A map processing method and device in a simulation system and electronic equipment

Abstract

The present disclosure relates to a map processing method and device in a simulation system and electronic equipment, and belongs to the technical field of map processing. The map processing method in the simulation system comprises: acquiring a map in at least one format; processing the map according to a rasterized map format to obtain a target map; the rasterized map format comprises a topology layer and a geometry layer; the topology layer comprises a logical structure of a road, and the road comprises a plurality of lanes; the geometry layer comprises a geometry shape description of the plurality of lanes; and the target map is imported into an automatic driving simulation system for automatic driving simulation task processing. The present disclosure can realize fast import and lightweight operation of a third-party map.

Description

Technical Field

[0001] This disclosure belongs to the field of map processing technology, and specifically relates to a map processing method, apparatus and electronic equipment in a simulation system. Background Technology

[0002] High-precision maps are the infrastructure for autonomous driving and play a crucial role in vehicle simulation. In vehicle simulation, it may be necessary to import various third-party maps in different formats to support the simulation. When importing multiple third-party maps into a vehicle simulation system, the different standards of these maps result in different vector representations, making the import process very complex and causing significant trouble. Summary of the Invention

[0003] The purpose of this disclosure is to provide a map processing method, apparatus, and electronic device in a simulation system, which solves the problem of difficulty in importing various third-party maps into the simulation system.

[0004] In a first aspect, embodiments of this disclosure provide a map processing method in a simulation system, including:

[0005] Obtain a map in at least one format;

[0006] The map is processed according to a rasterized map format to obtain the target map. This rasterized map format includes a topology layer and a geometry layer. The topology layer includes the logical structure of the roads, and each road includes multiple lanes. The geometry layer includes a description of the geometric shape of the multiple lanes. Both the topology layer and the geometry layer are scalar data.

[0007] Import the target map into the autonomous driving simulation system for autonomous driving simulation task processing.

[0008] Optionally, the map can be processed according to a rasterized map format to obtain the target map, including:

[0009] Obtain the map topology file and N map tile files. The map topology file includes the logical structure of the roads, and the map tile files include the geometric shape data of the lanes in the roads, and N positive integers.

[0010] Convert the map topology file into a rasterized map format to obtain the target topology layer data of the target map.

[0011] Convert N map tile files into geometric layers in a rasterized map format to obtain the target geometric layer data of the target map.

[0012] The target map is obtained based on the target topology layer data and the target geometry layer data.

[0013] Optionally, the map topology file is converted into a topology layer in a rasterized map format to obtain the target topology layer data of the target map, including:

[0014] Based on the logical structure of roads in the map topology file, assign values ​​to the logical relationships of roads in the topology layer of the rasterized map format;

[0015] Based on the physical lane information in the map topology file, the relationships between lanes in the topology layer of the rasterized map format are assigned values ​​to obtain the target topology layer data of the target map.

[0016] Optionally, based on the logical structure of roads in the map topology file, the logical relationships of roads in the topology layer of the rasterized map format are assigned values, including:

[0017] Based on the logical structure of roads in the map topology file, assign values ​​to the predecessors and successors of roads in the topology layer of the rasterized map format.

[0018] Optionally, based on the physical lane information in the map topology file, values ​​are assigned to the lane relationships in the topology layer of the rasterized map format, including:

[0019] Based on the physical lane information in the map topology file, the predecessor, successor, left neighbor, and right neighbor of the lanes in the topology layer of the rasterized map format are assigned values.

[0020] Optionally, the N map tile files are converted into geometric layers in a rasterized map format to obtain the target geometric layer data of the target map, including:

[0021] Based on the lane geometry expressions in N map tile files, the lane geometry descriptions in the geometry layer of the rasterized map format are assigned values ​​to obtain the scalar data of the target geometry layer of the target map.

[0022] Optionally, based on the lane geometry expressions in the N map tile files, the lane geometry descriptions in the geometric layers of the rasterized map format are assigned values ​​to obtain the target geometry layer data of the target map, including:

[0023] The geometric shape data of lanes in N map fragment files are used to assign values ​​to the left boundary, right boundary, and center line of the lanes in the geometric layer of the rasterized map format, respectively, to obtain the target geometric layer data of the target map.

[0024] Secondly, embodiments of this disclosure provide a map processing apparatus in a simulation system, comprising:

[0025] The acquisition module is used to acquire maps in at least one format;

[0026] The processing module is used to process the map according to the raster map format to obtain the target map. The raster map format includes a topology layer and a geometry layer. The topology layer includes the logical structure of the roads, and the roads include multiple lanes. The geometry layer includes the geometric shape description of the multiple lanes. Both the topology layer and the geometry layer are scalar data. The target map is then imported into the autonomous driving simulation system for autonomous driving simulation task processing.

