CN119533442A - Local driving map construction method, system, electronic equipment and storage medium - Google Patents
Local driving map construction method, system, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN119533442A CN119533442A CN202411431369.8A CN202411431369A CN119533442A CN 119533442 A CN119533442 A CN 119533442A CN 202411431369 A CN202411431369 A CN 202411431369A CN 119533442 A CN119533442 A CN 119533442A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- map
- lane
- gps positioning
- driving map
- 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.)
- Pending
Links
Landscapes
- Navigation (AREA)
Abstract
The invention provides a local driving map construction method, a system, electronic equipment and a storage medium, wherein the method comprises the steps of generating an initial driving map according to lane lines perceived by a vehicle-mounted sensor bev; the method comprises the steps of obtaining a medium-precision map in a preset range according to the current GPS positioning of a vehicle, matching lane lines of the medium-precision map with lane lines in an initial driving map, calculating GPS position correction of the vehicle, compensating the GPS positioning of the vehicle according to the GPS position correction of the vehicle, carrying out GPS positioning estimation based on the speed and imu perception data of the vehicle, updating projection points of a planning path in the initial driving map based on GPS positioning estimation results, and projecting obstacle, traffic light and signpost information perceived by a vehicle-mounted sensor into the initial driving map to obtain a local driving map. According to the scheme, the automatic driving cost can be reduced, the positioning accuracy and the perception accuracy of the vehicle are guaranteed, and the secondary route planning can be realized without depending on a high-accuracy map.
Description
Technical Field
The invention belongs to the technical field of automatic driving, and particularly relates to a local driving map construction method, a system, electronic equipment and a storage medium.
Background
With the gradual maturity of the automatic driving technology, the practical application on various automobiles is also more and more common. The automatic driving technology generally depends on a high-precision map and a fusion perception technology, and a local driving map formed based on the high-precision map and obstacle perception can provide a reference for driving decision planning, so that a vehicle can conveniently make a more accurate and intelligent driving decision.
However, in the commercialization process of the automatic driving technology, one type of scheme needs to adopt a high-precision map, an inertial navigation rtk device and the like, the high-precision map and the high-precision positioning device are usually high in cost and highly depend on the precision of the positioning device, the error is large when the signal is poor, and in the other type of scheme which depends on the visual perception bev, the perception stability is easily influenced by the external environment, and due to the lack of a global map, navigation and secondary route planning cannot be performed, and only basic lane keeping and other functions can be executed.
Disclosure of Invention
In view of the above, the embodiments of the present invention provide a local driving map construction method, system, electronic device and storage medium, which are used for solving the problems that the existing automatic driving scheme is high in cost, depends on high-precision positioning, and cannot perform secondary route planning.
In a first aspect of an embodiment of the present invention, there is provided a local driving map construction method, including:
Generating an initial driving map according to lane lines perceived by the vehicle-mounted sensor bev;
Acquiring a middle-precision map within a preset range according to the current GPS positioning of the vehicle, wherein the middle-precision map is a map with errors within the preset range;
Matching a lane line of the medium-precision map with a lane line of the initial driving map, and calculating a GPS (global positioning system) position correction of the vehicle;
Compensating the GPS positioning of the vehicle according to the GPS position correction quantity of the vehicle, performing GPS positioning estimation based on the vehicle speed and imu perception data, and updating projection points of a planning path in an initial driving map based on a GPS positioning estimation result;
and projecting the obstacle, traffic light and sign information perceived by the vehicle-mounted sensor into the initial driving map to obtain the local driving map.
In a second aspect of the embodiment of the present invention, there is provided a local driving map construction system including:
the map generation module is used for generating an initial driving map according to the lane lines perceived by the vehicle-mounted sensor bev;
the map acquisition module is used for acquiring a middle-precision map within a preset range according to the current GPS positioning of the vehicle, wherein the middle-precision map is a map with an error within the preset range;
The matching correction module is used for matching the lane line of the medium-precision map with the lane line in the initial driving map and calculating the GPS position correction of the vehicle;
the positioning compensation module is used for compensating the GPS positioning of the vehicle according to the GPS position correction quantity of the vehicle;
the positioning estimation module is used for carrying out GPS positioning estimation based on the vehicle speed and imu perception data, and updating projection points of the planning path in the initial driving map based on a GPS positioning estimation result;
and the fusion projection module is used for projecting the obstacle, traffic light and sign information perceived by the vehicle-mounted sensor into the initial driving map to obtain the local driving map.
