Vehicle way-giving method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a vehicle way-giving method and device, electronic equipment and a storage medium, and relates to the technical field of intelligent driving, and the method comprises the steps: determining whether a second vehicle running at a pressure speed exists behind a first vehicle or not based on an image collected by image collection equipment carried by the first vehicle; if the second vehicle exists, generating a planned path of the second vehicle based on the reference path and the environment information of the parking lot; based on the vehicle information of the second vehicle, determining a planned passage area in which the second vehicle travels according to the planned path; based on the environment information, generating a way-giving path of the first vehicle, the end point of the way-giving path being located outside the planned passing area; and controlling the first vehicle to run according to the yielding path. By applying the technical scheme provided by the embodiment of the invention, the suppression of the intelligent driving vehicle on the driving speed of the rear vehicle can be reduced.

Description

Technical Field

[0001] The present application relates to the field of intelligent driving technology, and in particular to a vehicle giving way method, device, electronic device and storage medium. Background Art

[0002] Smart driving vehicles usually travel at a low speed when driving in a parking lot. In addition, the roads in parking lots are usually narrow. Therefore, if other vehicles appear behind the smart driving vehicle, it is difficult for the rear vehicle to change lanes and overtake. It is easy for the smart driving vehicle to suppress the speed of the rear vehicle, making it difficult for the rear vehicle to pass quickly.

[0003] In view of the above situation, in order to reduce the suppression of the speed of the rear vehicle by the intelligent driving vehicle, it is necessary to provide a vehicle giving way. Summary of the invention

[0004] The purpose of the embodiments of the present application is to provide a vehicle yielding method, device, electronic device and storage medium to reduce the suppression of the speed of the vehicle behind by the intelligent driving vehicle. The specific technical solution is as follows:

[0005] In a first aspect of an embodiment of the present application, a vehicle yielding method is provided, the method comprising:

[0006] Based on an image captured by an image capture device carried by the first vehicle, determining whether there is a second vehicle traveling at a high speed behind the first vehicle;

[0007] If the second vehicle exists, generating a planned path for the second vehicle based on the reference path and environmental information of the parking lot;

[0008] Determining a planned passage area for the second vehicle to travel along the planned path based on the vehicle information of the second vehicle;

[0009] Based on the environmental information, generating a yield path for the first vehicle, wherein an end point of the yield path is located outside the planned passage area;

[0010] The first vehicle is controlled to travel along the yield path.

[0011] In a second aspect of an embodiment of the present application, a vehicle yielding device is provided, the device comprising:

[0012] A first determination module is used to determine whether there is a second vehicle traveling at a reduced speed behind the first vehicle based on an image captured by an image capture device carried by the first vehicle;

[0013] A first generating module, configured to generate a planned path for the second vehicle based on a reference path and environmental information of the parking lot if the second vehicle exists;

[0014] A second determining module, configured to determine a planned passage area for the second vehicle to travel along the planned path based on the vehicle information of the second vehicle;

[0015] a second generating module, configured to generate a yield path for the first vehicle based on the environmental information, wherein an end point of the yield path is located outside the planned passage area;

[0016] A control module is used to control the first vehicle to travel according to the yield path.

[0017] In a third aspect of the embodiments of the present application, an electronic device is provided, including:

[0018] Memory, used to store computer programs;

[0019] The processor is used to implement the steps of any method described in the first aspect when executing the program stored in the memory.

[0020] In a fourth aspect of an embodiment of the present application, a computer-readable storage medium is provided, wherein a computer program is stored in the computer-readable storage medium, and when the computer program is executed by a processor, the steps of any method described in the first aspect are implemented.

[0021] Beneficial effects of the embodiments of the present application:

[0022] In the technical solution provided by the embodiment of the present application, it is first determined based on the collected image whether there is a second vehicle driving at a reduced speed behind the first vehicle. When there is a second vehicle driving at a reduced speed behind the first vehicle, a planned driving path is actively planned for the second vehicle based on the reference path and the environmental information of the parking lot, and it is expected that the second vehicle will drive along the planned path to surpass the first vehicle during the subsequent driving process. Especially in the scenario where the lanes in the parking lot are narrow, the probability of the second vehicle driving along the planned path increases. In order to further increase the probability of the second vehicle driving along the planned path, a yield path with an end point outside the planned passage area that the second vehicle will pass through when driving along the planned path can also be planned for the first vehicle, and the first vehicle is controlled to drive along the yield path, thereby giving up the planned passage area for the second vehicle. In this way, the probability of the second vehicle driving along the planned path to surpass the first vehicle can be further increased, thereby reducing the suppression of the driving speed of the second vehicle by the first vehicle, and avoiding conflicts or collisions between the first vehicle and the second vehicle. By applying the technical solution provided in the embodiments of the present application, the intelligent driving vehicle can promptly give way to the vehicle behind it when a speed reduction situation occurs, thereby reducing the intelligent driving vehicle's suppression of the speed of the vehicle behind it, avoiding conflicts or collisions with other vehicles, and improving the driving safety of the intelligent driving vehicle.

[0023] Of course, implementing any product or method of the present application does not necessarily require achieving all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application, and for ordinary technicians in this field, other embodiments can also be obtained based on these drawings.

[0025] Figure 1 A schematic diagram of an example of a path provided in an embodiment of the present application;

[0026] Figure 2 A schematic diagram of a pressure speed scenario provided in an embodiment of the present application;

[0027] Figure 3 A schematic diagram of a first flow chart of a vehicle yielding method provided in an embodiment of the present application;

[0028] Figure 4 A schematic diagram of an example of a straightening process provided in an embodiment of the present application;

[0029] Figure 5 A schematic diagram of a first example of a planned traffic area provided in an embodiment of the present application;

[0030] Figure 6 A schematic diagram of a second example of a planned traffic area provided in an embodiment of the present application;

[0031] Figure 7 A detailed flow chart of step S301 provided in an embodiment of the present application;

[0032] Figure 8 A schematic diagram of a vehicle following detection area provided in an embodiment of the present application;

[0033] Fig. 9 A detailed flow chart of step S702 provided in an embodiment of the present application;

[0034] Fig.10 A schematic diagram of a first virtual lane area provided in an embodiment of the present application;

[0035] Fig.11 A schematic diagram of a second virtual lane area provided in an embodiment of the present application;

[0036] Fig.12 A schematic diagram of a virtual lane area provided in an embodiment of the present application;

[0037] Fig.13A detailed flow chart of step S302 provided in an embodiment of the present application;

[0038] Fig.14 A schematic diagram of a first sampling method for regional sampling points provided in an embodiment of the present application;

[0039] Fig.15 A schematic diagram of a second sampling method for regional sampling points provided in an embodiment of the present application;

[0040] Fig.16 A schematic diagram of a method for calculating distance statistical characteristic values ​​provided in an embodiment of the present application;

[0041] Fig.17 A second flow chart of the vehicle yielding method provided in an embodiment of the present application;

[0042] Fig.18 A first detailed flow chart of step S304 provided in an embodiment of the present application;

[0043] Fig.19 A schematic diagram of an updated scene model provided in an embodiment of the present application;

[0044] Fig. 20 A second detailed flow diagram of step S304 provided in an embodiment of the present application;

[0045] Fig.21 An example schematic diagram of a yield endpoint provided in an embodiment of the present application;

[0046] Fig. 22 An example schematic diagram of a yield path provided in an embodiment of the present application;

[0047] Fig.23 A schematic diagram of a flow chart of a yield recovery method provided in an embodiment of the present application;

[0048] Fig.24 A schematic diagram of a beyond detection area provided in an embodiment of the present application;

[0049] Fig.25 A schematic diagram of a second vehicle appearing in an overtaking detection area provided in an embodiment of the present application;

[0050] Fig.26 A schematic diagram of a process of straightening provided in an embodiment of the present application;

[0051] Fig. 27 An example schematic diagram of a teaching path provided in an embodiment of the present application;

[0052] Fig.28A third flow chart of the vehicle yielding method provided in an embodiment of the present application;

[0053] Fig.29 A schematic diagram of a structure of a vehicle yielding device provided in an embodiment of the present application;

[0054] Fig.30 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0055] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field based on the present application belong to the scope of protection of the present application.

[0056] The following is a description of the terms involved in the embodiments of the present application.

[0057] Scene model: An environmental model of the vehicle's surroundings constructed based on the perception information collected by the environmental information collection device and the high-precision map. The environmental information collection device may include radars, image collection devices, positioning devices, etc. carried on the vehicle. Among them, the image collection device may include one or more of the following: a driving recorder, a reversing camera, a panoramic camera; the positioning device may include one or more of the following: a vehicle-mounted navigator, a vehicle-mounted positioning terminal, etc. The environmental model includes: other traffic participants, lane lines, obstacles that hinder vehicle travel, etc. Other traffic participants may include: pedestrians, other vehicles; obstacles may include load-bearing columns in the parking lot, car blocks for each parking space, etc.

[0058] Path: The route from a starting point to a destination.

[0059] like Figure 1 As shown, Figure 1 One of the paths in is the route from the starting point P1 to the end point P5, which consists of five path points P1, P2, P3, P4, and P5. L1 is the Euclidean distance between the path points (P1, P2), L2 is the Euclidean distance between the path points (P2, P3), L3 is the Euclidean distance between the path points (P3, P4), and L4 is the Euclidean distance between the path points (P4, P5).

[0060] In addition, the path length s from the starting point to each path point can also be defined as: s(P1)=0, s(P2)=L1, s(P3)=L1+L2, s(P4)=L1+L2+L3, s(P5)=L1+L2+L3+L4, where s(P1) is the path length from the starting point P1 to the path point P1, s(P2) is the path length from the starting point P1 to the path point P2, s(P3) is the path length from the starting point P1 to the path point P3, s(P4) is the path length from the starting point P1 to the path point P4, and s(P5) is the path length from the starting point P1 to the end point P5.

