WO2019052867A1 - Procédé destiné à calculer un déroulement de voies d'un réseau routier et dispositif de serveur destiné à mettre en œuvre le procédé - Google Patents

Procédé destiné à calculer un déroulement de voies d'un réseau routier et dispositif de serveur destiné à mettre en œuvre le procédé Download PDF

Info

Publication number
WO2019052867A1
WO2019052867A1 PCT/EP2018/073835 EP2018073835W WO2019052867A1 WO 2019052867 A1 WO2019052867 A1 WO 2019052867A1 EP 2018073835 W EP2018073835 W EP 2018073835W WO 2019052867 A1 WO2019052867 A1 WO 2019052867A1
Authority
WO
WIPO (PCT)
Prior art keywords
lane
driving
lanes
segments
predetermined
Prior art date
Application number
PCT/EP2018/073835
Other languages
German (de)
English (en)
Inventor
Friedrich Schweizer
Original Assignee
Bayerische Motoren Werke Aktiengesellschaft
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Bayerische Motoren Werke Aktiengesellschaft filed Critical Bayerische Motoren Werke Aktiengesellschaft
Priority to CN201880050905.6A priority Critical patent/CN111033591B/zh
Publication of WO2019052867A1 publication Critical patent/WO2019052867A1/fr

Links

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/38—Electronic maps specially adapted for navigation; Updating thereof
    • G01C21/3804—Creation or updating of map data
    • G01C21/3807—Creation or updating of map data characterised by the type of data
    • G01C21/3815—Road data
    • G01C21/3819—Road shape data, e.g. outline of a route
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
    • G08G1/0108—Measuring and analyzing of parameters relative to traffic conditions based on the source of data
    • G08G1/0112—Measuring and analyzing of parameters relative to traffic conditions based on the source of data from the vehicle, e.g. floating car data [FCD]
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
    • G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications
    • G08G1/0141—Measuring and analyzing of parameters relative to traffic conditions for specific applications for traffic information dissemination
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/09—Arrangements for giving variable traffic instructions
    • G08G1/0962—Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
    • G08G1/0967—Systems involving transmission of highway information, e.g. weather, speed limits
    • G08G1/096766—Systems involving transmission of highway information, e.g. weather, speed limits where the system is characterised by the origin of the information transmission
    • G08G1/096775—Systems involving transmission of highway information, e.g. weather, speed limits where the system is characterised by the origin of the information transmission where the origin of the information is a central station

