EP3631364A1 - Method and apparatus for producing a lane-accurate road map - Google Patents

Abstract

A method for producing a lane-accurate road map (22) is proposed. The method has a step of providing a digital lane-accurate road map (14), a step of providing a trajectory data record (16) and a step of identifying at least one road (17) while segmenting the lane-accurate road map (14) into at least one road segment (26). Further, the method has a step of modelling the road segment (26) in at least one road model (28), wherein the road model (28) has parameters (L, W, G, C) for describing lanes (23) of the road (17). Further, the method has a step of randomly varying parameter values of at least some of the parameters (L, W, G, C) of the road model (28) by randomly selecting a change operation (40, 41, 42, 43, 44, 46, 48, 50) of the road model (28) and a step of assigning at least some of the trajectory data (27) of the trajectory data record (16) to the road model (28) while ascertaining at least one probability value for the road model (28). Based on the ascertained at least one probability value, optimum parameter values of the road model (28) are ascertained and, based thereon, a lane-accurate road map (22) is produced that can be distinguished in particular by a high level of accuracy.

Description

 Description title

 Method and device for creating a lane-accurate road map Field of the invention

The present invention relates generally to the creation of road maps. In particular, the present invention relates to a method and a

Data processing device for creating a digital lane-accurate road map.

State of the art

In particular with regard to an automated and / or autonomous driving of vehicles, various methods for creating digital road maps have been developed in the past.

For example, in a paper by Uruwaragoda et al., 2013, "Generating Lane Level Road Data from Vehicle Trajectories Using Kernel Density Estinnation", Proceedings of the 16th International I EEE Annual Conference on Intelligent Transportation Systems (ITSC 2013), 201, is a procedure To estimate a number and a width of lanes on roads, for this purpose, the centerline of the road is cut at discrete intervals at right angles from a roadway-specific roadmap.The intersections with trajectories of vehicles on the road are calculated for each of these perpendiculars and a kernel density estimate is carried out in each case Thus, support points along the road are generated, which contain information about a number of lanes and a track width and can be finally linked.

In a work by Schroedel et al., "Mining GPS Traces for Map Refinement," Data Mining and Knowledge Discovery, 2004, 9, information about a number of lanes and a lane width without map pre-knowledge is derived by an algorithm first segmenting the trajectories of vehicles and the midline is identified

Categorized distances to the trajectories of the vehicles with density estimation method in order to be able to make statements about the lanes. In Betaille et al., "Creating Enhanced Maps for Lane-Level Vehicle Navigation," a model-based approach is pursued in which clothoid-described models are measured on measured vehicle trajectory data be adjusted.

Disclosure of the invention

Embodiments of the invention may advantageously provide an improved method of creating a detailed and accurate one

lane-accurate road map and a corresponding

Data processing device can be provided.

One aspect of the invention relates to a method for creating and / or

Generation of a lane-accurate road map, in particular a digital lane-accurate road map. The method has the following steps:

 Provide a digital road-accurate road map to

 Description of a road course of at least one road;

 - Providing a trajectory data set, which a plurality of

Trajektoriendaten of road users along the at least one road has;

 Identify and / or determine the at least one road by segmenting, splitting and / or dividing the roadway accurate

 Road map in at least one road segment;

 Modeling the road segment in at least one road model, the road model having a plurality of parameters for geometrically and / or topologically describing lanes of the road; randomly varying and / or changing, in particular multiple randomly varying and / or altering, parameter values of at least a portion of the parameters of the road model by randomly selecting a change operation of the road model to change

 Parameter values;

 Assign at least a portion of the trajectory data of the

Trajektoreindatensatzes to the road model by determining at least one probability value for the road model, wherein the probability value with a quality and / or quality of an image, Replica and / or imitation of the trajectory data by the

 Street model correlated;

 Determining, based on the determined at least one

 Probability value of optimal parameter values of at least a part of the parameters of the road model; and

 Create a lane-accurate road map based on the optimal parameter values of the road model.

The "digital lane-exact road map" may here and hereinafter designate a road map which contains only information regarding a roadway and / or a lane, but no information regarding individual lanes on the lane.For example, the lane-exact road map may have one or more nodes and edges , where an edge may be used to represent a road and / or a road section and a node to represent an intersection., Likewise, the roadway may denote a graph with nodes and edges, where the edges may be arrows and the nodes may be points in the graph and / or the road-specific road map given and / or displayed.

The term "lane-accurate road map" may designate a digital road map and / or graph having information regarding individual lanes. "The lane-exact road map may in particular have information regarding a geometry of individual lanes, such as a lane width, a lane number, a distance between lanes The direction of travel and / or a curvature of a road and / or a road section may be considered and / or included in at least part of the "parameters for geometrically describing lanes of the road". Similarly, the "geometric description parameters" may include parameters for describing a number of lanes, a width of individual lanes, a curvature of a road or individual lanes, and / or a distance between lanes of opposite direction of travel

Containing information regarding a topology of the lanes, wherein the topology may describe a connection path, a connection and / or a connectivity between individual lanes. This topological Information can be considered and / or contained in at least part of the "parameters for the topological description of lanes of the road"

Description of lanes of the road "Parameter describing a link, a connection, a connectivity between individual

Lanes, a disappearance of individual lanes in the road segment and / or generating an additional lane in the road segment. The term "trajectory data" may refer to geographic coordinates, such as Global Positioning System (GPS) coordinates and / or Global Navigation Satellite System (GNSS) data, which may include a trajectory, a motion profile, a driveway, and / or a Movement of one

Road user, such as a vehicle, a bicycle and / or a pedestrian, describe along a road and / or at an intersection.

Similarly, the term "trajectory data set" may refer to a set of such trajectory data of one or more road users.

Further, the term "modeling the road segment in at least one road model" may include mapping, replicating, imitating, and / or modeling

Imitate the road segment in the at least one road model. In this case, the road model can designate a mathematical and / or model-based abstraction and / or description of the road segment.

The process according to the invention is summarized below. The lane-exact road map, for example, in a

Data processing device from a data memory of

Data processing device can be read. It can the

road-specific road map one or more nodes and / or one or more edges for the geographical description of one or more roads and / or one or more intersections. Providing the lane-exact road map can thus include reading the lane-exact road map and / or reading the at least one edge and / or the at least one node. The lane-exact road map can then be analyzed, for example based on the at least one node and / or the at least one edge, and in at least one Road segment divided and / or segmented. In particular, the lane-exact road map may have a plurality of roads, which may each be subdivided into individual road segments, for example based on the nodes and / or edges. In other words, roads and / or the at least one road may be identified based on the nodes and / or edges. Subsequently, each of the identified

Road segments are mapped, modeled, simulated and / or imitated in a separate street model. After that, for each of the

Road models, which may each be assigned to a road segment, at least a part of the parameters of the respective road model varies and / or changed. In particular, the parameters of each road model can be varied iteratively multiple times, with parameters

different road models at the same time or in a time sequence can be varied sequentially. The parameter values can be varied independently of the trajectory data. Furthermore, the

Trajektoriendaten to the respective road models, for example, based on geographical coordinates of the trajectory data and / or the

lane-exact road map, be assigned. It can be determined which of the trajectory data in one of the road segments

are arranged so that based on the individual

 Road models associated trajectory data can be determined.

