CN113534214B - Vehicle positioning method and device - Google Patents

Vehicle positioning method and device Download PDF

Info

Publication number
CN113534214B
CN113534214B CN202111053036.2A CN202111053036A CN113534214B CN 113534214 B CN113534214 B CN 113534214B CN 202111053036 A CN202111053036 A CN 202111053036A CN 113534214 B CN113534214 B CN 113534214B
Authority
CN
China
Prior art keywords
vehicle
time
real
current
data
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.)
Active
Application number
CN202111053036.2A
Other languages
Chinese (zh)
Other versions
CN113534214A (en
Inventor
高志军
张龙平
张妍
徐仕儒
陈锦
李亚妹
王硕
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beidou Tianxia Satellite Navigation Co ltd
Aerospace Hongtu Information Technology Co Ltd
Original Assignee
Beidou Tianxia Satellite Navigation Co ltd
Aerospace Hongtu Information Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beidou Tianxia Satellite Navigation Co ltd, Aerospace Hongtu Information Technology Co Ltd filed Critical Beidou Tianxia Satellite Navigation Co ltd
Priority to CN202111053036.2A priority Critical patent/CN113534214B/en
Publication of CN113534214A publication Critical patent/CN113534214A/en
Application granted granted Critical
Publication of CN113534214B publication Critical patent/CN113534214B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

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
    • G01S19/00—Satellite radio beacon positioning systems; Determining position, velocity or attitude using signals transmitted by such systems
    • G01S19/01—Satellite radio beacon positioning systems transmitting time-stamped messages, e.g. GPS [Global Positioning System], GLONASS [Global Orbiting Navigation Satellite System] or GALILEO
    • G01S19/13—Receivers
    • G01S19/35—Constructional details or hardware or software details of the signal processing chain
    • G01S19/37—Hardware or software details of the signal processing chain
    • 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
    • G01S19/00—Satellite radio beacon positioning systems; Determining position, velocity or attitude using signals transmitted by such systems
    • G01S19/38—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system
    • G01S19/39—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system the satellite radio beacon positioning system transmitting time-stamped messages, e.g. GPS [Global Positioning System], GLONASS [Global Orbiting Navigation Satellite System] or GALILEO
    • G01S19/42—Determining position
    • G01S19/45—Determining position by combining measurements of signals from the satellite radio beacon positioning system with a supplementary measurement

Landscapes

  • Engineering & Computer Science (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Signal Processing (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Traffic Control Systems (AREA)
  • Navigation (AREA)

Abstract

The embodiment of the application provides a vehicle positioning method and a vehicle positioning device, which relate to the technical field of positioning, wherein the vehicle positioning method comprises the steps of firstly acquiring real-time acquisition data of a sensor of a target vehicle; calculating the vehicle predicted speed at the current moment according to a pre-constructed predicted speed calculation model and data collected by a sensor in real time; then, calculating a first real-time vehicle position based on the vehicle characteristics according to a position model based on the vehicle characteristics, a vehicle predicted speed and sensor real-time acquisition data which are constructed in advance; calculating a second real-time vehicle position based on satellite positioning according to a pre-constructed position model based on satellite positioning and real-time data acquired by a sensor; and finally, performing fusion calculation processing on the first real-time vehicle position and the second real-time vehicle position to obtain the final real-time vehicle position of the target vehicle at the current moment, so that the vehicle positioning in a complex scene can be realized, and the method has the advantages of high positioning precision, high stability and good applicability.

