CN111552757A - Method, device and equipment for generating electronic map and storage medium - Google Patents

Method, device and equipment for generating electronic map and storage medium Download PDF

Info

Publication number
CN111552757A
CN111552757A CN202010363616.0A CN202010363616A CN111552757A CN 111552757 A CN111552757 A CN 111552757A CN 202010363616 A CN202010363616 A CN 202010363616A CN 111552757 A CN111552757 A CN 111552757A
Authority
CN
China
Prior art keywords
data
pose data
pose
target
point cloud
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202010363616.0A
Other languages
Chinese (zh)
Other versions
CN111552757B (en
Inventor
李经纬
梁伯均
王哲
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shanghai Sensetime Lingang Intelligent Technology Co Ltd
Original Assignee
Shanghai Sensetime Lingang Intelligent Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shanghai Sensetime Lingang Intelligent Technology Co Ltd filed Critical Shanghai Sensetime Lingang Intelligent Technology Co Ltd
Priority to CN202010363616.0A priority Critical patent/CN111552757B/en
Publication of CN111552757A publication Critical patent/CN111552757A/en
Priority to PCT/CN2021/086721 priority patent/WO2021218620A1/en
Priority to JP2022505577A priority patent/JP2022542289A/en
Application granted granted Critical
Publication of CN111552757B publication Critical patent/CN111552757B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/29—Geographical information databases
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/70—Determining position or orientation of objects or cameras
    • G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10028—Range image; Depth image; 3D point clouds

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Remote Sensing (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Navigation (AREA)

Abstract

The application provides a method, a device, equipment and a storage medium for generating an electronic map. The method comprises the following steps: acquiring pose data of a target object in a moving process, wherein the pose data comprise pose data to be adjusted of the target object in a target area and reference pose data of the target object outside the target area; adjusting the pose data to be adjusted according to the reference pose data to obtain target pose data; and generating an electronic map corresponding to the target area according to the target pose data.

