Automatic parking method and device, electronic equipment and medium

Abstract

The application discloses an automatic parking method, when a target vehicle is in a parking stage, collecting ultrasonic wave data in real time through an ultrasonic wave sensor of the target vehicle; obtaining a parking space group according to the real-time collected ultrasonic wave data; adjusting an initial parking space pose of the parking space group according to an occupancy grid map constructed based on the ultrasonic wave data, obtaining an adjusted parking space pose of the parking space group; obtaining a target parking space to be parked into by the target vehicle from the parking space group; and controlling the target vehicle to park into the target parking space based on the adjusted parking space pose. The automatic parking method, device, electronic equipment and medium disclosed by the application can effectively reduce pose estimation error when a parking space is detected by using an ultrasonic wave radar sensor, so that the accuracy of the obtained parking space pose is higher, and the safety performance during automatic parking is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of automatic parking, in particular to an automatic parking method and device, an electronic device and a medium. BACKGROUND

[0002] With the rapid development of automatic parking technology, ultrasonic radar sensors are widely used in automatic parking auxiliary systems. The ultrasonic radar parking space detection algorithm is used for parking space detection. After detecting the parking space, the vehicle is automatically parked in the corresponding parking space to improve the efficiency of automatic parking.

[0003] However, when using ultrasonic radar sensors to detect parking spaces, the prior art usually observes the corresponding scatter points through the left front and right front two side long-distance ultrasonic sensors, and then detects the parking space based on the observed scatter points. However, ultrasonic data is not as accurate as laser radar data. For long-distance ultrasonic waves, the observable area is roughly a sector, which will cause a certain deviation between the detected obstacle boundary and the actual obstacle boundary. Moreover, the detected parking space pose cannot be adjusted in the subsequent parking process. During the parking process, the ego vehicle often has a large amount of steering motion, which may cause a large cumulative positioning error, and thus the detected parking space pose may have a large deviation from the actual pose after coordinate transformation. In severe cases, it may even cause the ego vehicle to collide with the obstacles on both sides of the parking space, resulting in a large pose estimation error during the ego vehicle motion when using ultrasonic radar sensors to detect parking spaces, and the parking space pose deviation caused by the large pose estimation error will also increase. SUMMARY

[0004] The embodiments of the present application provide an automatic parking method, device, electronic device and medium, which can effectively reduce the pose estimation error when using ultrasonic radar sensors to detect parking spaces, so that the accuracy of the obtained parking space pose is higher, and thus the safety performance during automatic parking is improved.

[0005] The first aspect of the embodiments of the present application provides an automatic parking method, which comprises:

[0006] When the target vehicle is in the parking stage, real-time ultrasonic data is collected by the ultrasonic sensor of the target vehicle;

[0007] According to the real-time collected ultrasonic data, a stoppable parking space group is obtained;

[0008] According to the occupancy grid map constructed according to the ultrasonic data, the initial parking space pose of the parking space group is adjusted to obtain the adjusted parking space pose of the parking space group;

[0009] The target parking space to be parked into by the target vehicle is obtained from the parking space group;

[0010] Based on the adjusted parking space pose, the target vehicle is controlled to park in the target parking space.

[0011] Optionally, the initial parking space pose of the parking space group is adjusted based on the occupancy grid map constructed according to the ultrasonic data to obtain an adjusted parking space pose of the parking space group.

[0012] According to the ultrasonic data, ultrasonic scatter points are obtained.

[0013] According to the ultrasonic scatter points, the initial parking space pose is obtained.

[0014] The initial parking space pose is adjusted based on the occupancy grid map to obtain the adjusted parking space pose.

[0015] Optionally, the initial parking space pose is adjusted based on the occupancy grid map to obtain the adjusted parking space pose, including:

[0016] According to the occupancy grid map, a current lane direction of the target vehicle is obtained.

[0017] The initial parking space direction of the parking space group is adjusted based on the current lane direction to obtain an adjusted parking space direction of the parking space group.

[0018] According to the two-side obstacles in the two-side regions of interest of the parking space group and the tail obstacle in the tail region of interest, longitudinal adjustment parameters and transverse adjustment parameters of the parking space group are obtained, wherein the two-side obstacles and the tail obstacle are obtained based on the occupancy grid map.

[0019] The initial parking space position is adjusted based on the adjusted parking space direction, the longitudinal adjustment parameters and the transverse adjustment parameters to obtain the adjusted parking space pose.

[0020] Optionally, the initial parking space direction of the parking space group is adjusted based on the current lane direction to obtain the adjusted parking space direction, including:

[0021] According to the current lane direction and the initial parking space direction, a rotation angle difference is obtained.

[0022] The initial parking space direction is adjusted based on the rotation angle difference to obtain the adjusted parking space direction.

[0023] Optionally, the longitudinal adjustment parameters and the transverse adjustment parameters of the parking space group are obtained according to the two-side obstacles in the two-side regions of interest of the parking space group and the tail obstacle in the tail region of interest, including:

[0024] acquiring a left side region of interest, a right side region of interest and the rear region of interest of the target vehicle from the occupancy grid map, wherein the two side regions of interest include the left side region of interest and the right side region of interest;

[0025] acquiring obstacles in the two side regions of interest as the two side obstacles, and acquiring obstacles in the rear region of interest as the rear obstacles;

[0026] acquiring the longitudinal adjustment parameter according to the two side obstacles and the rear obstacles;

[0027] acquiring the lateral adjustment parameter according to the two side obstacles.

[0028] Optionally, the acquiring the longitudinal adjustment parameter according to the two side obstacles and the rear obstacles comprises:

[0029] acquiring a maximum longitudinal value corresponding to the two side obstacles;

[0030] acquiring the longitudinal adjustment parameter according to the maximum longitudinal value and a position of a nearest obstacle in the rear obstacles, wherein the nearest obstacle is an obstacle in the rear obstacles closest to the parking space group.

