CN109917376B

CN109917376B - Positioning method and device

Info

Publication number: CN109917376B
Application number: CN201910142536.XA
Authority: CN
Inventors: 于占海
Original assignee: Neusoft Reach Automotive Technology Shenyang Co Ltd
Current assignee: Neusoft Reach Automotive Technology Shenyang Co Ltd
Priority date: 2019-02-26
Filing date: 2019-02-26
Publication date: 2021-08-06
Anticipated expiration: 2039-02-26
Also published as: CN109917376A

Abstract

The application discloses a positioning method and a positioning device, wherein the positioning method comprises the following steps: the vehicle server divides a first point cloud map sent by a vehicle, and converts three-dimensional coordinate data of radar scanning points in each sub-map obtained through division into normal distribution parameter values; the vehicle server side matches a first normal distribution parameter set formed by normal distribution parameter values of all sub-maps in a normal parameter feature library to obtain a second normal distribution parameter set which is successfully matched; and the vehicle server determines the vehicle position information in the whole point cloud map according to the coordinate parameters corresponding to the second normal distribution parameter set. In the method, the calculated amount and the time required by matching different normal distribution parameters are much smaller than those required by matching different point cloud maps, so that the calculated amount and the calculated time of the point cloud maps are reduced, and the real-time property of vehicle positioning is improved.

Description

Positioning method and device

Technical Field

The present application relates to the field of vehicle technologies, and in particular, to a positioning method and apparatus.

Background

With the popularization of vehicles, the real-time positioning of the vehicles becomes more and more important. In the prior art, a common positioning method is as follows: firstly, a vehicle obtains a point cloud map taking the vehicle as a coordinate center through radar scanning, and the point cloud map is marked as a map to be positioned; and then, the vehicle service end receives a map to be positioned sent by the vehicle, matches the map to be positioned with an integral point cloud map formed by splicing a plurality of frame point cloud maps in a storage space of the map to be positioned, obtains a frame of point cloud map matched with the map to be positioned, so that the vehicle service end can obtain the position information of the vehicle according to the frame of point cloud map and feeds the position information back to the vehicle.

However, in the above positioning method, each frame of point cloud map includes a large number of points, and each point is represented by three-dimensional coordinate data, so that the data volume of each frame of point cloud map is large, which results in large calculation amount and long time consumption when matching the undetermined map with the whole point cloud map, and also results in low real-time performance of vehicle positioning.

Disclosure of Invention

In order to solve the technical problems in the prior art, the application provides a positioning method and a positioning device, which can reduce the data volume of a point cloud map, thereby reducing the calculated amount and the calculated time when the point cloud map is matched, and further improving the real-time performance of vehicle positioning.

In order to achieve the above purpose, the technical solution provided by the present application is as follows:

the application provides a positioning method, which comprises the following steps:

the vehicle server divides a first point cloud map sent by a vehicle, and converts three-dimensional coordinate data of radar scanning points in each sub-map obtained through division into normal distribution parameter values;

the vehicle server side matches a first normal distribution parameter set formed by the normal distribution parameter values of the sub-maps in a normal parameter feature library to obtain a second normal distribution parameter set which is successfully matched;

and the vehicle server determines vehicle position information in the whole point cloud map according to the coordinate parameters corresponding to the second normal distribution parameter set.

Optionally, when the normal parameter feature library includes at least one normal distribution parameter value, the vehicle service end matches a first normal distribution parameter set formed by the normal distribution parameter values of each sub-map in the normal parameter feature library to obtain a second normal distribution parameter set successfully matched, specifically:

the vehicle server matches the normal distribution parameter values in the first normal distribution parameter set with the normal distribution parameter values in a normal parameter feature library to obtain successfully matched normal distribution parameter values;

and the vehicle server side obtains a second normal distribution parameter set according to the successfully matched normal distribution parameter values.

Optionally, the method for generating the normal parameter feature library specifically includes:

the vehicle server divides the overall point cloud map into a plurality of sub-maps and obtains coordinate parameters of each sub-map corresponding to the overall point cloud map;

the vehicle server side converts the three-dimensional coordinate data of the radar scanning points in each sub-map obtained through division into normal distribution parameter values;

and the vehicle server side obtains a normal parameter feature library corresponding to the whole point cloud map according to the normal distribution parameter values corresponding to the sub-maps.

Optionally, when the normal parameter feature library includes at least one normal distribution parameter set, the vehicle service end matches a first normal distribution parameter set formed by the normal distribution parameter values of each sub-map in the normal parameter feature library to obtain a second normal distribution parameter set successfully matched, specifically:

and the vehicle server side matches the first normal distribution parameter set formed by the normal distribution parameter values of the sub-maps with the normal distribution parameter set in the normal parameter feature library to obtain a second normal distribution parameter set which is successfully matched.

the vehicle server divides the integral point cloud map into a plurality of block maps and obtains the coordinate parameters of each block map corresponding to the integral point cloud map;

the vehicle server divides each block map, converts three-dimensional coordinate data of radar scanning points in each sub map obtained by division into normal distribution parameter values, and obtains a normal distribution parameter set corresponding to each block map according to the normal distribution parameter values corresponding to each sub map;

and the vehicle server obtains a normal parameter feature library corresponding to the whole point cloud map according to the normal distribution parameter set corresponding to each block map.

Optionally, the vehicle service end matches the first normal distribution parameter set formed by the normal distribution parameter values of each sub-map in a normal parameter feature library to obtain a second normal distribution parameter set successfully matched, which specifically includes:

and based on a Newton optimization method, the vehicle server side matches the first normal distribution parameter set formed by the normal distribution parameter values of each sub-map in a normal parameter feature library to obtain a second normal distribution parameter set successfully matched.

Optionally, the vehicle service end divides a first point cloud map sent by the vehicle, specifically:

the vehicle server divides the first point cloud map sent by the vehicle according to the square template or the rectangular template.

The present application further provides a positioning method, including:

the vehicle scans by using a radar to obtain a first point cloud map;

the vehicle divides the first point cloud map, converts three-dimensional coordinate data of radar scanning points in each sub map obtained by division into normal distribution parameter values, and obtains a first normal distribution parameter set according to the normal distribution parameter values corresponding to the sub maps;

and the vehicle sends the first normal distribution parameter set to a vehicle service end so that the vehicle service end matches the first normal distribution parameter set in a normal parameter feature library, and determines vehicle position information in the whole point cloud map according to the coordinate parameters corresponding to a second normal distribution parameter set successfully matched with the first normal distribution parameter set.

The present application further provides a positioning method, including:

the vehicle scans by using a radar to obtain a first point cloud map;

the vehicle matches the first normal distribution parameter set in a normal parameter feature library sent by a vehicle server to obtain a second normal distribution parameter set which is successfully matched;

and the vehicle determines the vehicle position information in the whole point cloud map according to the coordinate information corresponding to the second normal distribution parameter set.

Optionally, when the normal parameter feature library includes at least one normal distribution parameter value, the vehicle matches the first normal distribution parameter set in the normal parameter feature library sent by the vehicle service end to obtain a second normal distribution parameter set successfully matched, which specifically includes:

the vehicle matches the normal distribution parameter values in the first normal distribution parameter set with the normal distribution parameter values in a normal parameter feature library to obtain successfully matched normal distribution parameter values;

and the vehicle obtains a second normal distribution parameter set according to the successfully matched normal distribution parameter values.

