Vehicle steering anti-scratching method and related device, storage medium and program

Abstract

The application provides a vehicle steering anti-collision method and related device, storage medium and program, which can be applied to an automatic driving domain controller of a target vehicle. The method comprises the following steps: determining a reference trajectory scene according to historical driving images of the target vehicle; determining X reference position points in the reference trajectory scene; performing relevant operations on the X reference position points, obtaining Y key position points from the X reference position points, and a plurality of standard vehicle body postures corresponding to each key position point in the Y key position points; and performing relevant operations when detecting that the target vehicle enters the reference trajectory scene, completing anti-collision safety detection and reminding of the target vehicle at a detection area at a preset distance from the Y key position points, so that the target vehicle does not have a collision event when performing a continuous steering operation. In this way, the user's adjustable space for the vehicle is avoided to be too small due to too late reminding, and the user's use experience is improved.

Description

Technical Field

[0001] The present application belongs to the general data processing technology field of the Internet industry, and specifically relates to a vehicle steering anti-scratch method and related devices, storage media and programs. Background Art

[0002] In some scenarios, when a user is steering a vehicle, limited steering space and other factors can cause the vehicle to scrape against a wall at certain angles, causing damage. To address this issue, existing technologies have added a scratch prevention reminder function. When the user's vehicle approaches a wall, the car will remind the user that the current distance is too close. However, since the distance between the user's vehicle and the wall is already very close, the user has very little room to adjust the vehicle's position. There is still a high possibility of scratching during adjustments, affecting the user experience. Summary of the Invention

[0003] The present application provides a vehicle steering anti-scratch method and related devices in order to solve the above problems and optimize the user experience.

[0004] In a first aspect, an embodiment of the present application provides a vehicle steering anti-scratch method, which is applied to an autonomous driving domain controller of an autonomous driving system of a target vehicle, the autonomous driving system including the autonomous driving domain controller and a sensor module disposed on the body of the target vehicle, the autonomous driving domain controller being communicatively connected to the sensor module, the method comprising:

[0005] Determining a reference trajectory scene passed by the target vehicle based on the historical driving image of the target vehicle, the reference trajectory scene being a trajectory scene passed by the target vehicle more than a preset number of times in the historical driving image, the reference trajectory scene including a first lane and a second lane, the first lane and the second lane intersecting;

[0006] Determine X reference position points in the reference trajectory scene, where the reference position points are starting positions of the target vehicle performing a continuous turning operation in the first lane toward the second lane, where X is a positive integer;

[0007] Perform the following operations a, b, and c for the X reference positions:

[0008] a. Determine N body postures of the target vehicle at the currently processed reference position, where the body posture indicates the angle between a straight line on which the target vehicle's body lies and a straight line on which a target wall lies. The target wall is a wall supported by the first lane in the direction indicated by the head of the target vehicle when performing a continuous steering maneuver;

[0009] b. determining N steering fault tolerances of the target vehicle at the current processing reference position point under the constraint of the N body postures, the steering fault tolerance being used to indicate the difficulty level of the target vehicle in performing a steering operation at the current processing reference position point, wherein N is a positive integer;

[0010] c. determining whether there is a steering fault tolerance greater than a preset fault tolerance in the N steering fault tolerances;

[0011] If yes, marking the current processing reference position point as a key position point; and selecting M steering fault tolerances greater than the preset fault tolerance from the N steering fault tolerances, and determining M standard body postures corresponding to the M steering fault tolerances, wherein M is a positive integer and M is less than or equal to N;

[0012] If no, continue to process the next reference position point until all X reference position points are processed to obtain Y key position points, wherein Y is an integer and Y is less than or equal to X;

[0013] When the target vehicle is detected to enter the reference trajectory scene, the following operations d, e, f, g and h are performed:

[0014] d. obtaining a detection position point when the target vehicle reaches a detection area associated with the Y key position points and a first body posture when the target vehicle reaches the detection area, the detection area being located between the Y key position points and a trajectory starting point, the trajectory starting point being a position point when the target vehicle enters the reference trajectory scene;

[0015] e. determining Y probability values of the target vehicle reaching the Y key position points according to the detection position point and the first body posture, and marking a key position point with the largest probability value as a target key position point;

[0016] f. determining a second body posture of the target vehicle at the target key position point according to the detection position point, the first body posture and the target key position point;

[0017] g. obtaining a plurality of standard body postures corresponding to the target key position point;

[0018] h. if the second body posture is not included in the plurality of standard body postures, outputting an auxiliary voice, the auxiliary voice being used to instruct a user to adjust a driving route of the target vehicle so that the target vehicle does not have a scraping event when performing a continuous steering operation to enter the second lane.

[0019] In a second aspect, the embodiments of the present application provide a vehicle steering anti-collision device, which is applied to an automatic driving domain controller of an automatic driving system of a target vehicle, the automatic driving system comprising the automatic driving domain controller and a sensor module arranged on a vehicle body of the target vehicle, the automatic driving domain controller being in communication connection with the sensor module, and the device comprising:

[0020] a first determining unit configured to determine a reference trajectory scene passed by the target vehicle according to historical driving images of the target vehicle, the reference trajectory scene being a trajectory scene in the historical driving images, a number of times of passing through the trajectory scene by the target vehicle being greater than a preset number of times, the reference trajectory scene comprising a first lane and a second lane, and the first lane and the second lane intersecting;

[0021] a second determining unit configured to determine X reference position points in the reference trajectory scene, the reference position points being start position points of the target vehicle performing continuous steering operations on the first lane to drive to the second lane, wherein X is a positive integer;

[0022] a first executing unit configured to perform operations a, b and c on the X reference position points as follows:

[0023] a, determining N vehicle body postures of the target vehicle at a currently processed reference position point, the vehicle body posture being used to indicate an included angle between a straight line where a vehicle body of the target vehicle is located and a straight line where a target wall is located, the target wall being a wall borne by the first lane in a direction where a vehicle head of the target vehicle points when performing the continuous steering operations;

[0024] b, determining N steering fault tolerances of the target vehicle at the currently processed reference position point under constraints of the N vehicle body postures, the steering fault tolerance being used to indicate a degree of difficulty of the target vehicle performing a steering operation at the currently processed reference position point, wherein N is a positive integer;

[0025] c, judging whether there is a steering fault tolerance greater than a preset fault tolerance in the N steering fault tolerances;

[0026] if yes, marking the currently processed reference position point as a key position point, and screening M steering fault tolerances greater than the preset fault tolerance from the N steering fault tolerances, and determining M standard vehicle body postures corresponding to the M steering fault tolerances, wherein M is a positive integer and M is less than or equal to N;

[0027] if no, continuously processing a next reference position point until all the X reference position points are processed to obtain Y key position points, wherein Y is an integer and Y is less than or equal to X;

[0028] The second execution unit is configured to perform operations d, e, f, g and h when it is detected that the target vehicle enters the reference trajectory scenario.

