Parking control method and device, vehicle and storage medium

Abstract

Embodiments of the present application provide a parking control method and device, a vehicle and a storage medium, and relate to the technical field of automatic parking. The method comprises the following steps: acquiring a parking space, a drivable area corresponding to the parking space and a real-time pose of a vehicle; generating a vehicle pose area distribution map according to a target point in the parking space, the vehicle pose area distribution map comprising a plurality of areas, each area having a predefined parking control parameter; determining a current area in which the vehicle is located in the vehicle pose area distribution map according to the real-time pose of the vehicle; and performing vehicle parking control in the drivable area by using the parking control parameter corresponding to the current area, so as to solve the problem of sudden change in curvature of a planned path scheme and reduce the complexity of a path planning algorithm and a control algorithm in the parking process.

Description

TECHNICAL FIELD

[0001] Embodiments of the present application relate to the technical field of automatic parking, in particular, to a parking control method and device, a vehicle and a storage medium. BACKGROUND

[0002] The technical field of automatic parking includes a path planning link and a control link. At present, the path planning link calculates a locally optimal path for vehicle driving by obtaining parking space and drivable area data identified by an environment perception link, and the calculation method can include but is not limited to a hybrid A-star algorithm, an RRT algorithm, etc. The path planning link sends the locally optimal path in the form of trajectory points to the control link. The control link takes the locally optimal path as a reference, tracks the trajectory points on the locally optimal path through a lateral control algorithm, and thus parks the vehicle in the parking space, and the lateral control algorithm can include but is not limited to a Pure Pursuit algorithm, an LQR algorithm, and an MPC algorithm, etc.

[0003] In the current automatic parking scheme, the one-time path planning scheme has the problem of sudden change of curvature, and in order to obtain a smoother path, secondary planning is needed to smooth the path, resulting in high complexity of the path planning algorithm. In addition, the trajectory tracking has high requirements for control accuracy, and the lateral control algorithm has high dependence on the accuracy of the kinematics and dynamics model of the vehicle, resulting in high complexity of the lateral control algorithm. That is to say, the current automatic parking scheme has the problems of sudden change of curvature and high complexity of the algorithm. SUMMARY

[0004] Embodiments of the present application provide a parking control method and device, a vehicle and a storage medium to improve the problems of sudden change of curvature and high complexity of the algorithm in the current automatic parking scheme.

[0005] In a first aspect, embodiments of the present application provide a parking control method. The method comprises: obtaining a parking space, a drivable area corresponding to the parking space, and a real-time pose of a vehicle; generating a vehicle pose area distribution map according to a target point in the parking space, the vehicle pose area distribution map comprising a plurality of areas, each area having a predefined parking control parameter; determining a current region in which the vehicle is located in the vehicle pose area distribution map according to the real-time pose of the vehicle; and performing vehicle parking control in the drivable area using the parking control parameter corresponding to the current region.

[0006] In a second aspect, an embodiment of the present application provides a parking control device. The device comprises: an information sensing module configured to acquire a parking space, a drivable area corresponding to the parking space, and a real-time pose of a vehicle; a distribution map generating module configured to generate a vehicle pose area distribution map according to a target point in the parking space, the vehicle pose area distribution map comprising a plurality of areas, each area having a predefined parking control parameter; a position determining module configured to determine a current area in which the vehicle is located in the vehicle pose area distribution map according to the real-time pose of the vehicle; and a parking control module configured to perform vehicle parking control in the drivable area using the parking control parameter corresponding to the current area.

[0007] In a third aspect, an embodiment of the present application provides a vehicle. The vehicle comprises a memory, one or more processors, and one or more application programs. The one or more application programs are stored in the memory and configured to cause the one or more processors to perform the method provided by an embodiment of the present application when invoked by the one or more processors.

[0008] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium. The computer-readable storage medium stores program codes, which are configured to cause a processor to perform the method provided by an embodiment of the present application when invoked by the processor.

[0009] The embodiments of the present application provide a parking control method, device, vehicle, and storage medium. The method can generate a vehicle pose area distribution map according to a target point in a parking space, each area in the vehicle pose area distribution map has a predefined parking control parameter, determine a current area in which the vehicle is located in the vehicle pose area distribution map according to a real-time pose of the vehicle, and perform vehicle parking control in a drivable area using the predefined parking control parameter corresponding to the current area. The method can perform parking control according to the current area in which the vehicle is currently located in the vehicle pose area distribution map, thereby solving the problem of sudden change in curvature of a planned path scheme. In addition, the path planning algorithm and the control algorithm are combined and performed synchronously, which can reduce the complexity of the path planning algorithm and the control algorithm in the parking process. BRIEF DESCRIPTION OF DRAWINGS

[0010] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without any creative effort.