[0031] Optionally, the acquiring the lateral adjustment parameter according to the two side obstacles comprises:

[0032] acquiring a minimum lateral value of an obstacle lateral direction between the left side obstacle and the right side obstacle, and acquiring a maximum lateral value of the obstacle lateral direction between the left side obstacle and the right side obstacle;

[0033] acquiring the lateral adjustment parameter according to the minimum lateral value and the maximum lateral value.

[0034] Optionally, in the process of controlling the target vehicle to park in the target parking space based on the adjusted parking space pose, the method further comprises:

[0035] continuously adjusting the adjusted parking space pose according to the occupancy grid map constructed based on the ultrasonic data, to obtain a real-time adjusted parking space pose of the parking space group.

[0036] Optionally, the real-time acquisition of the ultrasonic data by the ultrasonic sensor of the target vehicle comprises:

[0037] real-time acquisition of the ultrasonic data by all ultrasonic sensors arranged on the body of the target vehicle.

[0038] The second aspect of the embodiment of the application further provides an automatic parking device, and the device comprises:

[0039] an ultrasonic data acquisition unit, configured to collect ultrasonic data in real time through an ultrasonic sensor of the target vehicle when the target vehicle is in a parking stage;

[0040] a parking space group acquisition unit, configured to acquire a parking space group according to the ultrasonic data collected in real time;

[0041] a pose adjustment unit, configured to adjust an initial parking space pose of the parking space group according to an occupancy grid map constructed based on the ultrasonic data, to obtain an adjusted parking space pose of the parking space group;

[0042] a parking space selection unit, configured to acquire a target parking space to be parked into by the target vehicle from the parking space group;

[0043] a parking unit, configured to control the target vehicle to park into the target parking space based on the adjusted parking space pose.

[0044] The third aspect of the embodiment of the application provides an electronic device, comprising a memory and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by one or more processors to execute operation instructions included in the one or more programs for performing the automatic parking method provided in the first aspect.

[0045] The fourth aspect of the embodiment of the application provides a computer program product, characterized in that the computer program product comprises computer instructions stored in a computer readable storage medium and adapted to be read and executed by a processor to enable a computer device with the processor to perform steps corresponding to the automatic parking method provided in the first aspect.

[0046] The one or at least one technical solutions in the embodiment of the application have at least the following technical effects:

[0047] Based on the above technical scheme, when the target vehicle is in the parking stage, the ultrasonic sensor of the target vehicle is used to collect ultrasonic data in real time to obtain a parking group; the initial parking position of the parking group is adjusted based on the occupancy grid map constructed based on the ultrasonic data to obtain an adjusted parking position of the parking group; the target parking position of the target vehicle is obtained from the parking group; and the target vehicle is parked in the target parking position based on the adjusted parking position. Therefore, the parking position during parking is the adjusted parking position, which is obtained by adjusting the initial parking position based on the occupancy grid map constructed based on the ultrasonic data, so that the matching degree of the adjusted parking position and the actual parking position of the target vehicle is higher. In this way, the effect of effectively reducing the position estimation error when the ultrasonic radar sensor is used for parking detection can be achieved, the accuracy of the obtained parking position is higher, the probability of colliding with obstacles during parking is reduced, and the safety performance during automatic parking is improved. BRIEF DESCRIPTION OF DRAWINGS

[0048] Figure 1 A flowchart of an automatic parking method provided by an embodiment of the present application is shown in the figure.

[0049] Figure 2 A flowchart of obtaining an adjusted parking position provided by an embodiment of the present application is shown in the figure.

[0050] Figure 3 A structural diagram of an initial parking position and an adjusted parking position in an occupancy grid map is shown in the figure.

[0051] Figure 4 A block diagram of an automatic parking device provided by an embodiment of the present application is shown in the figure.

[0052] Figure 5 A structural diagram of an electronic device provided by an embodiment of the present application is shown in the figure. DETAILED DESCRIPTION

[0053] The main implementation principles, specific implementation manners, and corresponding beneficial effects of the technical solutions of the embodiments of the present application will be described in detail below with reference to the accompanying drawings.

[0054] EMBODIMENT

[0055] Please refer to Figure 1 The embodiment of the present application provides an automatic parking method, which comprises the following steps.

[0056] S101, when a target vehicle is in a parking stage, collecting ultrasonic data in real time through an ultrasonic sensor of the target vehicle;

[0057] S102, obtaining a parking group based on the real-time collected ultrasonic data;

[0058] S103, adjusting the initial parking space pose of the parking space group according to the occupancy grid map constructed based on the ultrasonic wave data, to obtain an adjusted parking space pose of the parking space group;

[0059] S104, obtaining a target parking space in the parking space group for the target vehicle to be parked in;

[0060] S105, controlling the target vehicle to park in the target parking space based on the adjusted parking space pose.

[0061] An automatic parking method in an embodiment of the present specification can be applied in a vehicle terminal or a user terminal, wherein the vehicle terminal can be a car machine or a controller of the target vehicle, and the target vehicle can be an electric vehicle, a hybrid vehicle, a fuel vehicle, etc., and the user terminal can be a smart phone, a smart watch, a tablet computer, a notebook computer, a desktop computer, etc. Hereinafter, the application in the vehicle terminal is taken as an example.

[0062] In step S101, it can be detected whether the target vehicle enters the parking lot for the first time in the recent period of time, and if so, it is determined that the target vehicle is in the parking stage, wherein the recent period of time can be set according to the actual demand, for example, it can be one hour, half an hour and 20 minutes, etc. in the recent period of time, and the camera device can be used to detect whether the target vehicle enters the parking lot for the first time in the recent period of time, and the camera device can be a camera, a camera and a holder, etc.