[0029] d. obtaining a detection position point when the target vehicle reaches a detection area associated with the Y key position points and a first vehicle body pose when the target vehicle reaches the detection area, the detection area being located between the Y key position points and a trajectory starting point, the trajectory starting point being a position point when the target vehicle enters the reference trajectory scenario;

[0030] e. determining Y probability values of the target vehicle reaching the Y key position points according to the detection position point and the first vehicle body pose, and marking a key position point with the largest probability value as a target key position point;

[0031] f. determining a second vehicle body pose of the target vehicle at the target key position point according to the detection position point, the first vehicle body pose and the target key position point;

[0032] g. obtaining a plurality of standard vehicle body poses corresponding to the target key position point;

[0033] h. if the second vehicle body pose is not included in the plurality of standard vehicle body poses, outputting an auxiliary voice, the auxiliary voice being used to instruct a user to adjust a driving route of the target vehicle, so that the target vehicle does not have a scraping event when performing a continuous steering operation to enter the second lane.

[0034] In a third aspect, an electronic device is provided, including a processor, a memory, and one or more programs stored in the memory and configured to be executed by the processor, the program including instructions for performing the steps in the first aspect.

[0035] In a fourth aspect, a computer readable storage medium is provided, which stores a computer program / instructions, the computer program / instructions being executed by a processor to implement the steps in the first aspect.

[0036] In a fifth aspect, a computer program product is provided, which includes a non-transitory computer readable storage medium storing a computer program, the computer program being operable to cause a computer to perform some or all of the steps described in the first aspect.

[0037] It can be seen that, in the embodiment of the application, the autonomous driving domain controller first determines the reference trajectory scene frequently passed by the target vehicle according to the historical driving image of the target vehicle, then determines X starting points, i.e., reference position points, of the target vehicle performing the steering operation in the scene, and then processes the X reference position points to obtain Y key position points with low difficulty in performing the steering operation and the corresponding standard vehicle body posture; when the target vehicle actually passes through the reference trajectory scene, the autonomous driving domain controller performs the steering auxiliary detection function: first, the detection position point and the first vehicle body posture of the target vehicle when reaching the detection area are obtained, and then the key position point most likely to be reached by the target vehicle, i.e., the target key position point, and the second vehicle body posture when reaching the target key position point are determined according to the position point and the first vehicle body posture at this time; if the second vehicle body posture is not included in the standard vehicle body posture corresponding to the target key position point, it indicates that the difficulty of the target vehicle performing the steering operation at the target key position point is high at this time, and the auxiliary voice is output at this time to assist the user in adjusting the driving route, so as to safely perform the steering operation and avoid the occurrence of the scratching event. In this way, the time of the anti-scratching reminder can be advanced, the user's adjustable space for the vehicle is avoided to be too small due to the too late reminder, and the output auxiliary voice can assist the user in adjusting the vehicle, thereby optimizing the user's use experience. BRIEF DESCRIPTION OF DRAWINGS

[0038] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or the prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0039] Figure 1 is a structural block diagram of an autonomous driving system provided by an embodiment of the present application;

[0040] Figure 2 is a flowchart of a vehicle steering anti-scratching method provided by an embodiment of the present application;

[0041] Figure 3a is an example diagram of a reference trajectory scene provided by an embodiment of the present application;

[0042] Figure 3b is an example diagram of another reference trajectory scene provided by an embodiment of the present application;

[0043] Figure 3c is an example diagram of another reference trajectory scene provided by an embodiment of the present application;

[0044] Figure 3d is an example diagram of another reference trajectory scene provided by an embodiment of the present application;

[0045] Figure 4 is another example schematic diagram of a reference trajectory scenario provided by an embodiment of the present application;

[0046] Figure 5a is a functional unit composition block diagram of a vehicle steering anti-collision device provided by an embodiment of the present application;

[0047] Figure 5b is a functional unit composition block diagram of another vehicle steering anti-collision device provided by an embodiment of the present application;

[0048] Figure 6 is a structural block diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0049] In order to enable persons skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by persons skilled in the art without creative work fall within the scope of protection of the present application.

[0050] The terms “first”, “second”, and the like in the specification and claims of the present application and the above-mentioned drawings are used to distinguish different objects, and are not used to describe a specific order. In addition, the terms “include” and “have” and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but can optionally include steps or units not listed, or can optionally include other steps or units inherent to the process, method, product or device.

[0051] Reference herein to “an embodiment” means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the present application. The appearance of the phrase in various places in the specification does not necessarily all refer to the same embodiment, nor does it necessarily refer to a separate or alternative embodiment in isolation or in combination with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0052] Please refer to Figure 1 , Figure 1 is a structural block diagram of an automatic driving system provided by an embodiment of the present application. As shown in Figure 1As shown, the automatic driving system 10 at least includes the automatic driving domain controller 11 and a sensor module 12 arranged on the target vehicle body, and the automatic driving domain controller 11 is in communication connection with the sensor module 12.

[0053] In the idle state, the automatic driving domain controller 11 can determine a reference trajectory scene frequently passed by the target vehicle according to historical driving images, and analyze the body posture of the target vehicle and the environmental state around the vehicle detected by the sensor module 12, and then determine a plurality of key position points and corresponding standard body postures in the scene, and analyze the detection position points and body postures detected by the sensor module 12 in the detection area when the target vehicle actually enters the reference trajectory scene, so as to determine whether the current state of the target vehicle can safely perform a steering operation, and realize early warning of vehicle steering anti-collision.

[0054] The sensor module 12 can include external sensors for detecting real-time information about the environment around the target vehicle and internal sensors for measuring the body posture of the target vehicle. The external sensors can include at least one image sensor, a distance measuring sensor and a global positioning system (GPS) receiver mounted on the front, side and rear of the vehicle. The information about the environment around the target vehicle can include information about the driving lane of the target vehicle and the driving lane entered after the target vehicle performs a steering operation, i.e. related information about the first lane and the second lane, which can include lane width, lane length, etc., which is not limited herein.

[0055] The following describes a vehicle steering anti-collision method provided by an embodiment of the application.

[0056] Please refer to Figure 2 , Figure 2 is a flowchart of a vehicle steering anti-collision method provided by an embodiment of the application, which is applied to an automatic driving domain controller 11 in an automatic driving system 10 as shown in Figure 1 As shown in Figure 2 , the method comprises the following steps.

[0057] Step 201: determining a reference trajectory scene passed by the target vehicle according to historical driving images of the target vehicle.

[0058] The reference trajectory scene refers to a trajectory scene in which the target vehicle has passed more than a preset number of times in the historical driving images. The reference trajectory scene includes a first lane and a second lane, where the first lane and the second lane intersect. The preset number of times can be determined based on historical data or customized by the user. For example, the reference trajectory scene can be an underground garage at the user's residence or workplace.

[0059] Step 202: Determine X reference position points in the reference trajectory scene.