[0027] Optionally, the processing module processes the map according to a rasterized map format to obtain the target map, including:

[0028] The first processing submodule is used to obtain the map topology file and N map tile files. The map topology file includes the logical structure of the roads, and the map tile files include the geometric shape data of the lanes in the roads, and N positive integers.

[0029] The second processing submodule is used to convert the map topology file into a topology layer in a rasterized map format to obtain the target topology layer data of the target map.

[0030] The third processing submodule is used to convert N map tile files into geometric layers in a rasterized map format to obtain the target geometric layer data of the target map.

[0031] The fourth processing submodule is used to obtain the target map based on the target topology layer data and the target geometry layer data.

[0032] Optionally, the second processing submodule includes:

[0033] The first processing unit is used to assign values ​​to the logical relationships of roads in the topology layer of the raster map format according to the logical structure of roads in the map topology structure file.

[0034] The second processing unit is used to assign values ​​to the lane relationships in the topology layer of the rasterized map format based on the physical lane information in the map topology structure file, so as to obtain the scalar data of the target topology layer of the target map.

[0035] Optionally, the first processing unit includes:

[0036] The first processing subunit is used to assign values ​​to the predecessors and successors of roads in the topology layer of the rasterized map format according to the logical structure of roads in the map topology structure file.

[0037] Optionally, the second processing unit includes:

[0038] The second processing subunit is used to assign values ​​to the predecessor, successor, left neighbor, and right neighbor of the lanes in the topology layer of the rasterized map format based on the physical lane information in the map topology structure file.

[0039] Optionally, the third processing submodule includes:

[0040] The fifth processing submodule is used to assign values ​​to the geometric shape descriptions of lanes in the geometric layer of the rasterized map format based on the geometric shape expressions of lanes in N map tile files, so as to obtain the scalar data of the target geometric layer of the target map.

[0041] Optionally, the fifth processing submodule includes:

[0042] The third processing unit is used to assign values ​​to the left boundary, right boundary, and center line of the lanes in the geometric layer of the rasterized map format, respectively, based on the lane geometry data in the N map tile files, to obtain the target geometry layer data of the target map.

[0043] Thirdly, embodiments of this disclosure provide an electronic device including a processor, a memory, and a program or instructions stored in the memory and executable on the processor, wherein the program or instructions, when executed by the processor, implement the steps of the map processing method in the simulation system of the first aspect.

[0044] Fourthly, embodiments of this disclosure provide a readable storage medium on which a program or instructions are stored, which, when executed by a processor, implement the steps of the map processing method in the simulation system of the first aspect.

[0045] In this embodiment, a map of at least one format is acquired; the map is processed according to a rasterized map format to obtain a target map; the rasterized map format includes a topology layer and a geometry layer; the topology layer includes the logical structure of roads, and each road includes multiple lanes; the geometry layer includes a geometric description of the multiple lanes; the target map is imported into an autonomous driving simulation system for autonomous driving simulation task processing. This solves the problem of difficulty in importing various third-party maps into the simulation system, and achieves fast import and lightweight operation of third-party maps. Attached Figure Description

[0046] Figure 1 The diagram shows a schematic flowchart of a map processing method in a simulation system provided by an embodiment of this disclosure;

[0047] Figure 2 A schematic diagram of the structure of a rasterized map format is shown;

[0048] Figure 3 A schematic diagram of target topology layer data in rasterized map format is shown;

[0049] Figure 4 A schematic diagram of target geometric layer data in rasterized map format is shown;

[0050] Figure 5 A schematic diagram of the structure of the map processing device in the simulation system provided in this embodiment is shown;

[0051] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure is shown;

[0052] Figure 7 A schematic diagram of the hardware structure of an electronic device implementing an embodiment of the present disclosure is shown. Detailed Implementation

[0053] The technical solutions of the embodiments of this disclosure will be clearly described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this disclosure. All other embodiments obtained by those skilled in the art based on the embodiments of this disclosure are within the scope of protection of this disclosure.

[0054] The terms "first," "second," etc., used in this disclosure and in the claims are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such use of data can be interchanged where appropriate so that embodiments of this disclosure can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first," "second," etc., are generally of the same class and the number of objects is not limited; for example, a first object can be one or more. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0055] The embodiments disclosed herein mainly relate to map format conversion, processing maps of different formats to obtain a target map that meets the rasterized map format. Here, rasterization refers to representing the map in the form of a set of pixels, that is, processing the map into a graphic composed of multiple square pixels.

