A planning trajectory evaluation method and device based on vehicle collision risk

Abstract

This application provides a method and apparatus for evaluating planned trajectories based on vehicle collision risk, relating to the field of vehicle driving assistance technology. The method includes acquiring the planned trajectory of a self-vehicle and the predicted trajectory of a target vehicle; traversing all trajectory points of the planned trajectory and acquiring the self-vehicle information and the target vehicle information corresponding to the current trajectory point; traversing all target vehicles and calculating the closest distance between the self-vehicle and the current target vehicle at the current trajectory point; evaluating the collision risk between the self-vehicle and the current target vehicle based on the closest distance; if all target vehicles have been traversed, evaluating the collision risk of the self-vehicle at the current trajectory point; if all trajectory points have been traversed, evaluating the collision risk of the self-vehicle corresponding to the planned trajectory. By simplifying the self-vehicle and target vehicle into direction vectors and calculating the closest distance between the two direction vectors at each moment, a more accurate collision risk evaluation of the self-vehicle's planned trajectory is achieved, solving the problem of low accuracy in existing methods.

Description

Technical Field

[0001] This application relates to the field of vehicle driving assistance technology, and more specifically, to a method and apparatus for evaluating planned trajectories based on vehicle collision risk. Background Technology

[0002] Vehicle collision risk is a crucial reference for evaluating vehicle trajectory planning. Data-driven collision risk assessment schemes do not require rule design but necessitate training the model on numerous standard operating conditions before deployment to the vehicle. This allows for the acquisition of relevant information through perception, directly yielding the optimal planned trajectory. However, this approach requires extensive model training, resulting in high costs and poor interpretability. Schemes based on vehicle dynamics and driving state models typically simplify the vehicle as a point mass for collision detection. They calculate the lateral and longitudinal driving states of both the vehicle and the target vehicle, then issue warnings based on predefined safety thresholds. However, this approach does not consider the geometric relationships between vehicles, leading to inaccurate relative distance calculations. Summary of the Invention

[0003] The purpose of this application is to provide a method and apparatus for evaluating planned trajectories based on vehicle collision risk. It simplifies the vehicle and the target vehicle into direction vectors, calculates the shortest distance between the two direction vectors at each moment, and achieves a more accurate collision risk evaluation of the planned trajectory of the vehicle, thus solving the problem of low accuracy in existing methods.

[0004] This application provides a method for evaluating planned trajectories based on vehicle collision risk, the method comprising:

[0005] Obtain the planned trajectory of the autonomous vehicle and the predicted trajectory of the target vehicle;

[0006] Traverse all trajectory points of the planned trajectory and obtain the vehicle information corresponding to the current trajectory point and the target vehicle information corresponding to the current trajectory point;

[0007] Iterate through all target vehicles and calculate the shortest distance between your vehicle and the current target vehicle at the current trajectory point;

[0008] The collision risk between the vehicle and the current target vehicle is assessed based on the closest distance.

[0009] If all target vehicles have been traversed, assess the collision risk of the vehicle at the current trajectory point;

[0010] If all trajectory points have been traversed, then assess the collision risk of the vehicle corresponding to the planned trajectory.

[0011] In the above implementation process, the vehicle is simplified into a direction vector. Geometric feature information and pose information of the vehicle are obtained based on visual perception. Through geometric analysis, the shortest distance between two direction vectors at each moment is calculated. This can more accurately obtain the shortest distance between the self-vehicle and the target vehicle, and achieve a more accurate collision risk assessment of the self-vehicle's planned trajectory, thus solving the problem of low accuracy of existing methods.

[0012] Furthermore, obtaining the vehicle information corresponding to the current trajectory point and the target vehicle information corresponding to the current trajectory point includes:

[0013] Obtain the motion state information and geometric feature information of the vehicle corresponding to the current trajectory point. The motion state information includes the heading angle α and the position coordinates S. ego =[X ego ,Y ego and velocity V ego The geometric feature information includes the length L of the vehicle body. ego ;

[0014] Based on the motion state information, obtain the first direction vector corresponding to the vehicle.

[0015] Obtain the motion state information and geometric feature information of the target vehicle corresponding to the current trajectory point. The motion state information includes the heading angle β and the position coordinates S. obs =[X obs ,Y obs and velocity V obs The geometric feature information includes the length L of the vehicle body. obs ;

[0016] Based on the motion state information, obtain the second direction vector corresponding to the target vehicle.

[0017] In the above implementation process, the vehicle motion state information is used to simplify the vehicle into a direction vector, so as to calculate the shortest distance between vehicles using the direction vector.

