A port point cloud mapping and matching positioning method and system for a joint dispatching platform

Abstract

The present invention relates to a port point cloud mapping and matching positioning method and system of a joint dispatching platform, the method comprising: Q1. In a port multi-bridge operation scenario, multiple unmanned container trucks execute the operation tasks issued by the joint dispatching platform, obtain the historical operation route data information of the vehicle, obtain the point cloud data information of the target area in real time based on the vehicle-mounted laser radar, and obtain the vehicle's posture data information in real time based on the vehicle-mounted IMU; Q2. Based on the point cloud data information of the target area and the posture data information of the vehicle, an improved feature selection algorithm based on penalty items is used to construct a point cloud map of the target area to obtain the point cloud map data information of the target area. The present invention can not only improve the accuracy of the laser positioning result, but also the vehicle-side mapping range is accurate, the point cloud map is concise, the vehicle-side computing platform and storage requirements are low, and it is more suitable for low-cost engineering promotion.

Description

Technical Field

[0001] The present invention relates to the technical field of port point cloud mapping and matching positioning, and in particular to a port point cloud mapping and matching positioning method and system for a joint dispatching platform. Background Art

[0002] With breakthroughs in related technologies such as autonomous driving and platform scheduling, as well as the increase in port transportation and container throughput, ports, as a semi-enclosed scene, have become the focus of everyone's competition for the commercial implementation of autonomous driving. However, the port environment is complex, with large metal tower cranes blocking the view, the environmental characteristics of the yard containers changing with the operation, and the flooding of lane line features by typhoon season rain, which has brought great challenges to the port's GPS, laser feature matching, visual feature matching and corresponding fusion positioning.

[0003] Traditional GPS, laser feature matching, visual feature matching, and corresponding fusion positioning cannot effectively cover typical scenarios where GPS signals are unstable under multi-path conditions with metal interference, lane lines are unreliable due to occlusion or disrepair, and the environment is constantly changing. Real-time map construction and matching based on lasers have high requirements on controller computing power, high application costs, and are difficult to promote in engineering applications.

[0004] In the prior art, the patent (application number: 201911199281.7) discloses a simultaneous mapping and positioning for port autonomous driving, including 3D laser SLAM, LeGO-LOAM mapping and NDT-MATCH positioning, characterized in that: the 3D laser SLAM includes multi-line laser radar data, the LeGO-LOAM mapping includes point cloud segmentation,

[0005] Point cloud feature extraction, laser odometer and laser mapping, the NDT-MATCH positioning includes point cloud mapping and point cloud registration. However, this solution does not supplement the minimum area that needs to be supplemented with laser point cloud mapping, resulting in low accuracy of the positioning result.

[0006] In the prior art, the patent (application number: 202111046232.7) discloses a fast relocation method for large-scale mapping scenes based on point clouds, which belongs to the field of robot autonomous driving technology. The method includes using SLAM technology for mapping. During the mapping process, the key frames of the 3D point cloud and the corresponding ring-domain feature vector library, the multi-resolution sub-map library, and data preprocessing are generated. The data preprocessing is as follows: calculating the score of each node in the multi-resolution sub-map tree structure to generate a node score database; starting relocation, using the current moment sensor data, performing ring-domain feature vector matching to obtain a candidate sub-map library; obtaining the best sub-map and the initial pose value of the vehicle from the candidate sub-map; performing precise matching in the best sub-map to obtain the final relocation result. However, this solution does not supplement the minimum area that needs to be supplemented for laser point cloud mapping, resulting in low accuracy of the positioning result. Summary of the invention

[0007] In view of the above shortcomings of the prior art, the present invention provides a port point cloud mapping and matching positioning method and system for a joint dispatching platform, which can not only improve the accuracy of laser positioning results, but also accurately build a vehicle-side map, simplify the point cloud map, and have low requirements for the vehicle-side computing platform and storage, which is more suitable for low-cost engineering promotion.