In a third aspect of the embodiments of the present invention, there is provided an electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps of the method according to the first aspect of the embodiments of the present invention when the computer program is executed by the processor.
In a fourth aspect of the embodiments of the present invention, there is provided a computer readable storage medium storing a computer program which, when executed by a processor, implements the steps of the method provided by the first aspect of the embodiments of the present invention.
In the embodiment of the invention, the local driving map is constructed based on the vehicle bev perception, the own GPS positioning and the medium-precision map, so that not only can the low-cost automatic driving and route planning be realized, but also the vehicle positioning precision and the vehicle perception precision can be ensured, and the influence caused by GPS signals is avoided. The local driving map constructed based on fusion not only has navigation data of primary planning, but also can realize secondary route planning of the vehicle.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings described below are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort to a person skilled in the art.
Fig. 1 is a schematic flow chart of a local driving map construction method according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a local driving map construction system according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, features and advantages of the present invention more comprehensible, the technical solutions in the embodiments of the present invention are described in detail below with reference to the accompanying drawings, and it is apparent that the embodiments described below are only some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
It should be understood that the term "comprising" and other similar meaning in the description of the invention or the claims and the above-mentioned figures is intended to cover a non-exclusive inclusion, such as a process, method or system, apparatus comprising a series of steps or elements, without limitation to the listed steps or elements. Furthermore, "first" and "second" are used to distinguish between different objects and are not used to describe a particular order.
Referring to fig. 1, a flow chart of a local driving map construction method provided by an embodiment of the present invention includes:
S101, generating an initial driving map according to lane lines perceived by an on-vehicle sensor bev;
The vehicle-mounted sensor can comprise a camera, a radar (such as millimeter wave radar and laser radar) and the like, and can output information such as positions, distances and the like of objects around the vehicle through vision fusion sensing, for example, objects such as lane lines, vehicles, pedestrians, traffic signs and the like can be sensed through the vehicle-mounted sensor. bev (Bird's-Eye-View) perception refers to converting vehicle-mounted sensor perception data into a top View representation.
The method comprises the steps of obtaining lane lines perceived by a vehicle-mounted sensor bev, obtaining lane line curves in a driving map through polynomial fitting, obtaining topological relations of the lane lines, and generating a lane center line under a vehicle coordinate system according to the lane line curves and the lane line topological relations so as to form an initial driving map.
For example, the vehicle perceives the lane lines c0, c1, c2, c3 to be obtained through bev, obtains a plurality of lane line curves through three-degree polynomial fitting, and generates a lane center line according to the lane line topological relation.
S102, acquiring a middle-precision map within a preset range according to the GPS positioning of the current vehicle, wherein the middle-precision map is a map with errors within the preset range;
The coordinates of utm (Universal Transverse Mercator GridSystem, namely a universal transverse ink card support grid system) of the GPS positioning data of the vehicle are matched with the coordinates of utm in the medium-precision map, and the medium-precision map in a preset range near the positioning point of the vehicle is acquired, namely, the map data in a certain range (for example, 40 m) around the positioning point of the vehicle is acquired by taking the positioning point of the vehicle as the center.
Compared with a common map, the medium-precision map has higher precision and more road details (such as traffic lights, scribing lines, lane directions, overpass directions and the like), but is lower than the high-precision map (the error is a few centimeters), and the details are fewer. The predetermined range for the medium precision map is typically within 50cm error.
The method comprises the steps of obtaining a medium-precision map lane topological relation, a lane line index of a lane where a vehicle is located in the same direction lane and a transverse distance from the vehicle to a lane center line.
S103, matching a lane line of the medium-precision map with a lane line in the initial driving map, and calculating a GPS (global positioning system) position correction of the vehicle;
The vehicle GPS position correction may include a lateral-longitudinal distance correction and a heading difference. And carrying out coordinate conversion and projection on the matched lane lines and vehicle positioning points based on the lane line index in the medium-precision map and the lane line introduction lane line matching in the driving map, and carrying out GPS position correction calculation on the driving map.
Specifically, after the lane index of the medium-precision map is matched with the lane index of the initial driving map, the lane coordinates and the GPS positioning coordinates of the medium-precision map are converted into a vehicle body coordinate system and projected into the initial driving map, and the transverse and longitudinal distance correction and the heading difference between the positioning point perceived by the vehicle bev and the GPS positioning projection point are calculated.