[0061] Figure 1 The path point sequence of the path can also be expressed according to the above path length s as: {(x(0), y(0), yaw(0)), (x(L1), y(L1), yaw(L1)), ..., (x(s(P5)), y(s(P5)), yaw(s(P5)))}, wherein x(0), x(L1), ..., x(s(P5)) respectively represent the values ​​of the first coordinates of the path points P1, P2, ..., P5, y(0), y(L1), ..., y(s(P5)) respectively represent the values ​​of the second coordinates of the path points P1, P2, ..., P5, and yaw(0), yaw(L1), ..., yaw(s(P5)) respectively represent the heading angles when the vehicle travels to the corresponding positions of the path points P1, P2, ..., P5.

[0062] You can also use s on each path point as an independent attribute, so that Figure 1 Each path point in the path can also be expressed in the form of (x, y, yaw, s). For example, path point P1 can be expressed as: (x(0), y(0), yaw(0), 0), and path point P2 can be expressed as: (x(L1), y(L1), yaw(L1), L1).

[0063] Smart driving vehicles usually travel at a low speed when driving in a parking lot. In addition, the roads in parking lots are usually narrow. Therefore, if other vehicles appear behind the smart driving vehicle, it is difficult for the rear vehicle to change lanes and overtake. It is easy for the smart driving vehicle to suppress the speed of the rear vehicle, making it difficult for the rear vehicle to pass quickly.

[0064] like Figure 2 In the parking lot scene shown, there are parking spaces on both sides of the parking lot. The first vehicle is a smart driving vehicle, and the second vehicle is another vehicle behind the first vehicle. The first vehicle and the second vehicle are moving in the same direction. When the first vehicle is traveling at a low speed, it will suppress the speed of the second vehicle behind it. And because the road is narrow, it is difficult for the second vehicle to change lanes and overtake the first vehicle, making it difficult for the second vehicle to pass quickly.

[0065] In this case, if the first vehicle fails to react in time to avoid the second vehicle behind it, the speed of the second vehicle will be suppressed by the first vehicle for a long time, which may easily cause dissatisfaction among the driver or passengers of the second vehicle and lead to a conflict.

[0066] Specifically, the above situation may occur at any stage when the first vehicle is driving in the parking lot. For example, the above any stage may include: the first vehicle is looking for a parking space in the parking lot, the first vehicle has found a parking space and is preparing to park in the parking space, or the first vehicle is parking in the parking space. For the situation of suppressing the speed of the rear vehicle occurring at any of the above stages, the following vehicle yielding method provided by the present application may be used to control the first vehicle to yield.

[0067] In view of the above situation, in order to reduce the suppression of the speed of the following vehicles by the intelligent driving vehicle, it is necessary to provide a vehicle giving way.

[0068] The present application embodiment provides a vehicle giving way method, such as Figure 3 As shown, the method includes the following steps S301-S305.

[0069] For ease of description, the following description uses a control device as the executor of the vehicle giving way method. The control device may be a controller mounted on the first vehicle, and may also be referred to as a vehicle-mounted controller.

[0070] Step S301: Determine whether there is a second vehicle traveling at a reduced speed behind the first vehicle based on an image captured by an image capture device carried by the first vehicle.

[0071] The first vehicle may be an intelligent driving vehicle. When the first vehicle enters a parking lot, it may travel along a teaching path in the parking lot, or it may be driven manually by a driver. The teaching path is a path recorded by the first vehicle in which the driver manually drives the first vehicle. The first vehicle may record teaching paths in which the driver manually drives the first vehicle in different scenarios. When entering each scenario, the first vehicle may travel along the teaching path in the scenario.

[0072] The first vehicle is equipped with an image acquisition device. The image acquisition device can acquire images of the environment around the first vehicle and upload the acquired images to a control device mounted on the first vehicle. The control device can obtain the acquired images uploaded by the image acquisition device, or the control device can also send a request to the image acquisition device to obtain the images acquired by the image acquisition device.

[0073] The control device can identify the vehicle located behind the first vehicle in the image captured by the acquired image acquisition device, and then determine whether there is a second vehicle driving at a reduced speed behind the first vehicle based on the positional relationship between the identified vehicle and the first vehicle. The second vehicle can be an intelligent driving vehicle or a manually driven vehicle, which is not limited.

[0074] In a possible implementation, the control device can determine whether there is a second vehicle driving at a high speed behind the first vehicle by judging whether each identified vehicle has maintained a fixed distance from the first vehicle for more than a preset time. Specifically, if the control device judges that there is a vehicle among the identified vehicles that has maintained a fixed distance from the first vehicle for more than a preset time, the control device can determine that there is a second vehicle driving at a high speed behind the first vehicle; if the control device judges that there is no vehicle among the identified vehicles that has maintained a fixed distance from the first vehicle for more than a preset time, the control device can determine that there is no second vehicle driving at a high speed behind the first vehicle. The preset time can be set according to actual conditions.

[0075] In another possible implementation, the control device may also determine whether there is a second vehicle driving at a high speed behind the first vehicle by determining whether the distance between each identified vehicle and the first vehicle is less than the safe distance. Specifically, if the control device determines that there is a vehicle among the identified vehicles whose distance to the first vehicle is less than the safe distance, the control device may determine that there is a second vehicle driving at a high speed behind the first vehicle; if the control device determines that there is no vehicle among the identified vehicles whose distance to the first vehicle is less than the safe distance, the control device may determine that there is no second vehicle driving at a high speed behind the first vehicle. The safe distance may be adjusted according to at least one of the speed limit of the road on which the first vehicle is currently traveling, the actual speed of the first vehicle, and the actual speed of the second vehicle.

[0076] Step S302: If there is a second vehicle, a planned path for the second vehicle is generated based on the reference path and environmental information of the parking lot.

[0077] In a possible implementation, the reference path may be a straightened path corresponding to the taught path of the first vehicle in the parking lot. The straightened path is a path obtained by straightening the taught path. The straightening process may transform a local curved path of the path into a straight path. The straightened path may be used as the center line of the lane in which the first vehicle is currently traveling.

[0078] like Figure 4In an example shown, the teaching path a represented by a solid line includes path points represented by five solid circles a1, a2, a3, a4, and a5. After the control device straightens the teaching path a, a straightened path A represented by a dotted line is obtained. The straightened path A includes five path points a1, a6, a3, a7, and a5. Figure 4 The two hollow dots a6 and a7 shown in the figure are the path points re-selected from the straightened path.

[0079] In a possible implementation, if the first vehicle is manually driven by a driver, in this scenario, the reference path may also be: a combination of the path that the first vehicle has already traveled and the predicted path that the first vehicle will travel in the next period of time, or a path obtained by straightening the above combined path.

[0080] When a vehicle is driving, it will usually bump due to uneven road conditions, and the teaching path recorded by the first vehicle or the path manually driven by the driver will also have a partially curved path. The control device can straighten the teaching path or the path manually driven by the driver, and transform these partially curved paths into straight paths, so that path planning can be performed based on the reference path obtained after the straightening process. The specific straightening process will be described in detail later, and will not be described here.

[0081] The environmental information of the parking lot includes: the structure of the parking lot, other traffic participants currently in the parking lot, lane lines in the parking lot, obstacles in the parking lot that hinder vehicle travel, and the like.

[0082] If the control device determines that there is a second vehicle traveling at a reduced speed behind the first vehicle, the control device may first obtain environmental information and a reference path, and then generate a planned path for the second vehicle based on the reference path and the environmental information.

[0083] The control device may obtain environmental information collected by the environmental information collection device from the environmental information collection device carried by the first vehicle, or may obtain environmental information from a pre-constructed scene model of the parking lot.

[0084] After acquiring the environmental information, the control device can determine the obstacle area of ​​the second vehicle in combination with the environmental information and the reference path, and generate a planned path for the second vehicle to travel.

[0085] Specifically, the control device can determine the area that the first vehicle will pass through when driving based on the reference path, and determine the area where obstacles that hinder the driving of vehicles are located in the parking lot based on the environmental information of the parking lot. When the control device generates the planned path for the second vehicle to drive, the planned path avoids the area that the first vehicle will pass through when driving, and the area where obstacles that hinder the driving of vehicles are located in the parking lot. When generating the planned path here, a preset path planning algorithm can be used to generate the planned path. For example, the above-mentioned preset algorithm can be a heuristic search algorithm, an ant colony algorithm, a dynamic programming algorithm, etc., which is not limited to this.

[0086] If the control device determines that there is no second vehicle driving at a reduced speed behind the first vehicle, the first vehicle may continue to travel, such as by the driver manually driving the first vehicle or continuing to travel according to the taught path.

[0087] Step S303: determining a planned passage area for the second vehicle to travel along the planned route based on the vehicle information of the second vehicle.

[0088] The vehicle information of the second vehicle may include the body length and body width of the second vehicle. The control device may identify the vehicle in the image captured by the image capture device, and then obtain the vehicle information such as the body length and body width of the second vehicle in the image.

[0089] The control device may use the second vehicle as a rectangular frame according to the vehicle information of the second vehicle, and determine the area covered by the rectangular frame when the second vehicle travels along the planned path. Specifically, the control device may use each path point on the planned path as the center point of the rectangular frame, and determine the area covered by the rectangular frame when the second vehicle travels along the planned path.

[0090] like Figure 5 As shown, Figure 5 The dotted line with an arrow in the middle is the planned path, and the dots marked on the dotted line are the path points of the planned path. Each dotted rectangular box represents the area covered by the body of the second vehicle when the second vehicle drives to the path point corresponding to the center position of the rectangular box.

[0091] The control device can Figure 5 The rectangular box areas corresponding to all the path points in the are directly used as the planned passage areas.

[0092] The control device may also perform curve fitting processing on the boundaries of each rectangular frame to obtain two smooth planned traffic area boundaries, and use the area between the two determined planned traffic area boundaries as the planned traffic area. Figure 6 As shown, the control device Figure 5Curve fitting is performed on the side boundaries of each rectangular frame area to obtain two smooth curves, solid line b and solid line c, so that the control device can use the area between the solid line b and the solid line c as the planned passage area.

[0093] Step S304: Generate a yield path for the first vehicle based on the environmental information.

[0094] Among them, the end point of the yield path is outside the planned traffic area.