Description

Vehicle positioning method and device
Technical Field
The application relates to the technical field of positioning, in particular to a vehicle positioning method and device.
Background
With the development of high and new technologies such as internet of things, artificial intelligence, big data and the like, the automatic driving is widely applied, and traffic accidents can be reduced to a certain extent, the traffic efficiency is improved, the traffic cost is saved, and the social development is promoted. The positioning technology is one of core technologies of an unmanned vehicle automatic driving system, and positioning output is key input of operations such as perception, path planning and the like in the unmanned vehicle automatic driving system. The existing vehicle positioning method generally adopts a positioning technology based on a Beidou/GNSS (Global Navigation Satellite System), and determines the position of a vehicle (i.e. a GNSS receiver on the vehicle) by measuring the distance between a Satellite with a known position and the vehicle (i.e. the GNSS receiver on the vehicle) in a distance intersection manner. However, in practice, it is found that the existing vehicle positioning method is easily affected by a complex environment (such as an urban high-rise shelter, a canyon, and the like), so that satellite signals are easily interfered, thereby reducing the positioning accuracy. Therefore, the existing vehicle positioning method has poor applicability, low stability and low positioning precision.
Disclosure of Invention
The embodiment of the application aims to provide a vehicle positioning method and device, which can realize vehicle positioning in a complex scene, and are high in positioning accuracy, high in stability and good in applicability.
In a first aspect, an embodiment of the present application provides a vehicle positioning method, including:
acquiring real-time acquisition data of a sensor of a target vehicle;
calculating the vehicle predicted speed at the current moment according to a pre-constructed predicted speed calculation model and the data acquired by the sensor in real time;
calculating a first real-time vehicle position based on vehicle characteristics according to a position model based on vehicle characteristics, the vehicle predicted speed and the sensor real-time acquisition data which are constructed in advance;
calculating a second real-time vehicle position based on satellite positioning according to a pre-constructed position model based on satellite positioning and the real-time acquisition data of the sensor;
and performing fusion calculation processing on the first real-time vehicle position and the second real-time vehicle position to obtain the final real-time vehicle position of the target vehicle at the current moment.
In the implementation process, acquiring real-time data acquired by a sensor of a target vehicle; calculating the vehicle predicted speed at the current moment according to a pre-constructed predicted speed calculation model and data collected by a sensor in real time; then, calculating a first real-time vehicle position based on the vehicle characteristics according to a position model based on the vehicle characteristics, a vehicle predicted speed and sensor real-time acquisition data which are constructed in advance; calculating a second real-time vehicle position based on satellite positioning according to a pre-constructed position model based on satellite positioning and real-time data acquired by a sensor; and finally, performing fusion calculation processing on the first real-time vehicle position and the second real-time vehicle position to obtain the final real-time vehicle position of the target vehicle at the current moment, so that the vehicle positioning in a complex scene can be realized, and the method has the advantages of high positioning precision, high stability and good applicability.
Further, the calculating the predicted speed of the vehicle at the current moment according to the pre-established predicted speed calculation model and the data collected by the sensor in real time comprises:
acquiring real-time meteorological condition data at the current moment, real-time road condition information at the current moment and preset vehicle type data;
acquiring the current speed of the target vehicle at the current moment according to the real-time data acquired by the sensor;
determining a current meteorological condition weight coefficient according to the real-time meteorological condition data, determining a current road condition smoothness coefficient according to the real-time road condition information, and determining a vehicle model weight coefficient of the target vehicle according to the vehicle type data;
and calculating the vehicle predicted speed of the target vehicle according to a pre-constructed predicted speed calculation model, the current speed of the vehicle, the current meteorological condition weight coefficient, the current road condition smoothness coefficient, the vehicle model weight coefficient, the real-time meteorological condition data, the real-time road condition information and the vehicle type data.
In the implementation process, the running speed of the vehicle at the current moment can be predicted according to the preset predicted speed calculation model and the data collected by the sensor in real time.
Further, the predicted speed calculation model includes:
Figure F_210908140014809_809499001
；
wherein the content of the first and second substances,
Figure F_210908140014920_920298002
；
wherein the current time is the kth time, bkPredicting a speed for said vehicle, bk1Is the current speed of the vehicle, bk2And (b) representing a weight coefficient of the vehicle model, a representing a unobstructed degree coefficient of the current road condition, c representing a weight coefficient of the current meteorological condition, S representing the vehicle type data, L representing the real-time road condition information, and Q representing the real-time meteorological condition data.
Further, the calculating a first real-time vehicle position based on the vehicle characteristics according to the pre-constructed position model based on the vehicle characteristics, the vehicle predicted speed and the real-time sensor collected data comprises:
determining the current course angle of the target vehicle at the current moment according to the real-time data collected by the sensor;
acquiring a last time final position finally calculated at the last time;
and calculating a first real-time vehicle position based on the vehicle characteristics according to a position model based on the vehicle characteristics, the current course angle and the last position at the previous moment, which are constructed in advance.
In the implementation process, the current course angle is acquired according to the data acquired by the sensor in real time, and then the first real-time vehicle position based on the vehicle characteristics is obtained through calculation according to the position model based on the vehicle characteristics, the current course angle and the last position at the last moment, so that the vehicle positioning based on the vehicle characteristics is realized.
Further, the vehicle feature-based location model includes:
Figure F_210908140015029_029677003
；
wherein the content of the first and second substances,
Figure F_210908140015158_158193004
；
wherein the current time is the kth time, the last time is the kth-1 time, and XkRepresenting the first real-time vehicle position, X, at the k-th time instantk-1' represents the last time final position of the k-1 th time, bkPredicting a speed, θ, for said vehiclekIs the current course angle, x, at the kth timek-1' abscissa information, y, representing the last position of the timek-1' positioning ordinate information indicating the last position at the previous time.
Further, the calculating a second real-time vehicle position based on satellite positioning according to a pre-constructed position model based on satellite positioning and the real-time acquisition data of the sensor comprises:
acquiring a satellite positioning position of the target vehicle, satellite position data of each positioning satellite and a real-time distance between each positioning satellite and the target vehicle according to the real-time data acquired by the sensors;
and calculating a second real-time vehicle position based on satellite positioning according to a pre-constructed position model based on satellite positioning, the satellite positioning position, the satellite position data and the real-time distance.
In the implementation process, the second real-time vehicle position based on satellite positioning can be calculated according to the real-time data collected by the sensor and the position model based on satellite positioning, so that the vehicle positioning based on satellite positioning is realized.
Further, the satellite positioning based location model comprises:
Figure F_210908140015267_267572005
；
wherein the content of the first and second substances,
Figure F_210908140015362_362714006
，i=1，2，3，…，n；
wherein the current time is the kth time, Xk'' denotes the second real-time vehicle position at the k-th instant, H denotes a satellite positioning-based coefficient matrix, l denotes a preset satellite positioning data error sum, v denotes a residual, (X)i，Yi，Zi) Satellite position data representing the i-th positioning satellite, (x, y, z) representing the satellite positioning position of the target vehicle, piRepresenting a real-time distance between an ith of the positioning satellites and the target vehicle.
Further, performing fusion calculation processing on the first real-time vehicle position and the second real-time vehicle position to obtain a final real-time vehicle position of the target vehicle at the current time, including:
calculating a coefficient matrix based on the vehicle characteristics according to a pre-constructed coefficient matrix based on the vehicle characteristics, the predicted vehicle speed and the current course angle;
calculating a fusion coefficient of the current moment according to the coefficient matrix based on the vehicle characteristics and the coefficient matrix based on the satellite positioning;
and calculating the final real-time vehicle position of the target vehicle at the current moment according to the first real-time vehicle position, the fusion coefficient, the second real-time vehicle position and the satellite positioning data error sum of a preset final position calculation formula.
In the implementation process, after a real-time vehicle position and a second real-time vehicle position are calculated, the final real-time vehicle position at the current moment can be calculated according to the satellite positioning data error sum, the fusion coefficient and a preset final position calculation formula.
Further, the preset final position calculation formula is as follows:
Figure F_210908140015491_491134007
；
wherein the current time is the kth time, Xk' denotes the final real-time vehicle position, XkRepresenting said first real-time vehicle position, KkRepresenting the fusion coefficient at the k-th time instant, l representing the satellite positioning data error sum, H representing the satellite positioning based coefficient matrix, Xk'' indicates the second real-time vehicle position.
A second aspect of embodiments of the present application provides a vehicle positioning apparatus, including:
the acquisition unit is used for acquiring the real-time acquisition data of the sensor of the target vehicle;