[0060] The reference position point refers to the starting position point where the target vehicle performs a continuous turning operation in the first lane and drives toward the second lane, and X is a positive integer.

[0061] For example, see Figure 3a , Figure 3a This is an example diagram of a reference trajectory scenario provided by an embodiment of the present application, such as Figure 3a As shown in this example, the target vehicle's driving trajectory is through first lane 301, then starting at reference position 303 and executing a continuous right turn toward second lane 302. It will be appreciated that if the target vehicle's driving trajectory is to execute a left turn from lane 302 toward lane 301, then the first lane is lane 302 in the figure, and the second lane is lane 301 in the figure. Because different trajectory scenarios and driving trajectories exist, the first and second lanes need to be determined based on specific circumstances. The illustration in this example is for illustrative purposes only and is not intended to be limiting.

[0062] Step 203: Perform the following operations a, b, and c for the X reference position points:

[0063] a. Determine N body postures of the target vehicle at the currently processed reference position point;

[0064] Among them, the vehicle body posture is used to indicate the angle between the straight line where the vehicle body of the target vehicle is located and the straight line where the target wall is located. The target wall refers to the wall supported by the first lane in the direction of the head of the target vehicle when performing continuous steering operations.

[0065] See also Figure 3b , Figure 3b This is an example diagram of another reference trajectory scenario provided by an embodiment of the present application, such as Figure 3bAs shown, one of the body poses of the target vehicle at the reference position point 304 currently processed is body pose 30, at this time the vehicle head points to the straight line 306 where the target wall is located, and the body pose is represented by the included angle α between the straight line 305 where the body of the target vehicle is located and the straight line 306 where the target wall is located. In particular, when the body pose of the target vehicle is as shown in the body pose, at this time the straight line where the body of the target vehicle is located is parallel to the straight line 306 where the target wall is located, and the included angle α is equal to 0. In other possible examples, please refer to Figure 3a , Figure 3c , Figure 3c is another example diagram of a reference trajectory scene provided by an embodiment of the present application, in which, as shown in Figure 3c , another body pose of the target vehicle at the reference position point 304 is body pose 31, at this time the vehicle tail points to the straight line 306 where the target wall is located, and when the figure surrounded by the straight line 305, the straight line 306 and the straight line 307 is an isosceles triangle with the straight line 305 and the straight line 307 as the base, at this time the included angle between the straight line 307 where the body of the target vehicle is located and the straight line 306 where the target wall is located is also α, and the same included angle may correspond to different body poses at the same reference position point, which may cause calculation errors. In order to avoid such a situation, at this time the obtuse angle β between the straight line 307 and the straight line 306 where the target wall is located is used to represent the body pose 31 of the target vehicle at the reference position point 304, and in this special scenario, β = 180°-α.

[0066] b. determining N steering fault tolerances of the target vehicle at the reference position point currently processed under the constraint of the N body poses;

[0067] wherein the steering fault tolerance is used to indicate the difficulty level of the target vehicle performing the steering operation at the reference position point currently processed, and N is a positive integer. The higher the steering fault tolerance, the easier it is for the user to drive the target vehicle to perform the steering operation at the reference position point currently processed in the current body pose, that is, the less likely the scratching event occurs.

[0068] In one possible example, the determining the N steering fault tolerances of the target vehicle at the current processing reference position point under the constraint of the N vehicle body postures comprises: for the N vehicle body postures, performing the following operations: obtaining a minimum rotation angle of a steering wheel of the target vehicle at the current processing reference position point under the constraint of a current processing vehicle body posture, the minimum rotation angle being used to indicate a minimum distance between a vehicle head of the target vehicle and a first wall when the target vehicle performs a continuous steering operation, the first wall being a wall of the second lane carried in a direction in which the vehicle head of the target vehicle points when performing the continuous steering operation; obtaining a maximum rotation angle of the steering wheel of the target vehicle at the current processing reference position point under the constraint of the current processing vehicle body posture, the maximum rotation angle being used to indicate a minimum distance between a vehicle body of the target vehicle and a target corner region when the target vehicle performs the continuous steering operation, the target corner region being an intersection region between the target wall and a second wall, the second wall being a wall of the second lane carried relative to the first wall; determining a rotatable angle range of the steering wheel of the target vehicle at the current processing reference position point under the constraint of the current processing vehicle body posture according to the minimum rotation angle and the maximum rotation angle; determining a steering fault tolerance of the target vehicle at the current processing reference position point under the constraint of the current processing vehicle body posture according to the rotatable angle range; and processing a next vehicle body posture until the N vehicle body postures are all processed to obtain the N steering fault tolerances of the target vehicle at the current processing reference position point under the constraint of the N vehicle body postures.

[0069] For example, refer to Figure 3d , Figure 3d is another example diagram of a reference trajectory scene provided by an embodiment of the present application, as Figure 3dAs shown, the minimum rotation angle of the target vehicle steering wheel refers to the rotation angle of the steering wheel when the target vehicle reaches the position point 34 at the current processing reference position point 304 with the current processing vehicle body posture 33, wherein the target vehicle reaches the position point 34, the target vehicle has the minimum distance between the vehicle head and the first wall 308, that is, the critical point of the scraping event; the maximum rotation angle of the target vehicle steering wheel refers to the rotation angle of the steering wheel when the target vehicle reaches the position point 35 at the current processing reference position point 304 with the current processing vehicle body posture 33, wherein the target vehicle reaches the position point 35, the target vehicle has the minimum distance between the vehicle body and the target corner area 309, that is, the critical point of the scraping event, wherein the target corner area 309 refers to the intersection area between the target wall and the second wall 310. Wherein, the minimum rotation angle and the maximum rotation angle of the target vehicle steering wheel can be obtained by real-time detection of the sensor module. For example, the minimum rotation angle of the target vehicle steering wheel is 40°, and the maximum rotation angle is 360°, which indicates that when the rotation angle of the target vehicle steering wheel is less than 40° or greater than 360°, a scraping event will occur, and the rotatable angle range is [40°, 360°], that is, in the specific case of the present example, when the rotation angle of the target vehicle steering wheel is within the interval, the steering operation will not cause a scraping event, thereby further determining the steering fault tolerance according to the rotatable angle range.

[0070] It can be seen that in the present example, the automatic driving domain controller determines the rotatable angle range of the steering wheel and the steering fault tolerance by the minimum rotation angle and the maximum rotation angle of the target vehicle steering wheel at the current processing reference position point under the constraint of the current processing vehicle body posture, thereby improving the accuracy of scene analysis, ensuring the accuracy of detection when the target vehicle actually enters the scene, and optimizing the user experience.

[0071] In one possible example, the determination of the steering fault tolerance of the target vehicle at the current processing reference position point under the constraint of the current processing vehicle body posture according to the rotatable angle range comprises: calculating the controllability of the steering wheel of the target vehicle at the current processing reference position point under the constraint of the current processing vehicle body posture according to the rotatable angle range, the controllability being used to represent the difficulty of driving the target vehicle at the current processing reference position point under the constraint of the current processing vehicle body posture; and determining the steering fault tolerance of the target vehicle at the current processing reference position point under the constraint of the current processing vehicle body posture according to the controllability.