[0063] When it is determined that the target vehicle is in the parking stage, all ultrasonic sensors arranged on the body of the target vehicle can be used to collect ultrasonic wave data in real time, so that the collected ultrasonic wave data is more abundant, wherein the all ultrasonic sensors arranged on the body of the target vehicle can include a left front ultrasonic sensor arranged on the left front of the body of the target vehicle, a right front ultrasonic sensor arranged on the right front of the body of the target vehicle, a left rear ultrasonic sensor arranged on the left rear of the body of the target vehicle, a right rear ultrasonic sensor arranged on the right rear of the body of the target vehicle, a front ultrasonic sensor arranged on the front of the body of the target vehicle, and a rear ultrasonic sensor arranged on the rear of the body of the target vehicle, etc.

[0064] In an embodiment, the left front ultrasonic sensor, the left rear ultrasonic sensor, the right front ultrasonic sensor and the right rear ultrasonic sensor usually belong to long-distance ultrasonic sensors, and the front ultrasonic sensor and the rear ultrasonic sensor usually belong to short-distance ultrasonic sensors; of course, all ultrasonic sensors arranged on the body of the target vehicle can be long-distance ultrasonic sensors or short-distance ultrasonic sensors, etc.

[0065] In an embodiment, after the ultrasonic data is collected in real time by the ultrasonic sensor of the target vehicle, the collected ultrasonic data is uploaded to the vehicle terminal, so that the vehicle terminal can obtain the collected ultrasonic data in real time.

[0066] After the collected ultrasonic data is obtained in real time, step S102 is performed.

[0067] In step S102, in order to make the accuracy of obtaining the parking space group higher, after the collected ultrasonic data is obtained in real time, first, it is detected whether the target vehicle is in a horizontal driving state of driving horizontally along the lane, and if it is detected that the target vehicle is in the horizontal driving state, the parking space detection is performed from the parking space detection ultrasonic data in the collected ultrasonic data in real time to obtain the parking space group. The parking space detection ultrasonic data includes ultrasonic data collected by the left ultrasonic sensor and ultrasonic data collected by the right ultrasonic sensor, wherein the left ultrasonic sensor includes at least one of the left front ultrasonic sensor and the right rear ultrasonic sensor, and the right ultrasonic sensor includes at least one of the right front ultrasonic sensor and the right rear ultrasonic sensor. Of course, all the ultrasonic data collected in real time can also be directly used for parking space detection to obtain the parking space group, and the present specification does not make specific limitations.

[0068] In addition, when the parking space detection is performed using the parking space detection ultrasonic data, the parking space detection algorithm using ultrasonic scatter points is usually used to perform the parking space detection to obtain the parking space group. The parking space group refers to that in the parking space detection algorithm based on ultrasonic scatter points, the parking space position is determined by detecting a continuous idle parking interval, and a continuous idle parking interval corresponds to 1-N parking spaces according to its length, the 1-N parking spaces are consistent in direction and adjacent to each other, and are called a parking space group, and N is an integer greater than 1.

[0069] In the process of performing the parking space detection using the parking space detection ultrasonic data, the initial parking space pose of the parking space group is also obtained at the same time.

[0070] In an embodiment, the parking space group that can be parked can be one or more, and the following is a specific example of the parking space group being one.

[0071] After the parking space group is obtained, step S103 is performed.

[0072] And, before performing step S103, first need to obtain the occupancy grid map, specifically, using all the real-time acquisition of ultrasonic data, build occupancy grid map. For example, in all ultrasonic sensors set on the target vehicle body including the left front ultrasonic sensor, left rear ultrasonic sensor, right front ultrasonic sensor, right rear ultrasonic sensor, front ultrasonic sensor and rear ultrasonic sensor these six kinds of ultrasonic sensors, then through the six kinds of ultrasonic sensor real-time acquisition of ultrasonic data, continuously build occupancy grid map.

[0073] In step S103, according to the constructed occupancy grid map, the initial parking space pose of the parking space group is adjusted to obtain the adjusted parking space pose of the parking space group.

[0074] Specifically, the ultrasonic data can be used to obtain ultrasonic scatter points, and the initial parking space pose of the parking space group can be obtained according to the ultrasonic scatter points. The initial parking space pose is adjusted using the occupancy grid map to obtain the adjusted parking space pose.

[0075] Specifically, in step S102, in the process of using the parking space detection ultrasonic data to detect the parking space, the initial parking space pose of the parking space group is obtained at the same time. In the process of using the parking space detection ultrasonic data to detect the parking space, the ultrasonic scatter points are first obtained, and the parking space group and the initial parking space pose of the parking space group are obtained by using the ultrasonic scatter points to detect the parking space.

[0076] In an embodiment, when the initial parking space pose is adjusted using the occupancy grid map to obtain the adjusted parking space pose, the current lane direction of the target vehicle can be obtained according to the occupancy grid map. The initial parking space direction of the parking space group is adjusted using the current lane direction to obtain the adjusted parking space direction of the parking space group. The longitudinal adjustment parameter and the transverse adjustment parameter of the parking space group are obtained according to the two side obstacles in the two side regions of interest and the tail obstacle in the tail region of interest of the parking space group, wherein the two side obstacles and the tail obstacle are obtained based on the occupancy grid map. The initial parking space position is adjusted according to the adjusted parking space direction, the longitudinal adjustment parameter and the transverse adjustment parameter to obtain the adjusted parking space pose.

[0077] Specifically, in the process of obtaining the current lane direction, the occupancy grid map can be divided into a left grid map of the ego vehicle and a right grid map of the ego vehicle. For the left grid map of the ego vehicle, a first obstacle set in the left grid map of the ego vehicle is obtained, and a straight line fitting is performed on the first obstacle set to obtain a left fitting straight line. In the process of performing the straight line fitting, a random sample consensus (RANSAC) algorithm and a least square method can be used to perform the straight line fitting. Correspondingly, for the right grid map of the ego vehicle, a second obstacle set in the right grid map of the ego vehicle is obtained, and a straight line fitting is performed on the second obstacle set to obtain a right fitting straight line. The left straight line and the right straight line can exist or not exist. For example, if the first obstacle set is successfully fitted with a straight line, the fitted straight line is the left fitting straight line, and the left fitting straight line actually exists. If the first obstacle set is not successfully fitted with a straight line, the left fitting straight line does not exist.