[0018] Furthermore, calculating the closest distance between the current vehicle and the current target vehicle at the current trajectory point includes:

[0019] If the first direction vector and the second direction vector are parallel, obtain the first direction vector. Distance from target vehicle S obs The nearest point P1;

[0020] Obtain the second direction vector The closest point to P1 is P2, and the distance between P1 and P2 is the closest distance between the first direction vector and the second direction vector.

[0021] If the first direction vector and the second direction vector are not parallel, obtain the intersection point of the lines containing the first direction vector and the second direction vector, and obtain the second direction vector based on the intersection point. Distance from the first direction vector The nearest point P0 on the line;

[0022] Based on P0, obtain the first direction vector. Distance from the second direction vector The nearest point P1;

[0023] Based on P1, obtain the second direction vector. Distance from the first direction vector The nearest point P2, the distance between P1 and P2 is the closest distance between the first direction vector and the second direction vector.

[0024] In the above implementation process, the shortest distance is calculated in two cases: when the first direction vector and the second direction vector are parallel and when they are not parallel.

[0025] Furthermore, the geometric feature information also includes the width W of the vehicle body. ego and the width W of the target vehicle's body. obs The assessment of the collision risk between the vehicle and the current target vehicle based on the closest distance includes:

[0026] Based on the width of the vehicle and the width of the current target vehicle, the safe radius R of the vehicle is set respectively. ego and the current target vehicle safety radius R obs ;

[0027] The safety radius expansion coefficient C of the current target vehicle is set based on the vehicle's own speed and the current target vehicle's speed. obs (C obs ≥1):

[0028] If the vehicle and the target vehicle are trending towards each other, then

[0029] Where k represents the conversion coefficient, V rel Indicates the relative speed between the vehicle and the target vehicle;

[0030] If the vehicle and the target vehicle are moving away from each other, then C obs =1;

[0031] Obtain the expansion safety radius ER of the current target vehicle. obs =C obs *R obs ;

[0032] Calculate the collision risk cost E between the vehicle and the current target vehicle, E∈[0,1]:

[0033] If L≥R ego +ER obs If E = 0, then E = 0;

[0034] If R ego +R obs <L<R ego +ER obs ,but

[0035] If L≤R ego +R obs Then E = 1;

[0036] Where L represents the shortest distance between the first direction vector of the vehicle and the second direction vector of the current target vehicle.

[0037] In the above implementation process, two layers of safety circles are designed. The safety radius serves as the basic threshold for collision safety, while the expanded safety radius serves as the threshold for calculating collision risk. The expanded safety radius is correlated with vehicle speed to improve prediction accuracy.

[0038] Furthermore, if all target vehicles have been traversed, the collision risk of the vehicle at the current trajectory point is assessed, including:

[0039] Calculate the collision risk cost E for the vehicle and each target vehicle separately. Then, the collision risk of the vehicle at the current trajectory point is the sum of the collision risk costs E of the vehicle and each target vehicle:

[0040] ∑E i＝ E1+E2+…+E i ;

[0041] Where i represents the ID of the target vehicle at the current trajectory point.

[0042] In the above implementation process, the sum of the collision risk costs E of the self-vehicle and each target vehicle is taken as the collision risk of the self-vehicle at the current trajectory point.

[0043] Furthermore, if all trajectory points have been traversed, the assessment of the collision risk of the vehicle corresponding to the planned trajectory includes:

[0044] Obtain the maximum value of the collision risk of the vehicle under all trajectory points. The maximum value is the assessment result of the collision risk of the vehicle corresponding to the planned trajectory.

[0045] In the above implementation process, the maximum collision risk of the vehicle under all trajectory points is taken as the final evaluation result.

[0046] This application embodiment also provides a trajectory evaluation device based on vehicle collision risk, the device comprising:

[0047] The trajectory acquisition module is used to acquire the planned trajectory of the self-driving vehicle and the predicted trajectory of the target vehicle;

[0048] The trajectory point traversal module is used to traverse all trajectory points of the planned trajectory and obtain the vehicle information corresponding to the current trajectory point and the target vehicle information corresponding to the current trajectory point.

[0049] The nearest distance calculation module is used to traverse all target vehicles and calculate the nearest distance between the current vehicle and the current target vehicle at the current trajectory point;

[0050] The first collision risk assessment module is used to assess the collision risk between the vehicle and the current target vehicle based on the closest distance.

[0051] The second collision risk assessment module is used to assess the collision risk of the vehicle at the current trajectory point if all target vehicles have been traversed.