[0008] In order to achieve the above-mentioned purpose and other related purposes, the technical solution provided by the present invention is as follows:

[0009] A port point cloud mapping and matching positioning method for a joint dispatching platform, the method comprising:

[0010] Q1. In the multi-bridge operation scenario at the port, multiple unmanned container trucks execute the operation tasks issued by the joint dispatching platform, obtain the historical operation route data information of the vehicles, obtain the point cloud data information of the target area in real time based on the on-board laser radar, and obtain the position data information of the vehicles in real time based on the on-board IMU;

[0011] Q2. Based on the point cloud data information of the target area and the position data information of the vehicle, a point cloud map of the target area is constructed using an improved feature selection algorithm based on penalty terms to obtain point cloud map data information of the target area;

[0012] Q3. Based on the point cloud map data information of the target area and the historical operation route data information of the vehicle, a minimum area function F that needs to be supplemented with laser point cloud mapping is established, and the point cloud map of the target area is optimized to obtain the optimized point cloud map data information of the target area;

[0013] Q4. Based on the optimized point cloud map data information of the target area and the point cloud data information of the target area, an improved ICP algorithm is used to perform real-time point cloud and point cloud map registration, and the laser positioning result data information of the vehicle is output.

[0014] Furthermore, in step Q2, the step of constructing a point cloud map of the target area using an improved feature selection algorithm based on penalty terms includes:

[0015] Q21. Based on the point cloud data information of the target area, establish a point cloud feature extraction function G based on a penalty term,

[0016] ,

[0017] Among them, x i is the point cloud data information of the target area, x0 is the point cloud mean point data information of the target area, α i and β i is the penalty item of the point cloud of the target area, extracts the feature points of the point cloud of the target area, and obtains the data information of the feature points of the point cloud of the target area;

[0018] Q22. Based on the point cloud feature point data information of the target area and the posture data information of the vehicle, establish a point cloud feature space selection function H of the target area,

[0019] ,

[0020] Among them, y is the point cloud feature point data information of the target area, z is the vehicle's posture data information, ω1, ω2 and ω3 are the point cloud feature space determining factors of the target area, and the spatial data information of the point cloud feature points of the target area is calculated to obtain the spatial data information of the point cloud feature points of the target area;

[0021] Q23. Based on the spatial data information of the point cloud feature points of the target area, establish a point cloud map construction function M of the target area,

[0022] ,

[0023] Among them, h is the spatial data information of the point cloud feature points of the target area, ρ1, ρ2, ρ3 and ρ4 are decision factors for constructing the point cloud map, and the point cloud map of the target area is constructed to obtain the point cloud map data information of the target area.

[0024] Furthermore, the point cloud mean point data information x0 of the target area,

[0025] ,

[0026] Among them, x iis the point cloud data information of the target area, λ 1i and λ 2i is the weight coefficient, n is the sample size;

[0027] The penalty term α of the target area point cloud i and β i for,

[0028] ,

[0029] ,

[0030] Among them, x i It is the point cloud data information of the target area.

[0031] Furthermore, the constraints of the decision factors ρ1, ρ2, ρ3 and ρ4 for constructing the point cloud map are:

[0032] .

[0033] Furthermore, in step Q3, the minimum area function F required to supplement the laser point cloud mapping is,

[0034] ,

[0035] Among them, m is the point cloud map data information of the target area, h is the historical operation route data information of the vehicle, θ1, θ2 and θ3 are the compensation constant factors of laser point cloud mapping, and f is the relationship function between the route of laser point cloud mapping and the point cloud map.

[0036] Furthermore, the relationship function f between the route of the laser point cloud mapping and the point cloud map is,

[0037] ,

[0038] Among them, h is the historical operation route data information of the vehicle, and A is the relationship matrix between the point cloud map and the route.