the first calculation unit is used for calculating the vehicle predicted speed at the current moment according to a pre-constructed predicted speed calculation model and the data acquired by the sensor in real time;
the second calculation unit is used for calculating a first real-time vehicle position based on the vehicle characteristics according to a position model based on the vehicle characteristics, the vehicle predicted speed and the sensor real-time acquisition data which are constructed in advance;
the third calculation unit is used for calculating a second real-time vehicle position based on satellite positioning according to a pre-constructed position model based on satellite positioning and the real-time acquisition data of the sensor;
and the fusion calculation unit is used for performing fusion calculation processing on the first real-time vehicle position and the second real-time vehicle position to obtain the final real-time vehicle position of the target vehicle at the current moment.
In the implementation process, the acquisition unit firstly acquires the real-time acquisition data of the sensor of the target vehicle; the first calculation unit calculates the vehicle predicted speed at the current moment according to a pre-constructed predicted speed calculation model and data acquired by a sensor in real time; then, a second calculation unit calculates a first real-time vehicle position based on the vehicle characteristics according to a position model based on the vehicle characteristics, a vehicle predicted speed and sensor real-time acquisition data which are constructed in advance; the third calculating unit calculates a second real-time vehicle position based on satellite positioning according to a pre-constructed position model based on satellite positioning and sensor real-time acquisition data; and finally, the fusion calculation unit performs fusion calculation processing on the first real-time vehicle position and the second real-time vehicle position to obtain the final real-time vehicle position of the target vehicle at the current moment, so that the vehicle positioning in a complex scene can be realized, and the method has high positioning accuracy, high stability and good applicability.
A third aspect of embodiments of the present application provides an electronic device, including a memory and a processor, where the memory is used to store a computer program, and the processor runs the computer program to make the electronic device execute the vehicle positioning method according to any one of the first aspect of embodiments of the present application.
A fourth aspect of the embodiments of the present application provides a computer-readable storage medium, which stores computer program instructions, and when the computer program instructions are read and executed by a processor, the computer program instructions perform the vehicle positioning method according to any one of the first aspect of the embodiments of the present application.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments of the present application will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and that those skilled in the art can also obtain other related drawings based on the drawings without inventive efforts.
Fig. 1 is a schematic flowchart of a vehicle positioning method according to an embodiment of the present disclosure;
FIG. 2 is a schematic flow chart of another vehicle positioning method provided in the embodiments of the present application;
FIG. 3 is a schematic structural diagram of a vehicle positioning device according to an embodiment of the present disclosure;
FIG. 4 is a schematic structural diagram of another vehicle positioning device provided in the embodiments of the present application;
fig. 5 is a schematic diagram illustrating a road network information base according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be described below with reference to the drawings in the embodiments of the present application.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures. Meanwhile, in the description of the present application, the terms "first", "second", and the like are used only for distinguishing the description, and are not to be construed as indicating or implying relative importance.
Example 1
Referring to fig. 1, fig. 1 is a schematic flow chart of a vehicle positioning method according to an embodiment of the present disclosure. The vehicle positioning method comprises the following steps:
and S101, acquiring real-time acquisition data of a sensor of the target vehicle.
In the embodiment of the application, the execution subject of the method is a vehicle.
In the embodiment of the present application, the vehicle is equipped with multiple types of sensors, including a GNSS positioning module, a camera, an electronic compass, a laser radar, a gyroscope, an accelerometer, and the like, which is not limited in the embodiment of the present application. The GNSS positioning module is used for high-precision positioning resolving, the camera provides road image information, the electronic compass provides a yaw angle, the electronic radar provides real-time obstacle detection, the gyroscope provides attitude information, and the accelerometer provides acceleration information. During vehicle operation, each sensor collects data in real time.
And S102, calculating the vehicle predicted speed at the current moment according to a pre-constructed predicted speed calculation model and data collected by a sensor in real time.
In the embodiment of the application, the predicted speed calculation model is used for calculating the predicted speed of the vehicle, and the specific calculation formula is as follows:
Figure F_210908140015616_616118008
；
wherein, bkPredicting speed for the vehicle, bk1Current speed obtained for the vehicle, bk2Is the theoretical speed of the vehicle.
As an optional implementation manner, the road image information provided by the camera, in combination with the vehicle type, weather, road condition information, and the like, may be used to perform vehicle theoretical speed modeling, specifically, the vehicle theoretical speed model is:
Figure F_210908140015792_792873009
；
wherein, bk2The method comprises the following steps of calculating the theoretical speed of a vehicle, wherein a is the weight of the model of the vehicle, b is the weight of the smooth degree of road conditions, c is the weight of meteorological conditions, model S is constructed vehicle type data (including attributes such as length, width and height), model L is constructed real-time road condition information (including congestion, traffic control, traffic accidents and the like) combined with road image information and network information, and model Q is constructed real-time meteorological condition data (including wind, rain, snow and the like). Wherein S, L, Q is modeled based on actual conditions.
In the above embodiment, the vehicle type data may be preset, and the real-time traffic information and the real-time weather data are information acquired at the kth time and may be acquired through the internet or the like.
In the above embodiment, a vehicle model weight determination model, a road condition smoothness weight determination model, and a meteorological condition weight determination model may be preset, and then the weight a of the vehicle model may be obtained according to preset vehicle type data and the vehicle model weight determination model; determining a model according to the acquired real-time road condition information and the road condition smoothness weight, and acquiring the weight b of the road condition smoothness; and determining a model according to the acquired real-time meteorological condition data and meteorological condition weight to acquire the meteorological condition weight c, wherein the embodiment of the application is not limited.
In the above embodiment, the original model of the road condition information, the original model of the meteorological condition, and the original model of the vehicle type may be preset, and then the model S may be constructed according to the preset data of the vehicle type and the original model of the road condition information; according to the acquired real-time road condition information and the original road condition information model, a model L can be constructed; and constructing a model Q according to the acquired real-time meteorological condition data and the meteorological condition original model.
After step S102, the method further includes the following steps:
s103, calculating a first real-time vehicle position based on the vehicle characteristics according to a position model based on the vehicle characteristics, the vehicle predicted speed and sensor real-time acquisition data which are constructed in advance.
In the embodiment of the application, the initial position X of the vehicle can be obtained through the Beidou/GNSS high-precision positioning technology (such as PPP, CORS, PPP-RTK and the like)0=[x0 y0]TThe initial attitude information of the vehicle can be obtained through the gyroscope, wherein the heading angle is theta0。
In the embodiment of the application, a position model based on vehicle characteristics is constructed:
Figure F_210908140015920_920777010
；
wherein, if the current time is the kth time, XkIs the predicted position (i.e. the first real-time vehicle position), X, at the kth time obtained from the vehicle characteristicsk-1’=[xk-1’ yk-1’]TIs the result of the position at time k-1, bkPredicting the speed, theta, for the vehicle at time kkIs the heading angle at which the vehicle is operating at time k.
After step S103, the following steps are also included:
and S104, calculating a second real-time vehicle position based on satellite positioning according to a pre-constructed position model based on satellite positioning and the real-time data collected by the sensor.
In the embodiment of the present application, the GNSS positioning module data may be utilized to construct an error equation and a position model based on the big dipper/GNSS (i.e., a position model based on satellite positioning):
error equation:
Figure F_210908140016045_045762011
；
satellite positioning based location model:
Figure F_210908140016139_139539012
；
wherein the content of the first and second substances,
Figure F_210908140016255_255321013
，i=1，2，3，…，n；
wherein the content of the first and second substances,
Figure F_210908140016353_353398014
is a residual, Xk'' is the vehicle position at the k-th time obtained by GNSS technology, (X)i，Yi，Zi) Is the position of the ith satellite, H is the coefficient matrix for GNSS positioning (i.e. the coefficient matrix for satellite-based positioning), (x, y, z) is the approximate position of the target vehicle (i.e. the satellite-positioned position), ρiIs the distance between the ith satellite and the vehicle, and l is the calculated GNSS data error sum.
In the above embodiments, the approximate position of the target vehicle may be obtained by the GNSS positioning module, and this embodiment of the present application is not limited thereto.
After step S104, the following steps are also included:
and S105, carrying out fusion calculation processing on the first real-time vehicle position and the second real-time vehicle position to obtain the final real-time vehicle position of the target vehicle at the current moment.
In the embodiment of the present application, based on the prediction result at the kth time, the actual GNSS positioning result at the kth time is used to perform residual error correction, and perform final positioning calculation:
Figure F_210908140016447_447180015
；
