Mapping method and device, control equipment, driving equipment and storage medium
By acquiring and combining map construction data of different sections, combining loop constraints and pose optimization algorithms, the problem of low map construction accuracy caused by GPS abnormalities in autonomous driving is solved, and the mapping effect in special scenarios such as tunnel sections is improved.
Patent Information
- Application Number
- CN202310621896.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-05-30
- Publication Date
- 2024-12-03
AI Technical Summary
In autonomous driving scenarios, especially in special scenarios such as tunnels, due to GPS abnormalities, traditional map construction solutions are difficult to ensure the establishment of high-precision maps, resulting in poor map construction results.
By obtaining the map construction data of the driving equipment before the starting point, after the end point of the target section, and the intersection section containing the target section, it is combined to build the map, and using loop constraints and pose optimization algorithms to determine the map of the target section.
It effectively improves the problem of low map construction accuracy caused by GPS abnormalities, improves the mapping effect in special scenarios such as tunnel sections, and ensures high accuracy and continuity of the map.
Smart Images

Figure CN119063745A_ABST
Abstract
Description
Technical Field
[0001] The embodiments of the present application relate to the field of data processing technology, and in particular to a mapping method, apparatus, control device, driving device, and storage medium. Background Art
[0002] The field of autonomous driving relies on high-precision maps for navigation planning. The establishment of high-precision maps relies on a variety of sensors such as lidar, cameras, IMU, wheel speed meters, GPS, etc. to obtain raw data, and obtains high-precision maps (for example, point cloud maps) by post-processing the raw data. However, the actual autonomous driving scenarios are more complex, including open roads in cities, viaducts, high-rise building occlusions, and tunnels. Among them, some special scenarios (such as tunnel scenarios) are more challenging for mapping due to GPS anomalies (such as GPS failure), resulting in poor mapping results of traditional mapping solutions. Therefore, it is necessary to propose a new mapping solution for these special scenarios to improve the mapping effect. Summary of the invention
[0003] In view of this, embodiments of the present application provide a mapping method, apparatus, control device, driving device and storage medium to at least partially solve the above problems.
[0004] According to a first aspect of an embodiment of the present application, a mapping method is provided, including:
[0005] Acquire first mapping data collected when the driving device is traveling on a first road section, wherein the first road section is a road section before a starting point of a target road section;
[0006] Acquire second mapping data collected when the driving device is traveling on a second road section, wherein the second road section is a road section after an end point of the target road section;
[0007] Acquire third mapping data collected when the driving device is traveling on a third road section including the target road section, wherein the first road section and the second road section all have intersection sections with the third road section;
[0008] A map is constructed by merging the first mapping data, the second mapping data, and the third mapping data to determine a map corresponding to the target road section.
[0009] In some optional embodiments, the merging and mapping according to the first mapping data, the second mapping data, and the third mapping data to determine a map corresponding to the target road section includes:
[0010] Determine a first intersection section between the first section and the third section, and a second intersection section between the second section and the third section;
[0011] Establishing a first loop constraint between the first road section and the third road section according to the first mapping data and the third mapping data corresponding to the first intersection road section;
[0012] Establishing a second loop constraint between the third road segment and the second road segment according to the third mapping data and the second mapping data corresponding to the second intersection road segment;
[0013] A map corresponding to the target road section is determined according to the established first loop constraint and second loop constraint, the first mapping data, the second mapping data, and the third mapping data.
[0014] In some optional embodiments, the establishing a first loop constraint between the first road section and the third road section according to the first mapping data and the third mapping data corresponding to the first intersection road section includes: determining a key mapping data frame that matches the first mapping data and the third mapping data from the first mapping data and the third mapping data corresponding to the first intersection road section; establishing the first loop constraint for the first road section and the third road section according to the loop relative poses between the matching key mapping data frames;
[0015] The establishing of a second loop constraint between the third road section and the second road section according to the third mapping data and the second mapping data corresponding to the second intersection road section comprises: determining, from the third mapping data and the second mapping data corresponding to the second intersection road section, a key mapping data frame that matches the third mapping data and the second mapping data; and establishing the second loop constraint for the third road section and the second road section according to the loop relative poses between the matching key mapping data frames.
[0016] In some optional embodiments, the first mapping data, the second mapping data, and the third mapping data all include point cloud data, and the key mapping data frame is a point cloud frame;
[0017] The loop-back relative poses between the matched key mapping data frames are obtained by a laser matching algorithm.
[0018] In some optional embodiments, determining a map corresponding to the target road section according to the established first loop constraint and second loop constraint, the first mapping data, the second mapping data, and the third mapping data includes:
[0019] According to the results of the first loop constraint and the second loop constraint and the third mapping data, optimizing the driving trajectory of the driving device on the third road section to obtain an optimized driving trajectory;
[0020] A map corresponding to the target road section is determined according to the optimized driving trajectory, the first mapping data, the second mapping data, and the third mapping data.
[0021] In some optional embodiments, the third mapping data includes the GPS positioning track, radar track and DR track of the driving device;
[0022] The optimizing the driving trajectory of the driving device on the third road section according to the result of the first loop constraint and the second loop constraint and the third mapping data to obtain an optimized driving trajectory includes:
[0023] Determining, according to the GPS positioning trajectory in the third mapping data, a plurality of positioning postures at a plurality of different positions of the driving device when traveling on a third road section;
[0024] Determining, according to the radar tracks in the third mapping data, a plurality of radar relative postures at a plurality of different positions of the driving device when the driving device is traveling on a third road section;
[0025] Determining, according to the DR tracks in the third mapping data, a plurality of DR relative postures at a plurality of different positions of the driving device when traveling on a third road section;
[0026] The driving trajectory of the driving device on the third road section is optimized according to the loop relative postures in the first loop constraint and the second loop constraint, the multiple positioning postures, the multiple radar relative postures, and the multiple DR relative postures to obtain the optimized driving trajectory.
[0027] In some optional embodiments, the third mapping data includes point cloud data;
[0028] The determining a map corresponding to the target road section according to the optimized driving trajectory, the first mapping data, the second mapping data, and the third mapping data includes:
[0029] The point cloud data in the third mapping data is transformed to the optimized driving trajectory through posture, and the optimized driving trajectory, the point cloud data in the third mapping data transformed to the optimized driving trajectory, the first submap determined according to the first mapping data, and the second submap determined according to the second mapping data are merged to determine a map corresponding to the target road section.
[0030] In some optional embodiments, the target section is a target tunnel section.