Description

Method, device and equipment for generating electronic map and storage medium
Technical Field
The present application relates to the field of computer technologies, and in particular, to a method, an apparatus, a device, and a storage medium for generating an electronic map.
Background
The establishment of high-precision maps is one of the key technologies in the field of automatic driving. The existing data acquisition method of high-precision maps uses a special acquisition vehicle, the acquisition vehicle is provided with an overhead acquisition device such as a laser radar and a depth camera and a Strapdown Inertial Navigation System (SINS), and the data acquisition method can be used for establishing maps under the condition of good satellite signals, and the precision can reach centimeter level. However, the above-mentioned technical solution for constructing a high-precision map depends on good satellite signals, and thus is difficult to be applied to various fields.
Disclosure of Invention
The embodiment of the application provides a method, a device, equipment and a storage medium for generating an electronic map, which aim to solve the problem that the existing electronic map generation mode is poor in applicability.
In a first aspect, an embodiment of the present application provides a method for generating an electronic map, including:
acquiring pose data of a target object in a moving process, wherein the pose data comprise pose data to be adjusted of the target object in a target area and reference pose data of the target object outside the target area;
adjusting the pose data to be adjusted according to the reference pose data to obtain target pose data;
and generating an electronic map corresponding to the target area according to the target pose data.
In one possible implementation, the reference pose data includes first pose data and second pose data, the first pose data including pose data for the target object at a first position before entering the target area, the second pose data including pose data for the target object at a second position after leaving the target area;
the pose data to be adjusted comprises pose data of a plurality of third positions of the target object in the moving process of the target object in the target area.
In a possible implementation manner, the adjusting the pose data to be adjusted according to the reference pose data to obtain target pose data includes:
acquiring point cloud data acquired by the target object, wherein the point cloud data comprises first point cloud data acquired by the target object at the first position, second point cloud data acquired by the target object at the second position and third point cloud data acquired by the target object at a plurality of third positions;
acquiring inertial measurement data of the target object in the target area;
and adjusting at least part of the pose data to be adjusted according to the reference pose data, the point cloud data and the inertial measurement data to obtain target pose data corresponding to at least part of the pose to be adjusted.
In a possible implementation manner, the adjusting at least a part of the pose data to be adjusted according to the reference pose data, the point cloud data and the inertial measurement data to obtain target pose data corresponding to at least a part of the pose to be adjusted includes:
adjusting at least part of the pose data to be adjusted according to the first pose data, the second pose data and the inertial measurement data to obtain intermediate pose data corresponding to at least part of the pose data to be adjusted;
and adjusting the intermediate pose data according to the point cloud data to obtain target pose data corresponding to the intermediate pose.
In one possible embodiment, adjusting the intermediate pose data according to the point cloud data to obtain target pose data corresponding to the intermediate pose includes:
performing point cloud registration according to point cloud data acquired twice in the point cloud data to obtain a first relative position relation of the point cloud data acquired twice in the moving process of the target object;
and adjusting the intermediate pose data according to the first relative position relationship, the first pose data and the second pose data to obtain the target pose data.
In one possible embodiment, the performing point cloud registration according to each two adjacent acquired point cloud data in the point cloud data includes:
and carrying out point cloud registration according to the point cloud data acquired twice in the adjacent point cloud data and the intermediate pose data.
In a possible implementation, the adjusting the intermediate pose data according to the first relative position relationship, the first reference pose, and the second reference pose to obtain the target pose data includes:
and adjusting the intermediate pose data by taking the first pose data, the second pose data and the first relative position relationship as constraint conditions to obtain the target pose data.
In a possible implementation, adjusting at least a portion of the pose data to be adjusted according to the first pose data, the second pose data, and the inertial measurement data to obtain intermediate pose data corresponding to at least a portion of the pose data to be adjusted includes:
according to inertia measurement data acquired between the time of acquiring the point cloud data of two adjacent times, determining a second relative position relation of the point cloud data of two adjacent times of the target object in the moving process;
and adjusting the pose data to be adjusted by taking the first pose data, the second pose data and the second relative position relationship as constraint conditions to obtain the intermediate pose data.
In a possible implementation, the adjusting the intermediate pose data according to the first relative position relationship, the first reference pose, and the second reference pose to obtain the target pose data includes:
and adjusting the intermediate pose data by taking the first pose data, the second pose data, the first relative position relationship and the second relative position relationship as constraint conditions to obtain the target pose data, wherein the second relative position relationship is determined according to inertial measurement data acquired between the moments of acquiring the adjacent two-time point cloud data.
In a possible implementation, the first relative position relationship includes a first relative pose and a first information matrix, the first information matrix is used for reflecting the accuracy of the first relative pose, and the weight of the first relative pose is positively correlated with the accuracy of the first relative pose;
and/or the second relative position relation comprises a second relative pose and a second information matrix, the second information matrix is used for reflecting the accuracy of the second relative pose, and the weight of the second relative pose is positively correlated with the accuracy of the second relative pose.
In a possible implementation manner, the electronic map corresponding to the target area comprises a first electronic map corresponding to the target area and a second electronic map corresponding to the target area;
generating an electronic map corresponding to the target area according to the target pose data, wherein the electronic map comprises:
generating the first electronic map according to the target pose data;
generating the second electronic map according to the reference pose data;
and splicing the first electronic map and the second electronic map to obtain the electronic map corresponding to the target area.
In one possible embodiment, the signal strength inside the target region is smaller than the signal strength outside the target region.
In a possible implementation manner, the reference pose data is acquired by a first manner, the pose data to be adjusted is acquired by a second manner, and the accuracy of the reference pose data is greater than that of the pose data to be adjusted.
In a second aspect, an embodiment of the present application provides an apparatus for generating an electronic map, including:
the system comprises an acquisition module, a display module and a control module, wherein the acquisition module is used for acquiring pose data of a target object in a moving process, and the pose data comprises pose data to be adjusted of the target object in a target area and reference pose data of the target object outside the target area;
the processing module is used for adjusting the pose data to be adjusted according to the reference pose data to obtain target pose data;
the processing module is further configured to generate an electronic map corresponding to the target area according to the target pose data.
In one possible implementation, the reference pose data includes first pose data and second pose data, the first pose data including pose data for the target object at a first position before entering the target area, the second pose data including pose data for the target object at a second position after leaving the target area;
the pose data to be adjusted comprises pose data of a plurality of third positions of the target object in the moving process of the target object in the target area.
In a possible implementation manner, the processing module is specifically configured to:
acquiring point cloud data acquired by the target object, wherein the point cloud data comprises first point cloud data acquired by the target object at the first position, second point cloud data acquired by the target object at the second position and third point cloud data acquired by the target object at a plurality of third positions;
acquiring inertial measurement data of the target object in the target area;
and adjusting at least part of the pose data to be adjusted according to the reference pose data, the point cloud data and the inertial measurement data to obtain target pose data corresponding to at least part of the pose to be adjusted.
In a possible implementation manner, the processing module is specifically configured to:
adjusting at least part of the pose data to be adjusted according to the first pose data, the second pose data and the inertial measurement data to obtain intermediate pose data corresponding to at least part of the pose data to be adjusted;
and adjusting the intermediate pose data according to the point cloud data to obtain target pose data corresponding to the intermediate pose.
In a possible implementation manner, the processing module is specifically configured to:
performing point cloud registration according to point cloud data acquired twice in the point cloud data to obtain a first relative position relation of the point cloud data acquired twice in the moving process of the target object;
and adjusting the intermediate pose data according to the first relative position relationship, the first pose data and the second pose data to obtain the target pose data.
In a possible implementation manner, the processing module is specifically configured to:
and carrying out point cloud registration according to the point cloud data acquired twice in the adjacent point cloud data and the intermediate pose data.
In a possible implementation manner, the processing module is specifically configured to:
and adjusting the intermediate pose data by taking the first pose data, the second pose data and the first relative position relationship as constraint conditions to obtain the target pose data.
In a possible implementation manner, the processing module is specifically configured to:
according to inertia measurement data acquired between the time of acquiring the point cloud data of two adjacent times, determining a second relative position relation of the point cloud data of two adjacent times of the target object in the moving process;
and adjusting the pose data to be adjusted by taking the first pose data, the second pose data and the second relative position relationship as constraint conditions to obtain the intermediate pose data.
In a possible implementation manner, the processing module is specifically configured to:
and adjusting the intermediate pose data by taking the first pose data, the second pose data, the first relative position relationship and the second relative position relationship as constraint conditions to obtain the target pose data, wherein the second relative position relationship is determined according to inertial measurement data acquired between the moments of acquiring the adjacent two-time point cloud data.
In a possible implementation, the first relative position relationship includes a first relative pose and a first information matrix, the first information matrix is used for reflecting the accuracy of the first relative pose, and the weight of the first relative pose is positively correlated with the accuracy of the first relative pose;
