A method and system for precise positioning based on port task operation and a storage medium

Abstract

The present application relates to a kind of based on the accurate positioning method, system and storage medium of port task operation, the method comprises: J1. vehicle receives port task operation, based on the point cloud data information of vehicle front road environment that real-time acquisition is obtained by vehicle-mounted forward long-range laser radar;J2. based on the point cloud data information of vehicle front road environment, the region of interest of vertical transport device is extracted, then feature extraction is carried out, obtains the point cloud feature cluster of vertical transport device, with high-precision map is matched, outputs the relative position data information of vehicle and vertical transport device.The present application not only improves the alignment accuracy of vehicle and vertical transport device in various environments in port, but also improves the overall operation efficiency of port.

Description

Technical Field

[0001] This invention relates to the field of navigation and positioning technology, and in particular to a precise positioning method, system and storage medium based on port task operations. Background Technology

[0002] With the continuous development of autonomous driving technology and its application in various industries, including the operation of unmanned container trucks in ports, the transportation of goods by unmanned container trucks requires docking with vertical transportation devices. If the positioning is inaccurate, it may lead to the tipping of goods or secondary transportation. Therefore, how to achieve more accurate positioning has become an urgent problem to be solved.

[0003] In the prior art, a patent (application number: 202211671515.5) describes a method for precise parking of unmanned vehicles in a port crane scenario, comprising: Step 1: Template map creation, which involves collecting panoramic point cloud data of the crane and creating a template map based on the point cloud data; Step 2: Target origin alignment of the template map, where the vehicle is parked at the desired precise parking position under the crane, and point cloud data of the vehicle's location is collected and aligned with the point cloud of the template map; Step 3: Precise parking based on the template map, where, when the unmanned vehicle approaches the crane, it receives a request for precise parking from the task management module, triggering a precise parking task. A laser scan of the crane obtains point cloud data, which is then matched with the template map to obtain the distance of the unmanned vehicle relative to the target origin and the required direction of movement in real time. This allows for adjustment of the unmanned vehicle's position information, achieving precise parking of the unmanned vehicle in the crane scenario. This method primarily relies on point cloud map matching for precise positioning, but it heavily depends on the consistency between the map features of the point cloud and the actual detection. However, the actual environment of a port is constantly changing and obstructed due to container loading and unloading operations, making it impossible to guarantee the accuracy of the matching. Therefore, the overall matching accuracy cannot be guaranteed.

[0004] In the prior art, the patent (application number: 202110738101.9) on the method, device, equipment and storage medium for positioning unmanned container trucks in ports mainly identifies three parts: the spreader body, the spreader and the container on the truck through sensors on the top of the truck. The final positioning distance is calculated by the position deviation. However, in actual process, the spreader body and the spreader vary greatly depending on the on-site environment. The patent does not elaborate on the specific identification scheme and the countermeasures for actual problems. Summary of the Invention

[0005] In view of the shortcomings of the prior art, the present invention provides a precise positioning method, system and storage medium based on port task operations, which not only improves the alignment accuracy of vehicles and vertical transportation devices in various port environments, but also improves the overall port operation efficiency.

[0006] To achieve the above and other related objectives, the present invention provides the following technical solution:

[0007] A precise positioning method based on port task operations, the method comprising:

[0008] J1. The vehicle receives port tasks and uses a forward-facing long-range lidar to acquire point cloud data of the road environment in front of the vehicle in real time.

[0009] J2. Based on the point cloud data of the road environment in front of the vehicle, extract the region of interest of the vertical transportation device, then perform feature extraction to obtain the point cloud feature cluster of the vertical transportation device, match it with the high-precision map, and output the relative position data information of the vehicle and the vertical transportation device.

[0010] J3. Based on the relative position data of the vehicle and the vertical transport device, a preset coordinate point is set. If the vehicle travels to the preset coordinate point, it stops. The Bella number detection algorithm and point cloud feature recognition are used to adjust the alignment of the vehicle and the vertical transport device to complete the container loading or unloading operation.

[0011] Furthermore, in step J3, the alignment adjustment between the vehicle and the vertical transport device using the Bella number detection algorithm and point cloud feature recognition includes:

[0012] J31. Real-time acquisition of point cloud data information of vertical transportation devices based on vehicle-mounted near-range lidar, and real-time acquisition of road image data information based on vehicle-mounted camera;

[0013] J32. Based on the point cloud data information of the vertical transportation device, extract the region of interest of the spreader, then perform feature extraction to obtain the point cloud feature cluster of the spreader, perform inter-frame matching, output the position data information of the spreader, and input the road image data information into the Bella number detection algorithm to obtain the position data information of the vehicle;

[0014] J33. Adjust the position of the vehicle based on the vehicle's position data and the lifting device's position data.

[0015] Furthermore, in step J32, the Bella number detection algorithm includes:

[0016] J321. Preprocess the road image data information and output the preprocessed road image data information;

[0017] J322. Input the preprocessed road image data information into the YOLOV5 network model for Bella number identification and classification, and output the category and location data information of the Bella number;

[0018] J323. Based on the category and location data of the Bella, the vehicle's location is calculated using a high-precision map, and the vehicle's location data is output.

