Method for determining the respective directions of travel of several lanes of a roadway

Abstract

The invention relates to a method for determining the respective directions of travel of several lanes of a roadway, comprising the following steps: Receiving environmental data representing the environment of a motor vehicle traveling on one of the multiple lanes, Detecting lane boundaries and roadway boundaries based on the surrounding data, Calculating a lane model describing the lanes based on the detected lane boundaries and the detected roadway boundaries, Defining an ego lane on which the motor vehicle is currently driving in the lane model, Determining the direction of travel of the ego lane based on a current direction of travel of the motor vehicle, Detecting other motor vehicles approaching and / or driving ahead of the motor vehicle based on the surrounding data, Assigning the detected additional vehicles to the lanes of the lane model, Determine the respective direction of travel of the lanes of the lane model based on the assignment. The invention relates to a device, a computer program and a machine-readable storage medium.

Description

[0001] The invention relates to a method for determining the respective directions of travel of several lanes of a roadway, a device, a computer program and a machine-readable storage medium. State of the art

[0002] The published patent application CN 1 11 479 741 A discloses a method for adapting a movement of a vehicle in an automatic driving mode.

[0003] The published patent application US 2021 / 0072757 A1 discloses a system for mapping a lane marking.

[0004] Patent specification RU 2 766 038 C1 discloses a method for generating information about the surroundings of a vehicle.

[0005] The patent specification DE 10 2010 050 167 B4 discloses a method for lane guidance with a driver assistance system.

[0006] The published patent application US 2016 / 159349 A1 discloses estimating a lane when a vehicle changes lanes. Disclosure of the invention

[0007] The object underlying the invention is to provide a concept for efficiently determining the respective directions of travel of several lanes of a roadway.

[0008] This object is achieved by means of the respective subject matter of the independent claims. Advantageous embodiments of the invention are the subject matter of the respective dependent subclaims.

[0009] According to a first aspect, a method is provided for determining the respective directions of travel of several lanes of a roadway, comprising the following steps: Receiving environmental data representing the environment of a motor vehicle traveling on one of the multiple lanes, Detecting lane boundaries of the lanes and roadway boundaries of the roadway based on the environmental data, calculating a lane model describing the lanes based on the detected lane boundaries and the detected roadway boundaries, Defining an ego lane on which the motor vehicle is currently driving in the lane model, Determining the direction of travel of the ego lane based on a current direction of travel of the motor vehicle, Detecting other motor vehicles approaching and / or driving ahead of the motor vehicle based on the surrounding data, Assigning the detected additional vehicles to the lanes of the lane model, Determine the respective direction of travel of the lanes of the lane model based on the assignment.

[0010] According to a second aspect, a device is provided which is configured to carry out all the steps of the method according to the first aspect.

[0011] According to a third aspect, a computer program is provided which comprises instructions which, when the computer program is executed by a computer, for example by the device according to the second aspect, cause the computer to carry out a method according to the first aspect.

[0012] According to a fourth aspect, a machine-readable storage medium is provided on which the computer program according to the third aspect is stored.

[0013] The invention is based on and incorporates the finding that the above-mentioned object is achieved by first detecting lane boundaries and roadway boundaries based on environmental data representing the environment of a motor vehicle traveling in one of the multiple lanes. Based on the detected boundaries, a lane model is calculated that describes the lanes.

[0014] The lane model then defines an ego lane in which the vehicle is currently traveling, with the direction of travel specified by the ego lane being determined based on the vehicle's current direction of travel. This efficiently determines the direction of travel of the lane in which the vehicle is currently traveling.

[0015] Furthermore, according to the concept described here, it is provided that, based on the surrounding data, other motor vehicles approaching the motor vehicle or the motor vehicles driving ahead are detected. These detected motor vehicles are then assigned to the lanes of the lane model. In other words, the detected additional motor vehicles are each assigned to one of the lanes of the lane model. Based on this assignment, the respective direction of travel of the lanes of the lane model can be efficiently determined. This is because, as a rule, the direction of travel of the motor vehicles is based on the direction of travel of the lanes, unless the driver is traveling the wrong way.In other words, if, for example, oncoming motor vehicles are traveling in a lane, it can be assumed that the direction of travel in that lane is opposite to the direction of travel of the motor vehicle traveling in the ego lane. For example, if motor vehicles are turning left or right in a lane, it can be assumed that this lane is a left-turn lane or a right-turn lane.