and/or the second relative position relation comprises a second relative pose and a second information matrix, the second information matrix is used for reflecting the accuracy of the second relative pose, and the weight of the second relative pose is positively correlated with the accuracy of the second relative pose.
In a possible implementation manner, the electronic map corresponding to the target area comprises a first electronic map corresponding to the target area and a second electronic map corresponding to the target area;
the processing module is specifically configured to:
generating the first electronic map according to the target pose data;
generating the second electronic map according to the reference pose data;
and splicing the first electronic map and the second electronic map to obtain the electronic map corresponding to the target area.
In one possible embodiment, the signal strength inside the target region is smaller than the signal strength outside the target region.
In a possible implementation manner, the reference pose data is acquired by a first manner, the pose data to be adjusted is acquired by a second manner, and the accuracy of the reference pose data is greater than that of the pose data to be adjusted.
In a third aspect, an embodiment of the present application provides an electronic device, including: at least one processor and memory;
the memory stores computer-executable instructions;
the at least one processor executing the computer-executable instructions stored by the memory causes the at least one processor to perform the method of generating an electronic map as described above in the first aspect and in various possible implementations of the first aspect.
In a fourth aspect, embodiments of the present application provide a computer-readable storage medium, where computer-executable instructions are stored, and when a processor executes the computer-executable instructions, a method for generating an electronic map as described in the first aspect and various possible implementations of the first aspect is implemented.
According to the method, the device, the equipment and the storage medium for generating the electronic map, firstly, pose data of a target object in a moving process are obtained, the pose data comprise pose data to be adjusted of the target object in a target area and reference pose data of the target object outside the target area, then the pose data to be adjusted are adjusted according to the reference pose data to obtain target pose data, and the electronic map corresponding to the target area is generated according to the target pose data. According to the method and the device, the pose data to be adjusted of the target object in the target area is adjusted by utilizing the reference pose data of the target object outside the target area, so that the pose data of the target object in the target area is more accurate, and the accuracy of the generated electronic map is improved.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to these drawings without inventive exercise.
Fig. 1 is a schematic architecture diagram of a system for generating an electronic map according to an embodiment of the present application;
fig. 2 is a schematic flowchart of a method for generating an electronic map according to an embodiment of the present application;
fig. 3 is a schematic flowchart of a method for generating an electronic map according to another embodiment of the present application;
fig. 4 is a schematic flowchart of a method for generating an electronic map according to another embodiment of the present application;
FIG. 5 is a schematic diagram of the ordering of point cloud data and inertial measurement data on a time axis according to an embodiment of the present disclosure;
fig. 6 is a schematic flowchart of a method for generating an electronic map according to a further embodiment of the present application;
fig. 7 is a schematic structural diagram of an apparatus for generating an electronic map according to an embodiment of the present application;
fig. 8 is a schematic hardware structure diagram of an electronic device according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Fig. 1 is a schematic architecture diagram of a system for generating an electronic map according to an embodiment of the present application. The system for generating the electronic map includes a target object 13 in which an acquisition device 11 and an Inertial Measurement Unit (IMU) 12 are deployed, and an electronic device 14. The target object 13 is a device that carries the acquisition device to move, and may be, for example, a vehicle, an unmanned aerial vehicle, a mobile robot, and the like, which is not limited herein. The collecting device 11 is a device for collecting environmental information, and may be, for example, a laser radar, a depth camera, a millimeter wave radar, and the like, which is not limited herein. The target object 13 moves in a target area of the electronic map to be constructed, in the moving process, the acquisition device 11 acquires point cloud data of the surrounding environment of the target object 13 according to a certain Frame rate (Frame rate), and the inertial measurement unit 12 acquires inertial measurement data in the moving process of the target object 13 according to the certain Frame rate. After the data collection is completed, the data collected by the collection device 11 and the inertial measurement unit 12 are sent to the electronic device 14. The electronic device 14 may be a device other than the target object 13, such as a desktop computer, a notebook computer, a mobile phone, or a server, or may be a vehicle-mounted terminal on the target object 13, which is not limited herein. The electronic device 14 generates an electronic map according to the point cloud data acquired by the acquisition device 11 and the inertia measurement data acquired by the inertia measurement unit 12.
Generally, an electronic map is constructed in an offline manner and an online manner. The off-line mode refers to map construction after data acquisition is finished. After the target object 13 completes data acquisition, the acquired data is sent to the electronic device 14. The electronic device 14 determines the pose of the acquisition device from the pose located by the inertial measurement unit 12, and then constructs an electronic map according to the point cloud data acquired by the acquisition device and the corresponding pose. In areas with strong satellite signals such as highways and playgrounds, the inertial measurement unit 12 can correct errors of the inertial measurement unit 12 in the moving process by combining the satellite signals to obtain a relatively accurate pose of the acquisition device, so that the accuracy of the electronic map is ensured. However, in the area where the satellite signals are weak, such as a tunnel, an underground parking lot, an underground mall, and the like, the inertial measurement unit 12 cannot correct the error of the inertial measurement unit 12 in the moving process by combining the satellite signals, so that a large error exists in the pose of the obtained acquisition device, and the accuracy of the generated map is poor.
The online mode is to adopt SLAM (Simultaneous Localization and Mapping) technology to map, and map in real time during data acquisition. However, the accurate positioning result obtained by the SLAM technology depends on abundant texture features for registration, and the texture features in the areas such as the tunnel and the underground parking lot are single, for example, the texture features of the tunnel wall in the tunnel are similar, and the point cloud data acquired at different positions in the tunnel are similar, so that the SLAM technology is difficult to accurately position in the areas, that is, the corresponding pose of the point cloud data cannot be accurately obtained, and therefore, the SLAM technology cannot construct an accurate map in the areas.
In the embodiment of the application, the pose data of the target object in the moving process is firstly acquired, the pose data comprises the pose data to be adjusted of the target object in the target area and the reference pose data of the target object outside the target area, then the pose data to be adjusted is adjusted according to the reference pose data to obtain the target pose data, and the electronic map corresponding to the target area is generated according to the target pose data. According to the method and the device, the pose data to be adjusted of the target object in the target area is adjusted by using the reference pose data of the target object outside the target area, so that the pose data with lower accuracy are adjusted by using the pose data outside the target area under the condition that the pose data are inaccurate due to weak satellite signals in the target area, the pose data of the target object in the target area are more accurate, and the accuracy of the generated electronic map is improved. The following examples are given by way of illustration.
It should be noted that the method for generating an electronic map provided in this embodiment is not only applicable to electronic map construction of an area with weak satellite signals, but also applicable to electronic map construction of an area with good satellite signals, and is not limited herein.
Fig. 2 is a schematic flowchart of a method for generating an electronic map according to an embodiment of the present application. The execution subject of the method may be the electronic device in fig. 1. As shown in fig. 2, the method includes:
s201, acquiring pose data of a target object in a moving process, wherein the pose data comprise pose data to be adjusted of the target object in a target area and reference pose data of the target object outside the target area.
In this embodiment, the target object may include, but is not limited to, a vehicle, a drone, a mobile robot, and the like. The target object may move within and outside of the target area. The target area may include, but is not limited to, tunnels, underground parking lots, underground malls, and the like. The target object can move from the outside of the target area to the inside of the target area; the target area can be moved from the outside of the target area to the outside of the target area after entering the target area from the outside of the target area. For example, the target object is a vehicle, the target area is a tunnel, and the vehicle can enter the tunnel entrance from the outside of the tunnel, then pass through the tunnel, and exit from the tunnel exit.
The pose data of the target object in the moving process can be obtained by measurement through an inertial measurement unit, or can be obtained by satellite positioning, SLAM technology, and the like. For example, an inertial measurement unit is mounted on the vehicle, and pose data in the moving process of the vehicle is acquired through the inertial measurement unit.
The data to be adjusted is pose data of the target object in the target area, and the reference pose data is pose data of the target object outside the target area. For example, during the process that the vehicle passes through the tunnel, the pose data of the vehicle before entering the tunnel entrance and the pose data after leaving the tunnel exit are reference pose data, and the pose data of the vehicle in the tunnel are data to be adjusted.
S202, adjusting the pose data to be adjusted according to the reference pose data to obtain target pose data.
In this embodiment, the pose data to be adjusted can be adjusted by referring to the pose data, and the pose data of the adjusted target object in the target area is obtained, that is, the target pose data. For example, the pose data in the tunnel is adjusted through the pose data of the vehicle outside the tunnel, so that the pose data in the tunnel is more accurate.
And S203, generating an electronic map corresponding to the target area according to the target pose data.
In this embodiment, the target object is provided with an acquisition device for acquiring environmental information. The acquisition device may include, but is not limited to, a laser radar, a depth camera, a millimeter wave radar, etc., and is not limited thereto. The target object can acquire the environment information corresponding to the target area through the acquisition device, and an electronic map corresponding to the target area is generated according to the target pose data and the environment information corresponding to the target area.
Due to the fact that satellite signals in the target area are weak, environmental texture features are single and the like, accuracy of collected pose data of the target object moving in the target area is poor, and if the collected pose data are directly used for electronic map generation, the electronic map has large errors. In this embodiment, the pose data of the target object to be adjusted in the target area is adjusted by the reference pose data of the target object outside the target area, and the pose data in the target area is adjusted by using the relationship between the pose data of the target object in the moving process inside and outside the target area, so that the accuracy of the pose data for constructing the electronic map can be improved, and the accuracy of the electronic map is further improved.
