A method and device for controlling the positioning of unmanned container trucks in ports under double-box tasks

Abstract

The present application provides a method and device for controlling the positioning of unmanned container trucks in ports under dual-box tasks. In this method, a first laser radar is selected to obtain a point cloud set of the front side, and the distance d from the front side of the previous vehicle-mounted container to the center of the rear axle of the vehicle and the angle α of the previous vehicle-mounted container relative to the tractor head are calculated through the point cloud set; the left turn or right turn is determined according to the angle α, and the second laser radar on the same side is selected to use, and the point cloud set of the side of the two vehicle-mounted containers within the specified angle threshold range is obtained through the second laser radar on this side; the real-time distance s between the two containers and the distance r from the center position of the two containers to the center of the rear axle of the vehicle are calculated; the distance L from the center of the sling to the center of the rear axle of the vehicle is calculated, and the parking reference distance is r-L. The present invention improves the parking accuracy and efficiency of unmanned vehicles when performing dual-box tasks in unmanned ports, making it easier for the dual-box sling to dismantle two containers at one time.

Description

Technical Field

[0001] The present application relates to the field of unmanned driving technology, and more specifically, to a method and device for controlling the alignment of an unmanned driving container truck in a port under a dual-box mission. Background Art

[0002] In unmanned ports, the parking method of unmanned vehicles on the yard crane often relies on the laser radar on the vehicle to identify the yard crane equipment. According to different scenarios and situations, such as performing container delivery tasks or container collection tasks, container tasks of different sizes, etc., corresponding parking tasks are performed, and then the parking of the vehicle is controlled to complete precise lifting and unloading actions.

[0003] In the prior art, there is often no efficient and accurate way to perform double-box tasks.

[0004] For example, in the unmanned vehicle yard bridge alignment control method and equipment applicable to multiple scenarios with application number CN202410521369.0, the movement of containers is identified by a laser radar installed on the top of the vehicle. However, when performing a double-box task, the moving distance of the front box can be obtained by scanning the top laser radar, and the top laser radar has a blind spot and cannot scan the moving distance of the rear box. The rear box in the distance can only be identified after the front box is lifted away. Not only is the recognition accuracy insufficient, but the efficiency of lifting the box is greatly reduced; and the alignment cannot be completed when the hoist is blocked when it is falling or when the weather is bad, such as rain, when the rain blocks the bridge equipment.

[0005] Another example is that in the prior art, a laser radar is often installed at the rear end of the trailer to identify the position of the rear container and to align with the top laser radar, so that the double-container spreader can adjust the spreader parameters to control the spreader to lift two containers at a time. However, the rear end of the trailer is more dangerous and prone to scratches and malfunctions. In addition, the wiring is too long and needs to extend from the tractor head to the rear end. It is also easy to be damaged in complex environments, resulting in inadequate transmission of position information.

[0006] Therefore, how to improve the parking accuracy and efficiency of unmanned vehicles when performing double-box tasks in unmanned ports to facilitate the double-box lift to dismantle two containers at one time has become a technical problem that needs to be solved urgently. Summary of the invention

[0007] The embodiments of the present application provide a method, device, medium and equipment for controlling the positioning of an unmanned container truck in a port under a double-box task, thereby improving the parking accuracy and efficiency of the unmanned vehicle when performing a double-box task in an unmanned port, making it easier for the double-box spreader to dismantle two containers at one time.

[0008] A method for controlling the positioning of an unmanned container truck in a port under a dual-box task is applied to an on-board terminal on an unmanned vehicle, wherein the on-board terminal is respectively connected to a first laser radar and two second laser radars for communication; the first laser radar is arranged on the top of the tractor head of the unmanned vehicle, and the two second laser radars are respectively arranged on both sides of the tractor head of the unmanned vehicle; the on-board terminal performs parking control on the unmanned vehicle according to the point cloud data sent by the first laser radar and the second laser radar;

[0009] The method comprises the following steps:

[0010] S1: The unmanned vehicle carries two containers and moves autonomously to the target location;

[0011] S2: Select to use the first laser radar to obtain a point cloud set of the front side of the previous vehicle container facing the tractor head, and calculate the distance d between the front side of the previous vehicle container and the center of the rear axle of the vehicle and the angle α of the previous vehicle container relative to the tractor head through the point cloud set;

[0012] S3: Determine whether the unmanned vehicle is turning left or right based on the real-time value of the angle α, and select the second laser radar on the same side according to the direction of the turn, and obtain the point cloud set of the side surface of the two vehicle-mounted containers within the specified angle threshold range through the second laser radar on the side; calculate the real-time distance s between the two containers based on the point cloud set of the side surface, and then calculate the distance r from the center position of the two containers to the center of the rear axle of the vehicle in combination with the standard length of the container and d;

[0013] S4: The unmanned vehicle stops after reaching the destination position through its own positioning system, selects to use the first laser radar to identify the point cloud set of the spreader, and calculates the distance L between the center of the spreader and the center of the rear axle of the vehicle, and the parking reference distance is rL;

[0014] S5: According to the parking reference distance, the unmanned vehicle autonomously controls the throttle brake to make adjustments so that the unmanned vehicle stops at the target location.

[0015] As a further improvement, the S2 step includes, specifically, including:

[0016] Establish a coordinate system, in which the direction parallel to the container at the target location of the unmanned vehicle is set as the X-axis, the direction perpendicular to the X-axis and parallel to the ground is set as the Y-axis, and the direction perpendicular to the X-axis and perpendicular to the ground is set as the Z-axis;

[0017] A first straight-pass filter is set to filter the point cloud set collected by the first laser radar, and a range value of the first straight-pass filter is determined by a coordinate range of the front side of the previous container on the unmanned vehicle and a coordinate range of the front side of the previous container swinging on the Y axis when the unmanned vehicle turns.