[0056] The target map in the rasterized map format can be applied to an autonomous driving simulation system. This autonomous driving simulation system is a simulation system that describes the structure or behavior of the autonomous driving simulation task system and has certain logical or quantitative relationships based on the properties of the various elements of the autonomous driving simulation task and their interrelationships. In one possible implementation, the target map can also be applied to other simulation systems that need to load third-party maps, but this disclosure is not limited thereto.

[0057] The autonomous driving simulation system involved in this disclosure includes an HDMAP map engine. This disclosure does not limit the map engine; it can also be an application or device that supports raster map formats. The virtual scene involved in this disclosure can be a virtual space constructed based on a target map, or it can be an open space; this disclosure is not limited to these limitations. The virtual scene can be a real-world environment simulated according to the target map. Of course, in one possible implementation, the virtual scene can also correspond to a real-world scene. The virtual scene can also support time control, allowing for free adjustment of night and day, and can also support a weather system, setting sunny, rainy, snowy, foggy, etc.

[0058] The map processing method, apparatus, and electronic equipment in the simulation system provided by this disclosure will be described in detail below with reference to the accompanying drawings and through specific embodiments and application scenarios.

[0059] Figure 1 This is a flowchart of a map processing method in a simulation system provided by an embodiment of this disclosure. See also... Figure 1 The method may include the following steps:

[0060] Step 101: Obtain a map in at least one format; the map here may be NDS (Navigation Data Standard); OpenStreetMap; lanelet (efficient autonomous driving map representation); ADASIS V3 (Advanced Driver Assistance Systems Interface Specification), etc., or other map formats, which are not limited in this disclosure.

[0061] Step 102: Process the map according to a rasterized map format to obtain a target map. The rasterized map format includes a topology layer and a geometry layer. The topology layer includes the logical structure of the road, which includes multiple lanes. The geometry layer includes a geometric description of the multiple lanes. Both the topology layer and the geometry layer are scalar data. In this embodiment, in order to import a third-party map into the autonomous driving simulation system, the third-party map can be processed according to a rasterized map format to obtain a target map. This target map can be used as an intermediate map format when importing into the autonomous driving simulation system, so that the autonomous driving simulation system can import data information from the third-party map more quickly.

[0062] Specifically, rasterized map formats include: topological layers (topo) and geometric layers (geo);

[0063] The topology layer defines the core architecture of the road, including its logical structure. A road consists of multiple lanes, meaning the road is the parent element of the lanes. The topology layer is derived from the map's topology file, which describes the map's topology.

[0064] The following is a detailed explanation of the roads and lanes:

[0065] A road is a road in a logical sense, while a lane is a physical lane. A group of lanes can constitute a road. The topology layer of a map is organized through the logical structure of roads. Lanes in the topology layer are the core entities for map navigation and routing. Roads can be navigated and routed through lanes, or the specific road can be located first according to the road topology information, and then navigation and routing can be performed through the lanes in the road.

[0066] The geometry layer defines the geometric shape description of each lane, including the geometric shape description of multiple lanes (e.g., left lane line; right lane line; lane center line), and may also include additional lane line attributes (e.g., lane line type); the geometry layer is obtained by converting N map tile files of the map, which describe the geometric data of the map.

[0067] In an optional embodiment of this disclosure, step 102 includes:

[0068] Step 1021: Obtain the map topology file and N map tile files of the map. The map topology file includes the logical structure of the roads, and the map tile files include the geometric shape data of the lanes in the roads, and N positive integers. In this embodiment, the topology layer describes the logical structure of the roads in the overall road network of the map. Its data volume is relatively small and is usually stored as a map topology file. The geometry layer is used to describe the geometric shape data of the roads. It usually has a large data volume and needs to be packaged into N map tile files according to preset rules. The geometric shape data of the entire map to be imported is tiled, which can realize lightweight loading of the map during the autonomous driving simulation task. Preferably, the geometric shape data of the roads is packaged according to the data volume of the map tile files according to the preset rules.

[0069] Step 1022: Convert the map topology file into a topology layer in a rasterized map format to obtain the target topology layer data of the target map;

[0070] In an optional embodiment of this disclosure, step 1022 includes:

[0071] Step 10221: Assign values ​​to the logical relationships of roads in the topology layer of the rasterized map format according to the logical structure of roads in the map topology file; wherein, the logical relationships of roads in the topology layer include: road predecessors; road successors; and lane relationships.

[0072] In an optional embodiment of this disclosure, step 10221 includes:

[0073] Based on the logical structure of roads in the map topology file, the predecessors and successors of roads in the topology layer of the rasterized map format are assigned values. In this embodiment, the connection relationship between roads can be established based on the road's predecessor and successor. The predecessor refers to the first connection end of the road, and the successor refers to the second connection end of the road.