[0011] Figure 1 FIG. 1 is a structural schematic diagram of a parking control system according to an embodiment of the present application;

[0012] Figure 2 is a flowchart of a parking control method provided by an embodiment of the present application;

[0013] Figure 3 is a schematic diagram of a vehicle posture region distribution map provided by an example embodiment of the present application;

[0014] Figure 4 is a schematic diagram of a vehicle posture region distribution map provided by an example embodiment of the present application;

[0015] Figure 5 is a schematic diagram of a vehicle posture region distribution map provided by an example embodiment of the present application;

[0016] Figure 6 is a flowchart of a parking control method provided by an embodiment of the present application;

[0017] Figure 7 is a schematic diagram of a vehicle posture region distribution map provided by an example embodiment of the present application;

[0018] Figure 8 is a schematic diagram of a vehicle posture region distribution map provided by an example embodiment of the present application;

[0019] Figure 9 is a schematic diagram of a vehicle posture region distribution map provided by an example embodiment of the present application;

[0020] Figure 10 is a schematic diagram of a vehicle posture region distribution map provided by an example embodiment of the present application;

[0021] Figure 11 is a schematic diagram of a vehicle posture region distribution map provided by an example embodiment of the present application;

[0022] Figure 12 is a schematic diagram of a vehicle posture region distribution map provided by an example embodiment of the present application;

[0023] Figure 13 is a structural schematic diagram of a parking control device provided by an embodiment of the present application;

[0024] Figure 14 is a structural schematic diagram of a vehicle provided by an embodiment of the present application;

[0025] Figure 15 is a structural schematic diagram of a computer readable storage medium provided by an embodiment of the present application. DETAILED DESCRIPTION

[0026] In order to enable persons skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the accompanying drawings in the embodiments of the present application.

[0027] Figure 1 FIG. 1 is a structural schematic diagram of a parking control system according to an embodiment of the present application. The parking control system 100 can be applied to a vehicle. The parking control system 100 includes a perception module 110 and a parking control module 120.

[0028] The perception module 110 is configured to perceive information, such as obstacles, distances between the vehicle and the obstacles, and parking space information. The perception module 110 includes a plurality of perception devices, which can include but are not limited to a camera, an ultrasonic sensor, a millimeter wave sensor, a laser sensor, and the like.

[0029] The parking control module 120 can include one or more processors, one or more controllers, and one or more positioning devices, and is configured to execute the parking control method provided by the embodiments of the present application. The processor can include but is not limited to a digital signal processing (Digital Signal Processing, DSP for short), a field-programmable gate array (Field-Programmable Gate Array, FPGA for short), and a programmable logic array (Programmable Logic Array, PLA for short). The controller can include but is not limited to an electronic control unit (Electronic Control Unit, ECU for short), a central control unit (Central Control Unit, CCU for short), a body control unit (Body Control Unit, BCU for short), and the like. The positioning device can refer to a global navigation satellite system (Global Navigation Satellite System, GNSS for short). The GNSS can include but is not limited to a global positioning system (Global Positioning System, GPS for short), a glonass (Global Navigation Satellite System, Glonass for short), a galileo satellite navigation system (Galileo Satellite Navigation System, Galileo for short), a beidou satellite navigation system, a wide area augmentation system (Wide Area Augmentation System, WAAS for short), a European geostationary navigation overlay service (European Geostationary Navigation Overlay Service, EGNOS for short), a multi-functional satellite augmentation system (Multi-Functional Satellite Augmentation System, MSAS for short), and the like.

[0030] Figure 2 This is a schematic flowchart of a parking control method provided in one embodiment of this application. The parking control method can be applied to a parking control module, a parking control device, or a vehicle. The parking control method may include steps S110 to S140.

[0031] Step S110: Obtain the parking space, the drivable area corresponding to the parking space, and the real-time position and pose of the vehicle.

[0032] In this application embodiment, a parking space refers to a space where vehicles can park. Parking spaces can include urban roads used by public security traffic management departments, including lanes for motor vehicles, lanes for non-motor vehicles, sidewalks, and parking spaces in garages. The drivable area corresponding to a parking space refers to the area where a vehicle can drive during the process of entering the parking space. The extent and shape of the drivable area are associated with the specific parking space. For example, such as... Figure 3 As shown, taking a perpendicular parking space as an example, the drivable area corresponding to the parking space is the area enclosed by the bold border 1.

[0033] The aforementioned sensing devices can be used to acquire information about parking spaces, the corresponding drivable areas, and the real-time position and orientation of vehicles. For example, the sensing devices can acquire information about the four corner points of a parking space, and the parking space can be determined based on this information. After determining the parking space, the sensing devices can acquire the drivable area corresponding to that parking space; the range and shape of the drivable area are associated with the specific parking space.

[0034] In some embodiments, to avoid wasting computing power due to an excessively large drivable area, it can be determined whether the drivable area exceeds a preset range. If it does, the boundary of the drivable area can be narrowed, thereby rationally limiting the drivable area and saving system computing power and parking time. For example, the road width (e.g., ...) within the drivable area can be determined. Figure 3 If the drivable area exceeds the preset road width (e.g., 6 meters), the boundary can be narrowed. Parking control is then performed based on the narrowed drivable area. The narrowing process can be done in preset increments (e.g., 0.5 meters). After each narrowing step, it is checked whether the width of the narrowed drivable area exceeds the preset road width. If it does, the narrowing is continued in preset increments until the narrowed drivable area is less than or equal to the preset road width, preventing the narrowed drivable area from becoming too small.

[0035] The real-time vehicle pose in this application embodiment may include, but is not limited to, the real-time vehicle position and real-time vehicle heading. Specifically, the real-time vehicle position in this application embodiment may be represented by the real-time rear axle center to facilitate the implementation of the parking control scheme provided in this application embodiment.