In the embodiment of the application, the pose data of the target object in the moving process is firstly acquired, the pose data comprises the pose data to be adjusted of the target object in the target area and the reference pose data of the target object outside the target area, then the pose data to be adjusted is adjusted according to the reference pose data to obtain the target pose data, and the electronic map corresponding to the target area is generated according to the target pose data. According to the method and the device, the pose data to be adjusted of the target object in the target area is adjusted by utilizing the reference pose data of the target object outside the target area, so that the pose data of the target object in the target area is more accurate, and the accuracy of the generated electronic map is improved.
In one embodiment, the signal strength within the target region is less than the signal strength outside the target region.
In this embodiment, the accuracy of the pose data of the target object is related to the signal strength, and the stronger the signal strength is, the more accurate the pose data of the target object is acquired. For example, the vehicle can utilize satellite signals to correct accumulated errors of inertial vehicle units outside a tunnel, so that pose data with high accuracy are obtained; the vehicle can not utilize satellite signals to correct the accumulated errors of the inertial vehicle unit in the tunnel, and only pose data with poor accuracy can be obtained.
When the signal intensity in the target area is smaller than the signal intensity outside the target area, the accuracy of the pose data to be adjusted of the target object in the target area is lower than that of the reference pose data outside the target area, so that the reference pose data can be used for adjusting the pose data to be adjusted, and the accuracy of the obtained target pose data is higher.
In one embodiment, the reference pose data is acquired by a first method, the pose data to be adjusted is acquired by a second method, and the accuracy of the reference pose data is greater than that of the pose data to be adjusted.
The reference pose data and the pose data to be adjusted adopt different acquisition modes, and the specific acquisition mode is not limited herein. For example, the first mode may be satellite positioning, satellite combined inertial measurement unit positioning, RTK (Real-time kinematic) carrier-phase differential techniques, and the like. The second way may be an inertial measurement unit, SLAM technology positioning, etc. The accuracy of the reference pose data obtained by the first method is greater than the accuracy of the pose data to be adjusted obtained by the second method.
In one embodiment, the electronic map corresponding to the target area comprises a first electronic map corresponding to the target area and a second electronic map corresponding to the target area; s203 in the embodiment shown in fig. 2 may include:
generating the first electronic map according to the target pose data;
generating the second electronic map according to the reference pose data;
and splicing the first electronic map and the second electronic map to obtain the electronic map corresponding to the target area.
In this embodiment, a first electronic map in the target area and a second electronic area outside the target area may be generated respectively, and then the first electronic map and the second electronic area are spliced to obtain an electronic map corresponding to the target area.
Taking a tunnel as an example, a first electronic map in the tunnel can be generated through target pose data of a vehicle in the tunnel and point cloud data corresponding to the target pose data. And generating a second electronic map outside the tunnel through reference pose data of the vehicle outside the tunnel and point cloud data corresponding to the reference pose data. The first electronic map and the second electronic map can be spliced to obtain the electronic map corresponding to the tunnel.
It should be noted that the execution sequence of the step of generating the first electronic map and the step of generating the second electronic map is not limited. For example, the step of generating the first electronic map may be performed first, and then the step of generating the second electronic map may be performed; or the step of generating the second electronic map can be executed firstly, and then the step of generating the first electronic map can be executed; the two steps may also be performed in parallel.
In a method for generating an electronic map according to another embodiment of the present application, based on the embodiment shown in fig. 2, the reference pose data includes first pose data and second pose data, the first pose data includes pose data of a first position before the target object enters the target area, and the second pose data includes pose data of a second position after the target object leaves the target area.
The pose data to be adjusted comprises pose data of a plurality of third positions of the target object in the moving process of the target object in the target area.
In this embodiment, the first position is a position before the target area, the second position is a position after the target area, and the third position is a position in the target area. For example, before a vehicle enters a tunnel entrance, at least one frame of position data is collected through an RTK carrier phase differential technology; when the vehicle moves in the tunnel, obtaining pose data to be adjusted through an inertia measurement unit; and after the vehicle is driven out of the tunnel outlet, acquiring at least one frame of position data again by using an RTK carrier phase difference technology. The location data may include, but is not limited to, one or more of a longitude, a latitude, an altitude, a vehicle speed, etc. of the location of the target object. The method comprises the steps that first position and attitude data before a vehicle enters a tunnel entrance can be obtained through at least one frame of position data before the vehicle enters the tunnel entrance, second position and attitude data after the vehicle enters the tunnel entrance can be obtained through at least one frame of position data after the vehicle exits the tunnel exit, and position and attitude data to be adjusted after the vehicle enters the tunnel entrance can be obtained through an inertial measurement unit for collecting the vehicle in the moving process in the tunnel.
Fig. 3 is a schematic flow chart of a method for generating an electronic map according to another embodiment of the present application, and on the basis of any one of the two embodiments, the present embodiment describes in detail a specific implementation process of S202. As shown in fig. 3, the method includes:
s301, acquiring pose data of a target object in a moving process, wherein the pose data comprise pose data to be adjusted of the target object in a target area and reference pose data of the target object outside the target area.
In this embodiment, S301 is similar to S201 in the embodiment of fig. 2, and is not described here again.
S302, point cloud data collected by the target object are obtained, wherein the point cloud data comprise first point cloud data collected by the target object at the first position, second point cloud data collected by the target object at the second position, and third point cloud data collected by the target object at a plurality of third positions.
In this embodiment, the target object may acquire the point cloud data through an acquisition device, where the acquisition device includes, but is not limited to, at least one of a laser radar, a depth camera, and a millimeter wave radar. The acquisition device can be arranged on the target object, and acquires the surrounding environment information along with the movement of the target object inside and outside the target area to obtain point cloud data. The first point cloud data is point cloud data acquired by a target object at a first position before the target object enters the target area, the second point cloud data is point cloud data acquired by the target object at a second position after the target object leaves the target area, and the third point cloud data is point cloud data acquired by the target object at a third position in the target area.
The point cloud data may include three-dimensional coordinates and reflectivity of each point in the point cloud, for example, the data of a point may be represented as (X, Y, Z, Intensity), where X, Y, Z represent the three-dimensional coordinates of the point and Intensity represents the reflectivity of the point. Each acquired point cloud data may have a corresponding time stamp.
S303, obtaining inertial measurement data of the target object in the target area.
In this embodiment, the inertial measurement data of the target object in the target area may be acquired by the inertial measurement unit. The inertial measurement unit may be configured on the target object to acquire inertial measurement data as the target object moves. The inertial measurement data acquired each time can comprise three-axis acceleration and three-axis angular velocity of the current pose. For example, the inertial measurement data may be represented as (ax, ay, az, wx, wy, wz), where ax, ay, az represent the three-axis acceleration of the frame and wx, wy, wz represent the three-axis angular acceleration of the frame.
It should be noted that the execution sequence of S301, S302, and S303 is not limited, and fig. 3 is only an example. S301, S302, and S303 may be executed in parallel, or may be executed sequentially according to a certain order, for example, S302, S303, and S301 may be executed sequentially, or S302, S301, and S303 may be executed sequentially, and in addition, other execution orders are also included, which are not listed herein.
S304, adjusting at least part of the pose data to be adjusted according to the reference pose data, the point cloud data and the inertial measurement data to obtain target pose data corresponding to at least part of the pose to be adjusted.
In this embodiment, at least part of the pose data to be adjusted may be adjusted according to the reference pose data, the point cloud data, and the inertial measurement data, so as to obtain target pose data. The point cloud data provides relevant information for adjustment from the perspective of environmental information, such as environmental information in a tunnel; the inertial measurement data provides relevant information for adjustment from the perspective of the moving state of the target object, such as information about the movement of the target object within the tunnel; the reference pose data provides two boundaries of poses for the adjustment, such as the accurate pose of the target object before the tunnel entrance and after the tunnel exit.
And S305, generating an electronic map corresponding to the target area according to the target pose data.
In this embodiment, S305 is similar to S203 in the embodiment of fig. 2, and is not described herein again.
According to the method and the device, the information is provided for the adjustment of the pose data to be adjusted from different angles by referring to the pose data, the point cloud data and the inertia measurement data, so that the accuracy of the target pose data is high, and the accuracy of the generated electronic map is improved.
Fig. 4 is a schematic flow chart of a method for generating an electronic map according to another embodiment of the present application, and based on the embodiment shown in fig. 3, the present embodiment describes in detail a specific implementation process of S304. As shown in fig. 4, the method includes:
s401, acquiring pose data of a target object in a moving process, wherein the pose data comprise pose data to be adjusted of the target object in a target area and reference pose data of the target object outside the target area.
In this embodiment, S401 is similar to S201 in the embodiment of fig. 2, and is not described here again.
S402, point cloud data collected by the target object are obtained, wherein the point cloud data comprise first point cloud data collected by the target object at the first position, second point cloud data collected by the target object at the second position and third point cloud data collected by the target object at a plurality of third positions.
In this embodiment, S402 is similar to S302 in the embodiment of fig. 3, and is not described here again.