S104, compensating the GPS positioning of the vehicle according to the GPS position correction quantity of the vehicle, performing GPS positioning estimation based on the vehicle speed and imu perception data, and updating projection points of the planned path in the initial driving map based on the GPS positioning estimation;
Because the vehicle GPS output positioning has deviation with the actual vehicle positioning, the vehicle GPS positioning needs to be supplemented and corrected to ensure the accuracy of the vehicle GPS positioning.
Specifically, the yaw difference value in the GPS position correction is obtained, the deviation difference value is compensated to the yaw angle of the GPS positioning of the vehicle, the transverse compensation value of the transverse distance correction under the utm (namely the universal transverse ink card support grid system)) coordinate system is calculated based on the corrected yaw angle, the transverse compensation value is compensated to the GPS positioning point of the vehicle, the longitudinal compensation value of the longitudinal distance correction under the utm coordinate system is calculated based on the curvature of the lane stop line or the lane line, and the longitudinal compensation value is compensated to the GPS positioning point of the vehicle.
When the vehicle is perceived to be positioned near the stop line of the intersection, the longitudinal distance of the GPS positioning point is corrected according to the distance from the vehicle to the stop line perceived by the vehicle bev and the distance from the GPS positioning point to the stop line in the medium-precision map. When no stop line exists, extracting bev recognized front multiple lane line curvature characteristic points to match corresponding lane line curvatures on a map (such as scenes of an urban road with radian, a curve, a shunt opening closing mouth and the like), thereby calculating a longitudinal distance error compensation value, and continuously compensating transverse distance errors when a straight road is in no stop line until the road meeting the curve and the like can be subjected to curvature matching, and then calculating and updating the longitudinal distance error compensation value. The compensated GPS position is utm coordinates, which need to be converted to the vehicle body coordinate system.
Preferably, the positioning point is corrected every 1s based on the frequency of the GPS positioning, and the GPS position correction amount is applied to the positioning output from the GPS.
The vehicle position change quantity and the heading change quantity per second are calculated based on the vehicle speed and imu perception data, and are converted into compensation values under a utm coordinate system to carry out interpolation compensation and estimation on GPS positioning.
Based on the angular velocity and acceleration output by an imu (Inertial Measurement Unit, i.e. inertial measurement unit) sensor, the GPS position of the vehicle can be estimated by combining the current speed and the current GPS positioning of the vehicle, so as to update the planned path in real time, and further update the projection point of the planned path on the driving map.
Optionally, when the GPS signal strength is detected to be lower than the preset threshold, the vehicle GPS location in the local driving map is continuously updated according to the estimated GPS location.
When the GPS signal is worse, the stability of the GPS signal can be ensured and the GPS signal is kept updated through GPS positioning estimation.
S105, projecting the obstacle, traffic light and sign information perceived by the vehicle-mounted sensor into the initial driving map to obtain the local driving map.
The obstacle is generally a common object on the road, and may be a motor vehicle, a non-motor vehicle, a pedestrian, or the like, which is not particularly limited herein. The vehicle-mounted sensor can sense obstacles, traffic lights, traffic signs and the like on the road besides being capable of sensing the lane lines bev.
The method comprises the steps of forming a bounding box by the central point coordinates, length, width and height of perceived and output obstacles in a driving map, determining the direction of the bounding box by speed and heading, projecting the relative coordinate values of predicted trajectories of the obstacles into a local driving map, projecting the coordinates of a signboard and traffic lights into the driving map, and storing semantic information and state information.
In this embodiment, based on the GPS module signal of the quasi-domain control and the medium-precision map with low cost, the primary planning of the medium-precision map and bev sensing information are combined to generate the local map to realize secondary planning, so that the implementation cost is low, the GPS positioning precision and bev sensing precision can be ensured, and meanwhile, when the GPS signal is poor, the local driving map construction and the automatic driving of the vehicle can be realized.
It should be understood that the sequence number of each step in the above embodiment does not mean the sequence of execution, and the execution sequence of each process should be determined by its function and internal logic, and should not be construed as limiting the implementation process of the embodiment of the present invention.
Fig. 2 is a schematic structural diagram of a local driving map building system according to an embodiment of the present invention, where the system includes:
the map generation module 210 is configured to generate an initial driving map according to the lane lines sensed by the vehicle-mounted sensor bev;
wherein the map generation module 210 includes:
The lane line generating unit is used for acquiring lane lines perceived by the vehicle-mounted sensor bev and obtaining a lane line curve in the driving map through polynomial fitting;
The lane center line generating unit is used for acquiring the lane line topological relation and generating a lane center line under the vehicle coordinate system according to the lane line curve and the lane line topological relation.
