CN112698315A - Mobile device positioning system, method and device - Google Patents
Mobile device positioning system, method and device Download PDFInfo
- Publication number
- CN112698315A CN112698315A CN201911015827.9A CN201911015827A CN112698315A CN 112698315 A CN112698315 A CN 112698315A CN 201911015827 A CN201911015827 A CN 201911015827A CN 112698315 A CN112698315 A CN 112698315A
- Authority
- CN
- China
- Prior art keywords
- road
- data
- current frame
- road characteristic
- determining
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 141
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 claims description 22
- 230000033001 locomotion Effects 0.000 claims description 16
- 238000004422 calculation algorithm Methods 0.000 claims description 15
- 229910052742 iron Inorganic materials 0.000 claims description 11
- 238000001914 filtration Methods 0.000 claims description 8
- 239000004575 stone Substances 0.000 claims description 8
- 238000013500 data storage Methods 0.000 claims description 5
- 238000010586 diagram Methods 0.000 abstract description 24
- 238000012545 processing Methods 0.000 abstract description 21
- 238000000605 extraction Methods 0.000 abstract description 8
- 230000014509 gene expression Effects 0.000 abstract description 7
- 238000004364 calculation method Methods 0.000 description 9
- 230000004927 fusion Effects 0.000 description 7
- 230000008569 process Effects 0.000 description 7
- 230000003068 static effect Effects 0.000 description 6
- 239000000284 extract Substances 0.000 description 5
- 238000001514 detection method Methods 0.000 description 4
- 230000008447 perception Effects 0.000 description 4
- 230000001133 acceleration Effects 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 3
- 238000004590 computer program Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000007613 environmental effect Effects 0.000 description 3
- 230000003993 interaction Effects 0.000 description 3
- 239000002184 metal Substances 0.000 description 3
- 229910052751 metal Inorganic materials 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 230000001934 delay Effects 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000002310 reflectometry Methods 0.000 description 2
- 230000004888 barrier function Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 239000002689 soil Substances 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/02—Systems using reflection of radio waves, e.g. primary radar systems; Analogous systems
- G01S13/06—Systems determining position data of a target
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/88—Radar or analogous systems specially adapted for specific applications
- G01S13/93—Radar or analogous systems specially adapted for specific applications for anti-collision purposes
- G01S13/931—Radar or analogous systems specially adapted for specific applications for anti-collision purposes of land vehicles
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/02—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00
- G01S7/41—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00 using analysis of echo signal for target characterisation; Target signature; Target cross-section
- G01S7/415—Identification of targets based on measurements of movement associated with the target
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- Computer Networks & Wireless Communication (AREA)
- General Physics & Mathematics (AREA)
- Electromagnetism (AREA)
- Traffic Control Systems (AREA)
Abstract
The application discloses a mobile device positioning system, a method, a device and related equipment. The positioning method comprises the following steps: collecting road environment data of a current frame; determining road characteristic determination reference factors of the object of the current frame according to the road environment data of the current frame and the historical frame; determining a reference factor according to the road characteristics, and determining any type of road characteristic data of the current frame from the object of the current frame; and determining the pose data of the mobile equipment according to the road characteristic data of the current frame and a pre-generated road characteristic data set. By adopting the processing mode, effective road characteristics with unlimited characteristic types are extracted, the road characteristic expression capacity is enhanced, and the comprehensive and accurate extraction of road environment characteristic points is achieved, so that a road characteristic diagram with high data quality is constructed, and equipment positioning is carried out on the basis of high-quality real-time road characteristics and a high-quality road characteristic data set; therefore, the positioning accuracy and robustness can be effectively improved, and the equipment cost is reduced.
Description
Technical Field
The application relates to the technical field of automatic driving, in particular to a mobile equipment positioning system, a method and a device, a road characteristic data generation method and a device, electronic equipment and mobile equipment.
Background
Vehicle location is one of the most basic, critical services to enable L3+ level autonomous driving. Current means for autonomous vehicle positioning include: RTK positioning, inertial navigation positioning, laser radar positioning, millimeter wave radar positioning, visual positioning, and the like. The millimeter wave radar has the advantages of low equipment cost, strong bad weather resistance, wide detection range and the like, and most vehicles are equipped with the millimeter wave radar, so that a stable and cheap high-precision positioning selection is provided for the L3+ automatic driving vehicle.
Currently, a typical vehicle positioning method based on millimeter wave radar is a Bosch Road Signature (Bosch Road Signature) positioning method. The Bosch road characteristic is a positioning service based on a high-precision map and a vehicle-mounted environment perception sensor, and the service and a Bosch satellite positioning intelligent sensor jointly form a Bosch automatic driving positioning solution, so that the safety of an automatic driving vehicle is improved. The cameras and radar mounted on the vehicles generate the Bosch road features by identifying the environmental features around the road, such as lane lines, traffic lights, guardrails, and the like. Different from a single positioning scheme depending on a camera, the radar sensor can identify road characteristics even under dark or low-visibility road conditions, and the detection range is wider. Through the vehicle-mounted communication module, the road characteristic information is transmitted to the cloud server, is used and generates an independent sensor positioning layer, and is finally integrated into a part of a high-precision map by a map provider. The road characteristic information that the automatic driving vehicle obtained through on-vehicle environmental perception sensor compares in real time with high-accuracy map location layer, can accurately know the position of oneself in current lane to realize centimeter level location.
However, in the process of implementing the present invention, the inventor finds that the bosch road feature positioning method has at least the following problems: 1) because the millimeter wave radar can only detect metal objects, the height information is insufficient, and the mode identification of the target cannot be carried out, namely the object of the target cannot be judged, the method fuses the millimeter wave radar and the camera, and determines different types of road features such as lane lines, traffic signal lamps, guardrails and the like by virtue of the object identification capability of the camera, so as to form a road map, and therefore, the technology based on sensor fusion can cause higher hardware cost and more calculation processing, so that more calculation resources and storage resources can be consumed, the positioning speed of equipment is reduced, and in addition, the synchronous time service processing related to the multi-sensor fusion can also cause the accuracy of the road map and the positioning of the equipment to be reduced, and more calculation resources to be consumed; 2) the millimeter wave radar feature data determined by the method is based on the labeled data of the road features, and is not the road features obtained by a data classification mode, so that the quantity and the types of identifiable road features are limited, the millimeter wave radar feature data only comprise conventional road features such as lane lines, traffic lights and guardrails, and no new road features which are not present in labeled data such as stone piers and iron columns are included, equipment is positioned based on the limited road features, and once some road segments have road features which are not obvious and of known types (such as traffic lights and guardrails), equipment positioning cannot be performed by means of a road map, and the robustness of vehicle positioning is reduced; 3) because the millimeter wave radar feature data are not enhanced by emphasis data, the accuracy of the road features is low, and the accuracy of equipment positioning is influenced; 4) because the millimeter wave radar is not a sensor for accurate time service, and a clock signal of a vehicle system is used for stamping time stamps on the sensing data of the millimeter wave radar, the time inconsistency of the sensor and the vehicle system can influence the accuracy of a road map and vehicle positioning.
Disclosure of Invention
The application provides a mobile device positioning system, which aims to solve the problems of low device positioning accuracy and robustness and the like in the prior art. The application further provides a mobile device positioning method and device, a road characteristic data generation method and device, an electronic device and a mobile device.
The application provides a mobile equipment positioning method, which comprises the following steps:
the first mobile equipment is used for acquiring road environment data of a first current frame in a driving road through the first space scanning device; determining a first road characteristic determination reference factor of the object of the first current frame according to the road environment data of the first current frame and the road environment data of the first historical frame, wherein the first road characteristic determination reference factor is multi-frame linkage data related to the road environment data of the first historical frame; determining a reference factor according to the first road characteristic, and determining any type of road characteristic data of a first current frame from the first current frame object; sending a road characteristic data acquisition and storage request aiming at the road characteristic data of the first current frame to a server;
the server is used for receiving the data acquisition and storage request and storing the road characteristic data of the first current frame into a road characteristic data set;
the second mobile equipment is used for acquiring road environment data of a second current frame in the driving road through a second space scanning device; determining a second road characteristic determination reference factor of the object of the second current frame according to the road environment data of the second current frame and the road environment data of the second historical frame, wherein the second road characteristic determination reference factor is multi-frame linkage data related to the road environment data of the second historical frame; determining a reference factor according to the second road characteristic, and determining any type of road characteristic data of a second current frame from the second current frame object; and determining pose data of the second mobile equipment according to the road characteristic data of the second current frame and the road characteristic data set.
The application also provides a road characteristic data generation method, which comprises the following steps:
collecting road environment data in a driving road through a space scanning device to serve as the road environment data of a current frame;
determining a road characteristic determination reference factor of an object of the current frame according to the road environment data of the current frame and the road environment data of a plurality of historical frames before the current frame, wherein the road characteristic determination reference factor is multi-frame linkage data related to the road environment data of the historical frames;
determining a reference factor according to the road characteristics, and determining any type of road characteristic data of the current frame from the current frame object;
and sending a road characteristic data acquisition and storage request aiming at the road characteristic data of the current frame to a server.
The application also provides a mobile device positioning method, which comprises the following steps:
receiving a road characteristic data acquisition and storage request aiming at the road characteristic data of a first current frame, which is sent by a first mobile device;
and storing the road characteristic data of the first current frame into a road characteristic data set.
Optionally, the road characteristic data set is stored in a road characteristic database.
Optionally, the method further includes:
receiving a mobile equipment positioning request aiming at the road characteristic data of the second current frame, which is sent by the second mobile equipment;
determining pose data of the second mobile equipment according to the road characteristic data of the second current frame and the road characteristic data set;
returning the pose data to the second mobile device.
The application also provides a mobile device positioning method, which comprises the following steps:
collecting road environment data in a driving road through a space scanning device to serve as the road environment data of a current frame;
determining a road characteristic determination reference factor of an object of the current frame according to the road environment data of the current frame and the road environment data of a plurality of historical frames before the current frame, wherein the road characteristic determination reference factor is multi-frame linkage data related to the road environment data of the historical frames;
determining a reference factor according to the road characteristics, and determining any type of road characteristic data of the current frame from the current frame object;
and determining pose data of the mobile equipment according to the road characteristic data and the road characteristic data set of the current frame.
Optionally, the determining the pose data of the mobile device according to the road feature data and the road feature data set of the current frame includes:
sending a mobile equipment positioning request aiming at road characteristic data of a current frame to a server, so that the server determines the pose data according to the road characteristic data of the current frame and the road characteristic data set;
and receiving the pose data returned by the server.
Optionally, the determining the pose data of the mobile device according to the road feature data and the road feature data set of the current frame includes:
and determining the pose data of the mobile equipment according to the road characteristic data of the current frame and a road characteristic data set stored in the local of the mobile equipment.
Optionally, any type of road feature includes: stone pier, iron column and nail.
Optionally, the spatial scanning device comprises an electromagnetic wave scanning device.