[0072] The maximum rotation angle of the target vehicle steering wheel in the same rotation direction is different due to the difference in vehicle structure. In this example, the maximum rotation angle of the target vehicle steering wheel in the same rotation direction is 1.5 turns, i.e. 540°, the rotatable angle range is [40°, 360°], i.e. the rotatable angle is 320°, and the controllability can be 320° / 540°x100%≈59.26%. Finally, the steering fault tolerance is determined according to the controllability.

[0073] It can be seen that in this example, the automatic driving domain controller calculates the controllability of the target vehicle through the rotatable angle range, thereby further determining the steering fault tolerance, improving the accuracy of scene analysis, ensuring the accuracy of detection when the target vehicle actually enters the scene, and optimizing the user experience.

[0074] In one possible example, the determining the steering fault tolerance of the target vehicle at the currently processed reference location point under the constraint of the currently processed vehicle body posture according to the controllability includes: querying a pre-created association table to obtain the steering fault tolerance of the target vehicle at the currently processed reference location point under the constraint of the currently processed vehicle body posture according to the controllability, the pre-created association table including a corresponding relationship between a plurality of controllabilities and a plurality of steering fault tolerances.

[0075] The pre-created association table can be a plurality of controllabilities and a plurality of corresponding steering fault tolerances obtained through historical experience data statistical analysis. It can be understood that the steering fault tolerance and the controllability are positively correlated, i.e. the greater the controllability at the currently processed reference location point under the constraint of the currently processed vehicle body posture, the greater the steering fault tolerance of the target vehicle.

[0076] It can be seen that in this example, the automatic driving domain controller obtains the association between the controllability and the steering fault tolerance through table lookup, thereby determining the steering fault tolerance of the target vehicle in the currently processed scene according to the calculated controllability, and improving the accuracy of detection when the target vehicle actually enters the scene.

[0077] In other possible examples, the determining the steering fault tolerance of the target vehicle at the currently processed reference location point under the constraint of the currently processed vehicle body posture according to the controllability further includes: determining the numerical value of the controllability as the numerical value of the steering fault tolerance. For example, the controllability of the target vehicle at the currently processed reference location point under the constraint of the currently processed vehicle body posture is 59.26%, and the numerical value of the corresponding steering fault tolerance is also 59.26%. In this way, the data processing amount is reduced, and the processing efficiency is improved on the basis of ensuring the detection accuracy.

[0078] c. determining whether there is a steering fault tolerance greater than the preset fault tolerance in the N steering fault tolerances;

[0079] If yes, mark the current processing reference position point as a key position point; and select M steering fault tolerances greater than the preset fault tolerance from the N steering fault tolerances, and determine M standard vehicle body attitudes corresponding to the M steering fault tolerances.

[0080] Wherein, M is a positive integer and M is less than or equal to N. The preset fault tolerance can be obtained by statistical analysis of historical experience data, and the preset fault tolerance can be flexibly changed according to the driving experience of the user to adapt to the different needs of different users. Illustratively, the 5 steering fault tolerances of the current processing reference position point under the constraint of 5 vehicle body attitudes are 30%, 40%, 60%, 65%, and 80%, and the preset fault tolerance is 50%, there are steering fault tolerances greater than the preset fault tolerance 60%, 65%, and 80%, that is, M = 3, and the three standard vehicle body attitudes corresponding to the three steering fault tolerances are determined by reverse mapping. At this time, the current processing reference position point is marked as a key position point, which represents that there is a standard vehicle body attitude that can safely steer the target vehicle at this position point.

[0081] If no, continue to process the next reference position point until all X reference position points are processed to obtain Y key position points.

[0082] Wherein, Y is an integer and Y is less than or equal to X. It can be understood that when Y = 0, it indicates that the steering fault tolerance of the X reference position points in the reference trajectory scene is less than the preset steering fault tolerance, that is, the difficulty of performing steering operation of the target vehicle at all reference position points in the trajectory scene is in a high difficulty. At this time, according to the user's needs, the preset fault tolerance can be changed or the processing of the trajectory scene can be skipped to process the next trajectory scene with a number of passes greater than the preset number of passes. For example, some users have rich driving experience, and can control the vehicle to safely steer even if the difficulty of performing steering operation is high, at this time, the preset fault tolerance can be reduced according to the user's needs to reprocess the trajectory scene; some users lack driving experience and need high fault tolerance to control the vehicle to safely steer, at this time, according to the user's needs, the processing of the trajectory scene can be skipped to process the next trajectory scene with a number of passes greater than the preset number of passes. Alternatively, when the user passes through the trajectory scene, a prompt voice will be output to prompt the user that the scene steering road condition is complex and remind the user to pay attention to safety.

[0083] In a possible example, after the M steering fault tolerances greater than the preset fault tolerance are screened out from the N steering fault tolerances and the M standard vehicle body attitudes corresponding to the M steering fault tolerances are determined, the method further includes: creating a mapping relationship table associated with the currently processed reference position point, the mapping relationship table associated with the currently processed reference position point including the mapping relationship between the currently processed reference position point and the M standard vehicle body attitudes.

[0084] For example, it is determined that the five vehicle body attitudes of the currently processed reference position point are 30°, 120°, 60°, 80° and 0° respectively, and the corresponding five steering fault tolerances are 30%, 40%, 60%, 65% and 80% respectively, and the preset fault tolerance is 50%, then it can be determined that the three standard vehicle body attitudes are 60°, 80° and 0°, and the mapping relationship between the reference position point and the three standard vehicle body attitudes is established at this time. Alternatively, the coordinates (x0, y0) of the reference position point can be determined in the form of a two-dimensional rectangular coordinate system, so as to associate the currently processed reference position point and the three standard vehicle body attitudes at the data level.

[0085] It can be seen that in the example, the automatic driving domain controller associates the determined standard vehicle body attitude and the currently processed reference position point through the mapping relationship table, which facilitates data processing when the target vehicle actually enters the detection area for detection, and improves the detection efficiency.

[0086] Step 204, when the target vehicle enters the reference trajectory scene, the following operations d, e, f, g and h are performed:

[0087] d, obtaining the detection position point when the target vehicle reaches the detection area associated with the Y key position points and the first vehicle body attitude when the target vehicle reaches the detection area.

[0088] The detection area is located between the Y key position points and the trajectory starting point, and the trajectory starting point refers to the position of the target vehicle when it enters the reference trajectory scene. Specifically, taking the reference trajectory scene as an underground garage, the trajectory starting point refers to any point on the horizontal straight line at the entrance of the underground garage.

[0089] In a possible example, the straight line where the detection area is located is perpendicular to the straight line where the target wall is located, and the distance between the detection area and the key position point closest to the trajectory starting point among the Y key position points is a preset distance.