wherein, XkIs a first real-time vehicle position, K, based on vehicle characteristicskIs the fusion coefficient at the k-th time, l is the calculated GNSS data error sum, H is the coefficient matrix of GNSS positioning, Xk'' is the second real-time vehicle position at time k, X, obtained using GNSS technologyk' is the high precision positioning result (i.e. the final real-time vehicle position) at this moment.
In the embodiment of the application, the high-precision positioning result at the current moment can be continuously and circularly calculated by circulating the steps S101 to S105, the vehicle position can be predicted in a short term by utilizing the vehicle characteristics under the condition that GNSS is unavailable or the positioning signal is not good, and on the other hand, the positioning precision of the vehicle can be improved by combining the GNSS positioning data and the positioning based on the vehicle characteristics.
In the embodiment of the application, the method is applied to a positioning scene of a vehicle, and based on the positioning scene of the vehicle, the method can also be applied to scenes of vehicle navigation, driving track planning, obstacle avoidance, automatic driving and the like, and the embodiment of the application is not limited.
As an optional implementation manner, after calculating the final real-time vehicle position of the target vehicle at the current time, the method may further include the following steps:
acquiring data in real time according to a sensor to acquire barrier information;
calculating the maximum influence range of the node barrier on the vehicle and the linear distance between the vehicle position and the barrier according to the final real-time vehicle position and the barrier information;
calculating a real-time obstacle avoidance value according to a preset obstacle avoidance path model, a maximum influence range and a linear distance;
acquiring an obstacle avoidance path according to the real-time obstacle avoidance value;
and controlling the vehicle to carry out obstacle avoidance driving according to the obstacle avoidance path.
As a further optional implementation, calculating a real-time obstacle avoidance value according to a preset obstacle avoidance path model, a maximum influence range, and a linear distance may include the following steps:
acquiring preset vehicle type data, real-time road condition information at the current moment and real-time meteorological condition data;
acquiring a vehicle type database, a real-time road condition information database and a real-time meteorological condition database;
and calculating a real-time obstacle avoidance value according to a preset obstacle avoidance path model, vehicle type data, real-time road condition information, real-time meteorological condition data, a maximum influence range, a linear distance, a vehicle type database, a real-time road condition information database and a real-time meteorological condition database.
In the above embodiment, the obstacle avoidance path model is:
Figure F_210908140016559_559989016
wherein s is the maximum influence range of the node barrier on the vehicle, gbIs the straight-line distance between the vehicle position and the obstacle position, U is the real-time obstacle avoidance value,
Figure F_210908140016688_688323017
a vehicle type database for satisfying the node communication,
Figure F_210908140016813_813891018
A real-time road condition information database for meeting the communication of the node,
Figure F_210908140016991_991167019
To satisfy the real-time weather condition database of the node communication.
The model S is constructed vehicle type data (including attributes such as length, width and height), the model L is constructed real-time road condition information (including congestion, traffic control, traffic accidents and the like) by combining road image information and network information, and the model Q is constructed real-time meteorological condition data (including wind, rain, snow and the like). Wherein S, L, Q is modeled based on actual conditions.
As a further optional implementation, obtaining an obstacle avoidance path according to the real-time obstacle avoidance value may include the following steps:
judging whether vehicle obstacle avoidance planning is needed or not according to the real-time obstacle avoidance value;
if so, generating an obstacle avoidance planning request according to the real-time obstacle avoidance value, the final real-time vehicle position and the real-time sensor acquisition data;
sending the obstacle avoidance planning request to a server so that the server carries out obstacle avoidance planning according to the obstacle avoidance planning request to obtain an obstacle avoidance path;
and receiving the obstacle avoidance path sent by the server according to the obstacle avoidance planning request.
In the above embodiment, the real-time obstacle avoidance value calculated by the obstacle avoidance path model is used when the distance between the vehicle and the obstacle is greater than the obstacle influence range (i.e. g)b>S hours), and the vehicle type data, the real-time traffic information, and the real-time weather condition data satisfy the conditions (i.e., S e)
Figure F_210908140017117_117638020
And L is an element of
Figure F_210908140017275_275230021
And Q ∈ Q
Figure F_210908140017385_385250022
In time), a real-time obstacle avoidance value can be calculated; when the distance between the vehicle and the obstacle is less than or equal to the influence range of the obstacle (i.e. g)bS ≦), or the vehicle type data, real-time road condition information, and real-time weather data do not satisfy the conditions (i.e., S ∉)
Figure F_210908140017497_497659023
Or L ∉
Figure F_210908140017606_606860024
Or Q ∉
Figure F_210908140017718_718719025
Time), U =0, indicates that the vehicle must not pass through the obstacle, and the obstacle avoidance planning is not performed.
In the above embodiment, whether vehicle obstacle avoidance planning is needed or not may be determined according to the real-time obstacle avoidance value, and if U =0, vehicle obstacle avoidance planning is not needed; and if U is not equal to 0, vehicle obstacle avoidance planning is required, wherein the larger U represents the higher traffic expectation.
In the above embodiment, the server may be a cloud server, and may receive an obstacle avoidance planning request sent by a vehicle in real time, where the obstacle avoidance planning request includes a real-time obstacle avoidance value, a final real-time vehicle position, and data collected by a sensor in real time, and then construct a road network information base according to the obstacle avoidance planning request.
Referring to fig. 5, fig. 5 is a schematic diagram of a road network information base composition provided in an embodiment of the present application, as shown in fig. 5, the road network information base includes attribute information, location information, road condition information, and weather information, where the attribute information includes vehicle quality, vehicle model, vehicle length, width, and height, the location information includes vehicle location, road network geometric relationship, and other vehicle locations, the road condition information includes lane level, traffic quality, road speed limit quality, traffic control, traffic accident, and congestion, the weather information includes wind, rain, snow, and the like, and other related information may also be synthesized.
In the above embodiment, the cloud server can comprehensively utilize the road network information base to perform unified planning to obtain the obstacle avoidance path, realize human-vehicle-road cooperation, and transmit the planning result (i.e., the obstacle avoidance path) to the vehicle in real time. Based on cloud management, a road network information base comprising attribute information, position information, road condition information and meteorological information can be constructed, and unified vehicle passing planning of the cloud is achieved. The vehicle-mounted existing sensor is utilized to realize high-precision positioning of a complex scene, and the positioning precision, the stability and the cost are high; the multi-factor obstacle avoidance path modeling and cloud traffic planning can be realized, and the use requirements of special scenes are met.
In the embodiment, the method is based on vehicle-mounted multi-source sensor data, makes full use of information such as vehicle types, weather, road conditions and the like, and performs high-precision fusion positioning of vehicle characteristics and Beidou/GNSS and obstacle avoidance path planning; based on cloud management, a road network information base comprising attribute information, position information, road condition information and meteorological information is constructed, and unified traffic planning of vehicles at the cloud is achieved. The vehicle-mounted existing sensor is utilized to realize high-precision positioning of a complex scene, and the positioning precision, the stability and the cost are high; the multi-factor obstacle avoidance path modeling and cloud end simultaneous planning are realized, and the use requirements of special scenes are met. The Beidou/GNSS and the vehicle-mounted sensor are integrated, so that high-precision positioning under the conditions that urban canyon environment and signals are easily interfered is achieved; and the method integrates information such as vehicle equipment characteristics, weather, road conditions and the like, and can be applied to vehicle positioning and path planning in complex environments such as different weather, terrain and the like and special scenes such as emergency, guarantee, battle and the like. In addition, the secondary technology can also be applied to the passage of various mobile carriers such as aviation, navigation and the like.
Therefore, the vehicle positioning method described in the embodiment can realize vehicle positioning in a complex scene, and is high in positioning accuracy, high in stability and good in applicability.
Example 2
Referring to fig. 2, fig. 2 is a schematic flow chart of a vehicle positioning method according to an embodiment of the present application. As shown in fig. 2, wherein the vehicle positioning method includes:
s201, acquiring real-time acquisition data of a sensor of the target vehicle.
S202, acquiring real-time meteorological condition data at the current moment, real-time road condition information at the current moment and preset vehicle type data.
In the embodiment of the present application, the vehicle type data is preset, and includes the size (including length, width, height, vehicle chassis height, etc.) of the target vehicle, weight, vehicle model, used time, etc., and this embodiment of the present application is not limited thereto.
In the embodiment of the application, the real-time road condition information and the real-time weather condition data are information at the current moment and can be acquired through the Internet and other modes.
And S203, acquiring the current speed of the target vehicle at the current moment according to the data acquired by the sensor in real time.
In the embodiment of the application, the driving speed of the target vehicle at the current moment (namely the current speed of the vehicle) can be calculated according to the data collected by the sensor in real time, and the driving speed can be an instantaneous speed, an average speed and the like.
S204, determining a current meteorological condition weight coefficient according to the real-time meteorological condition data, determining a current road condition smoothness coefficient according to the real-time road condition information, and determining a vehicle model weight coefficient of the target vehicle according to the vehicle type data.