[0052] The third collision risk assessment module is used to assess the collision risk of the vehicle corresponding to the planned trajectory if all trajectory points have been traversed.

[0053] In the above implementation process, the vehicle is simplified into a direction vector. Geometric feature information and pose information of the vehicle are obtained based on visual perception. Through geometric analysis, the shortest distance between two direction vectors at each moment is calculated. This can more accurately obtain the shortest distance between the self-vehicle and the target vehicle, and achieve a more accurate collision risk assessment of the self-vehicle's planned trajectory, thus solving the problem of low accuracy of existing methods.

[0054] Furthermore, the trajectory point traversal module includes:

[0055] The first information acquisition module is used to acquire the motion state information and geometric feature information of the vehicle corresponding to the current trajectory point. The motion state information includes the heading angle α and the position coordinates S. ego =[X ego ,Y ego and velocity V ego The geometric feature information includes the length L of the vehicle body. ego ;

[0056] The first direction vector acquisition module is used to acquire the first direction vector corresponding to the vehicle based on the motion state information.

[0057] The second information acquisition module is used to acquire the motion state information and geometric feature information of the target vehicle corresponding to the current trajectory point. The motion state information includes the heading angle β and the position coordinates S. obs =[X obs ,Y obs and velocity V obs The geometric feature information includes the length L of the vehicle body.obs ;

[0058] The second direction vector acquisition module is used to acquire the second direction vector corresponding to the target vehicle based on the motion state information.

[0059] In the above implementation process, the vehicle motion state information is used to simplify the vehicle into a direction vector, so as to calculate the shortest distance between vehicles using the direction vector.

[0060] This application also provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor runs the computer program to enable the electronic device to perform the vehicle collision risk-based trajectory evaluation method described in any one of the above-described methods.

[0061] This application also provides a readable storage medium storing computer program instructions. When the computer program instructions are read and executed by a processor, the planning trajectory evaluation method based on vehicle collision risk described above is performed. Attached Figure Description

[0062] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0063] Figure 1 A flowchart illustrating a trajectory planning evaluation method based on vehicle collision risk, provided for an embodiment of this application;

[0064] Figure 2 A flowchart for obtaining vehicle information provided in this application embodiment;

[0065] Figure 3 A schematic diagram of the target vehicle provided in the embodiments of this application;

[0066] Figure 4 A flowchart for calculating the closest distance when the direction vectors are parallel, provided for embodiments of this application;

[0067] Figure 5 The first direction vector is provided for the embodiments of this application. Distance from target vehicle S obs A schematic diagram of the nearest point P1;

[0068] Figure 6 The second direction vector is provided for the embodiments of this application. A schematic diagram of P2, the closest point to P1;

[0069] Figure 7 A flowchart for calculating the closest distance when the direction vectors are not parallel, provided in an embodiment of this application;

[0070] Figure 8 The requirements provided for the embodiments of this application Leave A schematic diagram of the nearest point P0 on the line;

[0071] Figure 9 The requirements provided for the embodiments of this application Leave A schematic diagram of the nearest point P1;

[0072] Figure 10 The requirements provided for the embodiments of this application Leave A diagram illustrating the nearest point P2;

[0073] Figure 11 A flowchart illustrating the collision risk cost calculation between the self-driving vehicle and the current target vehicle, provided for an embodiment of this application;

[0074] Figure 12 A schematic diagram of collision risk calculation provided for an embodiment of this application;

[0075] Figure 13 A structural block diagram of a vehicle collision risk-based trajectory evaluation device provided in this application embodiment;

[0076] Figure 14 This is a structural block diagram of another trajectory planning evaluation device based on vehicle collision risk.

[0077] icon:

[0078] 100 - Trajectory Acquisition Module; 200 - Trajectory Point Traversal Module; 201 - First Information Acquisition Module; 202 - First Direction Vector Acquisition Module; 203 - Second Information Acquisition Module; 204 - Second Direction Vector Acquisition Module; 300 - Closest Distance Calculation Module; 400 - First Collision Risk Assessment Module; 500 - Second Collision Risk Assessment Module; 600 - Third Collision Risk Assessment Module. Detailed Implementation

[0079] The technical solutions in the embodiments of this application will now be described with reference to the accompanying drawings.

