Vehicle driving strategy determination method and device, electronic equipment and storage medium

Abstract

The present disclosure provides a vehicle driving strategy determination method and device, electronic equipment and storage medium. The method comprises: collecting first driving data of a target host vehicle, wherein the first driving data comprises a first position and a first speed of the target host vehicle; collecting second driving data of an obstacle vehicle, wherein the second driving data comprises a second position and a second speed of the obstacle vehicle, the obstacle vehicle being a vehicle that is to cut into the lane where the target host vehicle is located and travel in the same direction as the target host vehicle after cutting in; determining a target distance between a cutting-in point at which the obstacle vehicle cuts into the lane where the target host vehicle is located and the first position based on the first position of the target host vehicle and the second position of the obstacle vehicle; and determining a driving strategy of the target host vehicle based on the target distance and the first speed of the target host vehicle. The present disclosure solves the problem in the related art that it is difficult to correctly determine the driving strategy of the host vehicle to ensure safe driving of the vehicle in the case where the obstacle vehicle is to cut into the lane where the host vehicle is located.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of data processing, and particularly relates to a vehicle driving strategy determination method and device, an electronic device and a storage medium. BACKGROUND

[0002] In the process of driving, if an obstacle vehicle wants to cut into the lane where the host vehicle is located, the host vehicle needs to determine the driving strategy of the host vehicle according to the driving state of the obstacle vehicle, so as to avoid collision with the obstacle vehicle.

[0003] In the related art, the driving trajectory of the obstacle vehicle is usually predicted by the host vehicle, and the driving strategy of the host vehicle is determined based on the prediction result. However, the obtained driving trajectory usually cannot meet the dynamics constraints of the vehicle, and the accuracy of the prediction result is usually low. When the host vehicle determines the driving strategy of the host vehicle based on the trajectory prediction of the obstacle vehicle, the host vehicle is likely to make an incorrect driving strategy due to inaccurate prediction result, and thus vehicle collision occurs. That is, in the related art, in the case where the obstacle vehicle wants to cut into the lane where the host vehicle is located, it is difficult to correctly determine the driving strategy of the host vehicle to ensure safe driving of the vehicle. SUMMARY

[0004] The present disclosure provides a vehicle driving strategy determination method and device, an electronic device and a storage medium.

[0005] According to an aspect of the present disclosure, a vehicle driving strategy determination method is provided, comprising: collecting first driving data of a target host vehicle, wherein the first driving data comprises a first position and a first speed of the target host vehicle; collecting second driving data of an obstacle vehicle, wherein the second driving data comprises a second position and a second speed of the obstacle vehicle, the obstacle vehicle being a vehicle that wants to cut into the lane where the target host vehicle is located and travels in the same direction as the target host vehicle after cutting in; determining a target distance between a cutting-in point of the obstacle vehicle cutting into the lane where the target host vehicle is located and the first position based on the first position of the target host vehicle and the second position of the obstacle vehicle; and determining a driving strategy of the target host vehicle based on the target distance and the first speed of the target host vehicle.

[0006] Optionally, determining the target distance between the cutting-in point of the obstacle vehicle cutting into the lane where the target host vehicle is located and the first position based on the first position of the target host vehicle and the second position of the obstacle vehicle comprises: determining an included angle between a line connecting the first position and the second position and a predetermined direction; in a case where the included angle exceeds a predetermined angle, directly determining the target distance between the cutting-in point and the target host vehicle based on the first position and the second position; and in a case where the included angle does not exceed the predetermined angle, determining the target distance between the cutting-in point and the first position based on the first position, the second position, and the second speed.

[0007] Optionally, in the case that the included angle exceeds the predetermined angle, the target distance between the cut-in point and the target host vehicle is determined directly based on the first position and the second position, comprising: determining a first position distance between the first position and the second position; determining a component of the first position distance in the lane direction as the target distance.

[0008] Optionally, in the case that the included angle does not exceed the predetermined angle, the target distance between the cut-in point and the first position is determined based on the first position, the second position, and the second speed, comprising: determining a second position distance between the first position and the second position; determining a third position distance as a component of the second position distance in the lane direction; determining a time length for the obstacle vehicle to cut into the lane where the target host vehicle is located according to the first position and the second position, and a first speed component of the second speed in a direction perpendicular to the lane direction; determining a fourth position distance according to a second speed component of the second speed in a direction parallel to the lane direction and the time length; and determining the target distance according to the third position distance and the fourth position distance.

[0009] Optionally, the driving strategy of the target host vehicle is determined based on the target distance and the first speed of the target host vehicle, comprising: obtaining a first arrival time length for the target host vehicle to maintain the first speed to reach the cut-in point; obtaining a second arrival time length for the obstacle vehicle to maintain the second speed to reach the cut-in point; in the case that the first arrival time length is less than the second arrival time length, confirming that the driving strategy of the target host vehicle is overtaking; and in the case that the first arrival time length is greater than the second arrival time length, confirming that the driving strategy of the target host vehicle is yielding.

[0010] Optionally, the driving strategy of the target host vehicle is determined based on the target distance and the first speed of the target host vehicle, comprising: in the case that the first arrival time length is equal to the second arrival time length, determining a first reaction time length of the target host vehicle and a second reaction time length of the obstacle vehicle; obtaining a time difference value of the first reaction time length and the second reaction time length; in the case that the time difference value is less than a preset time length, confirming that the driving strategy of the target host vehicle is overtaking; and in the case that the time difference value is not less than the preset time length, confirming that the driving strategy of the target host vehicle is yielding.

[0011] Optionally, in the case that the first arrival time length is equal to the second arrival time length, the first reaction time length of the target host vehicle is determined, comprising: determining a first braking distance traveled by the target host vehicle when the first speed is reduced to a first predetermined speed; determining a first distance difference value between the target distance and the first braking distance; and obtaining the first reaction time length based on the first speed and the first distance difference value.

[0012] Optionally, in the case that the first arrival time length is equal to the second arrival time length, the second reaction time length of the obstacle vehicle is determined, including: determining a second braking distance traveled by the obstacle vehicle from the second speed to the second predetermined speed; determining a fifth position distance between the second position and the cut-in point; determining a second distance difference between the fifth position distance and the second braking distance; obtaining the second reaction time length of the obstacle vehicle based on the second speed and the second distance difference.

[0013] According to another aspect of the present disclosure, a vehicle driving strategy determination apparatus is provided, including: a first acquisition module configured to acquire first driving data of a target host vehicle, wherein the first driving data includes a first position and a first speed of the target host vehicle; a second acquisition module configured to acquire second driving data of an obstacle vehicle, wherein the second driving data includes a second position and a second speed of the obstacle vehicle, the obstacle vehicle being a vehicle that is to cut into a lane where the target host vehicle is located and travel in the same direction as the target host vehicle after cutting in; a first determination module configured to determine a target distance between a cut-in point at which the obstacle vehicle cuts into the lane where the target host vehicle is located and the first position based on the first position of the target host vehicle and the second position of the obstacle vehicle; and a second determination module configured to determine a driving strategy of the target host vehicle based on the target distance and the first speed of the target host vehicle.

[0014] Optionally, the first determination module includes: a first determination unit configured to determine an included angle between a line connecting the first position and the second position and a predetermined direction of the lane; a second determination unit configured to determine the target distance between the cut-in point and the target host vehicle based on the first position and the second position directly in the case that the included angle exceeds a predetermined angle; and a third determination unit configured to determine the target distance between the cut-in point and the first position based on the first position, the second position, and the second speed in the case that the included angle does not exceed the predetermined angle.