[0095] The control device can determine the area where obstacles that hinder the vehicle's travel are located in the parking lot based on the environmental information. In addition, the control device can also determine a yielding end point outside the planned passage area.

[0096] In this way, when generating the yield path for the first vehicle, the control device can generate a yield path that starts from the current position of the first vehicle and ends at the yield end point determined above, and does not pass through the area where obstacles that hinder vehicle travel are located in the parking lot. The yield path generated in this way may pass through the planned passage area, but the yield end point where the first vehicle finally stops is not in the planned passage area, and thus will not hinder the second vehicle from traveling along the planned path.

[0097] In addition, the control device can also regard the planned passage area as an obstacle area.

[0098] In this way, when generating the yield path for the first vehicle, the control device can generate a yield path that starts from the current position of the first vehicle and ends at the yield end point determined above, and does not pass through the area where obstacles that hinder the vehicle's travel are located in the parking lot and the planned traffic area. From a visual perspective, this is equivalent to blackening the planned traffic area and the area where obstacles that hinder the vehicle's travel are located in the parking lot, and the yield path planned by the control device for the first vehicle will not pass through the blackened area. The yield path generated in this way does not pass through the planned traffic area, and at any time during the entire yield process, the first vehicle will not hinder the second vehicle from traveling along the planned path.

[0099] When generating the yield path here, a preset path planning algorithm may be used to generate the yield path. For example, the preset algorithm may be a heuristic search algorithm, an ant colony algorithm, a dynamic programming algorithm, etc., and there is no limitation on this.

[0100] Step S305, controlling the first vehicle to travel along the yield path.

[0101] After determining the yield path, the control device can control the first vehicle to travel along the yield path. Specifically, the control device can generate the control amount required to be executed by each actuator in the first vehicle according to the yield path, and then control each actuator to execute the control amount, so as to drive the first vehicle to travel along the yield path. The actuator may include: a steering actuator, a power actuator, a brake actuator, etc. The steering actuator can change the heading angle of the vehicle, the power actuator can change the speed and acceleration of the vehicle, and the brake actuator can change the speed and acceleration of the vehicle.

[0102] In addition, the above steps S301 to S305 are only one process in the process of giving way. In actual scenarios, the control device can execute the above step S301 multiple times to determine in real time whether there is a second vehicle that is being slowed down behind the first vehicle. When it is determined that there is a second vehicle, the control device executes the subsequent steps S302-S305 to give way to the vehicle. During the process of giving way, the control device will still execute the above steps S301-S305 multiple times, so as to continuously update the giving way path and control the first vehicle to continue driving according to the updated giving way path, so as to timely avoid according to the environmental information in the parking lot and the driving status of other vehicles such as the second vehicle.

[0103] In the technical solution provided by the embodiment of the present application, it is first determined based on the collected image whether there is a second vehicle driving at a reduced speed behind the first vehicle. When there is a second vehicle driving at a reduced speed behind the first vehicle, a planned driving path is actively planned for the second vehicle based on the reference path and the environmental information of the parking lot, and it is expected that the second vehicle will drive along the planned path to surpass the first vehicle during the subsequent driving process. Especially in the scenario where the lanes in the parking lot are narrow, the probability of the second vehicle driving along the planned path increases. In order to further increase the probability of the second vehicle driving along the planned path, a yield path with an end point outside the planned passage area that the second vehicle will pass through when driving along the planned path can also be planned for the first vehicle, and the first vehicle is controlled to drive along the yield path, thereby giving up the planned passage area for the second vehicle. In this way, the probability of the second vehicle driving along the planned path to surpass the first vehicle can be further increased, thereby reducing the suppression of the driving speed of the second vehicle by the first vehicle, and avoiding conflicts or collisions between the first vehicle and the second vehicle. By applying the technical solution provided in the embodiments of the present application, the intelligent driving vehicle can promptly give way to the vehicle behind it when a speed reduction situation occurs, thereby reducing the intelligent driving vehicle's suppression of the speed of the vehicle behind it, avoiding conflicts or collisions with other vehicles, and improving the driving safety of the intelligent driving vehicle.

[0104] The following describes a method for determining whether there is a second vehicle traveling at a high speed.

[0105] In a possible implementation, the Figure 7The method shown in the figure determines whether there is a second vehicle traveling at a reduced speed behind the first vehicle, that is, the above step S301 can be implemented by the following steps S701-S704.

[0106] Step S701, determining a plurality of first path points located behind a first vehicle on a reference path.

[0107] The control device can obtain the positioning information collected by the positioning device carried by the first vehicle, determine the location of the first vehicle according to the positioning information, and then determine the corresponding position of the first vehicle on the reference path, and then determine the multiple first path points behind the first vehicle according to the corresponding position of the first vehicle on the reference path. The connecting line of the corresponding position of the first vehicle on the reference path is perpendicular to the direction of the lane line.

[0108] In a possible implementation, the control device may further combine the above positioning information and the vehicle information of the first vehicle, such as the body length of the first vehicle, to determine the first path point. Specifically, the control device may determine the position of the first vehicle determined according to the above positioning information as the position of the body center of the first vehicle, and then extend the above determined position of the body center of the first vehicle backward by half of the body length to obtain the position of the rear of the first vehicle, and then determine the corresponding position of the rear of the first vehicle on the reference path, and then determine multiple first path points located behind the rear of the first vehicle based on the corresponding position of the rear of the first vehicle on the reference path.

[0109] The distance between the first path point and the first vehicle is less than a first preset distance. The first preset distance can be determined based on at least one of the following information: the farthest distance that can be captured by the image acquisition device of the first vehicle, the speed limit of the road currently traveled by the first vehicle, the actual travel speed of the first vehicle, and the actual travel speed of the second vehicle.

[0110] When determining the first path point, the control device can select all path points on the reference path that are located behind the first vehicle and whose distance from the first vehicle is less than a first preset distance as the first path points, or it can sample from all the above path points and use the sampled points as the first path points.

[0111] Step S702: Based on the positions of each pair of adjacent first path points, a virtual lane area corresponding to each pair of adjacent first path points is generated.

[0112] How to determine the virtual lane area will be described in detail later and will not be described in detail here.

[0113] Step S703: Based on the image captured by the image capture device carried by the first vehicle, it is detected whether the duration of the vehicle appearing in the vehicle following detection area is greater than a first preset duration. If so, the following step S704 is executed.

[0114] The vehicle following detection area is determined based on the generated virtual lane area.

[0115] In a possible implementation, the control device may directly use the set of all virtual lane areas determined above as the vehicle following detection area. Figure 8 As shown, the areas represented by the three dashed rectangular boxes S1, S2, and S3 are respectively virtual lane areas corresponding to the three pairs of adjacent first path points in the figure, that is, the areas represented by the virtual lane areas S1, S2, and S3 are respectively virtual lane areas corresponding to the three pairs of adjacent first path points, namely, the first path point 1 and the first path point 2, the first path point 2 and the first path point 3, and the first path point 3 and the first path point 4. The control device can determine the areas represented by S1, S2, and S3 as the vehicle following detection areas.

[0116] In a possible implementation manner, the control device may also integrate all the virtual lane areas determined above, and use the integrated area as the vehicle following detection area. Figure 8 As shown, the control device can integrate the three rectangular areas represented by S1, S2, and S3 into a large rectangular area, such as Figure 8 The area represented by the solid rectangular box includes the three virtual lane areas represented by S1, S2, and S3.

[0117] After determining the vehicle following detection area, the control device can detect whether a vehicle appears in the vehicle following detection area in the image captured by the image acquisition device, and if a vehicle appears, detect whether the duration of the appearance of the vehicle in the image captured by the image acquisition device is greater than a first preset duration. Specifically, the control device can determine the duration of the vehicle appearance based on the number of frames in which the vehicle appears in the captured image, or the start time and end time of the vehicle appearance.

[0118] Step S704: Determine the vehicle whose appearance duration is greater than the first preset duration as the second vehicle.

[0119] When the control device detects that a vehicle exists in the following vehicle detection area for a time period greater than a first preset time period, the control device may determine the vehicle as a second vehicle traveling at a reduced speed.

[0120] Above Figure 7A more accurate method for determining the second vehicle is provided, which can more accurately determine whether there is a vehicle driving at a low speed behind the intelligent driving vehicle, and thus can avoid the vehicle behind more promptly, further reducing the intelligent driving vehicle's suppression of the speed of the vehicle behind, better avoiding conflicts or collisions between the intelligent driving vehicle and other vehicles, and further improving the driving safety of the intelligent driving vehicle.

[0121] In a possible implementation manner, for each pair of adjacent first path points, Fig. 9 The virtual lane area corresponding to each pair of adjacent first path points is generated in the manner shown, that is, the above step S702 can be implemented through the following steps S901-S902.

[0122] Step S901: Taking the line connecting the pair of adjacent first path points as the center line of the first lane on which the first vehicle is traveling, a first virtual lane area of ​​the first lane is determined.

[0123] The control device may first generate a first virtual lane area of ​​the first lane in which the first vehicle is traveling. When generating the first virtual lane area, the control device may use the pair of adjacent first path points as the lane centerline of the first virtual lane area, and then extend to both sides of the lane centerline connected by the pair of adjacent first path points according to the pre-acquired lane width to determine the first virtual lane area.

[0124] In an example, Fig.10 As shown in the figure, assuming that the first vehicle is currently driving in the right lane, the control device pre-acquires that the lane width is 3.5 meters. For the first path point 1 and the first path point 2, which are adjacent first path points, the control device can use the line connecting the first path point 1 and the first path point 2 (not shown in the figure) as the center line of the right lane, and extend 1.75 meters to both sides to obtain Fig.10 The first virtual lane area is represented by the rectangular box in the figure.

[0125] Step S902: constructing a second virtual lane area by taking the first area boundary of the first virtual lane area as the boundary of the second virtual lane area.

[0126] The second virtual lane area is: a virtual lane area of ​​an opposite lane to the first lane.

[0127] The control device may first determine the number of lanes in the parking lot based on a pre-stored environment model of the parking lot. If the parking lot has only one lane, the control device may determine that there is no opposite lane in the first lane, and thus there is no need to construct a second virtual lane area.

