CN117705129A - Multi-sensor fusion positioning method, system, electronic equipment and storage medium - Google Patents
Multi-sensor fusion positioning method, system, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN117705129A CN117705129A CN202311605983.7A CN202311605983A CN117705129A CN 117705129 A CN117705129 A CN 117705129A CN 202311605983 A CN202311605983 A CN 202311605983A CN 117705129 A CN117705129 A CN 117705129A
- Authority
- CN
- China
- Prior art keywords
- positioning
- vehicle
- lane
- sensor
- acquiring
- 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
- 230000004927 fusion Effects 0.000 title claims abstract description 46
- 238000000034 method Methods 0.000 title claims abstract description 37
- 230000004438 eyesight Effects 0.000 claims abstract description 29
- 238000004364 calculation method Methods 0.000 claims description 18
- 238000012937 correction Methods 0.000 abstract description 5
- 238000010586 diagram Methods 0.000 description 18
- 238000004590 computer program Methods 0.000 description 11
- 230000000007 visual effect Effects 0.000 description 8
- 230000006870 function Effects 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 230000008447 perception Effects 0.000 description 3
- 230000004075 alteration Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000016776 visual perception Effects 0.000 description 1
Landscapes
- Navigation (AREA)
Abstract
The invention provides a multi-sensor fusion positioning method, a system, electronic equipment and a storage medium, wherein the method comprises the steps of acquiring a first positioning of a vehicle by a vehicle-mounted inertial navigation sensor, acquiring a current lane of the vehicle on a map based on the first positioning and a medium-precision map navigation system, acquiring a relative position of the vehicle in the current lane based on a vehicle-mounted vision sensor, calculating a second positioning of the vehicle based on the relative position, and calculating a positioning deviation value by the first positioning and the second positioning, so that the vehicle-mounted inertial navigation sensor is subjected to positioning correction according to the positioning deviation value, and high-precision positioning information is output; the vehicle can be fused and positioned through the plurality of sensors in the medium-precision map system, so that high-precision positioning meeting the automatic driving requirement can be output through the medium-precision map, dependence of automatic driving on the high-precision map is reduced, the vehicle-mounted sensor is corrected, and the sensing precision of the vehicle-mounted sensor is improved.
Description
Technical Field
The invention relates to the technical field of map positioning, in particular to a multi-sensor fusion positioning method, a multi-sensor fusion positioning system, electronic equipment and a storage medium.
Background
The automatic driving technology is a technology which enables an automobile to autonomously sense the road environment and navigate and drive without manual operation. The core is that the computer can automatically control the automobile to run by means of artificial intelligence, visual computing, radar, monitoring device, global positioning system and the like.
Currently, there are two main routes for automatic driving: 1) Heavy map routes based on high-precision maps, but the high-precision map is too high in manufacturing and maintaining cost, slow in map updating and low in freshness and supervision of national laws and regulations, so that the difficulty of the high-precision map scheme in urban road landing is increased. 2) The re-perception route based on AI vision needs to rely on a powerful AI algorithm, perception data can fail under factors such as weather, shielding objects and the like, and the accuracy of the pure vision route can not meet the requirement of automatic driving in some scenes at present. Therefore, how to meet the positioning requirement of the automatic driving technology through a medium-precision map system and a multi-sensor combination is a problem to be solved.
Disclosure of Invention
Aiming at the technical problems existing in the prior art, the invention provides a multi-sensor fusion positioning method, a multi-sensor fusion positioning system, electronic equipment and a storage medium, which are used for solving the problem of how to meet the positioning requirement of an automatic driving technology through a medium-precision map system and multi-sensor combination.
In a first aspect of the present invention, there is provided a multi-sensor fusion positioning method applied to a vehicle equipped with a medium-precision map navigation system, a vehicle-mounted inertial navigation sensor, and a vehicle-mounted vision sensor, including:
acquiring a first positioning of the own vehicle based on the vehicle-mounted inertial navigation sensor;
acquiring map information corresponding to the first positioning from the medium-precision map navigation system based on the first positioning;
calculating a current lane of the own vehicle in the map information based on the first positioning;
acquiring the relative position of the self-vehicle on the current lane based on the vehicle-mounted vision sensor;
acquiring a second location of the own vehicle in the map information based on the relative position;
and calculating a positioning deviation value based on the first positioning and the second positioning, and positioning the vehicle based on the positioning deviation value and the vehicle-mounted inertial navigation sensor.