[0015] Optionally, the second determination unit includes: a first determination sub-unit configured to determine a first position distance between the first position and the second position; and a second determination sub-unit configured to determine a component of the first position distance in the direction of the lane as the target distance.

[0016] Optionally, the third determination unit includes: a third determination sub-unit configured to determine a second position distance between the first position and the second position; a fourth determination sub-unit configured to determine a component of the second position distance in the direction of the lane as a third position distance; a fifth determination sub-unit configured to determine a time length for the obstacle vehicle to cut into the lane where the target host vehicle is located according to the first position and the second position and a first speed component of the second speed in a direction perpendicular to the direction of the lane; a sixth determination sub-unit configured to determine a fourth position distance according to a second speed component of the second speed in a direction parallel to the direction of the lane and the time length; and a seventh determination sub-unit configured to determine the target distance according to the third position distance and the fourth position distance.

[0017] Optionally, the second determining module comprises: a first obtaining unit, configured to obtain a first arrival time length of the target host vehicle traveling at the first speed to the cut-in point; a second obtaining unit, configured to obtain a second arrival time length of the obstacle vehicle traveling at the second speed to the cut-in point; a fourth determining unit, configured to determine that the driving strategy of the target host vehicle is to overtake the obstacle vehicle in a case where the first arrival time length is less than the second arrival time length; and a fifth determining unit, configured to determine that the driving strategy of the target host vehicle is to yield to the obstacle vehicle in a case where the first arrival time length is greater than the second arrival time length.

[0018] Optionally, the second determining module comprises: a sixth determining unit, configured to determine a first reaction time length of the target host vehicle and a second reaction time length of the obstacle vehicle in a case where the first arrival time length is equal to the second arrival time length; a third obtaining unit, configured to obtain a time difference between the first reaction time length and the second reaction time length; a fourth obtaining unit, configured to determine that the driving strategy of the target host vehicle is to overtake the obstacle vehicle in a case where the time difference is less than a preset time length; and determine that the driving strategy of the target host vehicle is to yield to the obstacle vehicle in a case where the time difference is not less than the preset time length.

[0019] Optionally, the sixth determining unit comprises: an eighth determining sub-unit, configured to determine a first braking distance of the target host vehicle traveling from the first speed to a first predetermined speed; a ninth determining sub-unit, configured to determine a first distance difference between the target distance and the first braking distance; and a first obtaining sub-unit, configured to obtain the first reaction time length based on the first speed and the first distance difference.

[0020] Optionally, the sixth determining unit comprises: a tenth determining sub-unit, configured to determine a second braking distance of the obstacle vehicle traveling from the second speed to a second predetermined speed; an eleventh determining sub-unit, configured to determine a fifth position distance between the second position and the cut-in point; a thirteenth determining sub-unit, configured to determine a second distance difference between the fifth position distance and the second braking distance; and a second obtaining sub-unit, configured to obtain the second reaction time length of the obstacle vehicle based on the second speed and the second distance difference.

[0021] According to another aspect of the present disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected with the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform any of the above methods.

[0022] According to another aspect of the present disclosure, a non-transitory computer readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable a computer to perform any of the above methods.

[0023] According to another aspect of the present disclosure, there is provided a computer program product comprising a computer program which, when executed by a processor, implements the method of any one of the above.

[0024] It should be understood that the contents described in this part are not intended to identify key or important features of the embodiments of the present disclosure, nor to limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0025] The accompanying drawings are used to better understand the present scheme and do not limit the present disclosure. Among them:

[0026] Figure 1 is a flowchart of a vehicle driving strategy determination method according to a first embodiment of the present disclosure;

[0027] Figure 2 is a schematic diagram of a scenario where a straight vehicle encounters a turning vehicle according to a second embodiment of the present disclosure;

[0028] Figure 3 is a schematic diagram of a scenario where a straight vehicle encounters a turning vehicle according to a third embodiment of the present disclosure;

[0029] Figure 4 is a framework diagram of a vehicle driving strategy determination device according to a fourth embodiment of the present disclosure;

[0030] Figure 5 is an electronic device block diagram for implementing the model inference acceleration method of the embodiments of the present disclosure. DETAILED DESCRIPTION

[0031] Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, which include various details of the embodiments of the present disclosure to help understanding, and should be considered as merely exemplary. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Also, in order to be clear and concise, the description below omits the description of well-known functions and structures.

[0032] In the embodiments of the present disclosure, a vehicle driving strategy determination method is provided, Figure 1 is a flowchart of a vehicle driving strategy determination method according to a first embodiment of the present disclosure. As shown in Figure 1 The vehicle driving strategy determination method comprises the following steps:

[0033] Step S101, collecting first driving data of a target host vehicle, wherein the first driving data comprises a first position and a first speed of the target host vehicle.

[0034] In an optional embodiment, the target host vehicle's first position can be acquired by a positioning system, and the target host vehicle's first speed can be acquired by a speed sensor.

[0035] In step S102, the second driving data of the obstacle vehicle is acquired, wherein the second driving data comprises a second position and a second speed of the obstacle vehicle, and the obstacle vehicle is a vehicle that is going to cut into the lane where the target host vehicle is located and travel in the same direction as the target host vehicle after cutting in.

[0036] In an optional embodiment, the second position and the second speed of the obstacle vehicle can be acquired by acquiring continuous image frames of the obstacle vehicle and analyzing the continuous image frames.

[0037] In an optional embodiment, the obstacle vehicle travels in the opposite direction of the target host vehicle on a lane outside the lane where the target host vehicle is located before cutting into the lane where the target host vehicle is located, and turns around at a certain time to travel towards the lane where the target host vehicle is located. The target host vehicle perceives the driving intention of the obstacle vehicle by image analysis, and determines the obstacle vehicle as the object to be analyzed when it is determined that the obstacle vehicle has the intention to enter the lane where the target host vehicle is located.

[0038] In another optional embodiment, the obstacle vehicle travels in the same direction as the target host vehicle on a lane outside the lane where the target host vehicle is located before cutting into the lane where the target host vehicle is located, and turns towards the lane where the target host vehicle is located at a certain time. The target host vehicle perceives the driving intention of the obstacle vehicle, and determines the obstacle vehicle as the object to be analyzed when it is determined that the obstacle vehicle has the intention to enter the lane where the target host vehicle is located.

[0039] In an optional embodiment, the target host vehicle acquires images of the obstacle vehicle at multiple times, analyzes the acquired images to acquire the second position and the second speed of the obstacle vehicle, and determines whether the obstacle vehicle will cut into the lane where the target host vehicle is located based on the second speed. In an optional embodiment, the target host vehicle acquires images of the obstacle vehicle, and determines the driving intention of the obstacle vehicle based on the on-off state of the turn signal of the obstacle vehicle in the images.

[0040] In step S103, the target distance between the cut-in point of the obstacle vehicle cutting into the lane where the target host vehicle is located and the first position is determined based on the first position of the target host vehicle and the second position of the obstacle vehicle.

[0041] In some optional embodiments, the cut-in point is a position at which the obstacle vehicle enters the lane in which the target host vehicle is located at the second speed. In one optional embodiment, the position of the cut-in point does not need to be calculated, and the motion trajectory of the obstacle vehicle does not need to be predicted. Based on the first position of the target host vehicle and the second position of the obstacle vehicle, a first position distance between the target host vehicle and the obstacle vehicle is determined. Based on the first position distance between the target host vehicle and the obstacle vehicle, a target distance between the cut-in point and the first position is determined.

[0042] In step S104, a driving strategy of the target host vehicle is determined based on the target distance and the first speed of the target host vehicle.