[0128] If the parking lot includes two opposite lanes, the control device may first determine the direction of the opposite lane of the first lane according to the pre-stored traffic rules of the parking lot where the first vehicle is currently traveling. For example, if the traffic rules of the parking lot where the first vehicle is currently traveling are to drive on the right, the first vehicle may determine that the opposite lane of the first lane is on the left side of the first lane.

[0129] The control device may select the area boundary of the first virtual lane area located on one side of the direction of the opposite lane of the first lane as the boundary of the second virtual lane area. For example, if the object lane of the first lane is on the left side of the first lane, the control device may select the area boundary on the left side of the first virtual lane area as the boundary of the second virtual lane area.

[0130] Furthermore, the control device may extend to the other side of the boundary of the second virtual lane area selected above to determine the second virtual lane area.

[0131] Continuing from the above Fig.10 For example, the first lane is the right lane, and the opposite lane to the first lane is the left lane. The control device can first determine that the parking lot includes two lanes based on the pre-stored environment model of the parking lot; then the control device can determine that the opposite lane to the first lane where the first vehicle is traveling is on the left side of the first lane based on the pre-stored traffic rules of the parking lot where the first vehicle is currently traveling, which is to drive on the right; then the control device can Fig.10 The left boundary of the first virtual lane area is used as the right boundary of the second virtual lane area, and extended to the left by 3.5 meters to obtain Fig.11 The virtual lane area of ​​the left lane is shown, namely the second virtual lane area.

[0132] By combining the first virtual lane area and the second virtual lane area, the virtual lane area corresponding to the pair of adjacent first path points can be obtained.

[0133] like Fig.12 As shown, the second virtual lane area on the left and the first virtual lane area on the right are the virtual lane areas corresponding to the first path point 1 and the first path point 2, a pair of adjacent first path points.

[0134] The control device may generate a virtual lane area corresponding to each pair of adjacent first path points according to the above steps S901-S902.

[0135] Using the above Fig. 9The provided method can more accurately determine the virtual lane area corresponding to the lane in which the first vehicle is traveling, so that the following vehicle detection area can be more accurately determined based on the above-determined virtual lane area, and thus it can be more accurately determined whether there is a vehicle driving at a low speed behind the intelligent driving vehicle according to the above-determined following vehicle detection area, and thus the rear vehicle can be avoided more timely, further reducing the intelligent driving vehicle's suppression of the rear vehicle's driving speed, better avoiding conflicts or collisions between the intelligent driving vehicle and other vehicles, and further improving the driving safety of the intelligent driving vehicle.

[0136] The following is an introduction to the method of generating a planned path.

[0137] In a possible implementation, the above-mentioned planned path may be generated in the following manner: Fig.13 The step of generating a planned path in the above step S302 can be implemented through the following steps S1301-S1302.

[0138] Step S1301: obtaining regional sampling points in a first traversable area based on environmental information.

[0139] The first traversable area is an area where there are no obstacles on both sides of the reference path.

[0140] The control device can determine the area where the obstacles that hinder the vehicle's travel are located in the parking lot based on the environmental information, and determine the area that the first vehicle passes through when traveling along the reference path in combination with the reference path. Then, the control device can use the areas on both sides of the reference path that are not the areas where the obstacles that hinder the vehicle's travel are located as the first passable area.

[0141] In a possible implementation, the control device may directly perform sampling in the first traversable area to obtain area sampling points.

[0142] like Fig.14 As shown in FIG. 1 , the horizontal direction is the reference path direction, the vertical direction is the direction perpendicular to the reference path, and the area between the solid line d and the solid line e is the first passable area. The control device performs sampling in the area between the solid line d and the solid line e to obtain the area sampling points as shown in FIG. Fig.14 The hollow dots in the .

[0143] In another possible implementation, the control device may first perform sampling on the road on which the second vehicle is currently traveling to obtain initial sampling points, and then determine regional sampling points in the initial sampling points located in the first passable area in combination with the first passable area.

[0144] like Fig.15As shown in FIG. 1 , the horizontal direction is the reference path direction, the vertical direction is the direction perpendicular to the reference path, and the area between the solid line d and the solid line e is the first passable area. The control device first performs sampling on the current driving road of the first vehicle to obtain the initial sampling point such as Fig.15 The control device then combines the first passable area between the solid line d and the solid line e to determine that the hollow dots between the solid line d and the solid line e are regional sampling points. Fig.15 In the process, sampling is carried out at equal intervals, where the longitudinal sampling interval is 1 meter, that is, the interval between two adjacent sampling points on the left and right is 1 meter; the transverse sampling interval is 0.5 meter, that is, the interval between two adjacent sampling points on the top and bottom is 0.5 meter.

[0145] Step S1302, performing path planning in the first passable area, obtaining a path with the smallest distance statistical characteristic value between the obtained regional sampling points as the planned path.

[0146] The distance statistical characteristic value may be the sum of squares, the sum of absolute values, etc. of the distances between the path points on the planned path and the regional sampling points. The control device may calculate the above distance statistical characteristic values ​​of the distances between the planned path and the regional sampling points, and then use the path with the smallest distance statistical characteristic value between the planned paths and the regional sampling points as the planned path.

[0147] In a possible implementation, the control device may calculate the sum of squares of distances between each planned path point and the regional sampling points in a direction perpendicular to the reference path direction, and use the sum of squares as a statistical characteristic value of the distance between the planned path and the regional sampling points.

[0148] like Fig.16 As shown, path f is one of the paths planned by the control device for the second vehicle. The control device can calculate the distance between the path point f1 on path f and the regional sampling points (x1, y11), (x1, y12), (x1, y13), the distance between the path point f2 and the regional sampling points (x2, y21), (x2, y22), (x2, y23), and the subsequent path points f3, f4, ..., fN and so on. Then, the control device can calculate the sum of the squares of the above distances and use the calculated sum of the squares as the statistical characteristic value of the distance between the path f and the regional sampling points.

[0149] Using the above Fig.13 The provided method for determining the planned path can ensure a certain accuracy while reducing the amount of calculation compared to other path planning algorithms such as heuristic search algorithm, ant colony algorithm, and dynamic programming algorithm.

[0150] In a possible implementation manner, the control device may perform path planning of the above-mentioned planned path in the first traversable area according to the following expression:

[0151] ;

[0152] Where x represents the coordinate value of the path point along the reference path direction on the planned path. Represents the coordinate values ​​of the path points of the planned path along a first direction, where the first direction is perpendicular to the reference path direction. , …, , , is the coefficient in the above expression corresponding to the planned path, and different paths have different coefficients. The above n can be any preset positive integer, and the specific value can be adjusted according to actual needs. In an example, the value of the above n can be 5.

[0153] Specifically, the control device can randomly generate m groups , …, , , The coefficient values ​​of , and based on the m sets of coefficient values, respectively generate m paths according to the above expression, where m is any preset integer value. For example, n is 5, m is 100, and the control device generates a set of coefficients of 2, 5, -3, 3, 2, 4. Then the control device can further generate a path based on the set of coefficients as follows:

[0154] ;

[0155] The control device can also generate 99 other paths according to the other 99 groups of coefficients.

[0156] The subsequent control device may calculate the distance statistical characteristic values ​​respectively according to the above step S1302 based on the 100 paths generated above, and determine the path with the smallest distance statistical characteristic value among the above 100 paths as the planned path.

[0157] Compared with path planning algorithms such as heuristic search algorithm, ant colony algorithm, dynamic programming algorithm, etc., the use of the above polynomial expression for path planning can further reduce the amount of calculation, reduce the required computing resources, and ensure a certain accuracy.

[0158] In addition, when calculating the above distance statistical characteristic value, the planned path can also be expressed according to the above expression. Fig.16 For example, the path f can be expressed as follows:

[0159] ;

[0160] Where x represents the coordinate value of the path point of path f along the reference path direction, represents the coordinate value of the path point of path f along the first direction. The sum of the squares of the distances between each path point on path f and the regional sampling point J can be expressed as:

[0161] ;

[0162] Wherein, N is the maximum number of regional sampling points along the reference path direction, M is the maximum number of regional sampling points along the first direction, is the coordinate value of the jth path point on path f along the reference path direction, is the coordinate value of the jth path point on path f along the first direction. The coordinate value along the reference path is The coordinate value of the sampling point of the i-th region along the first direction. is the distance between the j-th path point on the path f and the i-th regional sampling point in the same first direction.

[0163] In one possible implementation, after planning a planned path and determining a planned traffic area for the second vehicle traveling along the planned path, the control device can also detect whether the second vehicle is at risk of colliding with obstacles in the parking lot when traveling along the above-mentioned planned path, and if the above-mentioned risk does not exist, continue to generate a yield path for the first vehicle based on the planned traffic area corresponding to the planned path.

[0164] Based on this, the present application embodiment also provides Fig.17 A vehicle giving way method is shown, the method comprising the following steps S1701-S1706.

[0165] Step S1701, based on the image captured by the image capture device carried by the first vehicle, determines whether there is a second vehicle traveling at a reduced speed behind the first vehicle, which is the same as the above step S301.

[0166] Step S1702, if there is a second vehicle, a planned path for the second vehicle is generated based on the reference path and environmental information of the parking lot, which is the same as the above step S302.

[0167] Step S1703, based on the vehicle information of the second vehicle, determining the planned passage area for the second vehicle to travel along the planned path, which is the same as the above step S303.

[0168] Step S1704, based on the environmental information, detect whether the planned passage area has the risk of collision with obstacles in the parking lot; if not, execute step S1705.

[0169] The control device may first obtain information about obstacles that hinder vehicle travel in the parking lot from environmental information, determine the area where the obstacles are located in the parking lot, and then detect whether there is overlap between the planned passage area and the area where the obstacles are located.

[0170] If the control device detects that the planned passage area overlaps with the area where the obstacle is located, it means that the planned passage area is at risk of colliding with the obstacle in the parking lot; if the control device detects that the planned passage area does not overlap with the area where the obstacle is located, it means that the planned passage area does not have the risk of colliding with the obstacle in the parking lot.

