CN118092459A

CN118092459A - Unmanned vehicle field bridge alignment control method and equipment suitable for multiple scenes

Info

Publication number: CN118092459A
Application number: CN202410521369.0A
Authority: CN
Inventors: 江铭; 侯学锋; 邵志文; 严文裕; 陈兴; 俞剑斌
Original assignee: Xiamen Zhongke Xingchen Technology Co ltd
Current assignee: Xiamen Zhongke Xingchen Technology Co ltd
Priority date: 2024-04-28
Filing date: 2024-04-28
Publication date: 2024-05-28
Anticipated expiration: 2044-04-28
Also published as: CN118092459B

Abstract

The embodiment of the application provides a field bridge alignment control method and equipment for an unmanned vehicle applicable to multiple scenes. The method is applied to a vehicle-mounted terminal of an unmanned vehicle, and the unmanned vehicle receives a target place task and autonomously travels to the vicinity of the target place; judging whether the field bridge crane equipment of the target site is in place or not; acquiring a positioning reference distance; judging whether the vehicle has a bearing container when the vehicle initially executes the task according to the target site task; if so, selecting a first laser radar to identify a box offset distance for a box feeding task, and obtaining a target stop distance by obtaining a difference between the box offset distance and a stop reference distance; if not, obtaining a target parking distance through the parking reference distance for the box collecting task; and according to the target parking distance, the vehicle automatically controls the electric door brake to stop. The application improves the adaptability of the unmanned vehicle to various scenes in the actual operation of parking the field bridge, and ensures the positioning accuracy of the parking of the field bridge in the multiple scenes.

Description

Unmanned vehicle field bridge alignment control method and equipment suitable for multiple scenes

Technical Field

The application relates to the technical field of unmanned vehicles, in particular to a method and equipment for controlling the alignment of a field bridge of an unmanned vehicle applicable to multiple scenes.

Background

In the prior art, a field bridge parking method of an unmanned vehicle often depends on field bridge intelligent equipment transformation, and accurate hoisting and unpacking actions are completed through control of the field bridge equipment.

However, the intelligent transformation of the bridge equipment requires great manpower and material resources cost for the early hardware transformation and the later software maintenance and upgrading, and often needs to develop corresponding functions for different scenes and situations, such as carrying out a box feeding task or carrying out a box receiving task, carrying out container tasks with different sizes, and the like, and meanwhile, if the field bridge crane does not reach a target place, the overall task execution speed is also reduced, so that the adaptability and the expansibility are poor.

Therefore, how to improve the field bridge parking detection precision and efficiency of the unmanned vehicle in the unmanned port becomes a technical problem to be solved urgently.

Disclosure of Invention

The embodiment of the application provides a field bridge alignment control method, a device, a medium and equipment for an unmanned vehicle, which are applicable to multiple scenes, so that the adaptability of the unmanned vehicle in actual parking control can be improved at least to a certain extent, and the parking control effect is ensured.

Other features and advantages of the application will be apparent from the following detailed description, or may be learned by the practice of the application.

The field bridge alignment control method of the unmanned vehicle suitable for multiple scenes is applied to a vehicle-mounted terminal on the unmanned vehicle, and the vehicle-mounted terminal is respectively in communication connection with a first laser radar and two second laser radars; the first laser radars are arranged at the top of the unmanned vehicle, and the two second laser radars are respectively arranged at two sides of the unmanned vehicle; the vehicle-mounted 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;

the method comprises the following steps:

S1: the unmanned vehicle receives a target place task and autonomously travels to the vicinity of the target place;

S2: judging whether the field bridge crane equipment of the target site is in place or not; if the position is in place, the first laser radar is selected to identify the relative position of the field bridge hoisting equipment and the unmanned vehicle to obtain a stop reference distance; if the target point is not in place, the second laser radar is selected to identify the relative position of the container on the ground of the target point and the unmanned vehicle, and the parking reference distance is obtained;

S3: judging whether the unmanned vehicle has a carrying container or not when the unmanned vehicle initially executes the task according to the target site task; if so, selecting a first laser radar to identify a box offset distance for a box feeding task, and obtaining a target stop distance by obtaining a difference between the box offset distance and a stop reference distance; if not, obtaining a target parking distance through the parking reference distance for the box collecting task;

S4: and according to the target parking distance, the unmanned vehicle autonomously controls the electric gate brake to stop, so that the unmanned vehicle stops at the target place.

As a further improvement, when the first laser radar is used for identifying the relative position of the field bridge hoisting equipment and the unmanned vehicle to obtain the parking reference distance, the method specifically comprises the following steps:

When the unmanned vehicle reaches a target place, the container or the container position of the container to be placed on the unmanned vehicle is aligned with the target container position of the container to be placed on the ground or the ground target container respectively; after the field bridge hoisting equipment is in place, the field bridge hoisting equipment can be directly used for boxing or unpacking at the target site through a lifting appliance of the field bridge; the target site is positioned in a target area which is close to the field bridge hoisting equipment in the process that the unmanned vehicle advances to the field bridge hoisting equipment, when the unmanned vehicle runs to the target area independently, the unmanned vehicle enters an alignment and parking process, the unmanned vehicle can identify a rear beam and a front beam of the field bridge hoisting equipment in real time in the alignment and parking process, and the unmanned vehicle moves linearly in the whole alignment and parking process; and carrying out plane segmentation by using a random sampling consistency method and an priori normal vector, determining point clouds of the bottom surfaces and/or the side surfaces of the front beam and the rear beam of the field bridge lifting device identified by the first laser radar, and calculating the distance between the front beam and the unmanned vehicle according to the coordinate information of the point clouds of the bottom surfaces and/or the side surfaces to obtain a parking reference distance.