[0036] The real-time pose of the vehicle can be obtained in real time by the positioning device. For example, the current real-time position and the current real-time heading of the vehicle in a local coordinate system can be obtained by the positioning device. The local coordinate system can refer to a coordinate system with a target point in the parking space as the origin. The target point in the parking space refers to a point corresponding to the center of the rear axle of the vehicle when the vehicle is parked in the parking space (i.e., the actual vehicle pose when the vehicle is parked in the parking space is the same as the preset ideal vehicle pose). Figure 3 As shown in FIG. 1, point A is the target point in the parking space.

[0037] In some embodiments, the real-time pose of the vehicle can be periodically obtained by the positioning device according to a positioning period. The positioning period can be set according to the actual accuracy requirement, for example, the positioning period can be set to 500 milliseconds.

[0038] In step S120, a vehicle pose area distribution map is generated according to the target point in the parking space.

[0039] As described above, the target point in the parking space in the embodiments of the present application refers to a point corresponding to the center of the rear axle of the vehicle when the vehicle is parked in the parking space (i.e., the actual vehicle pose when the vehicle is parked in the parking space is the same as the preset ideal vehicle pose), for example Figure 3 point A shown in FIG. 1.

[0040] In some embodiments, the target point in the parking space can be derived according to the information of the four corner points of the parking space. The derivation method of the target point is associated with the parking space, and the corresponding derivation method can be set according to the parking space in the actual scene, and the mapping relationship between the parking space and the derivation method is stored, so that the target point can be derived according to the corresponding derivation method of the parking space, and the parking accuracy is improved.

[0041] The vehicle pose area distribution map in the embodiments of the present application actually divides the area that the vehicle can pass through during parking into a plurality of smaller areas according to certain rules, and predefines the parking control parameters of the vehicle in the smaller area based on the estimation of the successful parking of the vehicle. In this way, when the vehicle actually drives to the area, the parking control of the vehicle can be performed by comparing the actual pose of the vehicle with the parameters. Based on this logic, the vehicle pose area distribution map includes at least a plurality of areas, each area has predefined parking control parameters, so as to perform parking control according to the corresponding relationship between the real-time pose of the vehicle and the parking control parameters. The parking control parameters of different areas can be different.

[0042] The parking control parameters of each region can include, but are not limited to, the expected vehicle heading, the expected vehicle speed, the expected acceleration, the expected wheel rotation angle speed, the expected wheel rotation angle acceleration, the brake start distance, and the brake stop distance of the region, etc. The parking control parameters of each region can be pre-set and stored in the table corresponding to the fuzzy data set based on the fuzzy rules of prior experience or through data acquisition and model training, etc. During the entire parking control process, the table can be directly called, and the corresponding data can be obtained from the table.

[0043] The expected vehicle heading refers to the included angle between the vehicle heading and the target point in the parking space. As shown in Figure 3 , the expected vehicle heading of each region can refer to the included angle between the vehicle heading and the target point A in the parking space, and the arrow indicated by the blank small circle can represent the expected vehicle heading of each region.

[0044] It should be noted that the density of the regions in the vehicle attitude region distribution diagram can be adjusted according to system computing power, vehicle body size, and vehicle positioning accuracy, etc. For example, as shown in Figure 3 , the density of the regions in the vehicle attitude region distribution diagram is greater than Figure 4 , the density of the regions in the vehicle attitude region distribution diagram.

[0045] It should also be noted that the shape of the vehicle attitude region distribution diagram can be set according to actual needs. For example, as shown in Figure 3 and Figure 4 , the vehicle attitude region distribution diagram can be a sector, as shown in Figure 5 , the vehicle attitude region distribution diagram can also be a region formed by multiple rectangles, etc.

[0046] In some embodiments, the density of the regions in the vehicle attitude region distribution diagram can be obtained; and the vehicle attitude region distribution diagram is generated according to the target point and the density. The density can be a pre-set fixed value, or as previously described, the density can be dynamically adjusted according to system computing power, vehicle body size, and vehicle positioning accuracy, etc.

[0047] In some embodiments, assuming that the vehicle attitude region distribution diagram is a sector as shown in Figure 3 , the step of “generating the vehicle attitude region distribution diagram according to the target point and the density” can include the following steps: taking the target point as a common endpoint, generating multiple curves on the side of the vehicle according to the density, the curvatures of the multiple curves being different; taking the target point as a common center, generating multiple circular arcs on the side of the vehicle according to the density, the radii corresponding to the multiple circular arcs being different, the multiple curves and the multiple circular arcs intersecting to form multiple regions, and the multiple regions forming the vehicle attitude region distribution diagram.

[0048] The side edge curves of the multiple curves in the embodiments of this application (e.g.) Figure 3 Curves 3 and 5 shown correspond to the minimum turning radius of the vehicle. For example, Kmax = 1 / Rmin, where Rmin is the minimum turning radius, representing the two edge curves among the multiple curves.