On the basis of the technical scheme, the invention can also make the following improvements.
Preferably, the step of calculating a current lane of the own vehicle in the map information based on the first positioning includes:
acquiring a plurality of lanes and a plurality of lane centerlines in the map information based on the first positioning;
and setting a lane corresponding to the lane center line with the smallest first positioning distance as a current lane where the own vehicle is located.
Preferably, the step of setting the lane corresponding to the lane center line with the smallest first positioning distance as the current lane where the own vehicle is located includes:
acquiring first projection points of the first positioning on the central lines of a plurality of lanes, and calculating the projection distance between the first positioning and each first projection point;
and acquiring a lane center line corresponding to the first projection point with the minimum projection distance, and setting a lane corresponding to the lane center line as a current lane of the own vehicle.
Preferably, the step of obtaining the first projection points of the first location on the plurality of lane center lines, and calculating the projection distance between the first location and each first projection point includes:
and respectively selecting two endpoints on the lane central lines, and calculating a first projection point of the first positioning on each lane central line based on the first positioning and the two endpoints by using a vector projection calculation method to obtain the projection distance between the first positioning and each first projection point.
Preferably, the step of acquiring the relative position of the own vehicle on the current lane based on the on-vehicle vision sensor includes:
and acquiring the distance from the vehicle to the left lane boundary line and/or the distance from the vehicle to the right lane boundary line of the current lane based on the vehicle-mounted vision sensor.
Preferably, the step of acquiring the second location of the own vehicle in the map information based on the relative position includes:
acquiring a second projection point of the first position on a lane central line of the current lane;
selecting two calculation points on the lane center line of the current lane, and calculating the second positioning of the vehicle based on the two calculation points, the second projection point, the left lane boundary line distance and/or the right lane boundary line distance.
Preferably, after the step of calculating a positioning deviation value based on the first positioning and the second positioning, and positioning the own vehicle based on the positioning deviation value and the vehicle-mounted inertial navigation sensor, the method includes:
and recalculating the positioning deviation value based on a preset calculation frequency, and positioning the vehicle based on the latest positioning deviation value and the vehicle-mounted inertial navigation sensor.
In a second aspect of the present invention, there is provided a multi-sensor fusion positioning system applied to a vehicle equipped with a medium-precision map navigation system, an on-vehicle inertial navigation sensor, and an on-vehicle vision sensor, comprising:
the first positioning acquisition module is used for acquiring a first positioning of the vehicle based on the vehicle-mounted inertial navigation sensor;
the map acquisition module is used for acquiring map information corresponding to the first positioning from the medium-precision map navigation system based on the first positioning;
a lane acquisition module for calculating a current lane of the own vehicle in the map information based on the first positioning;
the position acquisition module is used for acquiring the relative position of the self-vehicle on the current lane based on the vehicle-mounted vision sensor;
a second positioning calculation module for acquiring a second positioning of the own vehicle in the map information based on the relative position;
and the fusion positioning module is used for calculating a positioning deviation value based on the first positioning and the second positioning, and positioning the vehicle based on the positioning deviation value and the vehicle-mounted inertial navigation sensor.
In a third aspect of the present invention, there is provided an electronic device comprising a memory, and a processor configured to implement the steps of any of the multi-sensor fusion positioning methods of the first aspect when executing a computer management class program stored in the memory.
In a fourth aspect of the present invention, there is provided a computer readable storage medium having stored thereon a computer management class program which when executed by a processor implements the steps of any of the multi-sensor fusion positioning methods of the first aspect described above.
