Vehicle travel control method and electronic device

Abstract

The application provides a vehicle driving control method and an electronic device. The method comprises the following steps: obtaining target motion information comprising first motion information of a target vehicle, second motion information of a target object, and third motion information between the target object and the target vehicle; determining a first collision identification result according to the target motion information and a collision identification condition; determining first collision risk information according to the target motion information, and then determining a second collision identification result; in the case that it is determined that there is a collision risk according to the first collision identification result and the second collision identification result, determining historical collision indication information and current collision indication information, and determining target collision indication information according to the historical collision indication information and the current collision indication information; and controlling a driving state of the target vehicle according to the target collision indication information and the third motion information. Based on twice collision identification, a more accurate collision identification result can be obtained, and the collision risk can be better reduced or the collision can be avoided.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicle control, in particular to a vehicle driving control method and an electronic device. BACKGROUND

[0002] With the development of vehicle electrification and intelligence, driving safety of vehicles attracts widespread attention. For example, during vehicle driving, a driver needs to pay attention to road conditions at all times to determine whether a target object such as a vehicle or a pedestrian on a neighboring lane moves to the lane of the ego vehicle, and when the above behavior occurs, the driver needs to determine whether the ego vehicle brakes based on driving experience to avoid a collision with a preceding vehicle.

[0003] However, behaviors such as lane changing of a vehicle on a neighboring lane and sudden crossing of a pedestrian may occur in a very short time, and the driver needs to respond in a very short time. If the response is not timely, the ego vehicle may not slow down in time, which may result in a collision risk. Therefore, how to accurately identify the collision risk between the ego vehicle and other vehicles, pedestrians and target objects, obtain an accurate collision identification result, and then control the vehicle to brake or perform other processing according to the collision identification result to reduce the collision risk or avoid a collision is a main research direction in the field of safe driving of vehicles. SUMMARY

[0004] The embodiments of the present application provide a vehicle driving control method and an electronic device, which can obtain a more accurate collision identification result, and dynamically control the driving state of a target vehicle according to target collision indication information and third motion information, so that the driving control of the target vehicle is more in line with actual control needs, which can reduce the collision risk or avoid a collision, thereby improving the driving safety of the vehicle.

[0005] To solve the above technical problem, in a first aspect, the embodiments of the present application provide a vehicle driving control method, which comprises: obtaining target motion information, the target motion information comprising first motion information of a target vehicle, second motion information of a target object, and third motion information between the target object and the target vehicle; determining a first collision identification result between the target object and the target vehicle according to the target motion information and a collision identification condition; determining first collision risk information between the target object and the target vehicle according to the target motion information, and determining a second collision identification result between the target object and the target vehicle according to the first collision risk information; in a case where it is determined that there is a collision risk between the target object and the target vehicle according to the first collision identification result and the second collision identification result, determining historical collision indication information and current collision indication information between the target object and the target vehicle, and determining target collision indication information according to the historical collision indication information and the current collision indication information; and controlling a driving state of the target vehicle according to the target collision indication information and the third motion information.

[0006] According to the technical solution, the first collision identification result is obtained by directly judging the conditions according to the target motion information and the collision identification conditions, the first collision risk information is determined according to the target motion information, the second collision identification result is determined according to the first collision risk information, in the case where it is determined that there is a collision risk between the target object and the target vehicle according to the first collision identification result and the second collision identification result, the historical collision indication information and the current collision indication information between the target object and the target vehicle are determined, and the target collision indication information is determined according to the historical collision indication information and the current collision indication information. In this way, the motion information of the target vehicle, the motion information of the target object and the motion information between the target object and the target vehicle are comprehensively considered, two collision identifications are performed, and a more accurate collision identification result is obtained. Further, the historical collision indication information is taken as a reference, and the more accurate target collision indication information is obtained by combining the historical collision indication information and the current collision indication information, so that the collision identification is more accurate, the vehicle driving control is more accurate, and according to the target collision indication information and the third motion information, the driving state of the target vehicle can be dynamically controlled, so that the driving control of the target vehicle is more in line with the actual control demand, the collision risk can be reduced or the collision can be avoided, thereby improving the vehicle driving safety and further improving the user driving experience.

[0007] In a possible implementation of the first aspect, according to the target motion information, the first collision risk information between the target object and the target vehicle is determined, including: according to the first motion information and the second motion information, trajectory intersection risk information between the target object and the target vehicle is determined; and according to the second motion information, lateral speed risk information and lateral acceleration risk information between the target object and the target vehicle are determined; and according to the third motion information, collision time risk information, lateral distance risk information and lane deviation risk information between the target object and the target vehicle are determined; and according to the trajectory intersection risk information, the lateral speed risk information, the lateral acceleration risk information, the collision time risk information, the lateral distance risk information and the lane deviation risk information, the first collision risk information is determined.

[0008] According to the technical solution, the more accurate collision risk information is obtained based on the trajectory intersection, the lateral speed, the lateral acceleration, the collision time, the lateral distance and the lane deviation risk information.

[0009] In a possible implementation of the first aspect, the first motion information of the target vehicle includes first trajectory prediction information of the target vehicle, the second motion information of the target object includes second trajectory prediction information of the target object, and the determining of the trajectory intersection risk information between the target object and the target vehicle according to the first motion information and the second motion information includes: determining whether there is a trajectory intersection point between the target object and the target vehicle according to the first trajectory prediction information of the target vehicle and the second trajectory prediction information of the target object; if there is no trajectory intersection point, determining that the trajectory intersection risk information is zero; and if there is a trajectory intersection point, determining a time difference between a time when the target vehicle reaches the trajectory intersection point and a time when the target object reaches the trajectory intersection point, and determining the trajectory intersection risk information according to the time difference.

[0010] By means of the technical solution, the trajectory prediction information of the target vehicle and the target object is considered, the trajectory intersection risk information is determined according to the time difference between the time when the target vehicle reaches the trajectory intersection point and the time when the target object reaches the trajectory intersection point, the trajectory intersection risk of the target object and the target vehicle is considered, and a more accurate collision recognition result is obtained.

[0011] In a possible implementation of the first aspect, the second motion information of the target object further includes lateral velocity information of the target object and lateral acceleration information of the target object, and the determining of the lateral velocity risk information and the lateral acceleration risk information between the target object and the target vehicle according to the second motion information includes: determining a lateral velocity sensitive coefficient according to the lateral velocity information of the target object, and determining the lateral velocity risk information according to the lateral velocity information and the lateral velocity sensitive coefficient; and determining a lateral acceleration sensitive coefficient according to the lateral acceleration information of the target object, and determining the lateral acceleration risk information according to the lateral acceleration information and the lateral acceleration sensitive coefficient.

[0012] By means of the technical solution, the lateral velocity sensitive coefficient is dynamically determined according to the lateral velocity information of the target object, and more accurate lateral velocity risk information is obtained according to the lateral velocity information and the lateral velocity sensitive coefficient. The lateral acceleration sensitive coefficient is determined according to the lateral acceleration information of the target object, and more accurate lateral acceleration risk information is obtained according to the lateral acceleration information and the lateral acceleration sensitive coefficient.

[0013] In a possible implementation of the first aspect, the third motion information includes a collision time between the target object and the target vehicle, lateral relative distance information between the target object and the target vehicle, and lateral distance information between the target object and lane lines of a lane in which the target vehicle is located, and the collision time risk information, the lateral distance risk information, and the lane deviation risk information between the target object and the target vehicle are determined according to the third motion information, including: determining a collision time sensitivity coefficient according to the collision time, and determining the collision time risk information according to the collision time and the collision time sensitivity coefficient; determining a lateral distance sensitivity coefficient according to the lateral relative distance information between the target object and the target vehicle, and determining the lateral distance risk information according to the lateral distance information of the target object relative to the target vehicle and the lateral distance sensitivity coefficient; and determining the lane deviation risk information according to the lateral distance information between the target object and the lane lines of the lane in which the target vehicle is located.

[0014] According to the above technical solution, the collision time sensitivity coefficient is determined according to the collision time, and more accurate collision time risk information is obtained according to the collision time and the collision time sensitivity coefficient. The lateral distance sensitivity coefficient is determined according to the lateral relative distance information between the target object and the target vehicle, and more accurate lateral distance risk information is obtained according to the lateral distance information of the target object relative to the target vehicle and the lateral distance sensitivity coefficient. In this way, the lane deviation risk information is obtained by considering the lateral distance information between the target object and the lane lines of the lane in which the target vehicle is located, so as to obtain the second collision identification result considering multiple collision influencing factors.

[0015] In a possible implementation of the first aspect, the method further includes: determining a weight coefficient corresponding to each of the trajectory intersection risk information, the lateral speed risk information, the lateral acceleration risk information, the collision time risk information, the lateral distance risk information, and the lane deviation risk information according to the target motion information; and determining the first collision risk information according to the trajectory intersection risk information, the lateral speed risk information, the lateral acceleration risk information, the collision time risk information, the lateral distance risk information, and the lane deviation risk information, including: determining the first collision risk information according to the trajectory intersection risk information, the lateral speed risk information, the lateral acceleration risk information, the collision time risk information, the lateral distance risk information, the lane deviation risk information, and the weight coefficients corresponding thereto.

[0016] According to the above technical solution, the weight coefficients corresponding to the trajectory intersection risk information, the lateral speed risk information, the lateral acceleration risk information, the collision time risk information, the lateral distance risk information, and the lane deviation risk information are determined according to the target motion information, so that the weight coefficients can be dynamically adjusted according to the current driving condition, and more accurate first collision risk information is obtained.