In the above embodiment, a vehicle model weight determination model, a road condition smoothness weight determination model, and a meteorological condition weight determination model may be preset, and then the weight a of the vehicle model may be obtained according to preset vehicle type data and the vehicle model weight determination model; determining a model according to the acquired real-time road condition information and the road condition smoothness weight, and acquiring the weight b of the road condition smoothness; and determining a model according to the acquired real-time meteorological condition data and meteorological condition weight to acquire the meteorological condition weight c, wherein the embodiment of the application is not limited.
S205, calculating the vehicle predicted speed of the target vehicle according to a pre-constructed predicted speed calculation model, the current speed of the vehicle, the current meteorological condition weight coefficient, the current road condition smoothness coefficient, the vehicle model weight coefficient, the real-time meteorological condition data, the real-time road condition information and the vehicle type data.
As an alternative embodiment, the predicted speed calculation model includes:
Figure F_210908140017843_843641026
；
wherein the content of the first and second substances,
Figure F_210908140017924_924182027
；
wherein the current time is the kth time, bkPredicting speed for the vehicle, bk1As the current speed of the vehicle, bk2The theoretical speed of the vehicle is represented by a vehicle model weight coefficient, b represents a smoothness coefficient of the current road condition, c represents a weight coefficient of the current meteorological condition, S represents vehicle type data, L represents real-time road condition information, and Q represents real-time meteorological condition data.
In the above embodiment, the original model of the road condition information, the original model of the meteorological condition, and the original model of the vehicle type may be preset, and then the model S may be constructed according to the preset data of the vehicle type and the original model of the road condition information; according to the acquired real-time road condition information and the original road condition information model, a model L can be constructed; and constructing a model Q according to the acquired real-time meteorological condition data and the meteorological condition original model.
In the embodiment of the present application, by implementing the steps S202 to S205, the predicted speed of the vehicle at the current time can be calculated according to the pre-constructed predicted speed calculation model and the data collected by the sensor in real time.
After step S205, the following steps are also included:
and S206, determining the current course angle of the target vehicle at the current moment according to the data collected by the sensor in real time.
And S207, acquiring the final position of the last time finally calculated at the last time.
S208, calculating a first real-time vehicle position based on the vehicle characteristics according to a position model based on the vehicle characteristics, the current course angle and the last position at last moment which are constructed in advance.
As an alternative embodiment, the vehicle feature-based location model includes:
Figure F_210908140018033_033667028
；
wherein the content of the first and second substances,
Figure F_210908140018146_146436029
；
wherein the current time is the kth time, the last time is the kth-1 time, and XkRepresenting a first real-time vehicle position, X, at a time kk-1' represents the last position at time k-1, bkPredicting speed, θ, for the vehiclekIs the current course angle, x, at time kk-1' abscissa information indicating last-time final position, yk-1' represents the positioning ordinate information of the last time final position.
In the above embodiment, Xk-1' represents the last time final position at the k-1 th time, specifically, the final real-time vehicle position calculated by the vehicle positioning method provided by the embodiment when the current time is the k-1 th time.
In the embodiment of the present application, by implementing the steps S206 to S208, the first real-time vehicle position based on the vehicle feature can be calculated according to the pre-constructed position model based on the vehicle feature, the vehicle predicted speed, and the sensor real-time collected data.
After step S208, the following steps are also included:
s209, acquiring the satellite positioning position of the target vehicle, the satellite position data of each positioning satellite and the real-time distance between each positioning satellite and the target vehicle according to the data acquired by the sensors in real time.
S210, calculating a second real-time vehicle position based on satellite positioning according to a pre-constructed position model based on satellite positioning, a satellite positioning position, satellite position data and a real-time distance.
As an alternative embodiment, the satellite positioning based location model comprises:
Figure F_210908140018239_239681030
；
wherein the content of the first and second substances,
Figure F_210908140018351_351936031
，i=1，2，3，…，n；
wherein the current time is the kth time, Xk'' denotes a second real-time vehicle position at the k-th time instant, H denotes a satellite positioning-based coefficient matrix, l denotes a preset satellite positioning data error sum, v denotes a residual error, (X)i，Yi，Zi) Satellite position data representing the i-th positioning satellite, (x, y, z) the satellite positioning position of the target vehicle, ρiRepresenting the ith positioning satellite and the targetReal-time distance between vehicles.
In the embodiment of the present application, by implementing the steps S209 to S210, the second real-time vehicle position based on the satellite positioning can be calculated according to the pre-constructed position model based on the satellite positioning and the real-time data collected by the sensor.
After step S210, the method further includes the following steps:
s211, calculating a coefficient matrix based on the vehicle characteristics according to the pre-constructed coefficient matrix based on the vehicle characteristics, the predicted speed of the vehicle and the current heading angle.
In the embodiment of the application, a coefficient matrix formula of vehicle characteristics is as follows:
Figure F_210908140018461_461292032
；
wherein, PkIs a matrix of coefficients at time k, Pk-1Is the coefficient matrix at the k-1 time.
And S212, calculating a fusion coefficient at the current moment according to the coefficient matrix based on the vehicle characteristics and the coefficient matrix based on the satellite positioning.
In the embodiment of the application, a fused coefficient matrix can be constructed through the coefficient matrix formula of the vehicle characteristics and the coefficient matrix H of the GNSS, so as to balance the contribution values of the two technologies.
In the embodiment of the present application, the fusion coefficient matrix is:
Figure F_210908140018557_557506033
；
wherein, KkIs the fusion coefficient at the k-th time, PkH is the coefficient matrix for the GNSS positioning, for the k-th time instant.
In the embodiment of the present application, after the fusion coefficient at the kth time is calculated, the latest fusion coefficient matrix K may be usedkUpdating PkFor the next time (time K + 1) to calculate, wherein,
Figure F_210908140018651_651233034
。
after step S212, the method further includes the following steps:
and S213, calculating the sum of the formula first real-time vehicle position, the fusion coefficient, the second real-time vehicle position and the satellite positioning data error according to the preset final position, and calculating the final real-time vehicle position of the target vehicle at the current moment.
As an alternative embodiment, the preset final position calculation formula is:
Figure F_210908140018747_747945035
；
wherein the current time is the kth time, Xk' means Final real-time vehicle position, XkRepresenting a first real-time vehicle position, KkRepresents the fusion coefficient at the k-th time, l represents the error sum of satellite positioning data, H represents the coefficient matrix based on satellite positioning, Xk'' indicates a second real-time vehicle position.
In the embodiment of the present application, by implementing the steps S211 to S213, the fusion calculation processing can be performed on the first real-time vehicle position and the second real-time vehicle position to obtain the final real-time vehicle position of the target vehicle at the current time.
The vehicle positioning method can fully utilize information such as vehicle types, meteorology and road conditions based on vehicle-mounted multi-source sensor data to perform fusion high-precision positioning of vehicle characteristics and Beidou/GNSS.
Therefore, the vehicle positioning method described in the embodiment can realize vehicle positioning in a complex scene, and is high in positioning accuracy, high in stability and good in applicability.
Example 3
Please refer to fig. 3, fig. 3 is a schematic structural diagram of a vehicle positioning device according to an embodiment of the present application. As shown in fig. 3, the vehicle positioning apparatus includes:
the acquiring unit 310 is configured to acquire data collected by a sensor of the target vehicle in real time.
The first calculating unit 320 is configured to calculate the predicted speed of the vehicle at the current time according to a pre-constructed predicted speed calculation model and data collected by the sensor in real time.
And the second calculating unit 330 is used for calculating a first real-time vehicle position based on the vehicle characteristics according to a pre-constructed position model based on the vehicle characteristics, the vehicle predicted speed and the sensor real-time collected data.
And the third calculating unit 340 is configured to calculate a second real-time vehicle position based on satellite positioning according to a pre-constructed satellite positioning-based position model and the sensor real-time acquisition data.
And the fusion calculation unit 350 is configured to perform fusion calculation processing on the first real-time vehicle position and the second real-time vehicle position to obtain a final real-time vehicle position of the target vehicle at the current time.
In the embodiment of the present application, for explanation of the vehicle positioning device, reference may be made to the description in embodiment 1 or embodiment 2, and details are not repeated in this embodiment.
Therefore, the vehicle positioning device described in the embodiment can realize vehicle positioning in a complex scene, and is high in positioning accuracy, high in stability and good in applicability.
Example 4
Referring to fig. 4, fig. 4 is a schematic structural diagram of a vehicle positioning device according to an embodiment of the present disclosure. The vehicle positioning device shown in fig. 4 is optimized from the vehicle positioning device shown in fig. 3. As shown in fig. 4, the first calculation unit 320 includes:
a first obtaining subunit 321, configured to obtain real-time weather condition data at the current time, real-time road condition information at the current time, and preset vehicle type data; and acquiring the current speed of the target vehicle at the current moment according to the data acquired by the sensor in real time.