[0039] Furthermore, in step Q4, the use of the improved ICP algorithm to perform registration of the real-time point cloud and the point cloud map includes:

[0040] Q41. Based on the optimized point cloud map data information of the target area and the point cloud data information of the target area, establish a relationship function W between the point cloud map of the target area and the point cloud,

[0041] ,

[0042] Among them, a is the point cloud map data information of the optimized target area, b is the point cloud data information of the target area, R is the orthogonal matrix between the point cloud map and the point cloud, t is the conversion matrix between the point cloud map and the point cloud, η1, η2 and η3 are the relationship factors between the point cloud map and the point cloud of the target area;

[0043] Q42. Based on the relationship function W between the point cloud map of the target area and the point cloud, the relationship between the point cloud map of the target area and the point cloud is characterized to obtain the relationship matrix data information between the point cloud map of the target area and the point cloud;

[0044] Q43. Based on the relationship matrix data information of the target area point cloud map and the point cloud, establish a registration function J of the target area point cloud map and the point cloud,

[0045] ,

[0046] Among them, c is the relationship matrix data information between the point cloud map and the point cloud of the target area, δ1, δ2 and δ3 are the registration constant parameters of the point cloud map and the point cloud, and the real-time point cloud and point cloud map are registered to output the laser positioning result data information of the vehicle.

[0047] Furthermore, the real-time point cloud and point cloud map are aligned to obtain the alignment value of the point cloud map and the point cloud according to the alignment function J of the point cloud map and the point cloud of the target area, and a preset threshold is set. If the alignment value of the point cloud map and the point cloud of the target area is less than the preset threshold, the laser positioning result data information of the vehicle is output; if the alignment value of the point cloud map and the point cloud of the target area is greater than the preset threshold, the laser positioning result data information of the vehicle is not output.

[0048] In order to achieve the above-mentioned purpose and other related purposes, the present invention also provides a port point cloud mapping and matching positioning system of a joint dispatching platform, including a computer device, which is programmed or configured to execute the steps of any one of the port point cloud mapping and matching positioning methods of the joint dispatching platform.

[0049] In order to achieve the above-mentioned objectives and other related objectives, the present invention also provides a computer-readable storage medium, which stores a computer program programmed or configured to execute any one of the port point cloud mapping and matching positioning methods of the joint scheduling platform.

[0050] The present invention has the following positive effects:

[0051] 1. The present invention constructs a point cloud map of the target area by adopting an improved feature selection algorithm based on penalty terms, and optimizes the point cloud map of the target area in combination with the minimum area function F that needs to supplement the laser point cloud mapping, so as to obtain the optimized point cloud map data information of the target area, which not only improves the accuracy of the point cloud map and ensures the accuracy of the laser positioning result, but also makes the vehicle-side mapping range accurate, the point cloud map concise, and has low requirements for the vehicle-side computing platform and storage, and is more suitable for low-cost engineering promotion.

[0052] 2. The present invention adopts an improved ICP algorithm to perform registration of real-time point cloud and point cloud map. It can not only accurately identify the range of comprehensive and complex working conditions with low probability through the platform task scheduling system, and efficiently transmit it to the unmanned container truck to realize accurate range mapping and point cloud map fleet sharing, but also facilitate registration. The obtained laser positioning result is more accurate, which is convenient for unmanned container trucks to complete complex operating tasks. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 It is a schematic diagram of the method flow of the present invention;

[0054] Figure 2 A schematic flow chart of an improved feature selection algorithm based on penalty terms according to the present invention;

[0055] Figure 3 It is a schematic flow chart of the improved ICP algorithm of the present invention;

[0056] Figure 4 A schematic diagram of the relationship between the joint dispatching platform and the unmanned container truck of the present invention;

[0057] Figure 5 It is a schematic diagram of the framework of the joint scheduling platform of the present invention;

[0058] Figure 6 It is a schematic diagram of the vehicle end frame of the unmanned container truck of the present invention. DETAILED DESCRIPTION