[0019] Furthermore, the preprocessing includes image scaling and image normalization.

[0020] Furthermore, the preset coordinate point is P, where P is the vertex coordinate of the quadratic fitting function F(x).

[0021] F(x) = ax 2 +bx+c,

[0022] Where a, b, and c are constant coefficients, and x is the independent variable.

[0023] Furthermore, the constant coefficients a, b, and c are determined by the relative position data information of the vehicle and the vertical transport device, which includes the relative coordinates of the vehicle, the relative coordinates of the vertical transport device, and the relative coordinates of the container.

[0024] To achieve the above and other related objectives, the present invention also provides a precise positioning system based on port task operations, which applies any of the precise positioning methods based on port task operations described in the present invention. The system includes:

[0025] The port task operation system is used to issue task instructions and data information for port operations.

[0026] A horizontal transport system includes a horizontal transport module and a precise alignment module for the work scenario. The precise alignment module for the work scenario includes a task logic calculation unit and an environmental detection unit for adjusting the vehicle position.

[0027] A vertical transport system, connected to the horizontal transport system, is used to receive vehicle position adjustment data and adjust the lifting device of the vertical transport unit to complete the packing operation.

[0028] Furthermore, the environmental detection unit is connected to a data acquisition unit, which includes a long-range lidar, a short-range lidar, and a camera.

[0029] Furthermore, the port task operation system is communicatively connected to the horizontal transportation system and the vertical transportation system.

[0030] 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 any of the port task operation-based precise positioning methods described above.

[0031] The present invention has the following positive effects:

[0032] 1. This invention completes port transportation operations through a distributed horizontal and vertical transportation system, which not only copes with different port transportation environments, but also improves the alignment accuracy of vehicles and vertical transportation devices in various port environments.

[0033] 2. In order to ensure the one-time container grabbing accuracy, this invention needs to further identify the relative position of the container loading or operation bay number in the horizontal transportation system and the spreader in the vertical transportation system, and perform certain smoothing processing on the logical units to complete the precise positioning of the final container loading and unloading operation, thereby improving the overall port operation efficiency. Attached Figure Description

[0034] Figure 1 This is a schematic diagram of the method flow of the present invention;

[0035] Figure 2 This is a schematic diagram of the system framework of the present invention. Detailed Implementation

[0036] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0037] Example 1: As Figure 1 As shown, a precise positioning method based on port task operations is described, the method comprising:

[0038] J1. The vehicle receives port tasks and uses a forward-facing long-range lidar to acquire point cloud data of the road environment in front of the vehicle in real time.

[0039] J2. Based on the point cloud data of the road environment in front of the vehicle, extract the region of interest of the vertical transportation device, then perform feature extraction to obtain the point cloud feature cluster of the vertical transportation device, match it with the high-precision map, and output the relative position data information of the vehicle and the vertical transportation device.

[0040] J3. Based on the relative position data of the vehicle and the vertical transport device, a preset coordinate point is set. If the vehicle travels to the preset coordinate point, it stops. The Bella number detection algorithm and point cloud feature recognition are used to adjust the alignment of the vehicle and the vertical transport device to complete the container loading or unloading operation.

[0041] In this embodiment, step J3, which involves adjusting the alignment of the vehicle and the vertical transport device using the Bella number detection algorithm and point cloud feature recognition, includes:

[0042] J31. Real-time acquisition of point cloud data information of vertical transportation devices based on vehicle-mounted near-range lidar, and real-time acquisition of road image data information based on vehicle-mounted camera;

[0043] J32. Based on the point cloud data information of the vertical transportation device, extract the region of interest of the spreader, then perform feature extraction to obtain the point cloud feature cluster of the spreader, perform inter-frame matching, output the position data information of the spreader, and input the road image data information into the Bella number detection algorithm to obtain the position data information of the vehicle;

[0044] J33. Adjust the position of the vehicle based on the vehicle's position data and the lifting device's position data.

[0045] In this embodiment, in step J32, the Bella number detection algorithm includes:

[0046] J321. Preprocess the road image data information and output the preprocessed road image data information;

[0047] J322. Input the preprocessed road image data information into the YOLOV5 network model for Bella number identification and classification, and output the category and location data information of the Bella number;

[0048] J323. Based on the category and location data of the Bella, the vehicle's location is calculated using a high-precision map, and the vehicle's location data is output.

[0049] In this embodiment, the preprocessing includes image scaling and image normalization.

[0050] In this embodiment, the preset coordinate point is P, where P is the vertex coordinate of the quadratic fitting function F(x).

[0051] F(x) = ax 2 +bx+c,

[0052] Where a, b, and c are constant coefficients, and x is the independent variable.