In particular, the step of modeling in the road model may occur prior to the step of associating the trajectory data with the road model. Subsequently, it can be checked how well the trajectory data are imitated and / or simulated by the respective road models, whereby a probability value can be determined for each of the road models as a measure of the quality and / or quality of such a map. Likewise, the

Probability in the context of the invention, a measure of a quality and / or quality of imaging, replica and / or imitation of the trajectory data by the corresponding road model denote. In particular, for each of the road models, a plurality of probability values may be obtained by multiple independently varying a portion of the parameters each

Road model are determined. From the likelihood values determined for each of the road models, at least one high and / or one highest likelihood value can be selected in each case in comparison with other likelihood values of the same road model, which thus corresponds to an optimum configuration of the associated road model and / or the optimal parameter values of the associated road model. Furthermore, in the context of identifying the highest

Probable value the so-called simulated annealing method are used. This may cause change operations that deteriorate a correspondence between the road model and trajectory data to be accepted less frequently as the time of the optimization process progresses, and / or that the optimization of the road model may occur directly in the optimal parameter values of the road model, i. the most likely and / or best street model ends. Ultimately, therefore, the

Probability values as well as the parameter values of the individual

 Road models are optimized iteratively. The optimal parameter values of the individual road models can be selected and / or selected and can thus represent a lane-accurate road map and / or

represent. In other words, the lane-exact road map may be given by the optimal parameters of the at least one road model.

The method according to the invention can thus provide that one or more road segments are imaged in one or more road models, and subsequently the optimal parameter values of the one road model or the road models are determined iteratively.

The method according to the invention can therefore be model-based

Designate an optimization method, based on which can be derived and / or determined from motion profiles, trajectory data and / or driving trajectories of one or more road users an accurate topological and geometric road map of a busy road network in an advantageous manner. In particular, a number, a course, a width, a distance and / or a connectivity of individual lanes can be determined with high precision. This can be for straight road segments,

Curve segments and / or done for crossing segments.

In particular, the invention may be considered to be based upon the findings described below. With the availability of connectivity solutions in many production vehicles and / or smartphone applications, countless movement profiles and / or trajectory data of vehicles and / or road users can already be detected today. This can thus represent a data source which can be simple, inexpensive and available at an early stage. At the same time wins the Nationwide accurate mapping of the road network worldwide in the context of automatic driving is becoming increasingly important. The method according to the invention can therefore advantageously permit an exact mapping of a road network based on an analysis of known movement profiles, trajectory data and / or driving trajectories, for example a large vehicle fleet. For example, in comparison to a mapping by highly specialized measuring vehicles, as is often done by traditional card manufacturers, those for the inventive method

used trajectories are cost-effective, simple and provided in large quantities, so that a cost-effective, fast, nationwide and accurate mapping of a road network can be made.

According to one embodiment, the optimal parameter values are determined based on a Monte Carlo method, in particular based on a Reversible Jump Markov Chain Monte Carlo method (RJMCMC). In particular, randomly selecting a change operation to randomly vary the parameter values of at least a portion of the parameters of the road model based on the Monte Carlo method and / or the Reversible Jump Markov Chain Monte Carlo method. In this case, all or at least a part of the change operations can be assumed to be equally distributed and, based on a random number, one of the change operations can be assumed to be random

Variation of at least a portion of the parameter values is selected, i. to be diced, as it were. After randomly selecting a change operation, this change operation may be performed and then it may be decided whether the change in the parameter values caused thereby is accepted or discarded. In the course of the RJMCMC method, input data, such as the trajectory data, may be generally considered to be a random experiment implementation, where a distribution of the input data may be implied by the underlying road network and / or road model. The aim of the RJMCMC method can be the unknown

Distribution, such as the actual road network, using the road model to reconstruct. In this case, the road model and / or the parameter values of the road model can be varied randomly and / or independently of the trajectory data. Subsequently, depending on the determined

Probability value and / or depending on the height of the determined

Probably the associated parameter values or the change of the parameter values are rejected or accepted, for example based on a comparison with a threshold and / or based on a

Rating metrics. Also, in the course of identifying the optimal

Parameter values are a simulated annealing method used.

According to one embodiment, the road model has at least one road block for modeling at least one partial area of the road block

Road segments constant number of lanes on. Alternatively or additionally, the road model has at least one connection block for modeling, based on at least one geometric parameter matrix and at least one topological parameter matrix, of a number of lanes changing at least in a subarea of the road segment, wherein values of the geometric parameter matrix are a change of a

Describe lane numbers within the road segment, and where values of the topological parameter matrix describe a connection between individual lanes within the road segment. In other words, it may be provided to model each identified road segment by at least one road block and a connection block of the road model. In particular, it may be provided, each identified

Road segment by a arranged between two connection blocks road block to model. By using one road block in each road segment, which models a constant lane number, advantageously a computational effort can be reduced. Furthermore, by using at least one connection block per road segment, flexibility of the road model may be increased, as any changes in geometry and / or topology of two adjacent ones

Road segments can be reliably and comprehensively modeled and / or taken into account in the connection block. In this case, the connection block can each have one geometric and one topological parameter matrix for each

Direction of travel of a roadway. In other words, the

Connecting block over two geometric and two topological

Parameter matrices for modeling a geometry and / or topology of lanes have different direction of travel.

According to one embodiment, the step of modeling the

Road segments in the road model, the following sub-steps: Parameterizing the road segment in a unit interval such that each point of the road in the road segment passes over one

 Parameterization value is set in the unit interval;

 Segmenting and / or dividing the road segment into at least one road block and at least one connection block of the road segment

 Road model;

 Modeling, emulating and / or imitating a disappearance or generation of a traffic lane within the road segment based on at least one geometric parameter matrix of the road

 Connecting block;

 Modeling, replicating, and / or mimicking a connection of individual lanes within the road segment based on at least one topological parameter matrix of the connection block; and

 Determine values of the geometric parameter matrix and / or values of the topological parameter matrix based on a random one

Selection of a modification operation of the road model.

In this case, the step of parameterizing may comprise a step of determining a length and / or a longitudinal extent of the road segment and a step of normalizing to the determined length. In other words, each road segment can be parameterized one-dimensionally, whereby advantageously each point of the road segment is represented by a value between zero and one, i. by a value of the unit interval.

In one embodiment, the digital roadway-specific roadmap has at least one intersection and a plurality of the intersection

connected roads, the method further comprising the following steps:

Identifying the at least one intersection while segmenting and / or dividing the lane-exact road map into at least one

 Crossover segment;

 Modeling, mapping, emulating and / or imitating the

 Junction segment in at least one crossing model, wherein the

Junction model a plurality of parameters to geometric and / or topological description of lanes of the intersection;

 randomly varying and / or changing, in particular multiple randomly varying, parameter values of at least a part of the parameters of the crossing model by randomly selecting one

Change operation of the intersection model to change from

 Parameter values;

 Assign at least a portion of the trajectory data of the

 Trajectory data set to the intersection model, determining at least one probability value for the intersection model, wherein the probability value correlates with a quality and / or a quality of an image of the trajectory data by the intersection model;

 Determining, based on the determined at least one

 Probability value of optimal parameter values of at least one

Part of the parameters of the crossing model; and

 Create a lane-accurate road map based on the optimal parameter values of the intersection model. According to the invention can therefore be provided, each road segment of the roadway accurate road map by a road model and each

Intersection segment to model by a crossing model. As a result, the individual properties of intersections and roads can be modeled in an advantageous manner, and a computational effort can be reduced.