And S403, acquiring inertial measurement data of the target object in the target area.
In this embodiment, S403 is similar to S303 in the embodiment of fig. 3, and is not described here again.
It should be noted that the execution sequence of S401, S402, and S403 is not limited, and fig. 4 is only an example. S401, S402, and S403 may be executed in parallel, or may be executed sequentially according to a certain order, for example, S402, S403, and S401 may be executed sequentially, or S402, S401, and S403 may be executed sequentially, or there may be other execution orders, which are not listed herein.
S404, adjusting at least part of the pose data to be adjusted according to the first pose data, the second pose data and the inertial measurement data to obtain intermediate pose data corresponding to at least part of the pose data to be adjusted.
S405, adjusting the intermediate pose data according to the point cloud data to obtain target pose data corresponding to the intermediate pose.
In this embodiment, the target pose data can be obtained by two times of adjustment. The first adjustment is to adjust the pose data to be adjusted according to the first pose data, the second pose data and the inertial measurement data to obtain intermediate pose data. And the second adjustment is to adjust the intermediate pose data according to the point cloud data to obtain target pose data.
And S406, generating an electronic map corresponding to the target area according to the target pose data.
In this embodiment, S406 is similar to S203 in the embodiment of fig. 2, and is not described herein again.
According to the embodiment, the pose to be adjusted is adjusted by sequentially adjusting the inertial measurement data and the point cloud data, so that the accuracy of the target pose data can be improved.
In one embodiment, S404 may include:
according to inertia measurement data acquired between the time of acquiring the point cloud data of two adjacent times, determining a second relative position relation of the point cloud data of two adjacent times of the target object in the moving process;
and adjusting the pose data to be adjusted by taking the first pose data, the second pose data and the second relative position relationship as constraint conditions to obtain the intermediate pose data.
In this embodiment, in the first adjustment process, a second relative position relationship between two adjacent collected point cloud data of the target object in the moving process may be determined according to the inertial measurement data collected between the time of collecting two adjacent point cloud data. For example, each time the point cloud data and the inertial measurement data are acquired, a time stamp is provided, and the time stamp is used for recording the acquisition time of the data. All the point cloud data acquired at each time and the inertia measurement data acquired at each time can be sequenced according to the time stamps, and the inertia measurement data between two adjacent point cloud data is determined.
As shown in fig. 5, each circle represents inertial measurement data acquired once, each triangle represents point cloud data acquired once, and the coordinate axis is a time axis. Wherein the circles between two adjacent triangles represent the acquired inertial measurement data between the two point cloud data acquisitions. It should be noted that the number of times of acquiring the inertia measurement data between the time points of two adjacent point cloud data is not limited, and is determined by the acquisition interval of the point cloud data and the acquisition interval of the inertia measurement data, the acquisition of the inertia measurement data three times between the time points of two adjacent point cloud data shown in fig. 5 is only an example, and the inertia measurement data of more times or less times may be included between the time points of two adjacent point cloud data.
The inertia measurement data acquired between the moments of the two adjacent point cloud data can be subjected to pre-integration processing to obtain a second relative position relation of the two adjacent point cloud data acquired in the moving process of the target object. And then adjusting the pose data to be adjusted by taking the first pose data, the second pose data and the second relative position relationship as constraint conditions to obtain intermediate pose data.
For example, the pose data to be adjusted may be used as an initial value to be optimized, the first pose data and the second pose data may be used as pose true values in the optimization, the second relative position relationship may be used as an optimization edge, and a pose optimization algorithm may be used to obtain intermediate pose data. The pose optimization algorithm may be a cerees optimization algorithm, a g2o (General graph optimization) General graph optimization algorithm, and the like, which is not limited herein.
Optionally, the second relative position relationship includes a second relative pose and a second information matrix, the second information matrix is used for reflecting the accuracy of the second relative pose, and the weight of the second relative pose is positively correlated with the accuracy of the second relative pose. The higher the accuracy of the second relative pose is, the larger the weight corresponding to the second relative pose in the adjustment process is, and the second relative pose with high accuracy has a greater effect on the adjustment process, so that the accuracy of the intermediate pose data is improved.
Fig. 6 is a schematic flow chart of a method for generating an electronic map according to still another embodiment of the present application, and based on the embodiment shown in fig. 4, the present embodiment describes in detail a specific implementation process of the second adjustment process. As shown in fig. 6, the method includes:
s601, acquiring pose data of a target object in a moving process, wherein the pose data comprise pose data to be adjusted of the target object in a target area and reference pose data of the target object outside the target area.
In this embodiment, S601 is similar to S201 in the embodiment of fig. 2, and is not described here again.
S602, point cloud data collected by the target object is obtained, wherein the point cloud data comprises first point cloud data collected by the target object at the first position, second point cloud data collected by the target object at the second position, and third point cloud data collected by the target object at a plurality of third positions.
In this embodiment, S602 is similar to S302 in the embodiment of fig. 3, and is not described here again.
And S603, acquiring inertial measurement data of the target object in the target area.
In this embodiment, S603 is similar to S303 in the embodiment of fig. 3, and is not described here again.
It should be noted that the execution sequence of S601, S602, and S603 is not limited, and fig. 6 is only an example. S601, S602, and S603 may be executed in parallel, or may be executed sequentially according to a certain order, for example, S602, S603, and S601 may be executed sequentially, or S602, S601, and S603 may be executed sequentially, or there may be other execution orders, which are not listed herein.
S604, adjusting at least part of the pose data to be adjusted according to the first pose data, the second pose data and the inertial measurement data to obtain intermediate pose data corresponding to at least part of the pose data to be adjusted.
In this embodiment, S604 is similar to S404 in the embodiment of fig. 4, and is not described here again.
S605, performing point cloud registration according to the point cloud data acquired twice in the point cloud data to obtain a first relative position relation of the point cloud data acquired twice in the moving process of the target object.
In this embodiment, the intermediate pose data obtained by the first adjustment is adjusted again, that is, adjusted for the second time. In the second adjustment process, point cloud registration is firstly carried out according to the point cloud data acquired twice adjacent to each other in the point cloud data, so that a first relative position relation of the point cloud data acquired twice adjacent to each other in the moving process of the target object is obtained. The point cloud registration algorithm is not limited herein, and may be, for example, an LLS-LOAM algorithm, an icp (iterative close point) registration algorithm, or the like.
In one embodiment, S605 may include:
and carrying out point cloud registration according to the point cloud data acquired twice in the adjacent point cloud data and the intermediate pose data.
For some target areas with abundant textural features, such as underground shopping malls and the like, the point cloud registration is directly carried out according to the collected point cloud data, so that a more accurate first relative position relation can be obtained. However, for a target area with a single texture feature, such as a tunnel, etc., due to the single texture feature, point cloud registration is directly performed according to the collected point cloud data, and a first relative position relationship obtained has a large error, even registration failure occurs. In this embodiment, during point cloud registration, intermediate pose data obtained by first adjustment may be used as an initial value in a point cloud registration process, and point cloud registration is performed on the basis of the intermediate pose data, so that the success rate and accuracy of point cloud registration are improved, the accuracy of the first relative position relationship is improved, the accuracy of second adjustment is improved, and the accuracy of the electronic map is improved. It should be noted that the mode that the intermediate pose data participates in the point cloud registration process is adopted in the embodiment, so that the electronic map accuracy of the target area with single texture features is improved, and the electronic map accuracy of the target area with rich texture features can also be improved to a certain extent.
S606, adjusting the intermediate pose data according to the first relative position relation, the first pose data and the second pose data to obtain the target pose data.
In this embodiment, in the second adjustment process, the first relative position relationship is obtained through point cloud registration, and then the intermediate pose data is adjusted by combining the first pose data and the second pose data according to the first relative position relationship obtained by the point cloud data, so as to obtain the target position data.
In one implementation, S606 may include: and adjusting the intermediate pose data by taking the first pose data, the second pose data and the first relative position relationship as constraint conditions to obtain the target pose data.
In this embodiment, the intermediate pose data may be used as an initial value to be optimized, the first pose data and the second pose data may be used as pose true values in optimization, the first relative position relationship may be used as an optimization edge, and a pose optimization algorithm may be used to obtain the intermediate pose data. The pose optimization algorithm may be a cerees optimization algorithm, a g2o (General graph optimization) General graph optimization algorithm, and the like, which is not limited herein. The pose optimization algorithm used in the second adjustment process may be the same as or different from the pose optimization algorithm used in the second adjustment process, and is not limited herein.
According to the embodiment, the first relative position relation obtained by the point cloud data is added into the constraint condition, so that the pose of the target object in the moving process can be optimized by using the environment information, and accurate target pose data can be obtained.
Optionally, the first relative position relationship includes a first relative pose and a first information matrix, the first information matrix is used for reflecting the accuracy of the first relative pose, and the weight of the first relative pose is positively correlated with the accuracy of the first relative pose. The higher the accuracy of the first relative pose is, the larger the weight corresponding to the first relative pose in the adjustment process is, and the first relative pose with high accuracy has a greater effect on the adjustment process, so that the accuracy of the target pose data is improved.
In another implementation, S606 may include: and adjusting the intermediate pose data by taking the first pose data, the second pose data, the first relative position relationship and the second relative position relationship as constraint conditions to obtain the target pose data, wherein the second relative position relationship is determined according to inertial measurement data acquired between the moments of acquiring the adjacent two-time point cloud data.