Establishing a coordinate system, wherein the direction of the container of the unmanned vehicle parallel to the target place is set as an X axis, the ground direction perpendicular to the X axis and parallel to the X axis is set as a Y axis, and the ground direction perpendicular to the X axis and perpendicular to the X axis is set as a Z axis;

setting a first straight-through filter to filter point clouds, acquiring position information of field bridge hoisting equipment after the target site task is in place, and determining a range value of the first straight-through filter based on the position information and the distance between two adjacent field bridge hoisting equipment;

performing plane segmentation by using a random sampling consistency method and a priori normal vector, aiming at point cloud data acquired by a first laser radar, removing invalid points, and obtaining bottom surface point clouds of a front beam and a rear beam of the field bridge crane by using a range value of a first straight-pass filter;

Clustering bottom surface point clouds of the front beam and the rear beam through European clustering, dividing the front beam and the rear beam into two point clouds, respectively averaging X values of the two point clouds, wherein the average value is the front beam bottom surface point clouds farther from the unmanned vehicle;

projecting the front beam bottom point cloud set into two-dimensional data, obtaining an X value of the two-dimensional data, wherein the minimum value comes from a point, closest to the first laser device, at the bottom of the front beam, and traversing all points through the point to find a row of points, closest to the unmanned vehicle, at the bottom of the front beam;

And performing least square fitting algorithm on the set of the found row of points to obtain a straight line representing the nearest distance between the bottom of the front beam and the unmanned vehicle, obtaining a distance value B1 between the unmanned vehicle and the direct distance value B1, and calculating through the B1 to obtain the parking reference distance.

As a further improvement, further comprising the steps of: setting a second through filter to filter point clouds, determining the range of the second through filter according to the height difference of the upper top surface and the lower bottom surface of the front beam on the Z axis and the width difference of the upper bottom surface and the Y axis of the B1, obtaining the point clouds of the rear side surface of the front beam, and averaging all X values in the point clouds to obtain B2;

Setting a third straight-through filter to filter point clouds, knowing that the distance between the rear side surface of the front beam and the rear side surface of the rear beam or the front side surface of the rear beam is B3, determining the range of the third straight-through filter according to the height difference of the upper top surface and the lower bottom surface of the rear beam on the Z axis and the width difference of the upper top surface and the lower bottom surface of the rear beam on the Y axis, obtaining the point clouds of the rear side surface of the rear beam or the front side surface of the rear beam, and averaging all X values in the point clouds to obtain B4;

the parking reference distance B is (b1+b2+b3+b4)/3.

As a further improvement, when the relative position of the container and the unmanned vehicle for identifying the target site by using the second laser radar is selected to obtain the parking reference distance, the method specifically comprises the following steps:

Setting a fourth straight-pass filter to filter point clouds, and determining a range value of the fourth straight-pass filter according to the position range of a target container to be received of a target site and a next container of the target container in the running direction;

Aiming at the point cloud data acquired by the second laser radar, removing invalid points, and then obtaining a point cloud set to be processed through a range value of a fourth straight-pass filter;

Carrying out plane segmentation by using a random sampling consistency method and an priori normal vector, and determining a target container to be received and identified by the second laser radar and a point cloud set of a next container of the target container in the travelling direction;

Projecting the point cloud set into two-dimensional data, acquiring X values of the two-dimensional data, arranging the X values from small to large, and screening out the X value of the front side surface of a target container and the X value of the rear side surface of the next container in the proceeding direction of the target container according to the distance D1 between every two adjacent containers; the front side surface of the target container and the rear side surface of the next container are arranged on a storage yard in a right opposite way;

Respectively judging a point with the radius range of each point in the two surfaces being 0.03m as an effective point, respectively averaging X values of the effective points in the two surfaces to respectively obtain D2 and D3, and when a target container and the next container in the proceeding direction exist, stopping the position, wherein the reference distance D is (D2+D3-D1)/2; when only the target container exists, the parking reference distance D is D2; the parking reference distance D is D3-D1 when only the next container of the target container in the proceeding direction is present.

As a further improvement, the target parking distance is obtained by differentiating the box offset distance and the parking reference distance, which specifically comprises:

setting a fifth direct-pass filter to filter point clouds, and determining the range value of the fifth direct-pass filter according to different types of box feeding tasks in the target place tasks;

aiming at the point cloud data acquired by the second laser radar, removing invalid points, and then obtaining a point cloud set to be processed through a range value of a fifth straight-pass filter;

carrying out plane segmentation by using a random sampling consistency method and an priori normal vector, and determining a point cloud set of the front side surface, close to the headstock, of the vehicle-mounted container identified by the second laser radar;

and taking an average value of the X values of the point clouds to obtain the box offset distance S.

As a further improvement, the target stopping distance further compensates the test calibration to obtain the target fine stopping distance, which specifically comprises: the field bridge hoisting equipment of the target site is in place and is used for a box feeding task; under the test calibration condition, when the parking of the unmanned vehicle is finished, the test calibration value is the relative distance between the vehicle-mounted container and the field bridge hoisting equipment;

the field bridge hoisting equipment of the target site is in place and is used for a box collecting task; under the test calibration condition, when the parking of the unmanned vehicle is finished, the test calibration value is the relative distance between the unmanned vehicle and the field bridge hoisting equipment;

When the field bridge hoisting equipment of the target site is not in place and is a box feeding task; the target stopping distance is equal to the target fine stopping distance, and calibration is not required to be carried out through testing;

when the field bridge hoisting equipment of the target site is not in place and is a box receiving task; under the condition of test calibration, when the parking of the unmanned vehicle is finished, the test calibration value is the relative distance between the unmanned vehicle and the ground container.