[0017] In a possible implementation of the first aspect, the first collision risk information is a first collision risk value, the historical collision indication information and the current collision indication information between the target object and the target vehicle are determined, and the target collision indication information is determined according to the historical collision indication information and the current collision indication information, including: determining the current collision indication information between the target object and the target vehicle according to the lateral speed information of the target object, the relative lateral distance information between the target object and the target vehicle, and the first collision risk value; and determining the historical collision indication information, a first weight coefficient corresponding to the historical collision indication information, and a second weight coefficient corresponding to the current collision indication information; obtaining the target collision indication information according to the first weight coefficient, the historical collision indication information, the second weight coefficient, and the current collision indication information.

[0018] By adopting the above technical solution, the historical collision indication information is considered, the target collision indication information is obtained according to the first weight coefficient, the historical collision indication information, the second weight coefficient, and the current collision indication information, so that the target collision indication information considering the historical collision indication information between the target vehicle and the target object can be obtained, and the collision trend of the target object and the target vehicle can be better reflected.

[0019] In a possible implementation of the first aspect, the third motion information further includes lateral relative speed information between the target object and the target vehicle, and the driving state of the target vehicle is controlled according to the target collision indication information and the third motion information, including: in a case where it is determined that the target collision indication information meets the collision indication condition, determining lateral distance parameter information according to the lateral relative distance information between the target object and the target vehicle, determining lateral speed parameter information according to the lateral relative speed information between the target object and the target vehicle, and determining collision time parameter information according to the collision time; determining a lateral distance weight coefficient according to the lateral distance parameter information, determining a lateral speed weight coefficient according to the lateral speed parameter information, and determining a collision time weight coefficient according to the collision time parameter information; determining second collision risk information according to the lateral distance weight coefficient, the lateral distance, the lateral speed weight coefficient, the lateral speed, the collision time weight coefficient, and the collision time; determining a first acceleration according to the second collision risk information; and controlling the driving state of the target vehicle according to the first acceleration.

[0020] By adopting the above technical solution, the parameters and weight coefficients of the control information used for controlling the driving state of the target vehicle are determined according to the target motion information, the first acceleration is obtained, so that the driving state of the target vehicle is controlled according to the first acceleration, and better collision avoidance control effect is achieved.

[0021] In a possible implementation of the first aspect, the third motion information further includes time-to-collision information between the target object and the target vehicle, and the method further includes: determining the collision indication condition by: determining a collision time threshold according to the time-to-collision information and the longitudinal speed information of the target vehicle; and determining a preset lateral relative distance threshold; determining the collision indication condition according to the collision time, the collision time threshold, the lateral relative distance, and the lateral relative distance threshold; and controlling the driving state of the target vehicle according to the first acceleration, including: determining a second acceleration based on a model predictive control method; and controlling the driving state of the target vehicle according to the first acceleration and the second acceleration.

[0022] According to the technical solution, the collision time threshold is determined according to the time-to-collision information and the longitudinal speed information of the vehicle and the target object, the lateral relative distance threshold is determined, and the collision indication condition is determined according to the collision time, the collision time threshold, the lateral relative distance, and the lateral relative distance threshold, so that the collision risk can be determined according to the current state of the target object and the target vehicle, a more accurate collision risk result is obtained, and the user's driving experience is improved.

[0023] In the second aspect, the implementation manner of the present application further discloses a vehicle for implementing the vehicle driving control method provided by any one of the implementation manners of the first aspect.

[0024] In the third aspect, the implementation manner of the present application further discloses an electronic device, including a processor and a memory connected with the processor in communication; the memory stores computer execution instructions; and the processor executes the computer execution instructions stored in the memory, so that the electronic device implements the vehicle driving control method provided by any one of the implementation manners of the first aspect.

[0025] In the fourth aspect, the implementation manner of the present application further discloses a computer readable storage medium, which stores a computer program, and the computer program can be executed by an electronic device to implement the vehicle driving control method provided by any one of the implementation manners of the first aspect.

[0026] In the fifth aspect, the implementation manner of the present application further discloses a computer program product, including a computer program, and the computer program is executed by an electronic device to implement the vehicle driving control method provided by any one of the implementation manners of the first aspect. BRIEF DESCRIPTION OF DRAWINGS

[0027] In order to more clearly illustrate the technical solutions of the present application, the drawings used in the implementation manner description will be briefly introduced.

[0028] Figure 1 FIG. 1 is a flowchart of a vehicle driving control method provided by an embodiment of the present application;

[0029] Figure 2A flowchart for determining the first collision risk information according to an embodiment of the present application is provided;

[0030] Figure 3 A schematic diagram of the relationship between the time difference and the trajectory intersection risk information according to an embodiment of the present application is provided;

[0031] Figure 4 A schematic diagram of the relationship between the lateral speed information and the lateral speed risk information according to an embodiment of the present application is provided;

[0032] Figure 5 A schematic diagram of the relationship between the lateral acceleration information and the lateral acceleration risk information according to an embodiment of the present application is provided;

[0033] Figure 6 A schematic diagram of the relationship between the collision time and the collision time risk information according to an embodiment of the present application is provided;

[0034] Figure 7 A schematic diagram of the relationship between the lateral relative distance information and the lateral distance risk information according to an embodiment of the present application is provided;

[0035] Figure 8 A schematic diagram of the relationship between the lateral distance information and the lane departure risk information according to an embodiment of the present application is provided;

[0036] Figure 9 A flowchart for determining the target collision indication information according to an embodiment of the present application is provided;

[0037] Figure 10 A flowchart for determining the control information for controlling the driving state of the target vehicle according to an embodiment of the present application is provided;

[0038] Figure 11 A schematic diagram of the relationship between the lateral relative distance information and the lateral distance parameter information according to an embodiment of the present application is provided;

[0039] Figure 12 A schematic diagram of the relationship between the lateral relative speed information and the lateral speed parameter information according to an embodiment of the present application is provided;

[0040] Figure 13 A schematic diagram of the relationship between the collision time and the collision time parameter information according to an embodiment of the present application is provided;

[0041] Figure 14 Another flowchart of the vehicle driving control method according to an embodiment of the present application is provided. DETAILED DESCRIPTION

[0042] How to accurately identify the collision risk between the ego vehicle and other target objects such as vehicles, pedestrians, etc., obtain accurate collision identification results, and then control the vehicle to brake or take other actions according to the collision identification results to reduce the collision risk or avoid collision is the main research direction in the field of safe driving of vehicles.

[0043] For example, when there are target objects such as overtaking vehicles, lane-changing vehicles, pedestrians, etc. in the left front, left front front, right front, and right front front of the target vehicle during assisted driving, it is necessary to predict whether a collision will occur between the target vehicle and the target object, so as to perform pre-control such as pre-braking or pre-acceleration of the target vehicle to avoid collision and achieve safe driving of the vehicle. Of course, when there are vehicles braking in front of the target vehicle, it is also necessary to predict whether a rear-end collision or other collision will occur between the target vehicle and the target object, so as to perform pre-braking of the target vehicle to avoid collision and achieve safe driving of the vehicle.

[0044] Of course, when there are vehicles braking in front of the target vehicle, it is also necessary to predict whether a rear-end collision or other collision will occur between the target vehicle and the target object, so as to perform pre-braking of the target vehicle to avoid collision and achieve safe driving of the vehicle.

[0045] Based on this, the present application provides a vehicle driving control method, which obtains first motion information of a target vehicle, second motion information of a target object, and third motion information between the target object and the target vehicle, determines a first collision identification result between the target object and the target vehicle according to the target motion information and a collision identification condition, determines first collision risk information according to the target motion information, determines a second collision identification result between the target object and the target vehicle according to the first collision risk information, determines historical collision indication information and current collision indication information between the target object and the target vehicle in the case where it is determined that there is a collision risk between the target object and the target vehicle according to the first collision identification result and the second collision identification result, and determines target collision indication information according to the historical collision indication information and the current collision indication information; and controls the driving state of the target vehicle according to the target collision indication information and the third motion information. In this way, through two collision identifications, more accurate collision identification results can be obtained, and the collision risk information determined according to the target motion information can better identify the intrusion trend of the target object, so as to make an early prediction of the collision between the target object and the target vehicle. Furthermore, the target collision indication information obtained by combining the historical collision indication information and the current collision indication information makes the collision identification more accurate, and the driving state of the target vehicle can be dynamically controlled according to the target collision indication information and the third motion information, so that the driving control of the target vehicle is more in line with the actual control requirements, the driving safety of the vehicle is improved, and the user driving experience is further improved.

[0046] Next, the vehicle driving control method provided by the present application will be described in detail.

[0047] Reference should be made to Figure 1The vehicle driving control method provided in the application comprises the following steps.

[0048] S100, target motion information is acquired, the target motion information comprising first motion information of a target vehicle, second motion information of a target object, and third motion information between the target object and the target vehicle.

[0049] S200, according to the target motion information and a collision identification condition, a first collision identification result between the target object and the target vehicle is determined.

[0050] S300, according to the target motion information, first collision risk information between the target object and the target vehicle is determined, and according to the first collision risk information, a second collision identification result between the target object and the target vehicle is determined.

[0051] S400, in the case where it is determined according to the first collision identification result and the second collision identification result that there is a collision risk between the target object and the target vehicle, historical collision indication information and current collision indication information between the target object and the target vehicle are determined, and according to the historical collision indication information and the current collision indication information, target collision indication information is determined.

[0052] S500, according to the target collision indication information and the third motion information, a driving state of the target vehicle is controlled.