[0043] In the above optional embodiments, the first driving data of the target host vehicle is collected, wherein the first driving data includes the first position and the first speed of the target host vehicle. The second driving data of the obstacle vehicle is collected, wherein the second driving data includes the second position and the second speed of the obstacle vehicle. The obstacle vehicle is a vehicle that is to cut into the lane in which the target host vehicle is located and travels in the same direction as the target host vehicle after cutting in. Based on the first position of the target host vehicle and the second position of the obstacle vehicle, a target distance between the cut-in point at which the obstacle vehicle cuts into the lane in which the target host vehicle is located and the first position is determined. Based on the target distance and the first speed of the target host vehicle, a driving strategy of the target host vehicle is determined. The target distance between the cut-in point at which the obstacle vehicle cuts into the lane in which the target host vehicle is located and the first position of the lane in which the target host vehicle is located is obtained based on the position information of the target host vehicle and the obstacle vehicle. The driving strategy of the target host vehicle is determined according to the target distance and the first speed of the target host vehicle. The determination of the driving strategy does not need to be based on the prediction of the driving trajectory of the obstacle vehicle. Thus, the error in the determination of the strategy caused by inaccurate prediction of the driving trajectory of the obstacle vehicle is avoided, especially in the case where the driving trajectory of the obstacle vehicle is relatively complex. The error in the determination of the strategy caused by inaccurate prediction of the driving trajectory of the obstacle vehicle is avoided. The safety of vehicle driving is improved. The problem that it is difficult to correctly determine the driving strategy of the host vehicle to ensure the safe driving of the vehicle in the related art in the case where the obstacle vehicle is to cut into the lane in which the host vehicle is located is solved.

[0044] In some optional embodiments, the method for determining the target distance between the cut-in point at which the obstacle vehicle cuts into the lane in which the target host vehicle is located and the first position based on the first position of the target host vehicle and the second position of the obstacle vehicle can include the following steps: determining an included angle between a line connecting the first position and the second position and a predetermined direction; in the case where the included angle exceeds a predetermined angle, directly determining the target distance between the cut-in point and the target host vehicle based on the first position and the second position; and in the case where the included angle does not exceed the predetermined angle, determining the target distance between the cut-in point and the first position based on the first position, the second position, and the second speed. In one optional embodiment, the predetermined direction includes multiple directions. For example, the predetermined direction can be the direction of the lane in which the target host vehicle is located, or can be an arbitrary fixed direction, such as the due east direction or the due west direction.

[0045] In the optional embodiment above, the target distance is determined based on different methods according to the different included angle between the line connecting the first position and the second position and the predetermined direction. Thus, the target distance can be accurately obtained, and the driving strategy of the target host vehicle can be accurately determined according to the target distance.

[0046] As some optional embodiments, in the case that the included angle exceeds the predetermined angle, the method of directly determining the target distance between the cut-in point and the target host vehicle based on the first position and the second position can include the following steps: determining a first position distance between the first position and the second position; and determining a component of the first position distance in the lane direction as the target distance.

[0047] In the optional embodiment above, in the case that the included angle exceeds the predetermined angle, it can be approximately considered that the obstacle vehicle vertically cuts into the lane where the target host vehicle is located along the direction perpendicular to the lane where the target host vehicle is located. In this case, the target distance between the cut-in point and the first position where the target host vehicle is located is equal to the component of the first position distance in the lane direction. Based on this method, the target distance in the case that the included angle exceeds the predetermined angle can be accurately obtained, and the driving strategy of the target host vehicle can be accurately determined based on the accurately obtained target distance.

[0048] In some optional embodiments, in the case that the included angle does not exceed the predetermined angle, the target distance between the cut-in point and the first position is determined based on the first position, the second position, and the second speed of the obstacle vehicle, which can include the following steps: determining a second position distance between the first position and the second position; determining a component of the second position distance in the lane direction as a third position distance; determining a time length for the obstacle vehicle to cut into the lane where the target host vehicle is located according to the first position and the second position, and a first speed component of the second speed of the obstacle vehicle in the direction perpendicular to the lane direction; determining a fourth position distance according to a second speed component of the second speed of the obstacle vehicle in the direction parallel to the lane direction and the time length; and determining the target distance according to the third position distance and the fourth position distance.

[0049] In the optional embodiment, when the included angle does not exceed the predetermined angle, it is considered that the obstacle vehicle has the ability to straighten, i.e., the obstacle vehicle has a distance component in the lane direction along the lane where the target host vehicle is located in the time period from the second position to the time point of cutting into the lane where the target host vehicle is located. In this case, the target distance between the cutting-in point and the first position where the target host vehicle is located is equal to the superposition of the distance component of the second position in the lane direction between the first position and the second position (the third position distance) and the distance component in the lane direction of the obstacle vehicle in the time period from the second position to the time point of cutting into the lane where the target host vehicle is located (the fourth position distance). That is, according to the third position distance and the fourth position distance, the target distance can be determined. Based on this method, the target distance when the included angle does not exceed the predetermined angle can be accurately obtained, and the driving strategy of the target host vehicle can be accurately determined based on the accurately obtained target distance.

[0050] In some optional embodiments, based on the target distance and the first speed of the target host vehicle, the method for determining the driving strategy of the target host vehicle can include the following steps: obtaining a first arrival time length of the target host vehicle driving at the first speed to the cutting-in point; obtaining a second arrival time length of the obstacle vehicle driving at the second speed to the cutting-in point; in the case where the first arrival time length is less than the second arrival time length, confirming that the driving strategy of the target host vehicle is overtaking; and in the case where the first arrival time length is greater than the second arrival time length, confirming that the driving strategy of the target host vehicle is yielding.

[0051] In the optional embodiment, in the case where the first arrival time length is less than the second arrival time length, it means that when the target host vehicle drives at the first speed and the obstacle vehicle drives at the second speed, the target host vehicle can arrive at the cutting-in point earlier than the obstacle vehicle, and therefore, the target host vehicle can avoid arriving at the cutting-in point at the same time as the obstacle vehicle by driving at a constant speed or accelerating at the first speed. That is, in the case where the first arrival time length is less than the second arrival time length, the target host vehicle drives in an overtaking mode, which can avoid a collision with the obstacle vehicle, thereby improving the safety of vehicle driving. In the case where the first arrival time length is greater than the second arrival time length, it means that when the target host vehicle drives at the first speed and the obstacle vehicle drives at the second speed, the target host vehicle will arrive at the cutting-in point later than the obstacle vehicle, and therefore, the target host vehicle can avoid arriving at the cutting-in point at the same time as the obstacle vehicle by driving at a constant speed or decelerating at the first speed. That is, in the case where the first arrival time length is greater than the second arrival time length, the target host vehicle drives in a yielding mode, which can avoid a collision with the obstacle vehicle, thereby improving the safety of vehicle driving. Based on the comparison result of the first arrival time length and the second arrival time length, the driving strategy of the target host vehicle is confirmed to be overtaking or yielding, which realizes accurate confirmation of the driving strategy of the target host vehicle and improves the safety of vehicle driving.

[0052] In some optional embodiments, the method for determining the driving strategy of the target host vehicle based on the target distance and the first speed of the target host vehicle can comprise the following steps: determining the first reaction time of the target host vehicle and the second reaction time of the obstacle vehicle in the case that the first arrival time is equal to the second arrival time; obtaining the time difference between the first reaction time and the second reaction time; confirming that the driving strategy of the target host vehicle is overtaking in the case that the time difference is less than a preset time; and confirming that the driving strategy of the target host vehicle is yielding in the case that the time difference is not less than the preset time. In an optional embodiment, the target host vehicle obtains the second position and the second speed of the obstacle vehicle and the second acceleration of the obstacle vehicle by analyzing the continuous video frame images of the obstacle vehicle, and determines the second reaction time of the obstacle vehicle based on the second position, the second speed and the second acceleration. In an optional embodiment, the target host vehicle obtains the first position, the first speed and the first acceleration of the target host vehicle by a sensor, and determines the first reaction time of the target host vehicle according to the first position, the first speed and the first acceleration.