[0018] After eliminating invalid points, the front side point cloud set of the previous container is obtained through the range value of the first straight-pass filter, and the point cloud set is clustered through Euclidean clustering to obtain several laser point cloud clusters;

[0019] After removing the Z-axis information in the point cloud cluster, the X and Y values ​​of all point clouds are obtained, and the average values ​​of X and Y in each point cloud cluster are calculated to obtain several points in the one-to-one corresponding point cloud cluster;

[0020] The intercept value and slope are obtained by performing a least squares fitting algorithm on a number of points, where the intercept value represents d and arctan (slope value) represents the angle α.

[0021] As a further improvement, the S3 step includes, specifically, the following:

[0022] Establish a coordinate system, in which the direction parallel to the container at the target location of the unmanned vehicle is set as the X-axis, the direction perpendicular to the X-axis and parallel to the ground is set as the Y-axis, and the direction perpendicular to the X-axis and perpendicular to the ground is set as the Z-axis;

[0023] A second direct-pass filter is set to filter the point cloud set collected by the second laser radar, and the range value of the second direct-pass filter when turning left or right is determined by the coordinate range of the two containers on the unmanned vehicle and the coordinate range of the two containers swinging on the Y axis when the unmanned vehicle turns.

[0024] The plane is segmented by using the random sampling consistency method and the prior normal vector. For the point cloud data within the limited angle threshold range collected by the second laser radar, the invalid points are removed and the range value of the second pass filter is used to obtain the side point cloud set when turning left or right.

[0025] After removing the Y-axis and Z-axis information in the point cloud cluster, the X values ​​of all point clouds are obtained and arranged in order from close to the tractor head to far away from the tractor head. The X difference between two adjacent point clouds is calculated starting from the first point cloud. When the X difference is greater than the first threshold for the first time, the X difference is taken as the real-time distance s between the two containers.

[0026] As a further improvement, specifically, the limited angle threshold range is [-27°, -21°] or [21°, 27°], and when the unmanned vehicle turns left or right, one of the two ranges is selected, and when the vehicle is in another turning direction, another different range is selected.

[0027] As a further improvement, the S4 step includes, specifically, the following:

[0028] Establish a coordinate system, in which the direction parallel to the container at the target location of the unmanned vehicle is set as the X-axis, the direction perpendicular to the X-axis and parallel to the ground is set as the Y-axis, and the direction perpendicular to the X-axis and perpendicular to the ground is set as the Z-axis;

[0029] A third direct-pass filter is set to filter the point cloud set collected by the first laser radar, and a range value of the third direct-pass filter is determined by the minimum safe height of the spreader, the spreader height when not falling, and the coordinate range of the spreader on the X-axis and the Y-axis;

[0030] After removing invalid points, the point cloud set of the spreader is obtained by the range value of the third pass filter. The spreader is a double-claw spreader. All X values ​​of the point cloud set of the spreader are summed and divided by the number of point cloud sets to obtain the middle value of the X value of the spreader. The point cloud set of the spreader is divided into two parts, front and back, using the middle value;

[0031] Arrange the X values ​​of the first half from small to large and take the Nth largest X value, and take the average of all X values ​​within a certain range positive and negative of the point to get the distance c1; Arrange the X values ​​of the second half from small to large and take the Nth smallest X value, and take the average of all X values ​​within a certain range positive and negative of the point to get the distance c2;

[0032] At this time, the distance L between the center of the sling and the center of the rear axle of the vehicle is (c1+c2) / 2.

[0033] As a further improvement, specifically, it includes: establishing a coordinate system, wherein the direction of the unmanned vehicle parallel to the container at the target location is set as the X-axis, the direction perpendicular to the X-axis and parallel to the ground is set as the Y-axis, and the direction perpendicular to the X-axis and perpendicular to the ground is set as the Z-axis;

[0034] A third direct-pass filter is set to filter the point cloud set collected by the first laser radar, and a range value of the third direct-pass filter is determined by the minimum safe height of the spreader, the spreader height when not falling, and the coordinate range of the spreader on the X-axis and the Y-axis;

[0035] After removing invalid points, the point cloud set of the spreader is obtained by the range value of the third pass filter. The spreader is a double-claw spreader. All X values ​​of the point cloud set of the spreader are summed and divided by the number of point cloud sets to obtain the middle value of the X value of the spreader. The point cloud set of the spreader is divided into two parts, front and back, using the middle value;

[0036] The random sampling consistency method and the prior normal vector are used to segment the plane of the spreader point cloud of the front and rear parts, and the point cloud sets of the front and rear sides of the spreader parallel to the vehicle width direction are determined. The two point cloud sets are respectively fitted by the least squares fitting algorithm to obtain two intercept values ​​c3 and c4;

[0037] At this time, the distance between the center of the sling and the center of the rear axle of the vehicle is L = (c3+c4) / 2.

[0038] A device is applied to an on-board terminal of an unmanned vehicle, wherein the on-board terminal is respectively connected to a first laser radar and two second laser radars for communication; the first laser radar is arranged on the top of the unmanned vehicle, and the two second laser radars are respectively arranged on both sides of the unmanned vehicle; the on-board terminal performs parking control on the unmanned vehicle according to point cloud data sent by the first laser radar and the second laser radar;

[0039] The device comprises:

[0040] The first control module is used to control the vehicle to autonomously move to the target location when the unmanned vehicle is equipped with two on-board containers;

[0041] The first calculation module is used to select and use the first laser radar to obtain a point cloud set of the front side of the previous vehicle container facing the tractor head, and calculate the distance d of the front side of the previous vehicle container from the center of the rear axle of the vehicle and the angle α of the previous vehicle container relative to the tractor head through the point cloud set;

[0042] The second calculation module is used to determine whether the unmanned vehicle is turning left or right according to the real-time value of the angle α, and select to use the second laser radar on the same side according to the turning direction, and obtain the point cloud set of the side surface of the two vehicle-mounted containers within the specified angle threshold range through the second laser radar on the side; calculate the real-time distance s between the two containers according to the point cloud set of the side surface, and then calculate the distance r from the center position of the two containers to the center of the rear axle of the vehicle in combination with the standard length of the container and d;

[0043] The third calculation module is used to control the unmanned vehicle to stop after reaching the destination position through its own positioning system, select the first laser radar to identify the point cloud set of the spreader, and calculate the distance L between the center of the spreader and the center of the rear axle of the vehicle, and the parking reference distance is rL;

[0044] The second control module autonomously controls the electric brake of the unmanned vehicle to make adjustments according to the parking reference distance, so that the unmanned vehicle stops at the target location.