The device is applied to a vehicle-mounted terminal on the unmanned vehicle, and the vehicle-mounted terminal is respectively in communication connection with the first laser radar and the two second laser radars; the first laser radars are arranged at the top of the unmanned vehicle, and the two second laser radars are respectively arranged at two sides of the unmanned vehicle; the vehicle-mounted 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;

The device comprises:

The first control module is used for controlling the unmanned vehicle to accept the task of the target place and automatically travel to the vicinity of the target place;

The first distance acquisition module is used for judging whether the field bridge crane equipment of the target site is in place or not; if the position is in place, the first laser radar is selected to identify the relative position of the field bridge hoisting equipment and the unmanned vehicle to obtain a stop reference distance; if the target point is not in place, the second laser radar is selected to identify the relative position of the container on the ground of the target point and the unmanned vehicle, and the parking reference distance is obtained;

The second distance acquisition module is used for judging whether the unmanned vehicle has a bearing container or not when the unmanned vehicle initially executes the task according to the target site task; if so, selecting a first laser radar to identify a box offset distance for a box feeding task, and obtaining a target stop distance by obtaining a difference between the box offset distance and a stop reference distance; if not, obtaining a target parking distance through the parking reference distance for the box collecting task;

and the second control module is used for controlling the electric door brake to stop automatically by the unmanned vehicle according to the target stop distance.

As a further improvement, a computer readable medium has stored thereon a computer program which, when executed by a processor, implements the unmanned vehicle field bridge alignment control method applicable to multiple scenarios as described in the above embodiments.

As a further improvement, an electronic device, comprising: one or more processors; and the storage device is used for storing one or more programs, and when the one or more programs are executed by the one or more processors, the one or more processors are enabled to realize the unmanned vehicle field bridge alignment control method applicable to multiple scenes.

According to an aspect of embodiments of the present application, there is provided a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the 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 unmanned vehicle field bridge alignment control method applicable to multiple scenes provided in the above-described embodiment.

According to the application, when the vehicle arrives near the target parking place, the target parking distance can be obtained by combining the point clouds acquired by the first laser radar and the second laser radar according to the box feeding or box receiving task and whether the field bridge lifting equipment of the target place is in place, so that the current vehicle is controlled to be parked according to the target parking distance. Therefore, the parking control of the current vehicle is realized under different scenes, even if the position of the field bridge crane equipment or the ground container of the target site is in error or change when the current vehicle is originally set, the unmanned vehicle can accurately park in real time under different scenes, the dependence of the vehicle on the high-precision requirement of GPS/GNSS positioning equipment and the intelligent reconstruction of the field bridge in the autonomous running process of the port field is improved, the field bridge operation flexibility of the unmanned vehicle is improved, the field parking time of the vehicle is reduced, the container loading and unloading operation efficiency of the field bridge of the unmanned vehicle and the adaptability in actual operation are improved, and the parking control precision is ensured.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application as claimed.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and together with the description, serve to explain the principles of the application. It is evident that the drawings in the following description are only some embodiments of the present application and that other drawings may be obtained from these drawings without inventive effort for a person of ordinary skill in the art. In the drawings:

FIG. 1 illustrates a flow diagram of an unmanned vehicle bridge alignment control method for multiple scenarios in accordance with one embodiment of the present application;

FIG. 2 illustrates a schematic diagram of a multi-scenario adaptive unmanned vehicle with a traction head moving between a front beam and a rear beam according to one embodiment of the present application;

FIG. 3 illustrates a block diagram of an alignment control device for multi-scenario adaptive unmanned vehicle parking according to one embodiment of the present application;

FIG. 4 shows a schematic diagram of a computer system suitable for use in implementing an embodiment of the application;

FIG. 5 illustrates a schematic diagram of an alignment process of an unmanned vehicle for multiple scenarios prior to approaching a field bridge crane apparatus in accordance with one embodiment of the present application;

fig. 6 shows a schematic diagram of a selection of a second lidar to identify the relative position of the container at the target site and the unmanned vehicle to obtain the parking reference distance when the bridge crane is out of position in one embodiment according to the application.

Detailed Description

Example embodiments will now be described more fully with reference to the accompanying drawings. However, the exemplary embodiments may be embodied in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of the example embodiments to those skilled in the art.

Furthermore, the described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the application. One skilled in the relevant art will recognize, however, that the application may be practiced without one or more of the specific details, or with other methods, components, devices, steps, etc. In other instances, well-known methods, devices, implementations, or operations are not shown or described in detail to avoid obscuring aspects of the application.

The block diagrams depicted in the figures are merely functional entities and do not necessarily correspond to physically separate entities. That is, the functional entities may be implemented in software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor devices and/or microcontroller devices.

The flow diagrams depicted in the figures are exemplary only, and do not necessarily include all of the elements and operations/steps, nor must they be performed in the order described. For example, some operations/steps may be decomposed, and some operations/steps may be combined or partially combined, so that the order of actual execution may be changed according to actual situations.

FIG. 1 shows a flow diagram of an unmanned vehicle bridge alignment control method applicable to multiple scenarios according to one embodiment of the application, which can be applied to a vehicle-mounted terminal on an unmanned vehicle, which is communicatively connected to a first lidar and two second lidars, respectively; the first laser radars are arranged at the top of the unmanned vehicle, and the two second laser radars are respectively arranged at two sides of the unmanned vehicle; and the vehicle-mounted 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.

As shown in fig. 2, the parking standard in the scheme is that the operation standard is met, when the field bridge equipment is in place, the unmanned vehicle can finish the parking process by depending on the position of a certain part on the field bridge lifting equipment, and the specific position of the parking position of the unmanned vehicle is determined according to the specification and the parameters of each field bridge, so that after the field bridge lifting equipment and the unmanned vehicle are parked, the loading and the box collecting are finished only by a lifting appliance (the field bridge lifting equipment is parked according to the position of a container to be placed on the ground or the position of the container to be received on the ground or the ground line drawing mark of a certain shellfish position before the field bridge lifting equipment is in place, and the position is also moved during the box lifting process, so that the unmanned vehicle can be used as a middle reference object by the relevant position of the certain part on the field bridge lifting equipment to realize the alignment with the target position); when the on-site bridge crane is not in place, the unmanned vehicle directly faces the ground container, and the position of the ground container can be known under the condition that the vehicle does not have a box, so that the alignment can be completed according to the calibration value; the storage yard is generally provided with a plurality of boxes, the unmanned vehicle can directly align the landing container when the landing bridge is not in place, but the landing container can be directly aligned to receive some interference, such as guardrail bars, even some areas can be directly provided with large-area guardrail iron nets and stone piers, the alignment field bridge hoisting equipment uses a high-height laser point cloud, and the laser point cloud has fewer interference items, so that the field bridge is generally used preferentially for aligning the unmanned vehicle under the condition that the field bridge is in place.

The origin of coordinates in the scheme is the center of a rear axle of a traction head of the unmanned vehicle; in order to consider the safety of production operation, the vehicle needs to be straightened in advance when the field bridge is aligned to run, so that the vehicle is in a straight line working condition in the alignment process or 20m before alignment, and a nonlinear irregular route is not generated; the prior experience refers to that real vehicle testing is carried out to obtain data, and corresponding operation can be carried out by finding out the commonality of the data.

With reference to fig. 1 and fig. 2, the following details of implementation of the technical solution of the embodiment of the present application are described in detail:

S1: the dispatching command center of the port can issue specific tasks to the unmanned vehicle, and the unmanned vehicle receives tasks of the target site and autonomously travels to the vicinity of the target site;

The destination position/box type (40 ruler or 20 ruler)/collecting box or sending box task/box position (front, middle and back) of the task is contained in the task, the destination position is marked by using the field bridge crane equipment or the container, and the destination position and the current unmanned vehicle position cannot be used for stopping to finish loading and unloading the container directly because of the error of the field bridge crane equipment or the container in moving, and the GPS positioning of the vehicle has a certain error, but can be used for judging the approximate position of the vehicle after the vehicle reaches the target place so as to assist in selecting laser point data;

s2: judging whether the field bridge crane equipment of the target site is in place or not according to the target site task; if the position is in place, the first laser radar is selected to identify the relative position of the field bridge hoisting equipment and the unmanned vehicle to obtain the parking reference distance, and the reason is that the characteristic points which are better identified by the field bridge hoisting equipment are mainly top beams, and the top beams cannot be effectively identified by adopting the second laser radar on the side surfaces, so the first laser radar on the top is used for identification; if the target point is not in place, the second laser radar is selected to identify the relative position of the container on the ground of the target point and the unmanned vehicle, and the parking reference distance is obtained;

In a yard of an unmanned harbor, the limited number of the yard bridge hoisting equipment can give priority to other unmanned vehicles to carry out hanging cabinet operation sometimes, so that the condition that the yard bridge hoisting equipment does not reach when the vehicles reach the vicinity of a destination range can occur, the scheme can still acquire a parking reference distance by utilizing the position of a ground container under the condition, and the throughput of a general unmanned wharf is large, so that the yard is generally densely arranged, and the condition that no container is beside the yard is less, therefore, the operation efficiency can be effectively improved, and the adaptability of the whole scheme under multiple scenes can be increased;

S4: and according to the target parking distance, the unmanned vehicle autonomously controls the electric gate brake to perform parking.

When the vehicle arrives near the target parking place, the target parking distance can be obtained by combining the point clouds obtained by the first laser radar and the second laser radar according to the box feeding or box receiving task and whether the field bridge lifting equipment of the target place is in place or not, so that the current vehicle is controlled to be parked according to the target parking distance. Therefore, the parking control of the current vehicle is realized under different scenes, even if the position of the field bridge crane equipment or the ground container of the target site is in error or change when the current vehicle is originally set, the unmanned vehicle can accurately park in real time under different scenes, the dependence of the vehicle on the high-precision requirement of GPS/GNSS positioning equipment and the intelligent reconstruction of the field bridge in the autonomous running process of the port field is improved, the field bridge operation flexibility of the unmanned vehicle is improved, the field parking time of the vehicle is reduced, the container loading and unloading operation efficiency of the field bridge of the unmanned vehicle and the adaptability in actual operation are improved, and the parking control precision is ensured.

Referring to fig. 2, when the first laser radar is used to identify the relative position of the bridge crane and the unmanned vehicle to obtain the parking reference distance, the method specifically includes:

When the unmanned vehicle reaches a target place, the container or the container position of the container to be placed on the unmanned vehicle is aligned with the target container position of the container to be placed on the ground or the ground target container respectively; after the field bridge hoisting equipment is in place, the field bridge hoisting equipment can be directly used for boxing or unpacking at the target site through a lifting appliance of the field bridge; the target site is positioned in a target area close to the field bridge hoisting equipment in the process that the unmanned vehicle moves to the field bridge hoisting equipment, when the unmanned vehicle runs to the target area autonomously, the unmanned vehicle enters a positioning and stopping process, the unmanned vehicle can recognize the point cloud information of the back beam and the front beam of the field bridge hoisting equipment in real time through a laser radar in the positioning and stopping process and output relative distances, and the unmanned vehicle moves linearly in the whole positioning and stopping process; and carrying out plane segmentation by using a random sampling consistency method and an priori normal vector, determining point clouds of the bottom surfaces and/or the side surfaces of the front beam and the rear beam of the field bridge lifting device identified by the first laser radar, and calculating the distance between the front beam and the unmanned vehicle according to the coordinate information of the point clouds of the bottom surfaces and/or the side surfaces to obtain a parking reference distance.

Through limiting the target site and the target area, the unmanned vehicle can be confirmed to always identify the point clouds of each surface of the front beam and the rear beam of the bridge crane equipment in real time and calculate and output relative distances in the process of positioning and stopping, the identifiable surfaces are more, the available data are more, and therefore more calculation modes can be adapted to different harbor conditions and tasks to collect the data for calculation, and the whole positioning method is more stable; meanwhile, the linear motion during alignment is ensured, so that the range value screening of the subsequent straight-through filter is more accurate and simple.

Further, referring to fig. 5, when the first laser radar is selected to identify the relative position of the bridge crane device and the unmanned vehicle to obtain the parking reference distance, the method specifically includes:

Setting a first straight-through filter to filter point clouds, acquiring position information of field bridge lifting equipment in place through a target place task, and determining range values of the first straight-through filter based on the position information and the distance between two adjacent field bridge lifting equipment, wherein under normal conditions, the closest distance between the two adjacent field bridge lifting equipment is the range from the rear side face of a rear beam of a previous field bridge to the front side face of a front beam of a next field bridge, and the distance is at least more than 10 meters to ensure that no safety accident occurs between the field bridges, so that the range values of the first straight-through filter are determined based on the range of 8 meters before and after the position of the field bridge lifting equipment in place, which is known in the target task information, and the point clouds of the target field bridge lifting equipment are only output by the first straight-through filter finally;

Performing plane segmentation by using a random sampling consistency method and a priori normal vector, removing invalid points (infinite point clouds) according to point cloud data acquired by a first laser radar, and then passing through a range value of a first straight-pass filter to obtain bottom point clouds of a front beam and a rear beam of a field bridge crane;

Clustering bottom surface point clouds of the front beam and the rear beam through European clustering, dividing the front beam and the rear beam into two point clouds, respectively averaging X values of the two point clouds, wherein the average value is the front beam bottom surface point clouds farther from the unmanned vehicle; because the bottom surface point cloud set output in the last step can not distinguish the data points of the front beam and the rear beam, european clustering (because the two plane point cloud distances of the front beam and the rear beam are far and the two point cloud sets are respectively concentrated) can be divided into two point cloud sets after clustering, and the bottom surface point cloud set of the front beam is determined according to the average value and used as a subsequent calculation basis.

Projecting the front beam bottom point cloud set into two-dimensional data, obtaining an X value of the two-dimensional data, wherein the minimum value comes from a point, closest to the first laser device, at the bottom of the front beam, and traversing all points through the point to find a row of points, closest to the unmanned vehicle, at the bottom of the front beam; (as can be seen from the data obtained from real vehicle testing, the length of different beams is the same, the traversing rule is that other X values which are different from the X values by plus or minus 4mm are found (the X values are based on laser precision and less possible interference items, the common error is smaller, normally within plus or minus 3mm, the range is expanded to within plus or minus 4mm when the X values are set), points outside the distance are points on other surfaces of the front beam, and the points do not need to be considered, the Y values need to be spaced a certain distance, the distance is related to the laser model, the distance can be obtained by experience, the distance between two adjacent Y values is about 40cm, and finally, a row of points closest to the vehicle are found through a plurality of corresponding X values and Y values;

And performing least square fitting algorithm on the set of the found row of points to obtain a straight line representing the nearest distance between the bottom of the front beam and the unmanned vehicle, obtaining a distance value B1 between the unmanned vehicle and the direct distance value B1, and calculating through the B1 to obtain the parking reference distance. The linear fitting least square fitting algorithm is an integration algorithm in the opencv library, and only the required fitting points are needed to be imported, so that the description is omitted. After the straight line is formed by the above method, the straight line can be understood to be a straight line parallel to the front beam, and the straight line is parallel to the unmanned vehicle because the unmanned vehicle is aligned in advance before alignment, so that the value is the shortest distance between the straight line and the center of the rear axle of the traction head of the unmanned vehicle in a top view; in the vehicle alignment process, if the following acquisition of B2 and B4 cannot be satisfied in order to simplify the operation process or field conditions, the alignment can be performed according to the B1 value as the stop reference distance in the whole course.