[0059] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0060] Example 1: Figure 1 or Figure 4 or Figure 5 or Figure 6As shown, a port point cloud mapping and matching positioning method of a joint dispatching platform, the method comprising:

[0061] Q1. In the multi-bridge operation scenario at the port, multiple unmanned container trucks execute the operation tasks issued by the joint dispatching platform, obtain the historical operation route data information of the vehicles, obtain the point cloud data information of the target area in real time based on the on-board laser radar, and obtain the position data information of the vehicles in real time based on the on-board IMU;

[0062] Q2. Based on the point cloud data information of the target area and the position data information of the vehicle, a point cloud map of the target area is constructed using an improved feature selection algorithm based on penalty terms to obtain point cloud map data information of the target area;

[0063] Q3. Based on the point cloud map data information of the target area and the historical operation route data information of the vehicle, a minimum area function F that needs to be supplemented with laser point cloud mapping is established, and the point cloud map of the target area is optimized to obtain the optimized point cloud map data information of the target area;

[0064] Q4. Based on the optimized point cloud map data information of the target area and the point cloud data information of the target area, an improved ICP algorithm is used to perform real-time point cloud and point cloud map registration, and the laser positioning result data information of the vehicle is output.

[0065] In this embodiment, if Figure 2 As shown, in step Q2, the point cloud map of the target area is constructed by using the improved feature selection algorithm based on penalty terms, including:

[0066] Q21. Based on the point cloud data information of the target area, establish a point cloud feature extraction function G based on a penalty term,

[0067] ,

[0068] Among them, x i is the point cloud data information of the target area, x0 is the point cloud mean point data information of the target area, α i and β i is the penalty item of the point cloud of the target area, extracts the feature points of the point cloud of the target area, and obtains the data information of the feature points of the point cloud of the target area;

[0069] Q22. Based on the point cloud feature point data information of the target area and the posture data information of the vehicle, establish a point cloud feature space selection function H of the target area,

[0070] ,

[0071] Among them, y is the point cloud feature point data information of the target area, z is the vehicle's posture data information, ω1, ω2 and ω3 are the point cloud feature space determining factors of the target area, and the spatial data information of the point cloud feature points of the target area is calculated to obtain the spatial data information of the point cloud feature points of the target area;

[0072] Q23. Based on the spatial data information of the point cloud feature points of the target area, establish a point cloud map construction function M of the target area,

[0073] ,

[0074] Among them, h is the spatial data information of the point cloud feature points of the target area, ρ1, ρ2, ρ3 and ρ4 are decision factors for constructing the point cloud map, and the point cloud map of the target area is constructed to obtain the point cloud map data information of the target area.

[0075] In this embodiment, the point cloud mean point data information x0 of the target area,

[0076] ,

[0077] Among them, x i is the point cloud data information of the target area, λ 1i and λ 2i is the weight coefficient, n is the sample size;

[0078] The penalty term α of the target area point cloud i and β i for,

[0079] ,

[0080] ,

[0081] Among them, x i It is the point cloud data information of the target area.

[0082] In this embodiment, the constraints of the decision factors ρ1, ρ2, ρ3 and ρ4 for constructing the point cloud map are:

[0083] .

[0084] Example 2: Based on the port point cloud mapping and matching positioning method of a joint dispatching platform in Example 1, the present invention is further illustrated and described below.