In addition, this can be a precision and / or accuracy of the created

increase lane-accurate road map. In this case, an intersection in the lane-exact road map can be identified, for example, by identifying a node connected with more than two edges. According to one embodiment, the crossing model has an outer one

 A crossing model for modeling a trafficable area of the intersection based on a distance parameter (d) and an angle parameter (a). Alternatively or additionally, the step of modeling the

Junction segments in the intersection model, the following sub-steps: - Means in an intersection node in the lane-exact road map, such as based on determining a node connected with more than two edges in the lane-exact road map; Determining a number of edges of the lane-exact road map associated with the intersection node by determining a number of roads connected to the intersection, the number of edges determined corresponding to the number of roads connected to the intersection; Generate and / or generate one of the number with the intersection

 connected streets corresponding number of crossing arms, each of the crossing arms by a distance parameter (d) for indicating a distance of a center of the intersection to a

 Defined boundary surface of the intersection along the respective crossing arm, and wherein each of the crossing arms by a

 Angular parameter (a) for indicating a rotation angle between the respective crossing arm and a reference direction, for example, a reference crossing arm is defined.

By the outer crossing model can advantageously a

Connection cross section between the crossing arms and the it

connected streets accurately modeled and / or matched, for example, in terms of a number of lanes, a width of lanes, a distance between lanes of opposite

Driving direction and / or a curvature.

According to one embodiment, the crossing model has an interior

A crossing model for modeling, based on a factor matrix (F) of the intersection model, intersection lanes, intersection lanes, and lane layout over a drivable area of the intersection. Alternatively or additionally, the

Step of modeling the intersection segment in the intersection model, the following substeps:

Modeling, replicating, mapping, and / or mimicking at least a portion of lanes entering the intersection, at least a portion of lane exiting the intersection, and a lane of at least a portion of lanes crossing an intersection of the intersection based on a factor matrix (F); where values of

 Factor matrix (F) describe a course and a connection of lanes on the crossing surface; and

Determining values of the factor matrix (F) based on at least a portion of the trajectory data of the trajectory data set. By means of the inner intersection model, it is advantageously possible to precisely model each possible connection of individual lanes via the intersection area. Furthermore, by determining the values of the factor matrix based on the trajectory data, a number of possible connections of the lanes via the intersection and thus a computation effort can be reduced, since the

Trajectory data always actual and realistic connections of the

Represent lanes and / or represent. According to one embodiment, the road model and / or a

 Junction model each have a number parameter (L) for describing a number of lanes, a width parameter (W) for describing a width of individual lanes, a curvature parameter (C) for describing a curvature of a road and a distance parameter (G)

Description of a distance between lanes of opposite

 Driving direction. The parameters mentioned above can be parameters of an inner intersection model and / or an outer intersection model of the intersection model. Also, the above parameters can be parameters of a road block and / or a connection block of the

Be street model. The distance between lanes of opposite

Driving direction can describe about a structural separation between adjacent lanes of opposite direction of travel. By above-listed parameters of the road model and / or the intersection model can be ensured in an advantageous manner that roads and / or

Intersections can be precisely modeled and thus accurate

lane-exact road map can be created.

According to one embodiment, the road model and / or a

Intersection model at least one change operation selected from the list consisting of an insertion operation for inserting a connection block into a road block, a merging operation for merging two road blocks and a connection block to a road block, a fitting operation for adjusting a parameterization value for parameterizing a longitudinal extension of a road; an add operation for adding a traffic lane, a removal operation for removing one

Lane, a distance adjustment operation for adjusting a distance between lanes of opposite direction of travel, a A width adjustment operation for adjusting a width of a lane and a curvature adjustment operation for adjusting a curvature of a road in the road model, a road block, and / or a connection block of the road model. By means of the above listed

Change operations may advantageously have the parameter values of all and / or at least a majority of the parameters of the

Road model and / or the crossing model can be varied by random selection of one of the change operations. Furthermore, the

Change operations reliably map all conceivable and realistic changes in a real road network, which in turn can allow to create a precise and realistic lane-exact road map.

According to an embodiment, the method further comprises a step of discarding or accepting randomly selected parameter values based on randomly selecting a change operation based on a

Evaluation metric, which describes the quality of the mapping of the trajectory data by the road model and / or an intersection model. The valuation metric has a first term for describing a

Agreement between the trajectory data and the road model and / or a crossing model. Furthermore, the evaluation metric has a second term for taking into account at least one predetermined parameter of a road geometry, in particular a parameter with respect to one

Lane width and / or a road width, on. For example, for a parameter, there may be a stochastic specification with respect to the values of the parameter, which can predetermine the dimension of the parameter.

 For example, a track width can be determined by means of a normal distribution, so that a track width in the vicinity of approximately 3.25 m is to be searched. Thus, it can be avoided that track widths of e.g. 6 m to be examined. Therefore, any prior knowledge about a road geometry and / or a crossing geometry can advantageously be taken into account via the evaluation metric. For example, in the valuation metric

Building standards and / or building guidelines for road construction are taken into account. This can be ensured in particular that realistic lane-exact road maps can be created by the inventive method. Also, a computing time can be reduced. Another aspect of the invention relates to a data processing apparatus for determining a lane-accurate road map based on a digital road-accurate road map. In this case, the data processing device is adapted to the method as above and below

described to execute. Here, the term "be set up" mean that the data processing device, for example via a

Program element has, which in its execution, for example on a processor of the data processing device, the data processing device instructs to carry out the inventive method. For example, the program element may have corresponding software instructions.

All the features, steps, functions and / or characteristics described above and below in relation to the method according to the invention can be features, functions and / or characteristics of the data processing device as described above and below, and vice versa.

According to one embodiment, the data processing device has a data memory for storing a digital roadway-specific road map and a processor. On the data memory can also be a

Program element to be stored, which when executed on the processor, the data processing device instructs to carry out the inventive method.

Brief description of the drawings

Embodiments of the invention will now be described in detail with reference to the accompanying drawings.

Fig. 1 shows a data processing apparatus according to a

Embodiment of the invention.

FIG. 2 is a flow chart illustrating steps of a method of creating a lane-accurate road map according to FIG

Embodiment of the invention. FIGS. 3A to 3D each illustrate a method of creating a

road-accurate road map.

4A to 4C each illustrate steps of a method for creating a lane-accurate road map according to an embodiment of the invention.

Figs. 5A to 5C each illustrate a road model according to one

Embodiment of the invention. FIGS. 6A to 6D each illustrate a crossing model according to one

 Embodiment of the invention.

Figs. 7A to 7E respectively illustrate change operations according to one

Embodiment of the invention.

FIGS. 8A and 8B each illustrate an application of a score metric according to one embodiment of the invention.

The figures are only schematic and not to scale. In the figures are the same, the same or similar elements with the same

 Provided with reference numerals.

EMBODIMENTS OF THE INVENTION FIG. 1 shows a data processing device 10 according to a

 Embodiment of the invention.