The invention provides a multi-sensor fusion positioning method, a multi-sensor fusion positioning system, electronic equipment and a storage medium, wherein the multi-sensor fusion positioning method comprises the following steps: acquiring a first positioning of the own vehicle based on the vehicle-mounted inertial navigation sensor; acquiring map information corresponding to the first positioning from the medium-precision map navigation system based on the first positioning; calculating a current lane of the own vehicle in the map information based on the first positioning; acquiring the relative position of the self-vehicle on the current lane based on the vehicle-mounted vision sensor; acquiring a second position of the own vehicle from the map information based on the relative position; and calculating a positioning deviation value based on the first positioning and the second positioning, and positioning the vehicle based on the positioning deviation value and the vehicle-mounted inertial navigation sensor. According to the invention, a first positioning of the self-vehicle is obtained through the vehicle-mounted inertial navigation sensor, a current lane of the self-vehicle on a map is obtained based on the first positioning and the medium-precision map navigation system, then the relative position of the self-vehicle in the current lane is obtained based on the vehicle-mounted visual sensor, a second positioning of the self-vehicle is calculated based on the relative position, and a positioning deviation value is calculated through the first positioning and the second positioning, so that the vehicle-mounted inertial navigation sensor is subjected to positioning correction according to the positioning deviation value, and high-precision positioning information is output; the vehicle can be fused and positioned in the medium-precision map system through the plurality of sensors, so that the medium-precision map can be positioned at high precision which meets the requirements of automatic driving, the dependence of the automatic driving on the high-precision map is reduced, the vehicle-mounted sensor is corrected, and the sensing precision of the vehicle-mounted sensor is improved.
Drawings
FIG. 1 is a flow chart of a multi-sensor fusion positioning method provided by the invention;
FIG. 2 is a diagram showing the comparison of original anchor points and fused anchor points of a vehicle;
FIG. 3 is a schematic diagram of a boundary line between a vehicle and a lane obtained by vehicle-mounted visual recognition provided by the invention;
FIG. 4 is a schematic diagram of calculating a positioning deviation value by a plurality of positioning points according to the present invention;
FIG. 5 is a schematic diagram showing a relationship between a first location P and a projection point n according to the present invention;
FIG. 6 is a diagram illustrating parameters of the first positioning P and the projection point n according to the present invention;
FIG. 7 is a schematic diagram showing the relationship between the projection point p and the second location n according to the present invention;
FIG. 8 is a schematic diagram of a multi-sensor fusion positioning system according to the present invention;
fig. 9 is a schematic hardware structure of one possible electronic device according to the present invention;
fig. 10 is a schematic hardware structure of a possible computer readable storage medium according to the present invention.
Detailed Description
The following describes in further detail the embodiments of the present invention with reference to the drawings and examples. The following examples are illustrative of the invention and are not intended to limit the scope of the invention.
Aiming at the problem that the high-precision map cannot meet the existing automatic driving requirement, in the embodiment, when the vehicle is provided with a medium-precision map system, a vehicle inertial navigation sensor and a vehicle-mounted vision sensor, the approximate positioning of the vehicle is obtained through the medium-precision map, and the approximate positioning is corrected through a fusion positioning mode, so that the accurate positioning of the vehicle is output on the medium-precision map, referring to fig. 1, fig. 1 is a flow chart of a multi-sensor fusion positioning method provided by the invention, as shown in fig. 1, the method comprises the following steps:
step S100: acquiring a first positioning of the own vehicle based on the vehicle-mounted inertial navigation sensor;
it should be noted that, the execution body of the method of this embodiment may be a computer terminal device having functions of data processing, network communication, and program running, for example: computers, vehicle-mounted computers, etc.; the present embodiment is not limited to this, and may be a server device having the same similar function, or may be a cloud server having a similar function. For easy understanding, the present embodiment and the following embodiments will be described by taking a vehicle-mounted computer as an example.
In general, the positioning information provided by the medium-precision map has an error of 50cm, so that a certain error exists between an original positioning point of the vehicle and the map, see fig. 2; in the embodiment, a plurality of sensors are fused to obtain a fused positioning point, and errors of the middle-precision map are corrected to realize the output of the high-precision map.
It will be appreciated that the first positioning described above is the original positioning of the vehicle, which may be subject to some error from the actual positioning of the vehicle.
Step S200: acquiring map information corresponding to the first positioning from the medium-precision map navigation system based on the first positioning;
specifically, after the first positioning is obtained, a map of the area where the first positioning is located is obtained by calling a map SDK of the medium-precision map, and a road with a connection relationship in the area where the first positioning is located is obtained by the lane connection relationship near the first positioning.
Step S300: calculating a current lane of the own vehicle in the map information based on the first positioning;
it will be appreciated that in general there will be multiple lanes on the road segment along which the vehicle is traveling, and in order to accurately calculate the location of the vehicle, it is also necessary to determine the current lane in which the vehicle is currently located, where the current lane of the vehicle may be obtained by the first location.