Optionally, the electromagnetic wave scanning device includes a millimeter wave radar.
Optionally, the road characteristic determination reference factor includes: accumulating the occurrence times of the object in the current frame and the historical frame, and the first position distance of the object in the current frame and the historical frame;
the determining of the reference factor according to the road feature and the determining of the road feature data of any type of the current frame from the current frame object includes:
and taking the position data of the target with the occurrence frequency larger than the occurrence frequency threshold and the first position distance smaller than the first distance threshold as the first road characteristic data of the current frame.
Optionally, the determining a reference factor according to the road feature, and determining any type of road feature data of the current frame from the current frame object further includes:
and determining second road characteristic data of the current frame according to the first road characteristic data through a road characteristic enhancement algorithm.
Optionally, the road characteristic enhancement algorithm includes:
and taking the first road characteristic data as the center and data which is subjected to Gaussian distribution as second road characteristic data.
Optionally, the distance between the positions of the adjacent historical frames is greater than a second distance threshold;
the method further comprises the following steps:
and if the second distance between the current frame and the adjacent historical frame reaches a second distance threshold, taking the current frame as a newly-added historical frame.
Optionally, the method further includes:
and if the number of the historical frames is greater than the threshold value of the historical frame data, removing the historical frames meeting the historical frame removing condition.
Optionally, the method further includes:
and determining a reference factor according to the road characteristics of the newly added historical frame, and marking the road characteristic type of each object in the newly added historical frame.
Optionally, the reference factor is determined according to the road characteristics of the newly added historical frame, the road characteristic type of each object in the newly added historical frame is marked, and at least one of the following modes is adopted:
marking objects corresponding to the road characteristic data in the newly-added historical frame as characteristic points;
marking the objects of which the occurrence times of the newly-added historical frames are less than the threshold value of the occurrence times as lively points;
and marking the objects with the appearance times of the newly-added historical frames smaller than an appearance time threshold value and the first position distance larger than a first distance threshold value as wandering points.
Optionally, the first position distance is determined by the following steps:
converting the road environment data of the current frame and the road environment data of the historical frame into road environment data under the same coordinate system;
taking the mean distance variance as the first location distance.
Optionally, the determining the pose data of the mobile device according to the road feature data and the road feature data set of the current frame includes:
acquiring pose data of a previous frame of the current frame; acquiring the movement distance of the current frame relative to the previous frame; acquiring road characteristic data of the historical frame;
and determining the pose data of the mobile equipment by a Bayesian filtering algorithm according to the road feature data of the current frame, the road feature data of the historical frame, the pose data of the previous frame, the motion distance and the road feature data set.
Optionally, the method further includes:
and updating the pose data of the previous frame according to the determined pose data.
Optionally, the initial pose data of the mobile device comprises pose data determined from a satellite positioning system.
Optionally, the method further includes:
determining time delay data according to the position difference of the same object in the current frame and the historical frame and the moving speed of the mobile equipment;
and calibrating the data acquisition time of the current frame according to the delay data.
The present application further provides a road characteristic data generation device, including:
the data acquisition unit is used for acquiring road environment data in a driving road through the space scanning device and taking the road environment data as road environment data of a current frame;
the reference factor determining unit is used for determining a road characteristic determination reference factor of an object of the current frame according to the road environment data of the current frame and the road environment data of a plurality of historical frames before the current frame, wherein the road characteristic determination reference factor is multi-frame linkage data related to the road environment data of the historical frames;
the road characteristic determining unit is used for determining a reference factor according to the road characteristics and determining any type of road characteristic data of the current frame from the current frame object;
and the request sending unit is used for sending a road characteristic data acquisition and storage request aiming at the road characteristic data of the current frame to the server.
The present application further provides a mobile device positioning apparatus, including:
the request receiving unit is used for receiving a road characteristic data acquisition and storage request aiming at the road characteristic data of a first current frame, which is sent by a first mobile device;
and the data storage unit is used for storing the road characteristic data of the first current frame into a road characteristic data set.
The present application further provides a mobile device positioning apparatus, including:
the data acquisition unit is used for acquiring road environment data in a driving road through the space scanning device and taking the road environment data as road environment data of a current frame;
the reference factor determining unit is used for determining a road characteristic determination reference factor of an object of the current frame according to the road environment data of the current frame and the road environment data of a plurality of historical frames before the current frame, wherein the road characteristic determination reference factor is multi-frame linkage data related to the road environment data of the historical frames;
the road characteristic determining unit is used for determining a reference factor according to the road characteristics and determining any type of road characteristic data of the current frame from the current frame object;
and the pose data determining unit is used for determining the pose data of the mobile equipment according to the road characteristic data and the road characteristic data set of the current frame.
The present application further provides a mobile device, comprising:
a spatial scanning device;
a processor; and
a memory for storing a program for implementing a road characteristic data generating method, the apparatus performing the following steps after being powered on and running the program of the method by the processor: collecting road environment data in a driving road through a space scanning device to serve as the road environment data of a current frame; determining a road characteristic determination reference factor of an object of the current frame according to the road environment data of the current frame and the road environment data of a plurality of historical frames before the current frame, wherein the road characteristic determination reference factor is multi-frame linkage data related to the road environment data of the historical frames; determining a reference factor according to the road characteristics, and determining any type of road characteristic data of the current frame from the current frame object; and sending a road characteristic data acquisition and storage request aiming at the road characteristic data of the current frame to a server.
The present application further provides a mobile device, comprising:
a spatial scanning device;
a processor; and
a memory for storing a program for implementing a method for locating a mobile device, the device being powered on and the program for implementing the method being executed by the processor for performing the steps of: receiving a road characteristic data acquisition and storage request aiming at the road characteristic data of a first current frame, which is sent by a first mobile device; and storing the road characteristic data of the first current frame into a road characteristic data set.
The present application further provides an electronic device, comprising:
a processor; and
a memory for storing a program for implementing a method for locating a mobile device, the device being powered on and the program for implementing the method being executed by the processor for performing the steps of: collecting road environment data in a driving road through a space scanning device to serve as the road environment data of a current frame; determining a road characteristic determination reference factor of an object of the current frame according to the road environment data of the current frame and the road environment data of a plurality of historical frames before the current frame, wherein the road characteristic determination reference factor is multi-frame linkage data related to the road environment data of the historical frames; determining a reference factor according to the road characteristics, and determining any type of road characteristic data of the current frame from the current frame object; and determining pose data of the mobile equipment according to the road characteristic data and the road characteristic data set of the current frame.
The present application also provides a computer-readable storage medium having stored therein instructions, which when run on a computer, cause the computer to perform the various methods described above.
The present application also provides a computer program product comprising instructions which, when run on a computer, cause the computer to perform the various methods described above.
Compared with the prior art, the method has the following advantages:
the mobile equipment positioning system provided by the embodiment of the application acquires road environment data of a first current frame in a driving road through a first space scanning device of first mobile equipment; determining a first road characteristic determination reference factor of a first current frame object according to the road environment data of the first current frame and the road environment data of the first historical frame; determining a reference factor according to the first road characteristic, and determining any type of road characteristic data of a first current frame from the first current frame object; sending a road characteristic data acquisition and storage request aiming at the road characteristic data of a first current frame to a server, so that the server stores the road characteristic data of the first current frame into a road characteristic data set; then, collecting road environment data of a second current frame in the driving road through a second space scanning device of second mobile equipment; determining a second road characteristic determination reference factor of a second current frame object according to the road environment data of the second current frame and the road environment data of a second historical frame; determining a reference factor according to the second road characteristic, and determining any type of road characteristic data of a second current frame from the second current frame object; determining pose data of a second mobile device according to the road characteristic data of the second current frame and the road characteristic data set; the processing mode extracts effective road characteristics with unlimited characteristic types from the road environment data of the current frame in a key point classification mode by combining the multi-frame accumulated road characteristic determination factors, enhances the road characteristic expression capacity, achieves the comprehensive and accurate extraction of road environment characteristic points, constructs a road characteristic diagram with high data quality, and carries out equipment positioning based on high-quality real-time road characteristics and a high-quality road characteristic data set; therefore, the positioning accuracy can be effectively improved. Meanwhile, the extracted road characteristics comprise any type of stable road characteristics, so that the problem that positioning cannot be performed when conventional road characteristics (such as structural characteristics and the like) cannot be effectively obtained is solved; therefore, the positioning robustness can be effectively improved. In addition, other sensors (such as cameras) are not needed to assist in determining road characteristics, and the problem of asynchronous time service during multi-sensor fusion is avoided; therefore, the equipment cost can be effectively reduced, and the positioning accuracy is improved.
Drawings
FIG. 1 is a schematic block diagram of an embodiment of a mobile device positioning system provided herein;
FIG. 2 is a schematic diagram of a scenario of an embodiment of a mobile device positioning system provided herein;
FIG. 3 is an interaction diagram of an embodiment of a mobile device location system provided herein;
FIG. 4 is a flow chart of extracting road features of an embodiment of a mobile device positioning system provided herein;
FIG. 5 is a schematic diagram of mobile device side feature enhancements for an embodiment of a mobile device positioning system provided herein;
fig. 6 is a flowchart of a dynamic time delay at a second mobile device side of an embodiment of a mobile device positioning system provided in the present application;
FIG. 7 is a diagram illustrating dynamic time delays on a second mobile device side of an embodiment of a mobile device positioning system provided herein;
FIG. 8 is a flow chart of a first mobile-device-side generation of a road characteristic data set of an embodiment of a mobile-device positioning system provided herein;
fig. 9 is a flowchart of second mobile device side device location of an embodiment of a mobile device location system provided by the present application;
FIG. 10 is a flow chart of an embodiment of a road characteristic data set generation method provided herein;
FIG. 11 is a schematic view of an embodiment of a road characteristic data set generation apparatus provided herein;
FIG. 12 is a schematic diagram of one embodiment of a mobile device provided herein;
FIG. 13 is a flow chart of an embodiment of a mobile device location method provided herein;
FIG. 14 is a schematic diagram of an embodiment of a mobile device positioning apparatus provided herein;
FIG. 15 is a schematic diagram of an embodiment of an electronic device provided herein;
FIG. 16 is a flow chart of an embodiment of a mobile device location method provided herein;
FIG. 17 is a schematic diagram of an embodiment of a mobile device positioning apparatus provided herein;
fig. 18 is a schematic diagram of an embodiment of a mobile device provided in the present application.
Detailed Description
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application. This application is capable of implementation in many different ways than those herein set forth and of similar import by those skilled in the art without departing from the spirit of this application and is therefore not limited to the specific implementations disclosed below.
In the application, a mobile device positioning system, a method and a device, a road characteristic data generation method and a device, an electronic device and a mobile device are provided. In the following embodiments, the vehicle will be taken as an example, and each of the various schemes will be described in detail.
First embodiment
Please refer to fig. 1, which is a diagram illustrating an embodiment of a mobile device positioning system according to the present application. The application provides a mobile device positioning system includes: a first mobile device 1, a server 2 and a second mobile device 2.
