A method for constructing a digital twin scenario for port simulation testing

Abstract

The present invention relates to the technical field of simulation test scene construction, specifically a method for constructing a digital twin scene of a port simulation test, including stage one, stage two, stage three and stage four; stage one: input and screening of multi-source data; stage two: geographic alignment of data; geo-alignment of the screened data, and distinction between the global projection coordinate system and the local coordinate system; stage three: import and adjustment of data; importing the above data into a simulation software platform and aligning it to assist in the modeling of static scenes; stage four: construction of digital twin scenes; adjusting the data imported in stage three to build a digital twin static scene. The beneficial effect is: using the actual existing and collected data from multiple sources as the basis for construction and production, the construction accuracy of the digital twin scene is improved, and the high degree of consistency between the digital twin scene and the real world is guaranteed to a great extent.

Description

Technical Field

[0001] The present invention relates to the technical field of simulation test scenario construction, and specifically to a method for constructing a digital twin scenario for port simulation testing. Background Art

[0002] At present, the existing port intelligent driving technology and related simulation test scenario technology mostly involve simulation test methods, construction of simulation test scenarios, test processes based on simulation platforms, etc., but lack the description and guidance of digital twin static scene construction methods. Most methods are based only on OpenDRIVE files as the basis for construction. However, affected by the OpenDRIVE production process, accuracy and completeness of elements, the high accuracy of static scenes cannot be guaranteed, and thus the high consistency between digital twin scenes and the real world cannot be guaranteed. Therefore, a method for constructing digital twin scenarios for port simulation tests is proposed. Summary of the invention

[0003] In order to overcome the technical defects in the prior art, ensure the high consistency between the digital twin scene and the real world, and effectively solve the technical problems in the background technology, the present invention provides the following technical solutions:

[0004] A method for constructing a digital twin scenario for port simulation testing, characterized in that it includes phase one, phase two, phase three and phase four;

[0005] Phase 1: Input and screening of multi-source data;

[0006] The input of multi-source data includes the input of actual existing data and real collected data, as well as the data generated by production;

[0007] The screening of multi-source data includes the screening of data timeliness, data integrity and data coordinate system;

[0008] Phase 2: Geo-reference of data;

[0009] Georeference the selected data and distinguish between the global projected coordinate system and the local coordinate system;

[0010] Phase 3: Data import and adjustment;

[0011] Import the above data into the simulation software platform and align them to assist in modeling static scenes;

[0012] Phase 4: Construction of digital twin scenarios;

[0013] Adjust the data imported in Phase 3 and build a digital twin static scene.

[0014] As a preferred technical solution of the present invention, the multi-source data includes CAD drawings, point cloud data, image data, GPS trajectory data, vector data and OpenDRIVE data.

[0015] As a preferred technical solution of the present invention, in the stage four, the imported data is adjusted, including adjusting the geographical location, geometric shape, road attributes and lane attributes of the road to achieve complete consistency with the real world.

[0016] Compared with the prior art, the beneficial effects of the present invention are: using multiple sources of actually existing and collected data as the basis for building production, thereby improving the construction accuracy of the digital twin scene, and ensuring the high consistency between the digital twin scene and the real world to a great extent; specifically, through the real design and collection of port roads and environmental data, a 1:1 high-precision digital twin scene is built for the port, and the real world is moved to the virtual world, which serves as the road basis for the simulation test of the intelligent driving system, assists the application of subsequent intelligent driving simulation tests, and improves the effectiveness of the simulation test. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a flowchart of the present invention. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0019] See also Figure 1 The present invention provides a technical solution: a method for building a digital twin scene for port simulation testing, which uses multi-source actual existing and collected data (CAD drawings, point cloud data, image data, GPS trajectory data, vector data, OpenDRIVE data, etc.) as the basis for building production to ensure high accuracy of the scene. It consists of four stages:

[0020] Phase 1: Input and screening of multi-source data;

[0021] Phase 2: Geo-reference of data;

[0022] Phase 3: Data import and adjustment;

[0023] Phase 4: Construction of digital twin scenarios.

[0024] The implementation of each stage is as follows:

[0025] Phase 1: Input and screening of multi-source data;

[0026] Multi-source data input includes actual existing data (such as CAD drawings used in the early stage of construction design and BIM models produced by construction planning) and real collected data (such as point clouds generated by lidar collection, images generated by cameras, and GPS trajectory data generated by inertial navigation equipment) and generated data (such as shapefile / geojson format data generated by vectorization and OpenDRIVE format data generated by special topological processing).

[0027] The screening of multi-source data includes: screening of data timeliness (i.e., selecting the latest time when data is acquired), screening of data integrity (ensuring that the data fully covers the scope of the digital twin scene to be built, including covering both directions of the road, covering the ground elements and aerial elements of the road), and screening of data coordinate systems (ensuring that the coordinate system used by the data with coordinates is consistent, that is, the projection coordinate system used to project the real spherical surface into a plane must be consistent).

[0028] Phase 2: Geo-reference of data;

[0029] Geo-reference the selected data. It is necessary to distinguish between the global projection coordinate system and the local coordinate system. The local coordinate system needs to find its origin based on the global projection coordinate system for translation alignment. In general, point matching can also be performed through the positions of three or more points of the same name in different data sources. The average value of the difference between the global projection coordinate system coordinates of the same name points and the local coordinate system coordinates of the same name points (the difference between the average values ​​cannot be greater than 0.3 meters) is equal to the translation coordinate amount between the two coordinate systems.

[0030] Phase 3: Data import and adjustment;

[0031] Import the above data into the simulation software platform, and select or convert it into an importable data format according to the data support of the simulation software platform. Multi-source data that has been georeferenced can be directly superimposed and aligned in the simulation software platform, and alignment can be achieved by adjusting the offset values ​​of different data. Based on the alignment, it can be used to assist in the modeling of static scenes.

[0032] Phase 4: Construction of digital twin scenarios

[0033] Based on the data imported in Phase 3, we started to build the digital twin static scene. When importing data in OpenDRIVE format, we can directly adjust the data in OpenDRIVE format based on other superimposed reference data sources, including adjusting the road's geographic location, geometry, road attributes, lane attributes (number of lanes, lane width, lane line type, lane line color) and other elements to achieve complete consistency with the real world. When importing data in Shapefile format, we can superimpose other reference data sources, manually draw roads in the simulation software, and adjust the road's geographic location, geometry, road attributes, lane attributes and other elements.

[0034] When using:

[0035] The construction method proposed in the present invention is not limited to any simulation platform software. By cooperating with geographic information systems and 3D modeling software (including but not limited to QGIS software, Das Viewer software, video viewing software, CloudCompare software, 3DsMax software, Revit software, etc.), the construction of digital twin scenes can be completed in the simulation platform software, and the simulation platform software can be used as the main software for running tests.

[0036] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for constructing a digital twin scenario for port simulation testing, characterized in that: It includes Phase 1, Phase 2, Phase 3 and Phase 4; Phase 1: Input and screening of multi-source data; The input of multi-source data includes the input of actual existing data and real collected data, as well as the data generated by production; The screening of multi-source data includes the screening of data timeliness, data integrity and data coordinate system; Phase 2: Georeferencing of data; Georeference the selected data and distinguish between the global projected coordinate system and the local coordinate system; Phase 3: Data import and adjustment; Import the above data into the simulation software platform and align them to assist in modeling static scenes; Phase 4: Construction of digital twin scenarios; Adjust the data imported in Phase 3 and build a digital twin static scene.

2. The method for constructing a digital twin scenario for port simulation testing according to claim 1 is characterized in that: The multi-source data includes CAD drawings, point cloud data, image data, GPS trajectory data, vector data and OpenDRIVE data.

3. The method for constructing a digital twin scenario for port simulation testing according to claim 1 is characterized in that: In the fourth stage, the imported data is adjusted, including adjusting the geographical location, geometric shape, road attributes and lane attributes of the road to achieve complete consistency with the real world.

Images