[0171] If the planned passage area has a risk of colliding with obstacles in the parking lot, the second vehicle will definitely not travel along the planned path corresponding to the planned passage area, and the control device can ignore the planned path corresponding to the planned passage area.

[0172] In a possible implementation manner, the control device may also regenerate the planned path of the second vehicle, that is, re-execute the above step S1702.

[0173] In another possible implementation, the control device may determine that the yielding condition is not met at present, and even if the first vehicle yields, it is difficult for the second vehicle to change lanes and overtake. In this case, the control device may not need to control the first vehicle to yield, and the first vehicle continues to drive normally according to the taught path.

[0174] If the planned passage area does not have the risk of colliding with obstacles in the parking lot, it means that the planned path corresponding to the planned passage area is relatively reasonable. The first vehicle can subsequently generate a yield path for the first vehicle based on the planned passage area, that is, execute the subsequent step S1705.

[0175] Step S1705, based on the environmental information, generating a yield path for the first vehicle, which is the same as the above step S304.

[0176] Among them, the end point of the yield path is outside the planned traffic area.

[0177] Step S1706, controlling the first vehicle to travel along the yield path, is the same as the above step S305.

[0178] In this way, the rationality of the planned traffic area that the second vehicle will pass through as determined above is improved, and the rationality of the yield path generated by the control device based on the planned traffic area is also improved. As a result, the first vehicle can avoid the second vehicle more accurately and avoid collision with the second vehicle, further improving the safety of the intelligent driving vehicle.

[0179] The following is an introduction to the method of generating a yield path.

[0180] In a possible implementation, the yield path may be generated in the following manner: Fig.18 The step of generating a yield path in the above step S304 can be implemented through the following steps S1801-S1802.

[0181] Step S1801: obtaining area sampling points in a first traversable area based on environmental information.

[0182] The first passable area is an area in front of the first vehicle in the parking lot, outside the planned passable area, and where no obstacles exist.

[0183] The control device can determine the area where the obstacles that hinder the driving of vehicles are located in the parking lot based on the environmental information, and determine the area in front of the first vehicle in the parking lot, outside the planned passage area, and without obstacles in combination with the planned passage area. Then, the control device can use the above-determined area as the first passable area.

[0184] When determining the first passable area, the control device may update the above-mentioned planned passable area in the scene model storing the environmental information. Fig.19 As shown, Fig.19 is the updated scene model, where the three dashed curves on the left and right are the left and right boundaries of the planned traffic area, and the middle dashed curve is the planned path. The scene model pre-stores information about parking spaces, obstacles, etc. in the parking lot.

[0185] The control device can directly perform sampling in the first passable area to obtain regional sampling points. The control device can also first perform sampling on the road where the second vehicle is currently traveling to obtain initial sampling points, and then determine the regional sampling points located in the first passable area among the initial sampling points in combination with the first passable area. Fig.14 and Fig.15 The explanation will not be repeated here.

[0186] Step S1802, path planning is performed in the first passable area to obtain a path with the smallest distance statistical characteristic value between the obtained regional sampling points as the yield path.

[0187] The distance statistical characteristic value may be the sum of squares, the sum of absolute values, etc. of the distances between the path points on the planned path and the regional sampling points. The control device may calculate the above distance statistical characteristic value of the distances between the planned path and the regional sampling points, and then use the path with the smallest distance statistical characteristic value between the planned paths and the regional sampling points as the yield path.

[0188] In a possible implementation, the control device may calculate the sum of squares of distances between each planned path point and the regional sampling points in a direction perpendicular to the reference path direction, and use the sum of squares as a statistical characteristic value of the distance between the planned path and the regional sampling points.

[0189] Using the above Fig.18 The provided method for determining the yield path has a lower computational complexity and can also ensure a certain degree of accuracy compared to other path planning algorithms such as heuristic search algorithm, ant colony algorithm, and dynamic programming algorithm.

[0190] In a possible implementation manner, the control device may perform path planning of the yield path in the first traversable area according to the following expression:

[0191] ;

[0192] Where x represents the coordinate value of the path point along the reference path direction on the planned path. Represents the coordinate values ​​of the path points of the planned path along a first direction, where the first direction is perpendicular to the reference path direction. , …, , , is the coefficient in the above expression corresponding to the planned path, and the coefficients of different paths are different. The above n can be any positive integer, and the specific value can be adjusted according to actual needs. In an example, the value of the above n can be 5.

[0193] Specifically, the control device can randomly generate m groups , …, , , The coefficient values ​​of , and based on the m sets of coefficient values, respectively generate m paths according to the above expression, where m is any preset integer value. For example, n is 5, m is 100, and the control device generates a set of coefficients of 2, 5, -3, 3, 2, 1. Then the control device can further generate a path based on the set of coefficients as follows:

[0194] ;

[0195] The control device can also generate 99 other paths according to the other 99 groups of coefficients.

[0196] The subsequent control device may calculate the distance statistical characteristic values ​​respectively according to the above step S1802 based on the 100 paths generated above, and determine the path with the smallest distance statistical characteristic value among the above 100 paths as the yield path.

[0197] Compared with path planning algorithms such as heuristic search algorithm, ant colony algorithm, dynamic programming algorithm, etc., the use of the above polynomial expression for path planning of the yield path can further reduce the amount of calculation, reduce the required computing resources, and ensure a certain degree of accuracy.

[0198] When generating the yield path, the control device may also predetermine the end point of the yield path. Based on this, the embodiment of the present application also provides the following Fig. 20 The method for generating a yield path shown, that is, the step of generating a yield path in the above step S304 can be implemented through the following steps S2001-S2002.

[0199] Step S2001, based on environmental information, determine the yielding end point of the first vehicle from a second passable area in front of the first vehicle in the parking lot, outside the planned passable area, and without obstacles.

[0200] The control device may randomly determine the yielding end point of the first vehicle from the second passable area. Fig.21 As shown, the control device can determine the parking space without obstacles on the right as the end point of giving way.

[0201] Step S2002: Based on the environmental information, a path is planned in the second traversable area with the yielding end point as the path end point to obtain a yielding path for the first vehicle.

[0202] The control device can determine the area where obstacles that hinder the driving of vehicles are located in the parking lot based on the environmental information. When generating the yield path for the first vehicle, the end point of the yield path avoids the planned passage area that the second vehicle will pass through when driving, and the area where obstacles that hinder the driving of vehicles are located in the parking lot. When generating the yield path here, a preset path planning algorithm can be used to generate the yield path. For example, the preset algorithm can be a heuristic search algorithm, an ant colony algorithm, a dynamic programming algorithm, etc., which is not limited to this.

[0203] The control device can also be used in the same way as above Fig.18 The yield path is determined in a similar manner. Specifically, the yield path can be determined as follows: based on the environmental information, the regional sampling points in the second passable area are obtained; a path with the end point being the yield end point is planned in the second passable area, and the path with the smallest distance statistical characteristic value between the obtained regional sampling points is obtained as the yield path. And, according to the above expression:

[0204] ;

[0205] When planning the yield path, it is necessary to ensure that the coordinate value of the yield endpoint along the reference path direction and the coordinate value along the first direction satisfy the above expression.

[0206] In one example, the control device determines a yield path for the first vehicle as follows: Fig. 22 shown. Fig. 22 The path from the current position of the first vehicle to the yielding end point is the yielding path.

[0207] Using the above Fig. 20 The provided yield path generation method first determines the yield endpoint, and then generates the yield path with the yield endpoint as the path endpoint. Since the yield endpoint is determined, the obtained yield path is relatively stable and will not change with each generation of the yield path. Therefore, when the first vehicle is controlled to travel based on the above-generated yield path, the driving path of the first vehicle is relatively stable, thereby improving the safety of the first vehicle.

[0208] After generating the yield path of the first vehicle according to any of the above methods and controlling the first vehicle to travel along the yield path, the control device can also monitor whether the yield is completed, and when the yield is completed, plan a return path for the first vehicle and control the first vehicle to resume traveling along the taught path. Based on this, the embodiment of the present application also provides the following yield recovery method, such as Fig.23 As shown, the method includes the following steps S2301-S2305.

[0209] Step S2301, monitoring whether the preset yielding end condition is met. If so, executing step S2302.

[0210] The yield end condition may include at least one of the following conditions 1 to 3.

[0211] Condition 1: The second vehicle exits the overtaking detection area.

[0212] Among them, the overtaking detection area is: an area determined by a virtual lane area generated based on each pair of adjacent second path points, and the second path points are: multiple path points located in front and behind the first vehicle on the reference path, and the distance between the second path points and the first vehicle is less than a second preset distance.

[0213] The method for determining the overtaking detection area can refer to the method for generating the following vehicle detection area, and specifically, refer to the relevant description of step S703; the method for generating the virtual lane area can refer to the method for generating the following vehicle detection area. Fig. 9 The relevant instructions will not be repeated here.

[0214] In an example, Fig.24 As shown, the overrun detection zone can be based on Fig.24 Specifically, the overtaking detection area may include the areas represented by T1, T2, T3, T4, and T5, respectively; or it may include a large rectangular area formed by integrating these five areas, such as Fig.24 The area represented by the solid rectangular frame includes the areas represented by T1, T2, T3, T4, and T5 respectively.

[0215] Fig.24 In the example, the second vehicle is located behind the first vehicle (not shown in the figure) and has not yet appeared in the overtaking detection area; Fig.25 In the example, a second vehicle appears in the overtaking detection area in front of the first vehicle.

[0216] The control device can detect whether the second vehicle enters the overtaking detection area and leaves the overtaking detection area after a period of time in the image captured by the image capture device. If so, it means that the second vehicle has left the overtaking detection area, and the control device can determine that the yielding is completed.

[0217] Condition 2: The second vehicle disappears from the image captured by the image capture device for a second preset time period.

[0218] The control device may detect whether the second vehicle does not appear in any image captured by the image acquisition device within a second preset time period before the current moment. If so, it means that the second vehicle disappears from the image captured by the image acquisition device for the second preset time period, and the control device may determine that the yielding is completed.