[0016] This allows the respective directions of travel of several lanes on a road to be determined efficiently.

[0017] This results in the technical advantage that a concept is provided for efficiently determining the respective directions of travel of several lanes on a roadway.

[0018] The direction of travel of a lane refers to the direction of travel that the lane indicates to motor vehicles or road users driving in that lane.

[0019] The motor vehicle driving in the ego lane can also be called an ego motor vehicle.

[0020] Environmental data within the meaning of the description includes, for example, image data from a camera that is included in the ego vehicle. For example, the ego vehicle captures its surroundings or environment using the image camera. Based on the capture, the camera outputs image data representing the surroundings of the vehicle.

[0021] In one embodiment of the method, it is provided that a respective number of oncoming and / or preceding motor vehicles that are assigned to the same lane is determined, wherein the respective direction of travel of the lanes is determined based on the respective number determined.

[0022] This provides the technical advantage, for example, of efficiently determining the respective direction of travel of the lanes. According to this embodiment, the motor vehicles traveling in the same lane are counted, so that the direction of travel of the lane can be determined from the respective direction of travel of these motor vehicles.

[0023] In one embodiment of the method, it is provided that the respective number is compared with a predetermined threshold value, wherein the respective direction of travel of the lanes is determined based on the respective comparison.

[0024] This provides the technical advantage, for example, of efficiently determining the respective lane direction. By specifying an appropriate threshold, road users or vehicles that do not adhere to a lane direction can be efficiently prevented from generating an incorrect result regarding the lane direction.

[0025] It is therefore assumed that the majority of road users or motor vehicles adhere to the direction of travel in the lanes or only occasionally change to the opposite lane to overtake.

[0026] In one embodiment of the method, it is provided that, if the respective number is greater than or greater than or equal to the predetermined threshold value, the lane corresponding to the respective number is assigned as a lane ahead of the motor vehicle or as an oncoming lane, depending on whether the other motor vehicles are driving ahead of the motor vehicle in the corresponding lane or are coming towards the other motor vehicles, wherein the respective direction of travel of the lanes is determined based on the assignment as a lane ahead or as an oncoming lane.

[0027] This provides the technical advantage, for example, that the respective direction of travel of the lanes can be determined efficiently.

[0028] In one embodiment of the method, it is provided that one or more arrows applied to the lanes are detected based on the environmental data, wherein the respective direction of travel of the lanes is determined based on the arrow(s) detected.

[0029] This provides the technical advantage, for example, of efficiently determining the direction of travel in each lane. Detected arrows can be used, for example, for plausibility checks.

[0030] In one embodiment of the method, it is provided that after the motor vehicle turns, a lane traveled by the motor vehicle immediately before the turn is defined as a lane for the direction of travel corresponding to the turn, wherein the direction of travel of this one lane is determined based on the definition.

[0031] This provides the technical advantage, for example, that the direction of travel of that lane can be determined efficiently. This allows, for example, a direction of travel determined initially for that lane to be corrected after a turn.

[0032] In one embodiment of the method, it is provided that a respective lateral distance of the detected boundaries to the motor vehicle is determined, wherein the ego lane is defined based on the determined lateral distances.

[0033] This provides the technical advantage, for example, that the ego lane can be determined efficiently.

[0034] In one embodiment of the method, it is provided that the lane whose boundaries have the smallest lateral distance of the determined distances to the motor vehicle is defined as the ego lane.

[0035] This provides the technical advantage, for example, that the ego lane can be determined efficiently.

[0036] "Delimiting" refers specifically to lane markings or roadway markings. In other words, a lane can be delimited by a roadway marking on one side and a lane marking on the other. For example, a lane can be delimited by lane markings on both sides.

[0037] In one embodiment of the method, it is provided that, for calculating the lane model, lanes are defined as an area between two detected boundaries whose lateral distance from one another is less than or equal to a predetermined distance threshold.

[0038] This provides the technical advantage, for example, that the lanes can be defined efficiently so that the lane model can be calculated efficiently.

[0039] In one embodiment of the method, it is provided that the detected boundaries are defined in a three-dimensional motor vehicle coordinate system (3D coordinate system).

[0040] This provides the technical advantage, for example, that the detected boundaries can be defined efficiently.

[0041] The motor vehicle coordinate system is therefore a coordinate system that is defined in relation to the motor vehicle.