[0045] A computer-readable medium stores a computer program, which, when executed by a processor, implements the port unmanned container truck alignment control method under a dual-box task.

[0046] An electronic device, comprising:

[0047] one or more processors;

[0048] A storage device is used to store one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the port unmanned container truck alignment control method under the dual-box task.

[0049] Other features and advantages of the present application will become apparent from the following detailed description, or may be learned in part by the practice of the present application.

[0050] The overall position acquisition method adopts the first laser radar in conjunction with two second laser radars. On the one hand, the first laser radar is used to identify the real-time position of the previous container and the angle of the previous container relative to the tractor head, and based on the angle, it is determined whether to turn left or right, and then which side of the second laser radar is selected to collect the distance between the two containers, so as to quickly calculate the distance from the center position of the two containers to the center of the rear axle of the vehicle in combination with the real-time position of the previous container, and the parking reference distance of the vehicle is calculated by combining this distance with the distance from the center position of the hoist to the center of the rear axle, so that the two containers can be lifted together at one time after the hoist is lowered. Since the collection of the distance between the two containers can occur during the turning process during the entire driving process, the second laser radar can be effectively used to continuously identify the distance changes between the two containers, which not only ensures the final alignment accuracy and efficiency, but also avoids the problem of easy damage caused by placing the laser radar at the rear of the vehicle, and the problem of being easily blocked by obstructions and unable to be identified.

[0051] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] The drawings herein are incorporated into the specification and constitute a part of the specification, showing embodiments consistent with the present application, and together with the specification, are used to explain the principles of the present application. Obviously, the drawings described below are only some embodiments of the present application, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0053] Figure 1 A schematic structural diagram of a method for controlling the positioning of an unmanned container truck in a port under a dual-box task during a turn according to an embodiment of the present application is shown;

[0054] Figure 2 A schematic diagram of the structure of a method for controlling the positioning of an unmanned container truck in a port under a double-box task according to an embodiment of the present application when the spreader falls after being in place;

[0055] Figure 3A block diagram of a port unmanned container truck alignment control device under a double-box task according to an embodiment of the present application is shown;

[0056] Figure 4 A schematic diagram of the structure of a computer system suitable for implementing an electronic device of an embodiment of the present application is shown. DETAILED DESCRIPTION

[0057] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this application will be more comprehensive and complete and fully convey the concept of the example embodiments to those skilled in the art.

[0058] In addition, described feature, structure or characteristic can be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present application. However, those skilled in the art will appreciate that the technical scheme of the present application can be put into practice without one or more of the specific details, or other methods, components, devices, steps, etc. can be adopted. In other cases, known methods, devices, realizations or operations are not shown or described in detail to avoid blurring the various aspects of the application.

[0059] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities may be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0060] The flowcharts shown in the accompanying drawings are only exemplary and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps can be decomposed, and some operations / steps can be combined or partially combined, so the actual execution order may change according to actual conditions.

[0061] Please refer to Figure 1 and Figure 2 An embodiment of the present application is a method for controlling the positioning of an unmanned container truck in a port under a dual-box task. The method can be applied to an on-board terminal on an unmanned vehicle, and the on-board terminal is respectively communicated with a first laser radar and two second laser radars; the first laser radar is arranged on the top of the tractor head of the unmanned vehicle, and the two second laser radars are respectively arranged on both sides of the tractor head of the unmanned vehicle; the on-board terminal performs parking control on the unmanned vehicle according to the point cloud data sent by the first laser radar and the second laser radar.

[0062] The parking standard in this case is to meet the operating standard. When the yard crane equipment is in place, the unmanned vehicle can rely on the point cloud information of the front box and the rear box collected by the first and second laser radars during the driving process and the point cloud information of the spreader during the final alignment to complete the parking process. After parking, the yard crane lifting equipment and the unmanned vehicle can simultaneously grab and collect two container bodies only through the spreader, and then transfer them to the ship at the port.

[0063] The origin of the coordinates in this case is the center of the rear axle of the driverless vehicle (i.e. the third axle from the front to the rear of the vehicle; the prior experience in this article refers to the data obtained through actual vehicle testing, and corresponding operations can be performed by discovering the commonalities of the data.

[0064] The method comprises the following steps:

[0065] S1: The unmanned vehicle carries two containers and moves autonomously to the target location;

[0066] S2: Select to use the first laser radar to obtain a point cloud set of the front side of the previous vehicle container facing the tractor head, and calculate the distance d between the front side of the previous vehicle container and the center of the rear axle of the vehicle and the angle α of the previous vehicle container relative to the tractor head through the point cloud set;

[0067] S3: Determine whether the unmanned vehicle is turning left or right based on the real-time value of the angle α, and select the second laser radar on the same side according to the direction of the turn, and obtain the point cloud set of the side surface of the two vehicle-mounted containers within the specified angle threshold range through the second laser radar on this side; calculate the real-time distance s between the two containers based on the point cloud set of the side surface, and then calculate the distance r from the center position of the two containers to the center of the rear axle of the vehicle in combination with the standard length of the container and d; the container spacing value will be detected throughout the entire process of going to the destination. After entering the final straight-line alignment stage, since the vehicle does not turn again, the spacing value obtained at the last turn is directly used. After entering the straight line, the spacing value of the container will basically not move too much, so the accuracy of the spacing value can be effectively guaranteed;

[0068] S4: The unmanned vehicle stops after reaching the destination position through its own positioning system, selects to use the first laser radar to identify the point cloud set of the spreader, and calculates the distance L between the center of the spreader and the center of the rear axle of the vehicle, and the parking reference distance is rL;

[0069] S5: According to the parking reference distance, the unmanned vehicle autonomously controls the throttle brake to make adjustments so that the unmanned vehicle stops at the target location.