The processing procedure for realizing the positioning of the mobile equipment by the system provided by the embodiment of the application comprises two stages: 1. a road characteristic data set generation stage, wherein a road characteristic data set is generated through interaction of first mobile equipment and a server side, and the data set covers road characteristic data in a target road area; 2. and a mobile equipment positioning stage, wherein the second mobile equipment compares the road characteristics of the current position of the second mobile equipment with the data in the data set by using the road characteristic data set, and takes the position of the matched characteristic point as the current position of the second mobile equipment. The processing procedure of the above two stages will be described below.
1. A road characteristic data set generation phase.
This stage involves the first mobile device and the server. And the first mobile equipment is responsible for acquiring and processing the road characteristic data at the stage, and uploading the identified road characteristic data to a server for storage. The first mobile device, including but not limited to: a movable apparatus such as an unmanned vehicle, a mobile robot, etc., and may also be a manned vehicle or the like loaded with the first space scanning device.
And the server is responsible for storing the road characteristic data at the stage. In this embodiment, the server is loaded with a database management system, and the road characteristic data set is stored in a road characteristic database. The database may store road characteristic data in a plurality of smaller areas, respectively, or may store road characteristic data of one city or one country in its entirety.
Please refer to fig. 2, which is a schematic view of a scene of generating a road characteristic data set of the system according to an embodiment of the present application. As can be seen from fig. 2, the road characteristics described in the embodiment of the present application may be connected to the cloud server through one or more vehicles connected to the system and equipped to the interconnected vehicles, and the road characteristics data generated by the millimeter wave radar acquisition is uploaded to the cloud server after being processed, so as to generate a road characteristics data set, and the road characteristics data set is provided for the autonomous vehicle. During specific implementation, the server can also calibrate the road map generated according to the road characteristic data set and a positioning reference map layer of a map provider synchronously so as to improve the accuracy of the road characteristic data set.
Please refer to fig. 3, which is a schematic diagram illustrating an apparatus interaction of the system according to an embodiment of the present disclosure. As can be seen from fig. 3, a first mobile device (e.g. a first vehicle) may collect road characteristic data of a target road by performing the following steps:
step 1.1, collecting road environment data of a first current frame in a driving road through a first space scanning device.
In the system provided by the embodiment of the application, in the process of driving the first vehicle, the position information and the like of the object in the environment space of the driving road of the vehicle can be acquired through the space scanning device installed on the vehicle, so as to obtain the data set of the object, and the data set is called as road environment data in the embodiment. With the road environment data, the scanned object can be recorded in the form of object points, each point represents an object and contains coordinate information, reflection Intensity information (Intensity), and the like. By virtue of the road environment data, the target space can be expressed under the same spatial reference system.
The space scanning device can be an electromagnetic wave sensor such as a millimeter wave radar, a microwave radar, a centimeter wave radar and the like, can detect and measure electromagnetic waves in an electromagnetic wave scanning mode to obtain object information in the surrounding environment, such as information of static objects such as traffic signal lamps, iron railings, stone piers, iron columns, road teeth, wall surfaces and the like, and information of moving objects such as people, vehicles and the like, and measured data is represented by data of a certain number of objects (such as 100 objects).
In this embodiment, the space scanning device mounted on the vehicle is a millimeter wave radar, and the millimeter wave radar scans the road environment at a certain Frame Rate (Frame Rate) and collects road environment data, for example, collects 10 frames of electromagnetic wave reflection data per second.
In specific implementation, the number of the data collected by the millimeter wave radar is tens to hundreds of objects (target number) through a parameter setting mode, but because the data collected by the millimeter wave radar is generally transmitted to the processor through a canbus line with lower cost, the transmission pressure is increased by a large data volume, and experiments prove that the data volume of 100-120 is relatively suitable. After setting the parameters, the number of target points observed per frame does not exceed the set target number, but may be less than the set target number. In the present embodiment, the millimeter wave radar can return data of at most 100 targets (objects) per frame, and the data of each target is composed as follows:
1) echo intensity (power) in decibels. The echo intensities of objects made of different materials are greatly different, and the echo intensity of a metal object is generally higher; the echo intensities of different types of objects (cars, railings, motorcycles, etc.) at different distances may also vary, and if the echo intensity is too low, the signal may be considered as noise. This embodiment filters points with low reflectivity using the intensity data, so that road features corresponding to stationary objects with high reflectivity can be selected.
2) Whether the detected obstacle is a bridge (track _ bridge _ objectType). The signal obtained from the electromagnetic wave reflection data can be used for judging whether the detected barrier is a bridge or not when the urban road meets the scene of the overpass.
3) Whether the obstacle is at the near flag (track _ meeting). The flag is mostly used in an AEB (automatic emergency braking) for active safety.
4) Identification of the obstacle (track _ id). Each obstacle has a fixed ID, for example, the ID range is 0-100. The IDs of the same object in the cross-frame tracking list are the same.
5) Tracking state of the obstacle (track _ status). The present embodiment can realize object tracking processing using the identification and tracking state of the obstacle.
6) The angle (track-theta) between the obstacle and the millimeter-wave radar. Each radar has an extreme detection range and the included angle may range between-45 ° and 45 °.
7) The distance (track _ distance) of the obstacle from the millimeter wave radar. The distance is a distance in a polar coordinate system, and coordinates in a Cartesian (XYZ) coordinate system of the vehicle can be calculated according to the distance and the included angle. In the embodiment, the spatial pose of the object can be obtained by using the included angle and the distance data.
8) The radial relative velocity (track _ relative _ radial _ velocity) of the obstacle and the host vehicle.
9) The radial relative acceleration (track _ relative _ radial _ acceleration) of the obstacle and the host vehicle. This value is obtained by differentiating the radial relative velocity.
10) The motion state of the obstacle (track _ mode _ type). From this value it can be determined whether the object is stationary or moving. The present embodiment can determine whether the obstacle is a dynamic object by using the radial relative velocity, the radial relative acceleration, and the motion state.
11) Width of the obstacle (track width). After the original radar data points are clustered, an area is obtained, and the range of the area is regarded as the width of the object. However, this width (length) is not accurate, and for example, if the boundary of the target is non-metallic, the width of the millimeter wave radar detection is lost much.
It should be noted that, as can be seen from the above attributes 8 and 9, in the raw data of the millimeter wave radar, each point is marked with a speed, which is a speed in the sensor coordinate system, and needs to be transferred to the geodetic coordinate system by a speed compensation technique, that is, it is determined whether the point is moving relative to the ground. However, this speed is very inaccurate because it can only indicate points of longitudinal speed, which are not detected for points of transverse speed. Meanwhile, when the first vehicle is stopped, the radial velocity of a point only represents the current velocity of the point, and the overall motion state of the point cannot be correctly judged. Therefore, the attribute 10 "object motion state" is not accurate, and if it is not enough to determine whether the object is a dynamic object according to the attribute 10, the system provided by the embodiment of the application can solve the problem well, so that the recall rate of the road characteristics can be improved, and the recall rate of the road characteristics can also be improved.
After the road environment data of the first current frame is collected through the millimeter wave radar, the road characteristic data of the current frame can be determined according to the road environment data and the road characteristic category data of the historical frame.
And step 1.2, determining a first road characteristic determination reference factor of the object of the first current frame according to the road environment data of the first current frame and the road environment data of the first historical frame.
The road characteristic determination reference factor is data that affects determination of the road characteristic, and is multi-frame linkage data related to road environment data of the history frames.
The road environment data of the first current frame may include electromagnetic wave reflection data of various objects in the road environment space, where the objects may be traffic signal lamps, iron railings, stone piers, iron columns, trees, buildings, pedestrians and other vehicles on the road, and the like.
The first historical frame may include a plurality of historical frames, such as up to 50 frames, and so on. In the road environment data of each first history frame, not only electromagnetic wave reflection information of various objects but also labeling information on whether or not the various objects are road features may be included.
Determining a first road characteristic determination reference factor of the object of the first current frame relative to the road environment data of the first historical frame in a multi-frame linkage mode according to the road environment data of the first current frame and the road environment data of the first historical frame.
The road characteristic determination reference factor includes data related to road characteristic determination, which is affected by the road environment data of the historical frame and the current frame, and this kind of data is related to multi-frame road environment data, so this embodiment is referred to as multi-frame linkage data. The road characteristic determination reference factors include but are not limited to: and accumulating the occurrence times of the current frame object in the current frame and the historical frame, and taking the position distance of the current frame object in the current frame and the historical frame as a first position distance.
In this embodiment, first, the millimeter wave radar associates the first current frame with the target in each first history frame, for example, tracking an obstacle according to the obstacle identifier in each history frame data, so as to determine the association relationship between the first current frame and the target in the first history frame. For example, the identifiers of 100 targets in the 1 st historical frame are 1-100, the identifiers of 100 targets in the 2 nd historical frame are 2-101, and the targets 2-100 in the two frames can be respectively associated through the target identifiers.
After the association relationship between the frame data objects is determined, the number of times that the first current frame object appears in the first current frame and the first historical frame in an accumulated mode can be counted, and the first position distance of the first current frame object in the first current frame and the first historical frame can be calculated. For example, there are 50 road environment data of the first historical frames, the first current frame is the 51 th frame, after the first current frame data is collected, according to the association relationship of the target of the first current frame among the frames, the target 2 is counted to appear 10 times in the 51 frames, the target 35 appears 5 times, and so on.
In a specific implementation, the first position distance of the target in the first current frame and the first history frame may be determined in various ways, for example, the position difference of the target in the 1 st first history frame and the first current frame is used as the first position distance, or the mean deviation of the distances of all adjacent frames is used as the first position distance of the target in the first current frame and the first history frame. The mean square error of the distance is adopted to represent the average distance of the point, so that even if a point with a larger distance suddenly appears, the mean square error is smaller because the distance from the point to other points is smaller, the distance data is more accurate, and the point can be accurately determined to be a stable point; therefore, the accuracy of the road characteristics can be effectively improved.
For example, assuming that the position of the target 2 in the 1 st first history frame is (10, 10), the position in the 2 nd first history frame is (50, 50), …, and the position in the first current frame is (100 ), the distance mean square error can be calculated as the position distance of the target 2 in the 51 frames by calculating the position difference of the target 2 in the adjacent frames and calculating the distance mean square error from the position differences of all the adjacent frames.
In this embodiment, before step 1.2 is performed, some points with poor object properties (properties 1-11 above) (such as noise) and points with high speed (objects with significant motion) may be filtered by using a property filtering and speed compensation method, and then steps 1.2 and 1.3 are performed, and further feature point filtering is performed on the remaining points by using a key point classification method, so that dynamic points with relatively low speed (objects with small motion) may be removed, and only points with static objects (i.e. stable points) may be remained, thereby ensuring that the extracted feature points (stable points) are both static points and points with relatively good properties. By adopting the processing mode, the data quality of the road characteristics can be effectively improved, and the positioning accuracy can be further effectively improved.