[0042] The 3D coordinate system refers in particular to the coordinates of the objects in the world relative to the car. In an image recorded by a video camera, for example, a two-dimensional (2D) image coordinate system (e.g., with the unit pixel) is initially used. In such a 2D image coordinate system, for example, the relative position of the objects to one another cannot be clearly determined because, for example, a distance estimate is missing. The 3D coordinates are determined, for example, using common methods known to those skilled in the art and are thus available for the method described here. With them, for example, the motor vehicle objects, i.e., the detected motor vehicles, (and in particular, arrow objects, i.e., the detected arrows,) can be assigned to the lanes in space.

[0043] For example, the method is a computer-implemented method.

[0044] For example, the device is programmed to execute the computer program.

[0045] Process features result analogously from corresponding device features, and vice versa. This means that the technical functionalities of the process result analogously from the corresponding technical functionalities of the device, and vice versa.

[0046] An arrow in the sense of the description is, for example, a directional arrow or is, for example, an advance warning arrow.

[0047] Directional arrows are, for example, placed on lanes at intersections, such as intersections or junctions, and enable road users to orient themselves early and select the desired direction of travel.

[0048] For example, an advance warning arrow indicates the end of a lane or announces a lane boundary.

[0049] The embodiments and exemplary embodiments described here can be combined with one another in any manner, even if this is not explicitly described.

[0050] The invention is explained in more detail below using preferred embodiments. Fig. 1 a flowchart of a method according to the first aspect, Fig. 2 a device according to the second aspect, Fig. 3 a machine-readable storage medium according to the fourth aspect and Fig. 4 an intersection.

[0051] Fig. 1 shows a flowchart of a method for determining the respective directions of travel of several lanes of a roadway, comprising the following steps: Receiving 101 environmental data representing an environment of a motor vehicle traveling on one of the multiple lanes, Detecting 103 lane boundaries of the lanes and roadway boundaries of the roadway based on the environmental data, calculating 105 a lane model describing the lanes based on the detected lane boundaries and the detected roadway boundaries, Determining 107 an ego lane on which the motor vehicle is currently driving in the lane model, Determining 109 the direction of travel of the ego lane based on a current direction of travel of the motor vehicle, Detecting 111 other motor vehicles approaching and / or driving ahead of the motor vehicle based on the surrounding data, Assigning 113 of the detected additional vehicles to the lanes of the lane model, Determining 115 the respective direction of travel of the lanes of the lane model based on the assignment.

[0052] Fig. 2 shows a device 201 which is configured to carry out all steps of the method according to the first aspect.

[0053] For example, the device 201 comprises an input configured to receive the environmental data.

[0054] For example, the device 201 comprises a computing unit which is configured to carry out or perform the steps of detecting the lane boundaries, calculating the lane model, defining the ego lane, determining the direction of travel of the ego lane, detecting the other motor vehicles, assigning the other motor vehicles to the lanes of the lane model and determining the direction of travel of the lanes of the lane model.

[0055] For example, the device 201 comprises an output which is configured to output a result of determining the respective direction of travel of the lanes of the lane model.

[0056] Fig. 3 shows a machine-readable storage medium 301 on which a computer program 303 is stored. The computer program 303 includes instructions that, when executed by a computer, cause the computer program 303 to execute a method according to the first aspect.

[0057] Fig. Figure 4 shows an intersection 401. A first street 403 and a second street 405 intersect. The first street 403 runs vertically relative to the plane of the paper, i.e., from top to bottom. The second street 405 runs from left to right, or horizontally, relative to the plane of the paper.

[0058] The first road 403 comprises a carriageway 407, indicated by a curly bracket. The carriageway 407 comprises four lanes: a first lane 409, a second lane 411, a third lane 413, and a fourth lane 415.

[0059] From left to right on the paper plane, the lanes are arranged in the following order: the first lane 409, then the second lane 411, then the third lane 413 and then the fourth lane 415.

[0060] A motor vehicle 417, which can be referred to as an ego vehicle, is traveling in the third lane 413. Another motor vehicle 419 is traveling in the fourth lane 415. Another motor vehicle 421 is traveling in the second lane 411.

[0061] A left lane boundary of lane 407 is identified by reference numeral 423. A right lane boundary of lane 407 is identified by reference numeral 425.

[0062] The lane markings of lanes 409, 411, 413, 415 are marked with reference number 427.