[0090] Please refer to Figure 4 , Figure 4 is another example of a reference trajectory scene provided by the embodiment of the application, as shown in Figure 4As shown, after the pre-processing, Y key position points (only 11 key position points are marked in the figure for illustrative auxiliary description due to the limitation of the length) in the reference trajectory scene are obtained, wherein the key position point 401 is the closest to the starting point of the trajectory among the Y key position points, and the distance from the key position point 401 to the detection area 402 is a preset distance d. When the target vehicle reaches the detection area 402, the detection position point 403 where the target vehicle is located and the first vehicle body posture at this time are obtained. Specifically, the specific position of the detection position point can be determined by obtaining the coordinates (x1, y1) of the detection position point 403, and the first vehicle body posture at this time is 0° in this example. In particular, the preset distance d can be twice the length of the vehicle body of the target vehicle, and twice the length of the vehicle body is the best distance for the user to adjust the driving route to make the vehicle safely turn according to historical experience data analysis.

[0091] As can be seen, in this example, since the detection area where the safety detection is performed is a certain distance away from the nearest key position point where the target vehicle starts to perform the turning operation, the safety detection and reminder of the target vehicle are advanced, which avoids the situation that the user has too small adjustable space for the vehicle due to the reminder being too late, and optimizes the user experience.

[0092] e. determining Y probability values of the target vehicle reaching the Y key position points according to the detection position point and the first vehicle body posture, and marking the key position point with the largest probability value as a target key position point;

[0093] The probability value can be determined comprehensively by the number of times that the target vehicle passes through each key position point in historical driving images, for example, when the target vehicle is at the detection position point 403 as shown in the first vehicle body posture, it is determined according to the historical driving images that the probability of the target vehicle reaching the key position point 401 to perform the turning operation is the largest, and then the key position point 401 is marked as the target key position point. Figure 4

[0094] f. determining a second vehicle body posture of the target vehicle at the target key position point according to the detection position point, the first vehicle body posture, and the target key position point;

[0095] ​In particular, the driving habits of the user can be analyzed according to historical driving images, so as to estimate the second vehicle body posture of the target vehicle at the target key position point according to the detection position point, the first vehicle body posture and the target key position point. In this example, the driving habits of the user in this example scenario are analyzed according to historical driving images, that is, the user keeps straight driving to the target key position point 401 and then performs a steering operation, so that the second vehicle body posture of the target vehicle at the target key position point 401 is estimated to be 0°, that is, the vehicle body posture remains unchanged. It can be understood that in other examples, due to different habits of the user, the first vehicle body posture and the second vehicle body posture are not always the same, and need to be determined according to specific scenarios. This example is only for auxiliary description and is not limited.

[0096] g. Obtain a plurality of standard vehicle body postures corresponding to the target key position point.

[0097] In one possible example, the plurality of standard vehicle body postures corresponding to the target key position point are obtained by querying a mapping relationship table associated with the target key position point with the target key position point as a query identifier.

[0098] The mapping relationship table associated with the target key position point is data processed and generated in the scene analysis stage, and includes a plurality of standard vehicle body postures corresponding to the target key position point, that is, the vehicle body posture of the target vehicle at the target key position point is one of the plurality of standard vehicle body postures, that is, the steering operation can be safely performed to avoid scratching events. In this example, since the mapping relationship table has been generated in the scene analysis stage, the plurality of standard vehicle body postures can be obtained by querying the mapping relationship table with the target key position point as a query identifier.

[0099] It can be seen that in this example, the autonomous driving domain controller can directly obtain a plurality of standard vehicle body postures by querying the mapping relationship table associated with the target key position point generated in the scene analysis stage, thereby improving the detection efficiency and optimizing the user experience.

[0100] h. If the second vehicle body posture is not included in the plurality of standard vehicle body postures, output an auxiliary voice, the auxiliary voice being used to instruct the user to adjust the driving route of the target vehicle, so that the target vehicle does not have a scratching event when performing a continuous steering operation to enter the second lane.

[0101] The output auxiliary voice includes but is not limited to the following forms: prompting the user to adjust the driving direction, going to the next key position point, and informing the user of the vehicle body posture that should be reached at the next key position point, which can be determined according to the current specific position and vehicle body posture of the target vehicle. The optimal one position point; or prompting the user to adjust the driving direction, performing reversing, turning and other operations, so that the vehicle body posture when reaching the target key position point is any one of the plurality of standard vehicle body postures.

[0102] It can be seen that in the embodiment of the present application, the autonomous driving domain controller first determines the reference trajectory scene frequently passed by the target vehicle according to the historical driving image of the target vehicle, then determines X starting points, i.e., reference position points, of the target vehicle performing the turning operation in this scene, and then processes the X reference position points to obtain Y key position points with low difficulty in performing the turning operation and the corresponding standard vehicle body postures. When the target vehicle actually passes through the reference trajectory scene, the autonomous driving domain controller performs the turning assistance detection function: first acquires the detection position point and the first vehicle body posture when the target vehicle reaches the detection area, and determines the key position point most likely to be reached by the target vehicle, i.e., the target key position point, and the second vehicle body posture when reaching the target key position point according to the position point and the first vehicle body posture at this time. If the second vehicle body posture is not included in the standard vehicle body posture corresponding to the target key position point, it indicates that the difficulty of the target vehicle performing the turning operation at the target key position point is high at this time, and an auxiliary voice is output at this time to assist the user in adjusting the driving route, so as to safely perform the turning operation and avoid the occurrence of the scratching event. In this way, the time of the anti-scratching reminder can be advanced, the user's adjustable space of the vehicle is avoided to be too small due to the reminder being too late, and the output auxiliary voice can assist the user in adjusting the vehicle, thereby optimizing the user's use experience.