[0219] Condition 3: The first vehicle reaches the end point of the yield path and remains stationary for a third preset time period.

[0220] The first vehicle can determine whether it has reached the end of the yield path based on the positioning information collected by the positioning device carried by itself, and determine whether to remain stationary for the third preset time period based on its own speed. If the positioning information of the first vehicle indicates that it has reached the end of the yield path, and the speed of the first vehicle indicates that the first vehicle has remained stationary for the third preset time period, the control device can determine that the yield is completed.

[0221] The above three conditions for ending the giving way more comprehensively cover the judgment conditions for ending the giving way in actual scenarios, and can more accurately judge whether the current first vehicle has ended the giving way. Furthermore, when the giving way is ended, the control device can promptly plan a return path for the first vehicle and control the first vehicle to resume normal driving, thereby improving the driving flexibility of the first vehicle.

[0222] Step S2302, determining a return path point of the first vehicle on the reference path.

[0223] The control device may select any path point on the teaching path that is ahead of the first vehicle in the driving direction as the return path point. Specifically, the selection may be made in combination with the body length of the first vehicle, the driving speed of the first vehicle, and the like.

[0224] Step S2303, generating a return path from the end path point to the return path point.

[0225] The end path point is the path point where the first vehicle is located when it is detected that the yield end condition is met.

[0226] The control device can determine the area where obstacles that hinder vehicle travel are located in the parking lot based on the environmental information. When generating the return path of the first vehicle, the yield path avoids the area where obstacles that hinder vehicle travel are located in the parking lot, and the yield end point is used as the path end point. When generating the yield path here, a preset path planning algorithm can be used to generate the yield path. For example, the preset algorithm can be a heuristic search algorithm, an ant colony algorithm, a dynamic programming algorithm, etc., which is not limited to this.

[0227] Step S2304, controlling the first vehicle to travel along the return path to the return path point, and controlling the first vehicle to continue traveling.

[0228] The control device can generate the control amount that each actuator in the first vehicle needs to execute according to the return path, and then control each actuator to execute the control amount, so as to drive the first vehicle to travel along the return path. After driving to the return path point, the control device can control the first vehicle to continue to travel along the teaching path; or it can prompt the driver to finish giving way on the display interface, and the driver can continue to manually drive the first vehicle.

[0229] Step S2305: If a parking space to be parked is detected during the driving process of the first vehicle, the first vehicle is controlled to park in the parking space to be parked.

[0230] The parking space to be parked may be: a private parking space of the first vehicle or an empty public parking space.

[0231] For a private parking space, the control device may first determine the position of the first vehicle in the parking lot based on the positioning information of the first vehicle before entering the parking lot and the deviation of the first vehicle caused by the path traveled after entering the parking lot; and then determine whether the first vehicle is currently within the specified distance range of the private parking space of the first vehicle based on the determined position of the first vehicle in the parking lot and the pre-stored position of the private parking space of the first vehicle in the parking lot. If the control device determines that the current position of the first vehicle is within the specified distance range of the private parking space of the first vehicle, the control device detects the private parking space of the first vehicle; if the control device determines that the current position of the first vehicle is not within the specified distance range of the private parking space of the first vehicle, the control device does not detect the private parking space of the first vehicle.

[0232] The control device may also detect whether identification information related to the private parking space of the first vehicle appears in the image based on the image captured by the image capture device carried by the first vehicle, so as to detect the private parking space of the first vehicle.

[0233] For public parking spaces, the control device may detect whether an empty public parking space appears in the image based on the image captured by the image capture device carried by the first vehicle.

[0234] When the control device detects a parking space to be parked, it can perform parking operations on behalf of the driver. The control device can plan a parking path for the first vehicle, and control the first vehicle to drive along the parking path and park in the parking space to be parked. When generating the parking path here, a preset path planning algorithm can be used to generate the parking path. For example, the preset algorithm can be a heuristic search algorithm, an ant colony algorithm, a dynamic programming algorithm, etc., which is not limited to this.

[0235] During the above parking process, the control device may also synchronously execute any of the above vehicle yielding methods and perform a yielding operation when a second vehicle is detected.

[0236] Using the above Fig.23 In the technical solution provided, the control device can monitor the yielding status of the first vehicle in real time. When yielding is completed, the control device can timely plan a return path for the first vehicle and control the first vehicle to resume normal driving, thereby improving the driving flexibility of the intelligent driving vehicle. Moreover, when a parking space to be parked is detected, the control device can control the first vehicle to perform parking operations instead of the driver, thereby improving the automatic valet parking function of the intelligent driving vehicle to a certain extent.

[0237] A method for straightening the teaching path to obtain a straightened path is also provided below.

[0238] This method is as Fig.26 As shown, the following steps S2601-S2604 are included.

[0239] Step S2601, selecting a first number of continuous path points starting from the third path point on the teaching path.

[0240] The initial value of the third path point is the starting point of the teaching path.

[0241] The first number may be any preset positive integer greater than 2. The above method of selecting the third path point is described below by using an example.

[0242] like Fig. 27 An example of a teach path is shown. Fig. 27 In the figure, the teaching path g represented by the solid line includes 6 path points g1, g2, g3, g4, g5, and g6, wherein g1 is the starting point of the teaching path g, g6 is the end point of the teaching path g, and len1, len2, len3, len4, and len5 are the path lengths between g1 and g2, g2 and g3, g3 and g4, g4 and g5, and g5 and g6, respectively. The value of the first number is 3.

[0243] The control device may determine that the initial value of the third path point is the starting point g1 of the teaching path g, and select three consecutive path points starting from g1 as g1, g2, and g3.

[0244] Step S2602: Based on the selected path point, determine whether the first path in the teaching path is a linear path.

[0245] The first path is the path from the third path point to the fourth path point, and the fourth path point is the last path point selected.

[0246] The control device can respectively determine the length of the first path and the length of the line between the third path point and the fourth path point, and compare whether the difference between the two lengths is less than a preset threshold. If the difference between the two lengths is less than the preset threshold, it means that the first path is close to a straight line, and the control device can determine that the first path is a straight path; if the difference between the two lengths is greater than the preset threshold, it means that the first path is relatively curved, and the control device can determine that the first path is not a straight path.

[0247] For example, continuing with the above Fig. 27 In the example, the third path point is g1, the fourth path point is g3, the first path is the solid line path between g1 and g3, the dotted line is the connecting line between g1 and g3, and the preset threshold is th.

[0248] The control device may determine that the length of the first path is len1+len2, and the length of the dotted line is E13. Then, the control device calculates the difference between len1+len2 and E13. If the control device determines that the calculated difference between len1+len2 and E13 is less than th, the control device may determine that the first path is a linear path; if the control device determines that the calculated difference between len1+len2 and E13 is greater than or equal to th, the control device may determine that the first path is not a linear path.

[0249] Step S2603, if it is not a straight path, update the first path to a straight line from the third path point to the fourth path point, and determine a second number of path points between the third path point and the fourth path point on the straight line, the second number being equal to the first number - 2.

[0250] The control device can directly replace the first path in the teaching path with a straight line from the third path point to the fourth path point. The control device can also select a new second number of path points on the replaced straight line, that is, if the first number is m, the control device can select m-2 path points on the updated straight line between the third path point and the fourth path point. In one example, the control device can select m-1 equally divided points on the updated path; in another example, the control device can also randomly select m-2 path points. The above method of selecting the second number of path points is not limited here.

[0251] The following is an example to illustrate this.

[0252] Continuing from the above Fig. 27 For example, assuming that the control device determines that the calculated difference between len1+len2 and E13 is greater than th, and determines that the first path is not a linear path, the control device may change the first path between g1 and g3, that is, Fig. 27 The solid line path in is updated to the straight line between g1 and g3, that is, Fig. 27 The dotted path in .

[0253] Afterwards, the control device may determine that the second number is 3-2=1, and the control device may determine a path point h2 between g1 and g3 on the dotted path. Specifically, the control device may divide the updated dotted path into two equal parts, and determine the midpoint h2 of the dotted path as a new path point.

[0254] If the control device determines that the first path is a linear path, there is no need to straighten the first path, and step S2604 can be directly executed to traverse the next path point.

[0255] Step S2604, update the third path point to the next path point of the third path in the teaching path, and determine whether the third path point traverses all path points in the teaching path. If not, return to execute the above step S2601.

[0256] The control device can determine whether the third path point traverses all path points in the teaching path by determining whether the updated third path point is the end point of the teaching path.

[0257] If the updated third path point is not the end point of the teaching path, it means that the third path point has not traversed all path points in the teaching path, and return to execute the above step S2601; if the updated third path point is the end point of the teaching path, it means that the third path point has traversed all path points in the teaching path, and the above-mentioned straightening process of the teaching path can be ended.

[0258] Still continuing with the above Fig. 27, after updating the first path between g1 and g3 and determining a new path point, the control device updates the third path point to h2, and determines whether h2 is the end point of the teaching path. The control device determines that h2 is not the end point of the teaching path, returns to execute step S2601, selects three consecutive path points h2, g3, and g4 starting from h2 on the updated teaching path, and executes subsequent processes.

[0259] According to the above Fig.26 The provided method is relatively simple to straighten the teaching path and can achieve a better straightening effect.

[0260] In addition, the combined path mentioned in the relevant description of step S302 can also be Fig.26 The straightening method provided is used for straightening, which will not be described in detail. Please refer to the above Fig.26 Description of .

[0261] The above-mentioned vehicle yielding method can improve the automatic valet parking (AVP) function of the smart driving vehicle to a certain extent, and can enable the smart driving vehicle to flexibly respond to speed reduction scenarios, avoiding conflicts with the driver or passengers of the speed reduced vehicle, and also improving the safety of the smart driving vehicle.

[0262] In order to further illustrate the above-mentioned vehicle yielding method, the present application embodiment also provides Fig.28 An example is shown.

[0263] Fig.28 In the process, the control device first pre-processes the teaching path, that is, straightens it, such as the above steps S2601-S2604.

[0264] Then, the control device determines whether the current scene has been entered into, that is, determines whether there is a second vehicle driving at a reduced speed behind the first vehicle, such as the above steps S301 and S701-S704.