The data processing device 10 has a data memory 12. For example, in the data memory 12, there may be deposited a roadway-compliant road map 14 which includes at least one node 11 (see, e.g., Figures 3C and 3D) and / or an edge 13 (see, e.g., Figures 3C and 3D) for describing

Street road 17 (see Fig. 4A) and / or an intersection 19 (see Fig. 4A) may have. In particular, the roadway-accurate road map 14 may include a plurality of nodes 11 and / or edges 13 for

Description of a road network with several streets 17 and / or

Have intersections 19. Also, in the data memory 12 a Trajektonendatensatz be deposited 16, which a plurality of

Trajektoriendaten 27 (see Fig. 3B) of road users may have.

Alternatively or additionally, the data processing device 10 may have an interface 15 via which the lane-specific road map 14 and / or the trajectory data record 16 of the data processing device 10 can be provided. The interface 15 may be carried out wirelessly, for example, so that the road-specific road map 14 and / or the

Trajektonendatensatz 16 can be received wirelessly, for example via WLAN, Bluetooth server and / or the like, for example, from at least one server and / or a cloud environment.

Furthermore, the data processing device 10 has at least one processor 18. On the processor 18, a stored approximately in the data memory 12 program element can be executed, which the

 Data processing device 10 and / or the processor 18 instructs to carry out the inventive method for creating a lane-accurate road map 22, as described above and below. Optionally, the data processing device 10 via an operating element 20 for inputting an operator input, such as by a user, have. The control element may also have a display element 21 for displaying the

roadway accurate road map 14, the lane exact road map 22 and / or the trajectory data set 16 have.

FIG. 2 is a flowchart illustrating steps of a method of creating a lane-accurate road map 22 according to one

Embodiment of the invention. In a first step S1, a digital roadway-accurate road map 14 is provided for describing a road course of at least one road 17 and / or at least one intersection 19, for example via the

Data memory 12 and / or via the interface 15 of

Data processing device 10. In particular, the roadway-compliant road map 14 may include a plurality of roads 17 and intersections 19.

Further, in step S1, a trajectory data set 16 is provided, which includes a plurality of trajectory data 27 of road users along the at least one road 17 and / or the at least one intersection 19 has. The trajectory data record 16 can also be provided via the data memory 12 and / or via the interface 15 of the data processing device 10.

In a step S2, the at least one road 17 is identified by segmenting the roadway-compliant road map 14 into at least one road segment 26 (see FIG. 4C). This can be done based on the node 1 1 and / or edges 13 of the roadway accurate road map 14. Optionally, in step S2, at least one intersection 19 may be segmented to segment the lane

 Road map 14 in at least one crossing segment 19 a done.

More specifically, in step S2, the road-by-road road map 14 may be divided into a plurality of road segments 26 and a plurality of crossing segments 19a.

In a further step S3, the at least one road segment 26 is modeled in at least one road model 28 (see FIGS. 5A, 5B). In particular, in step S2 all road segments 26 can each be modeled in a road model 28. In addition, in step S3, the at least one intersection 19 in a crossing model 34 (see FIGS. 6A-6C) can be modeled. In particular, each of the intersections 19 can be modeled in a separate intersection model 34. In this case, each of the road models 28 and / or each of the

Junction models 34 a plurality of parameters for the geometric and / or topological description of lanes 23 on.

In a further step S4, parameter values of at least part of the parameters of the road model 28 and / or the intersection model 34 are obtained by randomly selecting a change operation 40, 41, 42, 43, 44, 46, 48, 50 (see FIGS. 7A-7E) Road model 28 and / or the crossing model 34 varies. In particular, in step S4, the parameter values of all

 Road models 28 and all crossing models 34 are iteratively and repeatedly varied.

In a further step S5, at least part of the trajectory data 27 of the trajectory data record 16 is assigned to the road model 28 while determining at least one probability value for the road model 28.

More specifically, in step S5, the trajectory data 27 may be added to each of the Road models 28, each determining at least one

Probability value for each of the road models 28 are assigned. Further, in step S5, the trajectory data 27 may be assigned to the at least one intersection model 34 by determining at least one probability value in step S5, the trajectory data 27 to each of

Crossing models 34, each determining at least one

Probability value for each of the crossing models 34 are assigned. The probability values correlate with a quality of an image of the trajectory data 27 by the respective road model 28 and / or the respective intersection model 34.

In a step S6, optimal parameter values of at least part of the parameters of the road model 28 and / or the intersection model 34 are determined based on the determined at least one probability value. In particular, for each of the road models 28 and / or for each of the

Crossing models 34 optimal parameter values are determined.

In a step S7, a lane-accurate road map 22 is created based on the optimum parameter values of the at least one road model 28 and / or the at least one intersection model 34. In particular, the lane-exact road map 22 may be given by the optimal parameter values of all road models 28 and / or all intersection models 34.

FIGS. 3A to 3D each illustrate a method of creating a

Lane-precise roadmap 16. The roadway accurate

 Road map 16 may serve as the basis for creating a lane-accurate road map 22. Accordingly, all the steps described with reference to FIGS. 3A to 3D can also be part of the method according to the invention for creating a lane-accurate road map 22.

In FIG. 3A, trajectory data set 16 having a plurality of collected trajectory data 27 and / or trajectories 27 is illustrated. Further, FIG. 3A illustrates segmenting and / or splitting the trajectory data 27 into various traffic scenarios and / or segments 24a-c. Schematically, in FIG. 3A, a first segment 24a describing a curve, a second segment 24b describing an intersection, and a third segment representing a road describes, shown. The segments 24a-c are determined as described below.

The trajectory data 27 collected by a vehicle fleet, such as GNSS trajectories 27, can also be of any desired size in any number

Describe the traffic scenario. In order to make the dimension of the data to be evaluated tangible, the trajectories 27 can be automatically divided according to a logic. For this purpose, the trajectory data 27, which as

Input data can be divided into different traffic scenarios 24a-c and / or different segments 24a-c, where each of the

Segments 24a-c a straight road, a curve or an intersection

can describe.

In an automated method, each trajectory 27 can be traversed and based on limits in a travel angle change and / or a

Speed, individual measurement points can be identified as potential curve points. These points are thus either on a curve, an intersection or may be due to measurement errors come to pass. Subsequently, all identified points can be clustered, aggregated and / or summarized via distance limits. From a certain amount on

When combined, the cluster is considered a curve and / or intersection. Based on the found curves and / or

Intersections can then be triangulation and then a Delaunay decomposition constructed. Every cell of this decomposition can be a final one

describe independent traffic situation 24a-c and / or a segment 24a-c.

Likewise, the segments 24a-c can be considered as cells 24a-c of decomposition

be interpreted.

Based on a set of trajectory data 27, such as GNSS

Vehicle trajectories 27, a lane-exact road map 14 may be generated, which may correspond to a graph consisting of node 1 1 and edges 13, wherein the nodes 1 1 and edges 13 may represent a road centerline. Exemplary is such a roadway accurate

Road map 14 illustrated in FIG. 3D.