And 1.3, determining a reference factor according to the first road characteristic, and determining any type of road characteristic data of the first current frame from the first current frame object.
In the step, any type of road characteristic data of the first current frame is screened from the objects of the first current frame according to the multi-frame linkage data of each object in the first current frame. The arbitrary type of road characteristic data includes a known type of road characteristic and an unknown type of road characteristic. The unknown road characteristic types can comprise stone piers, stones, soil piles, iron columns, sewer iron plates, well covers, iron wire fences of trees, pavement nails, metal on the surface of buildings and the like; this processing is such that the extracted road feature data is not limited by known road feature types, but may include road feature data of any road feature type that never occurs. Various specific embodiments of this step can be adopted, and the embodiments adopted in this embodiment will be described below.
Referring to fig. 4, a flowchart of extracting road features according to the present embodiment is shown. As shown in fig. 4, in the present embodiment, the reference factors include: accumulating the occurrence times of the object of the first current frame in the first current frame and the first historical frame, and the first position distance of the target of the first current frame in the first current frame and the first historical frame; step 1.3 can be implemented as follows: and taking the position data of the object with the occurrence frequency larger than the occurrence frequency threshold and the first position distance smaller than the first distance threshold as the road characteristic data of the first current frame.
The system provided by the embodiment of the application determines which targets are road characteristics from the current frame targets through linkage of the current frame and a plurality of effective continuous historical frames. Specifically, the position data of the target whose occurrence number is greater than the occurrence number threshold and whose first position distance is less than a first distance threshold may be used as the road characteristic data of the current frame. The screening mode conforms to the natural law, and points which appear more times in continuous frames and are closer in position at different moments are more likely to be static objects, so that the static objects can be used as road characteristics.
The threshold of the number of occurrences and the threshold of the distance may be determined according to positioning accuracy requirements and experience, for example, the threshold of the number of occurrences is set to 15, and the threshold of the distance is set to 0.1.
For example, if the target 5 occurs 20 times in the current frame and 50 history frames, which are greater than the occurrence threshold 15, and the position difference of the target 5 in the 51 frames is 0.08 and less than the distance threshold 0.1, the target 5 is taken as a stable point, that is, the target 5 is the road feature of the first current frame, and the feature value is the position data of the target 5 in the world coordinate system. Wherein, the distance between the 1 st historical frame and the 50 th historical frame is 0.1 × 50 ═ 5 meters.
Since the raw data is position data in sensor coordinates, it is necessary to convert the position data into position data in a world coordinate system. In specific implementation, the true pose of the mobile device may be determined first, for example, the positioning data obtained by fusing the RTK and IMU data is used as the true pose, and then the coordinate system is converted according to the pose and the parameters of the millimeter wave radar. In this embodiment, the coordinate system of the object (body) is first transferred according to the calibration parameters, and then the coordinate system of the world is transferred according to the IMU and the GNSS.
Experiments show that for one frame of millimeter wave radar sensing data, the quantity of the road features determined by the multi-frame linkage mode provided by the embodiment of the application is far greater than the quantity of the road features extracted by the prior art for extracting the road features based on the millimeter wave radar sensing data. For example, a frame of millimeter wave radar sensing data includes 100 targets, 50 road features can be extracted by the method provided by the embodiment of the application, and only about 10 road features are extracted by the prior art.
And step 1.4, sending a road characteristic data storage request aiming at the road characteristic data of the first current frame to a server.
After the first mobile device identifies the environmental characteristics around the road where the first mobile device is located at the current moment through the 3 steps, the road characteristic information can be transmitted to the cloud server through the vehicle-mounted communication module. Correspondingly, after receiving the data storage request, the server stores the road characteristic data of the first current frame into a road characteristic data set, and provides the road characteristic data set for the automatic driving vehicle.
In one example, the first mobile device is configured to collect road characteristics for a specified road segment, such as collecting road characteristics from location 1 (e.g., north gate clique) to location 2 (core campus) within a clique area having a large footprint (1 ten thousand acres). Table 1 shows the road characteristic data of the prescribed link stored in the database in the present embodiment.
| Characteristic point identification | Characteristic point position (longitude and latitude) |
| 1 | (10,10) |
| 2 | (10,10) |
| … | |
| 100000 | (10,10) |
TABLE 1 road characteristic data set
As can be seen from table 1, the road segment includes 10000 road feature points, and the position of each feature point may be the position of the feature in the world coordinate system, such as longitude and latitude, and the like.
In this embodiment, the positional distance between adjacent history frames is greater than a second distance threshold; the following steps can be further included after step 1.4:
step 1.5: and if the position distance between the current frame and the adjacent historical frame reaches a second distance threshold, taking the current frame as a newly-added historical frame. By adopting the processing mode, the adjacent historical frames are separated by a certain distance, and the situation that a plurality of frames of similar road environment data collected when the vehicle waits for a red light are taken as the historical frames is avoided; therefore, the quality of the historical frame can be effectively improved, and the positioning accuracy and robustness are improved.
The following steps can be further included after step 1.5:
step 1.6: and if the number of the historical frames is greater than the threshold value of the historical frame data, removing the historical frames meeting the historical frame removing condition. By adopting the processing mode, the number of the historical frames is controlled; therefore, the storage resource and the calculation resource can be effectively saved, and the accuracy of the road characteristics can be ensured.
The following steps can be further included after step 1.5:
step 1.7: and marking the road characteristic types of all objects in the newly added historical frame according to the multi-frame linkage data of the newly added historical frame.
Step 1.7 may take at least one of the following forms:
the method comprises the following steps of 1, marking an object corresponding to road characteristic data in a newly-added historical frame as a characteristic point;
and 3, marking the object with the appearance times of the newly added historical frames smaller than the appearance time threshold and the first position distance larger than the first distance threshold as a wandering point.
The liveness point and the walking point are undetermined characteristics and can be used as a reference for the next calculation in the following process so as to accelerate the calculation. For example, if the wandering point is likely to become a stable point from the viewpoint of the average distance, for example, a distance threshold is set, and if the distance threshold is larger than the distance threshold, the wandering point is unlikely to become a stable point any more, and is directly discarded and is not put into the calculation of the stable point judgment. The liveliness point can be a stable point from the viewpoint of the tracking times, and if the tracking times do not reach the set time threshold value, the liveliness point can not appear any more, so that the wandering point can be discarded.
In this embodiment, the target 2 appears 10 times in 50 history frames and the current frame, and is smaller than the appearance time threshold 15, and because the appearance times are small, the target 2 is used as an active point; the target 25 appears 20 times in the current frame and 50 history frames, which are greater than the appearance time threshold 15, and the position difference of the target 25 in the 50 history frames and the current frame is 1.5, which is greater than the distance threshold 0.1, so that although the appearance time of the point is large, the distance between the points is too large, and the target 2 is taken as a wandering point.
If the road characteristic type of a certain next frame object in the historical frame is a characteristic point, the next frame object can be directly used as the road characteristic data of the next frame; the processing mode can effectively reduce the calculated amount of multi-frame linkage data of the next frame of object; therefore, the calculation resources can be effectively saved, and the road characteristic extraction speed is improved.
Table 2 shows road environment data of the history frame in the present embodiment.
TABLE 2 road Environment data of historical frame
The road characteristic data (the position of the road characteristic) determined through the above steps is the position of the target object included in the sensing data (the road environment data of the first current frame) of the millimeter wave radar, for example, the sensing data includes the position information of 100 objects, and the road characteristic data is the position information of 50 objects screened out therefrom. However, it is not sufficient to perform the device positioning based on these road characteristics, because the data collected by the millimeter wave radar is not stable, the position of a stable point (real road characteristic) in different frames fluctuates, and a space coordinate cannot be used to represent a stable point, thereby resulting in incomplete extracted road characteristics. In order to solve the problem, the embodiment adopts a feature data enhancement mode to determine more comprehensive road features so as to improve the quality of the road features and improve the positioning accuracy of the equipment.
In this embodiment, the first mobile device may further perform the processing step of feature data enhancement between steps 1.3-1.4, that is: and determining second road characteristic data of the current frame according to the first road characteristic data of the first current frame determined in the step 1.3 by a road characteristic enhancement algorithm.
The first road characteristic data is road characteristic data which is determined directly from the first current frame object according to the reference factor determined by the first road characteristic.
The second road characteristic data is road characteristic data determined based on the first road characteristic data. The second road characteristic data includes the position of an object which is close to the first road characteristic data but may not belong to the first current frame. That is, the second road feature data includes feature points in an expanded region that is close to the current frame feature (first road feature data).
As shown in fig. 5, in the present embodiment, a road characteristic enhancement algorithm based on a two-dimensional gaussian noise model in a polar coordinate system is adopted, and data that is centered on the first road characteristic data and follows gaussian distribution is used as second road characteristic data, thereby implementing characteristic data enhancement. The data of the reflection point of the millimeter wave radar mainly has two noise sources: angle noise + distance noise. The two noises can be described by a two-dimensional gaussian model, and the following formula can be specifically adopted:
x＝d*cosθ,y＝d*sinθ (3)
as can be seen from expressions 1 and 2, the angular noise is centered on the current point (first road feature data), and the angular accuracy is 2∑Gaussian noise of (2); the distance noise is centered at the current point and has a distance accuracy of 2∑Gaussian noise of (2); equation 3 is second road characteristic data (x, y) that converts the second road characteristic data (d, θ) expressed in polar coordinates into two-dimensional cartesian coordinates.
Table 3 shows the first road characteristic data and the second road characteristic data in one frame of millimeter wave radar perception data of the present embodiment.
TABLE 3 first road characteristic data and second road characteristic data
The second road characteristic data in table 3 may also be represented in the form of a noise model, i.e., by the above formula, or may be represented in a geometric description manner by the second road characteristic data centered on the first road characteristic data.
It should be noted that the timestamp of the millimeter wave radar sensing data adopted in this embodiment is a system timestamp printed by the host system, and is not the actual data acquisition time of the GPS accurate time service, which may result in inaccurate timestamp printed by the system for a frame of data if there is a delay in data transmission during the process of transmitting the frame of data to the system (through the network cable or the combox) by the millimeter wave radar. When the equipment is positioned, if the problem of inaccurate time of road environment data is not solved, an incorrect true value pose is obtained from incorrect time, the coordinate system is converted according to the incorrect true value pose, an incorrect position of the current frame object is obtained, the incorrect position can result in obtaining an incorrect position distance, and whether the current frame object is a road characteristic or not is judged according to the incorrect position distance, so that the incorrect road characteristic is extracted.
As shown in fig. 6, in this embodiment, the first mobile device may further perform a processing step of correcting the perceptual data timestamp, that is: the time stamp of the current frame data is determined by a time compensation algorithm. The time compensation algorithm of the present embodiment includes the following steps: 1) determining time delay data according to the position difference of the same object in the current frame and the historical frame and the moving speed of the mobile equipment, namely performing dynamic estimation on time delay; 2) and calibrating the data acquisition time of the current frame according to the delay data, namely correcting the sensing data time.
