Virtual parking space construction method and related equipment

Abstract

The invention discloses a virtual parking space construction method and related equipment, relates to the field of automatic parking, and mainly aims to solve the problem that the construction of a virtual parking space in a special scene still depends on manpower. The method comprises the following steps: acquiring fused obstacle information based on a sensor of a target vehicle; a virtual parking space is constructed based on the fused obstacle information, and the virtual parking space comprises a vertical parking space and a horizontal parking space; and selecting an initial recommended parking space for the target vehicle from the virtual parking spaces. The method is used for the virtual parking space construction process.

Description

Technical Field

[0001] The present invention relates to the field of automatic parking, and in particular to a virtual parking space construction method and related equipment. Background Art

[0002] At present, smart cars account for an increasing share of the market. As one of the main functions of smart cars, the automatic parking function is also used by more and more drivers. In order to solve the problem of being unable to perceive parking spaces in open areas and other environments without actual parking spaces, some automatic parking systems will include a custom parking space function, which supports users to drag the virtual parking space frame themselves, so as to achieve custom parking. However, this method requires the driver to drag the operation himself, which still relies on manual labor. Summary of the invention

[0003] In view of the above problems, the present invention provides a virtual parking space construction method and related equipment, the main purpose of which is to solve the problem that the construction of virtual parking spaces in special scenarios still relies on manual work.

[0004] In order to solve at least one of the above technical problems, in a first aspect, the present invention provides a method for constructing a virtual parking space, the method comprising:

[0005] Obtain fused obstacle information based on the target vehicle’s sensors;

[0006] Constructing a virtual parking space based on the fused obstacle information, wherein the virtual parking space includes a vertical parking space and a horizontal parking space;

[0007] An initial recommended parking space is selected for the target vehicle from the virtual parking spaces.

[0008] Optionally, the above method further includes:

[0009] Obtaining the roadside information of the target vehicle within a preset range;

[0010] In the case that there is no curb within the preset range of the target vehicle fed back by the curb information, constructing a vertical parking space and a horizontal parking space;

[0011] When the curb information feeds back that there is a curb within the preset range of the target vehicle, a horizontal parking space is constructed.

[0012] Optionally, constructing a virtual parking space based on the fused obstacle information includes:

[0013] Constructing a global coordinate system based on the position of the target vehicle, wherein the origin of the global coordinate system is the center of the rear axle of the target vehicle, the horizontal axis is parallel to the extension direction of the rear axle of the target vehicle, and the vertical axis is perpendicular to the extension direction of the rear axle of the target vehicle;

[0014] Dividing the effective area of ​​the vertical parking space based on the width of the target vehicle and the global coordinate system;

[0015] Obtaining obstacle distribution information within the effective area of ​​the vertical parking space;

[0016] constructing the vertical parking space based on the effective area of ​​the vertical parking space and the obstacle distribution information within the effective area;

[0017] The dividing of the effective area of ​​the vertical parking space based on the width of the target vehicle and the global coordinate system includes:

[0018] Determine a first lateral maximum value based on the sum of the closest parking distance to the target vehicle and a default length of the vertical parking space;

[0019] determining a first lateral minimum value based on half the width of the target vehicle;

[0020] determining a first longitudinal maximum value and a first longitudinal minimum value based on the sensor performance range;

[0021] The effective area of ​​the vertical parking space is divided based on the first lateral maximum value, the first lateral minimum value, the first longitudinal maximum value and the first longitudinal minimum value.

[0022] Optionally, the above method further includes:

[0023] Divide the number of valid intervals based on the valid area of ​​the vertical parking space, wherein each valid interval corresponds to a counting variable;

[0024] In the case where there is no obstacle in the valid interval, setting the initial value of the counting variable of all the valid intervals;

[0025] Starting from the rear axle center of the target vehicle, traverse the valid interval in the upward and downward directions respectively to change the initial value of the counting variable to the target value;

[0026] When the target value of the counting variable satisfies the number of the valid intervals, the vertical parking space is created.

[0027] Optionally, when there is a curb within a preset range of the target vehicle fed back by the curb information, constructing a horizontal parking space includes:

[0028] Determine a target curb within the preset range that is closest to the target vehicle;

[0029] Constructing a local coordinate system based on the position of the target vehicle, wherein the origin of the local coordinate system is the center of the rear axle of the target vehicle, the horizontal axis is perpendicular to the extension direction of the target curb, and the vertical axis is parallel to the extension direction of the target curb;

[0030] Dividing the effective area of ​​the horizontal parking space based on the width of the target vehicle, the local coordinate system and basic information of the target curb;

[0031] Obtaining obstacle distribution information within the effective area of ​​the horizontal parking space;

[0032] constructing the horizontal parking space based on the effective area of ​​the horizontal parking space and the obstacle distribution information within the effective area;

[0033] The dividing of the effective area of ​​the horizontal parking space based on the width of the target vehicle, the local coordinate system and the basic information of the target curb includes:

[0034] Determining a second lateral maximum value based on the distance between the target vehicle and the target curb, wherein the second lateral maximum value is less than the distance between the target vehicle and the target curb;

[0035] determining a second lateral minimum value based on half the width of the target vehicle;

[0036] Determining a second longitudinal maximum value and a second longitudinal minimum value based on the sensor performance range

[0037] The effective area of ​​the horizontal parking space is divided based on the second lateral maximum value, the second lateral minimum value, the second longitudinal maximum value and the second longitudinal minimum value.

