A precise secondary positioning method for unmanned truck in port tire crane or bridge crane

Abstract

The present application relates to a kind of port tyre crane or bridge crane unmanned truck accurate secondary positioning method, the tyre crane or bridge crane is scanned by laser radar installed on the unmanned truck, obtains point cloud data, is then processed by RANSAC algorithm to the point cloud data by bilateral filtering algorithm to point cloud data is carried out noise reduction processing, obtain linear equation about tyre crane or bridge crane, to further obtain accurate position information, the unmanned truck is dispatched.The present application is not only low in cost, and will not be affected by weather, further improve the work efficiency of unmanned truck.

Description

Technical Field

[0001] This invention relates to the field of container tire cranes or bridge cranes, and in particular to a method for precise secondary positioning of unmanned trucks under port tire cranes or bridge cranes. Background Technology

[0002] With the booming development of world trade and the unstoppable trend of globalization, maritime trade, as a crucial component of global trade, is a vital means for countries to participate in international trade. Port terminals serve as the connecting point between maritime and land transportation, and their importance in trade transportation is self-evident. Therefore, improving the efficiency of container transshipment, reducing labor costs and operational risks, and thereby enhancing port competitiveness, has always been a goal pursued by ports worldwide.

[0003] To improve port operational efficiency, reduce labor costs, and mitigate operational risks, increasing the automation and even intelligentization of port operations is an inevitable path for port development worldwide. In the process of port terminal automation, most automated terminals adopt a "bridge crane + rubber-tired gantry crane + IGV" operating model, with newer equipment typically only being used in newly built ports. However, in traditional port terminals, a large number of rubber-tired gantry cranes still operate in port yards, many of which still have decades of lifespan remaining. Coupled with site construction costs, ports will not replace all rubber-tired gantry cranes with other related equipment. Therefore, in the process of port automation, the automation of rubber-tired gantry cranes can significantly improve work efficiency.

[0004] The continuous development of computer technology, testing equipment, intelligent identification, and automatic motion control technology has laid the technological foundation for the automation of rubber-tired cranes. In particular, the development of identification technology has propelled the automation of rubber-tired cranes onto a fast track. For example, camera-based container positioning technology uses image processing to locate and track containers; there are also methods that use laser scanning to identify and locate containers.

[0005] In the existing technology 1, a visual image CPS system is used to install high-definition cameras on rubber-tired cranes or bridge cranes. Deep learning and other algorithms are used to identify, extract features and locate containers, and obtain the relative position of the container with respect to the gripper of the rubber-tired crane or bridge crane. The relative position is then sent to the unmanned truck through a cloud control platform, and the unmanned truck is controlled to move to the target position for precise alignment. The existing technology requires static scanning of the container outline, which is inefficient and affected by adverse weather conditions such as rain and fog. It is necessary to install equipment on each rubber-tired crane and bridge crane and to carry out intelligent transformation of the rubber-tired cranes and bridge cranes.

[0006] In the second existing technology, a laser point cloud CPS system is used, which involves installing high-precision 3D laser scanners on rubber-tired gantry cranes and bridge cranes. Deep learning and other algorithms are used to identify, extract features, and locate the container, obtaining its relative position to the grippers of the rubber-tired gantry cranes and bridge cranes. This relative position is then sent to an unmanned truck via a cloud control platform, controlling the truck to move to the target position for precise alignment. However, the existing 3D laser scanners are expensive, require static scanning of the container outline, and are inefficient. Furthermore, the technology requires installing equipment on each rubber-tired gantry crane and bridge crane, necessitating intelligent upgrades to the cranes. Summary of the Invention

[0007] In view of the shortcomings of the prior art, the present invention provides a method for precise secondary positioning of unmanned container trucks under port rubber-tired gantry cranes or bridge cranes, which is not only low in cost, but also unaffected by weather, and further improves the working efficiency of unmanned container trucks.

[0008] To achieve the above and other related objectives, the technical solution provided by this invention is as follows: A method for precise secondary positioning of an unmanned container truck under a port tire crane, comprising the following steps:

[0009] A1: The cloud platform loads the port crane point cloud model and global positioning initial value according to the task, outputs global path planning information, and the unmanned truck reaches the global target point based on the global path planning information and obtains the GPS information of the global target point.