[0070] The overall position acquisition method adopts the first laser radar in conjunction with two second laser radars. On the one hand, the first laser radar is used to identify the real-time position of the previous container and the angle of the previous container relative to the tractor head, and based on the angle, it is determined whether to turn left or right, and then which side of the second laser radar is selected to collect the distance between the two containers, so as to quickly calculate the distance from the center position of the two containers to the center of the rear axle of the vehicle in combination with the real-time position of the previous container, and the parking reference distance of the vehicle is calculated by combining this distance with the distance from the center position of the hoist to the center of the rear axle, so that the two containers can be lifted together at one time after the hoist is lowered. Since the collection of the distance between the two containers can occur during the turning process during the entire driving process, the second laser radar can be effectively used to continuously identify the distance changes between the two containers, which not only ensures the final alignment accuracy and efficiency, but also avoids the problem of easy damage caused by placing the laser radar at the rear of the vehicle, and the problem of being easily blocked by obstructions and unable to be identified.

[0071] Please refer to Figure 2 Further, the step S2 specifically includes:

[0072] A coordinate system is established, in which the direction of the unmanned vehicle parallel to the container at the target location is set as the X-axis, the direction perpendicular to the X-axis and parallel to the ground is set as the Y-axis, and the direction perpendicular to the X-axis and perpendicular to the ground is set as the Z-axis; since the installation position of the first laser radar is known, the first laser radar outputs a coordinate system with the laser itself as the origin, so it can be converted to the vehicle body coordinate system according to the installation position. At the same time, other laser radars can also be converted to the same coordinate system for easy processing, so the coordinates of the first laser radar output with the rear axle center as the origin are X: 2.842, Y: 0.0, Z: 3.38.

[0073] The first straight-pass filter is set to filter the point cloud set collected by the first laser radar. The range value of the first straight-pass filter is determined by the coordinate range of the front side of the previous container on the unmanned vehicle and the coordinate range of the front side of the previous container swinging on the Y axis when the unmanned vehicle turns. Under normal circumstances, when two 20-foot containers are carried on the vehicle, the X value of the previous container is 0.8, and the X value of the next container is -5.8, so the coordinate range of the previous container is set to X (-2.0, 1.0) Y (-3.0, 3.0) Z (2.0, 3.5), and the coordinate range of the next container is set to X (-5.0, -7.0) Y (-3.0, 3.0) Z (2.0, 3.5). The selection of X value is mainly related to the front and rear position of the box. It is selected based on experience according to the normal placement of different box sizes. The box itself will slide forward and backward by about 50cm. The Y value is selected according to the actual angle of the trailer swing when turning. The normal swing will not exceed 45 degrees. If the selection range is too large, the laser point cloud of other objects around will affect the next settlement, so it is controlled within plus or minus 3m. The selection of Z value is related to the trailer height. It is selected according to the actual read height. If it is too low, the laser point cloud of the trailer bracket will be selected, and if it is too high, the position of the bridge equipment hanger will be selected. The trailer height is generally about 1.6 meters, the height of a single standard container is 2.39 meters, and the entire height is about 4 meters. However, in order to reduce the amount of calculation, the value of Z does not need to be complete.

[0074] After eliminating invalid points, the range value of the first straight-pass filter is used to obtain the point cloud set of the front side of the previous container, and the point cloud set is clustered by Euclidean clustering to obtain several laser point cloud clusters; when the point cloud set meets the laser point number condition of more than 150, Euclidean clustering is performed, and the clustering threshold is 0.06m~0.1m, that is, the points with a mutual distance less than the threshold are clustered into one class, and finally 16 laser point cloud clusters are obtained (the unmanned vehicle uses a 16-line laser radar, so 16 laser point cloud clusters can be obtained after clustering is completed).

[0075] After removing the Z-axis information in the point cloud cluster, the X and Y values ​​of all point clouds are obtained, and the average values ​​of X and Y in each point cloud cluster are calculated to obtain several points in the one-to-one corresponding point cloud cluster;

[0076] The intercept value and slope are obtained by performing a least squares fitting algorithm on a number of points, where the intercept value represents d and arctan (slope value) represents the angle α.

[0077] Since the front side of the container is a regular concave-convex surface, this means that if the point cloud set is directly used without fitting a straight line, it is possible to get the front of the concave-convex surface, the back of the concave-convex surface, or a relatively inclined surface, which will cause the solution to be inaccurate. Therefore, it is first clustered into 16 clusters, each cluster has a concave-convex surface, and the average can reduce a part of the error. Moreover, if the 16 laser point cloud clusters are not first obtained by clustering and then averaged for fitting, but the point cloud set of the front side is directly used for straight line fitting, due to the large number of points, it will greatly affect the calculation speed. Therefore, the method of clustering first and then fitting is adopted. It is found that the results are stable and meet the production operation needs according to actual applications, and the distance from the front side of the previous vehicle container to the center of the rear axle of the vehicle can be effectively identified.