[0031] According to a second aspect of an embodiment of the present application, a mapping device is provided, including:
[0032] A first acquisition module is used to acquire first mapping data collected when the driving device is traveling on a first road section, wherein the first road section is a road section before the starting point of the target road section;
[0033] A second acquisition module is used to acquire second mapping data collected when the driving device is traveling on a second road section, wherein the second road section is a road section after the end point of the target road section;
[0034] A third acquisition module is used to acquire third mapping data collected when the driving device is traveling on a third road section including the target road section, wherein the first road section and the second road section all have intersection sections with the third road section;
[0035] The merging mapping module is used to merge and build a map according to the first mapping data, the second mapping data and the third mapping data to determine a map corresponding to the target road section.
[0036] According to a third aspect of an embodiment of the present application, a control device is provided, characterized in that it includes: a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus; the memory is used to store a computer program; and the processor is used to execute the method described in the first aspect above by running the computer program stored in the memory.
[0037] According to a fourth aspect of an embodiment of the present application, a driving device is provided, comprising: the control device provided in the aforementioned third aspect.
[0038] According to a fifth aspect of an embodiment of the present application, a computer storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the method described in the first aspect is implemented.
[0039] According to a sixth aspect of an embodiment of the present application, a computer program product is provided, including a computer program, wherein the computer program implements the method described in the first aspect when executed by a processor.
[0040] The mapping solution provided in the embodiment of the present application can obtain first mapping data collected when the driving device is traveling on a first road section, wherein the first road section is the section before the starting point of the target road section; obtain second mapping data collected when the driving device is traveling on a second road section, wherein the second road section is the section after the end point of the target road section; obtain third mapping data collected when the driving device is traveling on a third road section including the target road section, wherein the first road section, the second road section and the third road section all have intersection sections; and then merge and map based on the first mapping data, the second mapping data and the third mapping data to determine the map corresponding to the target road section. Therefore, the present application combines the first mapping data, the second mapping data and the third mapping data for merging and mapping to determine the map corresponding to the target road section, which can effectively improve the problem of low accuracy when mapping the target road section due to GPS abnormality of the target road section, can adapt to mapping requirements in special scenarios including but not limited to tunnel sections, and effectively improve the mapping effect. BRIEF DESCRIPTION OF THE DRAWINGS
[0041] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the embodiments of the present application. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.
[0042] Figure 1 A flowchart of the steps of an exemplary mapping method in the present application is shown.
[0043] Figure 2 A schematic diagram of the first section, the second section and the third section in the present application is shown.
[0044] Figure 3 An optional sub-step flow chart of step S108 in the present application is shown.
[0045] Figure 4 An optional sub-step flowchart of step S1082 in the present application is shown.
[0046] Figure 5 An optional sub-step flowchart of step S1083 in the present application is shown.
[0047] Figure 6 An optional sub-step flowchart of step S1084 in the present application is shown.
[0048] Figure 7 An optional sub-step flowchart of step S1084A in the present application is shown.
[0049] Figure 8A flowchart of the steps of another exemplary mapping method in the present application is shown.
[0050] Fig. 9 A structural block diagram of an exemplary mapping device in the present application is shown.
[0051] Fig.10 A structural block diagram of an exemplary control device in the present application is shown.
[0052] Fig.11 A structural block diagram of an exemplary driving device in the present application is shown. DETAILED DESCRIPTION
[0053] In order to make those skilled in the art better understand the technical solutions in the embodiments of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field should belong to the scope of protection of the embodiments of the present application. It should be understood that the various steps recorded in the method implementation mode of the present disclosure can be performed in different orders and / or performed in parallel. In addition, the method implementation mode may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.
[0054] The term "including" and its variations used in this document are open inclusions, that is, "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one other embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the description below. It should be noted that the concepts of "first", "second", etc. mentioned in this application are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units. It should be noted that the modifications of "one" and "multiple" mentioned in this application are illustrative rather than restrictive. Those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".
[0055] The specific implementation of the embodiment of the present application is further explained below in conjunction with the accompanying drawings of the embodiment of the present application.
[0056] According to a first aspect of the present application, a mapping method is provided. Figure 1 A flowchart of an exemplary mapping method in this application is shown. Figure 1As shown, the mapping method includes steps S102, S104, S106 and S108, specifically:
[0057] S102: Acquire first mapping data collected when the driving device is traveling on a first road section, wherein the first road section is a road section before a starting point of a target road section.
[0058] The mapping method in the present application can be applied to the mapping of any target road section, for example, it can be applied to the mapping of sections with GPS anomalies, and it has a good technical effect in improving the mapping accuracy of sections with GPS anomalies. For example, the target road section may include an open urban section, a tunnel section, a section blocked by high-rise buildings, an elevated bridge section, and the like. In an implementation scenario in the present application, the target road section may be a target tunnel section, and the mapping method is applied to map the target tunnel section, which can effectively improve the mapping accuracy of the target tunnel section. To facilitate the description of the technical solution of the present application, the target road section is taken as an example as follows.
[0059] In the present application, the driving device is a driving device with an automatic driving function. That is, the driving device may include an automatic driving mode, and when the driving device enters the automatic driving mode, automatic driving can be achieved. The driving device may be a fully automatic driving device, or a semi-automatic driving device that includes both a manual driving mode and an automatic driving mode. For example, the driving device may include an automatic driving vehicle, that is, a vehicle with an automatic driving function.
[0060] Optionally, the driving equipment in the embodiments of the present application may include vehicles with automatic driving functions (including vehicles with passenger functions (such as cars, buses, large buses, minibuses, etc.), vehicles with cargo functions (such as ordinary trucks, vans, trailers, closed trucks, tank trucks, flatbed trucks, container trucks, dump trucks, trucks with special structures), special vehicles (such as logistics distribution vehicles, automatic guided transport vehicles AGV, patrol cars, cranes, cranes, excavators, bulldozers, forklifts, rollers, loaders, off-road engineering vehicles, armored engineering vehicles, sewage treatment vehicles, sanitation vehicles, vacuum trucks, floor washing vehicles, sprinkler trucks, sweeping robots, food delivery robots, shopping guide robots, lawn mowers, golf carts, etc.), vehicles with entertainment functions (such as entertainment vehicles, amusement park automatic driving devices, balance cars, etc.), rescue vehicles (such as fire trucks, ambulances, power repair vehicles, engineering rescue vehicles, etc.)) and robots (such as sweeping robots, food delivery robots, etc.), etc.
[0061] In this application, the driving device may be provided with one or more sensors for sensing the environment information and the driving device information itself (such as driving status). For example, the sensor may include an image acquisition device (such as a camera, etc.), a point cloud acquisition device (such as a laser radar, etc.), etc. The sensor may also include a millimeter wave radar, an ultrasonic radar, an inertial measurement unit, a wheel speed meter, etc., which are not limited here. The data collected by these sensors can be used by the driving device to achieve the purposes of perception, positioning, planning, control, etc. Through the data collected by these sensors, the mapping data used for mapping can be determined.