[0053] The vehicle driving control method provided in the implementation of the application directly determines a condition according to target motion information and a collision identification condition to obtain a first collision identification result, determines first collision risk information according to the target motion information, determines a second collision identification result according to the first collision risk information, in the case where it is determined according to the first collision identification result and the second collision identification result that there is a collision risk between the target object and the target vehicle, historical collision indication information and current collision indication information between the target object and the target vehicle are determined, and target collision indication information is determined according to the historical collision indication information and the current collision indication information. In this way, the motion information of the target vehicle, the motion information of the target object, and the motion information between the target object and the target vehicle are comprehensively considered, two collision recognitions are performed, and a more accurate collision identification result is obtained. Further, the historical collision indication information is taken as a reference, and more accurate target collision indication information is obtained by combining the historical collision indication information and the current collision indication information, so that the collision recognition is more accurate, the vehicle driving control is more accurate, and according to the target collision indication information and the third motion information, the driving state of the target vehicle can be dynamically controlled, so that the driving control of the target vehicle is more in line with actual control requirements, the vehicle driving safety is improved, and the user driving experience is further improved.

[0054] It should be noted that steps S200 and S300 can be executed simultaneously, or step S200 can be executed first, and then step S300 can be executed, or step S300 can be executed first, and then step S200 can be executed.

[0055] For step S100, target motion information is acquired, the target motion information including first motion information of a target vehicle, second motion information of a target object, and third motion information between the target object and the target vehicle.

[0056] In an implementation manner of the present application, the first motion information of the target vehicle includes longitudinal vehicle speed information, lateral vehicle speed information of the target vehicle, and first trajectory prediction information of the target vehicle.

[0057] The longitudinal vehicle speed information and the lateral vehicle speed information of the target vehicle are obtained based on a speed sensor of the target vehicle.

[0058] The first trajectory prediction information of the target vehicle is generated based on current state information such as position information and vehicle speed information of the target vehicle and a trajectory planning algorithm.

[0059] The second motion information of the target object includes second trajectory prediction information of the target object, longitudinal speed information of the target object, lateral speed information of the target object, and lateral acceleration information of the target object.

[0060] For example, the target vehicle acquires road perception information, and identifies the target object and the longitudinal speed information, the lateral speed information, and the lateral acceleration information of the target object according to the road perception information.

[0061] The road perception information can be a perception image captured by a camera device of the target vehicle, and of course can also be point cloud information of the target object detected by a radar device.

[0062] Further, the second trajectory prediction information of the target object is generated based on a trajectory prediction model or a machine learning method according to the second motion information of the target object.

[0063] The third motion information between the target vehicle and the target object includes longitudinal relative distance information between the target object and the target vehicle, lateral relative distance information between the target object and the target vehicle, lateral distance information between the target object and a lane line of a lane where the target object is located relative to the target vehicle, and lateral relative speed information between the target object and the target vehicle.

[0064] For example, the first coordinate information of the target vehicle and the second coordinate information of the target object are acquired, and the longitudinal relative distance information between the target object and the target vehicle is obtained according to the longitudinal coordinate value of the first coordinate information of the target vehicle and the longitudinal coordinate value of the second coordinate information of the target object. For example, the longitudinal relative distance information between the target object and the target vehicle is obtained by difference calculation.

[0065] Further, the first coordinate information of the target vehicle and the second coordinate information of the target object are acquired, and the lateral relative distance information between the target object and the target vehicle is obtained according to the lateral coordinate value of the first coordinate information of the target vehicle and the lateral coordinate value of the second coordinate information of the target object. For example, the lateral relative distance information between the target object and the target vehicle is obtained by difference calculation.

[0066] Further, the lateral distance information between the target object and the lane line of the lane where the target vehicle is located can be obtained by measuring the vertical distance between the target object and the lane line of the lane where the target vehicle is located.

[0067] Of course, the lateral distance information between the target object and the lane line of the lane where the target vehicle is located can also be obtained according to the second coordinate information of the target object and the third coordinate information of a certain point of the lane line of the lane where the target vehicle is located.

[0068] It should be noted that if the lane line is not clearly marked on the road, a virtual lane line can be drawn according to the driving position of the target vehicle and the road surface condition to obtain the lane line of the lane where the target vehicle is located.

[0069] Further, the lateral relative speed information of the target object relative to the target vehicle is obtained as the lateral relative speed information between the target object and the target vehicle, taking the target vehicle as a stationary reference.

[0070] The lateral relative speed information of the target vehicle relative to the target object can also be obtained as the lateral relative speed information between the target object and the target vehicle, taking the target object as a stationary reference.

[0071] Of course, the lateral relative speed information between the target object and the target vehicle can also be obtained according to the difference between the lateral speed information of the target object and the lateral speed information of the target vehicle.

[0072] Further, the third motion information between the target vehicle and the target object further includes the time to collision (TTC) between the target object and the target vehicle and the time headway (THW) information between the target object and the target vehicle.

[0073] In an implementation form of the application, the collision time between the target object and the target vehicle is obtained by:

[0074] Based on the above, the longitudinal speed information of the target vehicle, the longitudinal speed information of the target object, and the longitudinal relative distance information between the target object and the target vehicle are determined.

[0075] According to the longitudinal speed information of the target vehicle and the longitudinal speed information of the target object, the longitudinal relative speed information between the target vehicle and the target object is determined.

[0076] According to the longitudinal relative speed information and the longitudinal relative distance information between the target object and the target vehicle, the collision time between the target object and the target vehicle is determined.

[0077] The collision time is obtained by:

[0078]

[0079] wherein, the collision time, the longitudinal speed information of the target vehicle, the longitudinal speed information of the target object, the longitudinal relative distance information between the target object and the target vehicle.

[0080] Further, the time-headway information between the target object and the target vehicle is obtained by:

[0081] According to the longitudinal speed information of the target vehicle and the longitudinal relative distance information between the target object and the target vehicle, the time-headway information between the target object and the target vehicle is determined.

[0082] The time-headway information is obtained by:

[0083]

[0084] wherein, the time-headway information, the longitudinal relative distance information between the target object and the target vehicle, the longitudinal speed information of the target vehicle.

[0085] For step S200, according to the target motion information and the collision recognition condition, a first collision recognition result between the target object and the target vehicle is determined.

[0086] In an implementation manner of the implementation manners of the present application, the first collision identification result between the target object and the target vehicle is determined according to the target motion information and the collision identification condition, including determining the first collision identification result between the target object and the target vehicle according to the first motion information of the target vehicle and the first collision identification condition (as an example of the target collision identification condition).

[0087] For example, if it is determined that the target vehicle is still in an accelerating state according to the longitudinal velocity information of the target vehicle in multiple (for example, 20 continuous frames), it is determined that the first collision identification result between the target object and the target vehicle is that there is a collision risk, and if it is determined that the target vehicle is in a decelerating state and the longitudinal velocity is less than a preset longitudinal velocity threshold, the first collision identification result between the target object and the target vehicle is that there is no collision risk.

[0088] In another implementation manner of the implementation manners of the present application, the first collision identification result between the target object and the target vehicle is determined according to the target motion information and the collision identification condition, including determining the first collision identification result between the target object and the target vehicle according to the second motion information of the target object and the second collision identification condition (as another example of the target collision identification condition).

[0089] For example, the mean velocity and the velocity variance of the target object are determined according to the lateral velocity information of the target object in multiple (for example, 20 continuous frames);

[0090] The first collision identification result between the target object and the target vehicle is determined according to the mean velocity, the velocity variance and the collision identification condition.

[0091] For example, if it is determined that the mean velocity of 5 continuous frames to 10 continuous frames is greater than a mean velocity threshold (for example, 0.3 m / s), it is determined that there is a clear invading direction velocity, if it is determined that the velocity variance of 5 continuous frames to 10 continuous frames is less than a variance threshold (for example, 0.05 m² / s²), it is determined that the invading action is stable and is not random fluctuation, then it is determined that the first collision identification result between the target object and the target vehicle is that there is a collision risk, and if it is determined that the mean velocity is less than or equal to the mean velocity threshold, or the velocity variance is greater than the variance threshold, it is determined that the first collision identification result between the target object and the target vehicle is that there is no collision risk.

[0092] In another implementation manner of the implementation manners of the present application, the first collision identification result between the target object and the target vehicle is determined according to the target motion information and the collision identification condition, including determining the first collision identification result between the target object and the target vehicle according to the first motion information of the target vehicle, the second motion information of the target object, the third motion information between the target object and the target vehicle and the third collision identification condition (as another example of the target collision identification condition).

[0093] For example, if it is determined according to the first trajectory prediction information of the target vehicle and the second trajectory prediction information of the target object that there is a trajectory intersection point between the target vehicle and the target object, it is determined that the first collision identification result between the target object and the target vehicle is that there is a collision risk, and if there is no trajectory intersection point, it is determined that the first collision identification result between the target object and the target vehicle is that there is no collision risk.

[0094] If it is determined that the collision time between the target vehicle and the target object is less than the collision time threshold, it is determined that the first collision identification result between the target object and the target vehicle is that there is a collision risk, and if it is greater than or equal to the collision time threshold, it is determined that the first collision identification result between the target object and the target vehicle is that there is no collision risk.

[0095] If it is determined that the time headway between the target vehicle and the target object is less than the time difference threshold, it is determined that the first collision identification result between the target object and the target vehicle is that there is a collision risk, and if it is greater than or equal to the time difference threshold, it is determined that the first collision identification result between the target object and the target vehicle is that there is no collision risk.

[0096] If it is determined that the longitudinal relative distance information between the target vehicle and the target object is less than the longitudinal distance threshold, it is determined that the first collision identification result between the target object and the target vehicle is that there is a collision risk, and if it is greater than or equal to the longitudinal distance threshold, it is determined that the first collision identification result between the target object and the target vehicle is that there is no collision risk.