The map obtaining module 220 is configured to obtain a middle-precision map within a predetermined range according to a current vehicle GPS positioning, where the middle-precision map is a map with an error within the predetermined range;
The method comprises the steps of obtaining a medium-precision map lane topological relation, a lane line index of a lane where a vehicle is located in the same direction lane and a transverse distance from the vehicle to a lane center line.
The matching correction module 230 is configured to match a lane line of the medium-precision map with a lane line in the initial driving map, and calculate a vehicle GPS position correction;
Specifically, after the lane index of the medium-precision map is matched with the lane index of the initial driving map, the lane coordinates and the GPS positioning coordinates of the medium-precision map are converted into a vehicle body coordinate system and projected into the initial driving map, and the transverse and longitudinal distance correction and the heading difference between the positioning point perceived by the vehicle bev and the GPS positioning projection point are calculated.
A positioning compensation module 240 for compensating the vehicle GPS positioning according to the vehicle GPS position correction;
wherein the positioning compensation module 240 comprises:
A yaw angle compensation unit for acquiring a yaw difference value in the GPS position correction amount and compensating the deviation difference value to a yaw angle of GPS positioning of the vehicle;
the transverse distance compensation unit is used for calculating a transverse compensation value of the transverse distance correction quantity under a utm coordinate system based on the corrected yaw angle and compensating the transverse compensation value to a GPS positioning point of the vehicle;
a longitudinal distance compensation unit for calculating a longitudinal compensation value of a longitudinal distance correction amount under utm coordinate system based on the lane stop line or the lane line curvature, and compensating the longitudinal compensation value to a GPS positioning point of the vehicle
The positioning estimation module 250 is used for performing GPS positioning estimation based on the vehicle speed and imu perception data, and updating projection points of the planning path in the initial driving map based on a GPS positioning estimation result;
wherein the performing GPS location estimation based on the vehicle speed and imu awareness data includes:
And calculating the position change quantity and the course change quantity of the vehicle per second based on the vehicle speed and imu perception data, converting the position change quantity and the course change quantity of the vehicle into compensation values under a utm coordinate system, and carrying out interpolation compensation and estimation on GPS positioning.
Optionally, when the GPS signal strength is detected to be lower than the preset threshold, the vehicle GPS location in the local driving map is continuously updated according to the estimated GPS location.
The fusion projection module 260 is configured to project the obstacle, traffic light and sign information sensed by the vehicle-mounted sensor into the initial driving map, and obtain a local driving map.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described system and module may refer to corresponding procedures in the foregoing method embodiments, which are not described herein again.
Fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present invention. The electronic device is used for constructing a local driving map. As shown in fig. 3, the electronic device 3 of this embodiment includes a memory 310, a processor 320, and a system bus 330, the memory 310 including an executable program 3101 stored thereon, and it will be understood by those skilled in the art that the electronic device structure shown in fig. 3 is not limiting of the electronic device and may include more or less components than illustrated, or may combine some components, or a different arrangement of components.
The following describes the respective constituent elements of the electronic device in detail with reference to fig. 3:
The memory 310 may be used to store software programs and modules, and the processor 320 may execute various functional applications and data processing of the electronic device by executing the software programs and modules stored in the memory 310. The memory 310 may mainly include a storage program area that may store an operating system, an application program required for at least one function (such as a sound playing function, an image playing function, etc.), etc., and a storage data area that may store data created according to the use of the electronic device (such as cache data), etc. In addition, memory 310 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid-state storage device.
An executable program 3101 containing a network request method on the memory 310, the executable program 3101 may be divided into one or more modules/units stored in the memory 310 and executed by the processor 320 to implement driving map construction or the like, and the one or more modules/units may be a series of computer program instruction segments capable of accomplishing specific functions for describing the execution of the computer program 3101 in the electronic device 3. For example, the computer program 3101 may be divided into a map generating module, a map acquiring module, a matching correcting module, a positioning compensating module, a positioning estimating module, a fusion projecting module, and other functional modules.
Processor 320 is a control center of the electronic device that utilizes various interfaces and lines to connect various portions of the overall electronic device, perform various functions of the electronic device and process data by running or executing software programs and/or modules stored in memory 310, and invoking data stored in memory 310, thereby performing overall condition monitoring of the electronic device. Alternatively, processor 320 may include one or more processing units, and preferably, processor 320 may integrate an application processor that primarily processes operating systems, applications, etc., with a modem processor that primarily processes wireless communications. It will be appreciated that the modem processor described above may not be integrated into the processor 420.