To create the roadway-accurate road map 14, first the input data 16, 27 can be segmented as described in FIG. 3A. For every Cell 24a-c may then be initialized with a graph which may describe the traffic scenario of the respective segment 24a-c or the respective cell 24a-c. The desired goal is that the models in the cells 24a-c, linked by boundary conditions, can be individually developed and finally fused into a graph. By way of example, the creation of a road-specific road map 14 in FIGS. 3B-3D for the

Road segment 24c shown in Fig. 3A. FIG. 3B shows a cell 24c or a segment 24c and the vehicle trajectories 27. FIG. 3C shows an initial road map 14 and FIG. 3D an optimized road map 14. The road maps 14 of FIGS. 3C and 3D can also be referred to as cell graphs 14 ,

For initialization, first all cell edges 25 can be cut with the trajectories 27 in order to determine the road centers on the cell edges 25, as shown in FIG. 3B. These centers can be included in the graphs of the corresponding cells 24c as nodes 11, as shown in Fig. 3C. In addition, in each cell 24c, the center of gravity of the cell 24c may be inserted as node 1 1 in the graph and connected by edges 13 to the nodes 1 1 on the cell edges 25. For linking the trajectory data 27 and the models or cell graphs, a valuation metric can be introduced, which describes how well the models map the data. On the one hand, the distance between the models and the trajectory data 27 and, on the other hand, the differences in the direction of travel can be taken into account. To optimize the models and create the final lane-exact roadmap 16 as shown in FIG

Reversible Jump Markov Chain Monte Carlo (RJMCMC) method can be used. In the process, the trajectory data 27 is regarded as the realization of a random experiment, the distribution of which is implied by the underlying road network. The aim of the method is to reconstruct the unknown distribution, in this case the road network. In doing so, the models are randomly varied independently of the trajectory data 27, and then a decision can be made about accepting or discarding the change based on the evaluation metric. The random variation of the models is done by the random selection of prescribed ones

Change operations. For example, there is a choice

 Moving operation, a generating operation, a removing operation, a

Split operation and / or merge operation. At the moving operation a node 1 1 of a cell graph 24c is moved in space. The create operation describes adding a new node 11 into the graph 24c and forms a reversible pair of operations with the remove operation. In the fusing operation, a node 1 1 is inserted into an adjacent edge 13, so that two closely adjacent edges 13 are unitized piecewise.

The splitting operation reverts such a construct and thus represents the opposite of the merging operation. The presence of reversible pairs may be advantageous for a correct stochastic description of the operation. As can be seen from a comparison of FIGS. 3C and 3D, the middle node 1 1 was removed during the optimization, since it is used for the

Description of the road 17 is not required.

FIGS. 4A to 4C respectively illustrate steps of a method for creating a lane-accurate road map 22 according to an embodiment of the invention. Specifically, in FIG. 4A, a roadway-accurate road map 14 is shown. Fig. 4B illustrates a parameterization, and Fig. 4C illustrates a segmentation of road 17 of the road map 14. Further, Figs. 5A to 5C respectively show

Road model 28 according to an embodiment of the invention. in the

Specifically, Fig. 5A shows a connection block 30 of the road model 28, Fig. 5B shows a road block 32 of the road model 28, and Fig. 5C shows geometric and topological parameter matrices of the connection block 30 of Fig. 5A.

FIG. 4A shows a road-grade graph 14 and / or a lane-exact road map 14, which includes a road 17 and at the ends a respective one

 Junction 19 by means of nodes 11 and edges 13 describes. In order to convert the road 17 into a lane-exact road map 22, the road 17 is first parameterized one-dimensionally. Thus, as shown in FIG. 4B, each point p of the road 17 may have a value p e [0; 1] of the unit interval.

Based on this parameterization, road segments 26, as shown in FIG. 4C, can be defined. In other words, the road 17 is subdivided into one or more road segments 26, which may be identified based on the nodes 11 and / or edges 13, for example. The segmentation of the road 17 into road segments 26 may allow lane-level traffic situations in the road model 28

as illustrated in FIGS. 5A to 5C. In this case, the driving on a constant number of lanes 23 and the widening or narrowing of the road 17 is distinguished by a lane 23.

A general road block 32 as shown in Fig. 5B may have a number parameter L for describing a number of lanes 23, a width parameter W for describing a width of individual lanes 23, a curvature parameter C for describing a curvature of a road 17, and a distance parameter G for describing a distance between adjacent lanes 23 have opposite direction of travel. Also, the road block 28 may have a type parameter T for describing a type of lane marking for each lane 23. The parameter G can be a size of a structural separation between the

Describe opposite lanes 23.

A generic road block 32 may thus be sized

be defined.

A road 17 is thus defined as a set of m road segments 26

and their parameterization values P, which describe the longitudinal extent on the road 17 according to FIGS. 4A to 4C:

To represent a curved road segment 26, all

Connections of lanes 23 on the road segment 26 can be described by cubic Hermite polynomials. As a result, it is possible for a road segment 26 not only to have a constant curvature, but also to assume an arbitrary course, whereby only the boundary conditions of continuity and differentiability are adhered to in order to produce a realistic road course. The boundary conditions are introduced by specifying the connection points and the slope or the gradient vector in the connection points. In order to influence the course of the polynomials, the magnitude of the slope vectors is accessible or integrated as parameter C in the road model 28. A general road block 32, also referred to below as B _A , may be specified by further restrictions or additions. A road block 32 as shown in FIG. 5B includes the restriction that the number L of the lanes 23 in the respective road segment 26 remains constant. Thus, a road segment can be imaged on which only the inherent properties such as the track widths W change. In FIG. 5B, the lanes 23 are marked with characteristic values -1, -2, +1, +2, wherein the sign indicates a direction of travel and the lanes of each direction of travel are numbered with consecutive natural numbers 1, 2.

A connection block 30, also referred to below as B _C , as illustrated in FIG. 5A, describes a traffic situation in which the number L of lanes 23 changes and in which a combination or splitting of lanes 23 can be modeled. Therefore, the connection block 30 becomes opposite to the road block 32 by a connection permutation

which describes both geometrically which

Lane 23 disappears or is generated, as well as topologically defined which lanes 23 are connected. As shown in FIG. 5C, an individual geometric parameter matrix and an individual geometric parameter matrix are used for each direction of travel

topological parameter matrix specified. An existing information

Connectedness of lanes 23 is indicated in binary terms by a one and a non-connectedness by a zero, as shown in Fig. 5C. Also in Figures 5A and 5C, the lanes 23 are marked with characteristics -1, -2, +1, +2, the sign indicating a direction of travel and the

Lanes 23 are numbered in each direction with consecutive natural numbers 1, 2. For example, in the situation illustrated in FIG. 5A, it is topologically possible to change from the lane -1 to the new lane -2 on the left side, or to remain on the existing lane. This topological information is not synonymous with a simple one

 Lane change maneuvers, which may be implied by the type of lane marking. A connection block 30 can therefore be used as

be defined.

In addition to these restrictions on the road model 30, it may further be predetermined that between two road blocks 32 a connection block 30 is, if necessary, to compensate for the differences between the road blocks 32 (eg with respect to the lane number L). If no changes are necessary, the connection block 30 can represent a road block 32 as a special case.

FIGS. 6A to 6D each illustrate a crossing model 34 according to one

Embodiment of the invention. In particular, FIGS. 6A and 6B show an outer intersection model 36 of the intersection model 34, FIG. 6C shows an inner intersection model 38 of the intersection model 34, and FIG. 6D shows a factor matrix F of the inner intersection model of FIG. 6C.

In the previous representation of a road map 14, such as shown in FIG. 4A, an intersection 19 has been represented by a node 11 connected to more than two edges 13. For the exact lane mapping and / or modeling of an intersection 19 both geometric

 Information about a crossing surface 37 and / or a navigable surface 37 or crossing surface 37, as well as topological information about the

Connectivity of the incoming and exporting lanes 23 and their infrastructure on the crossing surface 37 required. For this purpose, the roadway-accurate road map 14 is first segmented into at least one crossing segment 19 a and / or a

Junction segment 19a is in the lane road map 14th

identified. The crossing segment 19a is then in an inner

Junction model 38 and an outer intersection model 36 models, as explained in more detail below.

The crossing model 34, also referred to below, sets itself apart

two different single models together. FIGS. 6A and 6B show an outer crossing model 36, also designated below.

 For initialization, the nodes 11 of the lane-exact road map 14 are examined and, based on the connected edges 13, intersection nodes 35 are identified. Since a large intersection 19 in the lane-exact road map 14 may be described by a plurality of nodes 11, by means of a

Distance value may be summarized several nodes 11.

The outer intersection model 36 may be generated on the center of the participating nodes 11. On the basis of the identified crossing nodes 35, the information can be taken directly from how many roads 17 are connected to the junction 19. For each street 17, a crossing arm A1-A4 is created. Everyone Junction arm A1-A4 has a distance parameter d which describes the distance from the center to the beginning of the crossing surface 37 with respect to this crossing arm A1-A4 and an angle parameter a which defines a rotation angle relative to a reference direction, for example the east direction. Through these two parameters d, a, a transition point from the road 17 to the crossing area 37 is defined for each crossing arm A1-A4.

The inner crossing model 38, also referred to below, is in

Figs. 6C and 6D illustrate. The inner crossing model 38 describes the

Lane Connectivity 23. Each intersection arm A1-A4 has the same information as a general road block 32 of the lane

Road model 28, whereby the geometry of the connected streets 17 is fixed. There may be a connection between each incoming and outgoing lane 23, the course of which may be described by a cubic Hermite polynomial. Thus, each connection is influenced by a parameter C, which can specify the course over the crossing surface 37. The parameters C are stored in the factor matrix F, as shown in Fig. 6D, where a value of zero indicates that the connection does not exist. By identifying the outer lane courses, the boundary of the intersection area 37 is additionally defined. The factor matrix F can be used for each

 Direction and each crossing arm A1-A4 have a row and a column. For the sake of clarity, different directions of travel are illustrated by different signs of the indices in FIG. 6D. Furthermore, the lanes 23 of the individual crossing arms A1-A4 in FIG. 6D are numbered consecutively with natural numbers.

In the following, details of the road model 28, the crossing model 32 described in the preceding figures, in particular FIGS. 4A to 6D, as well as the method according to the invention for creating the lane-exact road map 22 will be described.

To initialize the models 28, 34, the roadway-specific road map 14 is divided into roads 17 and intersections 19. At each intersection 19, an initial intersection model 34 is generated with an arm spacing of d _n = 25m, the number of connected roads 17 and thus the

Angular parameter a of the crossing arms A1-A4 can be determined from the road map 14. Subsequently, the road models 28 between the intersections 19, where a road 17 in the graph is described by a chain {v _x , ..., v _y }. In the lane-specific road model 28, a connection block 30 is generated on each node 11 and a road block 32 is created therebetween. Each road 17 begins and ends with a connection block 30 which may optionally correct the differences between the adjacent road block 32 and the intersection. Each road 17 is initialized as two lanes with one lane 23 per direction of travel. The totality of the α road models 28 and for intersection models 34 will be referred to as.

The initialized models 28, 34, Φ represent the current configuration of the overall model. The parameters of these models are the described properties of the road blocks 32, the connection blocks 30, the inner intersection models 36, and the outer intersection models 38 RJMCMC method are varied, therefore, the following are the possible change operations and the

 corresponding transition cores introduced. For all models 28, 30, 32, 34, 36, 38 there are on the one hand change operations which only influence the values of the existing parameters and on the other hand those which influence the parameters

 Dimension of a model 28, 30, 32, 34, 36, 38 change.

FIGS. 7A to 7E respectively illustrate change operations 40, 41, 42, 43, 44, 46, 48, 50 according to an embodiment of the invention. Specifically, FIG. 7A on the left side illustrates an insertion operation 40 for inserting a

 Connection block 30 in a road block 32 and a merge operation

41 for merging two road blocks 32 and a connection block 30 to a road block 32 as a reversible change operation 41 to the

 Insertion operation 40. Further, Fig. 7A illustrates a right hand one

 Adjustment operation 42 for adjusting a parameterization value for parameterizing a longitudinal extent of a road 17. Fig. 7B illustrates a

Add operation 43 for adding a lane 23 and a

Further, Fig. 7C shows a distance adjusting operation 46 for adjusting a distance G between opposite-direction lanes 23, Fig. 7D shows a width adjustment operation 48 for adjusting a width W of a lane 23, and Fig. 7E shows a curvature adjustment operation 50 for adjusting a curvature C of a road 17. With respect to a road model 28, the change operations 40, 41, 42, 43, 44, 46, 48, 50 are again divided into two classes. The insertion operation

40, the merging operation 41 and the fitting operation 42 as shown in Fig. 7A change the road model 28 at the block level, that is, the individual properties are not changed but only the number of road blocks 32 and connection blocks 30 and their spatial

Extension will be changed. In the adding operation 43, an existing road block 32 becomes two road blocks 32 and one

Split connection block 30. The removal operation 44 correspondingly connects such a constellation and, with the addition operation 43, forms a reversible pair whose selection probabilities can be selected to satisfy the extended detailed balance condition. In the adaptation operation 42, the boundaries of a road block 32 and / or connection block 30 are changed with respect to the parameterization of the road model 28. The adding operation 43, the removing operation 44, the

Distance adjustment operation 46, the width adjustment operation 48, and the curvature adjustment operation 50 change the characteristics,

Parameter values of a road block 32. The parameter values of a

Connection block 30 can not be active, but only passively changed. These adapt their parameters to the adjacent road blocks 32. The adding operation 43 for adding a lane 23 and a

Distance operation 44 also forms a reversible pair, while the three adjustment operations 42, 46, 50 only change the values of the parameters.

In order not to favor any of the change operations 40, 41, 42, 43, 44, 46, 48, 50 in the random variation of parameter values of the road model 28 and / or the intersection model 34 or by any of the change operations 40,

41, 42, 43, 44, 46, 48, 50 with equal probability, the selection probabilities become all change operations 40, 41, 42, 43, 44. 46, 48, 50 assumed to be identical:

In the following, the individual change operations 40, 41, 42, 43, 44, 46, 48, 50 are considered in more detail. The transition from the upper illustration in Figure 7A to the left hand representation of Figure 7A is made by means of the insertion operation 40. The longitudinal

Extension of the road block 32, B _{s to be divided} is via the parameterization P of the road model with the values with the parameterized

Defined length. The division will be two new values

on this length with <u _; needed:

The acceptance probability is determined as:

The Jacobian of transformation is with a determinant of 1, because the matrix has triangular shape.