[0078] Please refer to Figure 2 The S3 step includes, specifically,

[0079] A coordinate system is established, in which the direction of the unmanned vehicle parallel to the container at the target location is set as the X-axis, the direction perpendicular to the X-axis and parallel to the ground is set as the Y-axis, and the direction perpendicular to the X-axis and perpendicular to the ground is set as the Z-axis; the coordinates of the two second laser radars are: X value 2.553, Y value 1.4, Z value 1.7; X value 2.553, Y value -1.4, Z value 1.7;

[0080] A second direct filter is set to filter the point cloud set collected by the second laser radar, and the range value of the second direct filter when turning left or right is determined by the coordinate range of the two containers on the unmanned vehicle and the coordinate range of the two containers swinging on the Y axis when the unmanned vehicle turns. In this embodiment, the double-box task refers to carrying two 20-foot containers at the same time, and the standard length of each container is 6.1m. By converting the angle and length when turning, the range value of one of the second direct filters can be set as: X(-10.0~0.0), Y(0.0~8.0), Z(3.7~5.5), and the range value of the second direct filter in another case is: X(-10.0~0.0), Y(-8.0~0.0), Z(3.7~5.5); the reason why the selected point of Z here is higher than the selected point of the first laser radar is that the selected point here will extend to the position of the rear box, and there will be a certain jump during driving. The original height may detect the trailer itself, so the value of Z is higher.

[0081] When the number of point cloud sets exceeds 30 points, the plane segmentation is performed using the random sampling consistency method and the prior normal vector. For the point cloud data within the limited angle threshold range collected by the second laser radar, the invalid points are removed and the range value of the second pass filter is used to obtain the side point cloud set when turning left or right.

[0082] After removing the Y-axis and Z-axis information in the point cloud cluster, the X values ​​of all point clouds are obtained and arranged in order from close to the tractor head to far from the tractor head. The X difference between two adjacent point clouds is calculated starting from the first point cloud. When the X difference is greater than the first threshold for the first time, the X difference is taken as the real-time distance s between the two containers. Since the front box is closer to the laser, the collected point clouds are more and continuous, while the rear box is less and discontinuous. Therefore, in order to avoid the problem of the rear box point cloud being greater than the first threshold and not correctly identifying the box seam, the calculation is performed in a front-to-back order.

[0083] Since only the X and Y values ​​of the point cloud are needed, it can be compressed into two dimensions to reduce the calculation process and storage space; the gap between the two boxes is about 50~70cm, and there may be some noise or interference points. Therefore, according to the actual situation, the first threshold is set to a threshold range of 0.3m~0.4m. Preferably, the first threshold is 0.3m.

[0084] By adopting this value-taking method, the point cloud set can be accurately acquired for a fixed value range in a left or right turn, so as to realize the real-time acquisition of the real-time distance between the two containers and ensure that the parameters of the laser point cloud are sufficient.

[0085] Furthermore, the angle threshold is valid throughout the range of [-27°, -21°] or [21°, 27°] according to the actual vehicle debugging; when the driverless vehicle turns left or right, one of the two ranges is selected, and when the vehicle is in another turning direction, another different range is selected. Using such a range setting can avoid the situation that the number of point clouds on the side of the container is small and the gap between the two boxes cannot be fully identified due to the occlusion of the front side of the front box due to the small turning angle; on the other hand, it can also avoid the situation that the box gap cannot be fully identified due to the occlusion of the left and right sides of the previous container due to the large turning angle.

[0086] Please refer to Figure 1 and Figure 2 , the S4 step includes, specifically including:

[0087] Establish a coordinate system, in which the direction parallel to the container at the target location of the unmanned vehicle is set as the X-axis, the direction perpendicular to the X-axis and parallel to the ground is set as the Y-axis, and the direction perpendicular to the X-axis and perpendicular to the ground is set as the Z-axis;

[0088] The third pass filter is set to filter the point cloud set collected by the first laser radar. The range value of the third pass filter is determined by the minimum safe height of the spreader, the spreader height when it is not falling, and the coordinate range of the spreader on the X-axis and Y-axis. At this time, the default field bridge equipment is in place, so the X value is determined by the difference between the position of the destination sent and the current position of the vehicle. According to prior experience, Z is (5.0~14.0). On the one hand, to ensure safety, when the spreader is within 5m above the ground, the vehicle is not allowed to move, so the minimum Z is 5. When the spreader is not falling, the spreader height is generally around 12.0m. According to the spreader width, the range of Y is set to (-1.4~1.4).

[0089] When the spreader is at a relatively far position (such as a height of about 12m when not falling), the number of points scanned by the laser is too small to perform plane segmentation, and other parts of the spreader may be segmented. Therefore, only points can be taken to calculate the distance between the head and tail ends. After removing invalid points, the point cloud set of the spreader is obtained by the range value of the third pass filter. The spreader is a double-claw spreader. All X values ​​of the spreader's point cloud set are summed and divided by the number of point cloud sets to obtain the middle value of the spreader's X value (since the spreader point cloud set is evenly distributed, all X values ​​divided by the number are approximately the middle value). The middle value is used to divide the spreader's point cloud set into two parts, the front and the back.

[0090] Arrange the X values ​​of the first half from small to large and take the Nth largest X value, and take all X values ​​within a certain range of positive and negative (can be positive and negative 0.05m, to ensure that enough points are taken) of the point and then take the average value to obtain the distance c1; Arrange the X values ​​of the second half from small to large and take the Nth smallest X value, and take all point X values ​​within a certain range of positive and negative (can be positive and negative 0.05m, to ensure that enough points are taken) of the point and then take the average value to obtain the distance c2; N ranges from 3 to 10, and can also be larger or smaller according to the actual output of the laser; Preferably, N is 5. Due to the characteristics of the sensor, there may be ghost points (there is no such point in reality but the laser scans and outputs by mistake), and there may be few ghost points, perhaps only one or two, so according to the experience value, it is obtained from the 5th;

[0091] At this time, the distance L between the center of the sling and the center of the rear axle of the vehicle is (c1+c2) / 2.