The first determining subunit 322 is configured to determine a current weather condition weight coefficient according to the real-time weather condition data, determine a smoothness coefficient of the current road condition according to the real-time road condition information, and determine a vehicle model weight coefficient of the target vehicle according to the vehicle type data.
The first calculating subunit 323 is configured to calculate the vehicle predicted speed of the target vehicle according to a pre-constructed predicted speed calculation model, the current speed of the vehicle, the current weather condition weight coefficient, the current road condition smoothness coefficient, the vehicle model weight coefficient, the real-time weather condition data, the real-time road condition information, and the vehicle type data.
As an alternative embodiment, the predicted speed calculation model includes:
Figure F_210908140018841_841668036
；
wherein the content of the first and second substances,
Figure F_210908140018936_936937037
(ii) a The current time is the kth time, bkPredicting speed for the vehicle, bk1As the current speed of the vehicle, bk2The theoretical speed of the vehicle is represented by a vehicle model weight coefficient, b represents a smoothness coefficient of the current road condition, c represents a weight coefficient of the current meteorological condition, S represents vehicle type data, L represents real-time road condition information, and Q represents real-time meteorological condition data.
As an alternative embodiment, the second calculation unit 330 includes:
and the second determining subunit 331 is configured to determine the current heading angle of the target vehicle at the current time according to the data collected by the sensor in real time.
A second obtaining subunit 332, configured to obtain a last time final position finally calculated at the last time.
And the second calculating subunit 333 is configured to calculate a first real-time vehicle position based on the vehicle feature according to the pre-constructed position model based on the vehicle feature, the current heading angle, and the last position at the previous moment.
As an alternative embodiment, the vehicle feature-based location model includes:
Figure F_210908140019030_030632038
；
wherein the content of the first and second substances,
Figure F_210908140019124_124851039
(ii) a The current time is the kth time, the last time is the kth-1 time, XkRepresenting a first real-time vehicle position, X, at a time kk-1' represents the last position at time k-1, bkPredicting speed, θ, for the vehiclekIs the current course angle, x, at time kk-1' abscissa information indicating last-time final position, yk-1' represents ordinate information of the last time final position.
As an alternative embodiment, the third computing unit 340 includes:
the third obtaining subunit 341 is configured to obtain, according to the data collected by the sensor in real time, the satellite positioning position of the target vehicle, the satellite position data of each positioning satellite, and the real-time distance between each positioning satellite and the target vehicle.
The third computing subunit 342 is configured to compute a second real-time vehicle position based on the satellite positioning according to the pre-constructed satellite positioning based position model, the satellite positioning position, the satellite position data, and the real-time distance.
As an alternative embodiment, the satellite positioning based location model comprises:
Figure F_210908140019233_233768040
；
wherein the content of the first and second substances,
Figure F_210908140019312_312927041
，i=1，2，3，…，n；
wherein the current time is the kth time, Xk'' denotes a second real-time vehicle position at the k-th time instant, H denotes a satellite positioning-based coefficient matrix, l denotes a preset satellite positioning data error sum, v denotes a residual error, (X)i，Yi，Zi) Indicates the ith particleSatellite position data for the satellites, (x, y, z) representing the satellite-based position of the target vehicle, ρiRepresenting the real-time distance between the ith positioning satellite and the target vehicle.
As an alternative embodiment, the fusion calculation unit 350 includes:
a fourth calculating subunit 351, configured to calculate a coefficient matrix based on the vehicle characteristics according to a pre-constructed coefficient matrix based on the vehicle characteristics, the predicted vehicle speed, and the current heading angle; and calculating the fusion coefficient of the current moment according to the coefficient matrix based on the vehicle characteristics and the coefficient matrix based on the satellite positioning.
And a fifth calculating subunit 352, configured to calculate a final real-time vehicle position of the target vehicle at the current time according to a preset final position calculating formula, the first real-time vehicle position, the fusion coefficient, the second real-time vehicle position, and the satellite positioning data error sum.
As an alternative embodiment, the preset final position calculation formula is:
Figure F_210908140019406_406605042
；
wherein the current time is the kth time, Xk' means Final real-time vehicle position, XkRepresenting a first real-time vehicle position, KkRepresents the fusion coefficient at the k-th time, l represents the error sum of satellite positioning data, H represents the coefficient matrix based on satellite positioning, Xk'' indicates a second real-time vehicle position.
As an alternative embodiment, the vehicle positioning device further comprises:
the information acquisition unit is used for acquiring data in real time according to the sensor after calculating the final real-time vehicle position of the target vehicle at the current moment, and acquiring barrier information;
the fourth calculation unit is used for calculating the maximum influence range of the node barrier on the vehicle and the linear distance between the vehicle position and the barrier according to the final real-time vehicle position and the barrier information;
the fifth calculation unit is used for calculating a real-time obstacle avoidance value according to a preset obstacle avoidance path model, a maximum influence range and a linear distance;
the path acquisition unit is used for acquiring an obstacle avoidance path according to the real-time obstacle avoidance value;
and the obstacle avoidance unit is used for controlling the vehicle to carry out obstacle avoidance driving according to the obstacle avoidance path.
As a further optional implementation, the fifth calculation unit comprises:
the fourth acquiring subunit is used for acquiring preset vehicle type data, and real-time road condition information and real-time meteorological condition data at the current moment; acquiring a vehicle type database, a real-time road condition information database and a real-time meteorological condition database;
and the sixth calculating subunit is used for calculating the real-time obstacle avoidance value according to the preset obstacle avoidance path model, the vehicle type data, the real-time road condition information, the real-time meteorological condition data, the maximum influence range, the linear distance, the vehicle type database, the real-time road condition information database and the real-time meteorological condition database.
In the above embodiment, the obstacle avoidance path model is:
Figure F_210908140019503_503314043
wherein s is the maximum influence range of the node barrier on the vehicle, gbIs the straight-line distance between the vehicle position and the obstacle position, U is the real-time obstacle avoidance value,
Figure F_210908140019597_597040044
a vehicle type database for satisfying the node communication,
Figure F_210908140019676_676100045
A real-time road condition information database for meeting the communication of the node,
Figure F_210908140019754_754737046
Real-time weather to satisfy the node communicationA situation database.
The model S is constructed vehicle type data (including attributes such as length, width and height), the model L is constructed real-time road condition information (including congestion, traffic control, traffic accidents and the like) by combining road image information and network information, and the model Q is constructed real-time meteorological condition data (including wind, rain, snow and the like). Wherein S, L, Q is modeled based on actual conditions.
As a further optional implementation, the path obtaining unit includes:
the judging subunit is used for judging whether vehicle obstacle avoidance planning needs to be carried out or not according to the real-time obstacle avoidance value;
the generating subunit is used for generating an obstacle avoidance planning request according to the real-time obstacle avoidance value, the final real-time vehicle position and the real-time sensor acquisition data when the judging subunit judges that the vehicle obstacle avoidance planning is required;
the sending subunit is configured to send the obstacle avoidance planning request to the server, so that the server performs obstacle avoidance planning according to the obstacle avoidance planning request to obtain an obstacle avoidance path;
and the receiving subunit is used for receiving the obstacle avoidance path sent by the server according to the obstacle avoidance planning request.
In the embodiment of the present application, for explanation of the vehicle positioning device, reference may be made to the description in embodiment 1 or embodiment 2, and details are not repeated in this embodiment.
Therefore, the vehicle positioning device described in the embodiment can realize vehicle positioning in a complex scene, and is high in positioning accuracy, high in stability and good in applicability.
The embodiment of the present application provides an electronic device, which includes a memory and a processor, where the memory is used to store a computer program, and the processor runs the computer program to make the electronic device execute the vehicle positioning method in any one of embodiment 1 or embodiment 2 of the present application.
The embodiment of the present application provides a computer-readable storage medium, which stores computer program instructions, and when the computer program instructions are read and executed by a processor, the method for positioning a vehicle according to any one of embodiment 1 or embodiment 2 of the present application is performed.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method can be implemented in other ways. The apparatus embodiments described above are merely illustrative, and for example, the flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In addition, functional modules in the embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.
The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on such understanding, the technical solution of the present application or portions thereof that substantially contribute to the prior art may be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The above description is only an example of the present application and is not intended to limit the scope of the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application. It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures.
The above description is only for the specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present application, and shall be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.