[0062] Optionally, the mapping data may include any data used for mapping, which is not specifically limited in this application, and may include point cloud data, GPS positioning trajectory of the driving device, radar trajectory, and DR trajectory. Among them, the point cloud data can be obtained by collecting the surrounding environment of the driving device when the driving device is driving through the laser radar on the driving device; the GPS positioning trajectory can be the driving trajectory obtained by the GPS positioning of the driving device; the radar trajectory can be the driving trajectory calculated by the data collected by the laser radar on the driving device; the DR (Dead Reckoning) trajectory can be calculated by data collected by sensors such as the inertial measurement unit (IMU) and the wheel speed meter. Correspondingly, the first mapping data may include the point cloud data, the GPS positioning trajectory, the radar trajectory, and the DR trajectory of the driving device obtained when the driving device is driving on the first road section.
[0063] In order to improve the accuracy of mapping the target road section (eg, the target tunnel road section), the GPS positioning data of the first road section may be kept accurate.
[0064] Optionally, in this application, after obtaining the first mapping data collected when the driving device is traveling on the first road section, the first road section can be mapped according to the first mapping data to determine the first sub-map. The first sub-map constructed is the high-precision map corresponding to the first road section. The mapping method used here can be any method, and is not particularly limited in this application. The first sub-map will be explained below and will not be repeated here.
[0065] S104: Acquire second mapping data collected when the driving device travels on a second road section, wherein the second road section is a road section after an end point of the target road section.
[0066] As mentioned above, the mapping data may include any data used for mapping, and this application does not impose any specific restrictions, for example, it may include point cloud data, GPS positioning track of the driving device, radar track and DR track. Correspondingly, the second mapping data may include point cloud data, GPS positioning track of the driving device, radar track and DR track, etc., obtained when the driving device is traveling on the second road section.
[0067] To improve the accuracy of mapping the target road section (eg, the target tunnel road section), the GPS positioning data of the second road section may be kept accurate.
[0068] Optionally, in this application, after obtaining the second mapping data collected when the driving device is traveling on the second road section, the second road section can be mapped according to the second mapping data to determine the second sub-map. The constructed second sub-map is the high-precision map corresponding to the second road section. The mapping method used here can be any method, and is not particularly limited in this application. The second sub-map will be explained below and will not be repeated here.
[0069] S106: Acquire third mapping data collected when the driving device travels on a third road section including the target road section, wherein the first road section, the second road section and the third road section all have intersection sections.
[0070] As mentioned above, the mapping data may include any data used for mapping, and this application does not impose specific restrictions. For example, it may include point cloud data, GPS positioning trajectory of the driving device, radar trajectory and DR trajectory. Correspondingly, the third mapping data may include point cloud data, GPS positioning trajectory, radar trajectory and DR trajectory of the driving device obtained when the driving device is traveling on the third road section. It should be understood that the GPS positioning data of the driving device in the target road section (such as the target tunnel section) may be abnormal, so the mapping accuracy and mapping effect are improved by the mapping method in this application.
[0071] Figure 2 The schematic diagram of the first section, the second section and the third section in this application is shown. Figure 2 It can be seen that the first section is the section before the starting point of the target section, the second section is the section after the end point of the target section, the third section includes the target section, and there are intersection sections between the first section, the second section and the third section. The intersection section of the first section and the third section is the first intersection section, and the intersection section of the second section and the third section is the second intersection section.
[0072] Reference Figure 2For example, in the present application, the first mapping data, the second mapping data and the third mapping data can be obtained in the following manner: first, the driving device starts driving from the starting point of the first road section and collects mapping data, drives to the end point of the first road section (that is, the end point of the first intersection section), and stores this part of the collected mapping data as the first mapping data, which can be obtained when needed; then, the driving device starts driving from the starting point of the second road section (that is, the starting point of the second intersection section) and collects mapping data, drives to the end point of the second road section, and stores this part of the collected mapping data as the second mapping data, which can be obtained when needed; finally, the driving device returns to the starting point of the third road section (that is, the starting point of the first intersection section) to start driving and collect mapping data, drives to the end point of the third road section (that is, the end point of the second intersection section), and stores this part of the collected mapping data as the third mapping data, which can be obtained when needed. It is easy to understand that here, the first intersection section and the second intersection section both collected mapping data twice, the mapping data collected for the first intersection section are respectively located in the first mapping data and the third mapping data, while the mapping data collected for the second intersection section are respectively located in the second mapping data and the third mapping data.
[0073] It should be understood that the starting point of the first section and the ending point of the second section are not limited in the present application and can be selected as needed. Figure 2 The starting point of the first section and the end point of the second section are not specifically marked. Optionally, the lengths of the first intersection section and the second intersection section can be selected as needed, for example, 50m to 100m can be selected; in addition, the length of the first intersection section and the length of the second intersection section can be the same or different, and no limitation is imposed on the comparison in this application.
[0074] S108: Merge and construct a map according to the first mapping data, the second mapping data, and the third mapping data to determine a map corresponding to the target road section.
[0075] In the present application, through the above steps S102 to S108, since the first mapping data collected by the driving device when driving on the first road section can be obtained, wherein the first road section is the section before the starting point of the target road section; the second mapping data collected by the driving device when driving on the second road section is obtained, wherein the second road section is the section after the end point of the target road section; the third mapping data collected by the driving device when driving on the third road section including the target road section is obtained, wherein the first road section, the second road section and the third road section all have intersection sections; and then the first mapping data, the second mapping data and the third mapping data are merged and mapped to determine the map corresponding to the target road section. Therefore, the present application combines the first mapping data, the second mapping data and the third mapping data for merging and mapping to determine the map corresponding to the target road section, which can effectively improve the problem of low accuracy when mapping the target road section due to GPS abnormality of the target road section, and can adapt to the mapping requirements in special scenarios including but not limited to tunnel sections, and effectively improve the mapping effect.
[0076] The specific implementation of step S108 is not limited in this application. In some optional embodiments, refer to Figure 3 In the flowchart shown, step S108 includes sub-steps S1081, S1082, S1083 and S1084, specifically:
[0077] S1081: Determine a first intersection section between the first road section and the third road section, and a second intersection section between the second road section and the third road section.
[0078] As described above, the intersection of the first section and the third section is the first intersection section, and the intersection of the second section and the third section is the second intersection section. Here, they can be determined as needed and will not be elaborated here.
[0079] S1082: Establishing a first loop constraint between the first road segment and the third road segment according to the first mapping data and the third mapping data corresponding to the first intersection road segment.