[0078] Thus, after the left fitting straight line and the right fitting straight line are obtained, the current lane direction is obtained according to the left fitting straight line, the right fitting straight line, and the driving direction of the target vehicle. For example, an average value between the fitted straight line and the driving direction can be taken as the current lane direction, or the current lane direction can be obtained by using a voting method. Of course, in the application scenario of the multi-modal algorithm, the current lane direction can also be obtained according to the orientation estimated by the image algorithm. After the current lane direction is obtained, the initial parking space direction is adjusted by using the current lane direction to obtain the adjusted parking space direction of the parking space group. The rotation angle difference can be obtained according to the current lane direction and the initial parking space direction. The initial parking space direction is adjusted by using the rotation angle difference to obtain the adjusted parking space direction.

[0079] Specifically, the initial parking space direction detected by the ultrasonic wave is horizontal or vertical to the lane line. Since the position information of the initial parking space is usually the side of the parking space close to the lane, when the parking space group is rotated, the midpoint of the line segment of the side of the parking space group close to the lane is taken as the center of rotation of the rotation angle difference θ adjust The initial parking space direction is adjusted, and the specific adjustment method is as follows:

[0080] θ adjust =AngleNorm(θ corridor -θ origin ) Formula 1

[0081] In formula 1, θ corridor is the current lane direction where the parking space group is located, θ origin is the initial parking space direction, and the AngleNorm method normalizes the angle difference to [-π, π).

[0082] In another embodiment, when the rotation angle difference is obtained according to the current lane direction and the initial parking space direction, the absolute value of the square difference between the parking space direction and the initial parking space direction can be obtained as the rotation angle difference, or the absolute difference between the current lane direction and the initial parking space direction can be directly obtained as the rotation angle difference.

[0083] In an embodiment, when the longitudinal adjustment parameter and the lateral adjustment parameter of the parking space group are obtained according to the two-side obstacles in the two-side interested region and the tail obstacles in the tail interested region of the two sides of the parking space group, the left interested region, the right interested region and the tail interested region of the target vehicle can be obtained from the occupancy grid map, wherein the two-side interested region includes the left interested region and the right interested region; the obstacles in the two-side interested region are obtained as the two-side obstacles, and the obstacles in the tail interested region are obtained as the tail obstacles; the longitudinal adjustment parameter is obtained according to the two-side obstacles and the tail obstacles; and the lateral adjustment parameter is obtained according to the two-side obstacles.

[0084] In an embodiment, when the obstacles in each interested region of the left interested region, the right interested region and the tail interested region are obtained, after all the obstacles in the interested region are obtained, the obstacles in the interested region are clustered, and the obstacles smaller than the set size are removed, and finally the obtained obstacles are obtained as the obstacles in the interested region. For example, taking the tail interested region as an example, if the tail interested region includes obstacles b1, b2, b3, c1, c2, c3 and d1, b1, b2, b3, c1, c2, c3 and d4 are clustered to obtain b1, b2 and b3 as a first class represented by B11, and c1, c2 and c3 are clustered to obtain a second class represented by C11, and d1 is clustered to obtain a third class represented by D11, but since the size of d1 is smaller than the set size, d1 is removed, so that the tail obstacles in the tail interested region are obstacles b1, b2, b3, c1, c2 and c3, and the first class B11 includes b1, b2 and b3, and the second class C11 includes c1, c2 and c3. The set size can be set according to actual needs, or can be set by the device or manually, and the set size is usually the size that does not affect the vehicle passing, for example, it can be 30cm×30cm×30cm and 25cm×25cm×26cm, etc.

[0085] In order to make the accuracy of the optimized pose more robust, obstacles smaller than the set size can be removed. Since obstacles smaller than the set size can be noise points in the process of constructing the grid map, after removing small size noise points, the remaining obstacles are used for pose optimization, which can make the accuracy of the optimized pose more robust.

[0086] In an embodiment, since the parking space can exist on the left and / or right side of the lane, there are two types of parking spaces, i.e. horizontal and vertical, i.e. 2x2=4 cases in total. Without loss of generality, the vertical parking space on the right side of the lane is taken as an example, and X represents the horizontal direction and Y represents the vertical direction in the following.

[0087] In an embodiment, for the convenience of calculation, all the obstacle grids in the three regions of interest can be transformed into a right-handed coordinate system with the center position of the parking space group after the orientation of the parking space is optimized as the origin, the orientation of the parking space as the positive direction of Y, and the left side of the parking space group as the positive direction of X. Of course, all the obstacle grids in the three regions of interest can also be transformed into a left-handed coordinate system or the like.

[0088] In an embodiment, when the longitudinal adjustment parameter is obtained according to the two-side obstacles and the tail obstacles, the maximum longitudinal value corresponding to the two-side obstacles can be obtained; and the longitudinal adjustment parameter is obtained according to the maximum longitudinal value and the position of the nearest obstacle in the tail obstacles, wherein the nearest obstacle is the obstacle closest to the parking space group in the tail obstacles.

[0089] In an embodiment, if there is no obstacle in the left region of interest, the right region of interest and the tail region of interest, the Y-direction position adjustment value is y adjust , wherein:

[0090] y adjust =y estimate -y origin Formula 2

[0091] In formula 2, y origin is the Y-direction position of the center of the parking space after the orientation is adjusted, since the obstacle grid coordinates of all the regions of interest have been transformed into the coordinate system with the center of the parking space group as the origin, y origin =0; y estimate is a set value, since there is no obstacle in the above-mentioned three regions of interest, y estimate =y origin .