[0080] It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this application, terms such as "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0081] Example 1

[0082] Please refer to Figure 1 , Figure 1 A flowchart illustrating a trajectory planning evaluation method based on vehicle collision risk, provided for embodiments of this application, is shown. The method includes the following steps:

[0083] Step S100: Obtain the planned trajectory of the autonomous vehicle and the predicted trajectory of the target vehicle;

[0084] The specific methods for generating the planned trajectory of the autonomous vehicle and the predicted trajectory of the target vehicle are not described in detail in this application and can be regarded as prior art.

[0085] Obtain the predicted trajectories of all target vehicles and assign an ID number to each target vehicle.

[0086] Step S200: Traverse all trajectory points of the planned trajectory and obtain the vehicle information corresponding to the current trajectory point and the target vehicle information corresponding to the current trajectory point;

[0087] Step S300: Traverse all target vehicles and calculate the shortest distance between the current vehicle and the current target vehicle at the current trajectory point;

[0088] Step S400: Assess the collision risk between the vehicle and the current target vehicle based on the closest distance;

[0089] Step S500: If all target vehicles have been traversed, assess the collision risk of the vehicle at the current trajectory point;

[0090] Step S600: If all trajectory points have been traversed, assess the collision risk of the vehicle corresponding to the planned trajectory.

[0091] like Figure 2 The diagram shown is a flowchart for obtaining vehicle information. Step S200 may specifically include:

[0092] Step S201: Obtain the motion state information and geometric feature information of the vehicle corresponding to the current trajectory point. The motion state information includes the heading angle α and the position coordinates S. ego =[X ego ,Y ego and velocity V ego The geometric feature information includes the length L of the vehicle body. ego and width Wego ;

[0093] Step S202: Obtain the first direction vector corresponding to the vehicle based on the motion state information.

[0094] The direction vector will be determined based on the position coordinates and the heading angle. Specifically, the position coordinates will be used as the starting point of the vector, and the direction of the vector will be determined based on the heading angle.

[0095] Step S203: Obtain the motion state information and geometric feature information of the target vehicle corresponding to the current trajectory point. The motion state information includes the heading angle β and the position coordinates S. obs =[X obs ,Y obs and velocity V obs The geometric feature information includes the length L of the vehicle body. obs and width W obs ;

[0096] Step S204: Obtain the second direction vector corresponding to the target vehicle based on the motion state information.

[0097] The target vehicle is defined as the vehicle that is closest to the vehicle in the eight directions from the starting point of the vehicle's planned trajectory (note that the number of target vehicles may vary at different times).

[0098] like Figure 3 The diagram shows the target vehicle, with eight directions including: front, rear, left, right, left front, left rear, right front, and right rear.

[0099] Finding the shortest distance between the vehicle and the target vehicle can be transformed into finding the shortest distance between the first direction vector and the second direction vector. Step S300 specifically includes the following steps:

[0100] Step S310: Obtain the direction vector from any point on the first direction vector to any point on the second direction vector. Wherein, any point on the first direction vector and any point on the second direction vector are respectively represented as:

[0101]

[0102]

[0103] Among them, K ego and K obs The scaling factor representing the direction vector;

[0104]

[0105] Step S320: Obtain the projections of the direction vectors onto the first direction vector and the second direction vector respectively:

[0106]

[0107]

[0108] Step S330: Calculate the closest distance between the first direction vector and the second direction vector based on the projection.

[0109] like Figure 4 The diagram shows the flowchart for calculating the shortest distance when the direction vectors are parallel. Step S330 specifically includes the following steps:

[0110] If the first direction vector and the second direction vector are parallel, in this scenario, the traveling vehicle and the target vehicle are traveling in parallel directions, possibly towards each other or in the same direction. Specifically, the following steps are included:

[0111] Step S331: Find the first direction vector Distance from target vehicle S obs The nearest point P1:

[0112] Let P obs For S obs At this time, K obs =0, from S obs Draw a perpendicular line to the line containing the first direction vector, with the foot of the perpendicular at T1. The proportionality coefficient K corresponding to T1 can be calculated. ego P1 can be solved in three cases:

[0113] If K ego >1 indicates that the perpendicular foot T1 is in the first direction vector If the endpoint is ahead, then the nearest point P1 is the first direction vector. The finish line, making K ego =1 gives P1, such as Figure 5 As shown, this is to find the first direction vector. Distance from target vehicle S obs A schematic diagram of the nearest point P1;

[0114] If 0≤K ego ≤1 indicates that the foot of the perpendicular T1 is in the first direction vector If the point is above, then the nearest point P1 is the foot of the perpendicular T1, according to... P1 can be obtained;

[0115] If K ego <0 indicates that the perpendicular foot T1 is in the first direction vector If the point is behind the starting point, then the nearest point P1 is the first direction vector. The starting point, which makes Kego =0 gives P1.