[0265] When it is determined that the speed reduction scenario has not been entered, the control device can end the process, and the first vehicle still drives normally according to the taught path.

[0266] When it is determined that a speed reduction scenario has been entered, that is, there is a second vehicle driving at a reduced speed behind the first vehicle, the control device plans a yield path, such as the above steps S302-S304, and the corresponding more specific implementation methods of these steps. The above steps S302-S304 plan the yield path by first generating a planned path, then determining a planned passage area based on the planned path, and then generating a yield path based on the planned passage area. The control device can also control the first vehicle to drive according to the above-planned yield path.

[0267] During the process of giving way, the control device may also monitor whether the giving way is completed, such as the above-mentioned step S2301.

[0268] If the yielding is not completed, the control device can continue to plan the yielding path according to any of the above vehicle yielding methods, and control the first vehicle to drive to the yielding end point. If the yielding is completed, the control device can control the first vehicle to exit the speed reduction scene, that is, resume driving along the teaching path, such as the above steps S2302-S2304.

[0269] In addition, the yield path and planned path generation method provided in this application does not need to extract lane lines, road boundaries and other information from high-precision maps, but plans based on real-time perceived environmental information. The lack of high-precision maps can significantly reduce the software and hardware costs required for the entire process.

[0270] Corresponding to the above-mentioned vehicle giving way method, the embodiment of the present application also provides a vehicle giving way device, such as Fig.29 As shown, the device comprises:

[0271] The first determination module 2901 is used to determine whether there is a second vehicle traveling at a reduced speed behind the first vehicle based on an image captured by an image capture device carried by the first vehicle.

[0272] The first generating module 2902 is used to generate a planned path for the second vehicle based on the reference path and environmental information of the parking lot if there is a second vehicle.

[0273] The second determination module 2903 is used to determine the planned passage area for the second vehicle to travel along the planned path based on the vehicle information of the second vehicle.

[0274] The second generating module 2904 is used to generate a yield path for the first vehicle based on the environmental information.

[0275] Among them, the end point of the yield path is outside the planned traffic area.

[0276] The control module 2905 is used to control the first vehicle to travel according to the yield path.

[0277] In the technical solution provided by the embodiment of the present application, it is first determined based on the collected image whether there is a second vehicle driving at a reduced speed behind the first vehicle. When there is a second vehicle driving at a reduced speed behind the first vehicle, a planned driving path is actively planned for the second vehicle based on the reference path and the environmental information of the parking lot, and it is expected that the second vehicle will drive along the planned path to surpass the first vehicle during the subsequent driving process. Especially in the scenario where the lanes in the parking lot are narrow, the probability of the second vehicle driving along the planned path increases. In order to further increase the probability of the second vehicle driving along the planned path, a yield path with an end point outside the planned passage area that the second vehicle will pass through when driving along the planned path can also be planned for the first vehicle, and the first vehicle is controlled to drive along the yield path, thereby giving up the planned passage area for the second vehicle. In this way, the probability of the second vehicle driving along the planned path to surpass the first vehicle can be further increased, thereby reducing the suppression of the driving speed of the second vehicle by the first vehicle, and avoiding conflicts or collisions between the first vehicle and the second vehicle. By applying the technical solution provided in the embodiments of the present application, the intelligent driving vehicle can promptly give way to the vehicle behind it when a speed reduction situation occurs, thereby reducing the intelligent driving vehicle's suppression of the speed of the vehicle behind it, avoiding conflicts or collisions with other vehicles, and improving the driving safety of the intelligent driving vehicle.

[0278] In one possible implementation, a target path may be generated in the following manner, wherein the target path is a planned path or a yield path: based on environmental information, regional sampling points in a first passable area are obtained, wherein if the target path is a planned path, the first passable area is: an area where there are no obstacles on both sides of the reference path; if the target path is a yield path, the first passable area is: an area in front of the first vehicle in the parking lot, outside the planned passable area, and where there are no obstacles; path planning is performed in the first passable area, and a path with the smallest statistical characteristic value of the distance to the obtained regional sampling points is obtained as the target path.

[0279] In a possible implementation, path planning may be performed in the first traversable area according to the following expression:

[0280] ;

[0281] Wherein, n is a preset positive integer, x represents the coordinate value of the path point along the reference path direction of the planned path, represents the coordinate value of the path point of the planned path along the first direction, the first direction is perpendicular to the reference path direction, , …, , , is the coefficient in the above expression corresponding to the planned path.

[0282] In one possible implementation, the first determination module 2901 may be specifically used to: determine a plurality of first path points located behind the first vehicle on a reference path corresponding to the teaching path, wherein the distance between the first path point and the first vehicle is less than a first preset distance; generate a virtual lane area corresponding to each pair of adjacent first path points based on the positions of each pair of adjacent first path points; detect whether a duration of appearance of a vehicle in a following vehicle detection area is greater than a first preset duration based on an image captured by an image acquisition device carried by the first vehicle, wherein the following vehicle detection area is determined based on the generated virtual lane area; if greater, the vehicle that appears for a duration greater than the first preset duration is determined as the second vehicle.

[0283] In one possible implementation, the first determination module 2901 may be specifically used to: for each pair of adjacent first path points, generate a virtual lane area corresponding to the pair of adjacent first path points in the following manner: determine a first virtual lane area for the first lane using a line connecting the pair of adjacent first path points as a center line of a first lane in which the first vehicle is traveling; construct a second virtual lane area using a first area boundary of the first virtual lane area as a boundary of a second virtual lane area, wherein the second virtual lane area is: a virtual lane area for the opposite lane of the first lane.

[0284] In a possible implementation, the vehicle yielding device may further include: a detection module for, after determining the planned passage area for the second vehicle to travel along the planned path based on the vehicle information of the second vehicle, detecting, based on environmental information, whether there is a risk of collision with obstacles in the parking lot in the planned passage area.

[0285] In one possible implementation, the second generation module 2904 can be specifically used to: determine the yielding end point of the first vehicle from a second passable area in front of the first vehicle in the parking lot, outside the planned passage area, and without obstacles based on environmental information; and perform path planning in the second passable area with the yielding end point as the path end point based on environmental information to obtain the yielding path of the first vehicle.

[0286] In a possible implementation manner, the above-mentioned vehicle yielding device may further include: a monitoring module, used to monitor whether a preset yielding end condition is met; if so, determining a return path point of the first vehicle on a reference path; generating a return path from the end path point to the return path point, wherein the end path point is: the path point where the first vehicle is located when it is detected that the yielding end condition is met; controlling the first vehicle to travel along the return path to the return path point, and controlling the first vehicle to continue traveling; if a parking space to be parked is detected during the driving of the first vehicle, controlling the first vehicle to park in the parking space to be parked.

[0287] In one possible implementation, the above-mentioned yield end condition may include at least one of the following conditions: the second vehicle exits the overtaking detection area, wherein the overtaking detection area is: an area determined based on a virtual lane area generated based on each pair of adjacent second path points, the second path points are: multiple path points on the reference path located in front of and behind the first vehicle, and the distance between the second path points and the first vehicle is less than a second preset distance; the second vehicle disappears from the image captured by the image acquisition device for a second preset time; the first vehicle reaches the end of the yield path and remains stationary for a third preset time.

[0288] In a possible implementation manner, the reference path may be: a straightened path corresponding to a taught path of the first vehicle in the parking lot.

[0289] In one possible implementation, the teaching path may be straightened in the following manner to obtain a straightened path: a first number of continuous path points are selected starting from the third path point on the teaching path, wherein the initial value of the third path point is the starting point of the teaching path; based on the selected path points, whether the first path in the teaching path is a straight path is determined, wherein the first path is: a path from the third path point to the fourth path point, and the fourth path point is: the last path point selected; if it is not a straight path, the first path is updated to a straight line from the third path point to the fourth path point, and a second number of path points are determined between the third path point and the fourth path point on the straight line, the second number being equal to the first number - 2; the third path point is updated to be the next path point of the third path point in the teaching path; and the step of selecting a first number of continuous path points starting from the third path point on the teaching path is returned until the third path point traverses all path points in the teaching path.

[0290] The present application also provides an electronic device, such as the above control device, Fig.30 As shown, including:

[0291] Memory 3001, used for storing computer programs;

[0292] The processor 3002 is used to implement the steps of any of the above-mentioned vehicle giving way methods when executing the program stored in the memory 3001.

[0293] In addition, the electronic device may further include a communication bus and / or a communication interface, and the processor 3002, the communication interface, and the memory 3001 communicate with each other via the communication bus.

[0294] The communication bus mentioned in the above electronic device can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0295] The communication interface is used for communication between the above electronic device and other devices.

[0296] The memory may include a random access memory (RAM) or a non-volatile memory (NVM), such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

[0297] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0298] In another embodiment provided in the present application, a computer-readable storage medium is provided, in which a computer program is stored. When the computer program is executed by a processor, the steps of any of the above-mentioned vehicle giving way methods are implemented.

[0299] In another embodiment provided in the present application, a computer program product including instructions is also provided, which, when executed on a computer, enables the computer to execute any one of the vehicle giving way methods in the above embodiments.

[0300] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it 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. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from a website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a solid-state hard disk (SSD), etc.

[0301] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0302] Each embodiment in this specification is described in a related manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device, electronic device, computer-readable storage medium, and computer program product embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.

[0303] The above description is only a preferred embodiment of the present application and is not intended to limit the protection scope of the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application are included in the protection scope of the present application.

Claims

1. A vehicle yielding method, characterized in that: The method comprises: Based on an image captured by an image capture device carried by the first vehicle, determining whether there is a second vehicle traveling at a reduced speed behind the first vehicle; If the second vehicle exists, generating a planned path for the second vehicle based on the reference path and environmental information of the parking lot; Determining a planned passage area for the second vehicle to travel along the planned path based on the vehicle information of the second vehicle; Based on the environmental information, generating a yield path for the first vehicle, wherein an end point of the yield path is located outside the planned passage area; The first vehicle is controlled to travel along the yield path.