Specifically, by traversing the map, the distance from the first positioning point to the center line of each lane in the map is calculated, so that the lane corresponding to the lane center with the smallest distance between the first positioning point and the center line of the lane is obtained as the current lane.
Further, in order to accurately obtain the current lane of the own vehicle, the method further includes:
step S310: acquiring a plurality of lanes and a plurality of lane centerlines in the map information based on the first positioning;
step S320: and setting a lane corresponding to the lane center line with the smallest first positioning distance as a current lane where the own vehicle is located.
Further, the step of setting the lane corresponding to the lane center line with the smallest distance as the current lane further includes:
step S321: acquiring first projection points of the first positioning on the central lines of a plurality of lanes, and calculating the projection distance between the first positioning and each first projection point;
further, the step of calculating the projection distance further comprises selecting two endpoints on the lane center lines respectively, and calculating a first projection point of the first positioning on each lane center line based on the first positioning and the two endpoints by using a vector projection calculation method to obtain the projection distance between the first positioning and each first projection point.
Step S322: and acquiring a lane center line corresponding to the first projection point with the minimum projection distance, and setting a lane corresponding to the lane center line as a current lane of the own vehicle.
Step S400: acquiring the relative position of the self-vehicle on the current lane based on the vehicle-mounted vision sensor;
specifically, the distance from the vehicle to the left lane boundary line and/or the distance from the vehicle to the right lane boundary line of the current lane are obtained based on the vehicle-mounted vision sensor.
It can be understood that the relative position of the vehicle in the current lane is the distance between the vehicle and the left lane boundary line or the right lane boundary line of the current lane, and the schematic diagram is shown in fig. 3.
Step S500: acquiring a second location of the own vehicle in the map information based on the relative position;
specifically, after the relative position of the own vehicle in the current lane is obtained, second positioning information of the own vehicle can be obtained through lane information, relative position and first positioning information, and the accuracy of the second positioning information is higher than that of the first positioning.
Further, in order to obtain a more accurate second positioning, the step of obtaining the second positioning includes:
step S501: acquiring a second projection point of the first position on a lane central line of the current lane;
step S502: selecting two calculation points on the lane center line of the current lane, and calculating the second positioning of the vehicle based on the two calculation points, the second projection point, the left lane boundary line distance and/or the right lane boundary line distance.
Step S600: and calculating a positioning deviation value based on the first positioning and the second positioning, and positioning the vehicle based on the positioning deviation value and the vehicle-mounted inertial navigation sensor.
It can be appreciated that the positioning deviation value can be used for parameter correction of the vehicle-mounted inertial navigation sensor, so that the vehicle-mounted inertial navigation sensor outputs more accurate positioning.
It can be appreciated that based on the defects in the background technology, the embodiment of the invention provides a multi-sensor fusion positioning method. The method comprises the following steps: acquiring a first positioning of the own vehicle based on the vehicle-mounted inertial navigation sensor; acquiring map information corresponding to the first positioning from the medium-precision map navigation system based on the first positioning; calculating a current lane of the own vehicle in the map information based on the first positioning; acquiring the relative position of the self-vehicle on the current lane based on the vehicle-mounted vision sensor; acquiring a second position of the own vehicle from the map information based on the relative position; and calculating a positioning deviation value based on the first positioning and the second positioning, and positioning the vehicle based on the positioning deviation value and the vehicle-mounted inertial navigation sensor. According to the invention, a first positioning of the self-vehicle is obtained through the vehicle-mounted inertial navigation sensor, a current lane of the self-vehicle on a map is obtained based on the first positioning and the medium-precision map navigation system, then the relative position of the self-vehicle in the current lane is obtained based on the vehicle-mounted visual sensor, a second positioning of the self-vehicle is calculated based on the relative position, and a positioning deviation value is calculated through the first positioning and the second positioning, so that the vehicle-mounted inertial navigation sensor is subjected to positioning correction according to the positioning deviation value, and high-precision positioning information is output; the vehicle can be fused and positioned in the medium-precision map system through the plurality of sensors, so that the medium-precision map can be positioned at high precision which meets the requirements of automatic driving, the dependence of the automatic driving on the high-precision map is reduced, the vehicle-mounted sensor is corrected, and the sensing precision of the vehicle-mounted sensor is improved.
In a possible embodiment, after the second positioning is obtained, that is, the accurate fusion positioning result is obtained, the coordinate of the positioning point after fusion and the coordinate of the original positioning point can be directly subtracted, further, the coordinate of the positioning point can be converted into UTM (Universal Transverse Mercator Grid System, universal transverse ink card grid system) at first to be more accurate, the deviation value between the two points is obtained, the positioning deviation value is updated by calculating a plurality of points at intervals, and the output result is obtained by fusing the original coordinate and the positioning deviation value.
Specifically, referring to fig. 4, D1 to Dn are original positioning points of inertial navigation of the vehicle, D1 to Dn are position points after fusion positioning, and n is a frequency of calculating a positioning deviation value in fig. 4.
After calculating the fused and positioned position point D1, calculating the positioning deviation values x1 and y1 between D1 and D1, and then calculating a second positioning point by using the same positioning deviation values x1 and y1 before the next position point recalculation (before the point Dn), calculating the deviation values x2 and y2 after the position point Dn is recalculated, and repeating the previous steps.
In the embodiment, the positioning deviation value is calculated and updated according to a certain frequency, so that the positioning output frequency is improved and the calculated amount is reduced under the condition that the positioning accuracy is not reduced.
In a possible embodiment, when the vehicle changes lanes or the front is blocked or the road surface is bad, the confidence coefficient in the visual perception data output by the vehicle-mounted visual sensor is reduced, when the confidence coefficient is lower than 85%, the perception effect of the vehicle-mounted visual sensor can be considered to be not added, the positioning deviation value is not updated according to the preset frequency, the last calculated or reserved deviation value is used for calculating the fusion positioning point, and the deviation value is recalculated after the perception data is stable and the confidence coefficient is higher.
In this embodiment, when the sensing effect of the vehicle-mounted vision sensor is poor, the inertial navigation sensor is corrected by using the previous or stored positioning deviation value, and the positioning deviation value is recalculated after the data of the vehicle-mounted vision sensor is stable, so that the positioning accuracy of the vehicle under the condition that the vehicle-mounted vision sensor fails is ensured.
In a possible embodiment, referring to fig. 5 and 6, in fig. 5 and 6, the set point p1 and the point p2 are two endpoints selected on the lane center line, p is the first location of the own vehicle (i.e. the projection point), the projection point is n, and according to the calculation method of vector projection, the method can be as follows:
the vector in the movement formula can be obtained:
order theWhere ratio is vector p 1 n and vector p 1 p 2 When the ratio is less than 0, p point is projected on line segment p 1 p 2 On the left side, when the ratio is more than or equal to 0 and less than or equal to 1, p points are projected on a line segment p 1 p 2 At 1 < ratio, p points are projected on line segment p 1 p 2 Right side.
Order the
In the case of the view of figure 6,
vx＝(x2-x1)；
vy＝(y2-y1)；
wx＝(px-x1)；
wy＝(py-y1)；
c1＝vx*wx+vy*wy；
c2＝vx*vx+vy*vy；
then ratio = c1/c2;
the n coordinates (nx, ny) of the projection point are:
nx＝x1+ratio*vx；
ny＝y1+ratio*vy；
in this embodiment, a first projection point of the first positioning point on the center line of the lane is calculated by a vector projection calculation method, so that the current lane where the own vehicle runs can be obtained through the first positioning point.
In one possible embodiment, referring to fig. 7, after the first positioning of the own vehicle is projected onto the lane center line to obtain the projection point in fig. 7, the lane boundary lines of the vehicle from both sides of the current lane are identified by combining with the vehicle-mounted vision sensor, and the actual positioning (i.e. the second positioning) of the vehicle is calculated as follows:
in FIG. 7, the set point p1 and the point p2 are two calculated points selected on the lane center line, the point p is the projected point of the first location, and the point n is the second location point obtained by final calculation, wherein
vx＝(x2-x1)；
vy＝(y2-y1)；
According to the triangle geometry, two included angles α in fig. 7 are the same, where dis is the distance between the vehicle and the lane boundary line on the left side of the current lane, and the coordinates of the obtained point n (nx, ny) are:
nx＝px-dis*sinα；
ny＝py+dis*sinα；
in the embodiment, the distance from the vehicle to the lane boundary line is obtained through the projection point of the vehicle on the lane center line and the recognition of the vehicle-mounted visual sensor, and the accurate positioning of the vehicle is calculated, so that the accurate positioning of the vehicle is output.