[0092] In an embodiment, if there is an obstacle in the left region of interest and the right region of interest, and there is no obstacle in the tail region of interest, the left-side obstacle in the left region of interest and the right-side obstacle in the right region of interest can be obtained; and the Y-direction position adjustment value y adjust is obtained according to the maximum Y value corresponding to the left-side obstacle and the right-side obstacle, wherein:

[0093]

[0094] In formula 3, L is the standard parking space length, and y side_obstacle_maxis the maximum Y value corresponding to the left obstacle grid and the right obstacle grid, and is the Y position of the parking space group center estimated according to the obstacles on both sides.

[0095] In an embodiment, if there are obstacles in the left region of interest, the right region of interest and the tail region of interest, the Y direction position adjustment value is obtained according to the maximum Y value corresponding to the left obstacle grid and the right obstacle grid and the nearest obstacle, that is, adjust wherein:

[0096]

[0097] In formula 4, Th is the minimum threshold value of the distance from the tail of the parking space to the rear wall obstacle, which can be 0.1 or 0.2 meters, etc., y back_obstacle_max is the maximum Y value corresponding to the tail obstacle grid in the tail region of interest, and is the Y minimum value of the parking space group center estimated according to the tail obstacle grid in the tail region of interest.

[0098] In an embodiment, when the lateral adjustment parameter is obtained according to the obstacles on both sides, the minimum lateral value of the obstacle lateral direction between the left obstacle and the right obstacle can be obtained, and the maximum lateral value of the obstacle lateral direction between the left obstacle and the right obstacle can be obtained; and then the lateral adjustment parameter is obtained according to the minimum lateral value and the maximum lateral value.

[0099] Specifically, the average value of the minimum lateral value and the maximum lateral value can be used as the lateral adjustment parameter, the difference between the average value and the lateral set value can be used as the lateral adjustment parameter, or the product of the average value and the weight can be used as the lateral adjustment parameter. The lateral set value can be set according to the actual situation, and the lateral set value can be represented by x origin .

[0100] In an embodiment, the lateral adjustment parameter is represented by x adjust , wherein:

[0101]

[0102] In formula 5, x origin is the X direction position of the adjusted parking space group center, since the obstacle grid coordinates of all the regions of interest have been transformed to the coordinate system with the parking space group center as the origin, x origin = 0; x side_front_obstacle_min is the minimum lateral value, and x side_rear_obstacle_max is the maximum lateral value.

[0103] And, after obtaining the adjusted parking space direction, the longitudinal adjustment parameter and the transverse adjustment parameter, the longitudinal direction of the parking space group is adjusted by using the longitudinal adjustment parameter, the transverse direction of the parking space group is adjusted by using the transverse adjustment parameter, and then the adjusted parking space pose is obtained according to the adjusted parking space direction, the adjusted longitudinal direction and the adjusted transverse direction of the parking space group.

[0104] In actual application, referring to Figure 2 , the step of obtaining the adjusted parking space pose specifically includes the following steps: S1, estimating the lane direction according to the occupancy grid map; after the lane direction is estimated, S2, optimizing the parking space orientation according to the lane direction is performed; then S3, the obstacles on the left and right sides and the tail of the parking space group are found, that is, the two-side obstacles in the left and right interest regions and the obstacle in the tail interest region are obtained as the tail obstacle; after the two-side obstacles and the tail obstacle are obtained, S4, obstacle clustering is performed and small obstacles are removed, wherein the small obstacle refers to the obstacle smaller than the set size, since the obstacle smaller than the set size may be a noise point in the process of constructing the grid map, after the small size noise point is removed, the remaining obstacles are used for pose optimization, which can make the optimized pose more accurate and robust.

[0105] And, after step S4 is performed, S5, the parking space longitudinal vector is calculated according to the obstacles on the left and right sides and the tail of the parking space group is performed; then S6, the parking space transverse vector is calculated according to the obstacles on the left and right sides of the parking space group, at this time, the parking space transverse vector can be calculated by using the optimization or search or direct calculation based on the obstacles on the left and right sides of the parking space group; finally, S7, the optimized parking space orientation angle, longitudinal direction and transverse position are output.

[0106] In this way, the transverse adjustment parameter and the longitudinal adjustment parameter of the parking space group are adjusted by the obstacles in the left interest region, the right interest region and the tail interest region, which reduces the deviation between the obstacle boundary detected by the ultrasonic wave and the actual obstacle boundary, so that the adjusted parking space pose adjusted by the transverse adjustment parameter and the longitudinal adjustment parameter matches the actual parking space pose of the parking space group more accurately.

[0107] After the adjusted parking space pose is obtained, or at the same time, step S104 is performed.

[0108] In step S104, the parking space corresponding to the parking space selection operation can be obtained as the target parking space according to the user's parking space selection operation in the parking space group. For example, if the parking space group includes parking spaces A1, A2 and A3, if the user clicks A3, A3 is taken as the target parking space according to the user's operation of clicking A3.

[0109] After the target parking space and the adjusted parking space pose are obtained, step S105 is performed.

[0110] In step S105, after obtaining the adjusted parking space pose and the target parking space, the adjusted parking space pose and the target parking space are processed by an automatic parking algorithm such as a path planning algorithm to obtain a control strategy of the target vehicle, and the target vehicle is controlled to park into the target parking space by the control strategy.

[0111] In another embodiment, during the process of controlling the target vehicle to park into the target parking space based on the adjusted parking space pose, the adjusted parking space pose can also be continuously adjusted according to the occupancy grid map constructed based on the ultrasonic data, to obtain a real-time adjusted parking space pose of the parking space group.