[0053] In the above optional embodiments, in the case that the first arrival time is equal to the second arrival time, it means that the target host vehicle travels at the first speed and the obstacle vehicle travels at the second speed, and the two vehicles will arrive at the cut-in point at the same time, i.e. the two vehicles will collide at the cut-in point. Therefore, the target host vehicle needs to adjust the driving speed to avoid the obstacle vehicle. In the case that the time difference between the first reaction time and the second reaction time is less than a preset time, it means that the target host vehicle may arrive at the cut-in point earlier than the obstacle vehicle even if it travels at a reduced speed, and therefore the target host vehicle adopts the overtaking driving strategy in this case. In the case that the time difference between the first reaction time and the second reaction time is not less than the preset time, it means that the target host vehicle can arrive at the cut-in point later than the obstacle vehicle even if it travels at a reduced speed, and therefore the target host vehicle adopts the yielding driving strategy in this case. Determining the driving strategy of the target host vehicle based on the time difference between the first reaction time and the second reaction time can avoid the target host vehicle and the obstacle vehicle arriving at the cut-in point at the same time, and improves the safety of vehicle driving.

[0054] In some optional embodiments, in the case that the first arrival time is equal to the second arrival time, the method for determining the first reaction time of the target host vehicle can comprise the following steps: determining the first braking distance of the target host vehicle when the target host vehicle reduces from the first speed to a first predetermined speed; determining the first distance difference between the target distance and the first braking distance; and obtaining the first reaction time based on the first speed and the first distance difference. In an optional embodiment, the ratio of the first distance difference to the first speed is the first reaction time. In this way, the first reaction time can be accurately obtained, the target host vehicle determines the driving strategy according to the obtained first reaction time, the accuracy of the driving strategy determined by the target host vehicle is improved, and the safety of vehicle driving is improved.

[0055] In some optional embodiments, in the case where the first arrival time length is equal to the second arrival time length, the method for determining the second reaction time length of the obstacle vehicle can comprise the following steps: determining a second braking distance traveled by the obstacle vehicle from the second speed to the second predetermined speed; determining a fifth position distance between the second position and the cut-in point; determining a second distance difference value between the fifth position distance and the second braking distance; and obtaining the second reaction time length of the obstacle vehicle based on the second speed and the second distance difference value. In an optional embodiment, the ratio of the second distance difference value to the second speed is the second reaction time length. In this way, the second reaction time length can be accurately obtained, so that the target host vehicle determines the driving strategy based on the obtained second reaction time length, improves the accuracy of the driving strategy determined by the target host vehicle, and improves the safety of vehicle driving.

[0056] Based on the above embodiments and optional embodiments, a vehicle driving strategy determination method is provided, which is described in detail below. It should be noted that in this optional embodiment, the target host vehicle is a straight vehicle, the obstacle vehicle is a vehicle driving on a lane other than the lane where the target host vehicle is located, and the vehicle changes from a state of driving in the opposite direction of the target host vehicle to a state of cutting into the lane where the target host vehicle is located. In this optional embodiment, the scenario where the target host vehicle is straight along the lane where the target host vehicle is located and the obstacle vehicle turns around to enter the lane where the target host vehicle is located is taken as an example for description.

[0057] It should be understood that this optional implementation is not only applicable to the scenario where a straight target host vehicle encounters a turning obstacle vehicle, but also applicable to the scenario where the obstacle vehicle and the target host vehicle drive in the same direction and have the intention to cut into the lane where the target host vehicle is located from another lane other than the lane where the target host vehicle is located.

[0058] In the related art, the host vehicle usually predicts the driving trajectory of the obstacle vehicle, and determines the driving strategy of the host vehicle based on the prediction result. However, the obtained driving trajectory usually cannot meet the dynamics constraints of the vehicle, and the accuracy of the prediction result is usually low. When the host vehicle determines the driving strategy of the host vehicle based on the trajectory prediction of the obstacle vehicle, it is easy to make an incorrect driving strategy due to the inaccurate prediction result, and thus vehicle collision occurs. That is, in the related art, in the case where the obstacle vehicle cuts into the lane where the host vehicle is located, it is difficult to correctly determine the driving strategy of the host vehicle to ensure safe driving of the vehicle.

[0059] In view of this, the optional embodiment of the present disclosure provides a vehicle driving strategy determination method, which comprises the following steps: collecting first driving data of a target host vehicle, wherein the first driving data comprises a first position and a first speed of the target host vehicle; collecting second driving data of an obstacle vehicle, wherein the second driving data comprises a second position and a second speed of the obstacle vehicle, the obstacle vehicle being a vehicle that is to cut into a lane where the target host vehicle is located and travels in the same direction as the target host vehicle after cutting in; determining a target distance between a cut-in point at which the obstacle vehicle cuts into the lane where the target host vehicle is located and the first position based on the first position of the target host vehicle and the second position of the obstacle vehicle, wherein the cut-in point at which the obstacle vehicle cuts into the lane where the target host vehicle is located is a position point at which the obstacle vehicle drives into the lane where the target host vehicle is located at the second speed, the position of the cut-in point does not need to be calculated, and the motion trajectory of the obstacle vehicle does not need to be predicted; determining the first position distance between the target host vehicle and the obstacle vehicle based on the first position of the target host vehicle and the second position of the obstacle vehicle; and determining the target distance between the cut-in point at which the obstacle vehicle cuts into the lane where the target host vehicle is located and the first position based on the first position distance between the target host vehicle and the obstacle vehicle; and determining a driving strategy of the target host vehicle based on the target distance and the first speed of the target host vehicle after the target distance between the cut-in point at which the obstacle vehicle cuts into the lane where the target host vehicle is located and the first position is obtained. The target distance between the cut-in point at which the obstacle vehicle cuts into the lane where the target host vehicle is located and the first position in the lane where the target host vehicle is located is obtained based on the position information of the target host vehicle and the obstacle vehicle, the driving strategy of the target host vehicle is determined according to the target distance and the first speed of the target host vehicle, and the determination of the driving strategy does not need to be based on the prediction of the driving trajectory of the obstacle vehicle. Thus, the determination error of the strategy caused by inaccurate prediction of the driving trajectory of the obstacle vehicle is avoided, especially in the case that the driving trajectory of the obstacle vehicle is relatively complex, the determination error of the strategy caused by inaccurate prediction of the driving trajectory of the obstacle vehicle is avoided, the safety of vehicle driving is improved, and the problem that it is difficult to correctly determine the driving strategy of the host vehicle to ensure the safe driving of the vehicle in the related art in the case that the obstacle vehicle is to cut into the lane where the host vehicle is located is solved.

[0060] The vehicle driving strategy determination method comprises the following steps:

[0061] Step 1, the target host vehicle performs target scene recognition.