In this embodiment, a specific implementation procedure of S404 in the embodiment shown in fig. 4 may be referred to for the determination manner of the second relative position relationship, which is not limited herein. In the second adjustment process, the intermediate pose data may be used as an initial value to be optimized, the first pose data and the second pose data may be used as pose true values in optimization, the first relative position relationship and the second relative position relationship may be used as sides of optimization, and a pose optimization algorithm may be used to obtain the intermediate pose data. The pose Optimization algorithm may be a cerees Optimization algorithm, a g2o (General Graph Optimization) General Graph Optimization algorithm, and the like, which is not limited herein. The pose optimization algorithm used in the second adjustment process may be the same as or different from the pose optimization algorithm used in the second adjustment process, and is not limited herein.
In the embodiment, the first relative position relationship obtained by the point cloud data and the second phase position relationship obtained by the inertial measurement data are added to the constraint condition, so that the pose of the target object in the moving process can be optimized by using the environmental information and the inertial measurement information of the target object, and accurate target pose data can be obtained.
And S607, generating an electronic map corresponding to the target area according to the target pose data.
In this embodiment, S607 is similar to S203 in the embodiment of fig. 2, and is not described herein again.
According to the method and the device, point cloud registration is carried out according to point cloud data acquired twice in the point cloud data to obtain the first relative position relation, then secondary adjustment is carried out on the intermediate pose data according to the first relative position relation, and the pose data of the target object can be adjusted by utilizing the environment information acquired in the moving process of the target object, so that the accuracy of the pose data is improved, and the accuracy of the electronic map is further improved.
The embodiment obtains high-precision pose through two times of adjustment, and reduces the requirement on the inertial measurement unit; the intermediate pose data obtained by the first adjustment is used as an initial value of point cloud registration, so that the success rate and the accuracy of point cloud registration are improved; and the pose of the point cloud registration correction acquisition device in other five degrees of freedom except the advancing direction of the target object is introduced, so that more accurate pose is obtained. According to the embodiment, a high-precision electronic map of a site with poor satellite signals, such as a tunnel, an underground parking lot and the like, can be constructed, and positioning, planning, navigation, control and the like can be further realized according to the generated electronic map.
Fig. 7 is a schematic structural diagram of an apparatus for generating an electronic map according to an embodiment of the present application. As shown in fig. 7, the apparatus 70 for generating an electronic map includes: an acquisition module 701 and a processing module 702.
The acquiring module 601 is configured to acquire pose data of a target object in a moving process, where the pose data includes pose data of the target object to be adjusted in a target area and reference pose data of the target object outside the target area.
And the processing module 602 is configured to adjust the pose data to be adjusted according to the reference pose data to obtain target pose data.
The processing module 602 is further configured to generate an electronic map corresponding to the target area according to the target pose data.
The method comprises the steps of firstly obtaining pose data of a target object in the moving process, wherein the pose data comprise pose data to be adjusted of the target object in a target area and reference pose data of the target object outside the target area, then adjusting the pose data to be adjusted according to the reference pose data to obtain target pose data, and generating an electronic map corresponding to the target area according to the target pose data. According to the method and the device, the pose data to be adjusted of the target object in the target area is adjusted by utilizing the reference pose data of the target object outside the target area, so that the pose data of the target object in the target area is more accurate, and the accuracy of the generated electronic map is improved.
Optionally, the reference pose data comprises first pose data comprising pose data of a first position before the target object enters the target area and second pose data comprising pose data of a second position after the target object leaves the target area;
the pose data to be adjusted comprises pose data of a plurality of third positions of the target object in the moving process of the target object in the target area.
Optionally, the processing module 602 is specifically configured to:
acquiring point cloud data acquired by the target object, wherein the point cloud data comprises first point cloud data acquired by the target object at the first position, second point cloud data acquired by the target object at the second position and third point cloud data acquired by the target object at a plurality of third positions;
acquiring inertial measurement data of the target object in the target area;
adjusting at least part of the pose data to be adjusted according to the reference pose data, the point cloud data and the inertial measurement data to obtain target pose data corresponding to at least part of the pose to be adjusted
Optionally, the processing module 602 is specifically configured to:
adjusting at least part of the pose data to be adjusted according to the first pose data, the second pose data and the inertial measurement data to obtain intermediate pose data corresponding to at least part of the pose data to be adjusted;
and adjusting the intermediate pose data according to the point cloud data to obtain target pose data corresponding to the intermediate pose.
Optionally, the processing module 602 is specifically configured to:
performing point cloud registration according to point cloud data acquired twice in the point cloud data to obtain a first relative position relation of the point cloud data acquired twice in the moving process of the target object;
and adjusting the intermediate pose data according to the first relative position relationship, the first pose data and the second pose data to obtain the target pose data.
Optionally, the processing module 602 is specifically configured to:
and carrying out point cloud registration according to the point cloud data acquired twice in the adjacent point cloud data and the intermediate pose data.
Optionally, the processing module 602 is specifically configured to:
and adjusting the intermediate pose data by taking the first pose data, the second pose data and the first relative position relationship as constraint conditions to obtain the target pose data.
Optionally, the processing module 602 is specifically configured to:
according to inertia measurement data acquired between the time of acquiring the point cloud data of two adjacent times, determining a second relative position relation of the point cloud data of two adjacent times of the target object in the moving process;
and adjusting the pose data to be adjusted by taking the first pose data, the second pose data and the second relative position relationship as constraint conditions to obtain the intermediate pose data.
Optionally, the processing module 602 is specifically configured to:
and adjusting the intermediate pose data by taking the first pose data, the second pose data, the first relative position relationship and the second relative position relationship as constraint conditions to obtain the target pose data, wherein the second relative position relationship is determined according to inertial measurement data acquired between the moments of acquiring the adjacent two-time point cloud data.
Optionally, the first relative position relationship includes a first relative pose and a first information matrix, the first information matrix is used for reflecting the accuracy of the first relative pose, and the weight of the first relative pose is positively correlated with the accuracy of the first relative pose;
and/or the second relative position relation comprises a second relative pose and a second information matrix, the second information matrix is used for reflecting the accuracy of the second relative pose, and the weight of the second relative pose is positively correlated with the accuracy of the second relative pose.
Optionally, the electronic map corresponding to the target area includes a first electronic map corresponding to the target area and a second electronic map corresponding to the target area;
the processing module is specifically configured to:
generating the first electronic map according to the target pose data;
generating the second electronic map according to the reference pose data;
and splicing the first electronic map and the second electronic map to obtain the electronic map corresponding to the target area.
Optionally, the signal strength inside the target region is less than the signal strength outside the target region.
Optionally, the reference pose data is acquired in a first manner, the pose data to be adjusted is acquired in a second manner, and the accuracy of the reference pose data is greater than that of the pose data to be adjusted.
The apparatus for generating an electronic map provided in the embodiment of the present application may be configured to execute the method embodiments described above, and the implementation principle and the technical effect of the apparatus are similar, which are not described herein again.
Fig. 8 is a schematic hardware structure diagram of an electronic device according to an embodiment of the present application. As shown in fig. 8, the electronic device 80 provided in the present embodiment includes: at least one processor 801 and a memory 802. The electronic device 80 further comprises a communication component 803. The processor 801, the memory 802, and the communication unit 803 are connected by a bus 804.
In particular implementations, execution of the computer-executable instructions stored by the memory 802 by the at least one processor 801 causes the at least one processor 801 to perform the method of generating an electronic map as described above.
For a specific implementation process of the processor 801, reference may be made to the above method embodiments, which have similar implementation principles and technical effects, and details of this embodiment are not described herein again.
In the embodiment shown in fig. 8, it should be understood that the Processor may be a Central Processing Unit (CPU), other general purpose processors, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of a method disclosed in the incorporated application may be directly implemented by a hardware processor, or may be implemented by a combination of hardware and software modules in the processor.
The memory may comprise high speed RAM memory and may also include non-volatile storage NVM, such as at least one disk memory.
The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended ISA (EISA) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, the buses in the figures of the present application are not limited to only one bus or one type of bus.
The present application also provides a computer-readable storage medium, in which computer-executable instructions are stored, and when a processor executes the computer-executable instructions, the method for generating an electronic map as above is implemented.
The readable storage medium may be implemented by any type or combination of volatile or non-volatile memory devices, such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disks. Readable storage media can be any available media that can be accessed by a general purpose or special purpose computer.
An exemplary readable storage medium is coupled to the processor such the processor can read information from, and write information to, the readable storage medium. Of course, the readable storage medium may also be an integral part of the processor. The processor and the readable storage medium may reside in an Application Specific Integrated Circuits (ASIC). Of course, the processor and the readable storage medium may also reside as discrete components in the apparatus.
Finally, it should be noted that: the above embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present application.