[0038] Optionally, the above method further includes:

[0039] In the case where there is a curb within the preset range, the four corner points of the horizontal parking space are constructed based on the curb;

[0040] In the case where there is no curb within the preset range, the four corner points of the horizontal parking space are constructed based on the effective area.

[0041] Divide the number of valid intervals based on the valid area of ​​the horizontal parking space, wherein each valid interval corresponds to a counting variable;

[0042] In the case where there is no obstacle in the valid interval, setting the initial value of the counting variable of all the valid intervals;

[0043] Starting from the rear axle center of the target vehicle, traverse the valid interval in the upward and downward directions respectively to change the initial value of the counting variable to the target value;

[0044] When the target value of the counting variable satisfies the number of the valid intervals, the horizontal parking space is created.

[0045] Optionally, the above method further includes:

[0046] When the horizontal parking space is constructed, determining coordinate information of four corner points of the horizontal parking space, wherein the coordinate information of the four corner points is based on a local coordinate system;

[0047] The coordinate information of the four corner points is transformed based on a global coordinate system, wherein the origin of the global coordinate system is the center of the rear axle of the target vehicle, the horizontal axis is parallel to the extension direction of the rear axle of the target vehicle, and the vertical axis is perpendicular to the extension direction of the rear axle of the target vehicle.

[0048] In a second aspect, an embodiment of the present invention further provides a virtual parking space construction device, comprising:

[0049] An acquisition unit, used for acquiring fused obstacle information based on a sensor of a target vehicle;

[0050] A construction unit, configured to construct a virtual parking space based on the fused obstacle information, wherein the virtual parking space includes a vertical parking space and a horizontal parking space;

[0051] A selection unit is used to select an initial recommended parking space for the target vehicle from the virtual parking spaces.

[0052] In order to achieve the above object, according to a third aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium includes a stored program, wherein when the program is executed by a processor, the steps of the above virtual parking space construction method are implemented.

[0053] In order to achieve the above-mentioned purpose, according to the fourth aspect of the present invention, there is provided an electronic device, comprising at least one processor and at least one memory connected to the processor; wherein the above-mentioned processor is used to call the program instructions in the above-mentioned memory to execute the steps of the above-mentioned virtual parking space construction method.

[0054] By means of the above technical scheme, the virtual parking space construction method and related equipment provided by the present invention are used to solve the problem that the construction of virtual parking spaces in special scenarios still relies on manual work. The present invention obtains fused obstacle information based on the sensor of the target vehicle; constructs a virtual parking space based on the fused obstacle information, wherein the virtual parking space includes a vertical parking space and a horizontal parking space; and selects an initial recommended parking space for the target vehicle from the virtual parking space. In the above scheme, a method for constructing an initial recommended parking space for a custom parking space is provided. The fused obstacles detected by the sensor are used as input, and a custom parking space is constructed mainly according to the distribution of obstacles around the target vehicle. The custom parking space can be a vertical parking space or a horizontal parking space, but obstacles are not allowed in the parking space. If there are multiple parking spaces to choose from, a parking space closest to the target vehicle is finally selected as the initial recommended parking space according to the distance between the parking space and the target vehicle. The above method does not require the driver to drag and construct the custom parking space by himself, and can directly perform automatic parking according to the initial recommended parking space constructed by the present invention. If the driver is not satisfied, the dragging operation is performed again, which reduces the driver's operation and improves parking efficiency.

[0055] Correspondingly, the virtual parking space construction device, equipment and computer-readable storage medium provided by the embodiments of the present invention also have the above-mentioned technical effects.

[0056] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented according to the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0058] Figure 1 A schematic diagram showing a flow chart of a method for constructing a virtual parking space provided by an embodiment of the present invention;

[0059] Figure 2 A schematic diagram of a vertical parking space structure provided by an embodiment of the present invention is shown;

[0060] Figure 3 A schematic diagram of a horizontal parking space structure provided by an embodiment of the present invention is shown;

[0061] Figure 4 A schematic block diagram showing the composition of a virtual parking space construction device provided by an embodiment of the present invention is shown;

[0062] Figure 5 A schematic block diagram of the composition of an electronic device for constructing a virtual parking space provided by an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0063] The exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present invention and to enable the scope of the present invention to be fully communicated to those skilled in the art.