[0062] In one embodiment, the target host vehicle can determine whether the obstacle vehicle has the intention of turning into the lane where the target host vehicle is located by collecting continuous image frames of the obstacle vehicle, and obtaining the position and speed of the obstacle vehicle at the target time and the position and speed of the obstacle vehicle at a historical time before the target time according to the continuous image frames, and determining whether the obstacle vehicle has the intention of turning into the lane where the target host vehicle is located based on the position of the obstacle vehicle at the target time and the speed of the obstacle vehicle at the continuous times including the target time. For example, it can be determined whether the obstacle vehicle changes from driving in the opposite direction of the target host vehicle to turning driving according to the speed of the obstacle vehicle at the continuous times including the target time, and it can be determined whether the obstacle vehicle drives toward the lane where the target host vehicle is located at the target time according to the speed of the obstacle vehicle at the target time. When the obstacle vehicle turns at the continuous times including the target time and drives toward the lane where the target host vehicle is located at the target time, it is determined that the obstacle vehicle has the intention of turning into the lane where the target host vehicle is located. In the case that the obstacle vehicle has the intention of turning into the lane where the target host vehicle is located, the obstacle vehicle is determined as the target obstacle vehicle to be analyzed. In another embodiment, the target host vehicle can determine whether the obstacle vehicle has the intention of turning into the lane where the target host vehicle is located by collecting an image of the obstacle vehicle, and judging whether the obstacle vehicle has the intention of turning into the lane where the target host vehicle is located according to the indication of the vehicle turn signal in the image, and if so, the obstacle vehicle is determined as the target obstacle vehicle to be analyzed.

[0063] Step 2, the target host vehicle obtains the first position and the first speed of the target host vehicle at the target time by a vehicle-mounted sensor, receiving positioning information sent by a navigation system, etc. The target host vehicle also obtains the perception information of the obstacle vehicle by the aforementioned method of analyzing continuous image frames, wherein the perception information includes the second position and the second speed of the obstacle vehicle at the target time.

[0064] Step 3, according to the first position and the second position, the first position distance S between the target host vehicle and the obstacle vehicle at the target time is obtained, and according to the included angle θ between the line connecting the first position and the second position and the lane direction of the lane where the target host vehicle is located, the target distance S between the turning point of the obstacle vehicle turning into the lane where the target host vehicle is located according to the second speed and the first position of the target host vehicle is determined. new .

[0065] Specifically, the target distance S is obtained according to the following method new :

[0066]

[0067] wherein s old is the longitudinal component of the first position distance S in the lane direction of the lane where the target host vehicle is located, and v s is the longitudinal component of the second speed of the obstacle vehicle in the lane direction of the lane where the target host vehicle is located. In this optional embodiment, the predetermined angle is It should be understood that the predetermined angle is not limited to The predetermined angle may be set to other values ​​as needed.

[0068] Among them, T cut_in The time it takes for the obstacle vehicle to cut into the lane where the target vehicle is located is obtained by the following method: cut_in (equivalent to the second arrival time duration in the aforementioned embodiment where the obstacle vehicle maintains the second speed and travels to the entry point):

[0069]

[0070] Among them, l nearest v is the component of the first position distance between the first position and the second position in the lane direction perpendicular to the lane where the target vehicle is located, l is the lateral component of the second velocity in the lane direction perpendicular to the lane where the target vehicle is located.

[0071] Figure 2 This is a schematic diagram of a scenario in which a straight-moving vehicle encounters a U-turning vehicle according to the second embodiment of the present disclosure. Figure 2 The scene diagram shown is for obtaining the target distance S new The method is further explained:

[0072] Reference Figure 2 As shown, point C is the first position of the target vehicle at the target time, point A is the second position of the obstacle vehicle at the target time, and point D1 is the entry point of the obstacle vehicle into the lane where the target vehicle is located at the second speed at the target time.

[0073] The first position distance S is equivalent to the distance CA between the first position C and the second position A; the angle θ between the line connecting the first position and the second position and the lane direction of the target vehicle is equivalent to the angle between the line connecting C and A and the line connecting C and D1; the target distance S new It is equivalent to the distance CD1 between the first position C and the cutting point D1.

[0074] Calculate target distance S new When the target distance CD1 is obtained, it is not necessary to calculate the position of the entry point D1. Instead, the distance CA between the first position C and the second position A is calculated, and the target distance CD1 is obtained based on the distance CA.

[0075] exist Figure 2 In the scenario shown, the angle θ between the line connecting C and A and the line connecting C and D1 is greater than In this case, without considering the longitudinal component of the second speed of the obstacle vehicle along the lane direction of the target host vehicle's lane, it is approximately considered that the obstacle vehicle drives into the target host vehicle's lane along a direction perpendicular to the target host vehicle's lane. The longitudinal component CD1 of the distance CA along the lane direction of the target host vehicle's lane (equivalent to the longitudinal component s of the first position distance S along the lane direction of the target host vehicle's lane) is calculated, and the longitudinal component CD1 is determined as the target distance S between the first position C and the cut-in point D1 of the target host vehicle's lane. old new new old

[0076] Figure 3 is a schematic diagram of a scenario in which a straight-ahead vehicle encounters a U-turn vehicle according to a third embodiment of the present disclosure. The method of obtaining the target distance S new is further described below in conjunction with the schematic diagram of the scenario shown in Figure 3

[0077] Referring to Figure 3 , point E is the first position of the target host vehicle at a target time, point B is the second position of the obstacle vehicle at the target time, point D2 is the cut-in point at which the obstacle vehicle cuts into the target host vehicle's lane according to the second speed of the obstacle vehicle at the target time, and point D3 is the vertical projection point of point B on the target host vehicle's lane.

[0078] The first position distance S is equivalent to the distance EB between the first position E and the second position B; the included angle θ between the line connecting the first position and the second position and the lane direction of the target host vehicle's lane is equivalent to the included angle between the line connecting E and B and the line connecting E and D2; and the target distance S new is equivalent to the distance ED2 between the first position E and the cut-in point D2.

[0079] When calculating the target distance S new , the position of the cut-in point D1 does not need to be calculated, but the distance EB between the first position E and the second position B is calculated, and the target distance ED2 is obtained according to the distance EB and the second speed. This is described in detail below.

[0080] In the scenario shown in Figure 3 , the included angle θ between the line connecting E and B and the line connecting E and D2 is less than In this case, it is indicated that the obstacle vehicle already has the ability to drive along the lane direction of the target host vehicle's lane, and the longitudinal distance component of the obstacle vehicle along the lane direction of the target host vehicle's lane needs to be considered during the period in which the obstacle vehicle moves from the second position B to reach the target host vehicle's lane.

[0081] The method of calculating the longitudinal component includes the following steps:

[0082] ​​​​​The time T taken by the obstacle vehicle to cut into the lane where the target host vehicle is located is obtained by the following method cut_in :

[0083]

[0084] wherein l nearest is the lateral component of the first position distance between the first position and the second position in the lane direction perpendicular to the lane where the target host vehicle is located, l nearest is equivalent to the distance BD3 between B and D3. Wherein v l is the lateral component of the second speed in the lane direction perpendicular to the lane where the target host vehicle is located.

[0085] According to the time T taken by the obstacle vehicle to cut into the lane where the target host vehicle is located cut_in and the longitudinal component v s of the second speed of the obstacle vehicle in the lane direction of the lane where the target host vehicle is located, the distance component of the obstacle vehicle in the lane direction of the lane where the target host vehicle is located within the time period taken by the obstacle vehicle to cut into the lane where the target host vehicle is located can be calculated, and the distance component is equivalent to the distance D3D2 between the D3 point and the D2 point.

[0086] According to the longitudinal component ED3 of the distance EB in the lane direction of the lane where the target host vehicle is located (equivalent to the longitudinal component s old of the first position distance S in the lane direction of the lane where the target host vehicle is located), and the distance component D3D2 in the lane direction of the lane where the target host vehicle is located, the target distance ED2 between the first position E and the cut-in point D2 can be calculated.