[0097] If it is determined that the lateral relative distance information between the target vehicle and the target object is less than the longitudinal distance threshold, it is determined that the first collision identification result between the target object and the target vehicle is that there is a collision risk, and if it is greater than or equal to the longitudinal distance threshold, it is determined that the first collision identification result between the target object and the target vehicle is that there is no collision risk.

[0098] If it is determined that the longitudinal relative speed information between the target vehicle and the target object is greater than the longitudinal speed threshold, it is determined that the first collision identification result between the target object and the target vehicle is that there is a collision risk, and if it is less than or equal to the longitudinal speed threshold, it is determined that the first collision identification result between the target object and the target vehicle is that there is no collision risk.

[0099] If it is determined that the lateral relative speed information between the target vehicle and the target object is greater than the lateral speed threshold, it is determined that the first collision identification result between the target object and the target vehicle is that there is a collision risk, and if it is less than or equal to the lateral speed threshold, it is determined that the first collision identification result between the target object and the target vehicle is that there is no collision risk.

[0100] Of course, the first collision identification result can also be obtained based on one or more of the above collision identification methods.

[0101] For step S300, according to the target motion information, first collision risk information between the target object and the target vehicle is determined, and according to the first collision risk information, a second collision identification result between the target object and the target vehicle is determined.

[0102] In an implementation manner of the present application, as shown in Figure 2 determining the first collision risk information between the target object and the target vehicle according to the target motion information comprises the following steps.

[0103] S310, according to the first motion information and the second motion information, trajectory intersection risk information between the target object and the target vehicle is determined.

[0104] For example, according to the first driving trajectory prediction information and the second driving trajectory prediction information, the trajectory intersection risk information between the target object and the target vehicle is determined.

[0105] In an implementation manner of the present application, according to the first motion information and the second motion information, the trajectory intersection risk information between the target object and the target vehicle is determined, which comprises determining whether there is a trajectory intersection point between the target object and the target vehicle according to the first trajectory prediction information of the target vehicle and the second trajectory prediction information of the target object.

[0106] For example, it is detected whether there is a trajectory intersection point between the trajectory of the target vehicle and the trajectory of the target object.

[0107] If there is no trajectory intersection point, the trajectory intersection risk information is determined to be zero.

[0108] If there is a trajectory intersection point, a time difference between a time when the target vehicle reaches the trajectory intersection point and a time when the target object reaches the trajectory intersection point is determined, and the trajectory intersection risk information is determined according to the time difference.

[0109] For example, the collision risk is evaluated within a certain time window (for example, 3-5 seconds), and the time difference between the target vehicle and the target object reaching the trajectory intersection point is calculated:

[0110]

[0111] wherein, is an absolute value of the time difference between the target vehicle and the target object reaching the trajectory intersection point, is a time when the target vehicle reaches the trajectory intersection point, is a time when the target object reaches the trajectory intersection point.

[0112] Further, the trajectory intersection risk information between the target object and the target vehicle is determined according to the time difference.

[0113] In an implementation of the present application, determining the trajectory intersection risk information according to the time difference comprises determining a trajectory intersection sensitivity coefficient according to the time difference, and determining the trajectory intersection risk information according to the time difference and the trajectory intersection sensitivity coefficient.

[0114] In an implementation of the present application, the trajectory intersection risk information is a trajectory intersection risk value, i.e., a trajectory intersection cost.

[0115] The trajectory intersection risk value is obtained in the following manner:

[0116]

[0117] The trajectory intersection risk value is obtained in the following manner: The trajectory intersection risk value is obtained in the following manner: is an exponential function, is a trajectory intersection sensitivity coefficient, is a time difference.

[0118] It should be noted that is an adjustable parameter for controlling the sensitivity of , , , , .

[0119] In an implementation of the present application, the time difference and the trajectory intersection sensitivity coefficient are positively correlated, i.e., The smaller the time difference is, the smaller the trajectory intersection sensitivity coefficient is. The smaller the time difference is, the smaller the trajectory intersection sensitivity coefficient is.

[0120] As shown in FIG. 3, when the time difference is equal to different values, the relationship curves of the time difference and the trajectory intersection risk value are different. That is, Figure 3 The larger the time difference is, the more obvious the change of the trajectory intersection risk value with the time difference is. Moreover, the time difference and the trajectory intersection risk value are negatively correlated, i.e., the smaller the time difference is, the larger the trajectory intersection risk value is. The smaller the time difference is, the closer the target vehicle and the target object arrive at the trajectory intersection point, the more likely the collision risk is, and the larger the trajectory intersection risk value needs to be. Therefore, the smaller the time difference is, the smaller the trajectory intersection sensitivity coefficient is selected, and the larger trajectory intersection risk value can be obtained, which can better reflect the higher collision risk of the target vehicle and the target object.

[0121] S320, according to the second motion information, determining the lateral speed risk information and the lateral acceleration risk information between the target object and the target vehicle.

[0122] S320, according to the second motion information, determining the lateral speed risk information and the lateral acceleration risk information between the target object and the target vehicle.

[0123] ​In the implementation of the present application, the lateral speed risk information and the lateral acceleration risk information between the target object and the target vehicle are determined according to the second motion information, including: determining a lateral speed sensitive coefficient according to the lateral speed information of the target object, and determining the lateral speed risk information according to the lateral speed information and the lateral speed sensitive coefficient.

[0124] In an implementation of the present application, the lateral speed risk information is a lateral speed risk value, that is, a lateral speed cost.

[0125] The lateral speed risk value is obtained by the following method:

[0126]

[0127] The lateral speed risk value is obtained by the following method: The lateral speed risk value is obtained by the following method: The lateral speed risk value is obtained by the following method: The lateral speed risk value is obtained by the following method: The lateral speed risk value is obtained by the following method:

[0128] In an implementation of the present application, The lateral speed sensitive coefficient is an adjustable lateral speed sensitive coefficient, which is used to control the sensitivity of the lateral speed , , , , , .

[0129] The lateral speed information of the target object and the lateral speed sensitive coefficient are positively correlated, that is, The greater the lateral speed information is, The greater the lateral speed sensitive coefficient is.

[0130] As shown in FIG. 4, when the lateral speed information is equal to different values, the relationship curves of the lateral speed information and the lateral speed risk value are different. That is, Figure 4 The greater the lateral speed information is, the more obvious the change of the lateral speed risk value with the lateral speed information is, and the lateral speed information and the lateral speed risk value are positively correlated, that is, the smaller the lateral speed information is, the greater the lateral speed risk value is. The greater the lateral speed information of the target object is, the higher the possibility of collision is, and a greater collision speed risk value is required. Therefore, the greater the lateral speed information is, the greater the selected lateral speed sensitive coefficient is, and a greater lateral speed risk value can be obtained, which can better reflect the higher collision risk of the target vehicle and the target object.

[0131] The greater the lateral speed information of the target object is, the higher the possibility of collision is, and a greater collision speed risk value is required. Therefore, the greater the lateral speed information is, the greater the selected lateral speed sensitive coefficient is, and a greater lateral speed risk value can be obtained, which can better reflect the higher collision risk of the target vehicle and the target object.

[0132] Further, the lateral acceleration risk information is determined according to the lateral acceleration information of the target object. ​

[0133] In the implementation of this application, determining the lateral acceleration risk information based on the lateral acceleration information of the target object includes: determining the lateral acceleration risk information based on the lateral acceleration information, lateral acceleration coefficient, and maximum lateral acceleration value of the target object.

[0134] In one implementation of this application, the lateral acceleration risk information is the lateral acceleration risk value, also known as the lateral acceleration cost.

[0135] The lateral acceleration risk value is obtained as follows:

[0136]

[0137] in, This represents the lateral acceleration risk value. It is the tangent function. The lateral acceleration coefficient, This is lateral acceleration information. This represents the maximum lateral acceleration.

[0138] In the implementation of this application, the lateral acceleration coefficient can be preset, for example... Among them, the larger the lateral acceleration coefficient, the more obvious the compression of the curve in the x-axis direction, that is, the larger the lateral acceleration coefficient, the greater the lateral acceleration risk value.

[0139] In this implementation, the lateral acceleration coefficient can be determined based on the lateral acceleration information, wherein the lateral acceleration information and the lateral acceleration coefficient are positively correlated, that is... The larger, The larger.

[0140] like Figure 5 As shown, the greater the positive lateral acceleration, the greater the lateral acceleration risk value, the higher the risk of collision for the target object, and the faster it will be selected for collision avoidance. Conversely, the greater the negative lateral acceleration, which is equivalent to a greater lateral deceleration, the more likely the target object is to move away from the target vehicle. Therefore, a negative lateral acceleration risk value reduces the subsequent first collision risk information to prevent misselection.

[0141] The greater the lateral acceleration of the target object, the higher the probability of a collision, and the greater the collision acceleration risk value is required. Therefore, when the lateral acceleration information is greater, the selected lateral acceleration coefficient is larger, which can obtain a greater lateral acceleration risk value and better reflect the higher collision risk between the target vehicle and the target object.

[0142] S330, based on the third motion information, determines the collision time risk information, lateral distance risk information, and lane departure risk information between the target object and the target vehicle.

[0143] In the implementation of the present application, the collision time risk information, the lateral distance risk information and the lane deviation risk information are determined according to the third motion information, including: determining a collision time sensitivity coefficient according to the collision time, and determining the collision time risk information according to the collision time and the collision time sensitivity coefficient.

[0144] In an implementation of the present application, the collision time risk information is a collision time risk value, that is, the collision time cost.