[0074] The assignment of values ​​for the predecessor and successor of a road includes:

[0075] The identifier (ID) of the other road that connects to the predecessor;

[0076] The type of the other road that connects to its predecessor;

[0077] The point of connection (Piont) to another road that is connected to the predecessor.

[0078] When a road in a topology layer includes multiple road segments, the topology layer also includes: the segment identifier of the road segment, the direction of the road segment, the starting point of the road segment, and the length of the road segment.

[0079] It is worth noting that the topology layer may also include a topology header, which includes: map type; map name; and the MD5 hash of the original map. The MD5 hash is a 128-bit feature code obtained by digitally transforming information using a publicly available MD5 message digest algorithm. Of course, the topology layer may also include other road logic structure related information, which will not be listed here, and this disclosure is not limited thereto.

[0080] Step 10222: Based on the physical lane information in the map topology file, assign values ​​to the lane relationships in the topology layer of the rasterized map format to obtain the scalar data of the target topology layer of the target map.

[0081] In the embodiments of this disclosure, since the relationship between lanes and roads is that of child and parent elements, the information of physical lanes in the topology layer of the rasterized map format is assigned to the relationship of lanes under the road segments.

[0082] In an optional embodiment of this disclosure, step 10222 includes:

[0083] Based on the physical lane information in the map topology file, values ​​are assigned to the predecessor, successor, left neighbor, and right neighbor of lanes in the topology layer of the rasterized map format. The lane relationships include the predecessor, successor, left neighbor, and right neighbor of the lane, and may also include the lane head, which includes: lane length, lane type, and speed limit. The assigned values ​​for the lane relationships include: the lane's predecessor identifier; the lane's successor identifier; the lane's left neighbor identifier; and the lane's right neighbor identifier.

[0084] In a specific embodiment 1, when performing physical lane information conversion and topology layer conversion on the third-party map OpenDrive, the following formula is used for assignment (the content after the symbol " / / " is for explanation):

[0085] <predecessor contactpoint="end"elementid="43"elementType="road" / >

[0086] / / The connection point of the road connected to the predecessor is assigned the value end, the identifier of the road connected to the predecessor is assigned the value 43, and the type of the road connected to the predecessor is assigned the value road.

[0087] <successor contactPoint="start"elementId="82"elementType="road" / >

[0088] / / The connection point to the subsequent road is assigned the value start, the identifier of the subsequent road is assigned the value 82, and the type of the subsequent road is assigned the value road.

[0089] When converting physical lane information to topology layers in the third-party map OpenDrive, the following formula is used for assignment (the content after the symbol " / / " is for explanation):

[0090] <predecessor id="-1" / >

[0091] / / The preceding identifier for this lane is assigned a value of -1.

[0092] <successor id="-1" / >

[0093] / / The successor identifier for this lane is assigned a value of -1.

[0094] Assign corresponding values ​​to the predecessor and successor in the target topology layer data TopoMapFile to achieve the conversion between the map topology structure file and the target topology layer data.

[0095] Furthermore, the aforementioned rasterized map format also includes: target objects on the road, which include: static objects on the road and / or target entities related to traffic signals;

[0096] Based on the logical structure of roads in the map topology file, values ​​are assigned to target objects on roads in the topology layer of the rasterized map format to obtain scalar data of target objects on roads in the target topology layer.

[0097] In one possible implementation, the rasterized map format can also include target objects on roads (Other). These target objects define the core elements outside the road, including static objects and traffic signal-related target entities (Signals). Common static objects include: guardrails; gantries; parking spaces, etc., while common traffic signals include: traffic lights; road markings; and traffic signs. The values ​​assigned to the target objects on roads in the topology layer include: the type of the target object on the road; and the identifier of the target object on the road.

[0098] It is worth noting that the relationship between the topology layer, the geometry layer, and the target objects on the road is a parallel one.

[0099] To further achieve lightweight map loading, the target objects on the road can also be included in the topology layer, which includes static objects on the road and / or target entities related to traffic signals.

[0100] Figure 2 A schematic diagram of the structure of a rasterized map format is shown. See [link / reference] Figure 2 In a specific embodiment 2, the rasterized map format includes target topology layer data (TopoMapFile) converted from the map's topology structure file, target geometry layer data (TileMapFile) converted from the map tile file, and target objects on the road consisting of static objects and target entities related to traffic signals.

[0101] Figure 3 A schematic diagram of target topology layer data in rasterized map format is shown. See [link / reference] Figure 3 In a specific embodiment 3, the target topology layer data (TopoMapFile) includes a topology header (TopoHeader) and the logical structure of N roads (RoadTopo). The topology header includes the map type (Type), map name (Name), and the MD5 hash of the original map (Md5).