The time-delay dynamic estimation is described below with reference to fig. 7. In a short time, the vehicle can be considered to be in a straight line motion, and the position variation of two points tracked (tracking) by front and rear frames due to the fluctuation of the time delay is in direct proportion to the current vehicle speed. In this embodiment, all the stable points of the current frame and the stable points corresponding to the previous historical frame are used, and the following formula is used to calculate the variation dt of the current time delay:
wherein j-1 indicates that the ds direction does not coincide with the vehicle forward direction, j-2 indicates that the ds direction coincides with the vehicle forward direction, and e indicates gaussian noise; n represents the total number of frames of the current frame and the historical frame. The "time delay" of the current frame is equal to the "time delay" of the previous historical frame + dt, so that a dynamic estimation value is obtained. For example, if the previous history frame delay is 0.01ms, the dynamic delay dt of the current frame is 0.005ms, and the delay of the current frame is 0.01+0.005 ms.
In one example, the dynamic delay estimation is optimized as a least square problem for multiple frames (e.g. all historical frames) as a whole, and the optimized amount is the dynamic delay compensation amount for consecutive k frames, and the formula is as follows:
wherein M represents the frame number of the historical frames, N represents the corresponding characteristic points tracked in the historical frames, and pj(dti) Represents the pose, p, of the ith feature point of the jth framek(dti) And representing the pose of the ith characteristic point of the kth frame. Since the formula is to put the time delays of all historical frames together for estimation, the result of one calculation may include the time delay supplement amount of multi-frame data.
Referring to fig. 8, a flowchart of the first mobile device side generating the road characteristic data set in the present embodiment is shown. In this embodiment, a positioning result of two sensors, namely an RTK sensor and an imu sensor, is used as a real-time positioning true value, a continuous positioning true value sequence buffer on a time sequence is maintained, a new frame of data (road environment data of a first current frame) transmitted by a millimeter wave radar is used, the data is transferred to the same coordinate system (a geodetic coordinate system) by using the bit data in the buffer and the calibration relative pose relationship of the sensors, then road characteristic identification, dynamic delay estimation and road characteristic enhancement are performed by combining effective continuous historical frames, effective road characteristic data are extracted, the road characteristic data are updated to a database, and the current frame is added into the effective continuous historical frame. Wherein, the definition of the effective continuous history frame is as follows: the current frame is spatially separated from the previous historical frame by more than a threshold.
The processing procedure of stage 1 is explained so far.
2. A mobile device positioning stage.
The second mobile device is a device with device location requirements including, but not limited to: unmanned vehicles, mobile robots, and the like are mobile devices. The automatic driving vehicle can obtain road characteristic information through a vehicle-mounted environment perception sensor (such as a millimeter wave radar), and can compare the road characteristic information with a road characteristic data set in a road characteristic database in real time, so that the position of the automatic driving vehicle in the current lane can be accurately known, and centimeter-level positioning is realized.
As shown in fig. 3, the second mobile device, at this stage, performs the positioning of the device by performing the following steps:
and 2.1, collecting road environment data of a second current frame in the driving road through a second space scanning device.
According to the system provided by the embodiment of the application, in the driving process of a second vehicle (called a self vehicle for short), the road environment data in the driving process of the vehicle can be obtained through the space scanning device arranged on the vehicle. In the present embodiment, the space scanning device mounted on the vehicle is a millimeter wave radar.
This step is similar to the implementation of step 1.1 in the road feature data set generation phase, and is not described here again.
And 2.2, determining a second road characteristic determination reference factor of the object of the second current frame according to the road environment data of the second current frame and the road environment data of the second historical frame.
The second road characteristic determination reference factor is multi-frame linkage data relating to road environment data of a second history frame.
This step is similar to the implementation of step 1.2 in the road feature data set generation phase, and is not described here again.
And 2.3, determining a reference factor according to the second road characteristic, and determining any type of road characteristic data of the second current frame from the second current frame object.
This step is similar to the implementation of step 1.3 in the road feature data set generation phase, and is not described here again.
After determining the road characteristic data of the second current frame, the next step may be entered, and the pose data of the second mobile device is determined according to the road characteristic data and the road characteristic data set of the second current frame.
And 2.4, determining pose data of the second mobile equipment according to the road characteristic data of the second current frame and the road characteristic data set.
In this step, the road characteristic information (observation information) of the current frame may be compared with the road characteristic data set in the road characteristic database, and the pose data of the second mobile device at the position where the characteristic points are matched is obtained.
This step may employ general algorithms for map-based location estimation, such as particle filters, etc. In specific implementation, the specific method for matching the observation information with the feature point database may be as follows: and taking the previous pose corresponding to the previous frame of the second current frame as an initial pose, taking the increment of the motion of the imu sensor in the time period (the time difference between the second current frame and the previous frame) as a motion model, taking millimeter waves to extract feature points (road feature data) in real time as an observation model, and performing optimal estimation on the current pose by using a Bayesian filtering method.
In this embodiment, the road characteristic data of the second current frame and the road characteristic data of the historical frame are used as observation models, and a bayesian filtering method is used to perform optimal estimation on the current pose; by the processing mode, when the road characteristics of the current frame are less, the position of the equipment can still be determined; therefore, robustness can be effectively improved, and positioning accuracy can be improved. For example, the distance between the 1 st historical frame and the 50 th historical frame is 0.1 (distance threshold) 50 ═ 5 meters, and the positioning is performed according to the road characteristics in the range of 5 meters of the current frame position.
In one example, the road characteristic data set comprises characteristic data of roads in a certain city (such as Hangzhou city), and the data volume is large, so that the data volume is stored in the server; in this case, the second mobile device may further perform the steps of: 1) sending a mobile equipment positioning request aiming at road characteristic data of a current frame to a server, so that the server determines the pose data according to the road characteristic data of the current frame and the road characteristic data set; 2) and receiving the pose data returned by the server.
In another example, the road characteristic data set includes characteristic data of a road of a certain enterprise park (such as an arieba xi park), the data volume is small, and in order to save network traffic, the positioning speed is increased, so that the data set is stored on the second vehicle; in this case, the second mobile device determines pose data for the device based on the road characteristic data for the current frame and a set of road characteristic data stored locally at the mobile device.
Please refer to fig. 9, which is a flowchart illustrating a positioning process of a second mobile device side device. In this embodiment, a new frame of road environment data transmitted by the millimeter wave radar is subjected to position alignment (converted to a world coordinate system) with an effective continuous historical frame by imu, and road feature extraction operation (obtaining a first road feature), perceived data timestamp correction and road feature enhancement operation (obtaining a second road feature) are performed to refine effective road features, and the effective road features and the road features in the historical frame are packed together to form current observation information.
In specific implementation, the pose increment obtained by adding the accurate pose of the previous frame to the imu integral can obtain the predicted pose of the current frame, namely the prior probability of Bayesian filtering. When the last accurate level is updated, the optimized result obtained by the filter is directly used as the pose of the current frame.
In fig. 9, the operations of correcting the perceptual data timestamp and enhancing the road characteristics correspond to corresponding parts in the generation of the road characteristic data set at stage 1, and are not described again here.
As can be seen from the above embodiments, the device positioning system provided in the embodiment of the present application acquires road environment data of a first current frame in a driving road through a first space scanning apparatus of a first mobile device; determining a first road characteristic determination reference factor of a first current frame object according to the road environment data of the first current frame and the road environment data of the first historical frame; determining a reference factor according to the first road characteristic, and determining any type of road characteristic data of a first current frame from the first current frame object; sending a road characteristic data acquisition and storage request aiming at the road characteristic data of a first current frame to a server, so that the server stores the road characteristic data of the first current frame into a road characteristic data set; then, collecting road environment data of a second current frame in the driving road through a second space scanning device of second mobile equipment; determining a second road characteristic determination reference factor of a second current frame object according to the road environment data of the second current frame and the road environment data of a second historical frame; determining a reference factor according to the second road characteristic, and determining any type of road characteristic data of a second current frame from the second current frame object; determining pose data of a second mobile device according to the road characteristic data of the second current frame and the road characteristic data set; the processing mode extracts effective road characteristics with unlimited characteristic types from the road environment data of the current frame in a key point classification mode by combining the multi-frame accumulated road characteristic determination factors, enhances the road characteristic expression capacity, achieves the comprehensive and accurate extraction of road environment characteristic points, constructs a road characteristic diagram with high data quality, and carries out equipment positioning based on high-quality real-time road characteristics and a high-quality road characteristic data set; therefore, the positioning accuracy can be effectively improved. Meanwhile, the extracted road characteristics comprise any type of stable road characteristics, so that the problem that positioning cannot be performed when conventional road characteristics (such as structural characteristics and the like) cannot be effectively obtained is solved; therefore, the positioning robustness can be effectively improved. In addition, other sensors (such as cameras) are not needed to assist in determining road characteristics, and the problem of asynchronous time service during multi-sensor fusion is avoided; therefore, the equipment cost can be effectively reduced, and the positioning accuracy is improved.
Second embodiment
In the foregoing embodiment, a mobile device positioning system is provided, and correspondingly, the present application further provides a road characteristic data generating method. The method corresponds to the embodiment of the method described above.
Please refer to fig. 10, which is a flowchart of an embodiment of a road characteristic data generating method according to the present application, an executing body of the method includes a road characteristic data generating apparatus, which may be deployed on a first mobile device. Since the embodiment of the method is basically similar to the first embodiment of the system, the description is simple, and relevant points can be referred to the partial description of the first embodiment of the system. The method embodiments described below are merely illustrative.
A method for generating road characteristic data according to this embodiment includes:
step S1001: collecting road environment data of a current frame in a driving road through a space scanning device;
step S1003: determining a road characteristic determination reference factor of the object of the current frame according to the road environment data of the current frame and the road environment data of the historical frame, wherein the road characteristic determination reference factor is multi-frame linkage data related to the road environment data of the historical frame;
step S1005: determining a reference factor according to the road characteristics, and determining any type of road characteristic data of the current frame from the current frame object;
step S1007: and sending a road characteristic data acquisition and storage request aiming at the road characteristic data of the current frame to a server.
As can be seen from the above embodiments, in the road characteristic data generation method provided in the embodiments of the present application, the spatial scanning device is used to collect road environment data of a current frame in a driving road; determining a road characteristic determination reference factor of the object of the current frame according to the road environment data of the current frame and the road environment data of the historical frame, wherein the road characteristic determination reference factor is multi-frame linkage data related to the road environment data of the historical frame; determining a reference factor according to the road characteristics, and determining any type of road characteristic data of the current frame from the current frame object; sending a road characteristic data acquisition and storage request aiming at the road characteristic data of the current frame to a server; the processing mode extracts effective road characteristics with unlimited characteristic types from the road environment data of the current frame in a key point classification mode by combining the multi-frame accumulated road characteristic determination factors, enhances the road characteristic expression capacity, achieves the comprehensive and accurate extraction of road environment characteristic points, constructs a road characteristic diagram with high data quality, and carries out equipment positioning based on high-quality real-time road characteristics and a high-quality road characteristic data set; therefore, the positioning accuracy can be effectively improved. Meanwhile, the extracted road characteristics comprise any type of stable road characteristics, so that the problem that positioning cannot be performed when conventional road characteristics (such as structural characteristics and the like) cannot be effectively obtained is solved; therefore, the positioning robustness can be effectively improved. In addition, other sensors (such as cameras) are not needed to assist in determining road characteristics, and the problem of asynchronous time service during multi-sensor fusion is avoided; therefore, the equipment cost can be effectively reduced, and the positioning accuracy is improved.