Optionally, when the normal parameter feature library includes at least one normal distribution parameter set, the vehicle matches the first normal distribution parameter set in the normal parameter feature library sent by the vehicle service end to obtain a second normal distribution parameter set successfully matched, which specifically includes:

and the vehicle matches the first normal distribution parameter set with a normal distribution parameter set in a normal parameter feature library to obtain a second normal distribution parameter set which is successfully matched.

Optionally, the vehicle matches the first normal distribution parameter set in a normal parameter feature library sent by a vehicle service end to obtain a successfully matched second normal distribution parameter set, which specifically includes:

and matching the first normal distribution parameter set in a normal parameter feature library sent by a vehicle server by the vehicle based on a Newton optimization method to obtain a second normal distribution parameter set which is successfully matched.

The present application further provides a positioning device, comprising:

the first conversion unit is used for dividing a first point cloud map sent by a vehicle by the vehicle server side and converting three-dimensional coordinate data of radar scanning points in each sub-map obtained by dividing into normal distribution parameter values;

the first obtaining unit is used for the vehicle server side to match a first normal distribution parameter set formed by the normal distribution parameter values of the sub-maps in a normal parameter feature library to obtain a second normal distribution parameter set which is successfully matched;

and the first determining unit is used for determining the vehicle position information in the whole point cloud map by the vehicle server according to the coordinate parameters corresponding to the second normal distribution parameter set.

Optionally, the first conversion unit includes:

the first dividing unit is used for dividing the first point cloud map sent by the vehicle according to a square template or a rectangular template by the vehicle server.

The present application further provides a positioning device, comprising:

the second acquisition unit is used for scanning the vehicle by utilizing a radar and acquiring a first point cloud map taking the current vehicle position as the center;

the third obtaining unit is used for the vehicle to divide the first point cloud map, converting the three-dimensional coordinate data of the radar scanning points in each sub map obtained through division into normal distribution parameter values, and obtaining a first normal distribution parameter set according to the normal distribution parameter values corresponding to the sub maps;

and the first sending unit is used for sending the first normal distribution parameter set to a vehicle service end by the vehicle so that the vehicle service end matches the first normal distribution parameter set in a normal parameter feature library, and determining vehicle position information in the whole point cloud map according to the coordinate parameters corresponding to the second normal distribution parameter set successfully matched with the first normal distribution parameter set.

The present application further provides a positioning device, comprising:

the fourth acquisition unit is used for scanning the vehicle by utilizing a radar and acquiring a first point cloud map with the current vehicle position as the center;

a fifth obtaining unit, configured to divide the first point cloud map by the vehicle, convert the three-dimensional coordinate data of the radar scanning points in each sub-map obtained through division into normal distribution parameter values, and obtain a first normal distribution parameter set according to the normal distribution parameter values corresponding to the sub-maps;

a sixth obtaining unit, configured to match, by the vehicle, the first normal distribution parameter set in a normal parameter feature library sent by a vehicle server to obtain a second normal distribution parameter set successfully matched;

and the second determining unit is used for determining the vehicle position information in the whole point cloud map according to the coordinate information corresponding to the second normal distribution parameter set.

Compared with the prior art, the method has the advantages that:

according to the positioning method, a first point cloud map sent by a vehicle is divided through the vehicle server, and three-dimensional coordinate data of radar scanning points in each sub-map obtained through division are converted into normal distribution parameter values; the vehicle server side matches a first normal distribution parameter set formed by the normal distribution parameter values of the sub-maps in a normal parameter feature library to obtain a second normal distribution parameter set which is successfully matched; and the vehicle server determines vehicle position information in the whole point cloud map according to the coordinate parameters corresponding to the second normal distribution parameter set. In the method, the data volume of the normal distribution parameter value is much smaller than the data volume of the three-dimensional coordinate data of the radar scanning points in the sub-map, so that the data volume of the first normal distribution parameter set is much smaller than the data volume of the first point cloud map, and the data volume of the normal parameter feature library is much smaller than the data volume of the corresponding point cloud map, thereby reducing the data volume of the point cloud map. Therefore, when the first normal distribution parameter set is matched in the normal parameter feature library, the calculation amount required by the matching process is much smaller than that required by matching of different point cloud maps in the prior art, and the time required by the matching process is much smaller than that required by matching of different point cloud maps in the prior art, so that the calculation amount and the calculation time of the point cloud maps in the matching process are reduced, and the real-time performance of vehicle positioning 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 described below, it is obvious that the drawings in the following description are only some embodiments described in the present application, and other drawings can be obtained by those skilled in the art without creative efforts.

Fig. 1 is a flowchart of an implementation manner of a positioning method provided in an embodiment of the present application;

fig. 2 is a flowchart of an implementation manner of S101 provided in an embodiment of the present application;

fig. 3 is a flowchart of an implementation manner of S1014 provided in an embodiment of the present application;

fig. 4 is a flowchart of an implementation manner of S102 provided in an embodiment of the present application;

FIG. 5 is a flowchart of a method for generating a normal parameter feature library according to an embodiment of the present disclosure;

fig. 6 is a flowchart of an implementation manner of S501 provided in an embodiment of the present application;

fig. 7 is a flowchart of an implementation manner of S1022 according to an embodiment of the present application;

fig. 8 is a flowchart of another implementation of a positioning method provided in an embodiment of the present application;

fig. 9 is a flowchart of another implementation of a positioning method according to an embodiment of the present application;

fig. 10 is a flowchart of an implementation manner of S903 provided in an embodiment of the present application;

fig. 11 is a flowchart of an implementation manner of S904 provided in an embodiment of the present application;

fig. 12 is a flowchart of another implementation manner of S904 provided in this application example;

FIG. 13 is a schematic structural diagram illustrating an embodiment of a positioning device according to an embodiment of the present disclosure;

FIG. 14 is a schematic structural diagram of another embodiment of a positioning device provided in the examples of the present application;

fig. 15 is a schematic structural diagram of another embodiment of a positioning device according to an embodiment of the present application.

Detailed Description

In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the 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 invention.

Method embodiment one

Referring to fig. 1, the figure is a flowchart of an implementation manner of a positioning method provided in an embodiment of the present application.

The positioning method provided by the embodiment of the application comprises the following steps:

s101: the vehicle server divides a first point cloud map sent by a vehicle, and converts three-dimensional coordinate data of radar scanning points in each sub-map obtained through division into normal distribution parameter values.

The S101 may adopt various embodiments, and one embodiment will be explained and explained as an example.

Referring to fig. 2, the figure is a flowchart of an implementation manner of S101 provided in an embodiment of the present application.

As an embodiment, S101 may specifically be:

s1011: the vehicle scans by using a radar to obtain a first point cloud map.

The radar is used for scanning the current vehicle position and the surrounding environment with the current vehicle position as the center to obtain a point cloud map corresponding to the current vehicle position.

Each frame of point cloud map comprises a plurality of radar scanning points, and the three-dimensional coordinate data of each radar scanning point is coordinate data relative to an origin. As an example, when the three-dimensional coordinate data of the first radar-scanned point on the first point cloud map is (X, Y, Z), it indicates that the distance from the first radar-scanned point to the origin of the first point cloud map in the X-axis direction is X; in the Y-axis direction, the distance from the first radar scanning point to the origin of the first point cloud map is Y; in the Z-axis direction, the distance from the first radar scanning point to the origin of the first point cloud map is Z.

It should be noted that, since the origin of each frame of point cloud map represents the position of the radar, and the radar is located on the vehicle, the origin of each frame of point cloud map may also represent the position of the vehicle.

S1012: and the vehicle sends the first point cloud map to a vehicle server.

The vehicle service end can be a cloud end, a cluster or other equipment comprising a server.

As an embodiment, S1012 may specifically be: the vehicle can send the first point cloud map to a vehicle server through a network.

S1013: the vehicle server divides the first point cloud map sent by the vehicle to obtain a plurality of sub-maps.

The vehicle service end may be divided according to different division rules, different division orders, and different division templates, which is not specifically limited in this application.

As an embodiment, S1013 may specifically be: the vehicle server divides the first point cloud map sent by the vehicle according to the square template or the rectangular template.

In the embodiment, the sub-maps obtained by dividing are square or rectangular, so that the sub-maps can be beneficial to the conversion of normal distribution parameters, the accuracy of the normal distribution parameter values corresponding to the sub-maps can be improved, and the accuracy of positioning can be further improved.

S1014: and the vehicle service end converts the three-dimensional coordinate data of the radar scanning points in each sub-map into normal distribution parameter values.

The normal distribution parameter value may include a plurality of parameter values.

As an example, the normal distribution parameter values may include: mean and standard deviation in x-direction, mean and standard deviation in y-direction, mean and standard deviation in z-direction.

As an embodiment, when the mean and standard deviation in the x direction include: when the mean and the standard deviation in the x direction, the mean and the standard deviation in the y direction, and the mean and the standard deviation in the z direction, S1014 may specifically be: the vehicle service end converts the three-dimensional coordinate data of the radar scanning points in each sub-map into 6 normal distribution parameter values: mean and standard deviation in x-direction, mean and standard deviation in y-direction and mean and standard deviation in z-direction.

In addition, the radar scanning points in the sub-map can be all scanning points in the sub-map, or can be partial scanning points in the sub-map.

As an embodiment, S1014 may specifically be: and the vehicle service end converts the three-dimensional coordinate data of all the radar scanning points in each sub-map into normal distribution parameter values.

Referring to fig. 3, the figure is a flowchart of an implementation manner of S1014 provided in an embodiment of the present application.

As another embodiment, S1014 may specifically be:

s10141: and the vehicle server side selects all the radar scanning points in each sub-map according to a preset rule to obtain partial radar scanning points in each sub-map.

S10142: and the vehicle server converts the three-dimensional coordinate data of the partial radar scanning points in each sub-map into normal distribution parameter values.

In this embodiment, because the data amount of the part of radar scanning points of the sub-map is small, the time required for the vehicle service end to convert the three-dimensional coordinate data of the part of radar scanning points of the sub-map into the positive distribution parameter values is short, so that the conversion efficiency is improved, and the positioning efficiency is further improved.

In addition, the embodiment of the application can adopt various methods to convert the three-dimensional coordinate data of the sub-map into the normal distribution parameter value.

As an embodiment, S1014 may specifically be: based on the voxelization processing method, the vehicle service end converts the three-dimensional coordinate data of the radar scanning points in each sub-map into normal distribution parameter values.

S102: and the vehicle server side matches the first normal distribution parameter set formed by the normal distribution parameter values of the sub-maps in a normal parameter feature library to obtain a second normal distribution parameter set which is successfully matched.

The S102 may adopt various embodiments, and one embodiment will be explained and explained as an example.

As an embodiment, when the normal parameter feature library includes at least one normal distribution parameter value, S102 may specifically be: the vehicle server matches the normal distribution parameter values in the first normal distribution parameter set with the normal distribution parameter values in a normal parameter feature library to obtain successfully matched normal distribution parameter values; and then, the vehicle server side obtains a second normal distribution parameter set according to the successfully matched normal distribution parameter values.

In this embodiment, a part of normal distribution parameter values in the first normal distribution parameter set may be matched with normal distribution parameter values in the normal parameter feature library, where the part of normal distribution parameter values in the first normal distribution parameter set may be determined according to an actual application scenario, or may be preset; all normal distribution parameter values in the first normal distribution parameter set can be matched with normal distribution parameter values in the normal parameter feature library.

As an example, S102 may specifically be: and the vehicle server side matches each normal distribution parameter value in the first normal distribution parameter set with the normal distribution parameter value in the normal parameter feature library respectively to obtain each successfully matched normal distribution parameter value, and the second normal distribution parameter set is formed by all successfully matched normal distribution parameter values.

In addition, in this embodiment, the normal parameter feature library may be stored in the vehicle service end in advance, and the method for generating the normal parameter feature library may specifically be:

firstly, the vehicle service end divides the overall point cloud map into a plurality of sub-maps and obtains the coordinate parameters of each sub-map corresponding to the overall point cloud map.

And secondly, converting the three-dimensional coordinate data of the radar scanning points in each sub-map obtained by dividing into normal distribution parameter values by the vehicle service side.

And then, the vehicle server side obtains a normal parameter feature library corresponding to the whole point cloud map according to the normal distribution parameter values corresponding to the sub-maps.

In the foregoing, a specific implementation of S102 is provided when the normal parameter feature library includes at least one normal distribution parameter value, in this implementation, S102 obtains a second normal distribution parameter set successfully matched with the first normal distribution parameter set by matching the normal distribution parameter value in the first normal distribution parameter set with the normal distribution parameter value in the normal parameter feature library.

In addition, another implementation manner of S102 is further provided in this embodiment, in which the normal parameter feature library includes at least one normal distribution parameter set, and each normal distribution parameter set includes a plurality of normal distribution parameter values. Therefore, based on the normal parameter feature library, S102 may specifically be: and the vehicle server side matches the first normal distribution parameter set formed by the normal distribution parameter values of the sub-maps with the normal distribution parameter set in the normal parameter feature library to obtain a second normal distribution parameter set which is successfully matched.

For ease of explanation and understanding, reference will now be made to the drawings.

Referring to fig. 4, this figure is a flowchart of an implementation manner of S102 provided in this application.

As an embodiment, S102 may specifically be:

s1021: and the vehicle server side forms a first normal distribution parameter set according to the normal distribution parameter values of the sub-maps.

S1022: and the vehicle server matches the first normal distribution parameter set with a normal distribution parameter set in a normal parameter feature library to obtain a second normal distribution parameter set which is successfully matched.

The normal parameter feature library includes: and each normal distribution parameter set corresponds to one block map. The block map may be obtained by dividing an overall point cloud map.

The normal parameter feature library may be pre-stored in the vehicle service end, and the normal parameter feature library may be generated and stored by the vehicle service end in various embodiments.

For convenience of explanation and understanding, a method for generating a normal parameter feature library will be described as an example.

Referring to fig. 5, the figure is a flowchart of a method for generating a normal parameter feature library according to an embodiment of the present application.

The method for generating the normal parameter feature library provided by the embodiment of the application specifically comprises the following steps:

s501: the vehicle server divides the integral point cloud map into a plurality of block maps and obtains the coordinate parameters of each block map corresponding to the integral point cloud map.

The overall point cloud map can be a geomap obtained by splicing a vehicle server according to a multi-frame historical point cloud map. The historical point cloud map can be a point cloud map sent by the vehicle to the vehicle service end at a historical time point.

The S501 may adopt various embodiments, and one embodiment will be explained and explained as an example.

Referring to fig. 6, the figure is a flowchart of an implementation manner of S501 provided in an embodiment of the present application.

As an embodiment, S501 may specifically be:

s5011: and the vehicle service end divides the whole point cloud map to obtain a plurality of block maps.

S5011 may adopt various dividing methods, which are not specifically limited in this application.

It should be noted that the contents of each two block maps may be completely different, or may be partially the same.

S5012: the vehicle server sets a first block map in the plurality of block maps as an origin.

As an embodiment, S5012 may specifically be: the vehicle server randomly selects one block map from the plurality of block maps as a first block map, and sets the first block map as an origin.

As another embodiment, S5012 may specifically be: the vehicle server selects one block map from the plurality of block maps according to a specific rule to serve as a first block map, and sets the first block map as an origin.

The specific rule may be preset or determined according to an actual application scenario.

As an example, a particular rule may be to select one block map centered on the overall point cloud map.

As another example, a particular rule may be to select a block map located in the lower left corner of the overall point cloud map.

S5013: and the vehicle server determines the coordinate parameter of each block map corresponding to the whole point cloud map according to the position relation between other block maps except the first block map and the first block map.

As an example, when the overall point cloud map is divided into 3 block maps, and from left to right, the following are performed in sequence: and taking the first block map as an origin, the coordinate parameters of the first block map are (0,0), the coordinate parameters of the second block map are (1,0), and the coordinate parameters of the third block map are (2, 0).

S502: the vehicle service end divides each block map, converts three-dimensional coordinate data of radar scanning points in each sub map obtained through division into normal distribution parameter values, and obtains a normal distribution parameter set corresponding to each block map according to the normal distribution parameter values corresponding to each sub map.

The content of S502 is the same as that of S101, and is not described herein again.

S503: and the vehicle server obtains a normal parameter feature library corresponding to the whole point cloud map according to the normal distribution parameter set corresponding to each block map.

Based on the normal distribution parameter set generated by the above method, S1022 may adopt various embodiments, and one embodiment will be described as an example below.

Referring to fig. 7, this figure is a flowchart of an implementation manner of S1022 provided in this application.

As an embodiment, when the normal parameter feature library includes N normal distribution parameter sets, S1022 may specifically be:

s10221: and the vehicle server matches the first normal distribution parameter set with a first normal distribution parameter set in a normal parameter feature library.

S10222: and the vehicle server judges whether the matching is successful. If yes, go to S10223; if not, S10224 is performed.

S10223: and the vehicle server determines a first normal distribution parameter set in the normal parameter feature library as a second normal distribution parameter set which is successfully matched.

S10224: and the vehicle server side matches the first normal distribution parameter set with a second normal distribution parameter set in a normal parameter feature library.

S10225: and the vehicle server judges whether the matching is successful. If yes, go to S10226; if not, S10227 is performed.

S10226: and the vehicle server determines a second normal distribution parameter set in the normal parameter feature library as a second normal distribution parameter set which is successfully matched.

S10227: and the vehicle server side matches the first normal distribution parameter set with a third normal distribution parameter set in a normal parameter feature library.

And sequentially and repeatedly executing the matching of the first normal distribution parameter set and the ith normal distribution parameter set in the normal parameter feature library by the vehicle server, and judging whether the matching is successful. If so, the vehicle server side determines that the ith normal distribution parameter set in the normal parameter feature library is a second normal distribution parameter set successfully matched with the ith normal distribution parameter set; if not, the vehicle server side matches the first normal distribution parameter set with the (i + 1) th normal distribution parameter set in the normal parameter feature library.

S10228: and the vehicle server side matches the first normal distribution parameter set with the (N-1) th normal distribution parameter set in the normal parameter feature library.

S10229: and the vehicle server judges whether the matching is successful. If yes, go to S102210; if not, S102211 is performed.

S102210: and the vehicle server determines the N-1 th normal distribution parameter set in the normal parameter feature library to be a second normal distribution parameter set which is successfully matched.

S102211: and the vehicle server matches the first normal distribution parameter set with the Nth normal distribution parameter set in the normal parameter feature library.

S102212: and the vehicle server judges whether the matching is successful. If yes, go to S102213; if not, S102214 is performed.

S102213: and the vehicle server determines the Nth normal distribution parameter set in the normal parameter feature library as a second normal distribution parameter set which is successfully matched.

S102214: and the vehicle server side determines that the first normal distribution parameter set fails to be matched with the normal parameter feature library.

In the above embodiment, the vehicle service end sequentially matches the first normal distribution parameter set with the normal distribution parameter sets in the normal parameter feature library. However, in this embodiment of the application, the vehicle service end may sequentially match the first normal distribution parameter set with the normal distribution parameter sets in the normal parameter feature library according to different matching orders. This is not a particular limitation of the present application.

In the embodiments provided above, not only a specific embodiment of S102 when the normal parameter feature library includes at least one normal distribution parameter value but also a specific embodiment of S102 when the normal parameter feature library includes at least one normal distribution parameter set is provided. In addition, since in any of the embodiments provided above, a plurality of matching methods can be employed when matching is performed. For example, the matching method may be a newton optimization method.

For convenience of explanation and understanding, the following description will be given taking the matching using the newton's optimization method as an example.

As an embodiment, in order to further improve the matching accuracy, S102 may specifically be: and based on a Newton optimization method, the vehicle server side matches the first normal distribution parameter set formed by the normal distribution parameter values of each sub-map in a normal parameter feature library to obtain a second normal distribution parameter set successfully matched.

In this embodiment, when the normal parameter feature library includes at least one normal distribution parameter value, in order to further improve the matching accuracy, S102 may specifically be: firstly, based on a Newton optimization method, the vehicle server matches normal distribution parameter values in the first normal distribution parameter set with normal distribution parameter values in a normal parameter feature library to obtain successfully matched normal distribution parameter values; and then, the vehicle server side obtains a second normal distribution parameter set according to the successfully matched normal distribution parameter values.

When the normal parameter feature library includes at least one normal distribution parameter set, in order to further improve the matching accuracy, S102 may specifically be: and on the basis of a Newton optimization method, the vehicle server side matches the first normal distribution parameter set formed by the normal distribution parameter values of the sub-maps with the normal distribution parameter set in the normal parameter feature library to obtain a second normal distribution parameter set which is successfully matched.

S103: and the vehicle server determines vehicle position information in the whole point cloud map according to the coordinate parameters corresponding to the second normal distribution parameter set.

The whole point cloud map corresponds to the normal parameter feature library, so that the whole point cloud map can be positioned according to the coordinate parameters corresponding to the second normal distribution parameter set.

When the normal parameter feature library comprises at least one normal distribution parameter value, the normal distribution parameter values in the normal parameter feature library all correspond to sub-maps obtained by dividing the whole point cloud map, at this time, because the second normal distribution parameter set is formed by a plurality of normal distribution parameter values in the normal parameter feature library, and each sub-map corresponding to the normal distribution parameter value has one coordinate parameter, the coordinate parameter corresponding to the second normal distribution parameter set is a coordinate parameter set, and the coordinate parameter set comprises coordinate parameters of all sub-maps corresponding to the normal distribution parameter values which are successfully matched.

Therefore, when the normal parameter feature library includes at least one normal distribution parameter value, S103 may specifically be: and the vehicle server determines the vehicle position information in the whole point cloud map according to the coordinate parameter set corresponding to the second normal distribution parameter set.

In addition, when the normal parameter feature library includes at least one normal distribution parameter set, the normal distribution parameter sets in the normal parameter feature library all correspond to a block map obtained by dividing the whole point cloud map, and at this time, since the second normal distribution parameter set corresponds to one coordinate parameter in the whole point cloud data, S103 may specifically be: and the vehicle server determines vehicle position information in the whole point cloud map according to the coordinate parameters corresponding to the second normal distribution parameter set.

And the coordinate parameters corresponding to the second normal distribution parameter set are used for representing the positions of the block map corresponding to the second normal distribution parameter set on the whole point cloud map.

It should be noted that, after the vehicle service end obtains the vehicle position information, the vehicle service end may send the vehicle position information to the vehicle, and may also send the vehicle position information to other devices, which is not specifically limited in this application.

In the positioning method provided by the embodiment of the application, the data volume of the normal distribution parameter value is much smaller than that of the three-dimensional coordinate data of the radar scanning point in the sub-map, so that the data volume of the first normal distribution parameter set is much smaller than that of the first point cloud map, and the data volume of the normal parameter feature library is much smaller than that of the corresponding point cloud map, so that the data volume of the point cloud map is reduced. Therefore, when the first normal distribution parameter set is matched in the normal parameter feature library, the calculation amount required by the matching process is much smaller than that required by matching of different point cloud maps in the prior art, and the time required by the matching process is much smaller than that required by matching of different point cloud maps in the prior art, so that the calculation amount and the calculation time of the point cloud maps in the matching process are reduced, and the real-time performance of vehicle positioning is improved.

In the positioning method provided in the above embodiment, the vehicle sends the first point cloud map to the vehicle server, and the vehicle server obtains the first normal distribution parameter set according to the first point cloud map, so that the vehicle position information is determined by matching the first normal distribution parameter set with the normal distribution parameter set in the normal parameter feature library.

In addition, in order to improve the transmission efficiency of the vehicle and the vehicle server, the vehicle can also obtain the first normal distribution parameter set and send the first normal distribution parameter set to the vehicle server, so that the transmission data of the vehicle and the vehicle server are reduced, the transmission efficiency is improved, and the positioning efficiency is further improved. Therefore, the present application provides another implementation manner of the positioning method, which will be explained and explained with reference to the drawings.

Method embodiment two

For brevity, the same parts of method embodiment two and method embodiment one will not be described again.

Referring to fig. 8, the figure is a flowchart of another implementation of the positioning method provided in the embodiment of the present application.

s801: the vehicle scans by using a radar to obtain a first point cloud map.

The content of S801 is the same as that of S1011, and is not described again here.

S802: the vehicle divides the first point cloud map, converts the three-dimensional coordinate data of the radar scanning points in each sub map obtained through division into normal distribution parameter values, and obtains a first normal distribution parameter set according to the normal distribution parameter values corresponding to the sub maps.

S803: and the vehicle sends the first normal distribution parameter set to a vehicle server.

As an embodiment, S803 may specifically be: and the vehicle sends the first normal distribution parameter set to a vehicle server through a network.

S804: and the vehicle server side matches the first normal distribution parameter set sent by the vehicle in a normal parameter feature library to obtain a second normal distribution parameter set which is successfully matched.

The content of S804 is the same as that of S1022, and is not described herein again.

S805: and the vehicle server determines vehicle position information in the whole point cloud map according to the coordinate parameters corresponding to the second normal distribution parameter set.

The content of S805 is the same as that of S103, and is not described again here.

In the positioning method provided by the embodiment of the application, the first point cloud map is divided by a vehicle, three-dimensional coordinate data of radar scanning points in each sub-map obtained through division is converted into normal distribution parameter values, and a first normal distribution parameter set is obtained according to the normal distribution parameter values corresponding to the sub-maps. Therefore, the vehicle only needs to send the first normal distribution parameter set to the vehicle server side, and does not need to send the first point cloud map to the vehicle server side. The data volume of the first normal distribution parameter set is much smaller than that of the first point cloud map, so that the data volume required to be transmitted when the vehicle transmits the first normal distribution parameter set to the vehicle service end is much smaller than that required when the vehicle transmits the first point cloud map to the vehicle service end, the data volume transmitted between the vehicle and the vehicle service end is reduced, the transmission efficiency between the vehicle and the vehicle service end is improved, the positioning efficiency is improved, and the positioning instantaneity is further improved.

In the method provided by the above embodiment, the vehicle service end matches the first normal distribution parameter set in the normal parameter feature library, and determines the vehicle position information according to the coordinate parameter corresponding to the second normal distribution parameter set that is successfully matched.

In addition, in order to further improve the positioning efficiency, the vehicle may further match the first normal distribution parameter set, and determine the vehicle position according to the successfully matched normal distribution parameter set.

Method embodiment three

For brevity, the third method embodiment has the same contents as the first method embodiment, and the parts of the second method embodiment that have the same contents as the first method embodiment will not be described again.

Referring to fig. 9, which is a flowchart illustrating a further implementation of the positioning method according to an embodiment of the present application.

s901: the vehicle scans by using a radar to obtain a first point cloud map.

The content of S901 is the same as that of S1011, and is not described again here.

S902: the vehicle divides the first point cloud map, converts the three-dimensional coordinate data of the radar scanning points in each sub map obtained through division into normal distribution parameter values, and obtains a first normal distribution parameter set according to the normal distribution parameter values corresponding to the sub maps.

S903: and the vehicle matches the first normal distribution parameter set in a normal parameter feature library sent by a vehicle server to obtain a second normal distribution parameter set which is successfully matched.

S903 can perform matching after the vehicle receives the whole normal parameter feature library; and the matching can also be carried out while receiving the normal parameter feature library sent by the vehicle server.

As an embodiment, S903 may specifically be: and when the vehicle receives the normal parameter feature library sent by the vehicle server, the vehicle matches the first normal distribution parameter set in the normal parameter feature library to obtain a second normal distribution parameter set which is successfully matched.

In order to improve matching efficiency, S903 may also perform matching while receiving the normal parameter feature library sent by the vehicle service end.

For convenience of explanation and understanding, the normal parameter feature library will be described below as including at least one normal distribution parameter set as an example.

The S903 may adopt various embodiments, and one embodiment will be explained and explained as an example.

Referring to fig. 10, the figure is a flowchart of an implementation manner of S903 provided in an embodiment of the present application.

In one embodiment, when the normal parameter feature library includes N normal distribution parameter sets,

s903 may specifically be:

s9031: and the vehicle matches the first normal distribution parameter set with the first normal distribution parameter set sent by the vehicle server.

S9032: and the vehicle judges whether the matching is successful. If yes, executing S9033; if not, executing S9034.

S9033: and the vehicle determines that the first normal distribution parameter set sent by the vehicle server side is a second normal distribution parameter set which is successfully matched.

S9034: and the vehicle matches the first normal distribution parameter set with a second normal distribution parameter set sent by a vehicle server.

S9035: and the vehicle judges whether the matching is successful. If yes, executing S9036; if not, executing S9037.

S9036: and the vehicle determines that the second normal distribution parameter set sent by the vehicle server side is the second normal distribution parameter set which is successfully matched.

S9037: and the vehicle matches the first normal distribution parameter set with a third normal distribution parameter set sent by a vehicle server.

And the vehicle is repeatedly executed in sequence to match the first normal distribution parameter set with the ith normal distribution parameter set sent by the vehicle server, and whether the matching is successful is judged. If so, the vehicle determines that the ith normal distribution parameter set sent by the vehicle server side is a second normal distribution parameter set successfully matched with the ith normal distribution parameter set; if not, the vehicle matches the first normal distribution parameter set with the (i + 1) th normal distribution parameter set sent by the vehicle server.

S9038: and the vehicle matches the first normal distribution parameter set with the (N-1) th normal distribution parameter set sent by the vehicle server.

S9039: and the vehicle judges whether the matching is successful. If yes, executing S90310; if not, go to S90311.

S90310: and the vehicle determines that the N-1 th normal distribution parameter set sent by the vehicle server side is combined into a second normal distribution parameter set which is successfully matched.

S90311: and the vehicle matches the first normal distribution parameter set with the Nth normal distribution parameter set sent by the vehicle server.

S90312: and the vehicle judges whether the matching is successful. If yes, executing S90313; if not, go to S90314.

S90313: and the vehicle determines that the Nth normal distribution parameter set sent by the vehicle server side is a second normal distribution parameter set successfully matched with the Nth normal distribution parameter set.

S90314: the vehicle determines that the first normal distribution parameter set fails to match.

In the above embodiment, the vehicle sequentially matches the first normal distribution parameter set with the normal distribution parameter set sent by the vehicle server to obtain the second normal distribution parameter set successfully matched.

In the above embodiment, the normal parameter feature library includes at least one normal distribution parameter set as an example. However, when the normal parameter feature library includes at least one normal distribution parameter value, the above embodiment may also be adopted, and for brevity, the description of the present application is omitted.

S904: and the vehicle determines the vehicle position information in the whole point cloud map according to the coordinate information corresponding to the second normal distribution parameter set.

The S904 can adopt various embodiments, and two embodiments will be explained and explained as an example.

Referring to fig. 11, this figure is a flowchart of an implementation manner of S904 provided in this application example.

As an embodiment, S904 may specifically be:

s9041: and the vehicle receives the integral point cloud map sent by the vehicle service terminal.

S9042: and the vehicle determines the vehicle position information in the whole point cloud map according to the coordinate information corresponding to the second normal distribution parameter set.

Referring to fig. 12, which is a flowchart of another implementation of S904 provided in this application example.

As another embodiment, S904 may specifically be:

s904 a: the vehicle acquires an integral point cloud map from a storage space of the vehicle;

s904 b: and the vehicle determines the vehicle position information in the whole point cloud map according to the coordinate information corresponding to the second normal distribution parameter set.

According to the positioning method provided by the embodiment of the application, the vehicle obtains the first normal distribution parameter set according to the first point cloud map, and the vehicle position information is determined according to the second normal distribution parameter set successfully matched with the first normal distribution parameter set. In the process, the vehicle server only needs to send the normal distribution parameter set to be matched to the vehicle, other communication with the vehicle is not needed, the number of times of communication between the vehicle and the vehicle server is reduced, the number of times of data transmission between the vehicle and the vehicle server is reduced, the transmission efficiency between the vehicle and the vehicle server is further improved, and the positioning efficiency is further improved. In addition, the vehicle matches the first normal distribution parameter and the normal distribution parameter set sent by the vehicle server, but does not match the first point cloud map with the point cloud map sent by the vehicle server, so that the calculation amount in the matching process is reduced, the calculation time required in the matching process is also reduced, the positioning efficiency is improved, and the positioning instantaneity is further improved.

Based on the positioning method provided by the embodiment, the embodiment of the application provides a positioning device. Which will be explained and explained below in connection with the drawings.

Apparatus embodiment one

Referring to fig. 13, the figure is a schematic structural diagram of an implementation manner of a positioning device provided in an embodiment of the present application.

The positioner that this application embodiment provided includes:

the first conversion unit 1301 is used for the vehicle server to divide a first point cloud map sent by a vehicle and convert the three-dimensional coordinate data of radar scanning points in each sub-map obtained through division into normal distribution parameter values;

a first obtaining unit 1302, configured to match, by the vehicle service end, a first normal distribution parameter set formed by the normal distribution parameter values of each sub-map in a normal parameter feature library, so as to obtain a second normal distribution parameter set successfully matched;

and a first determining unit 1303, configured to determine, by the vehicle server, vehicle position information in the overall point cloud map according to the coordinate parameter corresponding to the second normal distribution parameter set.

In order to further improve the positioning efficiency and further improve the real-time performance of positioning, the first converting unit 1301 includes:

In order to further improve the positioning efficiency and further improve the positioning real-time performance, when the normal parameter feature library includes at least one normal distribution parameter value, the first obtaining unit 1302 specifically includes:

the first matching subunit is used for the vehicle server to match the normal distribution parameter values in the first normal distribution parameter set with the normal distribution parameter values in the normal parameter feature library to obtain successfully matched normal distribution parameter values;

and the first obtaining subunit is used for obtaining a second normal distribution parameter set by the vehicle server according to the successfully matched normal distribution parameter values.

In order to further improve the positioning efficiency and further improve the positioning real-time performance, the method for generating the normal parameter feature library specifically comprises the following steps:

In order to further improve the positioning efficiency and further improve the positioning real-time performance, when the normal parameter feature library includes at least one normal distribution parameter set, the first obtaining unit 1302 specifically includes:

and the vehicle server is used for matching the first normal distribution parameter set formed by the normal distribution parameter values of the sub-maps with the normal distribution parameter set in the normal parameter feature library to obtain a second normal distribution parameter set which is successfully matched.

In order to further improve the positioning efficiency and further improve the real-time performance of positioning, the first obtaining unit 1302 specifically includes:

and the vehicle service end is used for matching the first normal distribution parameter set formed by the normal distribution parameter values of the sub-maps in a normal parameter feature library based on a Newton optimization method to obtain a second normal distribution parameter set successfully matched.

The positioner that this application embodiment provided includes: a first conversion unit 1301, a first acquisition unit 1302, and a first determination unit 1303. In this apparatus, since the data amount of the normal distribution parameter value is much smaller than the data amount of the three-dimensional coordinate data of the radar scanning point in the sub-map, the data amount of the first normal distribution parameter set is much smaller than the data amount of the first point cloud map, and the data amount of the normal parameter feature library is also much smaller than the data amount of the corresponding point cloud map, thereby reducing the data amount of the point cloud map. Therefore, when the first normal distribution parameter set is matched in the normal parameter feature library, the calculation amount required by the matching process is much smaller than that required by matching of different point cloud maps in the prior art, and the time required by the matching process is much smaller than that required by matching of different point cloud maps in the prior art, so that the calculation amount and the calculation time of the point cloud maps in the matching process are reduced, and the real-time performance of vehicle positioning is improved.

Based on the positioning method and the positioning device provided by the above embodiments, embodiments of the present application further provide another implementation manner of the positioning device, which will be explained and explained below with reference to the accompanying drawings.

Device embodiment II

Referring to fig. 14, the drawing is a schematic structural view of another implementation manner of the positioning device provided in the embodiment of the present application.

The positioner that this application embodiment provided includes:

a second obtaining unit 1401, configured to scan the vehicle with a radar, and obtain a first point cloud map with a current vehicle position as a center;

a third obtaining unit 1402, configured to divide the first point cloud map by the vehicle, convert the three-dimensional coordinate data of the radar scanning points in each sub-map obtained through division into normal distribution parameter values, and obtain a first normal distribution parameter set according to the normal distribution parameter values corresponding to each sub-map;

a first sending unit 1403, configured to send the first normal distribution parameter set to a vehicle service end by the vehicle, so that the vehicle service end matches the first normal distribution parameter set in a normal parameter feature library, and determine vehicle position information in the whole point cloud map according to a coordinate parameter corresponding to a second normal distribution parameter set successfully matched with the first normal distribution parameter set.

In order to further improve the positioning efficiency and further improve the real-time performance of positioning, the third obtaining unit 1402 includes:

and the second dividing subunit is used for dividing the first point cloud map sent by the vehicle according to the square template or the rectangular template by the vehicle server.

The positioner that this application embodiment provided includes: a second acquisition unit 1401, a third acquisition unit 1402, and a first transmission unit 1403. In the device, the first point cloud map is divided through a vehicle, three-dimensional coordinate data of radar scanning points in each sub-map obtained through division are converted into normal distribution parameter values, and a first normal distribution parameter set is obtained according to the normal distribution parameter values corresponding to the sub-maps. Therefore, the vehicle only needs to send the first normal distribution parameter set to the vehicle server side, and does not need to send the first point cloud map to the vehicle server side. The data volume of the first normal distribution parameter set is much smaller than that of the first point cloud map, so that the data volume required to be transmitted when the vehicle transmits the first normal distribution parameter set to the vehicle service end is much smaller than that required when the vehicle transmits the first point cloud map to the vehicle service end, the data volume transmitted between the vehicle and the vehicle service end is reduced, the transmission efficiency between the vehicle and the vehicle service end is improved, the positioning efficiency is improved, and the positioning instantaneity is further improved.

Based on the positioning method and the positioning device provided by the above embodiments, the embodiments of the present application further provide another implementation manner of the positioning device, which will be explained and explained below with reference to the accompanying drawings.

Device embodiment III

Referring to fig. 15, the figure is a schematic structural diagram of another implementation manner of the positioning device provided in the embodiment of the present application.

The positioner that this application embodiment provided includes:

a fourth acquisition unit 1501, configured to scan the vehicle with a radar, and acquire a first point cloud map centered on a current vehicle position;

a fifth obtaining unit 1502, configured to divide the first point cloud map by the vehicle, convert the three-dimensional coordinate data of the radar scanning points in each sub-map obtained through division into normal distribution parameter values, and obtain a first normal distribution parameter set according to the normal distribution parameter values corresponding to each sub-map;

a sixth obtaining unit 1503, configured to match, by the vehicle, the first normal distribution parameter set with a normal distribution parameter set sent by a vehicle server to obtain a second normal distribution parameter set successfully matched;

a second determining unit 1504, configured to determine, by the vehicle, vehicle position information in the overall point cloud map according to the coordinate information corresponding to the second normal distribution parameter set.

In order to further improve the positioning efficiency and further improve the real-time performance of positioning, the fifth obtaining unit 1502 includes:

and the third dividing subunit is used for dividing the first point cloud map sent by the vehicle according to the square template or the rectangular template by the vehicle server.

In order to further improve the positioning efficiency and further improve the positioning real-time performance, when the normal parameter feature library includes at least one normal distribution parameter value, the sixth obtaining unit 1503 specifically includes:

the second matching subunit is used for matching the normal distribution parameter values in the first normal distribution parameter set with the normal distribution parameter values in the normal parameter feature library by the vehicle to obtain the successfully matched normal distribution parameter values;

and the second obtaining subunit is used for obtaining a second normal distribution parameter set by the vehicle according to the successfully matched normal distribution parameter values.

In order to further improve the positioning efficiency and further improve the positioning real-time performance, when the normal parameter feature library includes at least one normal distribution parameter set, the sixth obtaining unit 1503 specifically includes:

and the vehicle is used for matching the first normal distribution parameter set with a normal distribution parameter set in a normal parameter feature library sent by a vehicle server to obtain a second normal distribution parameter set successfully matched with the first normal distribution parameter set.

In order to further improve the positioning efficiency and further improve the real-time performance of positioning, the sixth obtaining unit 1503 specifically includes:

the method is used for matching the first normal distribution parameter set in a normal parameter feature library sent by a vehicle server side by the vehicle based on a Newton optimization method to obtain a second normal distribution parameter set which is successfully matched.

The positioner that this application embodiment provided includes: a fourth acquisition unit 1501, a fifth acquisition unit 1502, a sixth acquisition unit 1503, and a second determination unit 1504. In the device, a first normal distribution parameter set is obtained through a vehicle according to a first point cloud map, and vehicle position information is determined according to a second normal distribution parameter set successfully matched with the first normal distribution parameter set. In the process, the vehicle server only needs to send the normal distribution parameter set to be matched to the vehicle, other communication with the vehicle is not needed, the number of times of communication between the vehicle and the vehicle server is reduced, the number of times of data transmission between the vehicle and the vehicle server is reduced, the transmission efficiency between the vehicle and the vehicle server is further improved, and the positioning efficiency is further improved. In addition, the vehicle matches the first normal distribution parameter and the normal distribution parameter set sent by the vehicle server, but does not match the first point cloud map with the point cloud map sent by the vehicle server, so that the calculation amount in the matching process is reduced, the calculation time required in the matching process is also reduced, the positioning efficiency is improved, and the positioning instantaneity is further improved.

It should be understood that in the present application, "at least one" means one or more, "a plurality" means two or more. "and/or" for describing an association relationship of associated objects, indicating that there may be three relationships, e.g., "a and/or B" may indicate: only A, only B and both A and B are present, wherein A and B may be singular or plural. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship. "at least one of the following" or similar expressions refer to any combination of these items, including any combination of single item(s) or plural items. For example, at least one (one) of a, b, or c, may represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", wherein a, b, c may be single or plural.

The foregoing is merely a preferred embodiment of the invention and is not intended to limit the invention in any manner. Although the present invention has been described with reference to the preferred embodiments, it is not intended to be limited thereto. Those skilled in the art can make numerous possible variations and modifications to the present teachings, or modify equivalent embodiments to equivalent variations, without departing from the scope of the present teachings, using the methods and techniques disclosed above. Therefore, any simple modification, equivalent change and modification made to the above embodiments according to the technical essence of the present invention are still within the scope of the protection of the technical solution of the present invention, unless the contents of the technical solution of the present invention are departed.

Claims

1. A positioning method for a vehicle service end, comprising:

dividing a first point cloud map sent by a vehicle, and converting three-dimensional coordinate data of radar scanning points in each sub-map obtained through division into normal distribution parameter values; wherein the normal distribution parameter values include: the mean and standard deviation in the x-direction, the mean and standard deviation in the y-direction, and the mean and standard deviation in the z-direction;

matching the first normal distribution parameter set formed by the normal distribution parameter values of each sub-map in a normal parameter feature library to obtain a second normal distribution parameter set successfully matched;

and determining vehicle position information in the whole point cloud map according to the coordinate parameters corresponding to the second normal distribution parameter set.

2. The method according to claim 1, wherein when the normal parameter feature library includes at least one normal distribution parameter value, the first normal distribution parameter set formed by the normal distribution parameter values of the sub-maps is matched in the normal parameter feature library to obtain a second normal distribution parameter set successfully matched, specifically:

matching the normal distribution parameter values in the first normal distribution parameter set with the normal distribution parameter values in a normal parameter feature library to obtain successfully matched normal distribution parameter values;

and obtaining a second normal distribution parameter set according to the successfully matched normal distribution parameter values.

3. The method according to claim 2, wherein the generation method of the normal parameter feature library specifically comprises:

dividing the integral point cloud map into a plurality of sub-maps, and obtaining coordinate parameters of each sub-map corresponding to the integral point cloud map;

converting the three-dimensional coordinate data of the radar scanning points in each sub-map obtained by dividing into normal distribution parameter values;

and obtaining a normal parameter feature library corresponding to the whole point cloud map according to the normal distribution parameter values corresponding to the sub-maps.

4. The method according to claim 1, wherein when the normal parameter feature library includes at least one normal distribution parameter set, the first normal distribution parameter set formed by the normal distribution parameter values of the sub-maps is matched in the normal parameter feature library to obtain a second normal distribution parameter set successfully matched, specifically:

and matching the first normal distribution parameter set formed by the normal distribution parameter values of each sub-map with the normal distribution parameter set in the normal parameter feature library to obtain a second normal distribution parameter set successfully matched.

5. The method according to claim 4, wherein the generation method of the normal parameter feature library specifically comprises:

dividing the integral point cloud map into a plurality of block maps, and obtaining coordinate parameters of each block map corresponding to the integral point cloud map;

dividing each block map, converting three-dimensional coordinate data of radar scanning points in each sub map obtained by division into normal distribution parameter values, and obtaining a normal distribution parameter set corresponding to each block map according to the normal distribution parameter values corresponding to each sub map;

and obtaining a normal parameter feature library corresponding to the whole point cloud map according to the normal distribution parameter set corresponding to each block map.

6. The method according to claim 1, wherein the matching is performed on a first normal distribution parameter set formed by normal distribution parameter values of the sub-maps in a normal parameter feature library to obtain a successfully matched second normal distribution parameter set, specifically:

and matching the first normal distribution parameter set formed by the normal distribution parameter values of the sub-maps in a normal parameter feature library based on a Newton optimization method to obtain a second normal distribution parameter set successfully matched.

7. The method according to claim 1, wherein the first point cloud map sent by the vehicle is divided, specifically:

and dividing the first point cloud map sent by the vehicle according to a square template or a rectangular template.

8. A positioning method for a vehicle, comprising:

scanning by using a radar to obtain a first point cloud map;

dividing the first point cloud map, converting the three-dimensional coordinate data of the radar scanning points in each sub map obtained by dividing into normal distribution parameter values, and obtaining a first normal distribution parameter set according to the normal distribution parameter values corresponding to the sub maps; wherein the normal distribution parameter values include: the mean and standard deviation in the x-direction, the mean and standard deviation in the y-direction, and the mean and standard deviation in the z-direction;

and sending the first normal distribution parameter set to a vehicle server so that the vehicle server matches the first normal distribution parameter set in a normal parameter feature library, and determining vehicle position information in the whole point cloud map according to coordinate parameters corresponding to a second normal distribution parameter set successfully matched with the first normal distribution parameter set.

9. A positioning method for a vehicle, comprising:

scanning by using a radar to obtain a first point cloud map;

matching the first normal distribution parameter set in a normal parameter feature library sent by a vehicle server to obtain a second normal distribution parameter set successfully matched;

and determining vehicle position information in the whole point cloud map according to the coordinate information corresponding to the second normal distribution parameter set.

10. The method according to claim 9, wherein when the normal parameter feature library includes at least one normal distribution parameter value, the first normal distribution parameter set is matched in a normal parameter feature library sent by a vehicle service end to obtain a second normal distribution parameter set successfully matched, specifically:

11. The method according to claim 9, wherein when the normal parameter feature library includes at least one normal distribution parameter set, the first normal distribution parameter set is matched in a normal parameter feature library sent by a vehicle service end to obtain a second normal distribution parameter set successfully matched, specifically:

and matching the first normal distribution parameter set with a normal distribution parameter set in a normal parameter feature library to obtain a second normal distribution parameter set which is successfully matched.

12. The method according to claim 9, wherein the matching of the first normal distribution parameter set in a normal parameter feature library sent by a vehicle service end is performed to obtain a successfully matched second normal distribution parameter set, which specifically includes:

and matching the first normal distribution parameter set in a normal parameter feature library sent by a vehicle server based on a Newton optimization method to obtain a second normal distribution parameter set successfully matched.

13. A locating device for a vehicle service end, comprising:

the first conversion unit is used for dividing a first point cloud map sent by a vehicle and converting three-dimensional coordinate data of radar scanning points in each sub-map obtained through division into normal distribution parameter values; wherein the normal distribution parameter values include: the mean and standard deviation in the x-direction, the mean and standard deviation in the y-direction, and the mean and standard deviation in the z-direction;

the first obtaining unit is used for matching a first normal distribution parameter set formed by the normal distribution parameter values of the sub-maps in a normal parameter feature library to obtain a second normal distribution parameter set which is successfully matched;

and the first determining unit is used for determining the vehicle position information in the whole point cloud map according to the coordinate parameters corresponding to the second normal distribution parameter set.

14. A positioning device, for a vehicle, comprising:

the second acquisition unit is used for scanning by using a radar and acquiring a first point cloud map with the current vehicle position as the center;

the third acquisition unit is used for dividing the first point cloud map, converting the three-dimensional coordinate data of the radar scanning points in each sub-map obtained through division into normal distribution parameter values, and obtaining a first normal distribution parameter set according to the normal distribution parameter values corresponding to the sub-maps; wherein the normal distribution parameter values include: the mean and standard deviation in the x-direction, the mean and standard deviation in the y-direction, and the mean and standard deviation in the z-direction;

and the first sending unit is used for sending the first normal distribution parameter set to a vehicle server so that the vehicle server matches the first normal distribution parameter set in a normal parameter feature library, and determining vehicle position information in the whole point cloud map according to the coordinate parameters corresponding to a second normal distribution parameter set successfully matched with the first normal distribution parameter set.

15. A positioning device, for a vehicle, comprising:

the fourth acquisition unit is used for scanning by using a radar and acquiring a first point cloud map with the current vehicle position as the center;

a fifth obtaining unit, configured to divide the first point cloud map, convert the three-dimensional coordinate data of the radar scanning points in each sub-map obtained through division into normal distribution parameter values, and obtain a first normal distribution parameter set according to the normal distribution parameter values corresponding to the sub-maps; wherein the normal distribution parameter values include: the mean and standard deviation in the x-direction, the mean and standard deviation in the y-direction, and the mean and standard deviation in the z-direction;

a sixth obtaining unit, configured to match the first normal distribution parameter set in a normal parameter feature library sent by a vehicle service end, so as to obtain a second normal distribution parameter set successfully matched;