[0102] The logical structure of N roads includes road predecessors (road_predecessors), road successors (road_successors), and road sections (road_sections); each road section includes the road section identifier (section_id), direction (dir), starting point (s_offset), length (length), and the relationship between the N lanes in the road (lane_topo).

[0103] The lane relationships here show the lane information of the N lanes contained in the road, as well as the connection and positional relationships between each lane; the lane relationships specifically include the lane head, the lane predecessors, the lane successors, the left neighbors, and the right neighbors; the lane head specifically includes the lane length, the lane type, and the speed limit;

[0104] Furthermore, the logical structure of N roads can also include static objects on the roads (road_objects) and target entities on the roads related to traffic signals (road_signal).

[0105] Specifically, when converting a third-party map to obtain the target topology layer data, values ​​are assigned to the predecessors and successors of roads in the topology layer of the rasterized map format according to the logical structure of roads in the map topology structure file.

[0106] Based on the physical lane information in the map topology file, the predecessor, successor, left neighbor, and right neighbor of the lanes in the topology layer of the rasterized map format are assigned values ​​to obtain the target topology layer data of the target map.

[0107] Step 1023: Convert N map tile files into geometric layers in a rasterized map format to obtain the target geometric layer data of the target map. This target geometric layer data (TileRoadFile) is obtained based on the geometric shape expression of the lane. This target geometric layer data is used to load the target geometric layer data within a preset range based on the current location when loading the map based on the target topology layer data. Similarly, the target geometric layer data that is not needed within the preset range for the current location can also be clearly cached to achieve lightweight loading of large amounts of map data.

[0108] In an optional embodiment of this disclosure, step 1023 includes:

[0109] Step 10231: Based on the lane geometry expressions in the N map tile files, assign values ​​to the lane geometry descriptions in the geometric layers of the rasterized map format to obtain the target geometry layer data of the target map. Here, the geometry description includes a file header (TileHeader) and road geometry information (Road Geometry). Tile partitioning is used to address the problem of large amounts of map geometry data. For example, if a third-party map contains 10,000 roads, storing the geometry data of all 10,000 roads in a single file would result in an excessively large file that is difficult to load. Therefore, the file needs to be rationally partitioned into 1000 tile files, meaning 10 roads are placed in one tile file. Multiple tile files contain the geometric data of roads from the third-party map.

[0110] Furthermore, in an optional embodiment of this disclosure, step 10231 includes:

[0111] Step 102311: Assign values ​​to the left boundary, right boundary, and center line of the lanes in the geometric layer of the rasterized map format using the lane geometry data from the N map tile files, to obtain the scalar data of the target geometry layer of the target map.

[0112] In the embodiments of this disclosure, the lane geometry data varies depending on the format of the third-party map. For example, in the OpenDrive map, the lane geometry data is expressed using a cubic polynomial, i.e., expressed using vectors.

[0113] The road's geometric information includes the road's unique identifier and the geometric information of the N lanes within the road. The lane's geometric information includes the lane's left boundary, right boundary, and centerline. Assigning values ​​to the lane's geometric shape description in the geometric layer of the raster map format specifically involves assigning values ​​to the left boundary, right boundary, and centerline of each of the N lanes. The geometric layer may also include a file header (version number and map name) and the lane's unique identifier, etc.

[0114] The left and right boundaries of the lanes, as well as the lane centerline, can be represented by a sequence of points along the boundary lines and ground markings along the boundary lines.

[0115] Figure 4 A schematic diagram of target geometric layer data in rasterized map format is shown. See [link / reference] Figure 4 In a specific embodiment 4, the target geometry layer data includes a file header and road geometry information. The file header includes a version number and a map name. The road geometry information includes a unique identifier (id) for the road and the geometry information of N lanes in the road.

[0116] The lane's geometric information specifically includes the lane's unique identifier, left boundary line, right boundary line, and center boundary line. The left boundary line includes a point list and a road mark list.

[0117] When the third-party map is an OpenDrive map, OpenDrive maps express the map's geometric information using a cubic polynomial, that is, they express geometric shape data using a vector representation, as shown below. The following describes a road reference line:

[0118] <geometry hdg="2.9779247649370753"length="10.579882686015212"s="2.43615512843301"x="7.8205183115584376"y=:"-1.6166283195711302">

[0119] <paramPo1y3 aU="0" aV="0" bU="10.33748838409727"bV="-1.1102230246251565E-15" cU="0.60136814467528588"cV="-4.5164566925430583"dU="-1.3626578992139518"

[0120]

[0121] By converting cubic polynomials into rasterized data (including scalar data and point data), the problem of the high difficulty of converting cubic polynomials and potential incompatibility issues is solved.