Third embodiment
Please refer to fig. 11, which is a schematic diagram of an embodiment of a road characteristic data generating device according to the present application. Since the apparatus embodiments are substantially similar to the method embodiments, they are described in a relatively simple manner, and reference may be made to some of the descriptions of the method embodiments for relevant points. The device embodiments described below are merely illustrative.
A road characteristic data generation device of this embodiment includes:
a data collecting unit 1101 for collecting road environment data in a driving road by a space scanning device as road environment data of a current frame;
a reference factor determining unit 1103, configured to determine a road characteristic determination reference factor of an object in the current frame according to the road environment data of the current frame and the road environment data of a plurality of historical frames before the current frame, where the road characteristic determination reference factor is multi-frame linkage data related to the road environment data of the historical frames;
a road characteristic determining unit 1105, configured to determine a reference factor according to the road characteristic, and determine any type of road characteristic data of the current frame from the object of the current frame;
a request sending unit 1107, configured to send a road characteristic data acquisition and storage request for the road characteristic data of the current frame to the server.
Fourth embodiment
Please refer to fig. 12, which is a schematic diagram of an embodiment of an electronic device according to the present application. Since the apparatus embodiments are substantially similar to the method embodiments, they are described in a relatively simple manner, and reference may be made to some of the descriptions of the method embodiments for relevant points. The device embodiments described below are merely illustrative.
An electronic device of the present embodiment includes: a spatial scanning apparatus 1200, a processor 1201 and a memory 1202; the memory is used for storing a program for realizing the positioning method of the mobile equipment, and after the equipment is powered on and runs the program of the method through the processor, the following steps are executed: collecting road environment data in a driving road through a space scanning device to serve as the road environment data of a current frame; determining a road characteristic determination reference factor of an object of the current frame according to the road environment data of the current frame and the road environment data of a plurality of historical frames before the current frame, wherein the road characteristic determination reference factor is multi-frame linkage data related to the road environment data of the historical frames; determining a reference factor according to the road characteristics, and determining any type of road characteristic data of the current frame from the current frame object; and sending a road characteristic data acquisition and storage request aiming at the road characteristic data of the current frame to a server.
Fifth embodiment
In the foregoing embodiment, a mobile device positioning system is provided, and correspondingly, the present application also provides a mobile device positioning method. The method corresponds to the embodiment of the method described above.
Please refer to fig. 13, which is a flowchart illustrating a mobile device positioning method according to an embodiment of the present application. Since the method embodiment is basically similar to the method embodiment one, the description is simple, and the relevant points can be referred to the partial description of the method embodiment one. The method embodiments described below are merely illustrative.
A method for positioning a mobile device in this embodiment includes:
step S1301: receiving a road characteristic data acquisition and storage request aiming at the road characteristic data of a first current frame, which is sent by a first mobile device;
step S1303: and storing the road characteristic data of the first current frame into a road characteristic data set.
The road characteristic data set may be stored in a road characteristic database.
In one example, the method may further comprise the steps of: 1) receiving a mobile equipment positioning request aiming at the road characteristic data of the second current frame, which is sent by the second mobile equipment; 2) determining pose data of the second mobile equipment according to the road characteristic data of the second current frame and the road characteristic data set; 3) returning the pose data to the second mobile device.
As can be seen from the foregoing embodiments, in the mobile device positioning method provided in the embodiment of the present application, a road characteristic data acquisition and storage request for road characteristic data of a first current frame, which is sent by a first mobile device, is received; storing the road characteristic data of the first current frame into a road characteristic data set; the processing mode extracts effective road characteristics with unlimited characteristic types from the road environment data of the current frame in a key point classification mode by combining the multi-frame accumulated road characteristic determination factors, enhances the road characteristic expression capacity, achieves the comprehensive and accurate extraction of road environment characteristic points, constructs a road characteristic diagram with high data quality, and carries out equipment positioning based on high-quality real-time road characteristics and a high-quality road characteristic data set; therefore, the positioning accuracy can be effectively improved. Meanwhile, the extracted road characteristics comprise any type of stable road characteristics, so that the problem that positioning cannot be performed when conventional road characteristics (such as structural characteristics and the like) cannot be effectively obtained is solved; therefore, the positioning robustness can be effectively improved. In addition, other sensors (such as cameras) are not needed to assist in determining road characteristics, and the problem of asynchronous time service during multi-sensor fusion is avoided; therefore, the equipment cost can be effectively reduced, and the positioning accuracy is improved.
Sixth embodiment
Please refer to fig. 14, which is a diagram illustrating an embodiment of a mobile device positioning apparatus according to the present application. Since the apparatus embodiments are substantially similar to the method embodiments, they are described in a relatively simple manner, and reference may be made to some of the descriptions of the method embodiments for relevant points. The device embodiments described below are merely illustrative.
A mobile device positioning apparatus of this embodiment includes:
a request receiving unit 1401, configured to receive a road characteristic data acquisition and storage request for road characteristic data of a first current frame, where the request is sent by a first mobile device;
a data storage unit 1403, configured to store the road characteristic data of the first current frame into a road characteristic data set.
Seventh embodiment
Please refer to fig. 15, which is a schematic diagram of an embodiment of an electronic device according to the present application. Since the apparatus embodiments are substantially similar to the method embodiments, they are described in a relatively simple manner, and reference may be made to some of the descriptions of the method embodiments for relevant points. The device embodiments described below are merely illustrative.
An electronic device of the present embodiment includes: a processor 1501 and memory 1502; the memory is used for storing a program for realizing the positioning method of the mobile equipment, and after the equipment is powered on and runs the program of the method through the processor, the following steps are executed: receiving a road characteristic data acquisition and storage request aiming at the road characteristic data of a first current frame, which is sent by a first mobile device; and storing the road characteristic data of the first current frame into a road characteristic data set.
Eighth embodiment
In the foregoing embodiment, a mobile device positioning system is provided, and correspondingly, the present application also provides a mobile device positioning method. The method corresponds to the embodiment of the method described above.
Please refer to fig. 16, which is a flowchart illustrating a mobile device positioning method according to an embodiment of the present application. Since the method embodiment is basically similar to the method embodiment one, the description is simple, and the relevant points can be referred to the partial description of the method embodiment one. The method embodiments described below are merely illustrative.
A method for positioning a mobile device in this embodiment includes:
step S1601: collecting road environment data of a current frame in a driving road through a space scanning device;
the space scanning device comprises an electromagnetic wave scanning device. The electromagnetic wave scanning device includes a millimeter wave radar.
Step S1603: determining a road characteristic determination reference factor of the object of the current frame according to the road environment data of the current frame and the road environment data of the historical frame, wherein the road characteristic determination reference factor is multi-frame linkage data related to the road environment data of the historical frame;
step S1605: determining a reference factor according to the road characteristics, and determining any type of road characteristic data of the current frame from the current frame object;
any type of road feature includes: stone pier, iron column and nail.
The road characteristic determination reference factor may include: accumulating the occurrence times of the object in the current frame and the historical frame, and the first position distance of the object in the current frame and the historical frame; accordingly, step S1603 may be implemented as follows: and taking the position data of the target with the occurrence frequency larger than the occurrence frequency threshold and the first position distance smaller than the first distance threshold as the first road characteristic data of the current frame.
In one example, step S1603 may further include the steps of: and determining second road characteristic data of the current frame according to the first road characteristic data through a road characteristic enhancement algorithm.
In one example, the first location distance is determined using the following steps: 1) converting the road environment data of the current frame and the road environment data of the historical frame into road environment data under the same coordinate system; 2) taking the mean distance variance as the first location distance.
The road characteristic enhancement algorithm can adopt the following modes: and taking the first road characteristic data as the center and data which is subjected to Gaussian distribution as second road characteristic data.
Step S1607: and determining pose data of the mobile equipment according to the road characteristic data and the road characteristic data set of the current frame.
In one example, step S1607 may include the steps of: 1) sending a mobile equipment positioning request aiming at road characteristic data of a current frame to a server, so that the server determines the pose data according to the road characteristic data of the current frame and the road characteristic data set; 2) and receiving the pose data returned by the server.
In another example, step S1607 may include the steps of: 1) and determining the pose data of the mobile equipment according to the road characteristic data of the current frame and a road characteristic data set stored in the local of the mobile equipment.
In yet another example, step S1607 may include the steps of: 1) acquiring pose data of a previous frame of the current frame; acquiring the movement distance of the current frame relative to the previous frame; acquiring road characteristic data of the historical frame; 2) and determining the pose data of the mobile equipment by a Bayesian filtering algorithm according to the road feature data of the current frame, the road feature data of the historical frame, the pose data of the previous frame, the motion distance and the road feature data set. In this embodiment, the pose obtained by adding the motion distance to the pose of the previous frame is used as the predicted pose of the current frame, that is, the prior probability of the bayesian filter, and then the pose data of the mobile device is determined by the bayesian filter algorithm based on the probability.
In specific implementation, the method can further comprise the following steps: and updating the pose data of the previous frame according to the determined pose data.
In particular implementations, the initial pose data for the mobile device includes pose data determined from a satellite positioning system.
In one example, the method may further comprise the steps of: 1) determining time delay data of the current frame according to the position difference of the same object in the current frame and the adjacent historical frame and the moving speed of the mobile equipment; 2) and determining the data acquisition time of the current frame according to the delay data. And relative to the data acquisition time given by the system, determining the time according to the delay data to be the calibrated data acquisition time of the current frame.
In one example, the positional distance between adjacent historical frames is greater than a second distance threshold; the method may further comprise the steps of: and if the position distance between the current frame and the adjacent historical frame reaches a second distance threshold, taking the current frame as a newly-added historical frame.
In specific implementation, the method can further comprise the following steps: and if the number of the historical frames is greater than the threshold value of the historical frame data, removing the historical frames meeting the historical frame removing condition.
In specific implementation, the method can further comprise the following steps: and determining a reference factor according to the road characteristics of the newly added historical frame, and marking the road characteristic type of each object in the newly added historical frame.
In specific implementation, the method can further comprise the following steps: determining a reference factor according to the road characteristics of the newly added historical frame, marking the road characteristic type of each object in the newly added historical frame, and adopting at least one of the following modes: 1) marking objects corresponding to the road characteristic data in the newly-added historical frame as characteristic points; 2) marking the objects of which the occurrence times of the newly-added historical frames are less than the threshold value of the occurrence times as lively points; marking the objects with the appearance times of the newly-added historical frames smaller than an appearance time threshold value and the first position distance larger than a first distance threshold value as wandering points; 3) and if the road characteristic type of the current frame object in the historical frame is the characteristic point, taking the current frame object as the road characteristic data of the current frame.