[0053] In this embodiment, the constant coefficients a, b, and c are determined by the relative position data information of the vehicle and the vertical transport device, which includes the relative coordinates of the vehicle, the relative coordinates of the vertical transport device, and the relative coordinates of the container.

[0054] Example 2: Based on the precise positioning method for port task operations in Example 1, the present invention will be further explained and described below.

[0055] like Figure 2 As shown, the present invention provides a precise positioning system based on port task operations, which applies any of the precise positioning methods based on port task operations described in the present invention. The system includes:

[0056] The port task operation system is used to issue task instructions and data information for port operations.

[0057] A horizontal transport system includes a horizontal transport module and a precise alignment module for the work scenario. The precise alignment module for the work scenario includes a task logic calculation unit and an environmental detection unit for adjusting the vehicle position.

[0058] A vertical transport system, connected to the horizontal transport system, is used to receive vehicle position adjustment data and adjust the lifting device of the vertical transport unit to complete the packing operation.

[0059] In this embodiment, the environmental detection unit is connected to a data acquisition unit, which includes a long-range lidar, a short-range lidar, and a camera.

[0060] In this embodiment, the port task operation system is communicatively connected to the horizontal transportation system and the vertical transportation system.

[0061] The present invention provides a computer-readable storage medium storing a computer program programmed or configured to perform any of the port task-based precise positioning methods described herein.

[0062] Any references to memory, storage, database, or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM), etc.

[0063] In summary, this invention not only improves the alignment accuracy of vehicles and vertical transport devices in various port environments, but also enhances the overall operational efficiency of the port.

[0064] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A precise positioning method based on port task operations, characterized in that, The method includes: J1. The vehicle receives port tasks and uses a forward-facing long-range lidar to acquire point cloud data of the road environment in front of the vehicle in real time. J2. Based on the point cloud data of the road environment in front of the vehicle, extract the region of interest of the vertical transportation device, then perform feature extraction to obtain the point cloud feature cluster of the vertical transportation device, match it with the high-precision map, and output the relative position data information of the vehicle and the vertical transportation device. J3. Based on the relative position data of the vehicle and the vertical transport device, a preset coordinate point is set. If the vehicle travels to the preset coordinate point, it stops. The Bella number detection algorithm and point cloud feature recognition are used to adjust the alignment of the vehicle and the vertical transport device to complete the container loading or unloading operation. In step J3, the alignment adjustment between the vehicle and the vertical transport device using the Bella number detection algorithm and point cloud feature recognition includes: J31. Real-time acquisition of point cloud data information of vertical transportation devices based on vehicle-mounted near-range lidar, and real-time acquisition of road image data information based on vehicle-mounted camera; J32. Based on the point cloud data information of the vertical transportation device, extract the region of interest of the spreader, then perform feature extraction to obtain the point cloud feature cluster of the spreader, perform inter-frame matching, output the position data information of the spreader, and input the road image data information into the Bella number detection algorithm to obtain the position data information of the vehicle; J33. Adjust the position of the vehicle based on the vehicle's position data and the spreader's position data; In step J32, the Bella number detection algorithm includes: J321. Preprocess the road image data information and output the preprocessed road image data information; J322. Input the preprocessed road image data information into the YOLOV5 network model for Bella number identification and classification, and output the category and location data information of the Bella number; J323. Based on the category and location data of the Bella, the vehicle's location is calculated using a high-precision map, and the vehicle's location data is output.

2. The precise positioning method based on port task operations according to claim 1, characterized in that: The preprocessing includes image scaling and image normalization.

3. The precise positioning method based on port task operations according to claim 1, characterized in that: The preset coordinate point is P, where P is the vertex coordinate of the quadratic fitting function F(x). F(x)=ax 2 +bx+c, Where a, b, and c are constant coefficients, and x is the independent variable.

4. The precise positioning method based on port task operations according to claim 3, characterized in that: The constant coefficients a, b, and c are determined by the relative position data information of the vehicle and the vertical transport device, which includes the relative coordinates of the vehicle, the relative coordinates of the vertical transport device, and the relative coordinates of the container.

5. A precise positioning system based on port task operations, characterized in that, The system employs the precise positioning method based on port task operations as described in any one of claims 1-4, and comprises: The port task operation system is used to issue task instructions and data information for port operations. A horizontal transport system includes a horizontal transport module and a precise alignment module for the work scenario. The precise alignment module for the work scenario includes a task logic calculation unit and an environmental detection unit for adjusting the vehicle position. A vertical transport system, connected to the horizontal transport system, is used to receive vehicle position adjustment data and adjust the lifting device of the vertical transport unit to complete the packing operation.

6. The precise positioning system based on port task operations according to claim 5, characterized in that: The environmental detection unit is connected to a data acquisition unit, which includes a long-range lidar, a short-range lidar, and a camera.

7. The precise positioning system based on port task operations according to claim 5, characterized in that: The port task operation system is communicatively connected to the horizontal transportation system, and the port task operation system is communicatively connected to the vertical transportation system.

8. 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 precise positioning method based on port task operations as described in any one of claims 1 to 4.

Images