[0112] Specifically, the occupancy grid map is continuously constructed based on the real-time obtained ultrasonic data, and the adjusted parking space pose is continuously adjusted based on the continuously constructed occupancy grid map to obtain the real-time adjusted parking space pose of the parking space group, so that during the process of controlling the target vehicle to park into the target parking space, the parking space poses of the parking space group are adjusted in real time, thereby reducing the problem that the relative pose deviation of the detected stopable parking space after transformation is large due to the cumulative error of the parking space pose estimation, and further ensuring the accuracy of the real-time obtained adjusted parking space pose.

[0113] For example, after obtaining the ultrasonic data, the ultrasonic scatter points in the scatter point diagram corresponding to the ultrasonic data are used for parking space detection to obtain an initial parking space pose of the parking space group; after obtaining the initial parking space pose, referring to Figure 3 the initial parking space pose 30 is displayed in the occupancy grid map constructed based on the ultrasonic data, and the left interest region 31, the right interest region 32 and the tail interest region 33 of the parking space group are obtained; the initial parking space pose 30 is adjusted based on the obstacles in the left interest region 31, the right interest region 32 and the tail interest region 33 to obtain an adjusted parking space pose 34 of the parking space group.

[0114] The one or at least one technical solutions in the embodiments of the present application have at least the following technical effects:

[0115] Based on the above technical scheme, when the target vehicle is in the parking stage, the ultrasonic sensor of the target vehicle is used to collect ultrasonic data in real time to obtain a parking group; an occupancy grid map is constructed based on the ultrasonic data, and the initial parking position of the parking group is adjusted based on the occupancy grid map to obtain an adjusted parking position of the parking group; a target parking position for the target vehicle to be parked in is obtained from the parking group; and the target vehicle is controlled to park in the target parking position based on the adjusted parking position. Therefore, the parking position during parking is the adjusted parking position, which is obtained by adjusting the initial parking position based on the occupancy grid map constructed based on the ultrasonic data, so that the matching degree of the adjusted parking position and the actual parking position of the target vehicle is higher. In this way, the effect of effectively reducing the position estimation error when the ultrasonic radar sensor is used to detect the parking position can be achieved, the accuracy of the obtained parking position is higher, the probability of colliding with obstacles during parking is reduced, and the safety performance during automatic parking is improved.

[0116] An automatic parking method is provided for the above embodiment, and an automatic parking device is also provided in the embodiment of the application. Please refer to Figure 4 The device comprises:

[0117] An ultrasonic data acquisition unit 401 is configured to collect ultrasonic data in real time through an ultrasonic sensor of a target vehicle when the target vehicle is in a parking stage.

[0118] A parking group acquisition unit 402 is configured to obtain a parking group based on the real-time collected ultrasonic data.

[0119] A position adjustment unit 403 is configured to adjust an initial parking position of the parking group based on an occupancy grid map constructed based on the ultrasonic data to obtain an adjusted parking position of the parking group.

[0120] A parking position selection unit 404 is configured to obtain a target parking position for the target vehicle to be parked in from the parking group.

[0121] A parking unit 405 is configured to control the target vehicle to park in the target parking position based on the adjusted parking position.

[0122] In an optional embodiment, the position adjustment unit 403 is configured to obtain ultrasonic scatter points based on the ultrasonic data, obtain the initial parking position based on the ultrasonic scatter points, and adjust the initial parking position based on the occupancy grid map to obtain the adjusted parking position.

[0123] In an optional implementation, the pose adjustment unit 403 is configured to: obtain a current lane direction of the target vehicle according to the occupancy grid map; adjust the initial parking space direction of the parking space group according to the current lane direction to obtain an adjusted parking space direction of the parking space group; obtain a longitudinal adjustment parameter and a lateral adjustment parameter of the parking space group according to two-side obstacles in the two-side regions of interest and a tail obstacle in the tail region of interest, wherein the two-side obstacles and the tail obstacle are obtained based on the occupancy grid map; and adjust the initial parking space position according to the adjusted parking space direction, the longitudinal adjustment parameter and the lateral adjustment parameter to obtain the adjusted parking space pose.

[0124] In an optional implementation, the pose adjustment unit 403 is configured to: obtain a rotation angle difference according to the current lane direction and the initial parking space direction; and adjust the initial parking space direction according to the rotation angle difference to obtain the adjusted parking space direction.

[0125] In an optional implementation, the pose adjustment unit 403 is configured to: obtain a left-side region of interest, a right-side region of interest and the tail region of interest of the target vehicle from the occupancy grid map, wherein the two-side regions of interest include the left-side region of interest and the right-side region of interest; obtain obstacles in the two-side regions of interest as the two-side obstacles and obtain obstacles in the tail region of interest as the tail obstacle; obtain the longitudinal adjustment parameter according to the two-side obstacles and the tail obstacle; and obtain the lateral adjustment parameter according to the two-side obstacles.

[0126] In an optional implementation, the pose adjustment unit 403 is configured to: obtain a maximum longitudinal value corresponding to the two-side obstacles; and obtain the longitudinal adjustment parameter according to the maximum longitudinal value and a position of a nearest obstacle in the tail obstacle, wherein the nearest obstacle is an obstacle in the tail obstacle closest to the parking space group.

[0127] In an optional implementation, the pose adjustment unit 403 is configured to: obtain a minimum lateral value of a lateral direction of obstacles between the left-side obstacle and the right-side obstacle and a maximum lateral value of the lateral direction of the obstacles between the left-side obstacle and the right-side obstacle; and obtain the lateral adjustment parameter according to the minimum lateral value and the maximum lateral value.

[0128] In an optional implementation, the pose adjustment unit 403 is configured to continuously adjust the adjusted parking space pose based on the occupancy grid map constructed according to the ultrasonic data, to obtain a real-time adjusted parking space pose of the parking space group during the process of controlling the target vehicle to park in the target parking space based on the adjusted parking space pose.