According to the embodiment, the mobile equipment positioning method provided by the embodiment of the application acquires the road environment data of the current frame in the driving road through the space scanning device; determining a road characteristic determination reference factor of the object of the current frame according to the road environment data of the current frame and the road environment data of the historical frame, wherein the road characteristic determination reference factor is multi-frame linkage data related to the road environment data of the historical frame; determining a reference factor according to the road characteristics, and determining any type of road characteristic data of the current frame from the current frame object; determining pose data of the mobile equipment according to the road characteristic data and the road characteristic data set of the current frame; the processing mode extracts effective road characteristics with unlimited characteristic types from the road environment data of the current frame in a key point classification mode by combining the multi-frame accumulated road characteristic determination factors, enhances the road characteristic expression capacity, achieves the comprehensive and accurate extraction of road environment characteristic points, constructs a road characteristic diagram with high data quality, and carries out equipment positioning based on high-quality real-time road characteristics and a high-quality road characteristic data set; therefore, the positioning accuracy can be effectively improved. Meanwhile, the extracted road characteristics comprise any type of stable road characteristics, so that the problem that positioning cannot be performed when conventional road characteristics (such as structural characteristics and the like) cannot be effectively obtained is solved; therefore, the positioning robustness can be effectively improved. In addition, other sensors (such as cameras) are not needed to assist in determining road characteristics, and the problem of asynchronous time service during multi-sensor fusion is avoided; therefore, the equipment cost can be effectively reduced, and the positioning accuracy is improved.
Ninth embodiment
Please refer to fig. 17, which is a diagram illustrating an embodiment of a mobile device positioning apparatus according to the present application. Since the apparatus embodiments are substantially similar to the method embodiments, they are described in a relatively simple manner, and reference may be made to some of the descriptions of the method embodiments for relevant points. The device embodiments described below are merely illustrative.
A mobile device positioning apparatus of this embodiment includes:
a data acquisition unit 1701 for acquiring road environment data in a driving road as road environment data of a current frame by a space scanning device;
a reference factor determining unit 1703, configured to determine a road characteristic determination reference factor of an object in the current frame according to the road environment data of the current frame and the road environment data of a plurality of historical frames before the current frame, where the road characteristic determination reference factor is multi-frame linkage data related to the road environment data of the historical frames;
a road characteristic determining unit 1705, configured to determine a reference factor according to the road characteristic, and determine any type of road characteristic data of the current frame from the object of the current frame;
a pose data determining unit 1707, configured to determine pose data of the mobile device according to the road feature data and the road feature data set of the current frame.
Tenth embodiment
Please refer to fig. 18, which is a diagram illustrating an embodiment of an electronic device according to the present application. Since the apparatus embodiments are substantially similar to the method embodiments, they are described in a relatively simple manner, and reference may be made to some of the descriptions of the method embodiments for relevant points. The device embodiments described below are merely illustrative.
An electronic device of the present embodiment includes: a spatial scanning device 1801, a processor 1801 and a memory 1802; the memory is used for storing a program for realizing the positioning method of the mobile equipment, and after the equipment is powered on and runs the program of the method through the processor, the following steps are executed: collecting road environment data in a driving road through a space scanning device to serve as the road environment data of a current frame; determining a road characteristic determination reference factor of an object of the current frame according to the road environment data of the current frame and the road environment data of a plurality of historical frames before the current frame, wherein the road characteristic determination reference factor is multi-frame linkage data related to the road environment data of the historical frames; determining a reference factor according to the road characteristics, and determining any type of road characteristic data of the current frame from the current frame object; and determining pose data of the mobile equipment according to the road characteristic data and the road characteristic data set of the current frame.
Although the present application has been described with reference to the preferred embodiments, it is not intended to limit the present application, and those skilled in the art can make variations and modifications without departing from the spirit and scope of the present application, therefore, the scope of the present application should be determined by the claims that follow.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.
1. Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include non-transitory computer readable media (transient media), such as modulated data signals and carrier waves.
2. As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application 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.
Claims (29)
1. A mobile device positioning method, comprising:
the first mobile equipment is used for acquiring road environment data of a first current frame in a driving road through the first space scanning device; determining a first road characteristic determination reference factor of the object of the first current frame according to the road environment data of the first current frame and the road environment data of the first historical frame, wherein the first road characteristic determination reference factor is multi-frame linkage data related to the road environment data of the first historical frame; determining a reference factor according to the first road characteristic, and determining any type of road characteristic data of a first current frame from the first current frame object; sending a road characteristic data acquisition and storage request aiming at the road characteristic data of the first current frame to a server;
the server is used for receiving the data acquisition and storage request and storing the road characteristic data of the first current frame into a road characteristic data set;
the second mobile equipment is used for acquiring road environment data of a second current frame in the driving road through a second space scanning device; determining a second road characteristic determination reference factor of the object of the second current frame according to the road environment data of the second current frame and the road environment data of the second historical frame, wherein the second road characteristic determination reference factor is multi-frame linkage data related to the road environment data of the second historical frame; determining a reference factor according to the second road characteristic, and determining any type of road characteristic data of a second current frame from the second current frame object; and determining pose data of the second mobile equipment according to the road characteristic data of the second current frame and the road characteristic data set.
2. A road characteristic data generation method, comprising:
collecting road environment data in a driving road through a space scanning device to serve as the road environment data of a current frame;
determining a road characteristic determination reference factor of an object of the current frame according to the road environment data of the current frame and the road environment data of a plurality of historical frames before the current frame, wherein the road characteristic determination reference factor is multi-frame linkage data related to the road environment data of the historical frames;
determining a reference factor according to the road characteristics, and determining any type of road characteristic data of the current frame from the current frame object;
and sending a road characteristic data acquisition and storage request aiming at the road characteristic data of the current frame to a server.
3. A mobile device positioning method, comprising:
receiving a road characteristic data acquisition and storage request aiming at the road characteristic data of a first current frame, which is sent by a first mobile device;
and storing the road characteristic data of the first current frame into a road characteristic data set.
4. The method of claim 3, wherein the road characteristic data set is stored in a road characteristic database.
5. The method of claim 3, further comprising:
receiving a mobile equipment positioning request aiming at the road characteristic data of the second current frame, which is sent by the second mobile equipment;
determining pose data of the second mobile equipment according to the road characteristic data of the second current frame and the road characteristic data set;
returning the pose data to the second mobile device.
6. A mobile device positioning method, comprising:
collecting road environment data in a driving road through a space scanning device to serve as the road environment data of a current frame;
determining a road characteristic determination reference factor of an object of the current frame according to the road environment data of the current frame and the road environment data of a plurality of historical frames before the current frame, wherein the road characteristic determination reference factor is multi-frame linkage data related to the road environment data of the historical frames;
determining a reference factor according to the road characteristics, and determining any type of road characteristic data of the current frame from the current frame object;
and determining pose data of the mobile equipment according to the road characteristic data and the road characteristic data set of the current frame.
7. The method of claim 6, wherein determining pose data of the mobile device from the road feature data and the road feature data set of the current frame comprises:
sending a mobile equipment positioning request aiming at road characteristic data of a current frame to a server, so that the server determines the pose data according to the road characteristic data of the current frame and the road characteristic data set;
and receiving the pose data returned by the server.
8. The method of claim 6, wherein determining pose data of the mobile device from the road feature data and the road feature data set of the current frame comprises:
and determining the pose data of the mobile equipment according to the road characteristic data of the current frame and a road characteristic data set stored in the local of the mobile equipment.
9. The method of claim 6,
any type of road feature includes: stone pier, iron column and nail.
10. The method of claim 6,
the space scanning device comprises an electromagnetic wave scanning device.
11. The method of claim 10, wherein the electromagnetic wave scanning device comprises a millimeter wave radar.
12. The method of claim 6,
the road characteristic determination reference factor includes: accumulating the occurrence times of the object in the current frame and the historical frame, and the first position distance of the object in the current frame and the historical frame;
the determining of the reference factor according to the road feature and the determining of the road feature data of any type of the current frame from the current frame object includes:
and taking the position data of the target with the occurrence frequency larger than the occurrence frequency threshold and the first position distance smaller than the first distance threshold as the first road characteristic data of the current frame.
13. The method of claim 12, wherein determining the reference factor according to the road characteristics to determine any type of road characteristic data of the current frame from the object of the current frame further comprises:
and determining second road characteristic data of the current frame according to the first road characteristic data through a road characteristic enhancement algorithm.
14. The method of claim 13, wherein the road feature enhancement algorithm comprises:
and taking the first road characteristic data as the center and data which is subjected to Gaussian distribution as second road characteristic data.
15. The method of claim 6,
the position distance between the adjacent historical frames is greater than a second distance threshold;
the method further comprises the following steps:
and if the second distance between the current frame and the adjacent historical frame reaches a second distance threshold, taking the current frame as a newly-added historical frame.
16. The method of claim 15, further comprising:
and if the number of the historical frames is greater than the threshold value of the historical frame data, removing the historical frames meeting the historical frame removing condition.
17. The method of claim 15, further comprising:
and determining a reference factor according to the road characteristics of the newly added historical frame, and marking the road characteristic type of each object in the newly added historical frame.
18. The method of claim 17,
determining a reference factor according to the road characteristics of the newly added historical frame, marking the road characteristic type of each object in the newly added historical frame, and adopting at least one of the following modes:
marking objects corresponding to the road characteristic data in the newly-added historical frame as characteristic points;
marking the objects of which the occurrence times of the newly-added historical frames are less than the threshold value of the occurrence times as lively points;
and marking the objects with the appearance times of the newly-added historical frames smaller than an appearance time threshold value and the first position distance larger than a first distance threshold value as wandering points.
19. The method of claim 12, wherein the first positional distance is determined by:
converting the road environment data of the current frame and the road environment data of the historical frame into road environment data under the same coordinate system;
taking the mean distance variance as the first location distance.
20. The method of claim 6, wherein determining pose data of the mobile device from the road feature data and the road feature data set of the current frame comprises:
acquiring pose data of a previous frame of the current frame; acquiring the movement distance of the current frame relative to the previous frame; acquiring road characteristic data of the historical frame;
and determining the pose data of the mobile equipment by a Bayesian filtering algorithm according to the road feature data of the current frame, the road feature data of the historical frame, the pose data of the previous frame, the motion distance and the road feature data set.
21. The method of claim 20, further comprising:
and updating the pose data of the previous frame according to the determined pose data.
22. The method of claim 21,
the initial pose data of the mobile device includes pose data determined from a satellite positioning system.
23. The method of claim 6, further comprising:
determining time delay data according to the position difference of the same object in the current frame and the historical frame and the moving speed of the mobile equipment;
and calibrating the data acquisition time of the current frame according to the delay data.