[0049] The curvatures of numerous curves and the radii of numerous arcs can be pre-set and stored in the table corresponding to the aforementioned fuzzy dataset. The number of curves and arcs is mapped to the density. Based on the density, multiple curvatures and radii corresponding to the density can be directly obtained from the table corresponding to the fuzzy dataset, and multiple curves can be generated based on the multiple curvatures, and multiple arcs can be generated based on the multiple radii. In some embodiments, the curvatures of the multiple curves can be an arithmetic sequence, and the radii of the multiple arcs can also be an arithmetic sequence, avoiding abrupt changes in the desired vehicle heading and improving the smoothness of parking control.

[0050] It should be noted that, in this embodiment, the desired vehicle heading for each region in the vehicle attitude region distribution map is the tangent direction of the curve corresponding to the center position within that region (e.g., ...). Figure 3 The small blank circles in each region (indicated by the arrows) have been pre-set and stored in the table corresponding to the fuzzy dataset for later retrieval.

[0051] For example, such as Figure 3 As shown, assuming point A is the target point and point B is the current rear axle center of the vehicle, multiple curves (e.g., curves 3 and 5, and similar curves) can be generated on the side where the vehicle is located, with the number of curves corresponding to the density. The curvature of these curves can be an arithmetic sequence. Similarly, multiple arcs (e.g., arc 4, and similar arcs) can be generated on the side where the vehicle is located, with the number of arcs corresponding to the density. The radii of these arcs can also be an arithmetic sequence. The intersection of multiple curves and arcs can form multiple regions, for example... Figure 3 The area indicated by the arrow in the blank circle is one region, and multiple regions form a fan-shaped distribution map of vehicle posture regions.

[0052] In some embodiments, such as Figure 5 As shown, assuming the vehicle posture area distribution map can be composed of multiple rectangles, then "generating the vehicle posture area distribution map based on the target point and density" can include the following steps: taking the horizontal line where the target point is located as the starting line of the horizontal line, generating multiple horizontal lines on the side where the vehicle is located according to the density; taking the vertical line where the target point is located as the starting line of the vertical line, generating multiple vertical lines on both sides of the starting line of the vertical line, with the horizontal lines perpendicular to the vertical lines, and the multiple horizontal lines intersecting to form multiple areas, and the multiple areas forming the vehicle posture area distribution map.

[0053] The number of horizontal lines and the number of vertical lines have a mapping relationship with the density, and the number can be stored in the table corresponding to the fuzzy rule set. In addition, the interval between adjacent horizontal lines and the interval between adjacent vertical lines can also be stored in the table corresponding to the fuzzy rule set. The number of horizontal lines corresponding to the density, the interval between adjacent horizontal lines, the number of vertical lines, and the interval between adjacent vertical lines can be obtained from the table corresponding to the fuzzy data set according to the density. A plurality of horizontal lines are generated based on the number of horizontal lines and the interval between adjacent horizontal lines, and a plurality of vertical lines are generated based on the number of vertical lines and the interval between adjacent vertical lines.

[0054] In some embodiments, the interval between adjacent horizontal lines can be the same, and the interval between adjacent vertical lines can be the same, to uniformly adjust the vehicle heading and avoid sudden changes in the desired vehicle heading, thereby improving the smoothness of the parking control. The interval between adjacent horizontal lines and the interval between adjacent vertical lines can be the same or different.

[0055] As shown in the example, Figure 5 Assuming that point A is the target point and point B is the current rear axle center of the vehicle, the horizontal line 6 where the target point A is located can be taken as the horizontal starting line, and a plurality of horizontal lines corresponding to the density are generated on the side of the vehicle. The vertical line 7 where the target point A is located can be taken as the vertical starting line, and a plurality of vertical lines are generated on both sides of the vertical starting line 7. The plurality of horizontal lines and the plurality of vertical lines intersect to form a plurality of rectangular regions, for example, the region where the arrow indicated by the blank circle is located is a rectangular region, and the plurality of rectangular regions form a vehicle posture region distribution map.

[0056] In step S130, the current region of the vehicle in the vehicle posture region distribution map is determined according to the real-time pose of the vehicle.

[0057] After the vehicle posture region distribution map is established, the current region of the vehicle in the vehicle posture region distribution map can be located in real time according to the real-time pose of the vehicle, and the actual position and the actual heading of the vehicle are adjusted according to the parking control parameters (e.g., the desired vehicle speed and the desired vehicle heading) of the current region of the vehicle until the vehicle is parked in the parking space. During the entire process of adjusting the vehicle heading, the vehicle will not drive out of the drivable region.

[0058] In some embodiments, the current region of the vehicle in the vehicle posture region distribution map can be determined according to the real-time rear axle center of the vehicle included in the real-time pose of the vehicle. As shown in the example, Figure 3 Assuming that point B is the current rear axle center of the vehicle, the region S where the vehicle is currently located is the current region.

[0059] Step S140, using the parking control parameter corresponding to the current region, performing vehicle parking control in the drivable region.

[0060] In some embodiments, the heading deviation value can be determined according to the real-time heading of the vehicle and the expected vehicle heading of the current region; the corresponding vehicle safety boundary can be determined according to the braking start distance and the braking stop distance of the current region; and the vehicle can be parked in the parking space by performing lateral control according to the heading deviation value, longitudinal control and gear shifting control according to the vehicle safety boundary, the heading deviation value and the drivable region in the drivable region. For specific description of this embodiment, please refer to subsequent steps S240 to S270.