[0010] A2: Based on the GPS information of the global target point, the cloud platform dispatches the tire crane to the global target point to complete the first positioning;

[0011] A3: Based on the lidar symmetrically arranged on the left and right sides of the unmanned truck, the inner sides of the front and rear side beams of the tire crane are scanned to obtain point cloud data of the inner sides of the front and rear side beams of the tire crane.

[0012] A4: Based on the initial global positioning value, and using the bilateral filtering algorithm, the point cloud data of the inner sides of the front and rear side beams of the tire crane are denoised to output an ordered point cloud dataset.

[0013] A5: Based on the ordered point cloud dataset, the RANSAC algorithm is used to process the ordered point cloud dataset and output at least four linear equations about ax + by + c = 0.

[0014] A6: Based on the data of linear equations, obtain the coordinate information of the center point between adjacent linear equations. The cloud platform schedules unmanned trucks to reach the intersection of the lines connecting the center point coordinates or the projection point of the intersection to complete the secondary precise positioning.

[0015] Furthermore, the cloud platform is wirelessly connected to the unmanned truck and the tire crane via 5G communication.

[0016] Furthermore, both the first positioning and the second precise positioning are established in a unified coordinate system with the global target point as the origin.

[0017] To achieve the above and other related objectives, the present invention also provides a method for precise secondary positioning of unmanned container trucks under port gantry cranes, comprising the following steps:

[0018] B1: The cloud platform loads the port crane point cloud model and global positioning initial value according to the task, and outputs global path planning information and bridge crane midpoint GPS information. The unmanned truck reaches the bridge crane midpoint based on the global path planning information and completes the first positioning.

[0019] B2: Based on the lidar set at the center of the top of the unmanned truck, the inner side of the bridge crane top beam is scanned to obtain the point cloud data of the inner side of the bridge crane top beam;

[0020] B3: Based on the initial global positioning value, the point cloud data on the inner side of the bridge crane top beam is denoised using a bilateral filtering algorithm to output an ordered point cloud dataset.

[0021] B4: Compress the ordered point cloud dataset into a point cloud plane according to the interval, extract the inner edge of the ordered point cloud dataset using the RANSAC algorithm, and output a linear equation about ax′+by′+c=0.

[0022] B5: Based on the linear equation ax′+by′+c=0, the midpoint coordinates of the bridge crane top beam are obtained, and the cloud platform schedules the unmanned truck to reach the midpoint coordinates to complete the secondary precise positioning.

[0023] Furthermore, the cloud platform and the unmanned truck are wirelessly connected via 5G communication.

[0024] Furthermore, both the first positioning and the second precise positioning are based on a unified coordinate system with the midpoint of the bridge crane as the origin.

[0025] To achieve the above and other related objectives, the present invention also provides a precise secondary positioning system for unmanned trucks under port rubber-tired gantry cranes or gantry cranes, including a computer device programmed or configured to perform the steps of the precise secondary positioning method for unmanned trucks under port rubber-tired gantry cranes or gantry cranes.

[0026] To achieve the above and other related objectives, the present invention also provides a computer-readable storage medium storing a computer program programmed or configured to perform the method for precise secondary positioning of unmanned trucks under port rubber-tired gantry cranes or bridge cranes.

[0027] The present invention has the following positive effects:

[0028] 1) This invention uses lidar to scan targets, which is low in cost and widely applicable.

[0029] 2) The lidar used in this invention is not affected by weather, which improves the working efficiency of tire cranes and unmanned trucks.

[0030] 3) This invention performs operations such as linear fitting on the acquired point cloud data, making the UAV card positioning accurate and stable. Attached Figure Description

[0031] Figure 1 This is a schematic diagram of the positioning method for tire cranes and unmanned trucks according to the present invention;

[0032] Figure 2 This is a schematic diagram of the positioning method for bridge cranes and unmanned trucks of the present invention;

[0033] Figure 3 This is a schematic diagram of the lidar scanning of the tire-mounted crane according to the present invention;

[0034] Figure 4 This is a schematic diagram of the lidar scanning of the bridge crane according to the present invention. Detailed Implementation

[0035] The following specific examples illustrate the implementation of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that, unless otherwise specified, the following embodiments and features described therein can be combined with each other.