The system bus 330 is used to connect functional components in the computer, and CAN transmit data information, address information, and control information, and the types of the system bus may be, for example, a PCI bus, an isa bus, and a CAN bus. Instructions from the processor 320 are transferred to the memory 310 through the bus, the memory 310 feeds back data to the processor 320, and the system bus 330 is responsible for data and instruction interaction between the processor 320 and the memory 310. Of course, the system bus 330 may also access other devices, such as a network interface, a display device, etc.
In an embodiment of the present invention, the executable program executed by the process 320 included in the electronic device includes:
generating an initial driving map according to the lane lines perceived by the vehicle-mounted sensor bev;
acquiring a medium-precision map in a preset range according to the current GPS positioning of the vehicle;
Matching a lane line of the medium-precision map with a lane line of the initial driving map, and calculating a GPS (global positioning system) position correction of the vehicle;
Compensating the GPS positioning of the vehicle according to the GPS position correction quantity of the vehicle, performing GPS positioning estimation based on the vehicle speed and imu perception data, and updating projection points of a planning path in an initial driving map based on a GPS positioning estimation result;
and projecting the obstacle, traffic light and sign information perceived by the vehicle-mounted sensor into the initial driving map to obtain the local driving map.
It will be clearly understood by those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described system, apparatus and module may refer to corresponding procedures in the foregoing method embodiments, which are not repeated herein.
In the foregoing embodiments, the descriptions of the embodiments are emphasized, and in part, not described or illustrated in any particular embodiment, reference is made to the related descriptions of other embodiments.
While the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those skilled in the art that the foregoing embodiments may be modified or equivalents may be substituted for some of the features thereof, and that the modifications or substitutions do not depart from the spirit and scope of the embodiments of the invention.
Claims (10)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411431369.8A CN119533442A (en) | 2024-10-14 | 2024-10-14 | Local driving map construction method, system, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411431369.8A CN119533442A (en) | 2024-10-14 | 2024-10-14 | Local driving map construction method, system, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN119533442A true CN119533442A (en) | 2025-02-28 |
Family
ID=94707789
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411431369.8A Pending CN119533442A (en) | 2024-10-14 | 2024-10-14 | Local driving map construction method, system, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN119533442A (en) |
-
2024
- 2024-10-14 CN CN202411431369.8A patent/CN119533442A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11307040B2 (en) | Map information provision system | |
| CN110160542B (en) | Method and device for positioning lane line, storage medium and electronic device | |
| US9965699B2 (en) | Methods and systems for enabling improved positioning of a vehicle | |
| CN112009484B (en) | Method and system for determining driving assistance data | |
| CN110763246A (en) | Automatic driving vehicle path planning method and device, vehicle and storage medium | |
| CN110530372B (en) | Positioning method, path determining device, robot and storage medium | |
| JP6956268B2 (en) | Driving environment information generation method, driving control method, driving environment information generation device | |
| US10963708B2 (en) | Method, device and computer-readable storage medium with instructions for determining the lateral position of a vehicle relative to the lanes of a road | |
| CN110555801B (en) | A correction method, terminal and storage medium for track deduction | |
| US11281228B2 (en) | Method and device for determining a position of a transportation vehicle | |
| JP7580155B2 (en) | Method, device, electronic device, and storage medium for determining traffic flow information | |
| JP2010086544A (en) | Creating geometry for advanced driver assistance system | |
| KR102115004B1 (en) | Apparatus and method for generating three dimensional map using aerial images | |
| CN117382675A (en) | Method, device, vehicle and storage medium for generating drivable area of road | |
| EP4230961B1 (en) | Vehicle localization using map and vision data | |
| CN115290101B (en) | Vehicle positioning method and system | |
| CN113306559A (en) | Compensation for vertical road camber in road shape estimation | |
| CN116147605A (en) | Vehicle automatic driving map generation method, device, equipment and storage medium | |
| EP4336468A1 (en) | Parameterization method for point cloud data | |
| US12214785B2 (en) | Vehicle localization to map data | |
| CN113390422B (en) | Automobile positioning method and device and computer storage medium | |
| CN119533442A (en) | Local driving map construction method, system, electronic equipment and storage medium | |
| JP2001041754A (en) | Map display device and its method | |
| CN115096330A (en) | Map change detection method and device, computer-readable storage medium and terminal | |
| CN117635674A (en) | Map data processing method and device, storage medium and electronic equipment |
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 |