[0129] In an optional implementation, the ultrasonic data acquisition unit 401 is configured to acquire the ultrasonic data in real time through all the ultrasonic sensors arranged on the target vehicle.

[0130] As to the apparatus in the above-mentioned embodiments, the specific manners in which various modules perform operations have been described in detail in the embodiments of the method, and thus will not be described in detail here.

[0131] Figure 5 FIG. 8 is a block diagram of an electronic device 800 for an automatic parking method according to an example embodiment. The electronic device 800 can be, for example, a mobile phone, a computer, a digital broadcasting terminal, a message transmitting / receiving device, a game console, a tablet device, a medical device, an exercise device, a personal digital assistant, or the like.

[0132] Referring to Figure 5 The electronic device 800 can include one or more of the following components: a processing component 802, a memory 804, a power supply component 806, a multimedia component 808, an audio component 810, an input / output (I / O) interface 812, a sensor component 814, and a communication component 816.

[0133] The processing component 802 generally controls the overall operations of the electronic device 800, such as operations associated with display, phone calls, data communications, camera operations, and recording operations. The processing component 802 can include one or more processors 820 to execute instructions to complete all or part of the steps of the methods described above. In addition, the processing component 802 can include one or more modules to facilitate the interaction between the processing component 802 and other components. For example, the processing component 802 can include a multimedia module to facilitate the interaction between the multimedia component 808 and the processing component 802.

[0134] The memory 804 is configured to store various types of data to support the operation of the electronic device 800. Examples of such data include instructions for any application or method operating on the electronic device 800, contact data, phonebook data, messages, pictures, videos, and the like. The memory 804 can be implemented by any type of volatile or nonvolatile memory, or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, a magnetic disc or a optical disc.

[0135] The power component 806 supplies power for various components of the electronic device 800. The power component 806 can include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the electronic device 800.

[0136] The multimedia component 808 includes a screen providing an interface for displaying on the electronic device 800 and a user. In some embodiments, the screen can include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes the touch panel, the screen can be implemented as a touch screen to receive an input signal from a user. The touch panel includes one or more touch sensors to sense a touch, a slide, and a gesture on the touch panel. The touch sensor can not only sense a boundary of a touching or a sliding action, but also detect duration and pressure related to the touching or sliding action. In some embodiments, the multimedia component 808 includes a front camera and / or a back camera. The front camera and / or the back camera can receive external multimedia data when the device 800 is in an operation mode, such as a photographing mode or a video mode. Each of the front camera and the back camera can be a fixed optical lens system or have a focal length and optical zoom capability.

[0137] The audio component 810 is configured to output and / or input an audio signal. For example, the audio component 810 includes a microphone (MIC) configured to receive an external audio signal when the electronic device 800 is in an operation mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signal can be further stored in the memory 804 or transmitted via the communication component 816. In some embodiments, the audio component 810 also includes a speaker for outputting an audio signal.

[0138] The I / O interface 812 provides an interface between the processing component 802 and peripheral interface modules, which can be a keypad, a click wheel, buttons, and the like. The buttons can include, but are not limited to, a home button, a volume button, a start button, and a lock button.

[0139] The sensor component 814 includes one or more sensors for providing status assessments for various aspects of the electronic device 800. For example, the sensor component 814 can detect an open / closed position of the device 800, relative positioning of components, such as a display and a keypad of the electronic device 800, a change in position of the electronic device 800 or a component of the electronic device 800, presence or absence of user contact with the electronic device 800, orientation or acceleration / deceleration / g-force and temperature of the electronic device 800. The sensor component 814 can include an accelerometer, a gyroscope sensor, a magnetic sensor, a pressure sensor or a temperature sensor.

[0140] The communication component 816 is configured to facilitate wired or wireless communication between the electronic device 800 and other devices. The electronic device 800 can access a wireless network based on a corresponding communication standard, such as WiFi, 2G, or 3G, or a combination thereof. In an example embodiment, the communication component 816 receives a broadcast signal or broadcast related information from an external broadcast management system via a broadcast channel. In an example embodiment, the communication component 816 further includes a Near Field Communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on Radio Frequency Identification (RFID) techniques, Infrared Data Association (IrDA) techniques, Ultra-WideBand (UWB) techniques, Bluetooth (BT) techniques, and other techniques.

[0141] In an example embodiment, the electronic device 800 can be implemented using one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, micro-controllers, microprocessors, or other electronic elements for performing the above-described methods.

[0142] In an example embodiment, a non-transitory computer-readable storage medium including instructions, such as the memory 804 including instructions, is also provided that, when executed by the processor 820 of the electronic device 800, can cause the processor 820 to perform the above-described methods. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disc, and an optical data storage device, and the like.

[0143] In addition, it should be noted that: the embodiments of the present application also provide a computer program product or computer program, the computer program product or computer program can include computer instructions, the computer instructions can be stored in a computer readable storage medium. The processor of the computer equipment reads the computer instructions from the computer readable storage medium, and the processor can execute the computer instructions, so that the computer equipment executes the foregoing Figure 1 The description of the automatic parking method in the corresponding embodiment will not be repeated here. In addition, the description of the beneficial effects of using the same method will not be repeated. For technical details not disclosed in the computer program product or computer program embodiments involved in the present application, please refer to the description of the method embodiments of the present application.

[0144] Other embodiments of the application will be apparent to those skilled in the art from consideration of the specification and practice of the application disclosed herein. The application is intended to cover any variations, uses or adaptations of the application following, in general, the principles of the application and including such departures from the present disclosure as come within known

[0145] It should be understood that the application is not limited to the precise construction that has been described above and shown in the accompanying drawings, and that various modifications and changes can be made without departing from the scope thereof. The only scope of the application is limited by the appended claims

[0146] The above only describes the preferred embodiments of the present application, and does not limit the present application, any modification, equivalent replacement, improvement, etc. within the spirit and principle of the present application should be included in the protection scope of the present application.