24. A road characteristic data generation device, comprising:
the data acquisition unit is used for acquiring road environment data in a driving road through the space scanning device and taking the road environment data as road environment data of a current frame;
the reference factor determining unit is used for determining a road characteristic determination reference factor of an object of the current frame according to the road environment data of the current frame and the road environment data of a plurality of historical frames before the current frame, wherein the road characteristic determination reference factor is multi-frame linkage data related to the road environment data of the historical frames;
the road characteristic determining unit is used for determining a reference factor according to the road characteristics and determining any type of road characteristic data of the current frame from the current frame object;
and the request sending unit is used for sending a road characteristic data acquisition and storage request aiming at the road characteristic data of the current frame to the server.
25. A mobile device positioning apparatus, comprising:
the request receiving unit is used for receiving a road characteristic data acquisition and storage request aiming at the road characteristic data of a first current frame, which is sent by a first mobile device;
and the data storage unit is used for storing the road characteristic data of the first current frame into a road characteristic data set.
26. A mobile device positioning apparatus, comprising:
the data acquisition unit is used for acquiring road environment data in a driving road through the space scanning device and taking the road environment data as road environment data of a current frame;
the reference factor determining unit is used for determining a road characteristic determination reference factor of an object of the current frame according to the road environment data of the current frame and the road environment data of a plurality of historical frames before the current frame, wherein the road characteristic determination reference factor is multi-frame linkage data related to the road environment data of the historical frames;
the road characteristic determining unit is used for determining a reference factor according to the road characteristics and determining any type of road characteristic data of the current frame from the current frame object;
and the pose data determining unit is used for determining the pose data of the mobile equipment according to the road characteristic data and the road characteristic data set of the current frame.
27. A mobile device, comprising:
a spatial scanning device;
a processor; and
a memory for storing a program for implementing a road characteristic data generating method, the apparatus performing the following steps after being powered on and running the program of the method by the processor: collecting road environment data in a driving road through a space scanning device to serve as the road environment data of a current frame; determining a road characteristic determination reference factor of an object of the current frame according to the road environment data of the current frame and the road environment data of a plurality of historical frames before the current frame, wherein the road characteristic determination reference factor is multi-frame linkage data related to the road environment data of the historical frames; determining a reference factor according to the road characteristics, and determining any type of road characteristic data of the current frame from the current frame object; and sending a road characteristic data acquisition and storage request aiming at the road characteristic data of the current frame to a server.
28. A mobile device, comprising:
a spatial scanning device;
a processor; and
a memory for storing a program for implementing a method for locating a mobile device, the device being powered on and the program for implementing the method being executed by the processor for performing the steps of: receiving a road characteristic data acquisition and storage request aiming at the road characteristic data of a first current frame, which is sent by a first mobile device; and storing the road characteristic data of the first current frame into a road characteristic data set.
29. An electronic device, comprising:
a processor; and
a memory for storing a program for implementing a method for locating a mobile device, the device being powered on and the program for implementing the method being executed by the processor for performing the steps of: collecting road environment data in a driving road through a space scanning device to serve as the road environment data of a current frame; determining a road characteristic determination reference factor of an object of the current frame according to the road environment data of the current frame and the road environment data of a plurality of historical frames before the current frame, wherein the road characteristic determination reference factor is multi-frame linkage data related to the road environment data of the historical frames; determining a reference factor according to the road characteristics, and determining any type of road characteristic data of the current frame from the current frame object; and determining pose data of the mobile equipment according to the road characteristic data and the road characteristic data set of the current frame.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911015827.9A CN112698315B (en) | 2019-10-23 | 2019-10-23 | Mobile equipment positioning system, method and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911015827.9A CN112698315B (en) | 2019-10-23 | 2019-10-23 | Mobile equipment positioning system, method and equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112698315A true CN112698315A (en) | 2021-04-23 |
| CN112698315B CN112698315B (en) | 2024-04-09 |
Family
ID=75505373
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911015827.9A Active CN112698315B (en) | 2019-10-23 | 2019-10-23 | Mobile equipment positioning system, method and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112698315B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023050679A1 (en) * | 2021-09-30 | 2023-04-06 | 上海商汤智能科技有限公司 | Obstacle detection method and apparatus, and computer device, storage medium, computer program and computer program product |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004171159A (en) * | 2002-11-18 | 2004-06-17 | Nec Corp | Road environment information reporting apparatus, on-board annunciator, device inside information center, and road environment information reporting program |
| CN104374395A (en) * | 2014-03-31 | 2015-02-25 | 南京邮电大学 | Graph-based vision SLAM (simultaneous localization and mapping) method |
| JP2016029564A (en) * | 2014-07-17 | 2016-03-03 | 株式会社リコー | Target detection method and target detector |
| US20160350904A1 (en) * | 2014-03-18 | 2016-12-01 | Huawei Technologies Co., Ltd. | Static Object Reconstruction Method and System |
| US20170006479A1 (en) * | 2015-07-01 | 2017-01-05 | Comcast Cable Communications, Llc | Intelligent Selection of Operating Parameters for a Wireless Access Point |
| CN107339996A (en) * | 2017-06-30 | 2017-11-10 | 百度在线网络技术（北京）有限公司 | Vehicle method for self-locating, device, equipment and storage medium |
| CN108286976A (en) * | 2017-01-09 | 2018-07-17 | 北京四维图新科技股份有限公司 | The fusion method and device and hybrid navigation system of a kind of point cloud data |
| CN109509210A (en) * | 2017-09-15 | 2019-03-22 | 百度在线网络技术（北京）有限公司 | Barrier tracking and device |
| CN109658449A (en) * | 2018-12-03 | 2019-04-19 | 华中科技大学 | A kind of indoor scene three-dimensional rebuilding method based on RGB-D image |
| CN109997052A (en) * | 2016-11-29 | 2019-07-09 | 大陆汽车有限责任公司 | Using cross-point sensor characteristic point with reference to build environment model and the method and system of positioning |
-
2019
- 2019-10-23 CN CN201911015827.9A patent/CN112698315B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004171159A (en) * | 2002-11-18 | 2004-06-17 | Nec Corp | Road environment information reporting apparatus, on-board annunciator, device inside information center, and road environment information reporting program |
| US20160350904A1 (en) * | 2014-03-18 | 2016-12-01 | Huawei Technologies Co., Ltd. | Static Object Reconstruction Method and System |
| CN104374395A (en) * | 2014-03-31 | 2015-02-25 | 南京邮电大学 | Graph-based vision SLAM (simultaneous localization and mapping) method |
| JP2016029564A (en) * | 2014-07-17 | 2016-03-03 | 株式会社リコー | Target detection method and target detector |
| US20170006479A1 (en) * | 2015-07-01 | 2017-01-05 | Comcast Cable Communications, Llc | Intelligent Selection of Operating Parameters for a Wireless Access Point |
| CN109997052A (en) * | 2016-11-29 | 2019-07-09 | 大陆汽车有限责任公司 | Using cross-point sensor characteristic point with reference to build environment model and the method and system of positioning |
| CN108286976A (en) * | 2017-01-09 | 2018-07-17 | 北京四维图新科技股份有限公司 | The fusion method and device and hybrid navigation system of a kind of point cloud data |
| CN107339996A (en) * | 2017-06-30 | 2017-11-10 | 百度在线网络技术（北京）有限公司 | Vehicle method for self-locating, device, equipment and storage medium |
| CN109509210A (en) * | 2017-09-15 | 2019-03-22 | 百度在线网络技术（北京）有限公司 | Barrier tracking and device |
| CN109658449A (en) * | 2018-12-03 | 2019-04-19 | 华中科技大学 | A kind of indoor scene three-dimensional rebuilding method based on RGB-D image |
Non-Patent Citations (2)
| Title |
|---|
| WEI ZHOU ET AL.: "Velocity Prediction of Intelligent and Connected Vehicles for a Traffic Light Distance on the Urban Road", 《IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS》, vol. 20, no. 11, pages 4119 - 4133, XP011754749, DOI: 10.1109/TITS.2018.2882609 * |
| 王春喜等: "路网匹配定位方法研究", 《宇航计测技术》, vol. 39, no. 2, pages 62 - 66 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023050679A1 (en) * | 2021-09-30 | 2023-04-06 | 上海商汤智能科技有限公司 | Obstacle detection method and apparatus, and computer device, storage medium, computer program and computer program product |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112698315B (en) | 2024-04-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Sun et al. | A 3D LiDAR data-based dedicated road boundary detection algorithm for autonomous vehicles | |
| CN108345822B (en) | Point cloud data processing method and device | |
| US10970317B2 (en) | System and method of a two-step object data processing by a vehicle and a server database for generating, updating and delivering a precision road property database | |
| US11085774B2 (en) | System and method of matching of road data objects for generating and updating a precision road database | |
| CN108372857B (en) | Efficient context awareness by event occurrence and episode memory review for autonomous driving systems | |
| Suhr et al. | Sensor fusion-based low-cost vehicle localization system for complex urban environments | |
| EP3130945B1 (en) | System and method for precision vehicle positioning | |
| US8359156B2 (en) | Map generation system and map generation method by using GPS tracks | |
| Holgado‐Barco et al. | Semiautomatic extraction of road horizontal alignment from a mobile LiDAR system | |
| CN110542908A (en) | laser radar dynamic object perception method applied to intelligent driving vehicle | |
| CN113379805A (en) | Multi-information resource fusion processing method for traffic nodes | |
| US11493624B2 (en) | Method and system for mapping and locating a vehicle based on radar measurements | |
| WO2021218388A1 (en) | High-precision map generation method, localization method, and device | |
| CN112740225B (en) | Method and device for determining road surface elements | |
| Kellner et al. | Road curb detection based on different elevation mapping techniques | |
| CN112578781B (en) | Data processing method, device, chip system and medium | |
| KR20230120974A (en) | Curb-based feature extraction for localization and lane detection using radar | |
| CN117593685B (en) | Method and device for constructing true value data and storage medium | |
| CN112698315B (en) | Mobile equipment positioning system, method and equipment | |
| CN114252897A (en) | Positioning method, positioning device, electronic equipment and computer storage medium | |
| WO2024078265A1 (en) | Multi-layer high-precision map generation method and apparatus | |
| CN117576652A (en) | Road object identification method and device, storage medium and electronic equipment | |
| CN117029840A (en) | Mobile vehicle positioning method and system | |
| JP7298882B2 (en) | Vehicle self-localization device and vehicle | |
| CN115668333A (en) | Electronic map generation method and device, computer equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20230705 Address after: Room 437, Floor 4, Building 3, No. 969, Wenyi West Road, Wuchang Subdistrict, Yuhang District, Hangzhou City, Zhejiang Province Applicant after: Wuzhou Online E-Commerce (Beijing) Co.,Ltd. Address before: Box 847, four, Grand Cayman capital, Cayman Islands, UK Applicant before: ALIBABA GROUP HOLDING Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |