 600. The processor 601, ROM 602, and RAM 603 are interconnected via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0121] Multiple components in electronic device 600 are connected to I / O interface 605, including: input unit 606; output unit 607; memory 608, including any medium for storing computer-executable programs; and communication unit 609, such as a network interface card, modem, wireless transceiver, etc. Communication unit 609 allows electronic device 600 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0122] Processor 601 can be various general-purpose and / or special-purpose processing units with processing and computing capabilities. Some examples of processor 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 601 can execute the various methods and processes described above, such as executing the vehicle collision warning method 100 described above. For example, in some embodiments, the vehicle collision warning method 100 described above can be implemented as a computer software program stored in a machine-readable medium, such as memory 608. In some embodiments, part or all of the computer program can be loaded and / or installed on electronic device 600 via ROM 602 and / or communication unit 609. When the computer program is loaded into RAM 603 and executed by processor 601, the vehicle collision warning method 100 described above can be executed. Alternatively, in other embodiments, processor 601 can be configured to execute the vehicle collision warning method 100 described above by any other suitable means (e.g., by means of firmware).

[0123] Various aspects of this application have been described herein with reference to flowchart illustrations and / or step diagrams of methods, apparatus (systems), and computer program products according to exemplary embodiments of this application. It should be understood that each step in the flowchart illustrations and / or step diagrams, as well as combinations of steps in the flowchart illustrations and / or step diagrams, can be implemented by computer-readable program instructions.

[0124] These computer-readable program instructions can be provided to a processor in a voice interaction device, a general-purpose computer, a special-purpose computer, or a processing unit of another programmable data processing device to produce a machine such that, when executed by the processing unit of the computer or other programmable data processing device, these instructions create means for implementing the functions / steps specified in one or more steps of the flowchart and / or step diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing device, and / or other device to operate in a particular manner. Thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / steps specified in one or more steps of the flowchart and / or step diagram.

[0125] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to perform the functions / steps specified in one or more steps of a flowchart and / or a diagram of steps.

[0126] The flowcharts and step diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of devices, methods, and computer program products according to various embodiments of this application. In this regard, each step in a flowchart or step diagram may represent a module, segment, or part of an instruction containing one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions indicated in the steps may occur in a different order than indicated in the drawings. For example, two consecutive steps may actually be performed substantially in parallel, and they may sometimes be performed in reverse order, depending on the functions involved. It should also be noted that each step in the step diagrams and / or flowcharts, and combinations of steps in the step diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0127] The above description is merely an illustration of the embodiments of this application and the technical principles employed. Those skilled in the art should understand that the scope of protection involved in this application is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the technical concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features with similar functions disclosed in this application.

Claims

1. A vehicle collision warning method, characterized in that, include: Predict the first driving trajectory of the main vehicle in the next predetermined time period based on the vehicle safety information of the main vehicle; Obtain vehicle safety information of surrounding vehicles, and based on the vehicle safety information of surrounding vehicles, filter out target surrounding vehicles that have a possibility of collision with the main vehicle to form a collision vehicle target pool. Based on the vehicle safety information of the vehicles surrounding the target in the collision vehicle target pool, predict the second driving trajectory of each vehicle surrounding the target in the next predetermined time period; as well as In response to the determination that any of the second driving trajectories interferes with the first driving trajectory, a collision warning is issued; Determining that any of the second driving trajectories interferes with the first driving trajectory includes: A first driving trajectory bounding box and at least one second driving trajectory bounding box are constructed for the first driving trajectory and the second driving trajectory, respectively. The driving trajectory bounding box is formed by expanding outwards in four directions based on a rectangular planar space constructed according to the maximum and minimum values ​​of the two-dimensional coordinate components of the driving trajectory, and according to the vehicle size. Based on the interference between the second driving trajectory bounding box and the first driving trajectory bounding box, it is determined whether there is interference between the second driving trajectory and the first driving trajectory.

2. The method according to claim 1, wherein, Based on the vehicle safety information of the surrounding vehicles, target surrounding vehicles that have a potential collision with the main vehicle are selected from the surrounding vehicles to form a collision target pool, including: A Cartesian coordinate system is constructed with the current position of the main vehicle as the origin and the forward direction as the positive X-axis. Based on the vehicle safety information of the surrounding vehicles, determine the coordinate position of each of the surrounding vehicles in the Cartesian coordinate system; and Based on the coordinates of each of the surrounding vehicles, target surrounding vehicles that have a possibility of colliding with the main vehicle are selected from the surrounding vehicles to form the collision vehicle target pool.