Definitions

  • the invention relates to a method for determining a course of lanes or lanes of the roads of a road network on the basis of driving trajectories of a plurality of motor vehicles.
  • the method may be performed by a server device which is also part of the invention.
  • Another possibility is to collect trajectory data of the driven driving trajectories of a plurality of motor vehicles centrally and to determine a respective course of the driving lanes on the basis of these driving trajectories.
  • a method of this type is known for example from DE 10 2015 000 399 A1. According to this method, based on the driving trajectories, a probability distribution for a residence probability of motor vehicles is determined. By combining mathematical maximum points in the function of the probability distribution, a lane course can be reconstructed. However, this is in some cases only for short lane segments, if the lane course, for example, can be clearly determined along a straight road section.
  • trajectory data lack altitude information from which it would be possible to detect whether the crossing travel trajectories are at the same height as in the case of an intersection, or whether the driving trajectories of one direction are at a different height level than the driving trajectories of the crossing direction, such as in the case of a bridge.
  • the information about the connection between roads is crucial to be able to indicate in a road map, for example, if there is a turn, which is only one Crossing the case would be and not at a bridge. Only then can the road map be used for a navigation assistance.
  • the invention is based on the object of determining or reconstructing the course of lanes of a road network on the basis of a multiplicity of driving trajectories of motor vehicles.
  • the invention provides a method for determining a course of lanes or lanes of a road network.
  • the course is determined on the basis of driving trajectories of a large number of motor vehicles.
  • a respective description of the driving trajectories can be received from the respective motor vehicle in the form of trajectory data.
  • the driving trajectories may indicate a sequence of position information relating to a respective position of the motor vehicle along the driving trajectory.
  • the driving trajectories can be provided, for example, by a respective navigation system of the motor vehicle.
  • the trajectory data may be collected by a server device.
  • the server device uses the travel trajectories to recognize a respective course of unconnected lane segments of the lanes.
  • unconnected lane segments result from the problem described above that, for example, on the basis of a probability distribution for limited sections, ie individual lane segments, clearly the course of the respective lane can be determined.
  • the length of such a lane segment may be in a range of, for example, 2 m to 500 m.
  • lane segments in each individual case study the individual driving trajectories of the motor vehicles determine between which of the lane segments at least some the motor vehicles are actually changed over.
  • Related lane segments are thus recognized, for example, by the fact that, for example, a predetermined minimum number of motor vehicles could switch between in each case two of the lane segments.
  • the minimum number and / or another condition is determined by a linkage criterion indicating which lane segments to link.
  • Those lane segments, which are identified as belonging together on the basis of the predetermined link criterion on the basis of the overlapping travel trajectories, are then linked or connected to a respective traffic lane.
  • the linkage criterion can specify how many vehicles must have changed over between at least two lane segments so that these two lane segments are recognized as connected. If the connection criterion is met, then the respective driving track segments are linked or connected. The lanes of the lanes determined in this way are then provided with lane data which describe the lanes.
  • the advantage of the invention is that it is possible to ascertain the course of lanes on the road network without additional measurement data based on the driving trajectories. In doubtful cases, such as cruising trajectories, the topological relationship between the previously reconstructed unconnected lane segments is determined. Thus, by means of the method a course of lanes of a road network can be mapped, in which also the change possibilities between lanes are indicated. Thus, the determined course of the lanes is suitable, for example, for a navigation assistance.
  • each two lane segments stipulates that these lane segments must have travel trajectories in common so that they are linked.
  • a predetermined minimum proportion of the driving trajectories, which run along one of the two driving track segments, must thus also run along the other of the two driving track segments. It is therefore provided a predetermined minimum proportion, which can be determined for example by a percentage.
  • the minimum content may range from 20% to 100%.
  • at least 50% of the driving trajectories that run over the one lane segment must also run over the other lane segment.
  • the linkage criterion with respect to the two lane segments may specify that a predetermined absolute minimum number of those lane trajectories that run along one of the two lane segments must also run along the other of the two lane segments. So the absolute number is decisive. This results in the advantage that individual cases can be excluded by the absolute minimum number is specified accordingly.
  • the minimum number may, for example, be in a range greater than 5.
  • An embodiment provides that the linking criterion with respect to three driving lane segments each pretends that one of these three lane segments is linked or connected to the other two of these lane segments if the driving trajectories that extend over this one lane segment affect the remaining two lane segments divide a numerical ratio that is in a predetermined range of values.