[0087] S new = ED2 = ED3 + D3D2 = s old + v s * T cut_in

[0088] wherein v s is the longitudinal component of the second speed of the obstacle vehicle in the lane direction of the lane where the target host vehicle is located.

[0089] Step 4, determining the driving strategy of the target host vehicle according to the time of the target host vehicle and the obstacle vehicle reaching the cut-in point.

[0090] Specifically, the first arrival time T1 of the target host vehicle reaching the cut-in point is obtained by the following method:

[0091]

[0092] wherein v1 is the first speed of the target host vehicle.

[0093] Continuing to refer to Figure 2 , in Figure 2In the scenario shown, the angle θ between the line connecting the first position C and the second position A and the lane direction of the lane where the target host vehicle is located exceeds a predetermined angle. In this case, the first arrival time T1 of the target host vehicle to the cut-in point D1 can be obtained by the following method:

[0094]

[0095] With reference to the foregoing Figure 3 In the scenario shown, Figure 3 In the scenario shown, the angle θ between the line connecting the first position E and the second position B and the lane direction of the lane where the target host vehicle is located does not exceed a predetermined angle. The first arrival time T1 of the target host vehicle to the cut-in point D2 can be obtained by the following method:

[0096]

[0097] When T1>T cut_in , it is determined that the driving strategy of the target host vehicle is to let the vehicle pass.

[0098] When T1<T cut_in , it is determined that the driving strategy of the target host vehicle is to overtake.

[0099] When T1=T cut_in , the driving strategy of the target host vehicle is determined according to the following method:

[0100] The first reaction time ttr adc of the target host vehicle is obtained according to the following method:

[0101]

[0102] wherein S1 is the first braking distance, v2 is the first preset speed corresponding to the target host vehicle, and a1 is the first acceleration of the target host vehicle. The value of v2 can be zero. The value of a1 is less than zero.

[0103] The second reaction time ttr obs of the obstacle vehicle is obtained according to the following method:

[0104]

[0105] wherein l1 is the second braking distance, v3 is the second preset speed corresponding to the obstacle vehicle, and a2 is the second acceleration of the obstacle vehicle. The value of v3 can be zero. The value of a2 is less than zero.

[0106] When ttr obsin the case that the distance is greater than 0, it indicates that the braking distance of the obstacle vehicle is less than the distance from the second position to the target host vehicle, i.e., the braking distance of the obstacle vehicle is less than the transverse component I of the first position distance between the first position and the second position in the lane direction perpendicular to the lane where the target host vehicle is located nearest i.e., when the obstacle vehicle travels at the second acceleration a2, its speed v l may be reduced to v3 before cutting into the lane where the target host vehicle is located, and thus the obstacle vehicle can avoid collision with the target host vehicle by braking deceleration.

[0107] in the case that ttr adc -ttr obs in the case that the distance is greater than threshold, it is determined that the driving strategy of the target host vehicle is overtaking, otherwise it is determined that the driving strategy of the target host vehicle is yielding, wherein threshold is a preset time length.

[0108] In this optional embodiment, when the angle between the line connecting the first position where the target host vehicle is located and the second position where the obstacle vehicle is located and the lane direction of the lane where the target host vehicle is located exceeds a predetermined angle, it is approximately considered that the obstacle vehicle cuts into the lane where the target host vehicle is located along a direction perpendicular to the lane where the target host vehicle is located, and the longitudinal component of the first position distance between the first position and the second position in the lane direction of the lane where the target host vehicle is located is determined as the target distance; when the angle between the line connecting the first position where the target host vehicle is located and the second position where the obstacle vehicle is located and the lane direction of the lane where the target host vehicle is located does not exceed the predetermined angle, it indicates that the obstacle vehicle has the ability to travel along the lane direction of the lane where the target host vehicle is located, and when calculating the target distance, the driving distance of the obstacle vehicle in the lane direction of the lane where the target host vehicle is located within the time period from the second position to the time of cutting into the lane where the target host vehicle is located is taken into account, and the driving distance and the longitudinal component of the first position distance between the first position and the second position in the lane direction of the lane where the target host vehicle is located are superimposed to obtain the target distance. In the case that the angle between the line connecting the first position where the target host vehicle is located and the second position where the obstacle vehicle is located and the lane direction of the lane where the target host vehicle is located exceeds and does not exceed the predetermined angle, different target distance calculation models are respectively constructed based on the method of linear extrapolation, so that the target distance can be accurately obtained, the driving measurement is determined based on the target distance, the accuracy of determining the driving strategy is improved, the problem of incorrect determination of the driving strategy of the target host vehicle caused by the predicted trajectory of the obstacle vehicle not meeting the dynamics constraint is avoided, the risk of vehicle collision is reduced, and the vehicle driving safety is improved. Determining the driving strategy of the target host vehicle according to the reaction time of the vehicle is based on the position and speed information of the target host vehicle and the obstacle vehicle at the target time, and does not depend on the trajectory prediction of the obstacle vehicle, so that the problem of incorrect determination of the driving strategy of the target host vehicle caused by inaccurate trajectory prediction is avoided, and the safety of vehicle driving is improved.

[0109] Figure 4 is a framework diagram of a vehicle driving strategy determination apparatus according to an embodiment of the present disclosure. Referring to Figure 4 , the vehicle driving strategy determination apparatus includes a first acquisition module 401, a second acquisition module 402, a first determination module 403, and a second determination module 404. Details are described below.

[0110] The first acquisition module 401 is configured to acquire first driving data of a target host vehicle, where the first driving data includes a first position and a first speed of the target host vehicle. The second acquisition module 402, connected to the first acquisition module 401, is configured to acquire second driving data of an obstacle vehicle, where the second driving data includes a second position and a second speed of the obstacle vehicle, and the obstacle vehicle is a vehicle that is to cut into a lane where the target host vehicle is located and travel in the same direction as the target host vehicle after cutting in. The first determination module 403, connected to the second acquisition module 402, is configured to determine a target distance between a cut-in point of the obstacle vehicle cutting into the lane where the target host vehicle is located and the first position based on the first position of the target host vehicle and the second position of the obstacle vehicle. The second determination module 404, connected to the first determination module 403, is configured to determine a driving strategy of the target host vehicle based on the target distance and the first speed of the target host vehicle.

[0111] It should be noted that the first acquisition module 401, the second acquisition module 402, the first determination module 403, and the second determination module 404 correspond to steps S101 to S104 in the vehicle driving strategy determination method respectively, and the multiple modules have the same instances and application scenarios as the corresponding steps, but are not limited to the content disclosed in the above embodiments.

[0112] In some optional embodiments, the first determination module includes a first determination unit configured to determine an included angle between a line connecting the first position and the second position and a predetermined direction of the lane, a second determination unit configured to determine the target distance between the cut-in point and the target host vehicle based on the first position and the second position directly in a case where the included angle exceeds a predetermined angle, and a third determination unit configured to determine the target distance between the cut-in point and the first position based on the first position, the second position, and the second speed in a case where the included angle does not exceed the predetermined angle.

[0113] In some optional embodiments, the second determination unit includes a first determination sub-unit configured to determine a first position distance between the first position and the second position, and a second determination sub-unit configured to determine a component of the first position distance in the direction of the lane as the target distance.