[0061] The parking control method provided by the embodiments of the present application can generate a vehicle posture region distribution map according to the target point in the parking space, perform vehicle parking control in the drivable region according to the parking control parameter corresponding to the current region of the vehicle in the vehicle posture region distribution map, and solve the problem of sudden change in curvature of the planned path scheme. In addition, the path planning algorithm and the control algorithm are combined and performed synchronously, which can reduce the complexity of the path planning algorithm and the control algorithm in the parking process.

[0062] Figure 6 is a flowchart of a parking control method provided by an embodiment of the present application. The parking control method can be applied to a parking control module, a parking control device or a vehicle. The parking control method can include steps S210 to S270.

[0063] Step S210, obtaining a parking space, a drivable region corresponding to the parking space and a real-time pose of a vehicle.

[0064] Step S220, generating a vehicle posture region distribution map according to a target point in the parking space.

[0065] For specific description of steps S210 and S220, please refer to steps S110 and S120 described above, which will not be repeated here.

[0066] Step S230, determining a current region of the vehicle in the vehicle posture region distribution map according to a real-time rear axle center of the vehicle. For specific description of step S230, please refer to the related part in step S130 described above, which will not be repeated here.

[0067] Step S240, determining a heading deviation value according to a real-time heading of the vehicle and an expected vehicle heading of the current region.

[0068] The expected vehicle heading of the current region can be obtained from a table corresponding to the fuzzy rule data set, and the heading deviation value can be obtained by subtracting the real-time heading of the vehicle from the expected vehicle heading of the current region.

[0069] Step S250: Determine the corresponding vehicle safety boundary based on the braking start distance and braking stop distance of the current area.

[0070] In this embodiment, the braking start distance refers to the distance used to initiate the vehicle's braking function. The vehicle braking function can be used to decelerate or stop the vehicle; in this embodiment, the braking stop distance refers to the distance used to stop the vehicle using the braking function. As mentioned earlier, the table corresponding to the fuzzy rule dataset stores the mapping relationship between regions within the vehicle attitude region distribution map and the braking start distance and braking stop distance. Therefore, both the braking start distance and braking stop distance can be obtained from the table corresponding to the fuzzy rule dataset based on the current region.

[0071] To prevent vehicles from exceeding the drivable area or colliding with obstacles during parking, embodiments of this application establish vehicle safety boundaries. The vehicle safety boundary is a new profile formed by expanding the vehicle outline multiple times to a certain distance. The number of layers of the vehicle safety boundary and the expansion distance of a single wheel are related to the braking start distance and braking stop distance. For example, assuming a vehicle has 3 layers of vehicle safety boundaries, the expansion distance of a single wheel is 0.2 meters. Therefore, the braking start distance (number of vehicle safety boundary layers * single wheel vehicle outline expansion distance) is 0.6 meters, and the braking stop distance ((number of vehicle safety boundary layers - 2) * single wheel vehicle outline expansion distance) is 0.2 meters.

[0072] For example, such as Figure 3 As shown, the bolded elliptical ring 2 represents the vehicle safety boundary. Figure 3 There are three layers of vehicle safety boundaries. It should be noted that, for ease of subsequent examination of the relationship between the vehicle safety boundaries and the drivable area, such as... Figure 4 as well as Figures 7-12 As shown, the vehicle safety boundary is displayed in bold.

[0073] Distance can be measured using sensing devices, and the vehicle's safety boundary can be obtained based on the braking start distance and braking stop distance of the current area. For example, one of the following methods can be used: camera ranging, lidar ranging, ultrasonic radar ranging, or millimeter-wave radar ranging. Lidar ranging methods may include, but are not limited to, triangulation, pulse time-of-flight (PTOF), and amplitude continuous wave (AMCW) ranging. Ultrasonic radar ranging methods may include, but are not limited to, round-trip time detection, phase detection, and acoustic amplitude detection. Millimeter-wave radar ranging methods may include, but are not limited to, continuous wave phase methods, pulse methods, continuous wave frequency modulation methods, continuous wave phase modulation methods, and pulse compression methods.

[0074] Step S260, within the drivable area, performing lateral control according to the heading deviation value, and performing longitudinal control and gear switching control according to the vehicle safety boundary, the heading deviation value and the drivable area, to perform parking.

[0075] In some embodiments, the lateral control according to the heading deviation value can take the heading deviation value as an adjustment amount, and control the vehicle to adjust the current heading by the heading deviation value to reach the expected vehicle heading corresponding to the current region. For example, a Proportion Integral Differential (PID) control algorithm can be used to perform lateral closed-loop control according to the heading deviation value. For example, assuming that the expected vehicle heading is 0°, and the current vehicle heading is 30°, the heading deviation value is 30°, and the vehicle is currently in the region A, then the vehicle can be controlled to adjust the current heading by 30° to reach the expected vehicle heading 0°. Figure 4 Figures 7-12 For the entire parking process, the change of the arrow pointed by point B in Figure 4 Figures 7-12 is the actual change of the vehicle heading achieved by the lateral control.

[0076] In some embodiments, the longitudinal control according to the vehicle safety boundary, the heading deviation value and the drivable area can include the following steps: acquiring the distance between the vehicle head and tail and the drivable area in real time, taking the shorter distance between the vehicle head and tail and the drivable area as the target distance; controlling the vehicle to decelerate when the target distance or the deviation value decreases; controlling the vehicle to start braking deceleration when the target distance is less than the braking start distance of the current region; and controlling the vehicle to stop when the vehicle safety boundary and the drivable area have an overlapping part. The control of the vehicle to decelerate when the target distance or the deviation value decreases can improve the user comfort during parking. When the target distance is less than the braking start distance of the current region, it is considered that the vehicle is close to the boundary of the drivable area, and the braking function can be started to brake the vehicle. When the vehicle safety boundary and the drivable area have an overlapping part, as shown in Figure 8 Figure 9 Figure 11 , it is considered that the vehicle is very close to the boundary of the drivable area, and the vehicle needs to be stopped to ensure that the vehicle is parked within the drivable area while avoiding collision with obstacles, and to ensure the safety of the vehicle during parking.

[0077] ​​​​The distance between the vehicle head and the drivable area can be obtained by distance measurement of the perception device, and the distance between the vehicle tail and the drivable area can be obtained by distance measurement of the perception device. If the distance between the vehicle head and the drivable area is greater than or equal to the distance between the vehicle tail and the drivable area, the distance between the vehicle tail and the drivable area can be taken as the target distance. If the distance between the vehicle head and the drivable area is less than the distance between the vehicle tail and the drivable area, the distance between the vehicle head and the drivable area can be taken as the target distance.

[0078] In some embodiments, the "gear shifting control according to the vehicle safety boundary, the heading deviation value, and the drivable area" can include the following steps: when the vehicle safety boundary and the drivable area have an overlapping part, performing gear shifting control between the forward gear and the reverse gear, for example, shifting the forward gear to the reverse gear or shifting the reverse gear to the forward gear; when the vehicle safety boundary and the drivable area do not have an overlapping part and the heading deviation value meets a specified condition, shifting the vehicle gear to the parking gear. The specified condition can be that the heading deviation value is less than or equal to a specified deviation value, and when the heading deviation value is less than or equal to the specified deviation value, the heading deviation value approaches 0.

[0079] It should be noted that the longitudinal control can also be controlled by a PID algorithm.

[0080] Step S270: When the heading deviation value is less than or equal to the heading deviation threshold value, the lateral deviation between the real-time rear axle center of the vehicle and the target point is less than or equal to the lateral deviation threshold value, and the longitudinal deviation between the real-time rear axle center of the vehicle and the target point is less than or equal to the longitudinal deviation threshold value, it is determined that the vehicle has parked in the parking space and the parking is stopped.

[0081] The heading deviation threshold value, the lateral deviation threshold value, and the longitudinal deviation threshold value can be set according to actual needs. When the heading deviation value is less than or equal to the heading deviation threshold value, the lateral deviation between the real-time rear axle center of the vehicle and the target point is less than or equal to the lateral deviation threshold value, and the longitudinal deviation between the real-time rear axle center of the vehicle and the target point is less than or equal to the longitudinal deviation threshold value, as shown in FIG. 8, the current rear axle center B of the vehicle is close to the target point A, and it can be considered that the vehicle has parked in the parking space, and the parking can be stopped at this time. By setting the heading deviation threshold value, the lateral deviation threshold value, and the longitudinal deviation threshold value to comprehensively determine whether to stop parking, the parking accuracy can be improved. Figure 12

[0082] ​The parking control method provided by the embodiments of the present application can generate a vehicle posture region distribution map according to a target point in a parking space, perform vehicle parking control in a drivable region according to a parking control parameter corresponding to a current region of the vehicle in the vehicle posture region map, and can solve the problem of curvature mutation in a planned path scheme. The combination of the path planning algorithm and the control algorithm can reduce the complexity of the path planning algorithm and the control algorithm in the parking process. The setting of the vehicle safety boundary can avoid the vehicle from driving out of the drivable region while ensuring that the vehicle and the obstacle do not collide, thereby ensuring the safety of the vehicle in the parking process. In addition, the setting of the heading deviation threshold, the lateral deviation threshold and the longitudinal deviation threshold can comprehensively determine whether to stop parking, and can improve the parking accuracy.

[0083] Figure 13 FIG. 1 is a structural schematic diagram of a parking control device provided by an embodiment of the present application. The parking control device can be applied to a vehicle. The parking control device 200 can include an information perception module 210, a distribution map generation module 220, a position determination module 230 and a parking control module 240.

[0084] The information perception module 210 is configured to acquire a parking space, a drivable region corresponding to the parking space and a real-time pose of a vehicle.

[0085] The distribution map generation module 220 is configured to generate a vehicle posture region distribution map according to a target point in the parking space, the vehicle posture region distribution map including a plurality of regions, each region having a predefined parking control parameter.

[0086] The position determination module 230 is configured to determine a current region of the vehicle in the vehicle posture region distribution map according to the real-time pose of the vehicle.

[0087] The parking control module 240 is configured to perform vehicle parking control in the drivable region by using a parking control parameter corresponding to the current region.

[0088] In some embodiments, the distribution map generation module 220 is further configured to acquire a density of a region in the vehicle posture region distribution map; and generate the vehicle posture region distribution map according to the target point and the density.

[0089] In some embodiments, the distribution map generation module 220 is further configured to generate a plurality of curves on a side of the vehicle according to the density, with the target point as a common endpoint, the plurality of curves having different curvatures; and generate a plurality of circular arcs on the side of the vehicle according to the density, with the target point as a common center, the plurality of circular arcs corresponding to different radii, the plurality of curves and the plurality of circular arcs intersecting to form a plurality of regions, the plurality of regions forming the vehicle posture region distribution map.

[0090] In some embodiments, the vehicle real-time pose includes a vehicle real-time rear axle center and a vehicle real-time heading, and the parking control parameters include a desired vehicle heading, a brake start distance and a brake stop distance. The position determining module 230 is further configured to determine a current region of the vehicle in the vehicle pose region distribution map. The parking control module 240 is further configured to determine a heading deviation value according to the vehicle real-time heading and the desired vehicle heading of the current region, determine a corresponding vehicle safety boundary according to the brake start distance and the brake stop distance of the current region, and perform lateral control according to the heading deviation value, longitudinal control and gear shifting control according to the vehicle safety boundary, the heading deviation value and the drivable region, so as to park the vehicle into the parking space.

[0091] In some embodiments, the parking control module 240 is further configured to obtain distances between the vehicle head and tail and the drivable region in real time, take a shorter distance between the vehicle head and tail and the drivable region as a target distance, control the vehicle to decelerate when the target distance or the deviation value decreases, control the vehicle to start brake deceleration when the target distance is less than the brake start distance of the current region, and control the vehicle to brake to a stop when the vehicle safety boundary and the drivable region have an overlapping part.

[0092] In some embodiments, the parking control module 240 is further configured to perform gear shifting control between forward gear and reverse gear when the vehicle safety boundary and the drivable region have an overlapping part, and switch the vehicle gear to the reverse gear when the vehicle safety boundary and the drivable region do not have an overlapping part and the heading deviation value meets a specified condition.

[0093] In some embodiments, the parking control module 240 is further configured to determine that the vehicle is parked into the parking space and stop parking when the heading deviation value is less than or equal to a heading deviation threshold, the lateral deviation between the vehicle real-time rear axle center and the target point is less than or equal to a lateral deviation threshold, and the longitudinal deviation between the vehicle real-time rear axle center and the target point is less than or equal to a longitudinal deviation threshold.

[0094] Those skilled in the art can clearly understand that the parking control device 200 provided by the embodiments of the present application can realize the parking control method provided by the embodiments of the present application. The specific working process of the above device and module can refer to the process corresponding to the parking control method in the embodiments of the present application, which will not be repeated here.

[0095] In the embodiments provided in the present application, the coupling, direct coupling or communication connection between the modules shown or discussed can be indirect coupling or communication coupling through some interfaces, devices or modules, and can be electrical, mechanical or other forms, which are not limited in the embodiments of the present application.

[0096] In addition, each functional module in the embodiments of the present application can be integrated in one processing module, or each module can exist physically independently, or two or more modules can be integrated in one module. The integrated module can be realized in the form of hardware or in the form of a functional module of software, which is not limited in the embodiments of the present application.

[0097] Figure 14 is a structural schematic diagram of a vehicle provided by an embodiment of the present application. The vehicle 300 can be a gasoline vehicle or a new energy vehicle, and the new energy vehicle can include but is not limited to an electric energy vehicle or a hydrogen energy vehicle, etc. The vehicle 300 can be an autonomous driving vehicle, a semi-autonomous driving vehicle or a non-autonomous driving vehicle, etc. The vehicle 300 can include one or more of the following components: a memory 310, one or more processors 320 and one or more application programs, wherein the one or more application programs can be stored in the memory 310 and configured to make the one or more processors 320 execute the above parking control method provided by the embodiments of the present application when called by the one or more processors 320.

[0098] The processor 320 can include one or more processing cores. The processor 320 connects various parts in the entire vehicle 300 by various interfaces and lines, for running or executing instructions, programs, code sets or instruction sets stored in the memory 310, and calling and running or executing data stored in the memory 310, to perform various functions and process data of the vehicle 300.

[0099] The processor 320 can be realized in at least one hardware form of a digital signal processing (Digital Signal Processing, DSP for short), a field-programmable gate array (Field-Programmable Gate Array, FPGA for short) and a programmable logic array (Programmable Logic Array, PLA for short).

[0100] The processor 320 can be integrated with one or several combinations of a central processing unit (CPU), a graphics processing unit (GPU) and a modem. The CPU is mainly used to process operating systems, user interfaces and application programs, etc. The GPU is used to render and draw display content. The modem is used to process wireless communication. It can be understood that the above-mentioned modem can also not be integrated in the processor 320, but be implemented by a separate communication chip.

[0101] The memory 310 can include a random access memory (RAM) and can also include a read-only memory (ROM). The memory 310 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 310 can include a program storage area and a data storage area. The program storage area can store instructions for implementing an operating system, instructions for implementing at least one function, instructions for implementing the above-mentioned various method embodiments, etc. The data storage area can store data created by the vehicle 300 in use, etc.

[0102] Figure 15 FIG. 4 is a structural schematic diagram of a computer readable storage medium provided by an embodiment of the present application. The computer readable storage medium 400 stores program code 410. The program code 410 is used to cause a processor to execute the above-mentioned parking control method provided by the embodiments of the present application when the processor calls the program code 410.