[0116] Step S332: Find the second direction vector The closest point to P1 is P2:

[0117] From P1 to the second direction vector Draw a perpendicular line from the line containing the line, with the foot of the perpendicular at T2. The proportionality coefficient K corresponding to T2 can be calculated. obs P2 can be solved in three cases:

[0118] If K obs >1 indicates that the perpendicular foot T2 is in the second direction vector. If the endpoint is ahead, then the nearest point P2 is the second direction vector. The finish line, making K obs =1 gives P2;

[0119] If 0≤K obs ≤1 indicates that the foot of the perpendicular T2 is in the second direction vector. If the point is above, then the nearest point P2 is the foot of the perpendicular T2, according to... P2 can be obtained;

[0120] If K obs <0 indicates that the perpendicular foot T2 is in the second direction vector. If the point is behind the starting point, then the nearest point P2 is the second direction vector. The starting point, which makes K obs =0 gives P2, such as Figure 6 As shown, this is to find the second direction vector. A schematic diagram of P2, the closest point to P1.

[0121] In summary, if the first direction vector and the second direction vector are parallel, then P1 is the first direction vector. Distance from target vehicle S obs The closest point to P1 is P2, which is the closest point to P1. The distance between P1 and P2 is the closest distance L between the first direction vector and the second direction vector.

[0122] like Figure 7 The diagram shows the flowchart for calculating the closest distance when the direction vectors are not parallel. If the first and second direction vectors are not parallel, there is a certain angle between the driving directions of the vehicle and the target vehicle in this scenario. The specific steps include:

[0123] Step S333: Find the second direction vector Distance from the first direction vector The nearest point P0 on the line:

[0124] First direction vector Second direction vector The lines intersect at point O, satisfying... Based on the projection formula above, the proportionality coefficient K corresponding to the intersection point O can be obtained. obs P0 can be solved in three cases:

[0125] If K obs >1 indicates that the intersection point O is in the second direction vector. If the endpoint is ahead, then the nearest point P0 is the second direction vector. The finish line, making K obs =1 gives P0, such as Figure 8 As shown, in order to find Leave A schematic diagram of the nearest point P0 on the line;

[0126] If 0≤K obs ≤1 indicates that the intersection point O is in the second direction vector. If the points are above, then the nearest point P0 is the intersection point O;

[0127] If K obs <0 indicates that the intersection point O is in the second direction vector. If the point is behind the starting point, then the nearest point P0 is the second direction vector. The starting point, which makes K obs =0, so P0 is obtained.

[0128] Step S334: Based on P0, find the first direction vector. Distance from the second direction vector The nearest point P1:

[0129] From P0 to the first direction vector Draw a perpendicular line from the line containing the line, with the foot of the perpendicular at T1. The proportionality coefficient K corresponding to T1 is calculated. ego P1 can be solved in three cases:

[0130] If K ego >1 indicates that the perpendicular foot T1 is in the first direction vector If the endpoint is ahead, then the nearest point P1 is the first direction vector. The finish line, making K ego =1 gives P1, such as Figure 9 As shown, in order to find Leave A schematic diagram of the nearest point P1;

[0131] If 0≤K ego ≤1 indicates that the foot of the perpendicular T1 is in the first direction vector If the point is above, then the nearest point P1 is the foot of the perpendicular T1, according to... P1 can be obtained;

[0132] If K ego <0 indicates that the perpendicular foot T1 is in the first direction vector If the point is behind the starting point, then the nearest point P1 is the first direction vector. The starting point, which makes K ego =0 gives P1.

[0133] Step S335: Based on P1, find the second direction vector. Distance from the first direction vector The nearest point P2:

[0134] From P1 to the second direction vector Draw a perpendicular line from the line containing the line, with the foot of the perpendicular at T2. The proportionality coefficient K corresponding to T2 can be calculated. obs P2 can be solved in three cases:

[0135] If K obs >1 indicates that the perpendicular foot T2 is in the second direction vector. If the endpoint is ahead, then the nearest point P2 is the second direction vector. The finish line, making K obs =1 gives P2;

[0136] If 0≤K obs ≤1 indicates that the foot of the perpendicular T2 is in the second direction vector. If the point is above, then the nearest point P2 is the foot of the perpendicular T2, according to... P2 can be obtained, such as Figure 10 As shown, in order to find Leave A diagram illustrating the nearest point P2;

[0137] If K obs <0 indicates that the perpendicular foot T2 is in the second direction vector. If the point is behind the starting point, then the nearest point P2 is the second direction vector. The starting point, which makes K obs =0 gives P2.