[0122] Specifically, the left boundary, right boundary, and lane centerline are converted into multiple consecutive points, such as (100, 55, 0.1); (105, 55, 0.1); (110, 55, 0.1); (115, 55, 0.1). These points are then assigned to the point sequence of the left boundary, right boundary, and lane centerline to obtain the target geometric layer data.

[0123] Step 1024: Obtain the target map based on the target topology layer data and the target geometry layer data. This target map is generated by converting the logical structure of roads, physical lane information, and lane geometry expressions from the map topology file into an intermediate format map. This intermediate format includes scalar data from both the target topology layer and the target geometry layer.

[0124] Step 103: Import the target map into the autonomous driving simulation system for autonomous driving simulation task processing.

[0125] In the embodiments of this disclosure, when performing autonomous driving simulation tasks based on a target map, a preset range can be used. When the target vehicle moves to the first position, the target topology layer data of the target map is loaded, and the target geometry layer data within the preset range is also loaded. At the same time, the target geometry layer data that is not needed within the preset range of the target vehicle will also be unloaded, thereby achieving lightweight loading of the target map.

[0126] The map processing method in the simulation system of this disclosure can be applied to, but is not limited to, autonomous driving simulation systems. It can also be applied to any simulation system that requires the map processing method described above. The above embodiments process the map according to a rasterized map format to obtain a target map. This target map provides an intermediate map format before importing the map into the autonomous driving simulation system. The rasterized map format includes a topology layer and a geometry layer. The topology layer includes the logical structure of the road, which includes multiple lanes. The geometry layer includes a geometric description of the multiple lanes. The target map is imported into the autonomous driving simulation system for autonomous driving simulation task processing. This enables faster import of various maps, allowing the simulation system to support maps with large data volumes. During operation, the map can be loaded in blocks, allowing the simulation system to run more lightweightly in the cloud.

[0127] All of the above-mentioned optional technical solutions can be combined in any way to form optional embodiments of this disclosure, and will not be described in detail here.

[0128] Figure 5 This disclosure provides a map processing device 500 in a simulation system, comprising:

[0129] Acquisition module 501 is used to acquire maps in at least one format;

[0130] The processing module 502 is used to process the map according to the raster map format to obtain the target map; the raster map format includes: a topology layer and a geometry layer; the topology layer includes the logical structure of the road, and the road includes multiple lanes; the geometry layer includes: the geometric shape description of the multiple lanes, and both the topology layer and the geometry layer are scalar data; the target map is imported into the autonomous driving simulation system for autonomous driving simulation task processing.

[0131] Optionally, the processing module 502 processes the map according to a rasterized map format to obtain the target map, including:

[0132] The first processing submodule is used to obtain the map topology file and N map tile files. The map topology file includes the logical structure of the roads, and the map tile files include the geometric shape data of the lanes in the roads, and N positive integers.

[0133] The second processing submodule is used to convert the map topology file into a topology layer in a rasterized map format to obtain the target topology layer data of the target map.

[0134] The third processing submodule is used to convert N map tile files into geometric layers in a rasterized map format to obtain the target geometric layer data of the target map.

[0135] The fourth processing submodule is used to obtain the target map based on the target topology layer data and the target geometry layer data.

[0136] Optionally, the second processing submodule includes:

[0137] The first processing unit is used to assign values ​​to the logical relationships of roads in the topology layer of the raster map format according to the logical structure of roads in the map topology structure file.

[0138] The second processing unit is used to assign values ​​to the lane relationships in the topology layer of the rasterized map format based on the physical lane information in the map topology structure file, so as to obtain the scalar data of the target topology layer of the target map.

[0139] Optionally, the first processing unit includes:

[0140] The first processing subunit is used to assign values ​​to the predecessors and successors of roads in the topology layer of the rasterized map format according to the logical structure of roads in the map topology structure file.

[0141] Optionally, the second processing unit includes:

[0142] The second processing subunit is used to assign values ​​to the predecessor, successor, left neighbor, and right neighbor of the lanes in the topology layer of the rasterized map format based on the physical lane information in the map topology structure file.

[0143] Optionally, the third processing submodule includes:

[0144] The fifth processing submodule is used to assign values ​​to the geometric shape descriptions of lanes in the geometric layer of the rasterized map format based on the geometric shape expressions of lanes in N map tile files, so as to obtain the scalar data of the target geometric layer of the target map.

[0145] Optionally, the fifth processing submodule includes:

[0146] The third processing unit is used to assign values ​​to the left boundary, right boundary, and center line of the lanes in the geometric layer of the rasterized map format, respectively, based on the lane geometry data in the N map tile files, to obtain the scalar data of the target geometric layer of the target map.

[0147] The apparatus provided in this disclosure can convert a map into an intermediate format target map when performing map processing in a simulation system, and import the target map into the autonomous driving simulation system for autonomous driving simulation task processing; it enables faster import of various maps, thereby enabling the simulation system to support maps with various large data volumes, and the map can be loaded in blocks during operation, allowing the simulation system to run more lightweightly in the cloud.