[0103] Consistent with the above-mentioned embodiments, please refer to Figure 5a , Figure 5a is a functional unit composition block diagram of a vehicle turning anti-scratching device provided by the embodiment of the present application, and the device is applied to a vehicle as Figure 1The automatic driving domain controller 11 shown in the figure, the vehicle steering anti-collision device 50 comprises: a first determination unit 501, configured to determine a reference trajectory scene passed by the target vehicle according to historical driving images of the target vehicle, the reference trajectory scene refers to a trajectory scene in the historical driving images, the number of times of passing through the target vehicle is greater than a preset number of times, the reference trajectory scene comprises a first lane and a second lane, and the first lane and the second lane intersect; a second determination unit 502, configured to determine X reference position points in the reference trajectory scene, the reference position point refers to a starting position point of the target vehicle performing continuous steering operation on the first lane to the second lane, wherein X is a positive integer; a first execution unit 503, configured to perform operations a, b and c on the X reference position points: a, determining N vehicle body postures of the target vehicle at the currently processed reference position point, the vehicle body posture is used to indicate the included angle between the straight line where the vehicle body of the target vehicle is located and the straight line where the target wall is located, and the target wall refers to the wall borne by the first lane in the direction indicated by the vehicle head of the target vehicle when performing continuous steering operation; b, determining N steering fault tolerance degrees of the target vehicle at the currently processed reference position point under the constraint of the N vehicle body postures, the steering fault tolerance degree is used to indicate the difficulty degree of the target vehicle performing steering operation at the currently processed reference position point, wherein N is a positive integer; c, judging whether there is a steering fault tolerance degree greater than a preset fault tolerance degree in the N steering fault tolerance degrees; if yes, marking the currently processed reference position point as a key position point; and selecting M steering fault tolerance degrees greater than the preset fault tolerance degree from the N steering fault tolerance degrees, and determining M standard vehicle body postures corresponding to the M steering fault tolerance degrees, wherein M is a positive integer and M is less than or equal to N; if not, the next reference position point is continuously processed until all the X reference position points are processed, Y key position points are obtained, wherein Y is an integer and Y is less than or equal to X; a second execution unit 504, configured to perform operations d, e, f, g and h when detecting that the target vehicle enters the reference trajectory scene: d, acquiring a detection position point when the target vehicle reaches a detection area associated with the Y key position points and a first vehicle body posture when the target vehicle reaches the detection area, the detection area is located between the Y key position points and a trajectory starting point, and the trajectory starting point refers to a position point when the target vehicle enters the reference trajectory scene; e, determining Y probability values of the target vehicle reaching the Y key position points according to the detection position point and the first vehicle body posture, and marking the key position point with the maximum probability value as a target key position point; f, determining a second vehicle body posture of the target vehicle at the target key position point according to the detection position point, the first vehicle body posture and the target key position point;g, acquiring a plurality of standard vehicle body postures corresponding to the target key position point; h, if the second vehicle body posture is not included in the plurality of standard vehicle body postures, outputting an auxiliary voice, the auxiliary voice being used to instruct the user to adjust the driving route of the target vehicle, so that the target vehicle does not have a scraping event when performing a continuous steering operation into the second lane.

[0104] In one possible example, in the determination of the N steering fault tolerances of the target vehicle at the currently processed reference position point under the constraint of the N vehicle body postures, the first execution unit 503 is specifically configured to: for the N vehicle body postures, acquire a minimum rotation angle of the steering wheel of the target vehicle at the currently processed reference position point under the constraint of the currently processed vehicle body posture, the minimum rotation angle being used to indicate a minimum distance between the vehicle head of the target vehicle and a first wall when the target vehicle performs a continuous steering operation, the first wall being a wall carried by the second lane in the direction of the vehicle head of the target vehicle when performing a continuous steering operation; acquire a maximum rotation angle of the steering wheel of the target vehicle at the currently processed reference position point under the constraint of the currently processed vehicle body posture, the maximum rotation angle being used to indicate a minimum distance between the vehicle body of the target vehicle and a target corner region when the target vehicle performs a continuous steering operation, the target corner region being an intersection region between the target wall and a second wall, the second wall being a wall carried by the second lane relative to the first wall; determine a rotatable angle range of the steering wheel of the target vehicle at the currently processed reference position point under the constraint of the currently processed vehicle body posture according to the minimum rotation angle and the maximum rotation angle; determine the steering fault tolerance of the target vehicle at the currently processed reference position point under the constraint of the currently processed vehicle body posture according to the rotatable angle range; continue to process the next vehicle body posture until all the N vehicle body postures are processed to obtain the N steering fault tolerances of the target vehicle at the currently processed reference position point under the constraint of the N vehicle body postures.

[0105] In a possible example, in the aspect of determining the steering fault tolerance of the target vehicle at the current processing reference location point under the constraint of the current processing vehicle body posture according to the rotatable angle range, the first execution unit 503 is specifically configured to: calculate a controllability of a steering wheel of the target vehicle at the current processing reference location point under the constraint of the current processing vehicle body posture according to the rotatable angle range, where the controllability is used to represent a degree of difficulty of user driving the target vehicle at the current processing reference location point under the constraint of the current processing vehicle body posture; and determine the steering fault tolerance of the target vehicle at the current processing reference location point under the constraint of the current processing vehicle body posture according to the controllability.

[0106] In a possible example, in the aspect of determining the steering fault tolerance of the target vehicle at the current processing reference location point under the constraint of the current processing vehicle body posture according to the controllability, the first execution unit 503 is specifically configured to: query a pre-created association relationship table to obtain the steering fault tolerance of the target vehicle at the current processing reference location point under the constraint of the current processing vehicle body posture according to the controllability, where the pre-created association relationship table includes a corresponding relationship between a plurality of controllabilities and a plurality of steering fault tolerances.

[0107] In a possible example, after the M steering fault tolerances greater than the preset fault tolerance are filtered out from the N steering fault tolerances, and the M standard vehicle body postures corresponding to the M steering fault tolerances are determined, the vehicle steering anti-collision device 50 is further configured to: create a mapping relationship table associated with the current processing reference location point, where the mapping relationship table associated with the current processing reference location point includes a mapping relationship between the current processing reference location point and the M standard vehicle body postures.

[0108] In a possible example, in the aspect of obtaining the plurality of standard vehicle body postures corresponding to the target key location point, the second execution unit 504 is specifically configured to: query a mapping relationship table associated with the target key location point by taking the target key location point as a query identifier, to obtain the plurality of standard vehicle body postures corresponding to the target key location point.

[0109] In a possible example, the straight line on which the detection area is located is perpendicular to a straight line on which the target wall is located, and a distance between the detection area and a key location point closest to the starting point of the track among the Y key location points is a preset distance.

[0110] It can be understood that, since the method embodiment and the device embodiment are different presentation forms of the same technical concept, the content of the method embodiment part in the present application should be synchronously adapted to the device embodiment part, which will not be repeated here.

[0111] In the case of employing an integrated unit, as Figure 5b shown, Figure 5b is another functional unit composition block diagram of the vehicle steering anti-collision device provided by the embodiment of the application. In Figure 5b , the vehicle steering anti-collision device 51 comprises a processing module 512 and a communication module 511. The processing module 512 is configured to control and manage the actions of the vehicle steering anti-collision device, for example, to perform the steps of the first determining unit 501, the second determining unit 502, the first executing unit 503 and the second executing unit 504, and / or to perform other processes of the technologies described herein. The communication module 511 is configured to support the interaction between the vehicle steering anti-collision device and other devices. As Figure 5b shown, the vehicle steering anti-collision device can further comprise a storage module 513, which is configured to store the program code and data of the vehicle steering anti-collision device.

[0112] The processing module 512 can be a processor or a controller, for example, a central processing unit (CPU), a general processor, a digital signal processor (DSP), an ASIC, an FPGA or other programmable logic device, a transistor logic device, a hardware component or any combination thereof. It can implement or execute various exemplary logical blocks, modules and circuits described in combination with the disclosure. The processor can also be a combination of computing functions, such as one or more microprocessor combinations, combinations of DSP and microprocessor, etc. The communication module 511 can be a transceiver, RF circuit or communication interface, etc. The storage module 513 can be a memory.