[0145] The collision time risk value is obtained by the following method:

[0146]

[0147] The collision time risk value is obtained by the following method: The collision time risk value is obtained by the following method: The collision time risk value is obtained by the following method: The collision time risk value is obtained by the following method: The collision time risk value is obtained by the following method:

[0148] In an implementation of the present application, The collision time sensitivity coefficient is adjustable, and is used to control the sensitivity of the collision time . , , , , .

[0149] In the implementation of the present application, the collision time and the collision time sensitivity coefficient are positively correlated, that is, The smaller the collision time is, the smaller the collision time sensitivity coefficient is.

[0150] As shown in Figure 6 , when is equal to different values, the relationship curves of the collision time and the collision time risk value are different. That is, The larger the collision time is, the smaller the collision time risk value is.

[0151] The smaller the collision time is, the higher the collision possibility is, and a larger collision time risk value is needed. Therefore, the smaller the collision time is, the smaller the collision time sensitivity coefficient is, a larger collision time risk value can be obtained, and the collision risk of the target vehicle and the target object can be better reflected.

[0152] Furthermore, based on the lateral relative distance information between the target object and the target vehicle, a lateral distance sensitivity coefficient is determined, and based on the lateral distance information of the target object relative to the target vehicle and the lateral distance sensitivity coefficient, lateral distance risk information is determined.

[0153] In one implementation of this application, the lateral distance risk information is the lateral distance risk value, also known as the lateral distance cost.

[0154] The lateral distance risk information was obtained in the following way:

[0155]

[0156] in, This represents the risk value for lateral distance. It is an exponential function. The lateral distance sensitivity coefficient, This refers to the lateral relative distance information between the target object and the target vehicle. This is the preset reference distance.

[0157] In one implementation of this application, An adjustable lateral distance sensitivity coefficient, used to control lateral distance. Sensitivity , , , , . For example, half the width of the lane.

[0158] In this implementation, the lateral relative distance information is negatively correlated with the lateral distance sensitivity coefficient; the smaller the lateral relative distance information, the larger the lateral distance sensitivity coefficient. When the lateral relative distance information is less than 1.5, Take a value of 1.5 to 2.0, so that With drastic changes in lateral distance information, when the relative lateral distance is greater than 1.5 and less than 2.5, Take a value of 1.0 to 1.5, so that As the lateral relative distance information changes from drastic fluctuations to a more stable state, when the lateral relative distance information is greater than 2.5, Take a value of 0.5 to 1.0, so that As the lateral relative distance information changes steadily, the lateral distance sensitivity coefficient can also be determined based on the driving road and lateral relative distance information in the implementation of this application. For example, different lateral distance sensitivity coefficients can be determined based on different lateral relative distance information on urban roads and highways.

[0159] like Figure 7 As shown, in When the lateral relative distance information is equal to different values, the relationship curves of the lateral relative distance information and the lateral distance risk value are different. That is, The greater the lateral distance risk value, the more obvious the change of the lateral distance risk value with the lateral relative distance information.

[0160] Further, the lane departure risk information is determined according to the lateral distance information between the lane line of the lane in which the target object is located relative to the target vehicle.

[0161] In an implementation manner of the present application, the lane departure risk information is a lane departure risk value, that is, a lane departure cost.

[0162] In the implementation manner of the present application, the lane departure risk value is determined according to the lateral distance information of the lane line of the lane in which the target object is located relative to the target vehicle, and the lane departure risk value is obtained by the following manner:

[0163]

[0164] Wherein, the lane departure risk value, the lateral distance information of the lane line of the lane in which the target object is located relative to the target vehicle, a preset constant.

[0165] For example, the smaller the lateral distance information of the lane line of the lane in which the target object is located relative to the target vehicle, the higher the lane departure risk value.

[0166] Wherein, a minimum constant, to avoid division by zero.

[0167] In another implementation manner of the present application, the lane departure risk value is determined according to the lateral distance information of the lane line of the lane in which the target object is located relative to the target vehicle, and the lane departure risk value is obtained by the following manner:

[0168] Wherein, the lane departure risk value is obtained by the following manner:

[0169]

[0170] Wherein, the lane departure risk value, a lane departure index, the lateral distance information of the lane line of the lane in which the target object is located relative to the target vehicle.

[0171] The target object is negatively correlated with the lateral distance information of the lane line of the lane in which the target vehicle is located, that is, The smaller, The greater. For example, Less than -0.5, Take 2.0~2.5, Greater than -0.5 less than 0.5, Take 2.0, Greater than 0.5, Take 1.5.

[0172] As Figure 8 shown, when Equal to different values, the relationship curve of the lateral distance information and the lane deviation risk value is different. That is, The greater, the more obvious the change of the lane deviation risk value with the lateral distance information. And, the lateral distance information is positively correlated with the lane deviation risk value, that is, the smaller the lateral distance, the greater the lane deviation risk value.

[0173] It should be noted that steps S310, S320 and S330 are not limited to the order of execution.

[0174] S340, according to the trajectory intersection risk information, the lateral velocity risk information, the lateral acceleration risk information, the collision time risk information, the lateral distance risk information and the lane deviation risk information, determine the first collision risk information.

[0175] In the implementation of the present application, the trajectory intersection risk information, the lateral velocity risk information, the lateral acceleration risk information, the collision time risk information, the lateral distance risk information and the lane deviation risk information are respectively determined according to the target motion information. Each corresponding weight coefficient.

[0176] For example, according to the time difference, the risk weight coefficient corresponding to the trajectory intersection risk information is determined, and the trajectory intersection risk weight coefficient is obtained.

[0177] For example, according to the corresponding relationship table or the corresponding relationship curve of the time difference and the trajectory intersection risk weight coefficient, the trajectory intersection risk weight coefficient is determined, wherein the smaller the time difference, the greater the trajectory intersection risk weight coefficient.

[0178] According to the lateral velocity information of the target vehicle, the risk weight coefficient corresponding to the lateral velocity risk information is determined, and the lateral velocity risk weight coefficient is obtained.

[0179] For example, according to the corresponding relationship table or the corresponding relationship curve of the lateral velocity information and the lateral velocity risk weight coefficient, the lateral velocity risk weight coefficient is determined, wherein the greater the lateral velocity, the greater the lateral velocity risk weight coefficient.

[0180] The lateral acceleration risk weight coefficient is determined according to the corresponding relationship between the lateral acceleration information and the lateral acceleration risk weight coefficient, and the lateral acceleration risk weight coefficient is obtained.

[0181] For example, the lateral acceleration risk weight coefficient is determined according to a corresponding relationship table or a corresponding relationship curve between the lateral acceleration information and the lateral acceleration risk weight coefficient, wherein the greater the lateral acceleration is, the greater the lateral acceleration risk weight coefficient is.

[0182] The collision time risk weight coefficient is determined according to the corresponding relationship between the collision time information and the collision time risk weight coefficient, and the collision time risk weight coefficient is obtained.

[0183] For example, the collision time risk weight coefficient is determined according to a corresponding relationship table or a corresponding relationship curve between the collision time and the collision time risk weight coefficient, wherein the smaller the collision time is, the greater the collision time risk weight coefficient is.

[0184] The lateral distance risk weight coefficient is determined according to the corresponding relationship between the lateral relative distance information between the target object and the target vehicle and the lateral distance risk weight coefficient, and the lateral distance risk weight coefficient is obtained.

[0185] For example, the lateral distance risk weight coefficient is determined according to a corresponding relationship table or a corresponding relationship curve between the lateral relative distance information between the target object and the target vehicle and the lateral distance risk weight coefficient, wherein the smaller the lateral relative distance information is, the greater the lateral distance risk weight coefficient is.

[0186] The lane deviation risk weight coefficient is determined according to the corresponding relationship between the lateral distance information of the target object relative to the lane line where the target vehicle is located and the lane deviation risk weight coefficient, and the lane deviation risk weight coefficient is obtained.

[0187] For example, the lane deviation risk weight coefficient is determined according to a corresponding relationship table or a corresponding relationship curve between the lateral distance information of the target object relative to the lane line where the target vehicle is located and the lane deviation risk weight coefficient, wherein the smaller the lateral distance information is, the greater the lane deviation risk weight coefficient is.

[0188] Further, the first collision risk information is determined according to the trajectory intersection risk information, the lateral speed risk information, the lateral acceleration risk information, the collision time risk information, the lateral distance risk information and the lane deviation risk information, including: the first collision risk information is determined according to the trajectory intersection risk information, the lateral speed risk information, the lateral acceleration risk information, the collision time risk information, the lateral distance risk information, the lane deviation risk information and the respective weight coefficients.

[0189] In an implementation manner of the present application, the first collision risk information is a first collision risk value.

[0190] According to the trajectory intersection risk information, the lateral speed risk information, the lateral acceleration risk information, the collision time risk information, the lateral distance risk information, the lane deviation risk information, and the respective weight coefficients, the first collision risk information is determined, including: according to the trajectory intersection risk weight coefficient, the lateral speed risk weight coefficient, the lateral acceleration risk weight coefficient, the collision time risk weight coefficient, the lateral distance risk weight coefficient, and the lane deviation risk weight coefficient, the trajectory intersection risk value, the lateral speed risk value, the lateral acceleration risk value, the collision time risk value, the lateral distance risk value, and the lane deviation risk value are weighted and summed to obtain the first collision risk value.

[0191] The first collision risk value is obtained by the following method:

[0192]

[0193] The first collision risk value is obtained by the following method: The first collision risk value is obtained by the following method: The lateral distance risk value is obtained by the following method: The lateral distance risk value is obtained by the following method: The lane deviation risk value is obtained by the following method: The lane deviation risk value is obtained by the following method: The lateral speed risk value is obtained by the following method: The lateral speed risk value is obtained by the following method: The trajectory intersection risk value is obtained by the following method: The trajectory intersection risk value is obtained by the following method: The collision time risk value is obtained by the following method: The collision time risk value is obtained by the following method: The lateral acceleration risk value is obtained by the following method: The lateral acceleration risk value is obtained by the following method.