Claims (5)

1. A vehicle positioning method, characterized by comprising:
acquiring real-time acquisition data of a sensor of a target vehicle;
calculating the vehicle predicted speed at the current moment according to a pre-constructed predicted speed calculation model and the data acquired by the sensor in real time;
calculating a first real-time vehicle position based on vehicle characteristics according to a position model based on vehicle characteristics, the vehicle predicted speed and the sensor real-time acquisition data which are constructed in advance;
calculating a second real-time vehicle position based on satellite positioning according to a pre-constructed position model based on satellite positioning and the real-time acquisition data of the sensor;
performing fusion calculation processing on the first real-time vehicle position and the second real-time vehicle position to obtain a final real-time vehicle position of the target vehicle at the current moment;
the method for calculating the vehicle predicted speed at the current moment according to the pre-constructed predicted speed calculation model and the data collected by the sensor in real time comprises the following steps:
acquiring real-time meteorological condition data at the current moment, real-time road condition information at the current moment and preset vehicle type data;
acquiring the current speed of the target vehicle at the current moment according to the real-time data acquired by the sensor;
determining a current meteorological condition weight coefficient according to the real-time meteorological condition data, determining a current road condition smoothness coefficient according to the real-time road condition information, and determining a vehicle type weight coefficient of the target vehicle according to the vehicle type data;
calculating the vehicle predicted speed of the target vehicle according to a pre-constructed predicted speed calculation model, the current speed of the vehicle, the current meteorological condition weight coefficient, the current road condition smoothness coefficient, the vehicle type weight coefficient, the real-time meteorological condition data, the real-time road condition information and the vehicle type data;
the predicted speed calculation model includes:
Figure 679231DEST_PATH_IMAGE001
；
wherein the content of the first and second substances,
Figure 954354DEST_PATH_IMAGE002
；
wherein the current time is the kth time, bkPredicting a speed for said vehicle, bk1Is the current speed of the vehicle, bk2Representing the theoretical speed of the vehicle, wherein a represents the weight coefficient of the type of the vehicle, b represents the unobstructed degree coefficient of the current road condition, c represents the weight coefficient of the current meteorological condition, S represents the data of the type of the vehicle, L represents the real-time road condition information, and Q represents the data of the real-time meteorological condition;
the calculating a first real-time vehicle position based on vehicle characteristics according to a pre-constructed position model based on vehicle characteristics, the vehicle predicted speed and the sensor real-time collected data comprises:
determining the current course angle of the target vehicle at the current moment according to the real-time data collected by the sensor;
acquiring a last-time final position finally calculated at the last time;
calculating a first real-time vehicle position based on the vehicle characteristics according to a position model based on the vehicle characteristics, the current course angle and the final position at the last moment, which are constructed in advance;
performing fusion calculation processing on the first real-time vehicle position and the second real-time vehicle position to obtain a final real-time vehicle position of the target vehicle at the current moment, including:
calculating a coefficient matrix based on the vehicle characteristics according to a pre-constructed coefficient matrix based on the vehicle characteristics, the predicted vehicle speed and the current course angle;
calculating a fusion coefficient of the current moment according to the coefficient matrix based on the vehicle characteristics and the coefficient matrix based on the satellite positioning;
calculating the final real-time vehicle position of the target vehicle at the current moment according to a preset final position calculation formula, the first real-time vehicle position, the fusion coefficient, the second real-time vehicle position and the satellite positioning data error sum;
the preset final position calculation formula is as follows:
Figure 535508DEST_PATH_IMAGE003
；
wherein the current time is the kth time, Xk' denotes the final real-time vehicle position, XkRepresenting said first real-time vehicle position, KkRepresents the fusion coefficient at the k-th time instant,lrepresenting the sum of the satellite positioning data errors, H representing the matrix of satellite positioning based coefficients, Xk'' indicates the second real-time vehicle position;
the coefficient matrix formula of the vehicle features is as follows:
Pk=
Figure 870675DEST_PATH_IMAGE004
wherein, PkA coefficient matrix based on the vehicle characteristics for the k-th time, Pk-1A coefficient matrix based on the vehicle characteristics, theta, at the time k-1kIs the current course angle, θ, at the kth timek-1Is the course angle at the k-1 th moment, bk-1Predicting the speed of the vehicle at the k-1 moment;
the matrix formula of the fusion coefficient is as follows:
Figure 599596DEST_PATH_IMAGE005
；
Figure 865361DEST_PATH_IMAGE006
；
wherein, KkIs the fusion coefficient, P, at the k-th instantkH represents the coefficient matrix based on satellite positioning for the coefficient matrix at the k time.
2. The vehicle localization method of claim 1, wherein the vehicle feature-based location model comprises:
Figure 363339DEST_PATH_IMAGE007
；
wherein the content of the first and second substances,
Figure 134986DEST_PATH_IMAGE008
；
wherein the current time is the kth time, the last time is the kth-1 time, and XkRepresenting the first real-time vehicle position, X, at the k-th time instantk-1' represents the last-time final position of the k-1 th time, bkPredicting a speed, θ, for said vehiclekIs the current course angle, x, at the kth timek-1' abscissa information, y, representing the last position of the timek-1' represents the location ordinate information of the last time final position.
3. The vehicle positioning method according to claim 1, wherein the calculating of the second real-time vehicle position based on satellite positioning according to the pre-constructed satellite positioning based position model and the sensor real-time acquisition data comprises:
acquiring a satellite positioning position of the target vehicle, satellite position data of each positioning satellite and a real-time distance between each positioning satellite and the target vehicle according to the real-time data acquired by the sensors;
and calculating a second real-time vehicle position based on satellite positioning according to a pre-constructed position model based on satellite positioning, the satellite positioning position, the satellite position data and the real-time distance.
4. The vehicle positioning method according to claim 3, characterized in that the satellite positioning based position model comprises:
Figure 23307DEST_PATH_IMAGE009
；
wherein the content of the first and second substances,
Figure 905813DEST_PATH_IMAGE010
，i=1，2，3，…，n；
wherein the current time is the kth time, Xk'' denotes the second real-time vehicle position at the k-th instant, H denotes a satellite positioning-based coefficient matrix,lrepresents a predetermined sum of satellite positioning data errors, (X)i，Yi，Zi) Satellite position data representing the i-th positioning satellite, (x, y, z) representing the satellite positioning position of the target vehicle, piRepresenting a real-time distance between an ith of the positioning satellites and the target vehicle.
5. A vehicle positioning apparatus, characterized by comprising:
the acquisition unit is used for acquiring the real-time acquisition data of the sensor of the target vehicle;
the first calculation unit is used for calculating the vehicle predicted speed at the current moment according to a pre-constructed predicted speed calculation model and the data acquired by the sensor in real time;
the second calculation unit is used for calculating a first real-time vehicle position based on the vehicle characteristics according to a position model based on the vehicle characteristics, the vehicle predicted speed and the sensor real-time acquisition data which are constructed in advance;
the third calculation unit is used for calculating a second real-time vehicle position based on satellite positioning according to a pre-constructed position model based on satellite positioning and the real-time acquisition data of the sensor;
the fusion calculation unit is used for performing fusion calculation processing on the first real-time vehicle position and the second real-time vehicle position to obtain a final real-time vehicle position of the target vehicle at the current moment;
the first calculation unit includes:
the first acquiring subunit is used for acquiring real-time meteorological condition data at the current moment, real-time road condition information at the current moment and preset vehicle type data; acquiring data in real time according to the sensor to acquire the current speed of the target vehicle at the current moment;
the first determining subunit is used for determining a current meteorological condition weight coefficient according to the real-time meteorological condition data, determining a current road condition smoothness coefficient according to the real-time road condition information, and determining a vehicle type weight coefficient of the target vehicle according to the vehicle type data;
the first calculating subunit is used for calculating the vehicle predicted speed of the target vehicle according to a pre-constructed predicted speed calculating model, the current speed of the vehicle, a current meteorological condition weight coefficient, a current road condition smoothness coefficient, a vehicle type weight coefficient, real-time meteorological condition data, real-time road condition information and vehicle type data;
the predicted speed calculation model includes:
Figure 946712DEST_PATH_IMAGE001
；
wherein the content of the first and second substances,
Figure 889260DEST_PATH_IMAGE002
(ii) a The current time is the kth time, bkPredicting speed for the vehicle, bk1As the current speed of the vehicle, bk2For the theoretical speed of the vehicle, a represents a weight coefficient of the type of the vehicle, b represents a coefficient of smoothness of the current road condition, c represents a weight coefficient of the current meteorological condition, S represents vehicle type data, L represents real-time road condition information, and Q representsReal-time weather data;
the second calculation unit includes:
the second determining subunit is used for determining the current course angle of the target vehicle at the current moment according to the data acquired by the sensor in real time;
the second acquiring subunit is used for acquiring a last-time final position finally calculated at a last time;
the second calculation subunit is used for calculating a first real-time vehicle position based on the vehicle characteristics according to a position model based on the vehicle characteristics, a current course angle and a final position at the last moment, which are constructed in advance;
the fusion calculation unit includes:
the fourth calculating subunit is used for calculating the coefficient matrix based on the vehicle characteristics according to the pre-constructed coefficient matrix based on the vehicle characteristics, the predicted speed of the vehicle and the current heading angle; calculating a fusion coefficient at the current moment according to the coefficient matrix based on the vehicle characteristics and the coefficient matrix based on satellite positioning;
the fifth calculating subunit is used for calculating the final real-time vehicle position of the target vehicle at the current moment according to a preset final position calculating formula, the first real-time vehicle position, the fusion coefficient, the second real-time vehicle position and the satellite positioning data error sum;
the preset final position calculation formula is as follows:
Figure 327195DEST_PATH_IMAGE003
；
wherein the current time is the kth time, Xk' means Final real-time vehicle position, XkRepresenting a first real-time vehicle position, KkRepresents the fusion coefficient at the k-th time instant,lrepresenting the sum of the satellite positioning data errors, H representing a matrix of coefficients based on satellite positioning, Xk'' denotes a second real-time vehicle position;
the coefficient matrix formula of the vehicle features is as follows:
Pk=
Figure 685495DEST_PATH_IMAGE004
wherein, PkA coefficient matrix based on the vehicle characteristics for the k-th time, Pk-1A coefficient matrix based on the vehicle characteristics, theta, at the time k-1kIs the current course angle, θ, at the kth timek-1Is the course angle at the k-1 th moment, bk-1Predicting the speed of the vehicle at the k-1 moment;
the matrix formula of the fusion coefficient is as follows:
Figure 158065DEST_PATH_IMAGE005
；
Figure 458465DEST_PATH_IMAGE006
；
wherein, KkIs the fusion coefficient, P, at the k-th instantkH represents the coefficient matrix based on satellite positioning for the coefficient matrix at the k time.
CN202111053036.2A 2021-09-09 2021-09-09 Vehicle positioning method and device Active CN113534214B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111053036.2A CN113534214B (en) 2021-09-09 2021-09-09 Vehicle positioning method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111053036.2A CN113534214B (en) 2021-09-09 2021-09-09 Vehicle positioning method and device

Publications (2)

Publication Number Publication Date
CN113534214A CN113534214A (en) 2021-10-22
CN113534214B true CN113534214B (en) 2021-12-21

Family

ID=78093119

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111053036.2A Active CN113534214B (en) 2021-09-09 2021-09-09 Vehicle positioning method and device

Country Status (1)

Country Link
CN (1) CN113534214B (en)

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20190113920A1 (en) * 2017-10-18 2019-04-18 Luminar Technologies, Inc. Controlling an autonomous vehicle using model predictive control
CN108647638B (en) * 2018-05-09 2021-10-12 东软睿驰汽车技术（上海）有限公司 Vehicle position detection method and device
CN108871336B (en) * 2018-06-20 2019-05-07 湘潭大学 A kind of vehicle location estimating system and method
CN109141456A (en) * 2018-08-21 2019-01-04 上海博泰悦臻网络技术服务有限公司 Navigation path planning method and server
CN111452619B (en) * 2020-01-22 2021-09-14 北京理工大学 Online energy consumption prediction method and system for electric vehicle
CN111443370B (en) * 2020-04-17 2022-02-18 中国第一汽车股份有限公司 Vehicle positioning method, device and equipment and vehicle

Also Published As

Publication number Publication date
CN113534214A (en) 2021-10-22

Similar Documents

Publication Publication Date Title
US11036238B2 (en) Positioning system based on geofencing framework
CN109084786B (en) Map data processing method
CN111561937B (en) Sensor fusion for accurate positioning
CN109410735B (en) Reflection value map construction method and device
JP5291935B2 (en) Apparatus and method for predicting future movement of an object
CN112650220A (en) Automatic vehicle driving method, vehicle-mounted controller and system
US11408739B2 (en) Location correction utilizing vehicle communication networks
US11507107B2 (en) Map information system
RU2757234C2 (en) Method and system for calculating data for controlling the operation of a self-driving car
CN113743469B (en) Automatic driving decision method integrating multi-source data and comprehensive multi-dimensional indexes
CN111380557A (en) Unmanned vehicle global path planning method and device
CN113553304A (en) Data storage system for automatic driving
JP2019174191A (en) Data structure, information transmitting device, control method, program, and storage medium
US10769942B2 (en) Method, device and system for wrong-way driver detection
CN111204342B (en) Map information system
CN113534214B (en) Vehicle positioning method and device
WO2019188820A1 (en) Information transmission device, data structure, control method, program, and storage medium
CN114995519B (en) Unmanned aerial vehicle AI landing method and system based on multi-obstacle scene
US11879969B2 (en) Radar altimeter inertial vertical loop
US11315417B2 (en) Method, device and system for wrong-way driver detection
CN115046546A (en) Automatic driving automobile positioning system and method based on lane line identification
CN115046547A (en) Automatic driving automobile positioning system and method under complex urban environment
CN111928863A (en) High-precision map data acquisition method, device and system
WO2019188874A1 (en) Data structure, information processing device, and map data generation device
US10876843B2 (en) Method, device and system for wrong-way driver detection

Legal Events

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