[0103] The computer readable storage medium 400 can include, but is not limited to, an electronic memory such as a flash memory, an electrically-erasable programmable read-only memory (EEPROM), an erasable programmable read-only memory (EPROM), a hard disk or a ROM.

[0104] In some embodiments, the computer-readable storage medium 400 can comprise a non-transitory computer-readable storage medium. The computer-readable storage medium 400 has a storage space for program codes 410 to perform any of the method steps of the above methods. These program codes 410 can be read from or written to one or more computer program products. The program codes 410 can be compressed in a suitable form.

[0105] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than limit the technical solutions thereof. Although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can still make modifications to the technical solutions recorded in the foregoing embodiments, or make equivalent replacements to part of the technical features thereof; and these modifications or replacements do not drive the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A parking control method, characterized in that, include: Acquire the parking space, the drivable area corresponding to the parking space, and the real-time position and pose of the vehicle, wherein the real-time position and pose of the vehicle includes the real-time rear axle center and the real-time heading of the vehicle. Based on the target point in the parking space, a vehicle attitude area distribution map is generated. The vehicle attitude area distribution map includes multiple areas, and each area has predefined parking control parameters, including the desired vehicle heading, braking start distance, and braking stop distance. Based on the real-time rear axle center of the vehicle, determine the current location of the vehicle in the vehicle attitude area distribution map; The heading deviation value is determined based on the vehicle's real-time heading and the expected vehicle heading in the current area; Based on the braking start distance and braking stop distance of the current area, determine the corresponding vehicle safety boundary; Within the drivable area, lateral control is performed based on the heading deviation value, and longitudinal control and gear shifting control are performed based on the vehicle safety boundary, the heading deviation value, and the drivable area, so as to enable the vehicle to park in the parking space.

2. The method according to claim 1, characterized in that, The step of generating a vehicle posture area distribution map based on the target points in the parking space includes: Obtain the density of regions within the vehicle attitude region distribution map; A vehicle attitude region distribution map is generated based on the target points and the density.

3. The method according to claim 2, characterized in that, The step of generating a vehicle posture region distribution map based on the target points and the density includes: Using the target point as a common endpoint, multiple curves are generated on the side where the vehicle is located according to the density, and the curvatures of the multiple curves are different. Using the target point as a common center, multiple arcs are generated on the side where the vehicle is located according to the density. The radii of the multiple arcs are different. The multiple curves and the multiple arcs intersect to form multiple regions, and the multiple regions form a vehicle posture region distribution map.

4. The method according to claim 1, characterized in that, The longitudinal control based on the vehicle safety boundary, the heading deviation value, and the drivable area includes: The distances between the front and rear of the vehicle and the drivable area are obtained in real time, and the shorter distance between the front and rear of the vehicle and the drivable area is taken as the target distance. When the target distance or the deviation value decreases, control the vehicle to decelerate; When the target distance is less than the braking initiation distance of the current area, the vehicle is controlled to begin braking and deceleration. When the vehicle safety boundary overlaps with the drivable area, the vehicle is controlled to brake and stop.

5. The method according to claim 4, characterized in that, The gear shifting control based on the vehicle safety boundary, the heading deviation value, and the drivable area includes: When the vehicle safety boundary and the drivable area overlap, gear switching control is performed between forward and reverse gears; When the vehicle safety boundary and the drivable area do not overlap and the heading deviation value meets the specified conditions, the vehicle gear is switched to the off-road gear.

6. The method according to any one of claims 1 to 5, characterized in that, The method further includes: When the heading deviation value is less than or equal to the heading deviation threshold, and the lateral deviation between the real-time rear axle center of the vehicle and the target point is less than or equal to the lateral deviation threshold, and the longitudinal deviation between the real-time rear axle center of the vehicle and the target point is less than or equal to the longitudinal deviation threshold, the vehicle is determined to be parked in the parking space and parking is stopped.

7. A parking control device, characterized in that, include: The information perception module is used to acquire the parking space, the drivable area corresponding to the parking space, and the real-time position and pose of the vehicle, wherein the real-time position and pose of the vehicle includes the real-time rear axle center and the real-time heading of the vehicle. The distribution map generation module is used to generate a vehicle attitude area distribution map based on the target points in the parking space. The vehicle attitude area distribution map includes multiple areas, and each area has predefined parking control parameters, including the desired vehicle heading, braking start distance, and braking stop distance. The position determination module is used to determine the current location of the vehicle in the vehicle attitude area distribution map based on the real-time rear axle center of the vehicle. The parking control module is used to determine a heading deviation value based on the vehicle's real-time heading and the expected vehicle heading of the current area; determine the corresponding vehicle safety boundary based on the braking start distance and braking stop distance of the current area; and perform lateral control based on the heading deviation value within the drivable area, and perform longitudinal control and gear shifting control based on the vehicle safety boundary, the heading deviation value, and the drivable area to enable the vehicle to park in the parking space.

8. A vehicle, characterized in that, include: Memory; One or more processors; One or more applications, stored in the memory, for causing the one or more processors to perform the method as described in any one of claims 1 to 6 when invoked by the one or more processors.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores program code that, when invoked by a processor, causes the processor to perform the method as described in any one of claims 1 to 6.

Images