[0114] In some optional embodiments, the third determining unit comprises: a third determining sub-unit, configured to determine a second position distance between the first position and the second position; a fourth determining sub-unit, configured to determine a third position distance as a component of the second position distance in a lane direction; a fifth determining sub-unit, configured to determine a time length for the obstacle vehicle to cut into the lane where the target host vehicle is located according to the first position and the second position, and a first speed component of the second speed of the obstacle vehicle in a direction perpendicular to the lane direction; a sixth determining sub-unit, configured to determine a fourth position distance according to a second speed component of the second speed of the obstacle vehicle in a direction parallel to the lane direction, and the time length; and a seventh determining sub-unit, configured to determine the target distance according to the third position distance and the fourth position distance.

[0115] In some optional embodiments, the second determining module comprises: a first obtaining unit, configured to obtain a first arrival time length for the target host vehicle to travel at the first speed to the cut-in point; a second obtaining unit, configured to obtain a second arrival time length for the obstacle vehicle to travel at the second speed to the cut-in point; a fourth determining unit, configured to determine that the travel strategy of the target host vehicle is to overtake in a case where the first arrival time length is less than the second arrival time length; and a fifth determining unit, configured to determine that the travel strategy of the target host vehicle is to yield in a case where the first arrival time length is greater than the second arrival time length.

[0116] In some optional embodiments, the second determining module comprises: a sixth determining unit, configured to determine a first reaction time length of the target host vehicle and a second reaction time length of the obstacle vehicle in a case where the first arrival time length is equal to the second arrival time length; a third obtaining unit, configured to obtain a time difference value of the first reaction time length and the second reaction time length; a fourth obtaining unit, configured to determine that the travel strategy of the target host vehicle is to overtake in a case where the time difference value is less than a preset time length, and determine that the travel strategy of the target host vehicle is to yield in a case where the time difference value is not less than the preset time length.

[0117] In some optional embodiments, the sixth determining unit comprises: an eighth determining sub-unit, configured to determine a first braking distance traveled by the target host vehicle when the first speed is reduced to a first predetermined speed; a ninth determining sub-unit, configured to determine a first distance difference value between the target distance and the first braking distance; and a first obtaining sub-unit, configured to obtain the first reaction time length based on the first speed and the first distance difference value.

[0118] In some optional embodiments, the sixth determining unit comprises: a tenth determining sub-unit, configured to determine a second braking distance traveled by the obstacle vehicle when the second speed is reduced to a second predetermined speed; an eleventh determining sub-unit, configured to determine a fifth position distance between the second position and the cut-in point; a thirteenth determining sub-unit, configured to determine a second distance difference value between the fifth position distance and the second braking distance; and a second obtaining sub-unit, configured to obtain the second reaction time length of the obstacle vehicle based on the second speed and the second distance difference value.

[0119] According to embodiments of the present disclosure, the present disclosure also provides an electronic device.

[0120] Figure 5 A schematic block diagram of an example electronic device 500 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptops, desktops, tablets, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown here, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the present disclosure described and / or claimed in this document.

[0121] As shown in Figure 5 The electronic device 500 includes a computing unit 501 that can perform various appropriate actions and processes in accordance with a computer program stored in a read-only memory (ROM) 502 or a computer program loaded from a storage unit 505 into a random access memory (RAM) 503. Various programs and data required for the operation of the electronic device 500 can also be stored in the RAM 503. The computing unit 501, the ROM 502, and the RAM 503 are connected to each other through a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0122] Various components in the electronic device 500 are connected to the I / O interface 505, including an input unit 506, such as a keyboard, a mouse, etc.; an output unit 504, such as various types of displays, speakers, etc.; a storage unit 504, such as a magnetic disk, an optical disk, etc.; and a communication unit 509, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 509 allows the electronic device 500 to exchange information / data with other devices through a computer network, such as the Internet, and / or various telecommunication networks.

[0123] The computing unit 501 can be various general and / or special purpose processing components with processing and computing capabilities. Some examples of the computing unit 501 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, and the like. The computing unit 401 performs various methods and processes described above, such as the model inference acceleration method. For example, in some embodiments, the model inference acceleration method can be implemented as a computer software program tangibly embodied in a machine-readable medium, such as the storage unit 504. In some embodiments, part or all of the computer program can be loaded and / or installed onto the device 500 via the ROM 502 and / or the communication unit 509. When the computer program is loaded onto the RAM 503 and executed by the computing unit 501, one or more steps of the model inference acceleration method described above can be performed. Alternatively, in other embodiments, the computing unit 501 can be configured to perform the model inference acceleration method by any other appropriate means, such as by means of firmware.

[0124] The present disclosure also provides a non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the method of any one of the above.

[0125] The present disclosure also provides a computer program product comprising a computer program which, when executed by a processor, implements the method of any one of the above.

[0126] Various implementations of the systems and techniques described above can be realized in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a programmable logic device (PLD), a computer hardware, firmware, software, and / or combinations thereof. These various implementations can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0127] Program code for carrying out methods of the present disclosure can be written in any combination of one or more programming languages. The program code can be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the program code, when executed by the processor or controller, produces the functions / operations specified in the flowcharts and / or block diagrams. The program code can be executed entirely on a machine, partially on a machine, partially on a machine as a standalone software package, or entirely on a remote machine or server.

[0128] In the context of the present disclosure, a machine-readable medium can be a tangible medium that contains or stores a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include but is not limited to an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the machine-readable storage medium will include one or more lines of electrical connections, portable computer disks, hard disk drives, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or Flash memory), optical fibers, portable compact disc read-only memories (CD-ROMs), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0129] To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0130] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0131] The computer system can include clients and servers. This relationship can be. The servers are typically remote from the clients with the interactions between them occurring over a communication network. The relationship between client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The servers can be cloud servers, servers of a distributed system, or servers incorporating blockchain.

[0132] It should be understood that the steps shown in the various forms above can be reordered, added to, or removed. For example, the steps described in the present disclosure can be performed in parallel, in series, or in a different order, as long as the desired results of the present disclosure are achieved, and the present disclosure is not limited in this regard.

[0133] The specific embodiments described above are not intended to be limiting, and persons skilled in the art will appreciate that various modifications, combinations, sub-combinations and alternatives can be made to the specific embodiments without departing from the spirit and principles of the disclosure. Any further modifications, equivalents and / or alternatives thereof are also encompassed within the scope of the present disclosure.