[0085] like Figure 1 or Figure 4 or Figure 5 or Figure 6As shown, a port point cloud mapping and matching positioning method of a joint dispatching platform, the method comprising:

[0086] Q1. In the multi-bridge operation scenario at the port, multiple unmanned container trucks execute the operation tasks issued by the joint dispatching platform, obtain the historical operation route data information of the vehicles, obtain the point cloud data information of the target area in real time based on the on-board laser radar, and obtain the position data information of the vehicles in real time based on the on-board IMU;

[0087] Q2. Based on the point cloud data information of the target area and the position data information of the vehicle, a point cloud map of the target area is constructed using an improved feature selection algorithm based on penalty terms to obtain point cloud map data information of the target area;

[0088] Q3. Based on the point cloud map data information of the target area and the historical operation route data information of the vehicle, a minimum area function F that needs to be supplemented with laser point cloud mapping is established, and the point cloud map of the target area is optimized to obtain the optimized point cloud map data information of the target area;

[0089] Q4. Based on the optimized point cloud map data information of the target area and the point cloud data information of the target area, an improved ICP algorithm is used to perform real-time point cloud and point cloud map registration, and the laser positioning result data information of the vehicle is output.

[0090] In this embodiment, in step Q3, the minimum area function F that needs to be supplemented with laser point cloud mapping is,

[0091] ,

[0092] Among them, m is the point cloud map data information of the target area, h is the historical operation route data information of the vehicle, θ1, θ2 and θ3 are the compensation constant factors of laser point cloud mapping, and f is the relationship function between the route of laser point cloud mapping and the point cloud map.

[0093] In an embodiment, the relationship function f between the route of the laser point cloud mapping and the point cloud map is,

[0094] ,

[0095] Among them, h is the historical operation route data information of the vehicle, and A is the relationship matrix between the point cloud map and the route.

[0096] In this embodiment, if Figure 3 As shown, in step Q4, the use of the improved ICP algorithm to perform registration of the real-time point cloud and the point cloud map includes:

[0097] Q41. Based on the optimized point cloud map data information of the target area and the point cloud data information of the target area, establish a relationship function W between the point cloud map of the target area and the point cloud,

[0098] ,

[0099] Among them, a is the point cloud map data information of the optimized target area, b is the point cloud data information of the target area, R is the orthogonal matrix between the point cloud map and the point cloud, t is the conversion matrix between the point cloud map and the point cloud, η1, η2 and η3 are the relationship factors between the point cloud map and the point cloud of the target area;

[0100] Q42. Based on the relationship function W between the point cloud map of the target area and the point cloud, the relationship between the point cloud map of the target area and the point cloud is characterized to obtain the relationship matrix data information between the point cloud map of the target area and the point cloud;

[0101] Q43. Based on the relationship matrix data information of the target area point cloud map and the point cloud, establish a registration function J of the target area point cloud map and the point cloud,

[0102] ,

[0103] Among them, c is the relationship matrix data information between the point cloud map and the point cloud of the target area, δ1, δ2 and δ3 are the registration constant parameters of the point cloud map and the point cloud, and the real-time point cloud and point cloud map are registered to output the laser positioning result data information of the vehicle.

[0104] In this embodiment, the real-time point cloud and point cloud map are aligned to obtain the alignment value of the point cloud map and the point cloud according to the alignment function J of the point cloud map and the point cloud of the target area, and a preset threshold is set. If the alignment value of the point cloud map and the point cloud of the target area is less than the preset threshold, the laser positioning result data information of the vehicle is output; if the alignment value of the point cloud map and the point cloud of the target area is greater than the preset threshold, the laser positioning result data information of the vehicle is not output.

[0105] In this embodiment, the present invention provides a port point cloud mapping and matching positioning system for a joint dispatching platform, including a computer device that is programmed or configured to execute the steps of any one of the port point cloud mapping and matching positioning methods for a joint dispatching platform.

[0106] In this embodiment, the present invention provides a computer-readable storage medium storing a computer program programmed or configured to execute any one of the port point cloud mapping and matching positioning methods of the joint scheduling platform.

[0107] In this embodiment, if Figure 4As shown in the figure, the overall system architecture includes: platform task scheduling system (supporting vehicle-side task issuance), unmanned container truck fleet (including laser radar, point cloud map construction module, point cloud matching and positioning module, and point cloud map return); the platform task scheduling system uses the operation tasks to identify in advance whether the operation route has a complex scene such as multi-bridge operation, and sends the minimum area that needs to be supplemented with laser point cloud mapping to the first unmanned container truck participating in the operation through the scheduling platform. The unmanned container truck realizes real-time mapping of the target area, and the point cloud map of the operation area is transmitted back to the platform to share with the operation fleet, and further realizes precise positioning in complex scenes through the vehicle-end cloud matching and positioning algorithm.

[0108] In this embodiment, if Figure 5 As shown in the figure, the platform task scheduling system includes an operation task management module, which is responsible for understanding the overall operation tasks and corresponding route information of the unmanned truck fleet; the mapping area and mapping task issuance module is responsible for configuring the mapping task of the first vehicle after prior identification, including the confirmation of the mapping condition status of the first vehicle such as GPS signal strength. If the mapping requirements are not met, the vehicle will be replaced, as well as the scope information of the mapping area to be constructed; the point cloud map management module is responsible for storing and distributing the point cloud map information constructed by the first vehicle.

[0109] In this embodiment, if Figure 6 As shown in the figure, the unmanned container truck system: (the prerequisite is that the unmanned container truck is equipped with a lidar sensor), includes a point cloud map construction module, in which any operating vehicle with a good GPS signal status receives the collection task instructions and range information through the platform end, implements the specific collection task, and stores the data in the point cloud map management module, and uploads it to the platform cloud. The platform cloud distributes it to all unmanned container truck fleets operating on related routes through broadcasting, and implements their respective point cloud map management; finally, the point cloud map matching module accurately matches and locates the constructed point cloud map through real-time point cloud environment detection information.

[0110] Any reference to memory, storage, database or other media used in the embodiments provided in the present 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. As an illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0111] In summary, the present invention can not only improve the accuracy of laser positioning results, but also make the vehicle-side mapping range accurate, the point cloud map concise, and have low requirements for the vehicle-side computing platform and storage, making it more suitable for low-cost engineering promotion.

[0112] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A port point cloud mapping and matching positioning method for a joint dispatching platform, characterized in that: The method comprises: Q1. In the multi-bridge operation scenario at the port, multiple unmanned container trucks execute the operation tasks issued by the joint dispatching platform, obtain the historical operation route data information of the vehicles, obtain the point cloud data information of the target area in real time based on the on-board laser radar, and obtain the position data information of the vehicles in real time based on the on-board IMU; Q2. Based on the point cloud data information of the target area and the position data information of the vehicle, a point cloud map of the target area is constructed using an improved feature selection algorithm based on penalty terms to obtain point cloud map data information of the target area; Q3. Based on the point cloud map data information of the target area and the historical operation route data information of the vehicle, a minimum area function F that needs to be supplemented with laser point cloud mapping is established, and the point cloud map of the target area is optimized to obtain the optimized point cloud map data information of the target area; Q4. Based on the optimized point cloud map data information of the target area and the point cloud data information of the target area, an improved ICP algorithm is used to perform real-time point cloud and point cloud map registration, and the laser positioning result data information of the vehicle is output; In step Q2, constructing a point cloud map of the target area using an improved feature selection algorithm based on penalty terms includes: Q21. Based on the point cloud data information of the target area, establish a point cloud feature extraction function G based on a penalty term, ， Among them, x i is the point cloud data information of the target area, x0 is the point cloud mean point data information of the target area, α i and β i is the penalty item of the point cloud of the target area, extracts the feature points of the point cloud of the target area, and obtains the data information of the feature points of the point cloud of the target area; Q22. Based on the point cloud feature point data information of the target area and the posture data information of the vehicle, establish a point cloud feature space selection function H of the target area, ， Among them, y is the point cloud feature point data information of the target area, z is the vehicle's posture data information, ω1, ω2 and ω3 are the point cloud feature space determining factors of the target area, and the spatial data information of the point cloud feature points of the target area is calculated to obtain the spatial data information of the point cloud feature points of the target area; Q23. Based on the spatial data information of the point cloud feature points of the target area, establish a point cloud map construction function M of the target area, ， Among them, h is the spatial data information of the point cloud feature points of the target area, ρ1, ρ2, ρ3 and ρ4 are the decision factors for constructing the point cloud map, and the point cloud map of the target area is constructed to obtain the point cloud map data information of the target area; In step Q4, the registration of the real-time point cloud and the point cloud map using the improved ICP algorithm includes: Q41. Based on the optimized point cloud map data information of the target area and the point cloud data information of the target area, establish a relationship function W between the point cloud map of the target area and the point cloud, ， Among them, a is the point cloud map data information of the optimized target area, b is the point cloud data information of the target area, R is the orthogonal matrix between the point cloud map and the point cloud, t is the conversion matrix between the point cloud map and the point cloud, η1, η2 and η3 are the relationship factors between the point cloud map and the point cloud of the target area; Q42. Based on the relationship function W between the point cloud map of the target area and the point cloud, the relationship between the point cloud map of the target area and the point cloud is characterized to obtain the relationship matrix data information between the point cloud map of the target area and the point cloud; Q43. Based on the relationship matrix data information of the target area point cloud map and the point cloud, establish a registration function J of the target area point cloud map and the point cloud, ， Among them, c is the relationship matrix data information between the point cloud map and the point cloud of the target area, δ1, δ2 and δ3 are the registration constant parameters of the point cloud map and the point cloud, and the real-time point cloud and point cloud map are registered to output the laser positioning result data information of the vehicle.

2. The port point cloud mapping and matching positioning method of the joint dispatching platform according to claim 1 is characterized by: The point cloud mean point data information x0 of the target area, ， Among them, x i is the point cloud data information of the target area, λ 1i and λ 2i is the weight coefficient, n is the sample size; The penalty term α of the target area point cloud i and β i for, ， ， Among them, x i It is the point cloud data information of the target area.

3. The port point cloud mapping and matching positioning method of the joint dispatching platform according to claim 1 is characterized by: The constraints of the decision factors ρ1, ρ2, ρ3 and ρ4 for constructing the point cloud map are: 。 4. The port point cloud mapping and matching positioning method of the joint dispatching platform according to claim 1 is characterized in that: In step Q3, the minimum area function F required to supplement the laser point cloud mapping is, ， Among them, m is the point cloud map data information of the target area, h is the historical operation route data information of the vehicle, θ1, θ2 and θ3 are the compensation constant factors of laser point cloud mapping, and f is the relationship function between the route of laser point cloud mapping and the point cloud map.

5. The port point cloud mapping and matching positioning method of the joint dispatching platform according to claim 4 is characterized by: The relationship function f between the route of the laser point cloud mapping and the point cloud map is: ， Among them, h is the historical operation route data information of the vehicle, and A is the relationship matrix between the point cloud map and the route.

6. The port point cloud mapping and matching positioning method of the joint dispatching platform according to claim 1 is characterized by: The real-time point cloud and point cloud map are aligned to obtain the alignment value of the point cloud map and the point cloud according to the alignment function J of the point cloud map and the point cloud of the target area, and a preset threshold is set. If the alignment value of the point cloud map and the point cloud of the target area is less than the preset threshold, the laser positioning result data information of the vehicle is output; if the alignment value of the point cloud map and the point cloud of the target area is greater than the preset threshold, the laser positioning result data information of the vehicle is not output.

7. A port point cloud mapping and matching positioning system for a joint dispatching platform, including a computer device, characterized in that: The computer device is programmed or configured to execute the steps of the port point cloud mapping and matching positioning method of the joint scheduling platform as described in any one of claims 1 to 6.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program that is programmed or configured to execute the port point cloud mapping and matching positioning method of the joint scheduling platform as described in any one of claims 1 to 6.

Images