[0138] In summary, if the first direction vector and the second direction vector are not parallel, then P1 is the first direction vector. Distance from the second direction vector The closest point, P2 is the second direction vector. Distance from the first direction vector The closest point, P1, is the distance between P2 and the first direction vector and the second direction vector.

[0139] The collision risk assessment of the planned trajectory of a vehicle can be divided into three steps: First, during the traversal of the planned trajectory, a collision risk assessment is performed on the vehicle and a single target vehicle at a certain moment. Then, at that moment, a collision risk assessment is performed on the vehicle and all target vehicles. After the traversal of the planned trajectory is completed, a collision risk assessment is finally performed on the entire planned trajectory.

[0140] like Figure 11 The diagram shows the flowchart for calculating the collision risk cost between the vehicle and the target vehicle. Step S400 specifically includes the following steps:

[0141] Step S401: Based on the width of the self-vehicle and the current target vehicle width, set the self-vehicle's safety radius R respectively. ego and the current target vehicle safety radius R obs ;

[0142] The safety radius and vehicle width are correlated; different vehicle widths correspond to different safety radii.

[0143] Step S402: Set the safety radius expansion coefficient C of the current target vehicle based on the vehicle's speed and the current target vehicle's speed. obs (C obs ≥1):

[0144] If the vehicle and the target vehicle are trending towards each other, then

[0145] Where k represents the conversion coefficient, V rel Indicates the relative speed between the vehicle and the target vehicle;

[0146] Since the trajectory of the target vehicle is predicted and its motion state is uncertain, the greater the relative speed, the higher the collision risk caused by the uncertainty. Therefore, the square of the relative speed is taken as the base of the expansion coefficient.

[0147] If the vehicle and the target vehicle are moving away from each other, then C obs =1;

[0148] Step S403: Obtain the expansion safety radius ER of the current target vehicle. obs =C obs *R obs ;

[0149] Step S404: Calculate the collision risk cost E between the self-vehicle and the current target vehicle, E∈[0,1]:

[0150] If L≥R ego +ER obs Then E = 0;

[0151] If R ego +Robs <L<R ego +ER obs ,but

[0152] If L≤R ego +R obs Then E = 1;

[0153] Where L represents the shortest distance between the first direction vector of the vehicle and the second direction vector of the current target vehicle.

[0154] When E=0, it means there is no risk of collision; when E=1, it means a collision is likely; the closer E is to 1, the greater the risk of collision between the vehicle and the target vehicle.

[0155] like Figure 12 The diagram illustrates collision risk calculation. Based on the nearest distance between direction vectors and their associated points, two layers of safety circles are designed with these associated points as centers. The safety radius serves as the basic collision safety threshold, while the expanded safety radius serves as the collision risk calculation threshold. Because the target vehicle's trajectory is predicted, the higher the vehicle speed, the lower the prediction accuracy. Therefore, the expanded safety radius needs to be correlated with the vehicle speed; the expanded safety radius represents the safety margin for avoiding collisions.

[0156] In step S500, the collision risk cost E of the vehicle and each target vehicle is calculated separately. Then, the collision risk of the vehicle at the current trajectory point is the sum of the collision risk costs E of the vehicle and each target vehicle.

[0157] ∑E i =E1+E2+…+E i ;

[0158] Where i represents the ID of the target vehicle at the current trajectory point.

[0159] In step S600, the maximum value of the collision risk of the vehicle under all trajectory points is obtained, and the maximum value is the assessment result of the collision risk of the vehicle corresponding to the planned trajectory.

[0160] This application can be applied not only to the field of vehicle driver assistance but also to the field of autonomous driving. By simplifying the vehicle as a direction vector and acquiring its geometric features and pose information based on visual perception, geometric analysis can be used to more accurately determine the closest distance between the vehicle and the target vehicle.

[0161] Example 2

[0162] This application provides a trajectory evaluation device based on vehicle collision risk, such as... Figure 13The diagram shown is a structural block diagram of a trajectory planning evaluation device based on vehicle collision risk, applied to the method described in Embodiment 1. The device includes, but is not limited to:

[0163] The trajectory acquisition module 100 is used to acquire the planned trajectory of the vehicle and the predicted trajectory of the target vehicle.

[0164] The trajectory point traversal module 200 is used to traverse all trajectory points of the planned trajectory and obtain the vehicle information corresponding to the current trajectory point and the target vehicle information corresponding to the current trajectory point.