Referring to fig. 8, fig. 8 is a schematic diagram of a structure diagram of a multi-sensor fusion positioning system provided by an embodiment of the present invention, as shown in fig. 8, the multi-sensor fusion positioning system is applied to a vehicle with a medium-precision map navigation system, a vehicle-mounted inertial navigation sensor and a vehicle-mounted vision sensor, and includes a first positioning acquisition module 100, a map acquisition module 200, a lane acquisition module 300, a position acquisition module 400, a second positioning calculation module 500 and a fusion positioning module 600, wherein:
a first positioning acquiring module 100, configured to acquire a first positioning of the own vehicle based on the vehicle-mounted inertial navigation sensor; a map obtaining module 200, configured to obtain map information corresponding to the first location from the medium-precision map navigation system based on the first location; a lane acquisition module 300 for calculating a current lane of the own vehicle in the map information based on the first positioning; a position obtaining module 400, configured to obtain a relative position of the own vehicle on the current lane based on the vehicle-mounted vision sensor; a second positioning calculation module 500, configured to obtain a second positioning of the own vehicle in the map information based on the relative position; and the fusion positioning module 600 is configured to calculate a positioning deviation value based on the first positioning and the second positioning, and position the vehicle based on the positioning deviation value and the vehicle-mounted inertial navigation sensor.
It can be understood that the multi-sensor fusion positioning system provided by the present invention corresponds to the multi-sensor fusion positioning method provided in the foregoing embodiments, and relevant technical features of the multi-sensor fusion positioning system may refer to relevant technical features of the multi-sensor fusion positioning method, which are not described herein.
Referring to fig. 9, fig. 9 is a schematic diagram of an embodiment of an electronic device according to an embodiment of the invention. As shown in fig. 9, an embodiment of the present invention provides an electronic device including a memory 1310, a processor 1320, and a computer program 1311 stored on the memory 1310 and executable on the processor 1320, the processor 1320 implementing the following steps when executing the computer program 1311:
acquiring a first positioning of the own vehicle based on the vehicle-mounted inertial navigation sensor; acquiring map information corresponding to the first positioning from the medium-precision map navigation system based on the first positioning; calculating a current lane of the own vehicle in the map information based on the first positioning; acquiring the relative position of the self-vehicle on the current lane based on the vehicle-mounted vision sensor; acquiring a second position of the own vehicle from the map information based on the relative position; and calculating a positioning deviation value based on the first positioning and the second positioning, and positioning the vehicle based on the positioning deviation value and the vehicle-mounted inertial navigation sensor.
Referring to fig. 10, fig. 10 is a schematic diagram of a computer readable storage medium according to an embodiment of the invention. As shown in fig. 10, the present embodiment provides a computer-readable storage medium 1400 on which a computer program 1411 is stored, the computer program 1411, when executed by a processor, implementing the steps of:
acquiring a first positioning of the own vehicle based on the vehicle-mounted inertial navigation sensor; acquiring map information corresponding to the first positioning from the medium-precision map navigation system based on the first positioning; calculating a current lane of the own vehicle in the map information based on the first positioning; acquiring the relative position of the self-vehicle on the current lane based on the vehicle-mounted vision sensor; acquiring a second position of the own vehicle from the map information based on the relative position; and calculating a positioning deviation value based on the first positioning and the second positioning, and positioning the vehicle based on the positioning deviation value and the vehicle-mounted inertial navigation sensor.