[0080] As mentioned above, mapping data is collected twice for both the first intersection section and the second intersection section. The mapping data collected for the first intersection section are respectively located in the first mapping data and the third mapping data, while the mapping data collected for the second intersection section are respectively located in the second mapping data and the third mapping data. Therefore, the first mapping data and the third mapping data corresponding to the first intersection section can be determined, and the first mapping data and the third mapping data corresponding to the first intersection section can be used to establish the first loop constraint between the first section and the third section.
[0081] The specific method of establishing the first loop constraint is not limited in the present application. In some optional embodiments, refer to Figure 4In the flowchart in FIG. 1 , step S1082 includes sub-steps S1082A and S1082B, specifically:
[0082] S1082A: Determine, from the first mapping data and the third mapping data corresponding to the first intersection road section, a key mapping data frame that matches the first mapping data and the third mapping data;
[0083] S1082B: Establishing the first loop constraint for the first road segment and the third road segment according to the loop relative poses between the matched key mapping data frames.
[0084] Based on this, the present application can effectively and accurately achieve the purpose of establishing a first loop constraint between the first road segment and the third road segment based on the first mapping data and the third mapping data corresponding to the first intersection road segment, so as to facilitate subsequent data processing according to the first loop constraint.
[0085] This application does not limit the type of key mapping data frames, for example, it can be a point cloud frame or an image frame.
[0086] In some optional embodiments, the first mapping data, the second mapping data, and the third mapping data all include point cloud data, and the key mapping data frame is a point cloud frame; the relative loop position between the matching key mapping data frames is obtained by a laser matching algorithm. Based on this, the present application can accurately determine the relative loop position between the matching key mapping data frames to establish a first loop constraint for the first road section and the third road section.
[0087] It should be noted that the key mapping data frames that match the first mapping data and the third mapping data refer to two frames of key mapping data frames (two frames can be a group) collected at the same position at different times (different times means when the driving device is traveling on the first section and the third section respectively) in the first mapping data and the third mapping data. For example, taking the key mapping data frame as a point cloud frame as an example, for example, when the driving device is traveling in the first intersection section, it passes through 1000 positions (only as an example), and each of the 1000 positions collects a frame of point cloud frame. Then, the first mapping data corresponding to the first intersection section may include 1000 frames of point cloud frames, and the third mapping data corresponding to the first intersection section may also include 1000 frames of point cloud frames. There are a total of 1000 sets of matching key mapping data frames (point cloud frames). It should be understood that this example does not serve as any limitation to the present application.
[0088] In the present application, any laser matching algorithm can be used to obtain the relative pose of the loop between the matching key mapping data frames. For example, the NDT (Normal Distributions Transform) algorithm can be used to achieve this, or other algorithms can be used to achieve this.
[0089] Optionally, in sub-step S1082, more loop constraints (ie, first loop constraints) may be established to ensure the continuity of the driving trajectory of the driving device in the first road section and the third road section.
[0090] S1083: Establishing a second loop constraint between the third road segment and the second road segment according to the third mapping data and the second mapping data corresponding to the second intersection road segment.
[0091] Similar to sub-step S1082, the third mapping data and the second mapping data corresponding to the second intersection section may be determined, and the second loop constraint between the second section and the third section may be established using the third mapping data and the second mapping data corresponding to the second intersection section.
[0092] The specific method of establishing the second loop constraint is not limited in the present application. In some optional embodiments, refer to Figure 5 In the flowchart in FIG. 1 , step S1083 includes sub-steps S1083A and S1083B, specifically:
[0093] S1083A: Determine, from the third mapping data and the second mapping data corresponding to the second intersection road segment, a key mapping data frame that matches the third mapping data and the second mapping data;
[0094] S1083B: Establishing the second loop constraint for the third road segment and the second road segment according to the loop relative poses between the matched key mapping data frames.
[0095] Based on this, the present application can effectively and accurately achieve the purpose of establishing a second loop constraint between the second road segment and the third road segment based on the third mapping data and the second mapping data corresponding to the second intersection road segment, so as to facilitate subsequent data processing according to the second loop constraint.
[0096] Similar to sub-step S1082, the present application does not limit the type of the key mapping data frame, for example, it can be a point cloud frame or an image frame.
[0097] In some optional embodiments, the first mapping data, the second mapping data, and the third mapping data all include point cloud data, and the key mapping data frame is a point cloud frame; the relative loop position between the matching key mapping data frames is obtained by a laser matching algorithm. Based on this, the present application can accurately determine the relative loop position between the matching key mapping data frames to establish a second loop constraint for the second road segment and the third road segment.
[0098] It should be noted that, similar to the key mapping data frames that match the first mapping data and the third mapping data mentioned above, the key mapping data frames that match the third mapping data and the second mapping data refer to two frames of key mapping data frames (two frames can be a group) collected at the same position at different times in the third mapping data and the second mapping data (different times means when the driving device is traveling on the third road section and the second road section respectively). For example, taking the key mapping data frame as a point cloud frame as an example, for example, when the driving device is traveling in the second intersection section, it passes through 1000 positions (only as an example), and each of the 1000 positions collects a frame of point cloud frame. Then, the third mapping data corresponding to the second intersection section may include 1000 frames of point cloud frames, and the second mapping data corresponding to the second intersection section may also include 1000 frames of point cloud frames. There are a total of 1000 sets of matching key mapping data frames (point cloud frames). It should be understood that this example does not serve as any limitation to the present application.
[0099] In the present application, any laser matching algorithm can be used to obtain the relative pose of the loop between the matching key mapping data frames. For example, the NDT (Normal Distributions Transform) algorithm can be used to achieve this, or other algorithms can be used to achieve this.
[0100] Optionally, more loop constraints (ie, second loop constraints) may be established in sub-step S1083 to ensure the continuity of the driving trajectory of the driving device in the third road section and the second road section.
[0101] S1084: Determine a map corresponding to the target road section according to the first loop constraint and the second loop constraint that are established, the first mapping data, the second mapping data, and the third mapping data.
[0102] Based on this, the present application, through the optional implementation methods of the above-mentioned sub-steps S1081 to S1084, can more conveniently and accurately merge the first mapping data, the second mapping data and the third mapping data to determine the map corresponding to the target road section, which can effectively improve the problem of low accuracy when mapping the target road section due to GPS abnormalities in the target road section, and can adapt to the mapping needs in special scenarios including but not limited to tunnel sections, and effectively improve the mapping effect.
[0103] The specific implementation of sub-step S1084 is not specifically limited in this application. In some optional embodiments, refer to Figure 6 In the flowchart shown, sub-step S1084 includes sub-steps S1084A and S1084B, specifically:
[0104] S1084A: Optimizing the driving trajectory of the driving device on the third road section according to the results of the first loop constraint and the second loop constraint and the third mapping data to obtain an optimized driving trajectory;
[0105] S1084B: Determine a map corresponding to the target road section according to the optimized driving trajectory, the first mapping data, the second mapping data, and the third mapping data.