[0063] Before intersection 401, a straight-ahead arrow 429 is displayed on the third lane 413. Before intersection 401, a right-turn arrow 431 is displayed on the fourth lane 415.

[0064] A direction of travel of the further motor vehicle 421 is marked with an arrow with the reference number 423, which points from top to bottom with respect to the plane of the paper.

[0065] A direction of travel of the ego motor vehicle 417 is marked with the reference number 435, which points from bottom to top with respect to the plane of the paper.

[0066] A direction of travel of the further motor vehicle 419 is marked with the arrow with the reference number 437, which runs from bottom to top with respect to the plane of the paper.

[0067] Thus, motor vehicle 421 is a motor vehicle traveling toward the ego motor vehicle 417. Motor vehicle 419 is a motor vehicle traveling ahead of the ego motor vehicle 417.

[0068] The ego motor vehicle 417 includes, for example, one or more cameras (not shown) that capture an environment or surroundings of the ego motor vehicle 417 and output corresponding environment data, in this case image data, based on the capture. Based on this environment data, the lane boundaries 427 can be detected. Furthermore, the left lane boundary 423 and the right lane boundary 425 can be detected based on this environment data.

[0069] Based on this information, i.e., based on the detected boundaries, a lane model describing lanes 409, 411, 413, and 415 can be calculated. The boundaries can, for example, be extrapolated, so that, in addition to the detected boundaries, the corresponding steps can be performed based on the extrapolated boundaries.

[0070] For example, it is intended that the detected boundaries are defined or specified in a three-dimensional coordinate system of the ego vehicle 417.

[0071] An ego lane is defined, which the motor vehicle 417, i.e., the ego motor vehicle, is currently traveling in. In this case, the ego lane is the third lane 413, i.e., the third from the left or the second from the right.

[0072] Furthermore, oncoming motor vehicles and other motor vehicles driving ahead are detected based on the surrounding data, whereby the detected other motor vehicles can be defined or specified with reference to the three-dimensional motor vehicle coordinate system.

[0073] The detected additional motor vehicles are each assigned to one of the lanes of the lane model. In this case, motor vehicle 421 is assigned to the second lane 411. The additional motor vehicle 419 is assigned to the fourth lane 415. The additional motor vehicles are thus assigned to the lanes of the lane model on the basis of the three-dimensional coordinates in relation to the coordinates of the lane model. For example, it is provided that a respective number of oncoming and preceding motor vehicles that are assigned to the same lane are counted. If, for example, a difference between the number of oncoming and preceding motor vehicles exceeds a threshold value for a lane or is equal to the threshold value, this lane is determined or defined as an oncoming or preceding lane with respect to the ego motor vehicle.

[0074] Furthermore, it is planned, for example, that the arrows applied to the roadway or individual lanes are detected based on the image data. In this case, these are the two arrows 429 and 431. These arrows are then also assigned to a lane. This assignment can be performed in the three-dimensional vehicle coordinate system.

[0075] Lanes with matching arrows for the directions of travel, i.e. oncoming or preceding or ahead, are defined as lanes for the corresponding directions.

[0076] Lanes with appropriate road arrows for the directions of travel (left / straight / right / mixed) are defined as lanes for the corresponding turning or straight-ahead directions.

[0077] As soon as the ego vehicle 417 has crossed the intersection 401 and, for example, has turned or taken a desired direction, the previously traveled lane is defined as the lane for the chosen direction of travel. In this way, any misallocations made before crossing can be subsequently corrected.

[0078] Due to the concept described here, an estimate of the direction of travel is available before crossing, which can then be corrected if necessary so that this corrected estimate can be reliably used, for example, for a high-resolution map.

[0079] Thus, in particular, a concept is provided for efficiently determining the respective directions of travel of multiple lanes on a roadway. Accordingly, based on this information, a navigation system can, for example, suggest the most suitable lane for a motor vehicle. For example, a driver assistance system can warn a motor vehicle driver that they are about to cross into the oncoming lane, thus avoiding an accident or collision with another motor vehicle.

[0080] The result, i.e., the determined directions of travel, can be stored in a central database, such as a map database, so that this information can be made available to a variety of other vehicles. This allows, for example, high-resolution road maps to be updated with information about currently available or closed lanes.