[0064] In order to solve the problem that the construction of virtual parking spaces in special scenarios still relies on manual work, an embodiment of the present invention provides a method for constructing virtual parking spaces, such as Figure 1 As shown, the method includes:

[0065] S101, acquiring fused obstacle information based on a sensor of a target vehicle;

[0066] Exemplarily, the above-mentioned sensor may be a sensing device such as an ultrasonic radar and a fisheye camera.

[0067] S102, constructing a virtual parking space based on the fused obstacle information, wherein the virtual parking space includes a vertical parking space and a horizontal parking space;

[0068] For example, parking spaces can be created on both sides of the target vehicle, with a maximum of two horizontal parking spaces and two vertical parking spaces on each side, that is, a maximum of eight parking spaces are generated, from which the optimal output is selected. This application takes the right side of the target vehicle as an example to create vertical and horizontal parking spaces that meet the conditions. The logic on the left side is the same, with only the position difference.

[0069] S103: Selecting an initial recommended parking space for the target vehicle from the virtual parking spaces.

[0070] By means of the above technical scheme, the virtual parking space construction method provided by the present invention solves the problem that the construction of virtual parking spaces in special scenarios still relies on manual work. The present invention obtains fused obstacle information based on the sensor of the target vehicle; constructs a virtual parking space based on the fused obstacle information, wherein the virtual parking space includes a vertical parking space and a horizontal parking space; and selects an initial recommended parking space for the target vehicle from the virtual parking space. In the above scheme, a method for constructing an initial recommended parking space for a custom parking space is provided. The fused obstacles detected by the sensor are used as input, and a custom parking space is constructed mainly according to the distribution of obstacles around the target vehicle. The custom parking space can be a vertical parking space or a horizontal parking space, but obstacles are not allowed in the parking space. If there are multiple parking spaces to choose from, a parking space closest to the target vehicle is finally selected as the initial recommended parking space according to the distance between the parking space and the target vehicle. The above method does not require the driver to drag and construct the custom parking space by himself, and can directly perform automatic parking according to the initial recommended parking space constructed by the present invention. If the driver is not satisfied, the dragging operation is performed again, thereby reducing the driver's operation and improving parking efficiency.

[0071] In one embodiment, the method further includes:

[0072] Obtaining the roadside information of the target vehicle within a preset range;

[0073] In the case that there is no curb within the preset range of the target vehicle fed back by the curb information, constructing a vertical parking space and a horizontal parking space;

[0074] When the curb information feeds back that there is a curb within the preset range of the target vehicle, a horizontal parking space is constructed.

[0075] For example, if there is a curb close to the target vehicle, the vertical parking space is insufficient, so consider constructing a horizontal parking space. The main logic of creating a horizontal parking space is the same as that of a vertical parking space. However, if the long side of the constructed parking space is at an angle to the curb, the final parking effect will affect the visual perception. Therefore, when there is a curb, a horizontal parking space needs to be constructed in the direction of the curb. When there is no curb, a horizontal parking space can also be constructed. The logic is the same as that of a vertical parking space, but the horizontal parking space has a longer effective interval in the longitudinal direction and a narrower area in the transverse direction due to the different length and width directions from the vertical parking space.

[0076] Based on the above solution, when constructing a horizontal parking space, it is determined based on whether there is a curb. If there is a curb, the car can be parked close to the curb. If there is no curb, the parking space is constructed according to the default horizontal parking space to optimize the user parking experience.

[0077] In one embodiment, the step of constructing a virtual parking space based on the fused obstacle information includes:

[0078] Constructing a global coordinate system based on the position of the target vehicle, wherein the origin of the global coordinate system is the center of the rear axle of the target vehicle, the horizontal axis is parallel to the extension direction of the rear axle of the target vehicle, and the vertical axis is perpendicular to the extension direction of the rear axle of the target vehicle;

[0079] Dividing the effective area of ​​the vertical parking space based on the width of the target vehicle and the global coordinate system;

[0080] Obtaining obstacle distribution information within the effective area of ​​the vertical parking space;

[0081] constructing the vertical parking space based on the effective area of ​​the vertical parking space and the obstacle distribution information within the effective area;

[0082] The dividing of the effective area of ​​the vertical parking space based on the width of the target vehicle and the global coordinate system includes:

[0083] Determine a first lateral maximum value based on the sum of the closest parking distance to the target vehicle and a default length of the vertical parking space;

[0084] determining a first lateral minimum value based on half the width of the target vehicle;

[0085] determining a first longitudinal maximum value and a first longitudinal minimum value based on the sensor performance range;

[0086] The effective area of ​​the vertical parking space is divided based on the first lateral maximum value, the first lateral minimum value, the first longitudinal maximum value and the first longitudinal minimum value.

[0087] like Figure 2 As shown, firstly, the effective area of ​​the vertical parking space is segmented: due to the limitation of the sensor, it is impossible to detect obstacles at a long distance, and the parking space construction range needs to be set. This application takes the center of the rear axle of the target vehicle as the origin, the x-axis, i.e., the horizontal axis, points to the right side of the driver (parallel to the extension direction of the rear axle of the target vehicle), and the y-axis, i.e., the vertical axis, points to the front of the vehicle (perpendicular to the extension direction of the rear axle of the target vehicle), as the global coordinate system. In the y direction, according to the sensor detection performance, the first longitudinal maximum value y_max and the first longitudinal minimum value y_min are set, and in the x direction, the first transverse maximum value x_max is set according to the nearest parking distance to the target vehicle plus the default length of the vertical parking space. In order to avoid the failure of parking due to obstacles at the entrance of the parking space, it is also necessary to judge whether there are obstacles in front of the entrance of the parking space, and it also needs to be included in the effective area. Therefore, half of the width of the target vehicle is taken as the first transverse minimum value x_min. According to the maximum and minimum values ​​of the above x and y directions, the effective area for creating a vertical parking space can be used. Then set the segmentation distance dis_area, and segment multiple effective intervals in the y direction.

[0088] In the above scheme, the first minimum horizontal value of x is half the width of the vehicle, 0.8m, and the first maximum horizontal value is 6.9m (including half the width of the vehicle, 0.8m, the closest parking distance, 0.6m, and the default vertical length of the parking space, 5.5m). The first minimum vertical value of y is -4m, and the first maximum vertical value is 6m. The segmentation distance dis_area is set to 0.2, and the y direction is divided into 50 valid intervals with an interval of 0.2m. The array obs_index

[50] is used to determine whether there is an obstacle in each interval. In the initial stage, all elements are initialized to 0, indicating that there is no obstacle in the interval.

[0089] Furthermore, the obstacle distribution is calculated, and according to the position of the fused obstacle output by sensors such as ultrasonic radar and camera, it is determined whether there is an obstacle in the above-mentioned valid interval. If there is an obstacle, the corresponding element of the array obs_index is set to 1.

[0090] This application sets a fused obstacle with two position points, representing the two endpoints of the obstacle, such as curbs, wheel chocks, etc. There are obstacles between the two endpoints, so all elements between the two endpoints of the obstacle need to be set to 1. For example, there is a fused obstacle at position point 1 (1.2, 3.7) in the global coordinate system, and position point 2 (1.5, 2.8) is within the above-mentioned valid area. According to the y-axis, the interval to which the two position points of this obstacle belong is calculated. The interval of point 1 is (3.7-(-4)) / 0.2, rounded up, and the interval of point 2 is (2.8-(-4)) / 0.2, that is, the intervals from 34 to 39 are set to 1, corresponding to the element values ​​1 of the array obs_index index 33 to 38. Loop through all fused obstacles to calculate the occupancy of all obstacles in the valid area.

[0091] Finally, create a vertical parking space: After calculating the distribution of obstacles in the valid area, this application creates a vertical parking space based on the distribution. According to the default vertical parking space width parking_w, the required number of intervals valid_count is calculated, that is, parking_w / dis_area is rounded up. If there are no obstacles distributed in the continuous interval of this required number of intervals, a vertical parking space can be created. The y values ​​of the four corner points of the parking space are determined according to the upper and lower boundaries of the y values ​​of this continuous obstacle-free interval. The x value of the far end is directly determined according to the maximum x value of the valid area, and the x value of the near end is determined according to the maximum x value of the valid area minus the default vertical parking space length.

[0092] In one embodiment, the method further includes:

[0093] Divide the number of valid intervals based on the valid area of ​​the vertical parking space, wherein each valid interval corresponds to a counting variable;

[0094] In the case where there is no obstacle in the valid interval, setting the initial value of the counting variable of all the valid intervals;

[0095] Starting from the rear axle center of the target vehicle, traverse the valid interval in the upward and downward directions respectively to change the initial value of the counting variable to the target value;

[0096] When the target value of the counting variable satisfies the number of the valid intervals, the vertical parking space is created.

[0097] Based on the above scheme, the default width of the vertical parking space is parking_w = ​​2.2m, and the default length is parking_l = 5.5m. Therefore, valid_count = 11. It takes 11 consecutive valid intervals to build a vertical parking space, and there are no obstacles in the intervals, that is, the values ​​of 11 consecutive elements of the array obs_index are 0. To find a parking space that meets the conditions, set the counting variable count, and the initial value is 0. Loop through each element of the array obs_index. If the element value is 0, count is increased by 1, and if it is 1, count is reset to zero. When count reaches 11, an interval sufficient to build a vertical parking space is found. In order to find a vertical parking space that meets the requirements and is close to the target vehicle as soon as possible, the search can be started from the rear axle of the target vehicle. Start_index = 20, that is, first start from the array obs_index

[20] to obs_index

[49] . During this period, count reaches 11. According to the index value at this time, the vertical parking space is output and the loop is exited. This can avoid looping the entire array and reduce the amount of calculation.

[0098] At this time, the area above the rear axle has been scanned, but the area below has not been scanned yet. If the scan is from obs_index

[20] to obs_index[0], there is a situation where a vertical parking space cannot be generated near obs_index

[20] . For example, if there is no obstacle between indexes 14 and 24, but there is an obstacle between obs_index

[25] and obs_index

[13] . If the above scanning method is used, a vertical parking space cannot be generated in the interval between 14 and 24. To solve this problem, the index for downward scanning should start from (start_index+valid_count-2), which is the interval occupied by the parking space above the rear axle minus one interval. That is, the scan below the rear axle needs to start from the array obs_index

[29] and scan towards obs_index[0]. At this time, all situations can be covered. Similarly, when scanning downward from obs_index

[29] , the vertical parking space can be output when the count reaches 11, and the scan is exited.

[0099] According to the above logic, a maximum of one parking space is constructed by scanning above the rear axle, and a maximum of one parking space is constructed by scanning below the rear axle, and a maximum of two vertical parking spaces are output. The y-coordinates of the four corner points of the specific vertical parking space are constructed according to the valid interval scanned above, and the x-coordinates are constructed according to the default parking space width of the vertical parking space. If there are no obstacles in the interval between indexes 20 and 30 of the above array, the coordinates of the four corner points are (1.4, 2.2), (6.9, 2.2), (1.4, 0), and (6.9, 0) respectively.

[0100] In one embodiment, when there is a curb within a preset range of the target vehicle fed back by the curb information, constructing a horizontal parking space includes:

[0101] Determine a target curb within the preset range that is closest to the target vehicle;

[0102] Constructing a local coordinate system based on the position of the target vehicle, wherein the origin of the local coordinate system is the center of the rear axle of the target vehicle, the horizontal axis is perpendicular to the extension direction of the target curb, and the vertical axis is parallel to the extension direction of the target curb;

[0103] Dividing the effective area of ​​the horizontal parking space based on the width of the target vehicle, the local coordinate system and basic information of the target curb;

[0104] Obtaining obstacle distribution information within the effective area of ​​the horizontal parking space;

[0105] constructing the horizontal parking space based on the effective area of ​​the horizontal parking space and the obstacle distribution information within the effective area;

[0106] The dividing of the effective area of ​​the horizontal parking space based on the width of the target vehicle, the local coordinate system and the basic information of the target curb includes:

[0107] Determining a second lateral maximum value based on the distance between the target vehicle and the target curb, wherein the second lateral maximum value is less than the distance between the target vehicle and the target curb;

[0108] determining a second lateral minimum value based on half the width of the target vehicle;

[0109] Determining a second longitudinal maximum value and a second longitudinal minimum value based on the sensor performance range

[0110] The effective area of ​​the horizontal parking space is divided based on the second lateral maximum value, the second lateral minimum value, the second longitudinal maximum value and the second longitudinal minimum value.

[0111] like Figure 3As shown, obstacle preprocessing is first performed: when the fused obstacle has a curb, all curb obstacles need to be extracted, and the target curb closest to the target vehicle is used as the reference. According to the coordinates of the two end points of the curb, the angle curb_angle between this curb and the y-axis of the global coordinate system is calculated as the basis for coordinate conversion, and the distance dis_curb_min from the target vehicle to this curb is calculated as the boundary range for subsequent effective area division. The global coordinate system centered on the rear axle of the local target vehicle is rotated according to the angle curb_angle to establish a local coordinate system. The origin of the local coordinate system is still at the center of the rear axle of the target vehicle, the y-axis is parallel to the curb (parallel to the extension direction of the target curb), and the x-axis is perpendicular to the curb and to the right (perpendicular to the extension direction of the target curb). All obstacle coordinates are converted to the local coordinate system. The horizontal parking space will be constructed in the local coordinate system later, and then reversely rotated to the global coordinate system.

[0112] Then, the effective area of ​​horizontal parking spaces is segmented: The effective area segmentation of horizontal parking spaces is similar to the effective area segmentation of vertical parking spaces. First, the construction range of the parking space is set in the local coordinate system. The second longitudinal maximum value y_max and the second longitudinal minimum value y_min are still set according to the sensor detection performance in the y direction, but the second transverse maximum value x_max in the x direction needs to be determined according to the distance dis_curb_min from the target vehicle to the curb. Considering the detection error of the curb, it is necessary to reduce a certain threshold value dis_thres inward based on the distance to the curb to avoid the parking space just coinciding with the curb or the curb error causing the parking space to be constructed on the curb. Therefore, the maximum value in the x direction is set to (dis_curb_min-dis_thres). If there is no curb, it is similar to the vertical parking space, and the maximum value is the closest parking distance to the target vehicle plus the default width of the horizontal parking space. Half of the width of the target vehicle is set to the second transverse minimum value x_min of x. Similarly, in the effective area, the segmentation distance dis_area is set, and multiple effective intervals are segmented in the y direction.

[0113] In the above scheme, the second maximum longitudinal value is 6m, and the second minimum longitudinal value is -4m. If there is a curb, the maximum value in the x direction is (dis_curb_min-dis_thres), where dis_curb_min is obtained based on the actual curb detected by the sensor and is reduced by 0.15m inward, that is, dis_thres = 0.15. If there is no curb, it is similar to the vertical parking space, and the second maximum lateral value is 3.6m (including half the vehicle width 0.8m plus the nearest parking distance 0.6m and the default width of the horizontal parking space 2.2m). The second minimum lateral value is half the vehicle width 0.8m. The segmentation distance is the same as the vertical parking space dis_area, which is 0.2m, and is divided into 50 intervals in the y direction, represented by the array obs_index

[50] .

[0114] Furthermore, the obstacle distribution is calculated: the logic is the same as that of calculating the obstacle distribution of the vertical parking space. According to the position of the fused obstacle output by the ultrasonic radar and the camera, it is determined whether there is an obstacle in the effective range of the horizontal parking space. If there is an obstacle, the corresponding element of the array obs_index is set to 1.

[0115] Finally, create a horizontal parking space: The logic is the same as the vertical parking space, but the horizontal parking space is the same direction as the y-axis. Therefore, the required number of intervals valid_count is calculated according to the default horizontal parking space length parking_l, that is, parking_l / dis_area rounded up. If there are no obstacles distributed in the continuous interval of this required number of intervals, a horizontal parking space can be created. Unlike the vertical parking space, at this time, since the parking space is constructed according to the angle of the curb, there may be an angle between it and the target vehicle, which may cause the target vehicle area to overlap with the created horizontal parking space, making the parking space unparkable. Therefore, this situation needs to be excluded. If the parking space overlaps with the target vehicle area, the count is reduced by 1, and the next interval is scanned, and the horizontal parking space is moved until the constructed horizontal parking space does not overlap with the target vehicle.

[0116] When constructing a parking space, the system scans the rear axle of the target vehicle twice, covering the effective area and finding the closest parking space to the target vehicle more efficiently, reducing the amount of calculation. Finally, the parking space closest to the target vehicle is recommended to optimize the parking experience.

[0117] The y values ​​of the four corner points of the parking space are determined according to the upper and lower boundaries of the y values ​​of this continuous obstacle-free interval. The x value of the far end is directly determined according to the maximum x value of the valid area, and the x value of the near end is determined by the maximum x value of the valid area minus the default horizontal parking space width.

[0118] In one embodiment, the method further includes:

[0119] In the case where there is a curb within the preset range, the four corner points of the horizontal parking space are constructed based on the curb;

[0120] In the case where there is no curb within the preset range, the four corner points of the horizontal parking space are constructed based on the effective area.

[0121] Divide the number of valid intervals based on the valid area of ​​the horizontal parking space, wherein each valid interval corresponds to a counting variable;

[0122] In the case where there is no obstacle in the valid interval, setting the initial value of the counting variable of all the valid intervals;

[0123] Starting from the rear axle center of the target vehicle, traverse the valid interval in the upward and downward directions respectively to change the initial value of the counting variable to the target value;

[0124] When the target value of the counting variable satisfies the number of the valid intervals, the horizontal parking space is created.

[0125] In this application, the default length of a horizontal parking space is parking_l = 5.5m, and the default width is parking_w = ​​2.2m, so valid_count = 28. It takes 28 consecutive valid intervals to build a horizontal parking space, and there are no obstacles in the interval, that is, the value of 28 consecutive elements in the array obs_index is 0. The scanning method is the same as the vertical parking space. Start scanning upward from the origin of the coordinate system, obs_index

[20] . When the counting variable count reaches 28, the horizontal parking space can be constructed and the loop can be exited. Then scan downward from (start_index+valid_count-2), obs_index

[46] , to obs_index[0]. When the counting variable count reaches 28, the horizontal parking space can be constructed and the loop can be exited. In this way, at most two horizontal parking spaces can be constructed.

[0126] The determination of the four corner points of the horizontal parking space is similar to that of the vertical parking space, and is constructed based on the scanned valid interval, but is divided into those with and without curbs. For example, if the elements in the array obs_index index 20 to 47 are all 0, that is, there is no obstacle. If there is a curb, the four corner points are constructed close to the curb, and the positions in the local coordinate system are (dis_curb_min-0.15-2.2, 5.6), (dis_curb_min-0.15, 5.6), (dis_curb_min-0.15, 0), (dis_curb_min-0.15-2.2, 0); if there is no curb, because the rotation angle is curb_angle = 0, the local coordinate system and the global coordinate system are equal, and the four corner points are constructed close to the right side of the valid area, and the coordinates are (1.4, 5.6), (3.6, 5.6), (3.6, 0), (1.4, 0).

[0127] In one embodiment, the method further includes:

[0128] When the horizontal parking space is constructed, determining coordinate information of four corner points of the horizontal parking space, wherein the coordinate information of the four corner points is based on a local coordinate system;

[0129] The coordinate information of the four corner points is transformed based on a global coordinate system, wherein the origin of the global coordinate system is the center of the rear axle of the target vehicle, the horizontal axis is parallel to the extension direction of the rear axle of the target vehicle, and the vertical axis is perpendicular to the extension direction of the rear axle of the target vehicle.

[0130] It should be noted that if there is a curb, the four corner points are established in a local coordinate system parallel to the curb and need to be converted to the global coordinate system for output. The four corner points need to be converted and rotated back in the opposite direction according to the above rotation angle curb_angle.

[0131] Finally, the above has established up to four parking spaces on the right side of the target vehicle, including up to two vertical parking spaces and two horizontal parking spaces. Similarly, up to four parking spaces can be constructed on the left side of the target vehicle according to the same logic. It is necessary to select the best parking space from these up to eight parking spaces as the initial parking space recommendation for the display screen and parking control to perform parking operations. By constructing the initial custom parking space, you can park directly according to the initial recommended parking space, solving the problem that the driver must drag the parking space to construct a custom parking space in the custom parking space mode, reducing the operation steps and improving efficiency.

[0132] According to normal driving habits, the priority of parking space selection is to choose the right side first, and then choose the left side if the right side cannot be constructed; if there are multiple parking spaces available on the right side, choose the parking space closest to the target vehicle.

[0133] Furthermore, as a response to the above Figure 1 In order to realize the method shown in the figure, the embodiment of the present invention also provides a virtual parking space construction device for Figure 1 The device embodiment corresponds to the aforementioned method embodiment. For ease of reading, this device embodiment will not repeat the details of the aforementioned method embodiment one by one, but it should be clear that the device in this embodiment can correspond to all the contents of the aforementioned method embodiment. Figure 4 As shown, the device includes: an acquisition unit 21, a construction unit 22 and a selection unit 23, wherein

[0134] An acquisition unit 21, used for acquiring fused obstacle information based on a sensor of a target vehicle;

[0135] A construction unit 22, configured to construct a virtual parking space based on the fused obstacle information, wherein the virtual parking space includes a vertical parking space and a horizontal parking space;

[0136] The selection unit 23 is used to select an initial recommended parking space for the target vehicle from the virtual parking spaces.

[0137] The processor includes a kernel, and the kernel calls the corresponding program unit from the memory. One or more kernels can be set, and a virtual parking space construction method is implemented by adjusting kernel parameters, which can solve the problem that the construction of virtual parking spaces in special scenarios still relies on manual work.

[0138] An embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium includes a stored program, and when the program is executed by a processor, the virtual parking space construction method is implemented.

[0139] An embodiment of the present invention provides a processor, which is used to run a program, wherein the virtual parking space construction method is executed when the program is run.

[0140] An embodiment of the present invention provides an electronic device, the electronic device comprising at least one processor and at least one memory connected to the processor; wherein the processor is used to call program instructions in the memory to execute the virtual parking space construction method as described above

[0141] An embodiment of the present invention provides an electronic device 30, such as Figure 5 As shown, the electronic device includes at least one processor 301, and at least one memory 302 and a bus 303 connected to the processor; wherein the processor 301 and the memory 302 communicate with each other via the bus 303; the processor 301 is used to call the program instructions in the memory to execute the above-mentioned virtual parking space construction method.

[0142] The intelligent electronic devices in this article can be PCs, PADs, mobile phones, etc.

[0143] The present application also provides a computer program product, which, when executed on a process management electronic device, is suitable for executing a program initialized with the steps of the above-mentioned virtual parking space construction method.

[0144] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0145] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0146] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0147] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0148] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0149] The present application also provides a computer program product, which includes computer software instructions. When the computer software instructions are executed on a processing device, the processing device is caused to execute the following Figure 1 This corresponds to the flow of control of the memory in the embodiment.

[0150] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on the computer, the process or function according to the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website site, a computer, a server or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (digital subscriber line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium can be any available medium that a computer can store or a data storage device such as a server or a data center that includes one or more available media integration. The available medium can be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid state drive (SSD)), etc.

[0151] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0152] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0153] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0154] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0155] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), disk or optical disk and other media that can store program codes.

[0156] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some of the technical features therein by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for constructing a virtual parking space, characterized in that: include: Obtain fused obstacle information based on the target vehicle’s sensors; Constructing a virtual parking space based on the fused obstacle information, wherein the virtual parking space includes a vertical parking space and a horizontal parking space; An initial recommended parking space is selected for the target vehicle from the virtual parking spaces.

2. The method according to claim 1, characterized in that Also includes: Obtaining the roadside information of the target vehicle within a preset range; In the case that there is no curb within the preset range of the target vehicle fed back by the curb information, constructing a vertical parking space and a horizontal parking space; When the curb information feeds back that there is a curb within the preset range of the target vehicle, a horizontal parking space is constructed.

3. The method according to claim 1, characterized in that The constructing a virtual parking space based on the fused obstacle information includes: Constructing a global coordinate system based on the position of the target vehicle, wherein the origin of the global coordinate system is the center of the rear axle of the target vehicle, the horizontal axis is parallel to the extension direction of the rear axle of the target vehicle, and the vertical axis is perpendicular to the extension direction of the rear axle of the target vehicle; Dividing the effective area of ​​the vertical parking space based on the width of the target vehicle and the global coordinate system; Obtaining obstacle distribution information within the effective area of ​​the vertical parking space; constructing the vertical parking space based on the effective area of ​​the vertical parking space and the obstacle distribution information within the effective area; The dividing of the effective area of ​​the vertical parking space based on the width of the target vehicle and the global coordinate system includes: Determine a first lateral maximum value based on the sum of the closest parking distance to the target vehicle and a default length of the vertical parking space; determining a first lateral minimum value based on half the width of the target vehicle; determining a first longitudinal maximum value and a first longitudinal minimum value based on the sensor performance range; The effective area of ​​the vertical parking space is divided based on the first lateral maximum value, the first lateral minimum value, the first longitudinal maximum value and the first longitudinal minimum value.

4. The method according to claim 3, characterized in that Also includes: Divide the number of valid intervals based on the valid area of ​​the vertical parking space, wherein each valid interval corresponds to a counting variable; In the case where there is no obstacle in the valid interval, setting the initial value of the counting variable of all the valid intervals; Starting from the rear axle center of the target vehicle, traverse the valid interval in the upward and downward directions respectively to change the initial value of the counting variable to the target value; When the target value of the counting variable satisfies the number of the valid intervals, the vertical parking space is created.

5. The method according to claim 4, characterized in that When there is a curb within a preset range of the target vehicle fed back by the curb information, constructing a horizontal parking space includes: Determine a target curb within the preset range that is closest to the target vehicle; Constructing a local coordinate system based on the position of the target vehicle, wherein the origin of the local coordinate system is the center of the rear axle of the target vehicle, the horizontal axis is perpendicular to the extension direction of the target curb, and the vertical axis is parallel to the extension direction of the target curb; Dividing the effective area of ​​the horizontal parking space based on the width of the target vehicle, the local coordinate system and basic information of the target curb; Obtaining obstacle distribution information within the effective area of ​​the horizontal parking space; constructing the horizontal parking space based on the effective area of ​​the horizontal parking space and the obstacle distribution information within the effective area; The dividing of the effective area of ​​the horizontal parking space based on the width of the target vehicle, the local coordinate system and the basic information of the target curb includes: Determining a second lateral maximum value based on the distance between the target vehicle and the target curb, wherein the second lateral maximum value is less than the distance between the target vehicle and the target curb; determining a second lateral minimum value based on half the width of the target vehicle; Determining a second longitudinal maximum value and a second longitudinal minimum value based on the sensor performance range The effective area of ​​the horizontal parking space is divided based on the second lateral maximum value, the second lateral minimum value, the second longitudinal maximum value and the second longitudinal minimum value.

6. The method according to claim 5, characterized in that Also includes: In the case where there is a curb within the preset range, the four corner points of the horizontal parking space are constructed based on the curb; In the case where there is no curb within the preset range, the four corner points of the horizontal parking space are constructed based on the effective area; Divide the number of valid intervals based on the valid area of ​​the horizontal parking space, wherein each valid interval corresponds to a counting variable; In the case where there is no obstacle in the valid interval, setting the initial value of the counting variable of all the valid intervals; Starting from the rear axle center of the target vehicle, traverse the valid interval in the upward and downward directions respectively to change the initial value of the counting variable to the target value; When the target value of the counting variable satisfies the number of the valid intervals, the horizontal parking space is created.

7. The method according to claim 6, characterized in that Also includes: When the horizontal parking space is constructed, determining coordinate information of four corner points of the horizontal parking space, wherein the coordinate information of the four corner points is based on a local coordinate system; The coordinate information of the four corner points is transformed based on a global coordinate system, wherein the origin of the global coordinate system is the center of the rear axle of the target vehicle, the horizontal axis is parallel to the extension direction of the rear axle of the target vehicle, and the vertical axis is perpendicular to the extension direction of the rear axle of the target vehicle.

8. A virtual parking space construction device, characterized in that: Also includes: An acquisition unit, used for acquiring fused obstacle information based on a sensor of a target vehicle; A construction unit, configured to construct a virtual parking space based on the fused obstacle information, wherein the virtual parking space includes a vertical parking space and a horizontal parking space; A selection unit is used to select an initial recommended parking space for the target vehicle from the virtual parking spaces.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein when the program is executed by a processor, the steps of the virtual parking space construction method according to any one of claims 1 to 7 are implemented.

10. An electronic device, characterized in that: The electronic device includes at least one processor and at least one memory connected to the processor; wherein the processor is used to call program instructions in the memory to execute the steps of the virtual parking space construction method according to any one of claims 1 to 7.

Images