Claims (20)

1. A method of generating an electronic map, the method comprising:
acquiring pose data of a target object in a moving process, wherein the pose data comprise pose data to be adjusted of the target object in a target area and reference pose data of the target object outside the target area;
adjusting the pose data to be adjusted according to the reference pose data to obtain target pose data;
and generating an electronic map corresponding to the target area according to the target pose data.
2. The method of claim 1, wherein the reference pose data comprises first pose data comprising pose data for the target object at a first position prior to entering the target region and second pose data comprising pose data for the target object at a second position after leaving the target region;
the pose data to be adjusted comprises pose data of a plurality of third positions of the target object in the moving process of the target object in the target area.
3. The method according to claim 2, wherein the adjusting the pose data to be adjusted according to the reference pose data to obtain target pose data comprises:
acquiring point cloud data acquired by the target object, wherein the point cloud data comprises first point cloud data acquired by the target object at the first position, second point cloud data acquired by the target object at the second position and third point cloud data acquired by the target object at a plurality of third positions;
acquiring inertial measurement data of the target object in the target area;
and adjusting at least part of the pose data to be adjusted according to the reference pose data, the point cloud data and the inertial measurement data to obtain target pose data corresponding to at least part of the pose to be adjusted.
4. The method of claim 3, wherein adjusting at least a portion of the pose data to be adjusted based on the reference pose data, the point cloud data, and the inertial measurement data to obtain target pose data corresponding to at least a portion of the pose to be adjusted comprises:
adjusting at least part of the pose data to be adjusted according to the first pose data, the second pose data and the inertial measurement data to obtain intermediate pose data corresponding to at least part of the pose data to be adjusted;
and adjusting the intermediate pose data according to the point cloud data to obtain target pose data corresponding to the intermediate pose.
5. The method of claim 4, wherein adjusting the intermediate pose data to obtain target pose data corresponding to the intermediate pose from the point cloud data comprises:
performing point cloud registration according to point cloud data acquired twice in the point cloud data to obtain a first relative position relation of the point cloud data acquired twice in the moving process of the target object;
and adjusting the intermediate pose data according to the first relative position relationship, the first pose data and the second pose data to obtain the target pose data.
6. The method of claim 5, wherein the performing point cloud registration from each two adjacent acquired point cloud data of the point cloud data comprises:
and carrying out point cloud registration according to the point cloud data acquired twice in the adjacent point cloud data and the intermediate pose data.
7. The method according to claim 5 or 6, wherein the adjusting the intermediate pose data according to the first relative positional relationship, the first reference pose, and the second reference pose to obtain the target pose data comprises:
and adjusting the intermediate pose data by taking the first pose data, the second pose data and the first relative position relationship as constraint conditions to obtain the target pose data.
8. The method according to any one of claims 4 to 7, wherein adjusting at least part of the pose data to be adjusted according to the first pose data, the second pose data, and the inertial measurement data to obtain intermediate pose data corresponding to at least part of the pose data to be adjusted comprises:
according to inertia measurement data acquired between the time of acquiring the point cloud data of two adjacent times, determining a second relative position relation of the point cloud data of two adjacent times of the target object in the moving process;
and adjusting the pose data to be adjusted by taking the first pose data, the second pose data and the second relative position relationship as constraint conditions to obtain the intermediate pose data.
9. The method according to claim 5 or 6, wherein the adjusting the intermediate pose data according to the first relative positional relationship, the first reference pose, and the second reference pose to obtain the target pose data comprises:
and adjusting the intermediate pose data by taking the first pose data, the second pose data, the first relative position relationship and the second relative position relationship as constraint conditions to obtain the target pose data, wherein the second relative position relationship is determined according to inertial measurement data acquired between the moments of acquiring the adjacent two-time point cloud data.
10. The method according to claim 8 or 9, wherein the first relative positional relationship comprises a first relative pose and a first information matrix, the first information matrix is used for reflecting the accuracy of the first relative pose, and the weight of the first relative pose is positively correlated with the accuracy of the first relative pose;
and/or the second relative position relation comprises a second relative pose and a second information matrix, the second information matrix is used for reflecting the accuracy of the second relative pose, and the weight of the second relative pose is positively correlated with the accuracy of the second relative pose.
11. The method according to any one of claims 1 to 10, wherein the electronic map corresponding to the target area comprises a first electronic map corresponding to the inside of the target area and a second electronic map corresponding to the outside of the target area;
generating an electronic map corresponding to the target area according to the target pose data, wherein the electronic map comprises:
generating the first electronic map according to the target pose data;
generating the second electronic map according to the reference pose data;
and splicing the first electronic map and the second electronic map to obtain the electronic map corresponding to the target area.
12. The method of any one of claims 1 to 11, wherein the signal strength inside the target region is less than the signal strength outside the target region.
13. The method according to any one of claims 1 to 11, characterized in that the reference pose data is acquired by a first means and the pose data to be adjusted is acquired by a second means, and the accuracy of the reference pose data is greater than the accuracy of the pose data to be adjusted.
14. An apparatus for generating an electronic map, comprising:
the system comprises an acquisition module, a display module and a control module, wherein the acquisition module is used for acquiring pose data of a target object in a moving process, and the pose data comprises pose data to be adjusted of the target object in a target area and reference pose data of the target object outside the target area;
the processing module is used for adjusting the pose data to be adjusted according to the reference pose data to obtain target pose data;
the processing module is further configured to generate an electronic map corresponding to the target area according to the target pose data.
15. The apparatus of claim 14, wherein the reference pose data comprises first pose data comprising pose data for the target object at a first position before entering the target region and second pose data comprising pose data for the target object at a second position after leaving the target region;
the pose data to be adjusted comprises pose data of a plurality of third positions of the target object in the moving process of the target object in the target area.
16. The apparatus of claim 15, wherein the processing module is specifically configured to:
acquiring point cloud data acquired by the target object, wherein the point cloud data comprises first point cloud data acquired by the target object at the first position, second point cloud data acquired by the target object at the second position and third point cloud data acquired by the target object at a plurality of third positions;
acquiring inertial measurement data of the target object in the target area;
and adjusting at least part of the pose data to be adjusted according to the reference pose data, the point cloud data and the inertial measurement data to obtain target pose data corresponding to at least part of the pose to be adjusted.
17. The apparatus of claim 16, wherein the processing module is specifically configured to:
adjusting at least part of the pose data to be adjusted according to the first pose data, the second pose data and the inertial measurement data to obtain intermediate pose data corresponding to at least part of the pose data to be adjusted;
and adjusting the intermediate pose data according to the point cloud data to obtain target pose data corresponding to the intermediate pose.
18. The apparatus of claim 17, wherein the processing module is specifically configured to:
performing point cloud registration according to point cloud data acquired twice in the point cloud data to obtain a first relative position relation of the point cloud data acquired twice in the moving process of the target object;
and adjusting the intermediate pose data according to the first relative position relationship, the first pose data and the second pose data to obtain the target pose data.
19. An electronic device, comprising: at least one processor and memory;
the memory stores computer-executable instructions;
the at least one processor executing the computer-executable instructions stored by the memory causes the at least one processor to perform the method of generating an electronic map of any of claims 1-10.
20. A computer-readable storage medium having stored thereon computer-executable instructions which, when executed by a processor, implement a method of generating an electronic map as claimed in any one of claims 1-10.
CN202010363616.0A 2020-04-30 2020-04-30 Method, device and equipment for generating electronic map and storage medium Active CN111552757B (en)