[0148] It should be noted that the map processing device in the simulation system provided in the above embodiments is only an example of the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the map processing device in the simulation system provided in the above embodiments and the map processing method embodiments in the simulation system belong to the same concept, and the specific implementation process can be found in the method embodiments, which will not be repeated here.

[0149] The map processing device in the simulation system of this disclosure can be a virtual device, or a component, integrated circuit, or chip in a server or terminal. This device can be a mobile electronic device or a non-mobile electronic device. For example, mobile electronic devices can be mobile phones, tablets, laptops, PDAs, in-vehicle electronic devices, wearable devices, ultra-mobile personal computers (UMPCs), netbooks, or personal digital assistants (PDAs), etc., while non-mobile electronic devices can be servers, network-attached storage (NAS), personal computers (PCs), televisions (TVs), ATMs, or self-service machines, etc. This disclosure does not impose specific limitations.

[0150] The map processing device in the simulation system of this disclosure embodiment can be a device with an operating system. This operating system can be Android, iOS, or other possible operating systems; this disclosure embodiment does not specifically limit the specific operating system used.

[0151] The map processing device in the simulation system provided in this disclosure can achieve... Figures 1 to 4 The various processes implemented in the method implementation examples will not be described again here to avoid repetition.

[0152] Optionally, such as Figure 6 As shown, this disclosure also provides an electronic device 600, including a processor 601, a memory 602, and a program or instructions stored in the memory 602 and executable on the processor 601. When executed by the processor 601, the program or instructions implement the various processes of the map processing method embodiments in the above-described simulation system and achieve the same technical effects. To avoid repetition, further details are omitted here. It should be noted that the electronic devices in this disclosure include the aforementioned mobile electronic devices and non-mobile electronic devices.

[0153] Figure 7 A schematic diagram of the hardware structure of an electronic device to implement an embodiment of this disclosure.

[0154] The electronic device 700 includes, but is not limited to, components such as: radio frequency unit 701, network module 702, audio output unit 703, input unit 704, sensor 705, display unit 706, user input unit 707, interface unit 708, memory 709, and processor 710.

[0155] Those skilled in the art will understand that the electronic device 700 may also include a power supply (such as a battery) for supplying power to various components. The power supply may be logically connected to the processor 710 through a power management system, thereby enabling functions such as managing charging, discharging, and power consumption through the power management system. Figure 7 The electronic device structure shown does not constitute a limitation on the electronic device. The electronic device may include more or fewer components than shown, or combine certain components, or have different component arrangements, which will not be elaborated here.

[0156] It should be understood that, in this embodiment of the disclosure, the input unit 704 may include a graphics processing unit (GPU) 7041 and a microphone 7042. The GPU 7041 processes image data of still images or videos obtained by an image capture device (such as a camera) in video capture mode or image capture mode. The display unit 706 may include a display panel 7061, which may be configured in the form of a liquid crystal display, an organic light-emitting diode, etc. The user input unit 707 includes a touch panel 7071 and other input devices 7072. The touch panel 7071 is also called a touch screen. The touch panel 7071 may include a touch detection device and a touch controller. Other input devices 7072 may include, but are not limited to, physical keyboards, function keys (such as volume control buttons, power buttons, etc.), trackballs, mice, joysticks, etc., which will not be described in detail here. The memory 709 can be used to store software programs and various data, including but not limited to applications and operating systems. The processor 710 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, user interface, and applications, and the modem processor mainly handles wireless communication. It is understandable that the aforementioned modem processor may not be integrated into the processor 710.

[0157] This disclosure also provides a readable storage medium storing a program or instructions. When the program or instructions are executed by a processor, they implement the various processes of the map processing method embodiments in the above simulation system and achieve the same technical effect. To avoid repetition, further details are omitted here.

[0158] The processor is the processor in the electronic device described in the above embodiments. The readable storage medium includes computer-readable storage media, such as computer read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk.

[0159] This disclosure also provides a chip, which includes a processor and a communication interface. The communication interface and the processor are coupled. The processor is used to run programs or instructions to implement the various processes of the map processing method embodiments in the above simulation system and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0160] It should be understood that the chip mentioned in the embodiments of this disclosure may also be referred to as a system-on-a-chip, system chip, chip system, or system-on-a-chip, etc.

[0161] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments of this disclosure is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0162] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solutions of this disclosure, in essence or the part that contributes to the prior art, can be embodied in the form of a computer software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods of the various embodiments of this disclosure.

[0163] The embodiments of this disclosure have been described above with reference to the accompanying drawings. However, this disclosure is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of this disclosure without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of this disclosure.