[0092] Please refer to Figure 1 and Figure 2 In another embodiment, when the spreader is at a relatively close position and the spreader is scanned in real time and plane segmentation can be performed, in order to further improve the detection accuracy of the spreader, the following method is used:

[0093] Establish a coordinate system, in which the direction parallel to the container at the target location of the unmanned vehicle is set as the X-axis, the direction perpendicular to the X-axis and parallel to the ground is set as the Y-axis, and the direction perpendicular to the X-axis and perpendicular to the ground is set as the Z-axis;

[0094] A third direct-pass filter is set to filter the point cloud set collected by the first laser radar, and a range value of the third direct-pass filter is determined by the minimum safe height of the spreader, the spreader height when not falling, and the coordinate range of the spreader on the X-axis and the Y-axis;

[0095] After removing invalid points, the point cloud set of the spreader is obtained by the range value of the third pass filter. The spreader is a double-claw spreader. All X values ​​of the point cloud set of the spreader are summed and divided by the number of point cloud sets to obtain the middle value of the X value of the spreader. The point cloud set of the spreader is divided into two parts, front and back, using the middle value;

[0096] When the point cloud set is greater than 30 points, the random sampling consistency method and the prior normal vector are used to perform plane segmentation of the front and rear parts of the spreader point cloud to determine the point cloud sets of the front and rear sides of the spreader parallel to the vehicle width direction. The two point cloud sets are respectively fitted by the least squares fitting algorithm to obtain two intercept values ​​c3 and c4; at this time, the distance L from the center of the spreader to the center of the rear axle of the vehicle is (c3+c4) / 2.

[0097] In this embodiment, a vehicle parking controller may be provided on the terminal, and the controller is used to ensure that the vehicle controls the vehicle electric brake according to the parking distance within the area to complete the parking self-execution process. According to the determined target parking distance, when the target parking distance is greater than or equal to the ideal braking distance, the terminal can autonomously control the speed of the current vehicle to achieve parking. When the target parking distance is less than the ideal braking distance, the current vehicle can be emergency braked to prevent the vehicle from exceeding the target parking position.

[0098] It should be understood that the ideal braking distance of a vehicle is not the same when traveling at different speeds. The ideal braking distance is related to the vehicle's load and driving speed. Technical personnel in this field can measure and obtain the ideal braking distance of the vehicle under different loads and driving speeds based on the actual vehicle, so that they can directly call it for subsequent comparison during actual use.

[0099] In one example, the ideal braking distance S of the driverless vehicle under different conditions can be determined according to the following formula: BRK : Where V is the driving speed, M is the mass of the container, and P 1 , P 2 , P 3 and P 4 It is a predetermined coefficient, which can be set by those skilled in the art based on prior experience.

[0100] It should be noted that the above-mentioned vehicle parking controller can not only be used for the first parking of the unmanned vehicle, but also can realize the above-mentioned function if there is a second parking (that is, the first parking is an invalid parking), thereby preventing the vehicle from exceeding the target parking position due to untimely braking, thereby ensuring the parking control effect.

[0101] The following describes an embodiment of the device of the present application, which can be used to execute the method for controlling the unmanned container truck alignment in a port under a double-box task in the above-mentioned embodiment of the present application. For details not disclosed in the embodiment of the device of the present application, please refer to the embodiment of the method for controlling the unmanned container truck alignment in a port under a double-box task in the above-mentioned embodiment of the present application.

[0102] Figure 3 A block diagram of a device according to an embodiment of the present application is shown.

[0103] A device, characterized in that it is applied to an on-board terminal of an unmanned vehicle, the on-board terminal is respectively connected to a first laser radar and two second laser radars for communication; the first laser radar is arranged on the top of the unmanned vehicle, and the two second laser radars are respectively arranged on both sides of the unmanned vehicle; the on-board terminal performs parking control on the unmanned vehicle according to the point cloud data sent by the first laser radar and the second laser radar;

[0104] The device comprises:

[0105] The first control module is used to control the vehicle to autonomously move to the target location when the unmanned vehicle is equipped with two on-board containers;

[0106] The first calculation module is used to select and use the first laser radar to obtain a point cloud set of the front side of the previous vehicle container facing the tractor head, and calculate the distance d of the front side of the previous vehicle container from the center of the rear axle of the vehicle and the angle α of the previous vehicle container relative to the tractor head through the point cloud set;

[0107] The second calculation module is used to determine whether the unmanned vehicle is turning left or right according to the real-time value of the angle α, and select to use the second laser radar on the same side according to the turning direction, and obtain the point cloud set of the side surface of the two vehicle-mounted containers within the specified angle threshold range through the second laser radar on the side; calculate the real-time distance s between the two containers according to the point cloud set of the side surface, and then calculate the distance r from the center position of the two containers to the center of the rear axle of the vehicle in combination with the standard length of the container and d;

[0108] The third calculation module is used to control the unmanned vehicle to stop after reaching the destination position through its own positioning system, select the first laser radar to identify the point cloud set of the spreader, and calculate the distance L between the center of the spreader and the center of the rear axle of the vehicle, and the parking reference distance is rL;

[0109] The second control module autonomously controls the electric brake of the unmanned vehicle to make adjustments according to the parking reference distance, so that the unmanned vehicle stops at the target location.

[0110] Figure 4 A schematic diagram of the structure of a computer system suitable for implementing an electronic device of an embodiment of the present application is shown.

[0111] Specifically, an electronic device includes: one or more processors; a storage device for storing one or more programs, when the one or more programs are executed by the one or more processors, the one or more processors implement the above-mentioned port unmanned container truck alignment control method under the dual-box task.

[0112] It should be noted that Figure 4 The computer system of the electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0113] like Figure 4 As shown, the computer system includes a central processing unit (CPU) 401, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 402 or the program loaded from the storage part 408 to the random access memory (RAM) 403, such as executing the method described in the above embodiment. Various programs and data required for system operation are also stored in the RAM 403. The CPU 401, ROM 402 and RAM 403 are connected to each other through a bus 404. The input / output (I / O) interface 405 is also connected to the bus 404.