[0081] For example, it is planned that the environmental data from a large number of motor vehicles will be provided so that a large amount of data is available which can be used to determine the respective direction of travel of the lanes, which can significantly improve the accuracy of determining the direction of travel.

[0082] This is particularly advantageous when threshold values ​​are specified to define or determine the respective direction of travel of the lanes. QUOTES CONTAINED IN THE DESCRIPTION

[0000] This list of documents submitted by the applicant was generated automatically and is included solely for the convenience of the reader. This list is not part of the German patent or utility model application. The DPMA assumes no liability for any errors or omissions. Cited patent literature

[0000] CN 1 11 479 741 A

[0002] US 2021 / 0072757 A1

[0003] RU 2 766 038 C1

[0004] DE 10 2010 050 167 B4

[0005] US 2016 / 159349 A1

[0006]

Claims

[1] Method for determining the respective directions of travel of several lanes (409, 411, 413, 415) of a roadway (407), comprising the following steps: Receiving (101) environmental data representing an environment of a motor vehicle (417) traveling on one of the plurality of lanes (409, 411, 413, 415), Detecting (103) lane boundaries (427) of the lanes (409, 411, 413, 415) and roadway boundaries (423, 425) of the roadway (407) based on the environmental data, Calculating (105) a lane model describing the lanes (409, 411, 413, 415) based on the detected lane boundaries (427) and the detected roadway boundaries (423, 425), Determining (107) an ego lane (413) on which the motor vehicle (417) is currently traveling in the lane model, Determining (109) the direction of travel of the ego lane (413) based on a current direction of travel of the motor vehicle (417), Detecting (111) other motor vehicles (419, 421) approaching and / or traveling ahead of the motor vehicle (417) based on the environmental data, Assigning (113) the detected further motor vehicles (419, 421) to the lanes (409, 411, 413, 415) of the lane model, determining (115) the respective direction of travel of the lanes (409, 411, 413, 415) of the lane model based on the assignment. [2] Method according to claim 1, wherein a respective number of oncoming and / or preceding further motor vehicles (419, 421) is determined which are assigned to a same lane (409, 411, 413, 415), wherein the respective direction of travel of the lanes (409, 411, 413, 415) is determined based on the respectively determined number. [3] Method according to claim 2, wherein the respective number is compared with a predetermined threshold value, wherein the respective direction of travel of the lanes (409, 411, 413, 415) is determined based on the respective comparison. [4] Method according to claim 3, wherein, if the respective number is greater than or greater than or equal to the predetermined threshold value, the lane corresponding to the respective number is assigned as a lane ahead of the motor vehicle (417) or as an oncoming lane, depending on whether the further motor vehicles (419, 421) are driving ahead of the motor vehicle (417) in the corresponding lane or are coming towards it, wherein the respective direction of travel of the lanes (409, 411, 413, 415) is determined based on the assignment as a lane ahead or as an oncoming lane. [5] Method according to one of the preceding claims, wherein, based on the environmental data, one or more arrows (429, 431) applied to the lanes (409, 411, 413, 415) are detected, wherein the respective direction of travel of the lanes (409, 411, 413, 415) is determined based on the detected arrow(s) (429, 431). [6] Method according to one of the preceding claims, wherein after a turn of the motor vehicle (417), a lane travelled by the motor vehicle (417) immediately before the turn is defined as a lane for the direction of travel corresponding to the turn, wherein the direction of travel of this one lane is determined based on the definition. [7] Method according to one of the preceding claims, wherein a respective lateral distance of the detected boundaries to the motor vehicle (417) is determined, wherein the ego lane (413) is defined based on the determined lateral distances. [8] Method according to claim 7, wherein the lane is defined as the ego lane (413) whose boundaries have the smallest lateral distance of the determined distances to the motor vehicle (417). [9] Method according to one of the preceding claims, wherein, for calculating the lane model, lanes (409, 411, 413, 415) are defined as an area between two detected boundaries whose lateral distance from one another is less than or equal to a predetermined distance threshold value. [10] Method according to one of the preceding claims, wherein the detected boundaries are defined in a three-dimensional motor vehicle coordinate system. [11] Device (201) which is arranged to carry out all the steps of the method according to one of the preceding claims. [12] Computer program (303) comprising instructions which, when the computer program (303) is executed by a computer, cause the computer to carry out a method according to one of claims 1 to 10. [13] Machine-readable storage medium (301) on which the computer program (303) according to claim 12 is stored.

Images