[0194] For step S400, in the case where the first collision identification result and the second collision identification result determine that there is a collision risk between the target object and the target vehicle, the historical collision indication information and the current collision indication information between the target object and the target vehicle are determined, and the target collision indication information is determined according to the historical collision indication information and the current collision indication information.

[0195] For example, in the case where the first collision identification result and / or the second collision identification result determine that there is a collision risk between the target object and the target vehicle, the historical collision indication information and the current collision indication information between the target object and the target vehicle are determined, and the target collision indication information is determined according to the historical collision indication information and the current collision indication information.

[0196] Further, in the case where the first collision identification result and the second collision identification result determine that there is no collision risk between the target object and the target vehicle, the target vehicle is controlled to drive normally.

[0197] As Figure 9 shown in the embodiments of the present application, the historical collision indication information and the current collision indication information between the target object and the target vehicle are determined, and the target collision indication information is determined according to the historical collision indication information and the current collision indication information, including the following steps.

[0198] S410, according to the lateral speed information of the target object, the relative lateral distance information between the target object and the target vehicle, and the first collision risk value, the current collision indication information between the target object and the target vehicle is determined.

[0199] In an implementation mode, the current collision indication information between the target object and the target vehicle is obtained by looking up a table according to the lateral speed information of the target object, the relative lateral distance information between the target object and the target vehicle, and the first collision risk value.

[0200] In another implementation mode, the current collision indication information is a current collision probability, and the current collision probability between the target object and the target vehicle is obtained based on a probability determination model according to the lateral speed information of the target object, the relative lateral distance information between the target object and the target vehicle, and the first collision risk value.

[0201] Of course, in the embodiments of the present application, the current collision probability can also be determined considering the longitudinal speed information of the target vehicle.

[0202] S420, the historical collision indication information, the first weight coefficient corresponding to the historical collision indication information and the second weight coefficient corresponding to the current collision indication information are determined.

[0203] For example, the historical collision indication information is a historical collision probability.

[0204] For example, the collision probability of the last time or the last few times is determined, wherein the collision probability of the last time or the last few times can be the collision probability of the last time, or the collision probability corresponding to the previous several frames of perception images.

[0205] S430, the target collision indication information is obtained according to the first weight coefficient, the historical collision indication information, the second weight coefficient and the current collision indication information.

[0206] For example, the target collision indication information is a target collision probability, wherein the target collision indication information is obtained according to the first weight coefficient, the historical collision indication information, the second weight coefficient and the current collision indication information, including: the historical collision probability and the current collision probability are weighted and averaged according to the first weight coefficient and the second weight coefficient, to obtain the target collision probability.

[0207] The target collision probability is obtained by the following way:

[0208]

[0209] wherein, is a target collision probability, is a first weight coefficient, is a historical collision probability, is a second weight coefficient, is a current collision probability.

[0210] In an implementation manner, , That is, the multi-frame probability superposition is performed with a step of 0.3, and the target collision probability is determined by considering the historical collision probability, so that the collision trend of the target object and the target vehicle can be continuously judged, a more accurate collision probability can be obtained based on the continuous offset of the target object, the misjudgment caused by the instantaneous offset of the target object can be avoided, and the probability of misjudgment is reduced.

[0211] For step S500, the driving state of the target vehicle is controlled according to the target collision indication information and the third motion information.

[0212] For example, when it is determined that the target collision probability is greater than a preset collision probability threshold (for example, 1), the driving state of the target vehicle is controlled according to the third motion information.

[0213] As shown in Figure 10 , in the implementation manner of the present application, the driving state of the target vehicle is controlled according to the target collision indication information and the third motion information, including the following steps.

[0214] S510, in a case where it is determined that the target collision indication information satisfies the collision indication condition, determining lateral distance parameter information according to lateral relative distance information between the target object and the target vehicle, determining lateral speed parameter information according to lateral relative speed information between the target object and the target vehicle, and determining collision time parameter information according to the collision time.

[0215] For example, when it is determined that the target collision probability is greater than a preset collision probability threshold (for example, 1), the lateral distance parameter information is determined according to the lateral relative distance information between the target object and the target vehicle.

[0216] In the implementation manner of the present application, the lateral distance parameter information is determined according to the lateral relative distance information between the target object and the target vehicle, including: determining the lateral distance parameter information according to the lateral relative distance information between the target object and the target vehicle based on an S-shaped curve function.

[0217] Wherein, the lateral distance parameter information is obtained by the following way:

[0218]

[0219] wherein, is the lateral distance parameter information, is an S-shaped curve function, is the lateral relative distance information between the target object and the target vehicle, is a curve state definition function, and c is a sensitive threshold, is a curve steepness function, and o is a curve steepness.

[0220] In an implementation manner of the present application, the lateral distance parameter information is a lateral distance parameter value.

[0221] In an implementation manner, c is 3.0, that is, that is, is used to define the critical point of the curve state change of the lateral relative distance information and the lateral distance parameter information, and if the lateral relative distance c = 3.0, it indicates that 3.0 is the sensitive threshold of the lateral relative distance. o is 3, that is, that is, is used to control the sensitivity of the state switching, when o = 3, the curve is steep, and the lateral distance parameter value changes rapidly near the critical point.

[0222] In another implementation manner, c is 0.5, as shown in Figure 11 the lateral distance parameter value changes sharply near 0.5. And as shown in the figure, the smaller the lateral relative distance is, the larger the lateral distance parameter value is.

[0223] In the implementation manner of the present application, the lateral velocity parameter information is determined according to the lateral relative speed information between the target object and the target vehicle, comprising: determining the lateral velocity parameter information according to the lateral relative speed information between the target object and the target vehicle based on an S-shaped curve function.

[0224] wherein, the lateral velocity parameter information is obtained by the following way:

[0225]

[0226] wherein, is the lateral velocity parameter information, is an S-shaped curve function, is determined according to the lateral relative speed information between the target object and the target vehicle, is a curve state definition function, and c is a sensitive threshold, is a curve steepness function, and o is a curve steepness.

[0227] In an implementation manner of the present application, the lateral velocity parameter information is a lateral velocity parameter value.

[0228] In an implementation, c=0.5, o=5, that is, is used to define the critical point of the curve state change of the lateral relative speed information and the lateral speed parameter information, if the lateral relative speed c=0.5, it indicates that 0.5 is the lateral relative speed sensitive threshold. o is 5, that is is used to control the sensitivity of state switching, When o=5, the curve is steep, and the lateral speed parameter value changes rapidly near the critical point.

[0229] In another implementation, c is 0.8, as shown in Figure 12 , the lateral speed parameter value changes sharply near 0.5. And, as shown in the figure, the greater the lateral relative speed, the greater the lateral speed parameter value.

[0230] In an implementation of the present application, the collision time parameter information is determined according to the collision time, comprising: determining the collision time parameter information according to the collision time based on an S-shaped curve function.

[0231] Wherein, the collision time parameter information is obtained by the following way:

[0232]

[0233] Wherein, is the collision time parameter information, is the S-shaped curve function, is the collision time, is the curve center point, is the curve steepness.

[0234] In an implementation of the present application, the collision time parameter information is a collision time parameter value.

[0235] In an implementation, c=3.0, o=2, that is, is used to define the critical point of the curve state change of the collision time and the collision time parameter information, if the collision time c=3.0, it indicates that 3.0 is the collision time sensitive threshold. o is 2, that is is used to control the sensitivity of state switching, When o=2, the curve is steep, and the collision time parameter value changes rapidly near the critical point.

[0236] In another implementation, c is 2.0, as shown in Figure 13 , the collision time parameter value changes sharply after 2.0. And, as shown in the figure, the smaller the collision time, the greater the collision time parameter value.

[0237] S520, determine a lateral distance weight coefficient according to the lateral distance parameter information, determine a lateral velocity weight coefficient according to the lateral velocity parameter information, and determine a collision time weight coefficient according to the collision time parameter information.

[0238] For example, the lateral distance parameter information, the lateral velocity parameter information, and the collision time parameter information are normalized respectively to obtain the corresponding lateral distance weight coefficient, the lateral velocity weight coefficient, and the collision time weight coefficient.

[0239] In the implementation of the present application, the lateral distance weight coefficient is determined according to the lateral distance parameter information, which includes normalizing the lateral distance parameter value to obtain the lateral distance weight coefficient.

[0240] The lateral distance weight coefficient is obtained in the following manner:

[0241]

[0242] The lateral distance weight coefficient is obtained in the following manner: The lateral distance weight coefficient is obtained in the following manner: The lateral distance parameter information is obtained in the following manner: The preset value is obtained in the following manner:

[0243] The lateral velocity weight coefficient is determined according to the lateral velocity parameter information, which includes normalizing the lateral velocity parameter value.

[0244] The lateral velocity weight coefficient is obtained in the following manner:

[0245]

[0246] The lateral velocity weight coefficient is obtained in the following manner: The lateral velocity weight coefficient is obtained in the following manner: The lateral velocity parameter information is obtained in the following manner: The preset value is obtained in the following manner:

[0247] The collision time weight coefficient is determined according to the collision time parameter information, which includes normalizing the collision time parameter value to obtain the collision time weight coefficient.

[0248] The collision time weight coefficient is obtained in the following manner:

[0249]

[0250] The collision time weight coefficient is obtained in the following manner: The collision time weight coefficient is obtained in the following manner: The collision time parameter information is obtained in the following manner: The preset value is obtained in the following manner:

[0251] S530, determine the second collision risk information according to the lateral distance weight coefficient, the lateral distance, the lateral speed weight coefficient, the lateral speed, the collision time weight coefficient and the collision time.

[0252] In the implementation of the present application, the second collision risk information is determined according to the lateral distance weight coefficient, the lateral relative distance information, the lateral speed weight coefficient, the lateral relative speed information, the collision time weight coefficient and the collision time, including obtaining the second collision risk information by the following way:

[0253]

[0254] wherein, the second collision risk information is, the lateral distance weight coefficient is, the lateral relative distance information is, the lateral speed weight coefficient is, the lateral relative speed information is, the collision time weight coefficient is, the collision time is.

[0255] wherein, the second collision risk information is the second collision risk score, which is used to represent the collision risk degree of the target object and the target vehicle.

[0256] S540, determine the first acceleration according to the second collision risk information.

[0257] In an implementation of the present application, the collision risk level is determined according to the second collision risk score.

[0258] In an implementation, the collision risk level is three levels, for example, when it is a low risk level, it is a medium risk level, it is a high risk level.

[0259] In another implementation, the collision risk level is five levels, for example, when it is an ultra-low risk level, it is a low risk level, it is a medium risk level, it is a high risk level, it is an ultra-high risk level.

[0260] Further, the corresponding first acceleration is determined according to the collision risk level.

[0261] In an implementation, the first acceleration is an acceleration interval, that is, the corresponding first acceleration interval is determined according to the collision risk level.

[0262] In another implementation, the first acceleration is a determined value, i.e., a value of the first acceleration corresponding to the collision risk level is determined.

[0263] In another implementation of the present application, the first acceleration interval or value can also be determined directly according to the second collision risk information.

[0264] Specifically, the first acceleration is determined based on a linear interpolation method according to the second collision risk score.

[0265] For example, the second collision risk information is 2.2, and the first acceleration interval is [-1.2 m / s² ~ -1.8 m / s²], and for another example, the second collision risk information is 2.2, and the first acceleration is -1.8 m / s². Wherein, the minus sign indicates that the acceleration direction is opposite to the vehicle speed direction, i.e., the deceleration.

[0266] S550, controlling the driving state of the target vehicle according to the first acceleration.

[0267] For example, the braking acceleration of the target vehicle is -1.8 m / s².

[0268] Further, in the implementation of the present application, the collision indication condition is that the target collision probability is greater than a preset collision probability threshold, wherein the collision indication condition is obtained by the following method:

[0269] According to the time headway information and the longitudinal speed information of the target vehicle, a collision time threshold is determined.

[0270] For example, an initial collision time threshold is preset, and the initial collision time threshold is dynamically adjusted according to the time headway information and the longitudinal speed information of the target vehicle to obtain the collision time threshold. Wherein, the smaller the time headway information, the smaller the collision time threshold, and the higher the longitudinal speed of the target vehicle, the smaller the collision time threshold.

[0271] A preset lateral relative distance threshold is determined, and the lateral relative distance threshold is set from 0.5 m to 1.5 m to ensure that the target object within the threshold range can be selected in advance and the target vehicle pre-control is performed in advance.

[0272] The collision indication condition is determined according to the collision time, the collision time threshold, the lateral relative distance, and the lateral relative distance threshold.

[0273] Wherein, if the collision time is less than or equal to the collision time threshold and the lateral relative distance is less than or equal to the lateral relative distance threshold, the preset collision probability threshold is 1, and the collision indication condition is that the target collision probability is greater than 1. Of course, it can also be other numerical values.

[0274] If the collision time is greater than the collision time threshold or the lateral relative distance is greater than the lateral relative distance threshold, the preset collision probability threshold is determined to be 0.7, and the collision indication condition is that the target collision probability is greater than 0.7. Of course, it can also be other numerical values.

[0275] Further, in the implementation of the present application, the second acceleration for avoiding the target vehicle from colliding is determined based on a model predictive control method (MPC), and of course the vehicle offset direction and offset angle for avoiding the target vehicle from colliding can also be determined.

[0276] The model predictive control method (MPC) is a mainstream method for solving optimal control problems in a finite time domain online, and realizes high-precision control of vehicle dynamics. In the implementation of the present application, collision recognition is combined with MPC to achieve better vehicle state control based on MPC.

[0277] For example, to avoid a collision, it is predicted that the target vehicle needs to drive to the right front.

[0278] Further, in the implementation of the present application, the driving state of the target vehicle is controlled according to the first acceleration, including: controlling the driving state of the target vehicle according to the first acceleration and the second acceleration.

[0279] For example, the first acceleration is corrected according to the second acceleration to obtain a target acceleration, so as to control the driving state of the target vehicle according to the target acceleration. Or the first acceleration is corrected according to the second acceleration to obtain a target acceleration, so as to control the driving state of the target vehicle according to the target acceleration.

[0280] Of course, the first acceleration and the second acceleration can also be the maximum, the minimum, or the average.

[0281] Further, in the implementation of the present application, the cost function weight term and the constraint boundary involved in the model predictive control method are also determined according to the target collision indication information, the second collision risk information, the collision time threshold, and the preset lateral relative distance threshold, to obtain an optimized model predictive control method.

[0282] Specifically, the collision avoidance weight of the collision avoidance safety item of the cost function of the MPC is adjusted based on the target collision probability and the collision risk score, and the dynamic safety distance of the collision avoidance safety item is adjusted based on the collision time threshold and the lateral relative distance threshold, to obtain a new collision avoidance safety item based on the collision avoidance weight and the dynamic safety distance.

[0283] The collision avoidance safety item is used to constrain the longitudinal safety distance between the target vehicle and the target object.

[0284] Further, the cost function of the MPC further comprises a comfort term, a speed tracking term, and a terminal cost term.

[0285] Further, adjusting the constraint boundary of the MPC according to the target collision probability comprises a scenario adaptive constraint.

[0286] The constraint boundary of the MPC further comprises a control quantity constraint and a state quantity constraint.

[0287] In the implementation of the present application, the driving state of the target vehicle is controlled according to the first acceleration, comprising: based on the optimized model predictive control method, the target acceleration of the target vehicle is controlled to smoothly transition to the first acceleration.

[0288] For example, based on the optimized MPC, the future multi-frame driving state is predicted, and the acceleration of the target vehicle is adjusted in advance to smoothly transition the target acceleration from the current value to the first acceleration.

[0289] And if the lateral relative distance between the target object and the target vehicle increases, that is, the intrusion tendency weakens, the MPC automatically reduces the acceleration, or even restores the acceleration, to improve the traffic efficiency.

[0290] Further, if the target collision probability is less than a preset collision probability threshold, that is, the target collision indication information does not satisfy the collision indication condition, it is determined that the collision risk is low, the first acceleration determination can be omitted, and only the second acceleration is predicted based on the MPC to realize vehicle control, so as to realize collision avoidance.

[0291] The vehicle driving control method provided by the implementation of the present application is especially suitable for vehicle collision avoidance control in the cutin scene where the target vehicle has a vehicle overtaking, lane changing, and crossing the road in front of the left and right front, such as Figure 14 As shown, the target motion information is obtained, on the one hand, the target object intrusion tendency is judged according to the target motion information to obtain a first collision identification result, and on the other hand, the collision risk cost is calculated according to the target motion information to obtain a second collision identification result. If the first collision identification result or the second collision identification result is a collision risk, the collision scene is judged based on the multi-frame probability superposition mode to obtain a more accurate target collision probability. If the collision risk is large according to the target collision probability, it is determined that the slow brake logic needs to be executed, and the first braking acceleration and the MPC optimized output target acceleration are calculated, wherein the acceleration is positive, indicating that the vehicle needs to accelerate to avoid collision, and the acceleration is negative, indicating that the vehicle needs to decelerate to avoid collision. In this way, more accurate collision avoidance control is realized. If the collision risk is small according to the target collision probability, the vehicle driving control is not needed, and the next frame of vehicle collision risk judgment is performed.

[0292] Further, in the second collision identification result determination process, the collision time is determined by introducing the collision idea, the risk cost of design is added according to different influence factors, and the weight optimization is performed according to the risk cost of each influence factor, so that a better collision identification result is obtained.

[0293] Based on the collision identification method of the application, the target object around the target vehicle can be judged in advance based on multiple scenes, the target object with collision risk can be selected in advance, and the collision identification accuracy of the selected target object is higher. Further, based on the driving state control method of the application, the target vehicle can be smoothly controlled to achieve better control effect.

[0294] The vehicle driving control method provided by the implementation manner of the application is applied to an electronic device, and the electronic device includes a processor and a memory in communication connection with the processor; the memory stores computer execution instructions; and the processor executes the computer execution instructions stored in the memory to execute the aforementioned vehicle driving control method.

[0295] The implementation manner of the application also provides a vehicle to implement the aforementioned vehicle driving control method.

[0296] The vehicle driving control method provided by the implementation manner of the application can also be applied to a vehicle driving control system, and the vehicle driving control system includes a cloud server and a target vehicle. Specifically, the target vehicle sends vehicle perception images and / or radar point cloud information to the cloud server, the cloud server obtains target motion information, determines a first collision identification result between a target object and the target vehicle according to the target motion information and a collision identification condition, determines first collision risk information according to the target motion information, determines a second collision identification result between the target object and the target vehicle according to the first collision risk information, determines historical collision indication information and current collision indication information between the target object and the target vehicle in a case where it is determined that there is a collision risk between the target object and the target vehicle according to the first collision identification result and the second collision identification result, determines target collision indication information according to the historical collision indication information and the current collision indication information, generates a control instruction according to the target collision indication information and third motion information, and issues the control instruction to the target vehicle to control the driving state of the target vehicle.