[0114] The following components are connected to the I / O interface 405: an input section 406 including a keyboard, a mouse, etc.; an output section 407 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 408 including a hard disk, etc.; and a communication section 409 including a network interface card such as a LAN (LocaL Area Network) card, a modem, etc. The communication section 409 performs communication processing via a network such as the Internet. A drive 410 is also connected to the I / O interface 405 as needed. A removable medium 411, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 410 as needed so that a computer program read therefrom is installed into the storage section 408 as needed.

[0115] In particular, according to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 409, and / or installed from the removable medium 411. When the computer program is executed by the central processing unit (CPU) 401, various functions defined in the system of the present application are executed. It should be noted that the computer-readable medium shown in the embodiment of the present application can be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to, electrical connections with one or more conductors, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM), flash memory, optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device, or device. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable computer program. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program used by or in combination with an instruction execution system, device, or device. The computer program contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, etc., or any suitable combination of the foregoing.

[0116] The flowchart and block diagram in the accompanying drawings illustrate the possible architecture, functions and operations of the system, method and computer program product according to various embodiments of the present application. Wherein, each box in the flowchart or block diagram can represent a module, a program segment, or a part of the code, and the above-mentioned module, program segment, or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0117] The units involved in the embodiments described in this application may be implemented by software or hardware, and the units described may also be set in a processor. The names of these units do not, in some cases, constitute limitations on the units themselves.

[0118] As another aspect, the present application further provides a computer program product or a computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the port unmanned container truck alignment control method under the dual-box task provided in the above embodiment.

[0119] The computer readable medium may be included in the electronic device described in the above embodiment; or it may exist independently without being assembled into the electronic device. The above computer readable medium carries one or more programs, and when the above one or more programs are executed by an electronic device, the electronic device implements the method described in the above embodiment.

[0120] It should be noted that, although several modules or units of the equipment for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present application, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into being embodied by multiple modules or units.

[0121] Through the description of the above implementation methods, it is easy for those skilled in the art to understand that the example implementation methods described here can be implemented by software, or by combining software with necessary hardware. Therefore, the technical solution according to the implementation method of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a touch terminal, or a network device, etc.) to execute the method according to the implementation method of the present application.

[0122] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the embodiments disclosed herein. The present application is intended to cover any variations, uses or adaptations of the present application, which follow the general principles of the present application and include common knowledge or customary technical means in the art that are not disclosed in the present application.

[0123] It should be understood that the present application is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A method for controlling the positioning of unmanned container trucks in a port under a double-box task, characterized in that: An on-board terminal applied to an unmanned vehicle, the on-board terminal being respectively connected to a first laser radar and two second laser radars for communication; the first laser radar being arranged on the top of the tractor head of the unmanned vehicle, and the two second laser radars being arranged on both sides of the tractor head of the unmanned vehicle; the on-board terminal performing parking control on the unmanned vehicle according to the point cloud data sent by the first laser radar and the second laser radar; The method comprises the following steps: S1: The unmanned vehicle carries two containers and moves autonomously to the target location; S2: Select to use the first laser radar to obtain the point cloud set of the front side of the previous vehicle container facing the tractor head, and calculate the distance d between the front side of the previous vehicle container and the center of the rear axle of the vehicle and the angle α of the previous vehicle container relative to the tractor head through the point cloud set. The center of the rear axle of the vehicle is the center of the third axle from the front to the rear of the vehicle; S3: Determine whether the unmanned vehicle is turning left or right based on the real-time value of the angle α, and select the second laser radar on the same side according to the direction of the turn, and obtain the point cloud set of the side surface of the two vehicle-mounted containers within the specified angle threshold range through the second laser radar on the side; calculate the real-time distance s between the two containers based on the point cloud set of the side surface, and then calculate the distance r from the center position of the two containers to the center of the rear axle of the vehicle in combination with the standard length of the container and d; S4: The unmanned vehicle stops after reaching the destination position through its own positioning system, selects to use the first laser radar to identify the point cloud set of the spreader, and calculates the distance L between the center of the spreader and the center of the rear axle of the vehicle, and the parking reference distance is rL; S5: According to the parking reference distance, the unmanned vehicle autonomously controls the electric brake to make adjustments so that the unmanned vehicle stops at the target location; The S2 step includes, specifically, the following: Establish a coordinate system, in which the direction parallel to the container at the target location of the unmanned vehicle is set as the X-axis, the direction perpendicular to the X-axis and parallel to the ground is set as the Y-axis, and the direction perpendicular to the X-axis and perpendicular to the ground is set as the Z-axis; A first straight-pass filter is set to filter the point cloud set collected by the first laser radar, and a range value of the first straight-pass filter is determined by a coordinate range of the front side of the previous container on the unmanned vehicle and a coordinate range of the front side of the previous container swinging on the Y axis when the unmanned vehicle turns. After eliminating invalid points, the front side point cloud set of the previous container is obtained through the range value of the first straight-pass filter, and the point cloud set is clustered through Euclidean clustering to obtain several laser point cloud clusters; After removing the Z-axis information in the point cloud cluster, the X and Y values ​​of all point clouds are obtained, and the average values ​​of X and Y in each point cloud cluster are calculated to obtain several points in the one-to-one corresponding point cloud cluster; The intercept value and slope are obtained by performing a least squares fitting algorithm on a number of points, where the intercept value represents d and arctan (slope value) represents the angle α.