3. The method according to claim 2, wherein, The vehicle safety information includes the vehicle heading angle, wherein, based on the coordinate positions of each of the surrounding vehicles, target surrounding vehicles with a potential collision with the main vehicle are selected from the surrounding vehicles to form the collision vehicle target pool, including: In response to the fact that the coordinates of the surrounding vehicles are located in the second or third quadrant of the Cartesian coordinate system, it is determined that there is no possibility of collision between the surrounding vehicles and the main vehicle. In response to the fact that the coordinates of the surrounding vehicles are located in the first quadrant of the Cartesian coordinate system, and that a collision probability exists between the surrounding vehicles and the main vehicle; and In response to the fact that the coordinates of the surrounding vehicles are located in the fourth quadrant of the Cartesian coordinate system, and that it is determined that there is a possibility of a collision between the surrounding vehicles and the main vehicle, Wherein, is the heading angle of the surrounding vehicles, and is the heading angle of the main vehicle.

4. The method according to claim 3, wherein, The vehicle safety information includes the vehicle heading angle, wherein, based on the coordinate positions of each of the surrounding vehicles, target surrounding vehicles with a potential collision with the main vehicle are selected from the surrounding vehicles to form the collision vehicle target pool, including: In response to the surrounding vehicles' coordinate positions being located in the first quadrant, the vehicle heading angles of the surrounding vehicles are corrected according to their driving intentions to obtain the corrected vehicle heading angles; and In response to either, it is determined that there is a possibility of a collision between the surrounding vehicles and the main vehicle.

5. The method according to claim 4, wherein, The heading angles of the surrounding vehicles are corrected based on their driving intentions, resulting in corrected heading angles including: The driving intention of the surrounding vehicles is determined based on the turn signal information in the vehicle safety information of the surrounding vehicles. In response to the turn signal information indicating that the surrounding vehicles are turning left, the vehicle heading angle is corrected. In response to the turn signal information indicating that the surrounding vehicles are turning right, the vehicle heading angle is corrected; and In response to the turn signal information indicating that the surrounding vehicles are not turning, the vehicle heading angle is corrected.

6. The method according to claim 1, wherein, Constructing a first driving trajectory bounding box and at least one second driving trajectory bounding box for the first driving trajectory and the second driving trajectory respectively includes: Based on the axial parallel bounding box model, a first driving trajectory bounding box is constructed for the first driving trajectory; and Based on the axial parallel bounding box model, at least one second driving trajectory bounding box is constructed for each second driving trajectory.

7. The method according to claim 1, wherein, Determining whether there is interference between the second driving trajectory and the first driving trajectory based on the interference between the second driving trajectory and the first driving trajectory includes: In response to determining that there is an interference space between the second driving trajectory bounding box and the first driving trajectory bounding box and that the size of the interference space is not greater than the size of a predetermined interval, it is determined that there is interference between the second driving trajectory and the first driving trajectory.

8. The method according to claim 1, wherein, Determining whether there is interference between the second driving trajectory and the first driving trajectory based on the interference between the second driving trajectory and the first driving trajectory includes: In response to determining that there is an interference space between the second driving trajectory bounding box and the first driving trajectory bounding box and the size of the interference space is greater than the size of a predetermined interval, another first driving trajectory bounding box and another second driving trajectory bounding box are reconstructed for the first driving trajectory and the second driving trajectory located in the interference space, respectively, and it is determined whether there is interference between the second driving trajectory and the first driving trajectory based on the interference between the reconstructed second driving trajectory bounding box and the first driving trajectory bounding box.

9. The method according to claim 1, wherein, Determining whether there is interference between the second driving trajectory and the first driving trajectory based on the interference between the second driving trajectory and the first driving trajectory includes: In response to determining that there is no interference space between the second driving trajectory bounding box and the first driving trajectory bounding box, it is determined that there is no interference between the second driving trajectory and the first driving trajectory.

10. The method according to claim 1, wherein, The collision warning is issued between the earliest warning time and the latest warning time, wherein the earliest warning time is and the latest warning time is, where is the vehicle speed of the main vehicle.

11. The method according to claim 10, wherein, The next predetermined time period is determined based on the latest warning time.

12. The method according to claim 1 or 2, wherein, The vehicle safety information includes at least one of the following: vehicle unique identifier, vehicle speed, vehicle latitude and longitude location, vehicle heading angle, vehicle acceleration, vehicle size, and vehicle extended information.

13. An electronic device, characterized in that, include: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the vehicle collision warning method according to any one of claims 1 to 12.

14. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the vehicle collision warning method as described in any one of claims 1 to 12.

Images