[0297] The embodiment of the application also provides a chip for executing the vehicle driving control method in the above-mentioned embodiments.

[0298] The embodiment of the present application further provides a computer readable storage medium, which stores computer instructions. When the computer instructions run on a processor of an electronic device, the processor of the electronic device executes the technical solution of the vehicle driving control method of the above embodiment.

[0299] In some possible implementation manners, various aspects of the method provided by the present application can also be implemented in the form of a program product, which includes program codes. When the program product runs on a processor of an electronic device, the program codes are used to make the processor of the electronic device execute the steps in the method described above according to various exemplary implementation manners of the present application. For example, the electronic device can execute the vehicle driving control method described in the embodiments of the present application.

[0300] The program product can adopt any combination of one or more readable media. The readable medium can be a readable data medium or a readable storage medium. The readable storage medium may, for example, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or component, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include an electrical connection having one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CDROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0301] The implementation manner of the present application further provides a computer program product, which includes a computer program stored in a computer readable storage medium. At least one processor can read the computer program from the computer readable storage medium, and the at least one processor can implement the technical solution of the vehicle driving control method in the above embodiment when executing the computer program.

[0302] It should be noted that in addition to the implementation manners of the present application described in the above specific embodiments, other advantages and effects of the present application can be easily understood by those skilled in the art from the content disclosed in the present application. Although the description of the present application is introduced in combination with the preferred embodiments, this does not mean that the features of the present application are limited to the implementation manners. On the contrary, the purpose of introducing the present application in combination with the implementation manners is to cover other options or modifications that can be extended from the present application. In order to provide a deep understanding of the present application, many specific details are included in the above description, and the present application can also be implemented without using these details. In addition, in order to avoid confusion or ambiguity of the present application, some specific details are omitted in the description. It should be noted that the embodiments and features in the embodiments in the present application can be combined with each other without conflict.

[0303] It should be noted that in this specification similar reference numerals and letters indicate similar items, and thus, once an item is defined in one figure, it should not require further defining and explaining in subsequent figures.

[0304] It should be noted that the terms "first", "second", and so on are used herein only to distinguish one item from another, and do not imply or suggest relative importance.

[0305] It should be noted that in the drawings, some structural or methodological features can be shown in a particular arrangement and / or order. However, it should be understood that such a particular arrangement and / or order can not be required. Rather, in some embodiments, these features can be arranged in a manner different from that shown in the illustrative drawings. Additionally, inclusion of structural or methodological features in a particular figure is not meant to imply that such features are required in all embodiments, and in some embodiments, these features can not be included or can be combined with other features.

[0306] While the present application has been illustrated and described with reference to certain preferred implementations thereof, it should be understood that the foregoing description is intended to illustrate the present application and not to limit the scope thereof. Those skilled in the art will find changes they can make to the present application in form and detail without departing from the spirit and scope thereof.

Claims

1. A vehicle travel control method characterized by comprising: The method comprises: obtaining target motion information, the target motion information comprising first motion information of a target vehicle, second motion information of a target object, and third motion information between the target object and the target vehicle; determining, according to the target motion information and a collision identification condition, a first collision identification result between the target object and the target vehicle; and determining, according to the target motion information, first collision risk information between the target object and the target vehicle, and determining, according to the first collision risk information, a second collision identification result between the target object and the target vehicle; in a case where it is determined, according to the first collision identification result and the second collision identification result, that there is a collision risk between the target object and the target vehicle, determining historical collision indication information and current collision indication information between the target object and the target vehicle, and determining, according to the historical collision indication information and the current collision indication information, target collision indication information; controlling a driving state of the target vehicle according to the target collision indication information and the third motion information; wherein determining, according to the target motion information, first collision risk information between the target object and the target vehicle comprises: determining, according to the first motion information and the second motion information, trajectory intersection risk information between the target object and the target vehicle; and determining, according to the second motion information, lateral speed risk information and lateral acceleration risk information between the target object and the target vehicle; and determining, according to the third motion information, collision time risk information, lateral distance risk information, and lane deviation risk information between the target object and the target vehicle; determining the first collision risk information according to the trajectory intersection risk information, the lateral speed risk information, the lateral acceleration risk information, the collision time risk information, the lateral distance risk information, and the lane deviation risk information.

2. The vehicle travel control method according to claim 1 characterized by The first motion information of the target vehicle comprises first trajectory prediction information of the target vehicle, and the second motion information of the target object comprises second trajectory prediction information of the target object. Determining, according to the first motion information and the second motion information, trajectory intersection risk information between the target object and the target vehicle comprises: determining, according to the first trajectory prediction information of the target vehicle and the second trajectory prediction information of the target object, whether there is a trajectory intersection point between the target object and the target vehicle; if there is no trajectory intersection point, determining that the trajectory intersection risk information is zero; if there is a trajectory intersection point, determining a time difference between a time at which the target vehicle reaches the trajectory intersection point and a time at which the target object reaches the trajectory intersection point, and determining the trajectory intersection risk information according to the time difference.

3. The vehicle travel control method according to claim 2, characterized by The second motion information of the target object further includes lateral velocity information of the target object and lateral acceleration information of the target object, and the lateral velocity risk information and the lateral acceleration risk information between the target object and the target vehicle are determined according to the second motion information, including: a lateral velocity sensitive coefficient is determined according to the lateral velocity information of the target object, and the lateral velocity risk information is determined according to the lateral velocity information and the lateral velocity sensitive coefficient; a lateral acceleration sensitive coefficient is determined according to the lateral acceleration information of the target object, and the lateral acceleration risk information is determined according to the lateral acceleration information and the lateral acceleration sensitive coefficient.

4. The vehicle travel control method according to claim 3, characterized by The third motion information includes a collision time between the target object and the target vehicle, lateral relative distance information between the target object and the target vehicle, and lateral distance information between lane lines of a lane where the target object is located relative to the target vehicle, and the collision time risk information, the lateral distance risk information and the lane deviation risk information between the target object and the target vehicle are determined according to the third motion information, including: a collision time sensitive coefficient is determined according to the collision time, and the collision time risk information is determined according to the collision time and the collision time sensitive coefficient; a lateral distance sensitive coefficient is determined according to the lateral relative distance information between the target object and the target vehicle, and the lateral distance risk information is determined according to the lateral distance information of the target object relative to the target vehicle and the lateral distance sensitive coefficient; the lane deviation risk information is determined according to the lateral distance information between the lane lines of the lane where the target object is located relative to the target vehicle.

5. The vehicle travel control method according to claim 4, characterized by The method further includes: weight coefficients corresponding to the trajectory intersection risk information, the lateral velocity risk information, the lateral acceleration risk information, the collision time risk information, the lateral distance risk information and the lane deviation risk information respectively are determined according to the target motion information; the first collision risk information is determined according to the trajectory intersection risk information, the lateral velocity risk information, the lateral acceleration risk information, the collision time risk information, the lateral distance risk information and the lane deviation risk information, including: the first collision risk information is determined according to the trajectory intersection risk information, the lateral velocity risk information, the lateral acceleration risk information, the collision time risk information, the lateral distance risk information, the lane deviation risk information and the weight coefficients corresponding thereto.

6. The vehicle travel control method according to claim 5, characterized by The first collision risk information is a first collision risk value, historical collision indication information and current collision indication information between the target object and the target vehicle are determined, and target collision indication information is determined according to the historical collision indication information and the current collision indication information, including: determine current collision indication information between the target object and the target vehicle according to the lateral speed information of the target object, the relative lateral distance information between the target object and the target vehicle, and the first collision risk value; and determine historical collision indication information, a first weight coefficient corresponding to the historical collision indication information, and a second weight coefficient corresponding to current collision indication information; obtain the target collision indication information according to the first weight coefficient, the historical collision indication information, the second weight coefficient, and the current collision indication information.

7. The vehicle travel control method according to claim 6, characterized by The third motion information further includes lateral relative speed information between the target object and the target vehicle, and the driving state of the target vehicle is controlled according to the target collision indication information and the third motion information, including: In a case where the target collision indication information meets a collision indication condition, lateral distance parameter information is determined according to lateral relative distance information between the target object and the target vehicle, lateral speed parameter information is determined according to lateral relative speed information between the target object and the target vehicle, and collision time parameter information is determined according to the collision time; a lateral distance weight coefficient is determined according to the lateral distance parameter information, a lateral speed weight coefficient is determined according to the lateral speed parameter information, and a collision time weight coefficient is determined according to the collision time parameter information; second collision risk information is determined according to the lateral distance weight coefficient, the lateral distance, the lateral speed weight coefficient, the lateral speed, the collision time weight coefficient, and the collision time; a first acceleration is determined according to the second collision risk information; the driving state of the target vehicle is controlled according to the first acceleration.

8. The vehicle travel control method according to claim 7, characterized by The third motion information further includes time-to-collision information between the target object and the target vehicle, and the method further includes determining the collision indication condition in the following manner: a collision time threshold is determined according to the time-to-collision information and longitudinal speed information of the target vehicle; and a preset lateral relative distance threshold is determined; the collision indication condition is determined according to the collision time, the collision time threshold, the lateral relative distance, and the lateral relative distance threshold; the driving state of the target vehicle is controlled according to the first acceleration, including: a second acceleration is determined based on a model predictive control method; the driving state of the target vehicle is controlled according to the first acceleration and the second acceleration.

9. An electronic device, comprising: including: a processor, and a memory connected to the processor in communication; the memory stores computer execution instructions; the processor executes the computer execution instructions stored in the memory, so that the electronic device executes the vehicle driving control method according to any one of claims 1-8.

Images