  • a branch of a lane can be detected thereby.
  • the range of values may be, for example, 1/5 - 4/5, to name just numerical values.
  • the branching is thus e.g. detected if the driving trajectories split in a ratio of 1/3 to 2/3.
  • this embodiment can also be applied to more than three lane segments accordingly.
  • An embodiment provides that, based on the individual driving trajectories, it is determined and signaled whether a lane change is possible between every two lanes. Does it at least a motor vehicle or a predetermined minimum number of motor vehicles to switch between two lanes (recognizable by theirêtrajektorien in the individual case consideration) so this lane change can be detected.
  • the minimum number may be predetermined by a predetermined lane change criterion that must be met for a lane change to be identified.
  • the lane change criterion may specify an absolute minimum number and / or a relative minimum number (numerical proportion of those motor vehicles that have traveled along the lanes). Due to the embodiment, a structural separation can be detected in an advantageous manner (no lane change recognizable) and / or it can be recognized a possibility for lane change.
  • An embodiment provides that by means of a respective course direction of the individual driving trajectories, i. Based on the respective direction of travel, a prescribed direction of the lanes and / or a one-way street is detected.
  • a one-way street here is a single lane or several adjacent lanes, all leading in the same direction, while no other adjacent lane points in the opposite direction. This has the advantage that the prescribed direction of travel can also be mapped on the basis of the driving trajectories.
  • the individual driving lane segments are already known.
  • such lane segments can always be defined or identified where the lane course is unambiguous, for example because there is no branch or intersection.
  • An embodiment of the method relates to the recognition of the respective course of these lane segments, that is to say the formation of the lane segments.
  • the driving trajectories are summarized by means of said statistical method to a probability distribution of the probability of residence of motor vehicles.
  • An example of such a statistical method is the formation of a histogram (histogram formation).
  • characteristic points are determined according to a predetermined search criterion. Then, each of some of the characteristic points are connected by a connection to a respective course of one of the lane segments using a predetermined connection method.
  • This connection method thus connects the characteristic points or at least describes a course of a lane segment segment that fulfills a predetermined optimization criterion with regard to the characteristic points, for example a minimization of the sum of the squared distances of the profile to the characteristic points.
  • Each lane segment may have a predetermined basic shape, for example, it may be a straight line segment or an arc segment. Nevertheless, by using a probability distribution and its characteristic points, despite deviations of the individual driving trajectories from the lane center, their course can still be reconstructed.
  • the statistical method for combining the driving trajectories may comprise a histogram formation.
  • the statistical method comprises a kernel density estimate.
  • a kernel density estimation for each position indication included in the travel trajectories, a two-dimensional probability density function (for the probability of stay in the X direction and the Y direction) with their average or maximum in a digital map can be set to the position according to FIG Position information to be positioned.
  • a probability density function is also called kernel.
  • the described probability distribution of the probability of residence of the motor vehicles is obtained as a two-dimensional, ie location-related probability function (for the X direction and Y direction). This results in the advantage that this probability distribution is determined as a continuous, ie continuous, function and thus coverage gaps can be compensated.
  • An embodiment then provides that the said search criterion for finding the characteristic points specifies that a local maximum and / or a saddle point of the probability distribution are each a characteristic point.
  • Each characteristic point thus denotes a location at which the probability of residence with respect to an adjacent surrounding area and / or a predetermined spatial direction is maximum.
  • a lane center can be recognized as the statistical mean value of the driving trajectories belonging to the lane.
  • connection method for connecting the individual characteristic points respectively connects such characteristic points to a lane segment segment which are arranged along a predetermined geometric basic shape.
  • a basic shape can be, for example, a straight line piece or a circle segment or an elliptic segment or a clotid segment.
  • the embodiment results in the advantage that each lane segment segment has a plausible form, as it can only ever occur structurally for a real traffic lane.
  • the connection method provides that associated characteristic points are identified by means of a Hough transformation.
  • the coordinates of the characteristic points can be transformed by means of the Hough transformation into the Hough parameter space (Hough space), as is known per se from the prior art, for example, from US Pat. No. 3,069,654 A.
  • Hough parameter space Hough parameter space
  • at least one accumulation point can then be determined which fulfills a predetermined accumulation criterion.
  • a cluster point may, according to a possible clustering criterion, be, for example, the mid-point of a region of predetermined size in which there is a predetermined minimum number of transformed points.
  • Such a cluster point then describes a lane segment whose shape can be determined by re-transforming the cluster point.
  • the embodiment results in the advantage that the courses of the individual lane segments can be determined automatically.