The merge operation 41 can be considered as a reverse case. The constellation road block 32, connection block 30, road block 32 is summarized, with no new components being needed for the transformation, but being calculated. The constellation is in the parameterization P of the road model 28 by the sequence {p _a , _b , p _c , p _ci } dei \ eri. The

Acceptance probability is:

The fitting operation 42 describes as a transition between the upper view in FIG. 7A and the right-hand view in FIG. 7A. the

Change of one of the two parameterization values of a road block 32.

The parameter can be changed by a maximum of half the parametrized length p, of the road block 32. In order to prefer no direction of movement, the search function is realized as a random movement: In order to insert a new lane with addition operation 43, as shown in FIG. 7B, the road model 28 is supplemented by a new lane width of a lane 23. The new track width is drawn from a normal distribution whose expected value and variance result from road construction specifications. These can be determined in the context of the scenario or the type of road 17. For the transformation follows:

The determinant of the Jacobian matrix is 1 and the probability of acceptance is: The acceptance probability for the opposite distance operation 44 is calculated accordingly, where the component u is the track width of the lane 23 to be removed:

The three change operations 46, 48, 50 shown in FIGS. 7C, 7D, 7E modify the existing parameter values of the road model 28 and / or intersection model. Therefore, the corresponding search functions are realized as equal distribution:

Since the intersection model 34 consists of the inner intersection model 36 and the outer intersection model 38, there are various change operations for each sub-model 36, 38. As shown in FIGS. 6A and 6B, the two parameters distance d and angle a influence the shape of the outer intersection model 36. The number of intersection arms A1-A4 is already extracted from the road map 14 in the initialization process and is not changed any more. Thus, two change operations are defined which change the two parameters d, a but not the dimension of the outer intersection model 36. In other words, the outer crossing model may have a Distance parameter change operation and a

Angle parameter change operation. Therefore, search functions are implemented as equal distribution:

In the inner crossing model 38, each crossing arm A1-A4 has a connection cross-section which has the same characteristics as a road block 32. Since at each crossing arm A1-A4 a connection block 30th

connected, it responds to the changes in the crossing arm Al-

A4 as well as changes to a road block 32. Therefore, the

Change operations for varying the terminal properties are identical to those already defined for a road block 32. In other words, the inner crossing model 38 has the above-described one

Change operations 40, 41, 42, 43, 44, 46, 48, 50. Influencing the

Factor matrix F of Figure 6D is not done by an RJMCMC operation.

FIGS. 8A and 8B each illustrate an application of a score metric according to one embodiment of the invention.

On the one hand, a measure of the correspondence between the road model 28 and / or the intersection model 34 and the trajectory data 27 in a first term is obtained for the evaluations and on the other hand, prior knowledge about the models 28, 34 is taken into account in a second term. Hereinafter

These dimensions are set out.

In the first step, the vehicle trajectories 27 are displayed on the lanes 23. For this purpose, first each center line of each road segment 26 and each intersection 19 is converted into a graph, wherein the center line is discretized in small steps with node 11 and edges 13. Each graph is then optimized to a minimum number of nodes 11 using the Douglas-Peucker algorithm. Finally, these graphs become one

Overall representation G merged. In the next step, a hidden Markov model (HMM) is generated for each trajectory 27, which as hidden states generates the edges 13 of the generated

Graph G and as emitted observations has the trajectory points. The HMM is solved using the Viterbi algorithm and yields the

most probable assignment of each measuring point to a lane 23:

The Euclidean distance Y _d between the trajectory and lane according to FIG. 8A, as well as the included driving angle Y _a are determined as the evaluation measure

Figure 8B evaluated. In addition, a limit for the minimum number of passes is introduced. Y _f describes a jump function which causes

Lanes with too few passes are classified as not reliable and the configuration is rejected. Generally, the definition of the function depends on the total number of passes and may, if appropriate, be designed such that a specific value is counted as a normal number and a deviation leads to devaluation. The first term of the valuation metric is thus given by:

The jump function for consideration of the passages is defined as: where the lanes of the model, the number of trajectories that have been mapped to the χth track and η describes the minimum number of passes to be reached.

In Prior knowledge about the lane-specific models 28, 34 is taken into account. To keep the road segments and intersections 19 realistic

Regularization terms introduced that influence the evolution of the properties. The width of a lane and the length of a block are regulated: With regard to the track width w, a normal distribution is assumed whose parameters are to be selected in the context of the scenario. Characteristics too

different scenarios can be taken from various guidelines for road construction.

Overfitting would be very short in this process due to a stringing

Road segments 26 arise. To counteract this will be one

Minimum length introduced for a road segment, which is realized by the rule using a jump function:

After all road models 28 and intersection models 34 have been initialized, the method may be varied using the defined RJMCMC change operations 40, 41, 42, 43, 44, 46, 48, 50. This will be an objective function

Determines which matches both the correspondence between the trajectory data 27 and the models 28, 34 in as well as existing prior knowledge

avoidable and to be strengthened developments of the models 28, 34 in

determined, whereby the relationship between the data and the

Model knowledge determined.

A corresponding algorithm for carrying out the method according to the invention can be subdivided into a warm-up phase and a main phase. In the warm-up phase, for example, not all change operations 40, 41, 42, 43, 44, 46, 48, 50 can be available, but only

Distance adjustment operation 46 of the road models 28 and crossing model 34 are used. The problem addressed by this measure occurs on roads with great structural separation: with equal choice of operations and an initial model with no structural separation, the method can quickly generate a multi-lane model. Many iterations are then used to replace the redundant lanes 23 with a structural separation. By the warm-up phase can be a better initial estimation of separation can be achieved in very few iterations.

Furthermore, the so-called simulated annealing method can be used, the purpose of which is to influence the above-described objective function as a function of the transit time:

where the function has a cooling function for each cell

represents. This causes the formation of the Markov chain to focus on better valued regions of the target function. In practice, this means that change operations that degrade the rating are less accepted as the runtime progresses. The value of the cooling function decreases as soon as a proposed change operation has been rejected. The cooling function is an exponentially decreasing function:

wherein the parameter Λ is chosen so that a certain number of steps 5 are needed to reach a temperature. This is the

Function converted into a calculation rule depending on the number of steps:

In addition, it should be noted that "comprehensive" does not exclude other elements and "a" or "an" does not exclude a multitude

Embodiments have been described, can also be used in combination with other features of other embodiments described above. Reference signs in the claims are not to be considered as limiting.

Claims

claims

1 . Method for creating a lane-accurate road map (22), the

 Method comprising the steps:

 Providing a digital roadway accurate road map (14) for

 Description of a road course of at least one road (17);

 Providing a trajectory dataset (16) having a plurality of trajectory data (27) of road users along the at least one road (17);

 Identifying the at least one road (17) while segmenting the roadway-accurate road map (14) into at least one road segment (26); characterized in that the method further comprises the steps of: modeling the road segment (26) in at least one road model (28);

 the road model (28) having a plurality of parameters (L, W, G, C) for geometrically and / or topologically describing lanes (23) of the road (17);

 randomly varying, in particular multiple randomly varying, parameter values of at least a portion of the parameters (L, W, G, C) of the road model (28) by randomly selecting a change operation (40, 41, 42, 43, 44, 46, 48, 50 ) of the road model (28) for changing

Parameter values;

 Associating at least a portion of the trajectory data (27) of the

 A trajectory data set (16) to the road model (28) determining at least one probability value for the road model (28), wherein the probability value corresponds to a figure of merit

Trajectory data (27) correlated by the road model (28);

 Determining, based on the determined at least one

 Probability value of optimal parameter values of at least a part of the parameters (L, W, G, C) of the road model (28); and

Creating a lane-accurate road map (22) based on the optimal parameter values of the road model (28).