Priority Applications (3)

Application Number Priority Date Filing Date Title
CN202010363616.0A CN111552757B (en) 2020-04-30 2020-04-30 Method, device and equipment for generating electronic map and storage medium
PCT/CN2021/086721 WO2021218620A1 (en) 2020-04-30 2021-04-12 Map building method and apparatus, device and storage medium
JP2022505577A JP2022542289A (en) 2020-04-30 2021-04-12 Mapping method, mapping device, electronic device, storage medium and computer program product

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010363616.0A CN111552757B (en) 2020-04-30 2020-04-30 Method, device and equipment for generating electronic map and storage medium

Publications (2)

Publication Number Publication Date
CN111552757A true CN111552757A (en) 2020-08-18
CN111552757B CN111552757B (en) 2022-04-01

Family

ID=72002623

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010363616.0A Active CN111552757B (en) 2020-04-30 2020-04-30 Method, device and equipment for generating electronic map and storage medium

Country Status (1)

Country Link
CN (1) CN111552757B (en)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112084289A (en) * 2020-09-18 2020-12-15 湖北亿咖通科技有限公司 Track fusion method and device
CN112269187A (en) * 2020-09-28 2021-01-26 广州视源电子科技股份有限公司 Robot state detection method, device and equipment
CN112559539A (en) * 2020-12-07 2021-03-26 北京嘀嘀无限科技发展有限公司 Method and device for updating map data
CN113183153A (en) * 2021-04-27 2021-07-30 北京猎户星空科技有限公司 Map creating method, device, equipment and medium
CN114283200A (en) * 2021-12-30 2022-04-05 北京三快在线科技有限公司 Pose determination method and device, storage medium and electronic equipment
WO2024159613A1 (en) * 2023-02-02 2024-08-08 北京初速度科技有限公司 Target area positioning method and apparatus, electronic device, and medium

Citations (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20090150790A1 (en) * 2005-07-28 2009-06-11 Markus Wilhelm Navigation graph with strategic information
US8884950B1 (en) * 2011-07-29 2014-11-11 Google Inc. Pose data via user interaction
CN107167148A (en) * 2017-05-24 2017-09-15 安科机器人有限公司 Synchronous superposition method and apparatus
CN107845114A (en) * 2017-11-10 2018-03-27 北京三快在线科技有限公司 Construction method, device and the electronic equipment of map
CN108827249A (en) * 2018-06-06 2018-11-16 歌尔股份有限公司 A kind of map constructing method and device
CN108876854A (en) * 2018-04-27 2018-11-23 腾讯科技（深圳）有限公司 Method for relocating, device, equipment and the storage medium of camera posture tracing process
CN109545072A (en) * 2018-11-14 2019-03-29 广州广电研究院有限公司 Pose calculation method, device, storage medium and the system of map structuring
CN109814572A (en) * 2019-02-20 2019-05-28 广州市山丘智能科技有限公司 Localization for Mobile Robot builds drawing method, device, mobile robot and storage medium
CN110473259A (en) * 2019-07-31 2019-11-19 深圳市商汤科技有限公司 Pose determines method and device, electronic equipment and storage medium
CN110889808A (en) * 2019-11-21 2020-03-17 广州文远知行科技有限公司 Positioning method, device, equipment and storage medium
CN110906941A (en) * 2019-12-03 2020-03-24 苏州智加科技有限公司 Construction method and system of automatic driving map for long-distance tunnel
CN110988949A (en) * 2019-12-02 2020-04-10 北京京东乾石科技有限公司 Positioning method, positioning device, computer readable storage medium and mobile device

Patent Citations (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20090150790A1 (en) * 2005-07-28 2009-06-11 Markus Wilhelm Navigation graph with strategic information
US8884950B1 (en) * 2011-07-29 2014-11-11 Google Inc. Pose data via user interaction
CN107167148A (en) * 2017-05-24 2017-09-15 安科机器人有限公司 Synchronous superposition method and apparatus
CN107845114A (en) * 2017-11-10 2018-03-27 北京三快在线科技有限公司 Construction method, device and the electronic equipment of map
CN108876854A (en) * 2018-04-27 2018-11-23 腾讯科技（深圳）有限公司 Method for relocating, device, equipment and the storage medium of camera posture tracing process
CN108827249A (en) * 2018-06-06 2018-11-16 歌尔股份有限公司 A kind of map constructing method and device
CN109545072A (en) * 2018-11-14 2019-03-29 广州广电研究院有限公司 Pose calculation method, device, storage medium and the system of map structuring
CN109814572A (en) * 2019-02-20 2019-05-28 广州市山丘智能科技有限公司 Localization for Mobile Robot builds drawing method, device, mobile robot and storage medium
CN110473259A (en) * 2019-07-31 2019-11-19 深圳市商汤科技有限公司 Pose determines method and device, electronic equipment and storage medium
CN110889808A (en) * 2019-11-21 2020-03-17 广州文远知行科技有限公司 Positioning method, device, equipment and storage medium
CN110988949A (en) * 2019-12-02 2020-04-10 北京京东乾石科技有限公司 Positioning method, positioning device, computer readable storage medium and mobile device
CN110906941A (en) * 2019-12-03 2020-03-24 苏州智加科技有限公司 Construction method and system of automatic driving map for long-distance tunnel

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
迟洪鹏等: "基于环境自识别的地下无轨车辆定位导航算法研究", 《公路交通科技》 *

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112084289A (en) * 2020-09-18 2020-12-15 湖北亿咖通科技有限公司 Track fusion method and device
CN112269187A (en) * 2020-09-28 2021-01-26 广州视源电子科技股份有限公司 Robot state detection method, device and equipment
CN112269187B (en) * 2020-09-28 2024-05-14 广州视源电子科技股份有限公司 Robot state detection method, device and equipment
CN112559539A (en) * 2020-12-07 2021-03-26 北京嘀嘀无限科技发展有限公司 Method and device for updating map data
CN113183153A (en) * 2021-04-27 2021-07-30 北京猎户星空科技有限公司 Map creating method, device, equipment and medium
CN114283200A (en) * 2021-12-30 2022-04-05 北京三快在线科技有限公司 Pose determination method and device, storage medium and electronic equipment
CN114283200B (en) * 2021-12-30 2024-10-25 北京三快在线科技有限公司 Pose determining method and device, storage medium and electronic equipment
WO2024159613A1 (en) * 2023-02-02 2024-08-08 北京初速度科技有限公司 Target area positioning method and apparatus, electronic device, and medium

Also Published As

Publication number Publication date
CN111552757B (en) 2022-04-01

Similar Documents

Publication Publication Date Title
CN111552757B (en) Method, device and equipment for generating electronic map and storage medium
CN113424232B (en) Three-dimensional point cloud map construction method, system and equipment
US11802769B2 (en) Lane line positioning method and apparatus, and storage medium thereof
US10788830B2 (en) Systems and methods for determining a vehicle position
CN111427061A (en) Robot mapping method and device, robot and storage medium
CN114636993A (en) External parameter calibration method, device and equipment for laser radar and IMU
CN114111775B (en) Multi-sensor fusion positioning method and device, storage medium and electronic equipment
CN112985404A (en) Method, device, equipment and medium for generating crowdsourcing map of parking lot
CN113984044A (en) Vehicle pose acquisition method and device based on vehicle-mounted multi-perception fusion
CN115236714A (en) Multi-source data fusion positioning method, device and equipment and computer storage medium
CN115164936A (en) Global pose correction method and device for point cloud splicing in high-precision map manufacturing
CN110794434B (en) Pose determination method, device, equipment and storage medium
CN114440864A (en) Method and device for positioning automobile
CN117606506A (en) Vehicle positioning method, device, electronic equipment and medium
CN113503883B (en) Method for collecting data for constructing map, storage medium and electronic equipment
Hariz et al. High-Resolution Mobile Mapping Platform Using 15-mm Accuracy LiDAR and SPAN/TerraStar C-PRO Technologies
Elsayed et al. From Stationary to Mobile: Unleashing the Full Potential of Terrestrial LiDAR through Sensor Integration
Noureldin et al. a Framework for Multi-Sensor Positioning and Mapping for Autonomous Vehicles
CN114897942A (en) Point cloud map generation method and device and related storage medium
CN111928863A (en) High-precision map data acquisition method, device and system
Li et al. AutoMine: A Multimodal Dataset for Robot Navigation in Open‐Pit Mines
JP2020073931A (en) Information processing device, control method, program, and storage media
CN113008245B (en) Positioning information fusion method and device and computer server
CN117953007B (en) Linear motion compensation control method based on image matching
CN116659487B (en) Pose adjustment method, pose adjustment device, electronic equipment and readable storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant