CN116295460A

CN116295460A - Road section determining method and device for vehicle, fusion positioning module and map engine

Info

Publication number: CN116295460A
Application number: CN202310317685.1A
Authority: CN
Inventors: 崔晨晨; 朱志华
Original assignee: Navinfo Co Ltd
Current assignee: Navinfo Co Ltd
Priority date: 2023-03-27
Filing date: 2023-03-27
Publication date: 2023-06-23

Abstract

The embodiment of the specification discloses a method and a device for determining a road section where a vehicle is located, a fusion positioning module and a high-precision map engine. The scheme may include: acquiring vehicle running information of a target vehicle at a first moment; determining an alternative matched road section set of the target vehicle in map data at the first moment based on the vehicle running information; then, for each road section in the candidate matching road section set, determining first matching degree information of the target vehicle and each road section at the first moment; determining the matching probability of the target vehicle and each road section based on the first matching degree information of the target vehicle and each road section at the first moment; and finally, determining the road section corresponding to the maximum value of the matching probability as the road section where the target vehicle is located.

Description

Road section determining method and device for vehicle, fusion positioning module and map engine

Technical Field

The application relates to the technical field of electronic maps, in particular to a method and a device for determining a road section where a vehicle is located, a fusion positioning module and a high-precision map engine.

Background

With the rise of automatic driving, map matching (map match) technology for matching vehicle positioning data with map data plays an increasingly important role.

After the sensor data is processed by the fusion positioning algorithm, a longitude and latitude positioning result can be obtained, and then the longitude and latitude positioning result is matched with map data, so that road positioning information or lane positioning information of the vehicle can be obtained. And a process of matching the longitude and latitude positioning result with the map data, namely a map matching process.

The conventional map matching method determines a link (link) where a vehicle is located in map data only depending on position information and heading angle information of the vehicle. However, in the case where the road scene is complex, matching is performed based on only the position information and the heading angle information, and the accuracy of matching is not high.

Disclosure of Invention

The embodiment of the specification provides a method and a device for determining a road section where a vehicle is located, a fusion positioning module and a high-precision map engine, so as to solve the problem that the matching accuracy is not high when the vehicle is matched with the road section in map data.

In order to solve the above technical problems, the embodiments of the present specification are implemented as follows:

The method for determining the road section where the vehicle is located provided by the embodiment of the specification comprises the following steps:

acquiring vehicle running information of a target vehicle at a first moment; the vehicle travel information includes at least one of latitude and longitude information and travel direction information; determining an alternative matched road segment set of the target vehicle in map data at the first moment based on the vehicle running information; for each road section in the candidate matching road section set, determining first matching degree information of the target vehicle and each road section at the first moment; determining the matching probability of the target vehicle and each road section based on first matching degree information of the target vehicle and each road section at the first moment; and determining the road section corresponding to the maximum value of the matching probability as the road section where the target vehicle is located.

The device for determining a road section where a vehicle is located provided in an embodiment of the present disclosure includes:

the information acquisition module is used for acquiring vehicle running information of the target vehicle at a first moment; the vehicle travel information includes at least one of latitude and longitude information and travel direction information;

the candidate matching road section determining module is used for determining a candidate matching road section set of the target vehicle in map data at the first moment based on the vehicle running information;

The matching degree information determining module is used for determining first matching degree information of the target vehicle and each road section at the first moment for each road section in the candidate matching road section set;

the matching probability determining module is used for determining the matching probability of the target vehicle and each road section based on first matching degree information of the target vehicle and each road section at the first moment;

and the road section determining module is used for determining the road section corresponding to the maximum value of the matching probability as the road section where the target vehicle is located.

The fusion positioning module provided by the embodiment of the specification comprises the device for determining the road section where the vehicle is located, wherein the device for determining the road section where the vehicle is located is used for determining the road section position of the vehicle in a high-precision map, and is used for assisting in cross verification with other sensor data of the vehicle, so that high-precision fusion positioning is realized, and the accurate position of the vehicle is obtained; the other vehicle sensors include at least one of inertial navigation, GNSS/RTK, vision and lidar.

The embodiment of the present specification provides a high-precision map engine, including:

the fusion positioning module is used for fusing the two modules;

the electronic horizon module is used for receiving external high-precision vehicle position information and matching the external high-precision vehicle position information with a map, and providing a functional interface for automatic driving application to conduct regulation and judgment;

And at least one of an automatic driving design operation domain judging module, a map updating module, a crowdsourcing preprocessing and returning module, a path cross correlation module and a lane-level path planning module;

the automatic driving design operation domain judging module is used for configuring an automatic driving area and judging requirements;

the map updating module is used for obtaining map data updating information of the high-precision map based on the vehicle position and the planned path;

the crowd-sourced preprocessing and returning module is used for returning the cloud and updating the map data center by preprocessing such as screening, fusing and the like on UGC visual vector data;

the route cross-correlation module is used for synchronizing a global route planning result initiated by a user to the automatic driving system, and obtaining a matching route of the navigation route on the high-precision map through cross-correlation with the high-precision map;

the lane-level path planning module is used for outputting lane levels and local path planning within a certain length range in front of the vehicle according to the navigation path matching and route correction results.

One embodiment of the present disclosure can achieve at least the following advantages: by regarding the state of the vehicle in the running process as a series of sequences, when the matching probability of the vehicle and each road section at the current moment is calculated, the matching probability of the vehicle and each road section at the previous moment is referred to, so that the accuracy of calculating the matching probability of the vehicle and each road section is improved, and the accuracy of determining the matching result of the road section where the vehicle is located is further improved.

Drawings

In order to more clearly illustrate the embodiments of the present description or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments described in the present application, and that other drawings may be obtained according to these drawings without inventive effort to a person skilled in the art.

Fig. 1 is a schematic flow chart of a method for determining a road section where a vehicle is located according to an embodiment of the present disclosure;

fig. 2 is a schematic diagram of a bifurcation application scenario provided in the embodiment of the present disclosure;

fig. 3 is a schematic diagram of an application scenario of an upper and lower layer road according to an embodiment of the present disclosure;

fig. 4 is a schematic diagram of another application scenario of a bifurcation provided in the embodiments of the present disclosure;

FIG. 5 is a flowchart of a training method for predicting a deep learning model of a road on which a vehicle is located according to an embodiment of the present disclosure;

fig. 6 is a schematic structural view of an apparatus for determining a road section on which a vehicle is located corresponding to fig. 1 according to an embodiment of the present disclosure;

fig. 7 is a schematic structural diagram of a high-precision map engine according to an embodiment of the present disclosure.

Detailed Description

For the purposes of making the objects, technical solutions and advantages of one or more embodiments of the present specification more clear, the technical solutions of one or more embodiments of the present specification will be clearly and completely described below in connection with specific embodiments of the present specification and corresponding drawings. It will be apparent that the described embodiments are only some, but not all, of the embodiments of the present specification. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without undue burden, are intended to be within the scope of one or more embodiments herein.

It should be understood that although the terms first, second, third, etc. may be used in this application to describe various information, these information should not be limited to these terms. These terms are only used to distinguish one type of information from another.

The following describes in detail the technical solutions provided by the embodiments of the present specification with reference to the accompanying drawings.

The method comprises the steps that sensor data are obtained by sensors such as a global navigation satellite system (Global Navigation Satellite System, GNSS), an inertial measurement unit (Inertial Measurement Unit, IMU) and the like, a longitude and latitude positioning result is obtained after the sensor data are processed by a fusion positioning algorithm, and then the longitude and latitude positioning result can be matched with map data to obtain road or lane positioning information of a vehicle. And a process of matching the longitude and latitude positioning result with the map data, namely a map matching process. In the process of applying map data to driving navigation, including the process of using standard-definition map data for vehicle navigation and using high-definition map data for automatic driving navigation, etc., a map matching technique as a link between positioning information and map data plays a vital role.

In the prior art, the traditional map matching method is based on a standard-definition map or a high-definition map, and the road section where the current vehicle positioning point is located is judged by inputting the angle difference between the heading angle of the vehicle and the extending direction of the road section and calculating the vertical distance from the vehicle positioning point to the road section. The method has the problem that for some complex road scenes, such as a fork road scene, an upper road scene, a lower road scene and the like, if the road section where the vehicle is positioned cannot be accurately and definitely positioned only by means of the position and the course angle of the vehicle body according to the traditional map matching method, data support cannot be effectively provided for automatic driving.

In order to solve the defects in the prior art, in the embodiment of the present specification, considering that the locating points of the vehicle acquired according to a certain frequency are regarded as a series of sequences, a viterbi algorithm (viterbi) concept based on a hidden markov model (Hidden Markov Model, HMM) is adopted, and when determining the road section where the vehicle is located at the current moment, the road section matching result of the vehicle at the previous moment can be referred to, that is, the road section matching result of the vehicle at the current position and the road section matching result of the vehicle at the previous moment are comprehensively considered, so that the accuracy of road section matching is improved.

Fig. 1 is a schematic flow chart of a method for determining a road section where a vehicle is located according to an embodiment of the present disclosure.

From the program perspective, the execution subject of the flow may be a program installed on an application server or an application terminal. It is understood that the method may be performed by any apparatus, device, platform, cluster of devices having computing, processing capabilities.

As shown in fig. 1, the process may include the steps of:

step 102: acquiring vehicle running information of a target vehicle at a first moment; the vehicle travel information includes at least one of latitude and longitude information and travel direction information.

In practical applications, the state of the vehicle (including information such as the vehicle pose and the road section on which the vehicle is located) is continuously changed during the running of the vehicle, and thus, the changed state during the running of the target vehicle can be regarded as a time-varying state sequence of the target vehicle. Wherein at different times the target vehicle corresponds to different states in the sequence of states. Based on the method in fig. 1, the state of the target vehicle at a certain time (e.g., the first time) can be determined, and more specifically, the road section where the target vehicle is located at a certain time (e.g., the first time) can be determined.

In the embodiment of the present specification, it is necessary to acquire the own vehicle travel information of the target vehicle before determining the road section in which the target vehicle is located, that is, before matching the target vehicle with the road section in the map data. Specifically, the own vehicle travel information of the target vehicle may include at least one of latitude and longitude information of the target vehicle and travel direction information of the target vehicle. Then, the target vehicle can be matched to the road section in the map data based on the own vehicle running information of the target vehicle.

The vehicle running information may be determined according to sensor information acquired by a sensor, for example, the vehicle running information may be determined based on sensor data acquired by a sensor such as a global navigation satellite system (Global Navigation Satellite System, GNSS) and an Inertial measurement unit (Inertial MeasurementUnit, IMU). In addition, in determining the own vehicle running information of the vehicle, the vehicle speed information, information acquired by the vehicle odometer, and the like may be used. Alternatively, in determining the own vehicle running information of the vehicle, sensor information collected by other vehicles, sensor information collected by road side equipment, and the like may also be utilized. The determination of the vehicle travel information may be performed in any conventional manner, and is not particularly limited in this application.

In a preferred embodiment, the acquired vehicle travel information of the target vehicle may be lane-level vehicle travel information. For example, the accuracy of latitude and longitude information in the vehicle running information may be in the order of centimeters. Under the condition of using the vehicle running information of the road level, the accuracy of the matching of the subsequent road sections can be improved.

Step 104: based on the vehicle travel information, a set of candidate matching road segments for the target vehicle in map data at the first time is determined.

In the implementation of the present specification, determining the road segment on which the vehicle is located specifically means determining the road segment with the highest matching degree with the vehicle in the map data according to the vehicle running information of the vehicle, and is regarded as the road segment on which the vehicle is currently actually running. The map data may specifically include standard-precision map data or high-precision map data.

In determining the road section where the vehicle is located, an expected forward range of the vehicle can be defined based on the prior value advantage in the map data, and an alternative matched road section set which is possibly the road section where the vehicle is currently located is determined from the expected forward range. In the case where the estimated forward travel range of the vehicle is defined, if the vehicle travel information of the vehicle is of a lane level, the estimated forward travel range of the vehicle may be defined based on the prescribed forward travel range of the lane (for example, the forward travel range of a straight lane, a left-turn lane, a right-turn lane, a turning lane is different).

In practical application, the step of determining the candidate matching road segments in step 104 may specifically include: and determining the map road section with the projection points falling in the target road section and the projection distance meeting the preset condition as an alternative matching road section meeting the condition according to the projection point position of the target vehicle perpendicular to the map road section and the projection distance between the target vehicle and the map road section.

More specifically, the projected position of the target vehicle with respect to each map segment may be determined based on latitude and longitude information of the target vehicle; then judging whether the projection position is positioned on the map road section, if the projection position is positioned outside the map road section, considering that the current map road section does not accord with the condition of the alternative matching road section, and ending the flow; and if the projection position is positioned on the map road section, calculating the projection distance between the target vehicle and the projection position. Under the condition that the projection distance between the target vehicle and the projection position is calculated, judging whether the projection distance is smaller than a preset distance threshold, if the projection distance is larger than or equal to the preset distance threshold, considering that the current map road section does not accord with the condition of the alternative matching road section, and ending the process; and if the projection distance is smaller than a preset distance threshold value, determining the map road section as a road section in the alternative matching road section set.

In an alternative embodiment, the candidate matching road segments may be further screened based on the driving direction information of the target vehicle. Specifically, after the projection distance is determined to be smaller than the preset distance threshold, the method may further include: determining an angle difference between the vehicle traveling direction and the extending direction of each map section based on the traveling direction information of the target vehicle; judging whether the angle difference value is smaller than a preset angle threshold value, if the angle difference value is larger than or equal to the preset angle threshold value, considering that the current map road section does not accord with the condition of the alternative matching road section, and ending the process; and if the angle difference value is smaller than a preset angle threshold value, determining the map road section as a road section in the alternative matching road section set.

For ease of understanding, a schematic diagram of a bifurcation application scenario in the embodiments of the present description is shown in fig. 2.

In fig. 2, a rectangular frame represents the target vehicle, the arrow direction on the rectangular frame represents the self-running direction heading, heading1 represents the extending direction of link3, and heading2 represents the extending direction of link 4. In step 102, the vehicle position of the target vehicle and the traveling direction (heading) of the target vehicle may be known. In step 104, distances and angles between the target vehicle and road segments (e.g., link3 and link 4) in the predicted forward range of the vehicle may be calculated. As shown in fig. 2, the distance between the target vehicle and link3 is d1, and the distance between the target vehicle and link4 is d2. In addition, the angle difference between the traveling direction of the target vehicle and the extending direction of link3 is the angle between head and head 1 (for example, may be denoted as α1, α1 is not shown in fig. 2), and the angle difference between the traveling direction of the target vehicle and the extending direction of link4 is the angle between head and head 2 (for example, may be denoted as α2, α2 is not shown in fig. 2).

Based on the method in step 104, several road segments may be determined as alternative matching road segments, which may comprise, for example, 1 road segment, 2 road segments or more. The solution of the embodiment of the present disclosure mainly solves the problem of how to determine the road section where the target vehicle is actually located in the case that 2 or more road sections are obtained by matching in step 104. In the actual application scene, the road bifurcation scene, the ramp mouth scene and the like can be included.

In the prior art, when complex road scenes such as intersections, turn junctions, upper and lower roads and the like are encountered, if the road section where the vehicle is currently located cannot be accurately judged only according to the position and the driving direction of the vehicle body and the position and the extending direction of the road section. And considering the fact that the vehicle may be changed in a complex road scene such as a fork, a turn, an upper and lower road, etc. when actually driving, it is possible to cause a large error if only the foregoing distance and direction information is considered.

In the embodiment of the present disclosure, after determining the candidate matching road segment set according to step 104, the road segment where the target vehicle is actually located may be determined according to

steps

106, 108 and 110. The road section on which the target vehicle is actually located means, expressed by the road section on which the target vehicle is most likely to be actually traveling, which is determined according to the method of the embodiment of the present specification. If link3 and link4 are included in the candidate matching road segment set as shown in fig. 2, it is necessary to determine whether the road segment where the target vehicle may actually be located is link3 or link4 according to the embodiment of the present disclosure.

Step 106: and for each road section in the candidate matching road section set, determining first matching degree information of the target vehicle and each road section at the first moment.

Since the anchor points of the vehicle are regarded as a series of sequences and the HMM model is being adapted to solve the sequence problem, when a complex road scene such as a fork, a turn, an upper road and a lower road is encountered, in steps 106 to 110, the HMM model and the viterbi algorithm are adopted, and the probability of each road section is calculated by calculating the measurement probability of the current position of the vehicle and the transition probability of the previous position of the vehicle to the current position, and the road section with the maximum probability value is determined as the road section where the vehicle is located by using the viterbi algorithm.

In practical applications, step 106 may specifically include: and for each road section in the candidate matching road section set, determining first matching degree information of the target vehicle and each road section at the first moment according to pose change information of the target vehicle at the first moment relative to the last moment and relative pose information of the target vehicle at the first moment relative to each road section.

Specifically, step 106 may include: and calculating transition probability and measurement probability of the target vehicle, and determining first matching degree information of the target vehicle and the target road segments in the candidate matching road segment set based on the transition probability and the measurement probability.

More specifically, step 106 may include: in one aspect, for a target road segment in the candidate matching road segment set, determining the transition probability based on vehicle driving information of the target vehicle at the first moment and vehicle driving information of the target vehicle at a previous moment; the transition probability is used for reflecting the probability that the target vehicle is converted from the pose corresponding to the previous moment to the pose corresponding to the first moment; on the other hand, for the target link, the measurement probability is determined based on the vehicle travel information of the target vehicle at the first time and the link attribute information of the target link in the map data; the measurement probability is used for reflecting the relevance of the relative pose information of the target vehicle relative to the target road section and the real position of the target vehicle on the target road section; then, first matching degree information of the target vehicle and the target road section is determined based on the transition probability and the measurement probability, and for example, the transition probability and the measurement probability may be multiplied to obtain the first matching probability of the target vehicle and the target road section.

Transition probabilities are important concepts in Markov chains, and if a Markov chain is divided into m states, the history can be converted into a sequence of the m states. From any one state, one of states 1, 2, … …, m must occur after any one transition, and transitions between such states are referred to as transition probabilities.

In the embodiment of the present specification, the transition probability may refer to a probability from a position on the vehicle to a current position of the vehicle. The method for determining the transition probability specifically comprises the following steps: calculating the position change quantity of the target vehicle from the last moment to the first moment based on the longitude and latitude information of the target vehicle at the first moment and the longitude and latitude information of the target vehicle at the last moment; and determining the transition probability of the target vehicle from the last moment to the first moment based on the position change quantity. Wherein the transition probability may be inversely related to the position change amount. In the embodiment of the present specification, the first physical quantity is inversely related to the second physical quantity, which may mean that the first physical quantity decreases as the second physical quantity increases, and the first physical quantity increases as the second physical quantity decreases.

In practical application, the distance from the last position of the vehicle to the current position of the vehicle can be used as input to calculate the transition probability. Alternatively, the transition probability may be calculated by a preset function (e.g., exp function).

The probability of measuring, i.e. the probability of an implicit state (or hidden state) to a visible state, is also called emission probability.

In the embodiment of the present specification, the hidden state represents vehicle travel information (including latitude and longitude positioning information and travel direction information) of the vehicle, and the visible state represents a road section on which the vehicle is located. The method for determining the measurement probability specifically may include: calculating the distance between the target vehicle and the target road section at the first moment based on the longitude and latitude information of the target vehicle at the first moment; determining a first probability associated with the distance based on the distance, the first probability being inversely associated with the distance; calculating an angle difference value between the vehicle running direction of the target vehicle at the first moment and the extending direction of the target road section; determining a second probability associated with the angle difference based on the angle difference, the second probability being inversely associated with the angle difference; based on the first probability and the second probability, a measurement probability is calculated, the measurement probability being positively correlated with the first probability and the measurement probability being positively correlated with the second probability, e.g. the first probability and the second probability may be summed to obtain the measurement probability. In the embodiment of the present specification, the first physical quantity being positively correlated with the second physical quantity may mean that the first physical quantity increases with an increase in the second physical quantity, and the first physical quantity decreases with a decrease in the second physical quantity.

In practical applications, taking the example of fig. 2 above as input, the measurement probability can be calculated by a preset function (e.g., exp function).

Specifically, the first probability is calculated based on the distance between the target vehicle and the target road segment at the first time, for example, the first probability corresponding to link3 may be calculated based on d1 and inversely related to d1, and the first probability corresponding to link4 may be calculated based on d2 and inversely related to d 2.

The second probability is calculated based on an angle difference between the vehicle traveling direction of the target vehicle at the first time and the extending direction of the target link, for example, it may be that the second probability corresponding to link3 is calculated based on α1 and is inversely related to α1, and the second probability corresponding to link4 is calculated based on α2 and is inversely related to α2.

The calculation of the measurement probability of the link at the first time based on the first probability and the second probability may be, for example, adding the first probability corresponding to link3 to the second probability corresponding to link3 to obtain the measurement probability corresponding to link3 at the first time (for example, denoted as k _{Measurement-link 3} ) The method comprises the steps of carrying out a first treatment on the surface of the Adding the first probability corresponding to link4 to the second probability corresponding to link4 to obtain a measurement probability corresponding to link4 at the first time (e.g., denoted as k _{Measurement-link 4} )。

Combining the above-mentioned calculation of the transition probability of the road section at the first time based on the position change amount (e.g., denoted as D) of the target vehicle from the second time to the first time, for example, obtaining the transition probability (e.g., denoted as k) corresponding to link3 at the first time _{Transfer-link 3} ) And the transition probability (e.g., denoted as k) corresponding to link4 at the first time _{Transfer-link 4} ). Then, a first matching probability k corresponding to link3 at the first moment can be calculated _{First match-link 3} ＝k _{Measurement-link 3} +k _{Transfer-link 3} The method comprises the steps of carrying out a first treatment on the surface of the Matching probability k corresponding to link4 at first moment _{First match-link 4} ＝k _{Measurement-link 4} +k _{Transfer-link 4} 。

It should be noted that k given above _{First match-link 3} And k _{First match-link 4} Is merely an example, for illustrative purposes. In practical application, other operation modes can be adopted to calculate and obtain first matching degree information of the target vehicle and each road section at the first moment.

Step 108: and determining the matching probability of the target vehicle and each road section based on the first matching degree information of the target vehicle and each road section at the first moment.

In an optional embodiment, the determining, based on the first matching degree information of the target vehicle and the road segments at the first moment, the matching probability of the target vehicle and the road segments may specifically include: acquiring second matching degree information of the target vehicle and each road section at the last moment; and determining the matching probability of the target vehicle and each road section based on the first matching degree information and the second matching degree information. The previous time is a time before the first time, and may be hereinafter referred to as a second time.

The second matching degree information may be determined according to pose change information of the target vehicle at the second moment relative to a third moment and relative pose information of the target vehicle at the second moment relative to each road section. Wherein the third time is earlier than the second time, or the third time is a time before the second time. The specific determination method of the second matching degree information may be similar to the specific determination method of the first matching degree information. For example, the transition probability and the measurement probability of the target road segment at the second moment may be calculated first, and then the transition probability and the measurement probability of the target road segment at the second moment may be multiplied to obtain the second matching probability of the target vehicle and the target road segment.

In step 108, specifically, on the basis of the first matching probability of the target vehicle and the target road section at the first moment, the second matching probability of the target vehicle and the target road section at the second moment before the first moment is further considered to comprehensively obtain the matching probability of the target vehicle and the target road section. Alternatively, a product of the first matching probability and the second matching probability may be calculated to obtain a matching probability of the target vehicle with the target road segment.

Along with the above example, for link3, a first probability of matching k of the target vehicle with link3 at a first time may be calculated _{First match-link 3} And a second matching probability k of the target vehicle and link3 at a second moment _{Second match-link 3} And then based on k _{First match-link 3} And k _{Second match-link 3} Obtaining the matching probability of the target vehicle and link3, optionally k _{Matching link3} ＝k _{First match-link 3} ×k _{Second match-link 3} . Similarly, for link4, a first probability of matching k of the target vehicle with link4 at the first time may be calculated _{First match-link 4} And a second matching probability k of the target vehicle and link4 at a second moment _{Second match-link 4} And then based on k _{First match-link 4} And k _{Second match-link 4} Obtaining the matching probability of the target vehicle and link4, optionally k _{Matching link4} ＝k _{Second match-link 4} ×k _{Second match-link 4} 。

In practical application, after the set of candidate matching road segments is determined in step 104, each road segment in the set of candidate matching road segments may be traversed in step 106 and step 108, and a matching probability value corresponding to each road segment respectively with the target vehicle may be calculated.

Step 110: and determining the road section corresponding to the maximum value of the matching probability as the road section where the target vehicle is located.

In practical application, on the one hand, according to the matching probability of each road segment determined in step 108, a road segment with a high matching probability may be determined from the matching probability as an optimal matching road segment of the target vehicle at the current moment (i.e., the first moment), and as a road segment where the target vehicle is currently located, the road segment is used for navigation. Along with the above example, k can be compared _{Matching link3} And k is equal to _{Matching link3} The road segment in which the probability value is large is determined as the best matching road segment of the target vehicle, and is considered as the road segment in which the target vehicle is currently located.

On the other hand, the matching probability of the target vehicle with each road segment at the present time determined in step 108 may be stored for use in calculating the matching probability of the target vehicle with each road segment at the next time.

It should be understood that, in the method described in one or more embodiments of the present disclosure, the order of some steps may be adjusted according to actual needs, or some steps may be omitted.

In the method in fig. 1, by regarding the state of the vehicle during running as a series of sequences, when calculating the matching probability of the vehicle and each road section at the current moment, the matching probability of the vehicle and each road section at the previous moment is referred to, so that the accuracy of calculating the matching probability of the vehicle and each road section is improved, and the accuracy of determining the result of the road section where the vehicle is located is further improved. In particular, for complex road scenes such as intersections, turn junctions, upper and lower roads and the like, the accuracy of positioning vehicles in a high-precision map can be remarkably improved, and powerful support is provided for driving navigation application.

Based on the method of fig. 1, the examples of the present specification also provide some specific implementations of the method, as described below.

In some complex road scenarios, for example, in upper and lower road scenarios such as viaducts, the continuity between road segments has a very high reference value for determining the road segment in which the vehicle is currently located. Therefore, in the embodiment of the present specification, when calculating the road section on which the target vehicle is located at the present time, the situation of the road section on which the target vehicle is located at the previous time may be further referred to on the basis of the foregoing scheme shown in fig. 1.

Specifically, before determining the matching probability of the target vehicle and each road segment based on the first matching degree information of the target vehicle and each road segment at the first time, the method may further include: and judging whether the target road section is the associated road section of the road section where the target vehicle is located at the last moment or not according to the target road sections in the candidate matching road section set, and obtaining an associated road section judging result.

The related road section judging result comprises a first result and a second result, wherein the first result indicates that the target road section is a related road section of the road section where the target vehicle is located at the last moment; the second result indicates that the target road segment is not an associated road segment of the road segment where the target vehicle was located at the last time. The target road section is an associated road section of the road section where the target vehicle is located at the previous moment, and specifically includes that the target road section and the road section where the target vehicle is located at the previous moment are the same road section, or the target road section is a continuous road section of the road section where the target vehicle is located at the previous moment.

On the basis of the foregoing determination, the determining, based on the first matching degree information of the target vehicle and the road segments at the first moment, the matching probability of the target vehicle and the road segments may specifically include: if the associated road section judging result indicates that the target road section is the associated road section of the road section where the target vehicle is located at the last moment, acquiring a preset associated road section weight coefficient; and determining the matching probability of the target vehicle and the target road section based on the first matching degree information of the target road section and the weight coefficient of the associated road section.

For example, the matching probability of the target link may be multiplied by the associated link weight coefficient based on the probability obtained based on the first matching degree information (or first matching probability) and the second matching degree information (or second matching probability). Wherein, the associated road section weight coefficient may be a number greater than 1.

Fig. 3 shows a schematic diagram of an upper and lower road application scenario according to an embodiment of the present disclosure.

As shown in fig. 3, there are shown a "current vehicle position" and a traveling direction (heading) of the target vehicle (rectangular frame) at the current time, and alternative matching road segments link1 and link2 at the current time; also, the "last state vehicle position" of the target vehicle at the previous time is shown. link1 is a link4 link, and link2 is a link3 link. In the scenario shown in fig. 3, the distance between the vehicle and link1 and link2 at the current moment is relatively close, and the angles between the vehicle and link1 and link2 are also relatively close, so that the road section where the vehicle is located cannot be accurately determined only by the distance and the angle.

If it is determined that link3 is the road section where the target vehicle is located at the previous moment in actual application, when determining the road section where the vehicle is located from the candidate matching road sections link1 and link2 at the current moment, the matching probability corresponding to the link2 of the continuous road section link3 can be multiplied by a preset coefficient when calculating, so that the calculated matching probability of the target vehicle and link2 is increased, and the accuracy of matching the vehicle and the road section is improved.

As shown in FIG. 3, if the matching probability k of the target vehicle and link1 at the current moment has been calculated _{Matching link1} Probability of matching k with link2 _{Matching link2} On the basis, if link3 is the road section where the target vehicle is located at the previous moment and link3 is the road section where link2 is connected, the matching probability k of link2 can be determined _{Matching link2} Updating, and assuming that the preset coefficient is a, k is calculated _{Matching link2} Is updated to a x k _{Matching link2} 。

In the embodiment of the foregoing description, the connection attribute of the lanes in the map data is utilized to increase the weight value for the probability calculated by the HMM model in consideration of the priori property of the high-precision map, so that the accuracy of road section positioning where the vehicle is located can be improved.

In reality, in some cases, the extending direction of the road section in the map data has a large deviation from the actual passing direction of the road due to the limitation of the mapping technique or the mapping defect, etc., and the actual traveling direction of the vehicle and the actual passing direction of the road are not generally different. In this case, there is a large error in the conventional distance and direction-based judgment method, and there is a large possibility of misjudgment, and then a phenomenon that the vehicle repeatedly jumps across the map section during navigation occurs. In the embodiment of the specification, the history state sequence is considered by using the HMM model, so that the accuracy is greatly improved, and even if the judgment is wrong, the judgment can be corrected back in time along with updating of the positioning point, and the phenomenon of repeated transverse jump can not occur.

On this basis, in the embodiment of the present disclosure, for a specific road scene, a deep learning model corresponding to the specific road scene may be trained by using a large amount of vehicle real-time data for the scenes, and then, when the vehicle travels to the specific road scene, when calculating a road section where the target vehicle is located in the current road scene, the road section where the target vehicle is actually located may be determined in combination with the prediction result of the pre-trained deep learning model corresponding to the current road scene on the basis of the scheme shown in fig. 1.

Specifically, before determining the matching probability of the target vehicle and each road segment based on the first matching degree information of the target vehicle and each road segment at the first time, the method may further include: judging whether the current scene of the target vehicle is a preset specific scene or not; if the current scene of the target vehicle is a preset specific scene, calculating the model probability corresponding to each road section in the alternative matching road section set by adopting a pre-trained deep learning model corresponding to the preset specific scene; the deep learning model is trained based on vehicle real-time data in the preset specific scene, wherein the vehicle real-time data comprise vehicle running information and corresponding vehicle real-time section information in a data map; and determining a model weight coefficient corresponding to each road section according to the model probability corresponding to each road section, wherein the model weight coefficient can be positively correlated with the model probability in actual application. Correspondingly, the determining the matching probability of the target vehicle and each road section based on the first matching degree information of the target vehicle and each road section at the first moment may specifically include: and determining the matching probability of the target vehicle and each road section based on the first matching degree information of the target road section and the model weight coefficient.

The method for calculating the model probability corresponding to each road section in the candidate matching road section set by adopting a pre-trained deep learning model corresponding to the preset specific scene specifically comprises the following steps: and inputting the vehicle running information of the current state and the road section attribute information of each road section in the alternative road section set, and outputting the model probability corresponding to each road section.

The determining the matching probability of the target vehicle and each road section based on the first matching degree information of the target road section and the model weight coefficient may specifically include multiplying the model weight coefficient on the basis of a probability obtained based on the first matching degree information (or called first matching probability) and the second matching degree information (or called second matching probability). Wherein the model weight coefficient may be a number greater than 1.

In the above embodiment, based on the HMM, for a specific road scene, a large amount of real-time data in the specific road scene may be used as training data (for example, parameters such as a distance between a vehicle and a road boundary on both sides, a distance between a vehicle and a boundary on both sides of a lane, a gradient of a road or a lane, a curvature of the road or the lane, and a connection relationship between the road or the lane), and the like, and the training may be performed on the specific road scene by using a logistic regression method to train a deep learning model corresponding to the specific road scene. When the method is applied, the output result of the deep learning model is model probability values corresponding to a plurality of candidate road segments, the model probability values can be obtained by adding a weight value to the probability values calculated based on the HMM model, and the prior of the high-precision map is combined, so that the accuracy of judging the road segments where the vehicles are located in the scene is improved.

Fig. 4 shows a schematic diagram of another bifurcation application scenario provided in the embodiments of the present specification.

In fig. 4, a rectangular frame indicates the vehicle position of the target vehicle, the arrow direction on the rectangular frame indicates the vehicle traveling direction heading, heading1 indicates the extending direction of link3, and heading2 indicates the extending direction of link 4. d1 represents the distance between the target vehicle and link3, and d2 represents the distance between the target vehicle and link 4. In the example of fig. 4, the actual traveling direction head of the vehicle (reflecting the actual traveling direction of the road) differs greatly from the link extending direction head 2 recorded in the map data, which generally results in a matching error. According to the scheme of the embodiment of the specification, through pre-training the deep learning model corresponding to the scene shown in fig. 4, when the target vehicle is in the specific scene, the pre-trained model can be called to calculate the corresponding model probability, and further the corresponding weight coefficient is provided for calculating the matching probability of each road section, so that the accuracy of matching from the vehicle to the road section is improved.

As shown in FIG. 3, if the matching probability k of the target vehicle and link3 at the current moment has been calculated _{Matching link3} Probability of matching k with link4 _{Matching link4} Based on the above, the probability coefficient b3 of the current link3 of the target vehicle and the probability coefficient b4 of the current link4 of the target vehicle given by the pre-trained deep learning model corresponding to the scene can be further combined, and k can be further calculated _{Matching link3} Updated to b3 k _{Matching link3} Will k _{Matching link4} Updated to b4 k _{Matching link4} 。

The training method of the deep learning model is specifically described below.

Fig. 5 shows a flowchart of a training method of the deep learning model for predicting a road on which a vehicle is located according to an embodiment of the present disclosure.

As in fig. 5, step 501, the data is preprocessed. In the original training data, the distribution range of the feature values is greatly different due to the fact that the sources and the measurement units of each dimension feature are different, and when Euclidean distances between different samples are calculated, the feature with the large value range plays a leading role. Therefore, it is necessary to pre-process the samples, normalize each dimension feature to the same value interval, and eliminate the correlation between different features.

Step 502, a model is created. In the embodiment of the present specification, since the method of determining the road section on which the vehicle is located is specifically a classification problem, a model for classification may be created in step 502. In particular, a model that classifies based on a logistic regression method may be created.

In step 503, a layer of the model is added. Building a neural network and adding layers of the model.

Step 504, an optimizer and a loss function are selected. The optimizer is a loss function that updates the network weights so that the model is optimized at the time of network training, and specifically, a gradient optimization-based deep learning optimizer, such as SGD, momentum, adaGrad, adam, nesterov or RMSprop, etc., may be employed. After the model design is completed, the optimal value of the model needs to be found through training configuration, namely, the quality of the model is measured through a loss function.

Step 505, training a model. Inputting training data of a training data set, and verifying the data by using verification set data. The training data input may include parameters such as grade, curvature, direction, distance, etc.

Step 506, save the model. And saving the trained model into a model file, and directly loading the model file to run when the model file is applied.

In the embodiment of the present specification, map matching is performed according to a high-precision map, and it is possible to employ high-precision lane-level positioning information as initially input vehicle travel information, and provide lane connection information or the like so that the priori property of the high-precision map is fully represented. Based on the method, the HMM model and the viterbi algorithm are adopted, so that the change state of the vehicle positioning point is more comprehensively considered, and the determined vehicle positioning road section is closer to the actual running condition of the vehicle. The calculation accuracy of the HMM model can be further improved based on the lane connection information and the road section connection information of the high-precision map.

Further, aiming at the abnormal situation that the deviation between the road section direction of the map and the actual road direction is large due to the drawing defect in the map, special learning is performed by adopting a logistic regression method, the drawing defect of the road section direction of the map is avoided, and the accuracy of the judging result of the road section where the vehicle is located can be further improved under the situation. In addition, in practical application, most of common cases do not need a deep learning model to participate in weight calculation, so that the occupancy rate of calculation resources is not high. The high-precision map is taken as an important component of automatic driving, accurate map information and high-precision positioning form an indispensable ring of automatic driving, so that map matching provides correct map information, and providing correct matching road section information enables automatic driving decisions to make more accurate judgment, and the priori and accuracy of the high-precision map are fully reflected.

Based on the same thought, the embodiment of the specification also provides a device corresponding to the method.

Fig. 6 is a schematic structural diagram of a device for determining a road section on which a vehicle is located, corresponding to fig. 1, according to an embodiment of the present disclosure. As shown in fig. 6, the apparatus may include:

An information obtaining module 602, configured to obtain vehicle running information of a target vehicle at a first time; the vehicle travel information includes at least one of latitude and longitude information and travel direction information;

an alternative matching road segment determining module 604, configured to determine, based on the vehicle driving information, an alternative matching road segment set of the target vehicle in map data at the first moment;

a matching degree information determining module 606, configured to determine, for each road segment in the candidate matching road segment set, first matching degree information of the target vehicle and each road segment at the first moment;

a matching probability determining module 608, configured to determine a matching probability of the target vehicle and each road segment based on first matching degree information of the target vehicle and each road segment at the first moment;

and the road section determining module 610 is configured to determine a road section corresponding to the maximum matching probability as a road section where the target vehicle is located.

It will be appreciated that each of the modules described above refers to a computer program or program segment for performing one or more particular functions. Furthermore, the distinction of the above-described modules does not represent that the actual program code must also be separate.

Based on the same thought, the embodiment of the specification also provides equipment corresponding to the method.

In an alternative embodiment of the present disclosure, a fusion positioning module is provided, where the fusion positioning module may include a device for determining a road section where a vehicle is located as shown in fig. 6, where the device for determining a road section where a vehicle is located is used to determine a road section position of the vehicle in a high-precision map, and assist in performing cross-validation with other sensor data of the vehicle, so as to implement high-precision fusion positioning, and obtain an accurate position of the vehicle; the other vehicle sensors include at least one of inertial navigation, GNSS/RTK, vision and lidar.

Based on the same thought, the embodiment of the specification also provides a high-precision map engine corresponding to the method, the device and the equipment.

As shown in fig. 7, the high-precision map engine 700 may include:

a fusion location module 701 including a device for determining a road section on which a vehicle is located as shown in fig. 6;

the electronic horizon module 702 is configured to receive external high-definition vehicle position information and match the external high-definition vehicle position information to a map, and provide a functional interface for an autopilot application to perform rule judgment;

And at least one of an autopilot design run domain determination module 703, a map update module 704, a crowd-sourced preprocessing and backhaul module 705, a path cross-correlation module 706, and a lane-level path planning module 707.

Wherein, the autopilot design operation domain judging module 703 is configured to configure an autopilot area and judge a requirement;

the map updating module 704 is configured to obtain map data updating information of a high-precision map based on a vehicle position and a planned path;

the crowd-sourced preprocessing and returning module 705 is configured to return the cloud and update the map data center by preprocessing such as screening and fusing the UGC visual vector data;

the path cross-correlation module 706 is configured to synchronize a global path planning result initiated by a user to an autopilot system, and obtain a matching path of a navigation path on a high-precision map by cross-correlating with the high-precision map;

the lane-level path planning module 707 is configured to output a lane level and a local path plan within a certain length range in front of the vehicle according to the results of the navigation path matching and the route correction.

The foregoing describes particular embodiments of the present disclosure, and in some cases, acts or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are referred to each other.

The apparatus, the device, and the method provided in the embodiments of the present disclosure correspond to each other, and therefore, the apparatus, the device, and the method also have similar beneficial technical effects as those of the corresponding method, and since the beneficial technical effects of the method have been described in detail above, the beneficial technical effects of the corresponding apparatus, device are not described here again.

For convenience of description, the above devices are described as being functionally divided into various units, respectively. Of course, the functions of each element may be implemented in one or more software and/or hardware elements when implemented in the present application.

It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

It should also be noted that 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 one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises the element.

The application may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The application may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.

The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and changes may be made to the present application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc. which are within the spirit and principles of the present application are intended to be included within the scope of the claims of the present application.

Claims

1. A method of determining a road segment in which a vehicle is located, the method comprising:

acquiring vehicle running information of a target vehicle at a first moment; the vehicle travel information includes at least one of latitude and longitude information and travel direction information;

determining an alternative matched road segment set of the target vehicle in map data at the first moment based on the vehicle running information;

for each road section in the candidate matching road section set, determining first matching degree information of the target vehicle and each road section at the first moment;

determining the matching probability of the target vehicle and each road section based on first matching degree information of the target vehicle and each road section at the first moment;

and determining the road section corresponding to the maximum value of the matching probability as the road section where the target vehicle is located.

2. The method of claim 1, wherein the determining, for each road segment in the candidate matching road segment set, the first matching degree information of the target vehicle and each road segment at the first moment specifically includes:

and calculating transition probability and measurement probability of the target vehicle, and determining first matching degree information of the target vehicle and the target road segments in the candidate matching road segment set based on the transition probability and the measurement probability.

3. The method according to claim 2, wherein the calculating the transition probability and the measurement probability of the target vehicle, and determining the first matching degree information of the target vehicle and the target road segments in the candidate matching road segment set based on the transition probability and the measurement probability, specifically comprises:

for a target road segment in the candidate matching road segment set, determining the transition probability based on the vehicle running information of the target vehicle at the first moment and the vehicle running information of the target vehicle at the last moment;

for the target road segment, determining the measurement probability based on vehicle driving information of the target vehicle at the first moment and road segment attribute information of the target road segment in the map data;

And determining first matching degree information of the target vehicle and the target road section based on the transition probability and the measurement probability.

4. The method according to claim 2, wherein the vehicle driving information comprises longitude and latitude information, and calculating the transition probability of the target vehicle comprises:

calculating the position change quantity of the target vehicle from the last moment to the first moment based on the longitude and latitude information of the target vehicle at the first moment and the longitude and latitude information of the target vehicle at the last moment;

determining a transition probability of the target vehicle from a previous time to the first time based on the position change amount; the transition probability is inversely related to the amount of change in position.

5. The method according to claim 2, wherein the vehicle travel information includes latitude and longitude information and travel direction information, and calculating the measurement probability of the target vehicle includes:

calculating the distance between the target vehicle and the target road section at the first moment based on the longitude and latitude information of the target vehicle at the first moment;

determining a first probability associated with the distance based on the distance; the first probability is inversely related to the distance;

Calculating an angle difference value between the vehicle running direction of the target vehicle at the first moment and the extending direction of the target road section;

determining a second probability associated with the angle difference based on the angle difference; the second probability is inversely related to the angle difference;

calculating a measurement probability based on the first probability and the second probability; the measurement probability is positively correlated with the first probability and the measurement probability is positively correlated with the second probability.

6. The method of claim 1, wherein the determining the probability of matching the target vehicle with each road segment based on the first matching degree information of the target vehicle with each road segment at the first time further comprises:

judging whether the target road section is an associated road section of the road section where the target vehicle is located at the last moment or not according to the target road sections in the candidate matching road section set, and obtaining an associated road section judging result;

the determining, based on the first matching degree information of the target vehicle and the road sections at the first moment, the matching probability of the target vehicle and the road sections specifically includes:

if the associated road section judging result indicates that the target road section is the associated road section of the road section where the target vehicle is located at the last moment, acquiring a preset associated road section weight coefficient;

And determining the matching probability of the target vehicle and the target road section based on the first matching degree information of the target road section and the weight coefficient of the associated road section.

7. The method of claim 1, wherein the determining the probability of matching the target vehicle with each road segment based on the first matching degree information of the target vehicle with each road segment at the first time further comprises:

judging whether the current scene of the target vehicle is a preset specific scene or not;

if the current scene of the target vehicle is a preset specific scene, calculating the model probability corresponding to each road section in the alternative matching road section set by adopting a pre-trained deep learning model corresponding to the preset specific scene; the deep learning model is trained based on vehicle real-time data in the preset specific scene, wherein the vehicle real-time data comprise vehicle running information and corresponding vehicle real-time section information in a data map;

determining model weight coefficients corresponding to the road sections according to the model probabilities corresponding to the road sections;

And determining the matching probability of the target vehicle and each road section based on the first matching degree information of the target road section and the model weight coefficient.

8. The method of claim 1, wherein the determining the matching probability of the target vehicle and each road segment based on the first matching degree information of the target vehicle and each road segment at the first moment specifically includes:

acquiring second matching degree information of the target vehicle and each road section at the last moment;

and determining the matching probability of the target vehicle and each road section based on the first matching degree information and the second matching degree information.

9. The method of claim 1, the vehicle travel information comprising latitude and longitude information; the determining, based on the vehicle driving information, the candidate matching road segment set of the target vehicle in the map data at the first moment specifically includes:

determining the projection position of the target vehicle relative to each map road section based on the longitude and latitude information of the target vehicle;

if the projection position is positioned on the map road section, calculating a projection distance between the target vehicle and the projection position;

And if the projection distance is smaller than a preset distance threshold value, determining the map road section as a road section in the alternative matching road section set.

10. The method of claim 9, the vehicle travel information further comprising travel direction information; before the map road segment is determined to be the road segment in the candidate matching road segment set, the method further comprises:

determining an angle difference between the vehicle traveling direction and the extending direction of each map section based on the traveling direction information of the target vehicle;

the determining the map road section as the road section in the candidate matching road section set specifically comprises:

and if the angle difference value is smaller than a preset angle threshold value, determining the map road section as a road section in the alternative matching road section set.

11. An apparatus for determining a road segment on which a vehicle is located, the apparatus comprising:

12. The fusion positioning module comprises the device for determining the road section where the vehicle is located according to claim 11, wherein the device for determining the road section where the vehicle is located is used for determining the road section position of the vehicle in a high-precision map, assisting in cross verification with other sensor data of the vehicle, and realizing high-precision fusion positioning to obtain the accurate position of the vehicle; the other vehicle sensors include at least one of inertial navigation, GNSS/RTK, vision and lidar.

13. A high precision map engine, comprising:

the fusion locator module of claim 12;