  • the lane-exact mapping is problematic since GPS data have such a large spread that the described driving trajectories may be too imprecise in regions to between two neighboring ones Distinguish lanes.
  • An embodiment therefore provides that the driving trajectories are formed or determined via a predetermined so-called dead reckoning method (dead reckoning method).
  • dead reckoning method evaluates an acceleration and / or speed and / or yaw rate and / or a so-called heading (direction indication, for example, as direction) with respect to the respective motor vehicle in order to determine a relative position change.
  • the generation of the trajectory data of the respective driving trajectory is based on an odometry of the motor vehicle, which uses vehicle sensors for determining the relative position change and / or a movement dynamics.
  • the driving trajectories can be determined in sections more accurately than with a GPS receiver.
  • a server device is also provided by the invention.
  • a server device may be configured as a server of the Internet.
  • the server device has a computing device which is set up to carry out an embodiment of the method according to the invention.
  • the method steps of the method can, for example, based on a Program codes for the computing device to be realized.
  • the server device can be realized by means of a computer or a computer network.
  • Fig. 1 is a schematic of an embodiment of the invention
  • Fig. 2 is a sketch illustrating a probability distribution of a
  • Fig. 3 is another diagram for illustrating the
  • FIG. 5 is a diagram illustrating a method step in which a
  • Fig. 6 is a road map, as by the server device by means of a
  • Embodiment of the method according to the invention may be formed and in which courses of lanes are mapped by linked lane segments;
  • Fig. 1 shows a server device 10, which may be, for example, a computer or a computer network, which may be connected as a server to the Internet 1 1.
  • the server device 10 may include a computing device 12, which may be configured to generate a road network 13 with roads 14 a road map 15, which describes the road network 13 so accurately that individual lanes 16 in particular together with information about, for example, the approved direction and / lane change options and / or structural separations in the map 15 are recorded.
  • the road map 15 is so lane accurate.
  • the server device 10 can receive trajectory data 18 from a plurality of motor vehicles 17 traveling along the lanes 16, which describe a respective travel trajectory 19 traveled or driven by the motor vehicle 17.
  • the trajectory data 18 can, for example, be transmitted to the server device 10 via a respective radio connection 20, for example a mobile radio connection, via, for example, a mobile radio network 21 and / or the Internet 1 1.
  • the server device 10 can enter or reconstruct or reconstruct the travel trajectories 19, for example in the road map 15.
  • the travel trajectories 19 are provided with a reference numeral.
  • a direction of travel 22 of the respective motor vehicle can be indicated.
  • Each driving trajectory 19 may each have position information 23, which indicate a location of the respective motor vehicle 17 at a respective time.
  • the connection of the position data 23 results in the course of the respective driving trajectory 19.
  • the coordinates from the respective position specification 23 can be entered in a coordinate system 24 which is illustrated in FIG.
  • the server device 10 can now reconstruct the courses of the lanes 16 from the courses of the driving trajectories 19.
  • an intersection 25 is shown, which can be seen on the basis of the originallyrajektorien 19 only as an overlap 26 of some of the originallyrajektorien 19. Because it could also be that instead of the Junction 25, the overlap 26 of since the motor vehicles 1 7 have crossed over another bridge over a bridge.
  • the server device 1 0 can still reconstruct the progress of the lanes 1 6 and here also the change possibilities between the lanes 1 6 reconstruct or recognize and thus enter or map in the map 15.
  • 2 illustrates how the server device 10 can first determine a statistical description of the residence probabilities of the individual motor vehicles 17 on the basis of the driving trajectories 1 9.
  • 2 shows for the coordinates X, Y a probability distribution 27 which indicates a respective probability of residence H (in the Z direction perpendicularly out of the plane of the drawing) for the fact that a motor vehicle has been at the respective coordinate or at the respective location.
  • the probability distribution 27 is illustrated by isolines and at the edge by 2-D cross-sections.
  • FIG. 3 again illustrates a cross-section 29 of the probability distribution 27 of FIG. 2.
  • the probability of residence H may be determined or formed on the basis of a kernel density estimate in the manner described.
  • characteristic points 28 can be determined, of which only a few are provided with a reference symbol in FIG. 2 in order to maintain clarity.
  • a characteristic point 28 may be, for example, a local maximum at maximum points Xi, X 2 or a saddle point of the function of the probability distribution 27.
  • FIG. 3 illustrates that along one direction (here the X direction) transverse to a course of one of the roads 14, two maxima and thus two characteristic points can result, which is an indication of two lanes. It can also be based on predetermined track width measures for plausibility.
  • characteristic points 28 can be connected by a respective connection 30, since it can be recognized that these characteristic points 28 designate the course of a lane segment 31 with a predetermined minimum reliability.
  • the combination of characteristic points 28 with associated connection 30 is in each case regarded as synonymous with a lane segment 31.