[0036] Example 1: As Figure 1 As shown, a method for precise secondary positioning of an unmanned container truck under a port tire crane includes the following steps:

[0037] A1: The cloud platform loads the port crane point cloud model and global positioning initial value according to the task, outputs global path planning information, and the unmanned truck reaches the global target point based on the global path planning information and obtains the GPS information of the global target point.

[0038] A2: Based on the GPS information of the global target point, the cloud platform dispatches the tire crane to the global target point to complete the first positioning;

[0039] A3: Based on the lidar symmetrically arranged on the left and right sides of the unmanned truck, the inner sides of the front and rear side beams of the tire crane are scanned to obtain point cloud data of the inner sides of the front and rear side beams of the tire crane.

[0040] A4: Based on the initial global positioning value, and using the bilateral filtering algorithm, the point cloud data of the inner sides of the front and rear side beams of the tire crane are denoised to output an ordered point cloud dataset.

[0041] A5: Based on the ordered point cloud dataset, the RANSAC algorithm is used to process the ordered point cloud dataset and output at least four linear equations about ax + by + c = 0.

[0042] A6: Based on the data of linear equations, obtain the coordinate information of the center point between adjacent linear equations. The cloud platform schedules unmanned trucks to reach the intersection of the lines connecting the center point coordinates or the projection point of the intersection to complete the secondary precise positioning.

[0043] Specifically, the cloud platform is wirelessly connected to the unmanned container truck and the tire crane via 5G communication.

[0044] Specifically, both the first positioning and the second precise positioning are established in a unified coordinate system with the global target point as the origin.

[0045] Specifically, such as Figure 3 As shown, the unmanned truck reaches the underside of the tire crane after the first positioning. The inner sides of the front and rear crossbeams of the tire crane are scanned by symmetrically installed LiDAR on both sides to obtain point cloud maps of the inner sides of the front and rear crossbeams. By using the coordinates (x1, y1) and (x2, y2) of two different points located on the same straight line inside the tire crane, we can obtain linear equations. At least four linear equations are obtained to determine the center point, thereby further performing a second precise positioning of the unmanned truck. It can be clearly seen that the second positioning is smoother and more reliable, and the real-time position of the unmanned truck relative to the tire crane can be dynamically output as real-time feedback for controlling the vehicle's movement.

[0046] Example 2: As Figure 2 As shown, a method for precise secondary positioning of unmanned container trucks under port gantry cranes includes the following steps:

[0047] B1: The cloud platform loads the port crane point cloud model and global positioning initial value according to the task, and outputs global path planning information and bridge crane midpoint GPS information. The unmanned truck reaches the bridge crane midpoint based on the global path planning information and completes the first positioning.

[0048] B2: Based on the lidar set at the center of the top of the unmanned truck, the inner side of the bridge crane top beam is scanned to obtain the point cloud data of the inner side of the bridge crane top beam;

[0049] B3: Based on the initial global positioning value, the point cloud data on the inner side of the bridge crane top beam is denoised using a bilateral filtering algorithm to output an ordered point cloud dataset.

[0050] B4: Compress the ordered point cloud dataset into a point cloud plane according to the interval, extract the inner edge of the ordered point cloud dataset using the RANSAC algorithm, and output a linear equation about ax′+by′+c=0.

[0051] B5: Based on the linear equation ax′+by′+c=0, the midpoint coordinates of the bridge crane top beam are obtained, and the cloud platform schedules the unmanned truck to reach the midpoint coordinates to complete the secondary precise positioning.

[0052] Specifically, the cloud platform and the unmanned truck are wirelessly connected via 5G communication.

[0053] Specifically, both the first positioning and the second precise positioning are based on a unified coordinate system with the midpoint of the bridge crane as the origin.

[0054] Specifically, such as Figure 4 As shown, after the unmanned truck completes the initial positioning, it reaches the midpoint of the gantry crane. Then, the lidar at the center of the top of the unmanned truck scans the gantry crane's top beam to obtain point cloud data of the inner side of the gantry crane's top beam. Using a linear fitting method, the linear equation ax′+by′+c=0 for the gantry crane's top beam is obtained. The coordinates of the center point of the gantry crane's top beam are calculated using the points at both ends. The unmanned truck is then dispatched through the cloud scheduling platform to reach the center point of the gantry crane's top beam, thus completing the secondary precise positioning.

[0055] In summary, this invention is not only low in cost but also unaffected by weather conditions, improving the working efficiency of unmanned trucks, as well as the operating efficiency of tire cranes and bridge cranes, preventing unnecessary losses and increasing production efficiency.

[0056] The above embodiments are merely illustrative of the principles and effects of the present invention and are not intended to limit the invention. Any person skilled in the art can modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or alterations made by those skilled in the art without departing from the spirit and technical concept disclosed in the present invention should still be covered by the claims of the present invention.

Claims

1. A method for precise secondary positioning of unmanned container trucks under a port tire crane, characterized in that, The unmanned truck is equipped with lidar sensors symmetrically arranged on its left and right sides. The secondary positioning method includes the following steps: A1. The cloud platform loads the port machinery point cloud model and global positioning initial value according to the task, outputs global path planning information, and the unmanned truck reaches the global target point based on the global path planning information and obtains the GPS information of the global target point. A2. Based on the GPS information of the global target point, the cloud platform dispatches the tire crane to the global target point to complete the first positioning; A3. Based on the lidar of the unmanned truck, scan the inner side of the front and rear side beams of the tire crane to obtain point cloud data of the inner side of the front and rear side beams of the tire crane; A4. Based on the initial value of global target point localization, and using a bilateral filtering algorithm, the point cloud data of the inner sides of the front and rear beams of the tire crane are denoised to output an ordered point cloud dataset. A5. Based on the ordered point cloud dataset, the RANSAC algorithm is used to process the ordered point cloud dataset and output at least four linear equations about ax + by + c = 0. A6. Based on the data of the linear equations, obtain the coordinate information of the center point between adjacent linear equations. The cloud platform dispatches unmanned trucks to the intersection of the lines connecting the center point coordinates or the projection point of the intersection to complete the secondary precise positioning. The first positioning in step A1 and the secondary precise positioning in step A6 are both established in a unified coordinate system with the global target point as the origin.

2. The method for precise secondary positioning of unmanned container trucks under a port tire crane as described in claim 1, characterized in that: In step A1, the cloud platform wirelessly connects with the unmanned truck and the tire crane via 5G communication.

3. A method for precise secondary positioning of unmanned container trucks under port gantry cranes, characterized in that, Includes the following steps: B1. The cloud platform loads the port crane point cloud model and global positioning initial value according to the task, and outputs global path planning information and bridge crane midpoint GPS information. The unmanned truck reaches the bridge crane midpoint based on the global path planning information and bridge crane GPS information, and completes the first positioning. B2. Based on the lidar set at the center of the top of the unmanned truck, the inner side of the bridge crane top beam is scanned to obtain the point cloud data of the inner side of the bridge crane top beam; B3. Based on the initial global positioning value, and using a bilateral filtering algorithm, the point cloud data on the inner side of the bridge crane top beam is denoised to output an ordered point cloud dataset. B4. Compress the ordered point cloud dataset according to the interval, extract the inner edge of the ordered point cloud dataset using the RANSAC algorithm, and output the linear equation about ax′+by′+c=0. B5. Based on the linear equation ax′+by′+c=0, obtain the midpoint coordinates of the top beam of the bridge crane. The cloud platform dispatches the unmanned truck to reach the midpoint coordinates to complete the secondary precise positioning. The first positioning in step B1 and the secondary precise positioning in step B5 are both established in a unified coordinate system with the midpoint of the bridge crane as the origin.

4. The method for precise secondary positioning of unmanned container trucks under port gantry cranes according to claim 3, characterized in that: In step B1, the cloud platform and the unmanned truck are wirelessly connected via 5G communication.

5. A precise secondary positioning system for unmanned container trucks under port rubber-tired gantry cranes or bridge cranes, comprising computer equipment, characterized in that, The computer device is programmed or configured to perform the steps of the precise secondary positioning method for unmanned container trucks under port rubber gantry cranes or gantry cranes as described in any one of claims 1 to 4.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that is programmed or configured to perform the method for precise secondary positioning of unmanned trucks under port rubber gantry cranes or gantry cranes as described in any one of claims 1 to 4.

Images