2. The method according to claim 1,

 wherein the optimal parameter values are determined based on a Monte Carlo method, in particular based on a Reversible Jump Markov Chain Monte Carlo method.

3. The method of claim 1 or 2, wherein the road model (28)

 at least one road block (32) for modeling a constant in at least a portion of the road segment (26) number of lanes (23); and or

 wherein the road model (28) comprises at least one connection block (30) for modeling, based on at least one geometric parameter matrix (RGL, RGR) and at least one topological parameter matrix (RTL, RTR) of at least a portion of the road segment (26) changing number of Having lanes (23),

 wherein values of the geometric parameter matrix (RGL, RGR) a change of a lane number (L) within the road segment (26)

 describe; and

 wherein values of the topological parameter matrix (RTL, RTR) describe a connection between individual lanes (23) within the road segment (26).

The method of any one of the preceding claims, wherein the step of modeling the road segment (26) in the road model (28) comprises the substeps of:

 Parameterizing the road segment (26) in a unit interval such that each point of the road (17) in the road segment (26) is set above a parameterization value in the unit interval;

 Segmenting the road segment (26) into at least one road block (32) and at least one connection block (30) of the road model (28); Modeling a disappearance or generation of a traffic lane (23) within the road segment (26) based on at least one geometric parameter matrix (RGL, RGR) of the connection block (30); Modeling a connection of individual lanes within the

 Road segment based on at least one topological

 Parameter matrix (RTL, RTR) of the connection block (30); and

Determining values of the geometric parameter matrix (RGL, RGR) and / or values of the topological parameter matrix (RTL, RTR) based on a random selection of a change operation (40, 41, 42, 43, 44, 46, 48, 50) of the road model (28).

A method according to any one of the preceding claims, wherein the digital roadway-grade road map (14) has at least one intersection (19) and a plurality of roads (17) connected to the intersection (19); the method further comprising:

 Identifying the at least one intersection (19) while segmenting the lane-exact road map (14) into at least one intersection segment (19a);

 Modeling the crossing segment (19a) in at least one

 Crossing model (34);

 wherein the intersection model (34) has a plurality of parameters (L, W, G, C) for geometrically and / or topologically describing lanes (23) of the intersection (19);

 random variation, in particular multiple random variation, of parameter values of at least part of the parameters of the

 Crossing model (34) by randomly selecting a

 Change operation (40, 41, 42, 43, 44, 46, 48, 50) of the intersection model (34) for changing parameter values;

 Associating at least a portion of the trajectory data (27) of the

 A trajectory data set (16) to the intersection model (34) determining at least one probability value for the intersection model, the probability value correlating with a merit of mapping the trajectory data (27) through the intersection model (34);

 Determining, based on the determined at least one

 Probability value of optimal parameter values of at least part of the parameters (L, W, G, C) of the intersection model (34); and

 Creating a lane-accurate road map (22) based on the optimal parameter values of the intersection model (34).

6. The method of claim 5, wherein the intersection model (34) comprises an outer intersection model (36) for modeling a trafficable intersection area (37) of the intersection (19) based on a distance parameter (d) and an angle parameter (a); and or

wherein the step of modeling the intersection segment (19a) in the intersection model (34) comprises the following substeps: Determining a junction node (35) in the lane accuracy

 Road map (14);

 Determining a number of edges (13) of the lane-level road map (14) connected to the intersection node (35), by determining a number of roads (17) connected to the intersection (19);

 Generating a number of intersection arms (A1 -A4) corresponding to the number of roads (17) connected to the intersection, each of the intersection arms (A1 -A4) being assigned a distance parameter (d) for indicating a distance of a center of the intersection (19) a boundary surface of the intersection (19) along the respective crossing arm (A1 -A4) is defined; and

 wherein each of the crossing arms (A1 -A4) is defined by an angle parameter (a) for indicating a rotation angle between the respective crossing arm (A1 - A4) and a reference direction.

The method according to one of claims 5 and 6, wherein the intersection model (34) comprises an inner intersection model (38) for modeling based on a factor matrix (F) of the intersection model (34) of lanes (23) introducing intersections (23 ), from lanes (23) executing from the intersection (19) and a lane (23) over one

 Crossing surface (37) of the intersection (19); and or

 wherein the step of modeling the intersection segment (19a) in the intersection model (34) comprises the following substeps:

 Modeling at least a portion of lanes (23) entering the intersection (19), at least a portion of lanes (23) from the intersection (19), and a course of at least a portion of the intersection (37) of the intersection (19) leading lanes (23) based on a factor matrix (F), values of the factor matrix (F) describing a course and connection of lanes (23) via the intersection (37); and

 Determining values of the factor matrix (F) based on at least a portion of the trajectory data (27) of the trajectory data set (16).

8. Method according to one of the preceding claims,

wherein the road model (28) and / or an intersection model (34) each have a number parameter (L) for describing a number of lanes (23), a width parameter (W) for describing a width of individual ones Lanes (23), a curvature parameter (C) for describing a curvature of a road (17) and a distance parameter (G) for

 Description of a distance between lanes (23) opposite direction of travel has.

9. Method according to one of the preceding claims,

 wherein the road model (28) and / or an intersection model (34) at least one change operation (40, 41, 42, 43, 44, 46, 48, 50) selected from the list consisting of an insertion operation (40) for inserting a connection block ( 30) into a road block (32), a merge operation (41) for merging two road blocks (32) and a connection block (30) to a road block (32), a

 Fitting operation (42) for adjusting a parameterization value for parameterizing a longitudinal extent of a road (17); an adding operation (43) for adding a lane (23), a

 Removal operation (44) for removing a lane (23), a

 Distance adjustment operation (46) for adjusting a distance between lanes (23) of opposite direction of travel, a

 A width adjusting operation (48) for adjusting a width of a lane (23) and a curvature adjusting operation (50) for adjusting a curvature of a road (17).

1 0. A method according to any one of the preceding claims, further comprising:

 Discarding or accepting randomly varied parameter values based on a randomly selecting a change operation based on a weighting metric that determines the quality of the image of the image

 Trajektoriendaten (27) through the street model (28) and / or a

 Junction model (34) describes;

 wherein the evaluation metric includes a first term for describing a match between the trajectory data (27) and the

 Road model (28) and / or a crossing model (34);

wherein the evaluation metric has a second term for taking into account at least one predetermined parameter of a road geometry, in particular a parameter with regard to a lane width and / or a road width.

11. A data processing device (10) for determining a lane-exact road map (22) based on a digital roadway accurate

 Road map (14),

 wherein the data processing device (10) is adapted to carry out the method according to any one of the preceding claims.

12. Data processing device (10) according to claim 1 1, wherein the

 Data processing device (10) has a data memory (12) for storing a digital roadway-accurate road map (14) and a processor (18).