[0106] Based on this, the present application can more conveniently and accurately determine the map corresponding to the target road section through the optional implementation methods of the above-mentioned sub-steps S1084A~S1084B, can effectively improve the problem of low accuracy when mapping the target road section due to GPS abnormalities in the target road section, can adapt to the mapping needs in special scenarios including but not limited to tunnel sections, and effectively improve the mapping effect.
[0107] Step S1084A in the present application is equivalent to calculating the optimal trajectory of the driving device on the third road section.
[0108] Optionally, in the present application, sub-step S1084A optimizes the driving trajectory of the driving device on the third road section, which can be implemented by a back-end optimization algorithm. Back-end trajectory optimization is a state estimation problem, and the optimal trajectory can be calculated from several driving trajectory data sources, such as the third mapping data (for example, the GPS positioning trajectory, radar trajectory, DR trajectory of the driving device included in the third mapping data), the results of the first loop constraint and the second loop constraint, etc.
[0109] The specific implementation of sub-step S1084A is not specifically limited in this application. In some optional embodiments, the third mapping data includes the GPS positioning track, radar track and DR track of the driving device. Figure 7 In the flowchart shown, sub-step S1084A includes sub-steps S201, S202, S203 and S204, specifically:
[0110] S201: Determine, based on the GPS positioning trajectory in the third mapping data, a plurality of positioning postures at a plurality of different positions of the driving device when the driving device is traveling on a third road section.
[0111] As described above, the GPS positioning trajectory can be a driving trajectory obtained by GPS positioning of the driving device. The positioning postures of multiple different positions of the driving device when driving on the third road section can be determined based on the GPS positioning trajectory in the third mapping data. The positioning posture in this application is an absolute posture.
[0112] For the convenience of representation in this application, the positioning posture of the driving device at the k-time position can be expressed as X k,GPS, and X k,GPs ∈SE(3), that is, X k,GPS It can be represented using a Euclidean transformation matrix.
[0113] S202: Determine, based on the radar tracks in the third mapping data, a plurality of radar relative postures at a plurality of different positions of the driving device when the driving device is traveling on a third road section.
[0114] As described above, the radar trajectory may be a driving trajectory calculated using data collected by a laser radar on the driving device. Based on the radar trajectory in the third mapping data, multiple radar relative postures at multiple different positions of the driving device when driving on the third road section may be determined.
[0115] For the convenience of representation in this application, the relative radar posture of the driving device at the k-th time can be expressed as X k-1,k,Lidar , and X k-1,k,Lidar ∈SE(3), that is, X k-1,k,Lidar It can be represented using a Euclidean transformation matrix.
[0116] S203: Determine, according to the DR trajectory in the third mapping data, a plurality of DR relative postures at a plurality of different positions of the driving device when traveling on a third road section.
[0117] As mentioned above, the DR (Dead Reckoning) trajectory can be calculated using data collected by sensors such as an inertial measurement unit (IMU) and a wheel speed meter. Based on the DR trajectory in the third mapping data, multiple DR relative postures at multiple different positions of the driving device when traveling on the third road section can be determined.
[0118] For the convenience of representation in this application, the DR relative position of the driving device at the kth moment can be expressed as X k-1,k,DR , and X k-1,k,DR ∈SE(3), that is, X k-1,k,DR It can be represented using a Euclidean transformation matrix.
[0119] S204: Optimize the driving trajectory of the driving device on the third road section according to the loop relative postures in the first loop constraint and the second loop constraint, the multiple positioning postures, the multiple radar relative postures, and the multiple DR relative postures to obtain the optimized driving trajectory.
[0120] Based on this, the present application can conveniently and accurately optimize the driving trajectory of the driving device on the third road section through the optional implementation of sub-steps S201 to S204 to obtain an optimized driving trajectory, so as to improve the accuracy of determining the map corresponding to the target road section.
[0121] Optionally, the multiple loop relative postures in the first loop constraint and the second loop constraint are obtained in the above steps, and the multiple loop relative postures can be directly obtained. For the convenience of representation in this application, the loop relative posture of the driving device at the kth position can be expressed as X k-1,k,Loop , and X k-1,k,Loop ∈SE(3), that is, X k-1,k,Loop It can be represented using a Euclidean transformation matrix.
[0122] Optionally, in sub-step S204, the driving trajectory of the driving device on the third road section can be optimized based on the loop relative postures in the first loop constraint and the second loop constraint, multiple positioning postures, multiple radar relative postures, and multiple DR relative postures to obtain an optimized driving trajectory.
[0123] Optionally, in sub-step S204, the driving trajectory of the driving device on the third road section can be back-end optimized through a graph optimization algorithm based on the first loop constraint and the loop relative postures in the second loop constraint, multiple positioning postures, multiple radar relative postures, and multiple DR relative postures to obtain an optimized driving trajectory.
[0124] Optionally, the entire problem of back-end optimization of the driving trajectory of the driving device on the third road section can be abstracted into a Pose Graph optimization problem. This Pose Graph optimization problem is a least squares problem. k-1,k,Loop , multiple positioning poses X k,GPS 、Relative posture of multiple radars X k-1,k,Lidar , multiple DR relative poses X k-1,k,DR Optimize as the edge of the Pose Graph.
[0125] Optionally, the expression of the Pose Graph optimization problem can be in the following form:
[0126]
[0127] Among them, ρ represents the robust kernel function, Indicates that multiple positioning poses X k,GPS The error of the calculated GPS positioning trajectory, Represents the relative pose X through multiple DRs k-1,k,DR The error of the calculated DR trajectory, Indicates the relative position X of multiple radars k-1,k,Lidar The error of the calculated radar track, Represents the relative pose X through multiple loop closures k-1,,LoopThe error of the calculated loop constraint. The above-mentioned entire Pose Graph optimization problem is equivalent to finding the minimum Gaussian covariance of various errors to obtain the optimized driving trajectory corresponding to the minimum value. In this application, through the above method, a good trajectory estimation can still be given when there are some outliers in the trajectory data, so as to optimize the driving trajectory of the driving device on the third road section to obtain the optimized driving trajectory.
[0128] The specific implementation method of sub-step S1084B is not specifically limited in the present application. In some optional embodiments, the third mapping data includes point cloud data, and the sub-step S1084B includes: transforming the point cloud data in the third mapping data to the optimized driving trajectory through posture, and merging the optimized driving trajectory, the point cloud data in the third mapping data transformed to the optimized driving trajectory, the first sub-map determined according to the first mapping data, and the second sub-map determined according to the second mapping data to determine the map corresponding to the target road section.