2. The method according to claim 1, characterized in that The target path is generated in the following manner, wherein the target path is the planned path or the yield path: Based on the environmental information, regional sampling points in a first passable area are obtained, wherein if the target path is the planned path, the first passable area is: an area where there are no obstacles on both sides of the reference path; if the target path is the yield path, the first passable area is: an area in front of the first vehicle in the parking lot, outside the planned passable area, and where there are no obstacles; Path planning is performed in the first traversable area to obtain a path with a minimum distance statistical characteristic value between the obtained area sampling points as the target path.

3. The method according to claim 2, characterized in that Path planning is performed in the first traversable area according to the following expression: ； Wherein, n is a preset positive integer, x represents the coordinate value of the path point along the reference path direction of the planned path, represents the coordinate values ​​of the path points of the planned path along a first direction, wherein the first direction is perpendicular to the direction of the reference path, , …, , , is the coefficient in the above expression corresponding to the planned path.

4. The method according to claim 1, characterized in that: The determining whether there is a second vehicle traveling at a reduced speed behind the first vehicle based on an image captured by an image capture device carried by the first vehicle comprises: Determine a plurality of first path points on the reference path that are located behind the first vehicle, wherein a distance between a first path point and the first vehicle is less than a first preset distance; Based on the positions of each pair of adjacent first path points, generating a virtual lane area corresponding to each pair of adjacent first path points; Based on the image captured by the image capture device carried by the first vehicle, detecting whether the duration of the vehicle appearing in the vehicle following detection area is greater than a first preset duration, wherein the vehicle following detection area is determined based on the generated virtual lane area; If it is greater, the vehicle whose appearance duration is greater than the first preset duration is determined as the second vehicle.

5. The method according to claim 4, characterized in that The step of generating a virtual lane area corresponding to each pair of adjacent first path points based on the positions of each pair of adjacent first path points includes: For each pair of adjacent first path points, a virtual lane area corresponding to the pair of adjacent first path points is generated in the following manner: Taking a line connecting the pair of adjacent first path points as a center line of a first lane in which the first vehicle is traveling, determining a first virtual lane area of ​​the first lane; The second virtual lane area is constructed by taking the first area boundary of the first virtual lane area as the boundary of the second virtual lane area, wherein the second virtual lane area is: a virtual lane area of ​​an opposite lane to the first lane.

6. The method according to claim 1, characterized in that After determining the planned passage area for the second vehicle to travel along the planned path based on the vehicle information of the second vehicle, the method further includes: Based on the environmental information, detecting whether the planned passage area has a risk of collision with an obstacle in the parking lot; If not present, the step of generating a yield path for the first vehicle based on the environmental information is performed.

7. The method according to claim 1, characterized in that The generating, based on the environmental information, a yield path for the first vehicle includes: Based on the environmental information, determining a yielding end point of the first vehicle from a second passable area in the parking lot that is in front of the first vehicle and outside the planned passable area and where no obstacles exist; Based on the environmental information, taking the yielding end point as a path end point, path planning is performed in the second passable area to obtain a yielding path for the first vehicle.

8. The method according to claim 1, characterized in that The method further comprises: Monitor whether the preset yielding end conditions are met; If satisfied, determining a return path point of the first vehicle on the reference path; generating a return path from an end path point to the return path point, wherein the end path point is: a path point where the first vehicle is located when it is detected that the yield end condition is met; Controlling the first vehicle to travel along the return path to the return path point, and controlling the first vehicle to continue traveling; If a parking space to be parked is detected during the driving of the first vehicle, the first vehicle is controlled to park in the parking space to be parked.

9. The method according to claim 8, characterized in that The yielding end condition includes at least one of the following conditions: the second vehicle exits an overtaking detection area, wherein the overtaking detection area is an area determined by a virtual lane area generated based on each pair of adjacent second path points, the second path points being a plurality of path points on the reference path located in front of and behind the first vehicle, and the distance between the second path points and the first vehicle being less than a second preset distance; The second vehicle disappears from the image captured by the image acquisition device for a second preset time period; The first vehicle arrives at an end point of the yield path and remains stationary for a third preset time period.

10. The method according to any one of claims 1 to 9, characterized in that The reference path is: a straightened path corresponding to the taught path of the first vehicle in the parking lot.

11. The method according to claim 10, characterized in that The teaching path is straightened in the following manner to obtain the straightened path: Selecting a first number of consecutive path points starting from a third path point on the teaching path, wherein an initial value of the third path point is a starting point of the teaching path; Based on the selected path points, determining whether a first path in the teaching path is a linear path, wherein the first path is: a path from the third path point to a fourth path point, and the fourth path point is: the last path point selected; If it is not a straight path, updating the first path to a straight line from the third path point to the fourth path point, and determining a second number of path points between the third path point and the fourth path point on the straight line, where the second number is equal to the first number minus 2; Updating the third path point to be the next path point of the third path point in the teaching path; Return to the step of selecting a first number of continuous path points starting from the third path point on the teaching path until the third path point traverses all path points in the teaching path.

12. A vehicle yielding device, characterized in that: The device comprises: A first determination module is used to determine whether there is a second vehicle traveling at a reduced speed behind the first vehicle based on an image captured by an image capture device carried by the first vehicle; A first generating module, configured to generate a planned path for the second vehicle based on a reference path and environmental information of the parking lot if the second vehicle exists; A second determining module, configured to determine a planned passage area for the second vehicle to travel along the planned path based on the vehicle information of the second vehicle; a second generating module, configured to generate a yield path for the first vehicle based on the environmental information, wherein an end point of the yield path is located outside the planned passage area; A control module is used to control the first vehicle to travel according to the yield path.

13. The device according to claim 12, characterized in that Generate a target path in the following manner, wherein the target path is the planned path or the yield path: based on the environmental information, obtain regional sampling points in a first passable area, wherein, if the target path is the planned path, the first passable area is: an area where there are no obstacles on both sides of the reference path; if the target path is the yield path, the first passable area is: an area in front of the first vehicle in the parking lot, outside the planned passable area, and where there are no obstacles; perform path planning in the first passable area, and obtain a path with the smallest distance statistical characteristic value from the obtained regional sampling points as the target path; and / or Path planning is performed in the first traversable area according to the following expression: ； Wherein, n is a preset positive integer, x represents the coordinate value of the path point along the reference path direction of the planned path, represents the coordinate values ​​of the path points of the planned path along a first direction, wherein the first direction is perpendicular to the direction of the reference path, , …, , , The coefficients in the above expression corresponding to the planned path; and / or The first determination module is specifically used to: determine multiple first path points on the reference path that are located behind the first vehicle, wherein the distance between the first path point and the first vehicle is less than a first preset distance; generate a virtual lane area corresponding to each pair of adjacent first path points based on the positions of each pair of adjacent first path points; detect whether the duration of appearance of a vehicle in a following vehicle detection area is greater than a first preset duration based on an image captured by an image acquisition device carried by the first vehicle, wherein the following vehicle detection area is determined based on the generated virtual lane area; if greater, determine the vehicle that has appeared for a duration greater than the first preset duration as the second vehicle; and / or The first determination module is specifically used to: for each pair of adjacent first path points, generate a virtual lane area corresponding to the pair of adjacent first path points in the following manner: determine a first virtual lane area of ​​the first lane using a line connecting the pair of adjacent first path points as a center line of a first lane in which the first vehicle is traveling; construct a second virtual lane area using a first area boundary of the first virtual lane area as a boundary of a second virtual lane area, wherein the second virtual lane area is: a virtual lane area of ​​an opposite lane to the first lane; and / or The device further includes: a detection module, configured to detect, based on the environmental information, whether there is a risk of collision between the planned passage area and an obstacle in the parking lot after determining the planned passage area for the second vehicle to travel along the planned path based on the vehicle information of the second vehicle; and / or The second generation module is specifically used to: determine, based on the environmental information, a yielding end point of the first vehicle from a second passable area in front of the first vehicle in the parking lot, outside the planned passable area, and without obstacles; based on the environmental information, perform path planning in the second passable area with the yielding end point as the path end point to obtain a yielding path for the first vehicle; and / or The device further comprises: a monitoring module, configured to monitor whether a preset yielding end condition is satisfied; if satisfied, determining a return path point of the first vehicle on the reference path; generating a return path from the end path point to the return path point, wherein the end path point is: a path point where the first vehicle is located when it is detected that the yielding end condition is satisfied; controlling the first vehicle to travel along the return path to the return path point, and controlling the first vehicle to continue traveling; if a parking space to be parked is detected during the driving of the first vehicle, controlling the first vehicle to park in the parking space to be parked; and / or The yielding end condition includes at least one of the following conditions: the second vehicle exits the overtaking detection area, wherein the overtaking detection area is: an area determined based on a virtual lane area generated based on each pair of adjacent second path points, the second path points are: multiple path points on the reference path located in front of and behind the first vehicle, and the distance between the second path points and the first vehicle is less than a second preset distance; the second vehicle disappears from the image captured by the image acquisition device for a second preset time; the first vehicle reaches the end of the yielding path and remains stationary for a third preset time; and / or The reference path is: a straightened path corresponding to a taught path of the first vehicle in the parking lot; and / or The teaching path is straightened in the following manner to obtain the straightened path: a first number of continuous path points are selected starting from the third path point on the teaching path, wherein the initial value of the third path point is the starting point of the teaching path; based on the selected path points, whether the first path in the teaching path is a straight path, wherein the first path is: a path from the third path point to the fourth path point, and the fourth path point is: the last path point selected; if it is not a straight path, the first path is updated to a straight line from the third path point to the fourth path point, and a second number of path points are determined between the third path point and the fourth path point on the straight line, the second number being equal to the first number-2; the third path point is updated to the next path point of the third path point in the teaching path; and the step of selecting a first number of continuous path points starting from the third path point on the teaching path is returned until the third path point traverses all path points in the teaching path.

14. An electronic device, characterized in that: include: Memory, used to store computer programs; A processor, configured to implement the steps of the method according to any one of claims 1 to 11 when executing a program stored in a memory.

15. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 11 are implemented.

Images