In order to further improve the alignment precision, the operation through B1 is further performed to obtain the reference distance of the stop position, which specifically comprises the following steps:

setting a second through filter to filter point clouds, determining the range of the second through filter according to the height difference of the upper top surface and the lower bottom surface of the front beam on the Z axis and the width difference of the upper bottom surface and the Y axis of the B1, obtaining the point clouds of the rear side surface of the front beam, and averaging all X values in the point clouds to obtain B2;

the parking reference distance B is (b1+b2+b3+b4)/3.

Wherein, B1 is calculated through the rear edge line of the bottom of the front beam, compared with other parts of the field bridge, the front beam is most stable relative to the rear beam because the front beam is interfered by the lifting tool when the rear beam is identified when the head of the vehicle passes through the position of the lifting tool under the condition that the alignment is nearly completed; meanwhile, after the vehicle continues to advance forward for alignment, the situation that the front beam is opened by the vehicle head possibly occurs, at the moment, the laser equipment cannot identify the rear side surface of the front beam, so that the bottom rear edge line of the front beam is the most stable, and the recognition can be carried out in the whole alignment process, therefore, in the detection process, the B1 obtained by the bottom rear edge line of the front beam is used as the basis, the following other detection distance items are introduced for ensuring the stability and adaptability of the whole detection, and in special cases, when the following B2 and B4 cannot be obtained, the alignment and the position stop can be carried out only according to the B1 value.

Because the unmanned vehicle is a process of receiving the point cloud data in real time and outputting the target parking distance in real time when entering the target area, the received point cloud data are different when the vehicle approaches the near-field bridge hoisting equipment and when the vehicle is positioned below the field bridge hoisting equipment; and the three distances of B2, B3 and B4 exist all the time in the alignment running process of the unmanned vehicle close to the field bridge hoisting equipment after the field bridge hoisting equipment is in place, so that the accuracy and stability of positioning can be further improved through the common calculation of the distances.

Before the vehicle approaches the near-field bridge crane, please refer to fig. 5, in this case, the laser beam herein uses the front-beam rear bottom, the front-beam rear side, and the rear-beam rear side to calculate B2 and B4 (where B4 is a positive value), and B3 is the distance from the front-beam rear side to the rear-beam rear side; the B value obtained by combining multiple faces is more stable, namely, the B value is better than the B1 is directly used as the B value for alignment, and the pre-alignment of the vehicle before the vehicle approaches the near-field bridge hoisting equipment can be finished only through the B1.

When the locomotive of the vehicle is located between the front beam and the rear beam, please refer to fig. 2, in which case, the front beam rear bottom, front beam rear side, rear beam front side are used in the laser recognition bridge herein to calculate B2 and B4 (since the origin of coordinates is the locomotive rear axle center, where B4 is a negative value), and B3 is the distance from the front beam rear side to the rear beam front side; the B value obtained by combining multiple faces is more stable, namely, the B value is better than the B1 is directly used as the B value for alignment, and the final parking alignment of the vehicle can be finished only through the B1.

In summary, if only one surface of one beam is taken, if the bridge is required to be additionally provided with an interference object such as a lamp or a camera and the like because of the operation, errors can be generated during point cloud detection, so that the surfaces are comprehensively considered to be selected for solving the alignment distance in the practical debugging process; and the field bridge is of a rigid structure, and the relative distances are not changed in the alignment process, so that the stability of alignment distance output is facilitated.

In the scheme, the optimal mode is that before a vehicle approaches near-field bridge hoisting equipment, B1 is adopted for pre-alignment, on one hand, the value of B1 is relatively stable, and the value can be collected under normal conditions; on the other hand, the distance between the vehicle and the field bridge is a certain distance, so that accurate positioning is not needed temporarily, and the preset positioning can be finished only through B1 to properly reduce the calculated amount after other distances are added; and when the traction head of the vehicle is positioned between the front beam and the rear beam, B is obtained through the operation of B1, B2, B3 and B4 so as to finish final accurate stop position alignment.

Referring to fig. 6, in an embodiment, when the bridge crane is not in place, selecting a relative position between a container for identifying a target location by using a second laser radar and an unmanned vehicle to obtain a parking reference distance specifically includes: establishing a coordinate system, wherein the direction of the container of the unmanned vehicle parallel to the target place is set as an X axis, the ground direction perpendicular to the X axis and parallel to the X axis is set as a Y axis, and the ground direction perpendicular to the X axis and perpendicular to the X axis is set as a Z axis;

Setting a fourth straight-through filter to filter point clouds, and determining a range value of the fourth straight-through filter according to the relevant parameters such as the distance, the approximate position and the length of the container and the like, wherein the distance between every two adjacent containers is 30-50 cm in the vehicle running direction under normal conditions according to the position ranges of a target container of a to-be-received container of a target site and a next container of the target container in the running direction;

The method is characterized in that the related parameters of two containers are adopted to calculate the parking reference distance as a redundant design, on one hand, the target ground container and the next container of the target container in the running direction are regularly discharged, the fixed distance is reserved between the two containers, and if the target position container is interfered (a long cylindrical guardrail bar can influence the detection of the target container when a field bridge exists), two point clouds can be collected to be used as error compensation; on the other hand, the containers can be stacked in the field area under the normal condition, but no container is stacked in the target position or only the container is stacked in the target position under the special condition, so that the container in front of the target position can be identified or the target container can be directly identified to finish the alignment process; if the position of the shellfish position of the target container and the situation that the former shellfish position does not exist in the floor container, waiting for the field bridge crane to be in place, and then aligning through the field bridge, the method has strong adaptability and can flexibly select according to different container conditions of the target position.

Based on the situation that the field bridge is in place and the field bridge is not in place, the scheme can obtain the target parking distance by solving the difference between the box body offset distance and the parking reference distance, and specifically comprises the following steps:

setting a fifth direct-pass filter to filter point clouds, and determining the range value of the fifth direct-pass filter according to different types of box feeding tasks in the target place tasks; the container type in port operation mainly comprises 20 chi casees and 40 chi casees, so there is the following condition probably on the unmanned vehicle: the 20 boxes are placed at the center or the front end or the rear end, the two 20 boxes are placed at the front and the rear, the 40 boxes are placed at the center, and the field bridge is a single crane, namely one container is lifted at a time, so the following conditions exist in the alignment process: the range value of the pass filter can be obtained according to prior experience of different types of tests in the front of 20 meters, the rear of 20 meters, the middle of 20 meters and the middle of 40 meters.

In addition, when the laser equipment on the unmanned vehicle possibly deviates during the use process or the device for aligning the container on the field bridge crane equipment deviates, after the unmanned vehicle recognizes the field bridge crane equipment or the ground container for stopping when the unmanned vehicle is unloaded according to the scheme, the final stopping position can be inaccurate due to the deviation of the output point cloud information, so that the error condition is observed and final alignment compensation is carried out manually after stopping under the test condition, and the error value, namely a test calibration value, is obtained; based on the error value, compensating the error value in advance when the subsequent alignment is stopped; the target accurate stopping distance is obtained after the test calibration value is further compensated through the target stopping distance; in general, when the current test calibration value cannot meet the operation requirement, the calibration value is redetermined, and the alignment compensation specifically includes the following steps:

The field bridge hoisting equipment of the target site is in place and is used for a box feeding task; under the test calibration condition, when the parking of the unmanned vehicle is finished, the test calibration value is the relative distance between the vehicle-mounted container and the field bridge hoisting equipment;

When the field bridge hoisting equipment of the target site is not in place and is a box feeding task; the target stopping distance is equal to the target fine stopping distance, calibration is not needed through testing, and in the case, the front plane of the ground container can be aligned by being flush with the front plane of the vehicle-mounted container, if errors generated by the displacement of the laser equipment of the unmanned vehicle occur on the vehicle-mounted container and the ground container at the same time, the relative distance is accurate, and compensation is not needed;

By the compensation mode, the adaptability of the overall parking method is stronger, errors generated when the laser equipment of the unmanned vehicle or the positioning equipment of the field bridge hoisting equipment is offset can be effectively solved, and the overall alignment accuracy is further improved.

In this embodiment, a vehicle parking controller may be provided on the terminal, the controller being configured to ensure that the vehicle controls the vehicle electric door brake to complete the parking self-execution process in accordance with the parking distance in the area. 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 so as to realize parking. And when the target parking distance is smaller than the ideal braking distance, the current vehicle can be braked in an emergency mode, and the vehicle is prevented from exceeding the target parking position.

It should be understood that the ideal braking distances corresponding to the vehicles are different under different speeds, and the ideal braking distances are related to the load and the driving speed of the vehicles, and can be calculated according to the actual vehicles by a person skilled in the art to obtain the ideal braking distances of the vehicles under different loads and different driving speeds, so that the ideal braking distances can be directly used for subsequent comparison in the actual use process.

In one example, the ideal braking distance S _BRK for the unmanned vehicle under different conditions may be determined according to the following equation:

Where V is the speed of travel, M is the container mass, P ₁、P₂、P₃ and P ₄ are predetermined coefficients, which can be set by those skilled in the art based on prior experience.

It should be noted that, the above-mentioned vehicle stop position controller not only can be used to the primary stop position of unmanned vehicle, if have the secondary stop position (namely the first stop position is the invalid stop position), this vehicle stop position controller also can realize above-mentioned function, prevents that the vehicle from surpassing the target stop position because of the brake is untimely, has guaranteed stop position control effect.

The following describes an embodiment of the apparatus of the present application, which may be used to implement the method for controlling the alignment of a field bridge of an unmanned vehicle applicable to multiple scenes in the above embodiment of the present application. For details not disclosed in the embodiments of the apparatus of the present application, please refer to the embodiments of the method for controlling the alignment of a field bridge of an unmanned vehicle applicable to multiple scenes.

Fig. 3 shows a block diagram of an apparatus according to an embodiment of the application.

Referring to fig. 3, an apparatus according to an embodiment of the present application is applied to a vehicle-mounted terminal on an unmanned vehicle, which is communicatively connected to a first lidar and two second lidars, respectively; the first laser radars are arranged at the top of the unmanned vehicle, and the two second laser radars are respectively arranged at two sides of the unmanned vehicle; the vehicle-mounted 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;

The device comprises:

Fig. 4 shows a schematic diagram of a computer system suitable for use in implementing an embodiment of the application.

Specifically, an electronic device includes: one or more processors; and the storage device is used for storing one or more programs, and when the one or more programs are executed by the one or more processors, the one or more processors are enabled to realize the unmanned vehicle field bridge alignment control method applicable to multiple scenes.

It should be noted that, the computer system of the electronic device shown in fig. 4 is only an example, and should not impose any limitation on the functions and the application scope of the embodiments of the present application.

As shown in fig. 4, the computer system includes a central processing unit (Central Processing Unit, CPU) 401 that can perform various appropriate actions and processes, such as performing the methods described in the above embodiments, according to a program stored in a Read-Only Memory (ROM) 402 or a program loaded from a storage portion 408 into a random access Memory (Random Access Memory, RAM) 403. In the RAM 403, various programs and data required for the system operation are also stored. The CPU 401, ROM 402, and RAM 403 are connected to each other by a bus 404. An Input/Output (I/O) interface 405 is also connected to bus 404.

The following components are connected to the I/O interface 405: an input section 406 including a keyboard, a mouse, and the like; an output portion 407 including a Cathode Ray Tube (CRT), a Liquid crystal display (Liquid CRYSTAL DISPLAY, LCD), and a speaker, etc.; a storage section 408 including a hard disk or the like; and a communication section 409 including a network interface card such as a LAN (Local Area Network ) card, a modem, or the like. The communication section 409 performs communication processing via a network such as the internet. The 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, or the like is installed on the drive 410 as needed, so that a computer program read therefrom is installed into the storage section 408 as needed.

In particular, according to embodiments of the present application, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, embodiments of the present application include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising a computer program for performing the method shown in the flowchart. In such an embodiment, the computer program may be downloaded and installed from a network via the communication portion 409 and/or installed from the removable medium 411. When executed by a Central Processing Unit (CPU) 401, performs the various functions defined in the system of the present application.

It should be noted that, the computer readable medium shown in the embodiments of the present application may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium can be, for example, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-Only Memory (ROM), an erasable programmable read-Only Memory (Erasable Programmable Read Only Memory, EPROM), a flash Memory, an optical fiber, a portable compact disc read-Only Memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present application, however, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, with a computer-readable computer program embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. A computer program embodied on a 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.

The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. Where each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The units involved in the embodiments of the present application may be implemented by software, or may be implemented by hardware, and the described units may also be provided in a processor. Wherein the names of the units do not constitute a limitation of the units themselves in some cases.

As another aspect, the present application also provides a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the 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 unmanned vehicle field bridge alignment control method applicable to multiple scenes provided in the above-described embodiment.

The computer-readable medium may be contained in the electronic device described in the above embodiment; or may exist alone without being incorporated into the electronic device. The computer-readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to implement the methods described in the above embodiments.

It should be noted that although in the above detailed description several modules or units of a device for action execution are mentioned, such a division is not mandatory. Indeed, the features and functions of two or more modules or units described above may be embodied in one module or unit in accordance with embodiments of the application. Conversely, the features and functions of one module or unit described above may be further divided into a plurality of modules or units to be embodied.

From the above description of embodiments, those skilled in the art will readily appreciate that the example embodiments described herein may be implemented in software, or may be implemented in software in combination with the necessary hardware. Thus, the technical solution according to the embodiments of the present application may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (may be a CD-ROM, a U-disk, a mobile hard disk, etc.) or on a network, and includes several instructions to cause a computing device (may be a personal computer, a server, a touch terminal, or a network device, etc.) to perform the method according to the embodiments of the present application.

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

It is to be understood that the application is not limited to the precise arrangements and instrumentalities shown in the drawings, which have been described above, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the application is limited only by the appended claims.

Claims

1. The unmanned vehicle field bridge alignment control method suitable for multiple scenes is characterized by being applied to a vehicle-mounted terminal on an unmanned vehicle, wherein the vehicle-mounted terminal is respectively in communication connection with a first laser radar and two second laser radars; the first laser radars are arranged at the top of the unmanned vehicle, and the two second laser radars are respectively arranged at two sides of the unmanned vehicle; the vehicle-mounted 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;

the method comprises the following steps:

2. The method according to claim 1, wherein selecting the first lidar to identify the relative position of the bridge crane device and the unmanned vehicle to obtain the parking reference distance comprises:

3. The method according to claim 2, wherein selecting the first lidar to identify the relative position of the bridge crane device and the unmanned vehicle to obtain the parking reference distance comprises:

4. A method according to claim 3, further comprising the step of:

the parking reference distance B is (b1+b2+b3+b4)/3.

5. The method according to claim 1, wherein selecting the container using the second lidar to identify the target location relative to the unmanned vehicle to obtain the parking reference distance comprises:

Respectively judging a point with the radius range of each point in the two surfaces being 0.03m as an effective point, respectively averaging X values of the effective points in the two surfaces to respectively obtain D2 and/or D3, and when a target container and a next container in the proceeding direction exist, stopping the position, wherein the reference distance D is (D2+D3-D1)/2; when only the target container exists, the parking reference distance D is D2; the parking reference distance D is D3-D1 when only the next container of the target container in the proceeding direction is present.

6. The method according to claim 1, wherein the target stopping distance is obtained by a difference between the box offset distance and the stopping reference distance, specifically comprising:

7. The method according to claim 1, wherein the target stopping distance further compensates the test calibration value to obtain the target fine stopping distance, specifically comprising:

8. The device is characterized by being applied to a vehicle-mounted terminal on the unmanned vehicle, and the vehicle-mounted terminal is respectively in communication connection with a first laser radar and two second laser radars; the first laser radars are arranged at the top of the unmanned vehicle, and the two second laser radars are respectively arranged at two sides of the unmanned vehicle; the vehicle-mounted 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;

The device comprises:

9. A computer readable medium having stored thereon a computer program, which when executed by a processor implements the method for controlling the alignment of a field bridge of an unmanned vehicle applicable to multiple scenes according to any of claims 1 to 7.

10. An electronic device, comprising:

one or more processors;

Storage means for storing one or more programs that, when executed by the one or more processors, cause the one or more processors to implement the multi-scenario adaptive unmanned vehicle field bridge alignment control method of any of claims 1 to 7.