[0129] Based on this, the present application can more conveniently and accurately determine the map corresponding to the target section according to the optimized driving trajectory, the first mapping data, the second mapping data and the third mapping data in this way, and can effectively improve the problem of low accuracy when mapping the target section due to GPS abnormalities in the target section. It can adapt to the mapping needs in special scenarios including but not limited to tunnel sections, and effectively improve the mapping effect.
[0130] In this application, the first submap determined according to the first mapping data is a map corresponding to the first road section, and the second submap determined according to the second mapping data is a map corresponding to the second road section. The first submap and the second submap can be implemented in any manner, and this application does not limit this.
[0131] In the present application, the first submap is determined according to the first mapping data, and the second submap is determined according to the second mapping data, which can be completed before mapping the third road section. Then, the first submap and the second submap are fixed, and the third road section including the target road section is mapped on the basis of the fixed first submap and the second submap. Since the GPS status of the first road section and the second road section is good, the driving trajectory of the driving device in the first submap and the second submap (for example, the first fused trajectory and the second fused trajectory mentioned below) is well matched with its GPS positioning trajectory. Finally, the map corresponding to the target road section obtained by merging the first submap and the second submap has good mapping accuracy and effect.
[0132] Optionally, the first mapping data includes point cloud data, and GPS positioning trajectory, radar trajectory, and DR trajectory of the driving device; determining the first sub-map based on the first mapping data may include: determining the optimal first fused trajectory of the driving device in the first road section based on the GPS positioning trajectory, radar trajectory, and DR trajectory in the first mapping data, and then transforming the point cloud data in the first mapping data to the first fused trajectory through posture transformation to obtain the first sub-map.
[0133] Optionally, the second mapping data includes point cloud data, and a GPS positioning trajectory, a radar trajectory, and a DR trajectory of the driving device; determining the second sub-map based on the second mapping data may include: determining an optimal second fused trajectory of the driving device in the second road section based on the GPS positioning trajectory, the radar trajectory, and the DR trajectory in the second mapping data, and then transforming the point cloud data in the second mapping data to the second fused trajectory through posture transformation to obtain the second sub-map.
[0134] Optionally, "merging the optimized driving trajectory, the point cloud data in the third mapping data transformed to the optimized driving trajectory, the first submap determined according to the first mapping data, and the second submap determined according to the second mapping data to determine the map corresponding to the target road section" may include: keeping the first fused trajectory in the first submap and the second fused trajectory in the second submap fixed, merging the optimized driving trajectory into the first fused trajectory and the second fused trajectory, and then merging the point cloud data in the third mapping data transformed to the optimized driving trajectory, the point cloud data in the first submap, and the point cloud data in the second submap to determine the map corresponding to the target road section.
[0135] The optimized driving trajectory is merged into the first fused trajectory and the second fused trajectory. The first intersection section and the second intersection section can be used to ensure the continuity among the merged first fused trajectory, the optimized driving trajectory (i.e., the optimal trajectory of the driving device on the third section), and the second fused trajectory.
[0136] It is understandable that the above description of the mapping method is only an exemplary description of the present application and does not constitute any limitation to the present application.
[0137] Refer to the following Figure 8 The flowchart shown further illustrates another example of a mapping method of the present application. The mapping method of this example is used to map a target tunnel section, and the mapping result is a high-precision point cloud map. The mapping method includes steps S801, S802, S803, S804 and S805, specifically:
[0138] S801: pre-dividing a first section, a second section, and a third section including the target tunnel section according to information about surrounding sections of the target tunnel section, a first intersection section exists between the first section and the third section, and a second intersection section exists between the first section and the third section, and collecting first mapping data, second mapping data, and third mapping data when the driving device travels on the first section, the second section, and the third section, respectively;
[0139] Optionally, the first intersection section and the second intersection section are both between 50m and 100m.
[0140] S802: Mapping is performed according to the first mapping data to determine a first submap, and mapping is performed according to the second mapping data to determine a second submap, so as to ensure that the fused trajectory in the first submap and the second submap is well matched with the GPS positioning trajectory;
[0141] S803: determining an optimized driving trajectory of the driving device in the third road section according to the third mapping data, and transforming the point cloud data pose of the driving device in the third road section to the optimized driving trajectory;
[0142] S804: By merging and mapping, the optimized driving trajectory is merged into the two fused trajectories in the first submap and the second submap, the continuity between the merged optimized driving trajectory and the two fused trajectories is ensured through the first intersection section and the second intersection section, and the point cloud data in the third mapping data under the optimized driving trajectory, the point cloud data in the first submap, and the point cloud data in the second submap are merged;
[0143] S805: Based on the combined mapping results, a high-precision point cloud map corresponding to the target tunnel section is finally obtained.
[0144] It should be understood that the description of this exemplary mapping method does not limit the present application in any way.
[0145] Based on the above content, it can be seen that the mapping solution provided in the embodiment of the present application can obtain the first mapping data collected by the driving device when traveling on the first road section, wherein the first road section is the section before the starting point of the target road section; obtain the second mapping data collected by the driving device when traveling on the second road section, wherein the second road section is the section after the end point of the target road section; obtain the third mapping data collected by the driving device when traveling on the third road section including the target road section, wherein the first road section and the second road section and the third road section all have intersection sections; and then merge and map according to the first mapping data, the second mapping data and the third mapping data to determine the map corresponding to the target road section. Therefore, the present application combines the first mapping data, the second mapping data and the third mapping data for merging and mapping to determine the map corresponding to the target road section, which can effectively improve the problem of low accuracy when mapping the target road section due to GPS abnormality of the target road section, and can adapt to the mapping requirements in special scenarios including but not limited to tunnel sections, and effectively improve the mapping effect.
[0146] According to a second aspect of an embodiment of the present application, a mapping device is provided. Fig. 9 The structure block diagram of an exemplary mapping device 100 of the present application is shown. The mapping device 100 of this embodiment includes:
[0147] A first acquisition module 102 is used to acquire first mapping data collected when the driving device is traveling on a first road section, wherein the first road section is a road section before the starting point of the target road section;
[0148] The second acquisition module 104 is used to acquire second mapping data collected when the driving device is traveling on a second road section, wherein the second road section is a road section after the end point of the target road section;
[0149] A third acquisition module 106 is used to acquire third mapping data collected when the driving device travels on a third road section including the target road section, wherein the first road section and the second road section all have intersection sections with the third road section;
[0150] The merging mapping module 108 is used to merge and build a map according to the first mapping data, the second mapping data and the third mapping data to determine a map corresponding to the target road section.