Claims

1. An automatic parking method, characterized in that: The method comprises: When the target vehicle is in a parking phase, ultrasonic data is collected in real time by an ultrasonic sensor of the target vehicle; Obtaining a group of available parking spaces based on the ultrasonic data collected in real time; Adjusting the initial parking space pose of the parking space group according to the occupancy grid map constructed from the ultrasonic data to obtain an adjusted parking space pose of the parking space group, including: obtaining a current lane direction of the target vehicle according to the occupancy grid map, and adjusting the initial parking space direction of the parking space group using the current lane direction to obtain an adjusted parking space direction of the parking space group, wherein a rotation angle difference is obtained according to the current lane direction and the initial parking space direction; adjusting the initial parking space direction using the rotation angle difference to obtain the adjusted parking space direction, wherein the adjusted parking space direction is used to adjust the initial parking space pose to obtain the adjusted parking space pose; Obtaining a target parking space for the target vehicle to be parked from the parking space group; Based on the adjusted parking space posture, the target vehicle is controlled to park in the target parking space.

2. The method according to claim 1, wherein The step of adjusting the initial parking space pose of the parking space group based on the occupancy grid map constructed according to the ultrasonic data to obtain the adjusted parking space pose of the parking space group includes: Acquiring ultrasonic scattered points according to the ultrasonic data; Acquiring the initial parking space posture according to the ultrasonic scattered points; The initial parking space posture is adjusted using the occupancy grid map to obtain the adjusted parking space posture.

3. The method according to claim 2, wherein The adjusting the initial parking space posture by using the occupancy grid map to obtain the adjusted parking space posture includes: Obtaining a longitudinal adjustment parameter and a lateral adjustment parameter of the parking space group according to side obstacles in the side regions of interest of the parking space group and a rear obstacle in the rear region of interest, wherein the side obstacles and the rear obstacle are obtained based on the occupancy grid map; The initial parking space posture is adjusted according to the adjusted parking space direction, the longitudinal adjustment parameter, and the lateral adjustment parameter to obtain the adjusted parking space posture.

4. The method according to claim 3, wherein The acquiring of the longitudinal adjustment parameter and the lateral adjustment parameter of the parking space group according to the side obstacles in the side regions of interest of the parking space group and the rear obstacle in the rear region of interest includes: Acquire a left region of interest, a right region of interest, and the tail region of interest of the target vehicle from the occupancy grid map, wherein the two side regions of interest include the left region of interest and the right region of interest; Obtaining obstacles in the two side regions of interest as the two side obstacles, and obtaining obstacles in the tail region of interest as the tail obstacle; Acquiring the longitudinal adjustment parameter according to the obstacles on both sides and the rear obstacle; The lateral adjustment parameter is obtained according to the obstacles on both sides.

5. The method according to claim 4, wherein The acquiring the longitudinal adjustment parameter according to the obstacles on both sides and the rear obstacle includes: Obtain the maximum longitudinal value corresponding to the obstacles on both sides; The longitudinal adjustment parameter is obtained according to the maximum longitudinal value and a position of a nearest obstacle among the rear obstacles, wherein the nearest obstacle is an obstacle among the rear obstacles that is closest to the parking space group.

6. The method according to claim 5, wherein The obstacles on both sides include a left obstacle and a right obstacle, and obtaining the lateral adjustment parameter according to the obstacles on both sides includes: Obtaining a minimum lateral value of the obstacle in the lateral direction between the left obstacle and the right obstacle, and obtaining a maximum lateral value of the obstacle in the lateral direction between the left obstacle and the right obstacle; The horizontal adjustment parameter is obtained according to the minimum horizontal value and the maximum horizontal value.

7. The method according to any one of claims 1 to 6, wherein: In the process of controlling the target vehicle to park in the target parking space based on the adjustment of the parking space posture, the method further includes: The adjusted parking space posture is continuously adjusted according to the occupancy grid map constructed by the ultrasonic data to obtain the real-time adjusted parking space posture of the parking space group.

8. The method according to any one of claims 1 to 6, wherein: The real-time collection of ultrasonic data by the ultrasonic sensor of the target vehicle includes: Ultrasonic data is collected in real time by all ultrasonic sensors arranged on the body of the target vehicle.

9. An automatic parking device, characterized in that: The device comprises: an ultrasonic data acquisition unit, configured to collect ultrasonic data in real time through an ultrasonic sensor of the target vehicle when the target vehicle is in a parking phase; A parking space group acquisition unit, configured to acquire a parking space group based on the ultrasonic data collected in real time; a posture adjustment unit, configured to adjust the initial parking space posture of the parking space group according to the occupancy grid map constructed from the ultrasonic data to obtain an adjusted parking space posture of the parking space group, comprising: obtaining a current lane direction of the target vehicle according to the occupancy grid map, and adjusting the initial parking space direction of the parking space group using the current lane direction to obtain an adjusted parking space direction of the parking space group, wherein a rotation angle difference is obtained according to the current lane direction and the initial parking space direction; and adjusting the initial parking space direction using the rotation angle difference to obtain the adjusted parking space direction, wherein the adjusted parking space direction is used to adjust the initial parking space posture to obtain the adjusted parking space posture; a parking space selection unit, configured to obtain a target parking space for the target vehicle to be parked from the parking space group; A parking unit is configured to control the target vehicle to park in the target parking space based on the adjusted parking space posture.

10. An electronic device, characterized in that: The invention comprises a memory and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by one or more processors to execute the operation instructions corresponding to the method according to any one of claims 1 to 8 contained in the one or more programs.

11. A computer program product, characterized in that The computer program product includes computer instructions, which are stored in a computer-readable storage medium and are suitable for being read and executed by a processor, so as to enable a computer device having the processor to perform the method according to any one of claims 1 to 8.

Images