The embodiment of the invention provides a multi-sensor fusion positioning method, a multi-sensor fusion positioning system, electronic equipment and a storage medium, wherein the multi-sensor fusion positioning method comprises the following steps: acquiring a first positioning of the own vehicle based on the vehicle-mounted inertial navigation sensor; acquiring map information corresponding to the first positioning from the medium-precision map navigation system based on the first positioning; calculating a current lane of the own vehicle in the map information based on the first positioning; acquiring the relative position of the self-vehicle on the current lane based on the vehicle-mounted vision sensor; acquiring a second position of the own vehicle from the map information based on the relative position; and calculating a positioning deviation value based on the first positioning and the second positioning, and positioning the vehicle based on the positioning deviation value and the vehicle-mounted inertial navigation sensor. According to the invention, a first positioning of the self-vehicle is obtained through the vehicle-mounted inertial navigation sensor, a current lane of the self-vehicle on a map is obtained based on the first positioning and the medium-precision map navigation system, then the relative position of the self-vehicle in the current lane is obtained based on the vehicle-mounted visual sensor, a second positioning of the self-vehicle is calculated based on the relative position, and a positioning deviation value is calculated through the first positioning and the second positioning, so that the vehicle-mounted inertial navigation sensor is subjected to positioning correction according to the positioning deviation value, and high-precision positioning information is output; the vehicle can be fused and positioned in the medium-precision map system through the plurality of sensors, so that the medium-precision map can be positioned at high precision which meets the requirements of automatic driving, the dependence of the automatic driving on the high-precision map is reduced, the vehicle-mounted sensor is corrected, and the sensing precision of the vehicle-mounted sensor is improved.
In the foregoing embodiments, the descriptions of the embodiments are focused on, and for those portions of one embodiment that are not described in detail, reference may be made to the related descriptions of other embodiments.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following claims be interpreted as including the preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit or scope of the invention. Thus, it is intended that the present invention also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.
Claims (10)
1. A multi-sensor fusion positioning method, which is applied to a vehicle with a medium-precision map navigation system, a vehicle-mounted inertial navigation sensor and a vehicle-mounted vision sensor, the method comprising:
acquiring a first positioning of the own vehicle based on the vehicle-mounted inertial navigation sensor;
acquiring map information corresponding to the first positioning from the medium-precision map navigation system based on the first positioning;
calculating a current lane of the own vehicle in the map information based on the first positioning;
acquiring the relative position of the self-vehicle on the current lane based on the vehicle-mounted vision sensor;
acquiring a second location of the own vehicle in the map information based on the relative position;
and calculating a positioning deviation value based on the first positioning and the second positioning, and positioning the vehicle based on the positioning deviation value and the vehicle-mounted inertial navigation sensor.
2. The multi-sensor fusion positioning method according to claim 1, wherein the step of calculating a current lane of the own vehicle in the map information based on the first positioning includes:
acquiring a plurality of lanes and a plurality of lane centerlines in the map information based on the first positioning;
and setting a lane corresponding to the lane center line with the smallest first positioning distance as a current lane where the own vehicle is located.
3. The multi-sensor fusion positioning method according to claim 2, wherein the step of setting the lane corresponding to the lane center line having the smallest positioning distance as the current lane in which the own vehicle is located, comprises:
acquiring first projection points of the first positioning on the central lines of a plurality of lanes, and calculating the projection distance between the first positioning and each first projection point;
and acquiring a lane center line corresponding to the first projection point with the minimum projection distance, and setting a lane corresponding to the lane center line as a current lane of the own vehicle.
4. The multi-sensor fusion positioning method according to claim 3, wherein the step of obtaining first projection points of the first positioning at a plurality of the lane center lines and calculating a projection distance of the first positioning from each first projection point comprises:
and respectively selecting two endpoints on the lane central lines, and calculating a first projection point of the first positioning on each lane central line based on the first positioning and the two endpoints by using a vector projection calculation method to obtain the projection distance between the first positioning and each first projection point.
5. The multi-sensor fusion positioning method according to claim 1, wherein the step of acquiring the relative position of the own vehicle in the current lane based on the in-vehicle vision sensor comprises:
and acquiring the distance from the vehicle to the left lane boundary line and/or the distance from the vehicle to the right lane boundary line of the current lane based on the vehicle-mounted vision sensor.
6. The multi-sensor fusion positioning method according to claim 5, wherein the step of acquiring the second positioning of the own vehicle in the map information based on the relative position includes:
acquiring a second projection point of the first position on a lane central line of the current lane;
selecting two calculation points on the lane center line of the current lane, and calculating the second positioning of the vehicle based on the two calculation points, the second projection point, the left lane boundary line distance and/or the right lane boundary line distance.