[0165] The closest distance calculation module 300 is used to traverse all target vehicles and calculate the closest distance between the current vehicle and the current target vehicle at the current trajectory point;

[0166] The first collision risk assessment module 400 is used to assess the collision risk between the vehicle and the current target vehicle based on the closest distance.

[0167] The second collision risk assessment module 500 is used to assess the collision risk of the vehicle at the current trajectory point if all target vehicles have been traversed.

[0168] The third collision risk assessment module 600 is used to assess the collision risk of the vehicle corresponding to the planned trajectory if all trajectory points have been traversed.

[0169] Among them, such as Figure 14 The diagram shown is a structural block diagram of another trajectory planning evaluation device based on vehicle collision risk. The trajectory point traversal module 200 includes:

[0170] The first information acquisition module 201 is used to acquire the motion state information and geometric feature information of the vehicle corresponding to the current trajectory point. The motion state information includes the heading angle α and the position coordinates S. ego =[X ego ,Y ego and velocity V ego The geometric feature information includes the length L of the vehicle body. ego ;

[0171] The first direction vector acquisition module 202 is used to acquire the first direction vector corresponding to the vehicle based on the motion state information.

[0172] The second information acquisition module 203 is used to acquire the motion state information and geometric feature information of the target vehicle corresponding to the current trajectory point. The motion state information includes the heading angle β and the position coordinate S. obs =[X obs ,Y obs and velocity V obs The geometric feature information includes the length L of the vehicle body.obs ;

[0173] The second direction vector acquisition module 204 is used to acquire the second direction vector corresponding to the target vehicle based on the motion state information.

[0174] The specific implementation process has been described in detail in Example 1, and will not be repeated here.

[0175] This application also provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor runs the computer program to enable the electronic device to perform the vehicle collision risk-based trajectory evaluation method described in Embodiment 1.

[0176] This application also provides a readable storage medium storing computer program instructions. When the computer program instructions are read and executed by a processor, the planning trajectory evaluation method based on vehicle collision risk described in Embodiment 1 is performed.

[0177] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can also be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram and / or flowchart, and combinations of blocks in block 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.

[0178] In addition, the functional modules in the various embodiments of this application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0179] If the aforementioned functions are implemented as software functional modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0180] The above description is merely an embodiment of this application and is not intended to limit the scope of protection of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application. It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0181] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0182] It should be noted that, in this document, 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.

Claims

1. A method for evaluating planned trajectories based on vehicle collision risk, characterized in that, The method includes: Obtain the planned trajectory of the autonomous vehicle and the predicted trajectory of the target vehicle; Traverse all trajectory points of the planned trajectory and obtain the vehicle information and target vehicle information corresponding to the current trajectory point. Specifically, this includes obtaining the motion state information and geometric feature information of the vehicle corresponding to the current trajectory point, wherein the motion state information includes the heading angle. Location coordinates and speed The geometric feature information includes the length of the vehicle body. Based on the motion state information, obtain the first direction vector corresponding to the vehicle. ; Obtain the motion state information and geometric feature information of the target vehicle corresponding to the current trajectory point, wherein the motion state information includes the heading angle. Location coordinates and speed The geometric feature information includes the length of the vehicle body. Based on the motion state information, obtain the second direction vector corresponding to the target vehicle. ; Iterate through all target vehicles and calculate the shortest distance between your vehicle and the current target vehicle at the current trajectory point. Specifically, this includes: if the first direction vector and the second direction vector are parallel, obtain the first direction vector. Distance from target vehicle Find the nearest point P1; obtain the second direction vector. The closest point to P1 is P2, and the distance between P1 and P2 is the shortest distance between the first direction vector and the second direction vector. If the first direction vector and the second direction vector are not parallel, the intersection point of the lines containing the first direction vector and the second direction vector is obtained, and the second direction vector is obtained based on the intersection point. Distance from the first direction vector Find the nearest point P0 on the line; based on P0, obtain the first direction vector. Distance from the second direction vector Find the nearest point P1; based on P1, obtain the second direction vector. Distance from the first direction vector The nearest point P2, the distance between P1 and P2 is the closest distance between the first direction vector and the second direction vector; The collision risk between the vehicle and the current target vehicle is assessed based on the closest distance. If all target vehicles have been traversed, assess the collision risk of the vehicle at the current trajectory point; If all trajectory points have been traversed, then assess the collision risk of the vehicle corresponding to the planned trajectory.

2. The method for evaluating planned trajectories based on vehicle collision risk according to claim 1, characterized in that, Geometric feature information also includes the width of the vehicle body. and the width of the target vehicle's body. The assessment of the collision risk between the vehicle and the current target vehicle based on the closest distance includes: Set the vehicle's safety radius based on the vehicle's width and the current target vehicle's width. and the current target vehicle's safe radius ; The safety radius expansion coefficient of the current target vehicle is set based on the vehicle's own speed and the current target vehicle's speed. : If the vehicle and the target vehicle are trending towards each other, then ; in, k Indicates the conversion factor. Indicates the relative speed between the vehicle and the target vehicle; If the vehicle and the target vehicle are moving away from each other, then ; Obtain the expansion safety radius of the current target vehicle. ; Calculate the collision risk cost between the vehicle and the target vehicle. E , : like ,but E =0; like ,but ; like ,but E =1; in, L This represents the shortest distance between the first direction vector of the vehicle and the second direction vector of the current target vehicle.

3. The method for evaluating planned trajectories based on vehicle collision risk according to claim 1, characterized in that, If all target vehicles have been traversed, the collision risk of the vehicle at the current trajectory point is assessed, including: Calculate the collision risk cost for the vehicle and each target vehicle separately. E Then, the collision risk of the vehicle at the current trajectory point is the collision risk cost between the vehicle and each target vehicle. E The sum: ； in, i This indicates the ID of the target vehicle at the current trajectory point.

4. The method for evaluating planned trajectories based on vehicle collision risk according to claim 3, characterized in that, If all trajectory points have been traversed, the collision risk of the vehicle corresponding to the planned trajectory is assessed, including: Obtain the maximum value of the collision risk of the vehicle under all trajectory points. The maximum value is the assessment result of the collision risk of the vehicle corresponding to the planned trajectory.

5. A trajectory planning evaluation device based on vehicle collision risk, characterized in that, The device includes: The trajectory acquisition module is used to acquire the planned trajectory of the self-driving vehicle and the predicted trajectory of the target vehicle; The trajectory point traversal module is used to traverse all trajectory points of the planned trajectory and obtain the vehicle information and target vehicle information corresponding to the current trajectory point. Specifically, the trajectory point traversal module includes: a first information acquisition module, used to acquire the motion state information and geometric feature information of the vehicle corresponding to the current trajectory point, wherein the motion state information includes the heading angle. Location coordinates and speed The geometric feature information includes the length of the vehicle body. The first direction vector acquisition module is used to acquire the first direction vector corresponding to the vehicle based on the motion state information. The second information acquisition module is used to acquire the motion state information and geometric feature information of the target vehicle corresponding to the current trajectory point, wherein the motion state information includes the heading angle. Location coordinates and speed The geometric feature information includes the length of the vehicle body. The second direction vector acquisition module is used to acquire the second direction vector corresponding to the target vehicle based on the motion state information. ; The closest distance calculation module is used to traverse all target vehicles and calculate the closest distance between the current vehicle and the current target vehicle at the current trajectory point. Specifically, it includes: if the first direction vector and the second direction vector are parallel, obtaining the first direction vector. Distance from target vehicle Find the nearest point P1; obtain the second direction vector. The closest point to P1 is P2, and the distance between P1 and P2 is the shortest distance between the first direction vector and the second direction vector. If the first direction vector and the second direction vector are not parallel, the intersection point of the lines containing the first direction vector and the second direction vector is obtained, and the second direction vector is obtained based on the intersection point. Distance from the first direction vector Find the nearest point P0 on the line; based on P0, obtain the first direction vector. Distance from the second direction vector Find the nearest point P1; based on P1, obtain the second direction vector. Distance from the first direction vector The nearest point P2, the distance between P1 and P2 is the closest distance between the first direction vector and the second direction vector; The first collision risk assessment module is used to assess the collision risk between the vehicle and the current target vehicle based on the closest distance. The second collision risk assessment module is used to assess the collision risk of the vehicle at the current trajectory point if all target vehicles have been traversed. The third collision risk assessment module is used to assess the collision risk of the vehicle corresponding to the planned trajectory if all trajectory points have been traversed.

6. An electronic device, characterized in that, The electronic device includes a memory and a processor, the memory being used to store a computer program, and the processor running the computer program to cause the electronic device to perform the vehicle collision risk-based trajectory evaluation method according to any one of claims 1 to 4.

7. A readable storage medium, characterized in that, The readable storage medium stores computer program instructions, which are read and executed by a processor to perform the vehicle collision risk-based trajectory evaluation method according to any one of claims 1 to 4.

Images