[0151] The mapping solution provided by the embodiment of the present application is that the first acquisition module 102 can acquire the first mapping data collected when the driving device is driving on the first road section, wherein the first road section is the section before the starting point of the target road section; the second acquisition module 104 can acquire the second mapping data collected when the driving device is driving on the second road section, wherein the second road section is the section after the end point of the target road section; the third acquisition module 106 can acquire the third mapping data collected when the driving device is driving on the third road section including the target road section, wherein the first road section, the second road section and the third road section all have intersection sections; the merged mapping module 108 can merge and map according to the first mapping data, the second mapping data and the third mapping data to determine the map corresponding to the target road section. Therefore, the present application combines the first mapping data, the second mapping data and the third mapping data for merged mapping to determine the map corresponding to the target road section, which can effectively improve the problem of low accuracy when mapping the target road section due to GPS abnormality of the target road section, and can adapt to the mapping requirements in special scenarios including but not limited to tunnel sections, and effectively improve the mapping effect.
[0152] In some optional embodiments, the merged mapping module 108 is specifically used to: determine a first intersection section between the first section and the third section, and a second intersection section between the second section and the third section; establish a first loop constraint between the first section and the third section based on the first mapping data and the third mapping data corresponding to the first intersection section; establish a second loop constraint between the third section and the second section based on the third mapping data and the second mapping data corresponding to the second intersection section; determine the map corresponding to the target section based on the established first loop constraint and the second loop constraint, the first mapping data, the second mapping data and the third mapping data.
[0153] In some optional embodiments, the merged mapping module 108 is specifically used to: determine the key mapping data frames that match between the first mapping data and the third mapping data corresponding to the first intersection road segment; establish the first loop constraint for the first road segment and the third road segment based on the relative loop poses between the matching key mapping data frames; and determine the key mapping data frames that match between the third mapping data and the second mapping data corresponding to the second intersection road segment; establish the second loop constraint for the third road segment and the second road segment based on the relative loop poses between the matching key mapping data frames.
[0154] In some optional embodiments, the first mapping data, the second mapping data, and the third mapping data all include point cloud data, and the key mapping data frame is a point cloud frame; the loop relative pose between the matched key mapping data frames is obtained by a laser matching algorithm.
[0155] In some optional embodiments, the merged mapping module 108 is specifically used to: optimize the driving trajectory of the driving device on the third road section according to the results of the first loop constraint and the second loop constraint, and the third mapping data to obtain an optimized driving trajectory; determine the map corresponding to the target road section according to the optimized driving trajectory, the first mapping data, the second mapping data and the third mapping data.
[0156] In some optional embodiments, the third mapping data includes the GPS positioning trajectory, radar trajectory and DR trajectory of the driving device; the merged mapping module 108 is specifically used to: determine multiple positioning postures at multiple different positions of the driving device when traveling on the third road section according to the GPS positioning trajectory in the third mapping data; determine multiple radar relative postures at multiple different positions of the driving device when traveling on the third road section according to the radar trajectory in the third mapping data; determine multiple DR relative postures at multiple different positions of the driving device when traveling on the third road section according to the DR trajectory in the third mapping data; optimize the driving trajectory of the driving device on the third road section according to the loop relative postures in the first loop constraint and the second loop constraint, the multiple positioning postures, the multiple radar relative postures, and the multiple DR relative postures to obtain the optimized driving trajectory.
[0157] In some optional embodiments, the third mapping data includes point cloud data; the merging mapping module 108 is specifically used to: transform the point cloud data in the third mapping data to the optimized driving trajectory through posture, and merge the optimized driving trajectory, the point cloud data in the third mapping data transformed to the optimized driving trajectory, the first submap determined according to the first mapping data, and the second submap determined according to the second mapping data to determine the map corresponding to the target road section.
[0158] In some optional embodiments, the target section is a target tunnel section.
[0159] The mapping device 100 of the embodiment of the present application and the mapping method provided in the first aspect are based on the same inventive concept, and are used to implement the corresponding mapping methods in the aforementioned multiple method embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be described in detail here. In addition, the functional implementation of each module in the mapping device 100 of this embodiment can refer to the description of the corresponding parts in the aforementioned method embodiments, which will not be described in detail here.
[0160] According to a third aspect of an embodiment of the present application, a processing unit is provided, comprising: a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus; the memory is used to store a computer program; and the processor is used to execute the mapping method described in the first aspect by running the computer program stored in the memory.
[0161] Fig.10 The embodiment of the present application does not limit the specific implementation of the control device 1000. As an example, refer to Fig.10 The control device 1000 provided in the embodiment of the present application includes: a processor 1002, a communication interface 1004, a memory 1006, and a communication bus 1008. Among them:
[0162] The processor 1002 , the communication interface 1004 , and the memory 1006 communicate with each other via a communication bus 1008 .
[0163] The communication interface 1004 is used to communicate with other electronic devices or servers.
[0164] The processor 1002 is used to execute the computer program 1010, and specifically can execute the relevant steps in any of the aforementioned mapping method embodiments.
[0165] Specifically, the computer program 1010 may include program codes, which include computer operation instructions.
[0166] The processor 1002 may be a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application. The one or more processors included in the smart device may be processors of the same type, such as one or more CPUs; or processors of different types, such as one or more CPUs and one or more ASICs.
[0167] The memory 1006 is used to store the computer program 1010. The memory 1006 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.
[0168] The computer program 1010 may be specifically configured to enable the processor 1002 to execute the mapping method in any of the aforementioned embodiments.
[0169] The specific implementation of each step in the computer program 1010 can refer to the corresponding description of the corresponding steps and units in any of the above-mentioned mapping method embodiments, which will not be repeated here. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working process of the above-described devices and modules can refer to the corresponding process description in the above-mentioned method embodiments, which will not be repeated here.
[0170] The control device 1000 in the embodiment of the present application has been described in detail in the aforementioned mapping method embodiment, so its related contents and beneficial effects can be understood with reference to the aforementioned method embodiment, and will not be described again here.
[0171] According to a fourth aspect of the embodiment of the present application, a driving device 2000 is provided, referring to Fig.11 As shown in the block diagram, the driving device 2000 includes the control device 1000 provided by the third aspect.
[0172] According to a fifth aspect of an embodiment of the present application, a computer storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the mapping method described in the first aspect is implemented.
[0173] According to a sixth aspect of an embodiment of the present application, a computer program product is provided, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements the mapping method as described in the first aspect.
[0174] The driving device 2000 / computer storage medium / computer program product embodiment in the embodiment of the present application has been described in detail in the aforementioned mapping method embodiment, so its related content and beneficial effects can be understood with reference to the above-mentioned method embodiment and will not be repeated here.