[0113] All related contents of each scene involved in the above method embodiments can be cited to the functional description of the corresponding functional module, which will not be repeated here. The above vehicle steering anti-collision device 51 can perform the vehicle steering anti-collision method shown in Figure 2 .

[0114] The above-described embodiments can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented by software, the above-described embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present application are wholly or partially generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions can be transferred from one website, computer, server, or data center to another website, computer, server, or data center through wired or wireless means. The computer-readable storage medium can be any available medium accessible by a computer or a data storage device such as a server, data center, etc. containing one or more available medium collections. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. The semiconductor medium can be a solid-state disk.

[0115] Figure 6 is a structural block diagram of an electronic device provided by an embodiment of the present application. As shown in Figure 6 the electronic device 600 can include one or more of the following components: a processor 601, a memory 602 coupled with the processor 601, wherein the memory 602 can store one or more computer programs, and the one or more computer programs can be configured to be executed by the one or more processors 601 to implement the method described in the above embodiments. The electronic device 600 can be the autonomous driving domain controller 11 in the above embodiments.

[0116] The processor 601 can include one or more processing cores. The processor 601 connects various parts within the entire electronic device 600 by running or executing instructions, programs, code sets or instruction sets stored in the memory 602, and calling data stored in the memory 602, to perform various functions and process data of the electronic device 600. Optionally, the processor 601 can be implemented in at least one of a hardware form of a digital signal processing (DSP), a field-programmable gate array (FPGA), a programmable logic array (PLA). The processor 601 can integrate a combination of one or several of a central processing unit (CPU), a graphics processor (GPU), and a modem, etc. Among them, the CPU mainly processes operating systems, user interfaces, and application programs, etc.; the GPU is responsible for rendering and drawing display content; and the modem is used for processing wireless communication. It can be understood that the above-mentioned modem can also not be integrated into the processor 601, but be realized by a separate communication chip.

[0117] The memory 602 can include a random access memory (RAM) and can also include a read-only memory (ROM). The memory 602 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 602 can include a program storage area and a data storage area, wherein the program storage area can store instructions for implementing an operating system, instructions for implementing at least one function (such as a touch function, a sound playing function, an image playing function, etc.), instructions for implementing the above-mentioned various method embodiments, etc. The data storage area can also store data created by the electronic device 600 in use, etc.

[0118] It can be understood that the electronic device 600 can include more or less structural elements than those in the above structural block diagram, which is not limited herein.

[0119] The embodiments of the present application also provide a computer storage medium, wherein a computer program / instructions are stored on the computer storage medium, and the computer program / instructions are executed by a processor to implement part or all steps of any method described in the above method embodiments.

[0120] The embodiment of the present application further provides a computer program product, which comprises a non-transitory computer readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute part or all of the steps of any method described in the above method embodiments.

[0121] It should be understood that the size of the sequence number of the above processes does not mean the order of execution in various embodiments of the present application, and the execution order of the processes should be determined according to its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0122] In several embodiments provided in the present application, it should be understood that the disclosed methods, devices and systems can be implemented in other ways. For example, the above-described device embodiments are only schematic; for example, the division of the units is only a logical function division, and actual implementation can have another division manner; for example, a plurality of units or components can be combined or integrated into another system, or some features can be omitted or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interface, device or unit, and can be electrical, mechanical or other forms.

[0123] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on a plurality of network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the present embodiment.

[0124] In addition, each functional unit in each embodiment of the present application can be integrated in one processing unit, or each unit can be physically included separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware, or in the form of hardware plus software functional unit.

[0125] The integrated unit in the form of software function unit can be stored in a computer readable storage medium. The software function unit is stored in a storage medium, including a plurality of instructions for enabling a computer device (which can be a personal computer, an electronic device, or a network device, etc.) to execute part of steps of the method according to various embodiments of the present application. The aforementioned storage medium includes a U disk, a mobile hard disk, a magnetic disk, an optical disk, a volatile memory or a non-volatile memory. The non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically EPROM (EEPROM) or a flash memory. The volatile memory can be a random access memory (RAM) used as an external cache. By way of example but not limitation, many forms of random access memory (RAM) can be used, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchlink DRAM (SLDRAM), and direct rambus RAM (DRAM) and various other media that store program codes.

[0126] Although the present application is disclosed as above, the present application is not limited thereto. Any person skilled in the art can easily conceive variations or substitutions without departing from the spirit and scope of the present application, and various modifications can be made, including combinations of different functions and implementation steps, including software and hardware implementations, which are all within the scope of the present application.

Claims

1. A vehicle turning anticreep method, characterized by, The method comprises: determining a reference track scene passed by a target vehicle according to historical driving images of the target vehicle, the reference track scene being a track scene in which the target vehicle passes more than a preset number of times in the historical driving images, the reference track scene comprising a first lane and a second lane, and the first lane and the second lane intersecting; determining X reference position points in the reference track scene, the reference position points being start position points at which the target vehicle performs continuous steering operations on the first lane to drive to the second lane, wherein X is a positive integer; performing operations a, b and c on the X reference position points: a, determining N vehicle body postures of the target vehicle at a currently processed reference position point, the vehicle body posture being used to indicate an included angle between a straight line on which a vehicle body of the target vehicle is located and a straight line on which a target wall is located, the target wall being a wall borne by the first lane in a direction in which a vehicle head of the target vehicle points when performing continuous steering operations; b, determining N steering fault tolerance degrees of the target vehicle at the currently processed reference position point under constraints of the N vehicle body postures, the steering fault tolerance degree being used to indicate a degree of difficulty of the target vehicle in performing a steering operation at the currently processed reference position point, wherein N is a positive integer; c, judging whether there is a steering fault tolerance degree greater than a preset fault tolerance degree in the N steering fault tolerance degrees; if yes, marking the currently processed reference position point as a key position point, and selecting M steering fault tolerance degrees greater than the preset fault tolerance degree from the N steering fault tolerance degrees, and determining M standard vehicle body postures corresponding to the M steering fault tolerance degrees, wherein M is a positive integer and M is less than or equal to N; if no, continuously processing a next reference position point until all the X reference position points are processed to obtain Y key position points, wherein Y is an integer and Y is less than or equal to X; when detecting that the target vehicle enters the reference track scene, performing operations d, e, f, g and h: d, obtaining a detection position point at which the target vehicle reaches a detection area associated with the Y key position points and a first vehicle body posture of the target vehicle when reaching the detection area, the detection area being located between the Y key position points and a track start point, the track start point being a position point at which the target vehicle enters the reference track scene; e, determining Y probability values of the target vehicle reaching the Y key position points according to the detection position point and the first vehicle body posture, and marking a key position point with a maximum probability value as a target key position point; f, determining a second vehicle body posture of the target vehicle at the target key position point according to the detection position point, the first vehicle body posture and the target key position point; g, obtaining a plurality of standard vehicle body postures corresponding to the target key position point; and h, determining a target steering fault tolerance degree of the target vehicle at the target key position point according to the second vehicle body posture and the plurality of standard vehicle body postures. h. if the second vehicle body posture is not included in the plurality of standard vehicle body postures, output an auxiliary voice, the auxiliary voice being used to instruct the user to adjust a driving route of the target vehicle so that a scraping event does not occur when the target vehicle performs a continuous steering operation to enter the second lane.