Claims

1. A method for determining a driving strategy of a target host vehicle, comprising: collecting first driving data of the target host vehicle, wherein the first driving data comprises a first position and a first speed of the target host vehicle; collecting second driving data of an obstacle vehicle, wherein the second driving data comprises a second position and a second speed of the obstacle vehicle, the obstacle vehicle being a vehicle that cuts into a lane where the target host vehicle is located and travels in the same direction as the target host vehicle after cutting in; determining a target distance between a cutting-in point of the obstacle vehicle cutting into the lane where the target host vehicle is located and the first position of the target host vehicle based on the first position of the target host vehicle and the second position of the obstacle vehicle; determining the driving strategy of the target host vehicle based on the target distance and the first speed of the target host vehicle by comparing a time length for the obstacle vehicle to cut into the lane where the target host vehicle is located and a time length for the target host vehicle to reach the cutting-in point; wherein the determining the target distance between the cutting-in point of the obstacle vehicle cutting into the lane where the target host vehicle is located and the first position of the target host vehicle based on the first position of the target host vehicle and the second position of the obstacle vehicle comprises: determining an included angle between a line connecting the first position and the second position and a predetermined direction, wherein the predetermined direction is a lane direction of the lane where the target host vehicle is located; in a case where the included angle exceeds a predetermined angle, directly determining the target distance between the cutting-in point and the target host vehicle based on the first position and the second position; in a case where the included angle does not exceed the predetermined angle, determining the target distance between the cutting-in point and the first position based on the first position, the second position, and the second speed; the directly determining the target distance between the cutting-in point and the target host vehicle based on the first position and the second position in the case where the included angle exceeds the predetermined angle comprises: determining a first position distance between the first position and the second position; determining a component of the first position distance in the lane direction as the target distance; the determining the target distance between the cutting-in point and the first position based on the first position, the second position, and the second speed in the case where the included angle does not exceed the predetermined angle comprises: determining a second position distance between the first position and the second position; determining a third position distance as a component of the second position distance in the lane direction; determining a time length for the obstacle vehicle to cut into the lane where the target host vehicle is located according to the first position and the second position and a first speed component of the second speed in a direction perpendicular to the lane direction; determining a fourth position distance according to a second speed component of the second speed in a direction parallel to the lane direction and the time length; determining the target distance according to the third position distance and the fourth position distance; the determining the driving strategy of the target host vehicle based on the target distance and the first speed of the target host vehicle comprises: obtaining a first arrival time length for the target host vehicle to travel at the first speed to the cutting-in point; ​ ​ ​ ​ ​ 2. The method of claim 1, wherein, ​ ​ ​ 3. The method of claim 1, wherein, ​ ​ ​ ​ ​ ​ 4. The method of claim 1, wherein, ​ ​ acquire a second arrival time length for the obstacle vehicle to travel at the second speed to the cut-in point; in a case where the first arrival time length is less than the second arrival time length, determine that the driving strategy of the target host vehicle is to overtake; in a case where the first arrival time length is greater than the second arrival time length, determine that the driving strategy of the target host vehicle is to give way.

5. The method of claim 4, wherein, the driving strategy of the target host vehicle is determined based on the target distance and a first speed of the target host vehicle, including: in a case where the first arrival time length is equal to the second arrival time length, determine a first reaction time length of the target host vehicle and a second reaction time length of the obstacle vehicle; acquire a time difference value of the first reaction time length and the second reaction time length; in a case where the time difference value is less than a preset time length, determine that the driving strategy of the target host vehicle is to overtake; in a case where the time difference value is not less than the preset time length, determine that the driving strategy of the target host vehicle is to give way.

6. The method of claim 5, wherein, the first reaction time length of the target host vehicle is determined in a case where the first arrival time length is equal to the second arrival time length, including: determine a first braking distance of the target host vehicle when the first speed is reduced to a first predetermined speed; determine a first distance difference value between the target distance and the first braking distance; obtain the first reaction time length based on the first speed and the first distance difference value.

7. The method of claim 5, wherein, the second reaction time length of the obstacle vehicle is determined in a case where the first arrival time length is equal to the second arrival time length, including: determine a second braking distance of the obstacle vehicle when the second speed is reduced to a second predetermined speed; determine a fifth position distance between the second position and the cut-in point; determine a second distance difference value between the fifth position distance and the second braking distance; obtain the second reaction time length of the obstacle vehicle based on the second speed and the second distance difference value.

8. A vehicle driving strategy determination apparatus, comprising: a first acquisition module configured to acquire first driving data of a target host vehicle, wherein the first driving data comprises a first position and a first speed of the target host vehicle; a second acquisition module configured to acquire second driving data of an obstacle vehicle, wherein the second driving data comprises a second position and a second speed of the obstacle vehicle, the obstacle vehicle being a vehicle that is to cut into a lane in which the target host vehicle is located and travel in the same direction as the target host vehicle after cutting in; a first determination module configured to determine, based on the first position of the target host vehicle and the second position of the obstacle vehicle, a target distance between a cut-in point at which the obstacle vehicle cuts into the lane in which the target host vehicle is located and the first position; a second determination module configured to determine, based on the target distance and the first speed of the target host vehicle, a driving strategy of the target host vehicle by comparing a time length for the obstacle vehicle to cut into the lane in which the target host vehicle is located and a time length for the target host vehicle to reach the cut-in point. The first determining module comprises: a first determining unit configured to determine an included angle between a line connecting the first position and the second position and a predetermined direction of the lane, wherein the predetermined direction is a lane direction of the lane where the target host vehicle is located; a second determining unit configured to determine a target distance between the cut-in point and the target host vehicle based on the first position and the second position directly in a case where the included angle exceeds a predetermined angle; and a third determining unit configured to determine a target distance between the cut-in point and the first position based on the first position, the second position, and the second speed in a case where the included angle does not exceed the predetermined angle.

9. The apparatus of claim 8, wherein, The second determining unit comprises: a first determining sub-unit configured to determine a first position distance between the first position and the second position; a second determining sub-unit configured to determine a component of the first position distance in the lane direction as the target distance.

10. The apparatus of claim 8, wherein, The third determining unit comprises: a third determining sub-unit configured to determine a second position distance between the first position and the second position; a fourth determining sub-unit configured to determine a component of the second position distance in the lane direction as a third position distance; a fifth determining sub-unit configured to determine a time length for the obstacle vehicle to cut into the lane where the target host vehicle is located according to the first position and the second position and a first speed component of the second speed perpendicular to the lane direction; a sixth determining sub-unit configured to determine a fourth position distance according to a second speed component of the second speed parallel to the lane direction and the time length; a seventh determining sub-unit configured to determine the target distance according to the third position distance and the fourth position distance.

11. The apparatus of claim 8, wherein, The second determining module comprises: a first obtaining unit configured to obtain a first arrival time length for the target host vehicle to travel to the cut-in point at the first speed; a second obtaining unit configured to obtain a second arrival time length for the obstacle vehicle to travel to the cut-in point at the second speed; a fourth determining unit configured to confirm that a driving strategy of the target host vehicle is overtaking in a case where the first arrival time length is less than the second arrival time length; a fifth determining unit configured to confirm that the driving strategy of the target host vehicle is yielding in a case where the first arrival time length is greater than the second arrival time length.

12. The apparatus of claim 11, wherein, The second determining module comprises: a sixth determining unit configured to determine a first reaction time length of the target host vehicle and a second reaction time length of the obstacle vehicle in a case where the first arrival time length is equal to the second arrival time length; a third obtaining unit configured to obtain a time difference value of the first reaction time length and the second reaction time length; a fourth obtaining unit configured to confirm that the driving strategy of the target host vehicle is overtaking in a case where the time difference value is less than a preset time length, and confirm that the driving strategy of the target host vehicle is yielding in a case where the time difference value is not less than the preset time length.

13. The apparatus of claim 12, wherein, The sixth determining unit comprises: An eighth determining subunit is configured to determine a first braking distance traveled by the target host vehicle when the first speed is reduced to a first predetermined speed; A ninth determining subunit is configured to determine a first distance difference between the target distance and the first braking distance; A first obtaining subunit is configured to obtain the first reaction duration based on the first speed and the first distance difference.

14. The apparatus of claim 12, wherein, The sixth determining unit comprises: A tenth determining subunit is configured to determine a second braking distance traveled by the obstacle vehicle when the second speed is reduced to a second predetermined speed; An eleventh determining subunit is configured to determine a fifth position distance between the second position and the cut-in point; A thirteenth determining subunit is configured to determine a second distance difference between the fifth position distance and the second braking distance; A second obtaining subunit is configured to obtain a second reaction duration of the obstacle vehicle based on the second speed and the second distance difference.

15. An electronic device, comprising: at least one processor; and a memory connected with the at least one processor in communication; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1 to 7.

16. A non-transitory computer readable storage medium having stored thereon computer instructions, wherein, The computer instructions are used to enable the computer to perform the method of any one of claims 1 to 7.

17. A computer program product comprising a computer program which, when executed by a processor, implements the method of any one of claims 1 to 7.

Images