  • all can characteristic points 31 are transformed from a predetermined region, for example by means of a Hough transformation, and in the Hough parameter space accumulation points are determined by means of a predetermined accumulation criterion as described. Each cluster point can then describe a lane segment 31 whose course can be determined by reverse transformation.
  • FIG. 4 illustrates how, starting from the individual, unconnected lane segments 31, the course of the lanes 16 in the road network 13 can be reconstructed, that is to say in FIG. the topology of the driving lane segments 31.
  • a link 32 is determined between two or more than two lane segments 31. This is no longer carried out on the basis of the statistical description, that is, on the basis of the probability of habitation 27, but individual consideration of individual ones of the driving trajectories 19. Based on the respective individual course of the driving trajectories 19, it can be determined whether there is a change or an exchange of one of the motor vehicles 17 from one of the lane segments 31 to another of the lane segments 31 occurred or occurred.
  • connection criterion 33 can be used, which, for example, can specify an absolute minimum number of travel trajectories 19 that have to run between each two driving track segments 31 so that they are linked by a link 32. It may also be prescribed of those driving trajectories 19, which lead along a lane segment 31, a predetermined minimum relative proportion (for example, a minimum percentage), which must also lead over the other lane segment 31, so that the link 32 is formed or set.
  • FIG. 5 illustrates how, based on individual travel trajectories 19, a possibility for a lane change 35 can also be detected.
  • One possibility for a lane change 35 can be differentiated from the actual link 32 of two lane segments 31, as it results from the course of lanes 16 itself, for example, based on the number or relative frequency of the respective underlying Whyrajektorien 19, because regardrajektorien a lane change are rarer as driving trajectories that run within a lane.
  • a structural separation 36 or a lane separation can also be generally recognized by recognizing, for a theoretically possible link 37, that there are still no driving trajectories 19 or that the number of driving trajectories 19 is smaller than a threshold value.
  • FIG. 6 illustrates the finished road map 15, in which by individual Fahrspursegmente 32 and their respective link 32, the courses of the lanes 16 are modeled. The recognized possibilities for lane change are not shown.
  • At the intersection 25 can be determined by means of links 32 in the road map 15 by the server device 10 or by a navigation device that can use the road map 15, which driving options or navigation options in the road network 13 are available.
  • the lanes 16 thus determined may be written by lane data 38, for example, in the one respective navigation device of motor vehicles, e.g. the motor vehicles 17, can be transmitted, for example, so that they can provide a navigation assistance on the basis of the lane data 38. Based on the lane data 38, it is then possible to plan a driving route and to take into account the progress of the lanes 16 and the change possibilities according to the links 32, for example at the intersection 25.
  • a plurality of driving trajectories 19 of motor vehicles 17 is considered for creating a lane-precise road map 15.
  • These driving trajectories 19 need not be generated via GPS points, but can be generated via a dead-reckoning method.
  • the position of the respective motor vehicle is determined at a respective current detection time relative to the last detection time point by using information about acceleration, speed, yaw rate and / or heading.
  • This information can be generated in an advantageous manner from existing series sensors of the respective motor vehicle.
  • This method is more accurate than the GPS when considering small distances (lane segments) and may be subject to a movement model of the vehicle for plausibility.
  • landmarks can be used as fixed points, between which the calculated trajectory 19 is suspended or anchored in sections. Thus, a drift or an offset can be corrected.
  • a loose lane net is initially generated.
  • This loose lane only indicates whereabouts of vehicles and does not yet contain any information as to whether it is, for example, a one-way street or a pure or mixed right turn lane.
  • High accuracy GPS data could be used to generate the loose lane network. However, these can only be produced with great effort and are therefore not suitable.
  • a plurality of travel trajectories 19 generated by the dead reckoning method can be evaluated by means of a kernel density estimator.
  • Figure 7 illustrates how to correct for drift during the dead reckoning process.
  • a road 14 may be defined by known landmarks 38, e.g. Curves 39, e.g. be recognized while driving, be clearly identified.
  • the exact knowledge of the position of the landmarks 38 is now used to match or reproduce the actually driven driving trajectory 19 back onto the road and thus the drift that has arisen due to the dead-reckoning method in an estimated driving trajectory 40 by a displacement 41 to correct.
  • 19 conclusions about the number of lanes 16 can be drawn by evaluating a high number of driving trajectories.
  • the lane description determined as a result is not congruent with the lane center but normally distributed (see FIG. 3).
  • a Kern emphasizeticianrs a statement about the lane center and the number of lanes 16 can be made.
  • the position in the longitudinal direction can be generated.
  • the result is the loose lane net, which includes all possible positions of the vehicles on the different lanes. It can be described as a probability distribution 27.
  • the driving trajectories 19 are again considered individually in a single evaluation (see FIGS. 4 and 5).
  • the position information 23 of the driveneauxektorien 19 on the loose lane network can be determined whether the lanes 16 are structurally separated or lane changes are possible, whether it is one-way or if it is, for example, a mixed or pureSteabbiegespur. Accordingly, the lane line continuously improves with more trajectory data 28.

Landscapes

  • Engineering & Computer Science (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Chemical & Material Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Traffic Control Systems (AREA)
  • Navigation (AREA)

Abstract

L'invention concerne un procédé destiné à calculer un déroulement de voies (16) d'un réseau routier (13) selon le principe de trajectoires de conduite (19) d'une pluralité de véhicules automobiles (17), un déroulement respectif de segments (31) de voies non reliés des voies (16) étant d'abord reconnu au moyen des trajectoires de conduite (19) par un dispositif de serveur (10). Selon l'invention, une relation topologique entre les segments (31) de voies est alors calculée en calculant dans un examen isolé respectif au moyen des trajectoires de conduite (19) individuelles entre lesquels des segments (31) de voies au moins quelques-uns des véhicules automobiles (17) sont effectivement passés, les segments (31) de voies qui sont reconnus sur le principe d'un critère de combinaison (33) prédéfini à l'aide des trajectoires de conduite (19) empruntées comme étant correspondants, étant reliés en une voie (16) respective et des données (38) de voie, lesquelles décrivent les déroulements des voies (16) calculées, étant préparées.
PCT/EP2018/073835 2017-09-14 2018-09-05 Procédé destiné à calculer un déroulement de voies d'un réseau routier et dispositif de serveur destiné à mettre en œuvre le procédé WO2019052867A1 (fr)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201880050905.6A CN111033591B (zh) 2017-09-14 2018-09-05 用于确定道路网的行车道的走向的方法以及服务器设备

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
DE102017216237.6 2017-09-14
DE102017216237.6A DE102017216237A1 (de) 2017-09-14 2017-09-14 Verfahren zum Ermitteln eines Verlaufs von Fahrspuren eines Straßennetzes sowie Servervorrichtung zum Durchführen des Verfahrens

Publications (1)

Publication Number Publication Date
WO2019052867A1 true WO2019052867A1 (fr) 2019-03-21

Family

ID=63556301

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/EP2018/073835 WO2019052867A1 (fr) 2017-09-14 2018-09-05 Procédé destiné à calculer un déroulement de voies d'un réseau routier et dispositif de serveur destiné à mettre en œuvre le procédé

Country Status (3)

Country Link
CN (1) CN111033591B (fr)
DE (1) DE102017216237A1 (fr)
WO (1) WO2019052867A1 (fr)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113554044B (zh) * 2020-04-23 2023-08-08 百度在线网络技术（北京）有限公司 步行道路宽度的获取方法、装置、设备以及存储介质
DE102020118318A1 (de) 2020-07-10 2022-01-13 Bayerische Motoren Werke Aktiengesellschaft Verfahren und Vorrichtung zur Erkennung eines Verkehrsknotenpunktes auf Basis von Trajektoriendaten
CN114360261B (zh) * 2021-12-30 2023-05-19 北京软通智慧科技有限公司 车辆逆行的识别方法、装置、大数据分析平台和介质
CN118675366A (zh) 2023-03-20 2024-09-20 通用汽车环球科技运作有限责任公司 车辆停车场操纵的智能通知

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US3069654A (en) 1960-03-25 1962-12-18 Paul V C Hough Method and means for recognizing complex patterns
US20120116678A1 (en) * 2009-05-04 2012-05-10 James Alan Witmer Methods and systems for creating digital transportation networks
WO2016055248A1 (fr) * 2014-10-10 2016-04-14 Here Global B.V. Appareil et procédés associés pour utilisation dans la cartographie des intersections routières au niveau des voies
DE102015000399A1 (de) 2015-01-13 2016-07-28 Audi Ag Kartographieren von Fahrspuren mittels Fahrzeugflottendaten

Family Cites Families (23)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP3568768B2 (ja) * 1998-01-20 2004-09-22 三菱電機株式会社 車両位置同定装置
US6385539B1 (en) * 1999-08-13 2002-05-07 Daimlerchrysler Ag Method and system for autonomously developing or augmenting geographical databases by mining uncoordinated probe data
DE102004038739A1 (de) * 2004-08-10 2006-02-23 Robert Bosch Gmbh Verfahren zur Darstellung von Karteninformationen
WO2006125291A1 (fr) * 2005-05-25 2006-11-30 Hiroyuki Takada Système et procédé d’évaluation des temps de parcours d’une sonde de circulation
JP4654823B2 (ja) * 2005-08-03 2011-03-23 株式会社デンソー 道路地図データ更新システム及び道路検出システム
DE102005049769A1 (de) * 2005-10-18 2007-04-26 Robert Bosch Gmbh Informationsverarbeitungssystem sowie Verfahren zum Verarbeiten von Informationen in Bezug auf aufeinanderfolgende Einheiten
JP5064870B2 (ja) * 2007-04-17 2012-10-31 株式会社日立製作所 デジタル道路地図の生成方法及び地図生成システム
JP2010107305A (ja) * 2008-10-29 2010-05-13 Aisin Aw Co Ltd 道路情報生成装置、道路情報生成方法および道路情報生成プログラム
WO2011023246A1 (fr) * 2009-08-25 2011-03-03 Tele Atlas B.V. Système de navigation pour véhicule et procédé associé
DE102009046855A1 (de) * 2009-11-19 2011-05-26 Robert Bosch Gmbh Verfahren und Navigationsgerät zum Bereitstellen von Zusatzdaten in einer digitalen Straßenkarte
GB201211636D0 (en) * 2012-06-29 2012-08-15 Tomtom Belgium Nv Method and apparatus for detecting deviations from map data
GB201221150D0 (en) * 2012-11-23 2013-01-09 Tomtom Belgium Nv Method of extracting gps traces to display driving trajectories through an area over one or more junctions
DE102012222931A1 (de) * 2012-12-12 2014-06-12 Robert Bosch Gmbh Verfahren und Vorrichtung zur Ermittlung einer Position und/oder Art einer Straßeninfrastruktureinrichtung
US9816823B2 (en) * 2013-03-15 2017-11-14 Hewlett Packard Enterprise Development Lp Updating road maps
DE102014200638A1 (de) * 2014-01-16 2015-07-30 Bayerische Motoren Werke Aktiengesellschaft Verfahren und System zum Schätzen eines Fahrspurverlaufs
CN103971521B (zh) * 2014-05-19 2016-06-29 清华大学 道路交通异常事件实时检测方法及装置
US9658074B2 (en) * 2014-10-13 2017-05-23 Here Global B.V. Diverging and converging road geometry generation from sparse data
CN104318766B (zh) * 2014-10-22 2016-06-08 北京建筑大学 一种公交gps轨迹数据的路网匹配方法
DE102014017083A1 (de) * 2014-11-19 2016-05-19 Elektrobit Automotive Gmbh Technik zum Abgleichen erfasster Positionen mit digitalem Kartenmaterial
DE102015013085A1 (de) * 2015-10-08 2016-03-31 Daimler Ag Verfahren zum Bestimmen eines Soll-Fahrspurverlaufs eines Kraftfahrzeugs
CN106996783B (zh) * 2016-01-25 2020-01-31 北京四维图新科技股份有限公司 一种行驶轨迹与路网底图的智能匹配方法及装置
CN105788274B (zh) * 2016-05-18 2018-03-27 武汉大学 基于时空轨迹大数据的城市交叉口车道级结构提取方法
US10107631B2 (en) * 2016-08-19 2018-10-23 GM Global Technology Operations LLC Methods and systems for vehicle positioning feedback