7. The multi-sensor fusion positioning method according to claim 1, wherein the step of calculating a positioning deviation value based on the first positioning and the second positioning, and positioning the own vehicle based on the positioning deviation value and the in-vehicle inertial navigation sensor, after the step of:
and recalculating the positioning deviation value based on a preset calculation frequency, and positioning the vehicle based on the latest positioning deviation value and the vehicle-mounted inertial navigation sensor.
8. The multi-sensor fusion positioning system is characterized in that the system is applied to a vehicle with a medium-precision map navigation system, a vehicle-mounted inertial navigation sensor and a vehicle-mounted vision sensor, and comprises:
the first positioning acquisition module is used for acquiring a first positioning of the vehicle based on the vehicle-mounted inertial navigation sensor;
the map acquisition module is used for acquiring map information corresponding to the first positioning from the medium-precision map navigation system based on the first positioning;
a lane acquisition module for calculating a current lane of the own vehicle in the map information based on the first positioning;
the position acquisition module is used for acquiring the relative position of the self-vehicle on the current lane based on the vehicle-mounted vision sensor;
a second positioning calculation module for acquiring a second positioning of the own vehicle in the map information based on the relative position;
and the fusion positioning module is used for calculating a positioning deviation value based on the first positioning and the second positioning, and positioning the vehicle based on the positioning deviation value and the vehicle-mounted inertial navigation sensor.
9. An electronic device comprising a memory, a processor for implementing the steps of the multi-sensor fusion positioning method according to any one of claims 1-7 when executing a computer management class program stored in the memory.
10. A computer readable storage medium, having stored thereon a computer management class program which when executed by a processor implements the steps of the multisensor fusion positioning method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311605983.7A CN117705129A (en) | 2023-11-27 | 2023-11-27 | Multi-sensor fusion positioning method, system, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311605983.7A CN117705129A (en) | 2023-11-27 | 2023-11-27 | Multi-sensor fusion positioning method, system, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117705129A true CN117705129A (en) | 2024-03-15 |
Family
ID=90148898
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311605983.7A Pending CN117705129A (en) | 2023-11-27 | 2023-11-27 | Multi-sensor fusion positioning method, system, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117705129A (en) |
-
2023
- 2023-11-27 CN CN202311605983.7A patent/CN117705129A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR102558055B1 (en) | Suboptimal estimation method | |
| JP5997797B2 (en) | Vehicle map data processing device | |
| US11125566B2 (en) | Method and apparatus for determining a vehicle ego-position | |
| CN110530372B (en) | Positioning method, path determining device, robot and storage medium | |
| WO2018179616A1 (en) | Vehicle position deduction apparatus | |
| JP2010086544A (en) | Creating geometry for advanced driver assistance system | |
| CN111076734B (en) | High-precision map construction method for unstructured roads in closed area | |
| CN111220143B (en) | Method and device for determining position and posture of imaging equipment | |
| CN115235500B (en) | Lane line constraint-based pose correction method and device and all-condition static environment modeling method and device | |
| JP2020516880A (en) | Method and apparatus for reducing midpoints in a polygon | |
| EP3859273B1 (en) | Method for constructing driving coordinate system, and application thereof | |
| US20220176989A1 (en) | High precision position estimation method through road shape classification-based map matching and autonomous vehicle thereof | |
| CN113359171B (en) | Positioning method and device based on multi-sensor fusion and electronic equipment | |
| CN112747755B (en) | Method and device for determining road route, readable storage medium and map updating system | |
| CN111912413B (en) | Positioning method and device | |
| CN114323050A (en) | Vehicle positioning method and device and electronic equipment | |
| JP7418196B2 (en) | Travel trajectory estimation method and travel trajectory estimation device | |
| CN110855789B (en) | Position relation determining method and device, storage medium and equipment | |
| JP6790951B2 (en) | Map information learning method and map information learning device | |
| CN113566817A (en) | Vehicle positioning method and device | |
| CN113306559A (en) | Compensation for vertical road camber in road shape estimation | |
| CN111204342B (en) | Map information system | |
| CN117705129A (en) | Multi-sensor fusion positioning method, system, electronic equipment and storage medium | |
| Sajeed et al. | Vehicle lane departure estimation on urban roads using GIS information | |
| CN115046546A (en) | Automatic driving automobile positioning system and method based on lane line identification |
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 |