2. The method according to claim 1, characterized in that The S3 step includes, specifically, the following: Establish a coordinate system, in which the direction parallel to the container at the target location of the unmanned vehicle is set as the X-axis, the direction perpendicular to the X-axis and parallel to the ground is set as the Y-axis, and the direction perpendicular to the X-axis and perpendicular to the ground is set as the Z-axis; A second direct-pass filter is set to filter the point cloud set collected by the second laser radar, and the range value of the second direct-pass filter when turning left or right is determined by the coordinate range of the two containers on the unmanned vehicle and the coordinate range of the two containers swinging on the Y axis when the unmanned vehicle turns. The plane is segmented by using the random sampling consistency method and the prior normal vector. For the point cloud data within the limited angle threshold range collected by the second laser radar, the invalid points are removed and the range value of the second pass filter is used to obtain the side point cloud set when turning left or right. After removing the Y-axis and Z-axis information in the point cloud cluster, the X values ​​of all point clouds are obtained and arranged in order from close to the tractor head to far away from the tractor head. The X difference between two adjacent point clouds is calculated starting from the first point cloud. When the X difference is greater than the first threshold for the first time, the X difference is taken as the real-time distance s between the two containers.

3. The method according to claim 2, characterized in that Specifically include: The limited angle threshold range is [-27°, -21°] or [21°, 27°]. When the unmanned vehicle turns left or right, one of the two ranges is selected, and when the vehicle is in another turning direction, another different range is selected.

4. The method according to claim 1, characterized in that: The S4 step includes, specifically, the following: Establish a coordinate system, in which the direction parallel to the container at the target location of the unmanned vehicle is set as the X-axis, the direction perpendicular to the X-axis and parallel to the ground is set as the Y-axis, and the direction perpendicular to the X-axis and perpendicular to the ground is set as the Z-axis; A third direct-pass filter is set to filter the point cloud set collected by the first laser radar, and a range value of the third direct-pass filter is determined by the minimum safe height of the spreader, the spreader height when not falling, and the coordinate range of the spreader on the X-axis and the Y-axis; After removing invalid points, the point cloud set of the spreader is obtained by the range value of the third pass filter. The spreader is a double-claw spreader. All X values ​​of the point cloud set of the spreader are summed and divided by the number of point cloud sets to obtain the middle value of the X value of the spreader. The point cloud set of the spreader is divided into two parts, front and back, using the middle value; Arrange the X values ​​of the first half from small to large and take the Nth largest X value, and take the average of all X values ​​within a certain range positive and negative of the point to get the distance c1; Arrange the X values ​​of the second half from small to large and take the Nth smallest X value, and take the average of all X values ​​within a certain range positive and negative of the point to get the distance c2; At this time, the distance L between the center of the sling and the center of the rear axle of the vehicle is (c1+c2) / 2.

5. The method according to claim 1, characterized in that Specifically include: Establish a coordinate system, in which the direction parallel to the container at the target location of the unmanned vehicle is set as the X-axis, the direction perpendicular to the X-axis and parallel to the ground is set as the Y-axis, and the direction perpendicular to the X-axis and perpendicular to the ground is set as the Z-axis; A third direct-pass filter is set to filter the point cloud set collected by the first laser radar, and a range value of the third direct-pass filter is determined by the minimum safe height of the spreader, the spreader height when not falling, and the coordinate range of the spreader on the X-axis and the Y-axis; After removing invalid points, the point cloud set of the spreader is obtained by the range value of the third pass filter. The spreader is a double-claw spreader. All X values ​​of the point cloud set of the spreader are summed and divided by the number of point cloud sets to obtain the middle value of the X value of the spreader. The point cloud set of the spreader is divided into two parts, front and back, using the middle value; The random sampling consistency method and the prior normal vector are used to segment the plane of the spreader point cloud of the front and rear parts, and the point cloud sets of the front and rear sides of the spreader parallel to the vehicle width direction are determined. The two point cloud sets are respectively fitted by the least squares fitting algorithm to obtain two intercept values ​​c3 and c4; At this time, the distance between the center of the sling and the center of the rear axle of the vehicle is L=(c3+c4) / 2.

6. A port unmanned container truck alignment control device under double-box mission, characterized in that: An on-board terminal applied to an unmanned vehicle, the on-board terminal being respectively connected to a first laser radar and two second laser radars for communication; the first laser radar being arranged on the top of the unmanned vehicle, and the two second laser radars being arranged on both sides of the unmanned vehicle; the on-board terminal performing parking control on the unmanned vehicle according to the point cloud data sent by the first laser radar and the second laser radar; The device comprises: The first control module is used to control the vehicle to autonomously move to the target location when the unmanned vehicle is equipped with two on-board containers; The first calculation module is used to select and use the first laser radar to obtain a point cloud set of the front side of the previous vehicle container facing the tractor head, and calculate the distance d between the front side of the previous vehicle container and the center of the rear axle of the vehicle and the angle α of the previous vehicle container relative to the tractor head through the point cloud set. The center of the rear axle of the vehicle is the center of the third axle from the front to the rear of the vehicle; The second calculation module is used to determine whether the unmanned vehicle is turning left or right according to the real-time value of the angle α, and select to use the second laser radar on the same side according to the turning direction, and obtain the point cloud set of the side surface of the two vehicle-mounted containers within the specified angle threshold range through the second laser radar on the side; calculate the real-time distance s between the two containers according to the point cloud set of the side surface, and then calculate the distance r from the center position of the two containers to the center of the rear axle of the vehicle in combination with the standard length of the container and d; The third calculation module is used to control the unmanned vehicle to stop after reaching the destination position through its own positioning system, select the first laser radar to identify the point cloud set of the spreader, and calculate the distance L between the center of the spreader and the center of the rear axle of the vehicle, and the parking reference distance is rL; The second control module autonomously controls the electric brake of the unmanned vehicle to make adjustments according to the parking reference distance, so that the unmanned vehicle stops at the target location.

7. A computer readable medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, the method for controlling the positioning of an unmanned container truck in a port under a dual-box task according to any one of claims 1 to 5 is implemented.

8. An electronic device, characterized in that: include: one or more processors; A storage device for storing one or more programs, which, when executed by the one or more processors, enables the one or more processors to implement the port unmanned container truck alignment control method under a dual-box task as described in any one of claims 1 to 5.

Images