2. The method of claim 1, wherein, The determining the N steering fault tolerances of the target vehicle at the currently processed reference position point under the constraint of the N vehicle body postures comprises: For the N vehicle body postures, the following operations are performed: obtaining a minimum rotation angle of a steering wheel of the target vehicle at the currently processed reference position point under the constraint of the currently processed vehicle body posture, the minimum rotation angle being used to indicate a minimum distance between a vehicle head of the target vehicle and a first wall when the target vehicle performs a continuous steering operation, the first wall being a wall carried by the second lane in a direction indicated by the vehicle head of the target vehicle when the target vehicle performs the continuous steering operation; obtaining a maximum rotation angle of the steering wheel of the target vehicle at the currently processed reference position point under the constraint of the currently processed vehicle body posture, the maximum rotation angle being used to indicate a minimum distance between a vehicle body of the target vehicle and a target corner region when the target vehicle performs the continuous steering operation, the target corner region being an intersection region between the target wall and a second wall, the second wall being a wall carried by the second lane relative to the first wall; determining a rotatable angle range of the steering wheel of the target vehicle at the currently processed reference position point under the constraint of the currently processed vehicle body posture according to the minimum rotation angle and the maximum rotation angle; determining a steering fault tolerance of the target vehicle at the currently processed reference position point under the constraint of the currently processed vehicle body posture according to the rotatable angle range; processing a next vehicle body posture until the N vehicle body postures are all processed to obtain the N steering fault tolerances of the target vehicle at the currently processed reference position point under the constraint of the N vehicle body postures.

3. The method of claim 2, wherein, The determining the steering fault tolerance of the target vehicle at the currently processed reference position point under the constraint of the currently processed vehicle body posture according to the rotatable angle range comprises: calculating a controllability of the steering wheel of the target vehicle at the currently processed reference position point under the constraint of the currently processed vehicle body posture according to the rotatable angle range, the controllability being used to represent a degree of difficulty of driving the target vehicle by the user at the currently processed reference position point under the constraint of the currently processed vehicle body posture; determining the steering fault tolerance of the target vehicle at the currently processed reference position point under the constraint of the currently processed vehicle body posture according to the controllability.

4. The method of claim 3, wherein, The determining the steering fault tolerance of the target vehicle at the currently processed reference position point under the constraint of the currently processed vehicle body posture according to the controllability comprises: According to the controllability query, a pre-created association table is obtained to obtain the steering fault tolerance of the target vehicle at the current processing reference position point under the constraint of the current processing body posture, and the pre-created association table includes a corresponding relationship between a plurality of controllabilities and a plurality of steering fault tolerances.

5. The method according to any one of claims 1 to 4, characterized in that, After the M steering fault tolerances greater than the preset fault tolerance are filtered out from the N steering fault tolerances, and the M standard body postures corresponding to the M steering fault tolerances are determined, the method further comprises: creating a mapping relationship table associated with the current processing reference position point, wherein the mapping relationship table associated with the current processing reference position point includes a mapping relationship between the current processing reference position point and the M standard body postures.

6. The method of claim 5, wherein, The method further comprises: taking the target key position point as a query identifier, querying the mapping relationship table associated with the target key position point, and obtaining a plurality of standard body postures corresponding to the target key position point.

7. A vehicle steering anti-collision device characterized by comprising: The device comprises: a first determination unit configured to determine a reference trajectory scene passed by a target vehicle according to historical driving images of the target vehicle, the reference trajectory scene being a trajectory scene passed by the target vehicle more than a preset number of times in the historical driving images, the reference trajectory scene including a first lane and a second lane, and the first lane and the second lane intersecting; a second determination unit configured to determine X reference position points in the reference trajectory scene, the reference position point being a starting position point of the target vehicle driving to the second lane by performing a continuous steering operation on the first lane, wherein X is a positive integer; a first execution unit configured to perform operations a, b and c on the X reference position points as follows: a, determining N body postures of the target vehicle at a current processing reference position point, the body posture being used to indicate an included angle between a straight line where a body of the target vehicle is located and a straight line where a target wall is located, the target wall being a wall carried by the first lane in a direction where a head of the target vehicle points when performing a continuous steering operation; b, determining N steering fault tolerances of the target vehicle at the current processing reference position point under the constraint of the N body postures, the steering fault tolerance being used to indicate a difficulty level of the target vehicle performing a steering operation at the current processing reference position point, wherein N is a positive integer; c, determining whether there is a steering fault tolerance greater than a preset fault tolerance in the N steering fault tolerances; if yes, marking the current processing reference position point as a key position point, and filtering out M steering fault tolerances greater than the preset fault tolerance from the N steering fault tolerances, and determining M standard body postures corresponding to the M steering fault tolerances, wherein M is a positive integer and M is less than or equal to N; if no, continuing to process a next reference position point until all the X reference position points are processed to obtain Y key position points, wherein Y is an integer and Y is less than or equal to X; The second execution unit is configured to perform the following operations d, e, f, g, h when detecting that the target vehicle enters the reference trajectory scene: d. obtaining a detection position point when the target vehicle reaches a detection area associated with the Y key position points and a first vehicle body attitude when the target vehicle reaches the detection area, the detection area being located between the Y key position points and a trajectory starting point, the trajectory starting point being a position point when the target vehicle enters the reference trajectory scene; e. determining Y probability values of the target vehicle reaching the Y key position points according to the detection position point and the first vehicle body attitude, and marking a key position point with the largest probability value as a target key position point; f. determining a second vehicle body attitude of the target vehicle at the target key position point according to the detection position point, the first vehicle body attitude and the target key position point; g. obtaining a plurality of standard vehicle body attitudes corresponding to the target key position point; h. if the second vehicle body attitude is not included in the plurality of standard vehicle body attitudes, outputting an auxiliary voice, the auxiliary voice being used to instruct a user to adjust a driving route of the target vehicle, so that the target vehicle does not have a scraping event when performing a continuous steering operation to enter the second lane.

8. An electronic device, comprising: A computer program product including a processor and a memory, one or more programs stored in the memory and configured to be executed by the processor, the programs including instructions for performing the steps in the method of any one of claims 1-6.

9. A computer readable storage medium having stored thereon computer programs / instructions, characterized in that, The computer program / instructions, when executed by a processor, implement the steps of the method of any one of claims 1-6.

10. A computer program product, characterised in that, The computer program in the computer program product, when executed by a processor, implements the method of any one of claims 1-6.

Images