Claims

1. A map processing method in a simulation system, characterized by, The method comprises the following steps: acquiring at least one format of a map; processing the map according to a rasterized map format to obtain a target map; the rasterized map format comprises a topology layer and a geometry layer; the topology layer comprises a logical structure of a road, and the road comprises a plurality of lanes; the geometry layer comprises a geometric shape description of the plurality of lanes; the topology layer and the geometry layer are both scalar data; introducing the target map into an automatic driving simulation system to process an automatic driving simulation task; wherein, processing the map according to the rasterized map format to obtain the target map comprises: acquiring a map topology structure file and N map slice files of the map; the map topology structure file comprises a logical structure of a road, and the map slice files comprise geometric shape data of lanes in the road, N being a positive integer; converting the map topology structure file into a topology layer in the rasterized map format to obtain target topology layer data of the target map; converting the N map slice files into a geometry layer in the rasterized map format to obtain target geometry layer data of the target map; obtaining the target map according to the target topology layer data and the target geometry layer data; wherein, converting the map topology structure file into the topology layer in the rasterized map format to obtain the target topology layer data of the target map comprises: assigning a logical relationship of a road in the topology layer in the rasterized map format according to a logical structure of the road in the map topology structure file; assigning a relationship of a lane in the topology layer in the rasterized map format according to information of a physical lane in the map topology structure file to obtain scalar data of a target topology layer of the target map.

2. The map processing method in a simulation system according to claim 1, wherein, assigning a logical relationship of a road in the topology layer in the rasterized map format according to a logical structure of the road in the map topology structure file comprises: assigning a predecessor of the road and a successor of the road in the topology layer in the rasterized map format according to the logical structure of the road in the map topology structure file.

3. The map processing method in a simulation system according to claim 1, wherein, assigning a relationship of a lane in the topology layer in the rasterized map format according to information of a physical lane in the map topology structure file comprises: assigning a predecessor, a successor, a left neighbor and a right neighbor of the lane in the topology layer in the rasterized map format according to the information of the physical lane in the map topology structure file.

4. The map processing method in a simulation system according to claim 1, wherein, converting the N map slice files into the geometry layer in the rasterized map format to obtain the target geometry layer data of the target map comprises: assigning a geometric shape description of a lane in the geometry layer in the rasterized map format according to a geometric shape expression of the lane in the N map slice files to obtain scalar data of a target geometry layer of the target map.

5. The map processing method in a simulation system according to claim 4, wherein, assigning a geometric shape description of a lane in the geometry layer in the rasterized map format according to a geometric shape expression of the lane in the N map slice files to obtain scalar data of a target geometry layer of the target map comprises: The geometric shape data of the lanes in the N map fragment files are used to assign values ​​to the left boundary, right boundary, and center line of the lanes in the geometric layer of the rasterized map format, respectively, to obtain the scalar data of the target geometric layer of the target map.

6. A map processing apparatus in a simulation system, characterized by comprising: include: The acquisition module is used to acquire maps in at least one format; The processing module is used to process the map according to the raster map format to obtain the target map; The rasterized map format includes a topology layer and a geometry layer; the topology layer includes the logical structure of roads, and the roads include multiple lanes; the geometry layer includes geometric descriptions of the multiple lanes; the target map is imported into an autonomous driving simulation system for autonomous driving simulation task processing; wherein, processing the map according to the rasterized map format to obtain the target map includes: obtaining the map topology structure file and N map tile files; the map topology structure file includes the logical structure of roads, and the map tile files include the geometric shape data of the lanes in the roads, and N positive integers; converting the map topology structure file into the topology layer in the rasterized map format to obtain the target topology of the target map. Layer data; converting the N map tile files into geometric layers in the rasterized map format to obtain target geometric layer data of the target map; obtaining the target map based on the target topology layer data and the target geometric layer data; wherein, converting the map topology structure file into a topology layer in the rasterized map format to obtain target topology layer data of the target map includes: assigning values ​​to the logical relationships of roads in the topology layer of the rasterized map format according to the logical structure of roads in the map topology structure file; assigning values ​​to the relationships of lanes in the topology layer of the rasterized map format according to the physical lane information in the map topology structure file, to obtain scalar data of the target topology layer of the target map.

7. An electronic device, comprising: It includes a processor, a memory, and a program or instructions stored in the memory and executable on the processor, wherein the program or instructions, when executed by the processor, implement the steps of the map processing method in the simulation system as described in any one of claims 1 to 5.

8. A readable storage medium, characterized by, The readable storage medium stores a program or instructions that, when executed by a processor, implement the steps of the map processing method in the simulation system as described in any one of claims 1 to 5.

Images