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US3069654A (en) 1960-03-25 1962-12-18 Paul V C Hough Method and means for recognizing complex patterns
US20120116678A1 (en) * 2009-05-04 2012-05-10 James Alan Witmer Methods and systems for creating digital transportation networks
WO2016055248A1 (fr) * 2014-10-10 2016-04-14 Here Global B.V. Appareil et procédés associés pour utilisation dans la cartographie des intersections routières au niveau des voies
DE102015000399A1 (de) 2015-01-13 2016-07-28 Audi Ag Kartographieren von Fahrspuren mittels Fahrzeugflottendaten

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
DAVID BETAILLE ET AL: "Creating Enhanced Maps for Lane-Level Vehicle Navigation", IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, IEEE, PISCATAWAY, NJ, USA, vol. 11, no. 4, 1 December 2010 (2010-12-01), pages 786 - 798, XP011336963, ISSN: 1524-9050, DOI: 10.1109/TITS.2010.2050689 *

Also Published As

Publication number Publication date
CN111033591A (zh) 2020-04-17
DE102017216237A1 (de) 2019-03-14
CN111033591B (zh) 2022-06-07

Similar Documents

Publication Publication Date Title
DE112016007047B4 (de) Fahrspur-schätzsystem
WO2019052867A1 (fr) Procédé destiné à calculer un déroulement de voies d'un réseau routier et dispositif de serveur destiné à mettre en œuvre le procédé
DE102017112865A1 (de) Vorrichtung zur automatisierten Fahrsteuerung, System mit derselben, und Verfahren hierfür
DE102015208790A1 (de) Bestimmen einer Trajektorie für ein Fahrzeug
DE102015000399B4 (de) Kartographieren von Fahrspuren mittels Fahrzeugflottendaten
WO2018019465A1 (fr) Procédé, dispositif et support d'informations lisible par ordinateur comprenant des instructions pour déterminer la position latérale d'un véhicule par rapport aux voies de circulation d'une chaussée
EP3391086B1 (fr) Procédé amélioré de détermination de la construction de bord d'une chaussée pour la localisation de véhicules automobiles
WO2019053013A1 (fr) Procédé de détermination de la position d'un véhicule automobile dans une environnement et dispositif de commande d'un véhicule automobile et moyen informatique pour fonctionner sur un réseau de données
DE102020203756A1 (de) Autobahnausfahrt-erfassung und linienspiegelung zur fahrzeugtrajektorien-bestimmung
WO2015197329A1 (fr) Procédé de traitement des données de mesure d'un véhicule en vue de définir le début de la recherche d'un emplacement de stationnement et produit logiciel informatique
EP2963631A1 (fr) Procédé de détermination d'un stationnement à partir d'une pluralité de points de mesure
DE102017208509A1 (de) Verfahren zum Erzeugen eines Straßenmodells während einer Fahrt eines Kraftfahrzeugs sowie Steuervorrichtung und Kraftfahrzeug
WO2016086249A1 (fr) Procédé permettant de déterminer la position d'un véhicule
EP4165375A1 (fr) Procédé de détermination d'un type d'utilisation d'un motif de points de repère destinée à une localisation autonome d'un véhicule, et système de localisation autonome électronique d'un véhicule
DE102013217060B4 (de) Spurgenaue Positionierung eines Fahrzeugs
WO2020193128A1 (fr) Commande d'un véhicule autmobile
DE102019217144A1 (de) Ampelspurzuordnung aus Schwarmdaten
DE102020105313A1 (de) Verfahren, Recheneinrichtung und System zum Kartographieren von Landmarken eines Straßennetzes in einer Straßenkarte
DE102020208378B3 (de) Ampelspurzuordnung aus Schwarmdaten
DE102017011982A1 (de) Verfahren zur Streckenvorausschau
DE102017006142A1 (de) Verfahren zur Lokalisierung eines Fahrzeuges innerhalb eines Fahrstreifens
DE102013217061B4 (de) Spurgenaue Positionierung eines Fahrzeugs
DE102021207528A1 (de) Erkennung von Verbindungsmustern anhand von Trajektoriendaten
WO2022018007A1 (fr) Procédé d'estimation d'un mouvement ego d'un véhicule sur la base de mesures d'un capteur lidar et dispositif informatique
DE102020211331A1 (de) Zuordnung von Ampeln zu zugehörigen Fahrspuren

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18768824

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 18768824

Country of ref document: EP

Kind code of ref document: A1