[0175] It should be pointed out that, according to the needs of implementation, the various components / steps described in the embodiments of the present application can be split into more components / steps, or two or more components / steps or partial operations of components / steps can be combined into new components / steps to achieve the purpose of the embodiments of the present application.
[0176] The above-mentioned method according to the embodiment of the present application can be implemented in hardware, firmware, or implemented as software or computer code that can be stored in a recording medium (such as a CD ROM, RAM, floppy disk, hard disk or magneto-optical disk), or implemented as a computer code originally stored in a remote recording medium or a non-temporary machine-readable medium downloaded through a network and to be stored in a local recording medium, so that the method described herein can be stored in such software processing on a recording medium using a general-purpose computer, a special-purpose processor or programmable or special-purpose hardware (such as an ASIC or FPGA). It can be understood that a computer, a processor, a microprocessor controller or programmable hardware includes a storage component (e.g., RAM, ROM, flash memory, etc.) that can store or receive software or computer code, and when the software or computer code is accessed and executed by a computer, a processor or hardware, the method described herein is implemented. In addition, when a general-purpose computer accesses the code for implementing the method shown here, the execution of the code converts the general-purpose computer into a special-purpose computer for executing the method shown here.
[0177] Those of ordinary skill in the art will appreciate that the units and method steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the embodiments of the present application.
[0178] The above implementation methods are only used to illustrate the embodiments of the present application, and are not limitations on the embodiments of the present application. Ordinary technicians in the relevant technical field can make various changes and modifications without departing from the spirit and scope of the embodiments of the present application. Therefore, all equivalent technical solutions also belong to the scope of the embodiments of the present application. The scope of patent protection of the embodiments of the present application should be limited by the claims.
Claims
1. A mapping method, characterized in that: include: Acquire first mapping data collected when the driving device is traveling on a first road section, wherein the first road section is a road section before a starting point of a target road section; Acquire second mapping data collected when the driving device is traveling on a second road section, wherein the second road section is a road section after an end point of the target road section; Acquire third mapping data collected when the driving device is traveling on a third road section including the target road section, wherein the first road section and the second road section all have intersection sections with the third road section; A map is constructed by merging the first mapping data, the second mapping data, and the third mapping data to determine a map corresponding to the target road section.
2. The method according to claim 1, characterized in that The merging and mapping according to the first mapping data, the second mapping data and the third mapping data to determine a map corresponding to the target road section includes: Determine a first intersection section between the first section and the third section, and a second intersection section between the second section and the third section; Establishing a first loop constraint between the first road section and the third road section according to the first mapping data and the third mapping data corresponding to the first intersection road section; Establishing a second loop constraint between the third road segment and the second road segment according to the third mapping data and the second mapping data corresponding to the second intersection road segment; A map corresponding to the target road section is determined according to the established first loop constraint and second loop constraint, the first mapping data, the second mapping data, and the third mapping data.
3. The method according to claim 2, characterized in that The step of establishing a first loop constraint between the first road section and the third road section according to the first mapping data and the third mapping data corresponding to the first intersection road section comprises: determining a key mapping data frame that matches between the first mapping data and the third mapping data from the first mapping data and the third mapping data corresponding to the first intersection road section; and establishing the first loop constraint for the first road section and the third road section according to the loop relative poses between the matching key mapping data frames; The establishing of a second loop constraint between the third road section and the second road section according to the third mapping data and the second mapping data corresponding to the second intersection road section comprises: determining, from the third mapping data and the second mapping data corresponding to the second intersection road section, a key mapping data frame that matches the third mapping data and the second mapping data; and establishing the second loop constraint for the third road section and the second road section according to the loop relative poses between the matching key mapping data frames.
4. The method according to claim 3, characterized in that The first mapping data, the second mapping data, and the third mapping data all include point cloud data, and the key mapping data frame is a point cloud frame; The loop-back relative poses between the matched key mapping data frames are obtained by a laser matching algorithm.
5. The method according to any one of claims 2 to 4, characterized in that: The determining a map corresponding to the target road section according to the established first loop constraint and second loop constraint, the first mapping data, the second mapping data, and the third mapping data includes: According to the results of the first loop constraint and the second loop constraint and the third mapping data, optimizing the driving trajectory of the driving device on the third road section to obtain an optimized driving trajectory; A map corresponding to the target road section is determined according to the optimized driving trajectory, the first mapping data, the second mapping data, and the third mapping data.
6. The method according to claim 5, characterized in that The third mapping data includes the GPS positioning track, radar track and DR track of the driving device; The optimizing the driving trajectory of the driving device on the third road section according to the result of the first loop constraint and the second loop constraint and the third mapping data to obtain an optimized driving trajectory includes: Determining, according to the GPS positioning trajectory in the third mapping data, a plurality of positioning postures at a plurality of different positions of the driving device when traveling on a third road section; Determining, according to the radar tracks in the third mapping data, a plurality of radar relative postures at a plurality of different positions of the driving device when the driving device is traveling on a third road section; Determining, according to the DR tracks in the third mapping data, a plurality of DR relative postures at a plurality of different positions of the driving device when traveling on a third road section; The driving trajectory of the driving device on the third road section is optimized according to the loop relative postures in the first loop constraint and the second loop constraint, the multiple positioning postures, the multiple radar relative postures, and the multiple DR relative postures to obtain the optimized driving trajectory.
7. The method according to claim 6, characterized in that The third mapping data includes point cloud data; The determining a map corresponding to the target road section according to the optimized driving trajectory, the first mapping data, the second mapping data, and the third mapping data includes: The point cloud data in the third mapping data is transformed to the optimized driving trajectory through posture, and the optimized driving trajectory, the point cloud data in the third mapping data transformed to the optimized driving trajectory, the first submap determined according to the first mapping data, and the second submap determined according to the second mapping data are merged to determine a map corresponding to the target road section.
8. The method according to any one of claims 1 to 4, characterized in that The target section is a target tunnel section.
9. A mapping device, characterized in that: include: A first acquisition module is used to acquire first mapping data collected when the driving device is traveling on a first road section, wherein the first road section is a road section before the starting point of the target road section; A second acquisition module is used to acquire second mapping data collected when the driving device is traveling on a second road section, wherein the second road section is a road section after the end point of the target road section; A third acquisition module is used to acquire third mapping data collected when the driving device is traveling on a third road section including the target road section, wherein the first road section and the second road section all have intersection sections with the third road section; The merging mapping module is used to merge and build a map according to the first mapping data, the second mapping data and the third mapping data to determine a map corresponding to the target road section.
10. A control device, characterized in that: include: A processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus; The memory is used to store computer programs; The processor is configured to execute the method according to any one of claims 1 to 8 by running the computer program stored in the memory.
11. A driving device, characterized in that: include: A control device as claimed in claim 10.
12. A computer storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.
