Method for creating a virtual lane

Abstract

The invention relates to a method for creating a virtual lane, to a computer program product, to a control device for a vehicle, and to a vehicle. The method for creating a virtual lane of an ego vehicle (100) comprises the following steps: a) determining (S1) trajectories (401, 501, 601) of at least two different lane markings (400, 500, 600) in the surroundings of the ego vehicle (100); b) determining (S2) a trajectory (201, 301) of at least one vehicle (200, 300) driving in front; c) comparing (S3) the determined trajectory (201, 301) of the at least one vehicle (200, 300) driving in front with trajectories (401, 501, 601) of the at least two different lane markings (400, 500, 600); d) creating (S4) the virtual lane depending on the comparison carried out in step c).

Description

[0001] METHOD FOR CREATING A VIRTUAL LANE

[0002] The present invention relates to a method for creating a virtual lane, a computer program product, a control device for a vehicle and a vehicle.

[0003] When driving, especially on motorways, situations arise in which roadworks change the layout of the lanes. Lanes are usually narrowed and diverted onto the hard shoulder so that the work can be carried out. To mark lanes within roadworks, differently coloured lane markings are often used. These lane markings have a shorter lifespan on the asphalt as they are only temporarily attached and are intended to be removed without leaving any residue. This leads to situations in which these differently coloured lane markings are only partially present. In addition to the fact that conventional lane departure warning systems cannot easily distinguish the differently coloured temporary lane markings from normal lane markings, the lack of differentiation, and in particular the lack of temporary lane markings, means that lane departure warning systems usually deactivate within roadworks.It is particularly advantageous, especially in narrow lanes within a construction site, if the driver of a vehicle is supported by a lane keeping assistant.

[0004] US 2018 / 247138 A1 discloses a method and a device for generating a virtual lane. The method comprises generating a virtual lane, for example, from an image depicting a section in front of the vehicle. Furthermore, the validity of the generated virtual lane is checked based on objects present in the image. For example, a warning sign, e.g., indicating that the lane is closed, can be detected in the image, and in response, the generated virtual lane can be discarded.

[0005] Against this background, one object of the present invention is to provide an improved method for creating a virtual lane. According to a first aspect, a method for creating a virtual lane of an ego vehicle is provided. The method comprises the following steps: a) determining trajectories of at least two different lane markings in the environment of the ego vehicle; b) determining a trajectory of at least one preceding vehicle; c) comparing the determined trajectory of the at least one preceding vehicle with trajectories of the at least two different lane markings; d) creating the virtual lane depending on the comparison in step c).

[0006] This method has the advantage that a virtual lane is created not only based on the determined trajectory of the lane markings, but also based on the presence of a vehicle ahead. This creates a virtual lane with greater confidence than if only the lane markings were taken into account. In particular, this minimizes the likelihood of an erroneous virtual lane, which could arise, for example, due to missing markings or problems distinguishing between temporary lane markings and normal lane markings.

[0007] If at least two different lane markings are detected in the vicinity of the ego vehicle, a trajectory is determined for each of the lane markings. The trajectory of the lane markings is the direction in which the lane runs. The trajectory is formed, for example, from the paths of a pair of lane markings (right and left lane markings) and the center of the lane.

[0008] At least one preceding vehicle is detected, and a trajectory of the preceding vehicle is also determined. The trajectory is determined, for example, from the position, orientation, and the like of the preceding vehicle. In step c), the trajectory of the preceding vehicle is compared with the at least two trajectories of the detected lanes. The trajectory of the preceding vehicle is compared with each trajectory of the detected lanes.

[0009] Based on this comparison, the virtual lane is created. The created virtual lane can be displayed, for example, to the driver of the ego vehicle via a display unit and / or transmitted via an interface to a driver assistance system, such as a lane keeping assistant.

[0010] According to one embodiment, the trajectory of the preceding vehicle is determined using one or more sensors of the ego vehicle.

[0011] The one or more sensors of the ego vehicle are configured to collect data about at least one vehicle ahead. This data is then used to determine the trajectory of the vehicle ahead.

[0012] According to one embodiment, the trajectory of the preceding vehicle is determined from data received from the ego vehicle.

[0013] The trajectory can also be determined from data received by the ego vehicle from the vehicle ahead. The ego vehicle has a receiver configured to receive data from other vehicles. One possibility for this is, for example, interconnected vehicles, such as in car-to-car communication. For example, the camera data from the vehicle ahead can also be received, allowing the ego vehicle to determine the further course of the lane.

[0014] According to one embodiment, the created virtual lane has virtual lane markings that correspond to one of the at least two different detected lane markings. Accordingly, the virtual lane is not a theoretical lane, but rather corresponds to one of the two detected lane markings. This ensures that the vehicle is not traveling in a nonexistent lane, but rather that the vehicle is traveling in a predetermined lane.

[0015] According to one embodiment, the virtual lane has at least a specified minimum width.

[0016] A specified minimum width ensures, on the one hand, that the virtual lane is selected so that the ego vehicle can drive in it. On the other hand, specifying a minimum width ensures that the virtual lane actually corresponds to a real lane and that no errors occurred during the creation of the virtual lane. The minimum width corresponds, for example, to the vehicle's width. The minimum width can also be set by the vehicle driver themselves, for example, if the entered value is not less than the vehicle's width.

[0017] According to one embodiment, in step d) the virtual lane is determined depending on the correspondence of the trajectory of the preceding vehicle with the trajectories of the at least two different lane markings.

[0018] The match can, for example, be a similarity or match between the trajectory of the vehicle ahead and the trajectory of the lane markings. The orientation or direction of the trajectories plays an important role in this.

[0019] According to one embodiment, the different lane markings differ in their color and / or shape. To distinguish the temporary lane markings from normal lane markings, they differ, for example, in their color and / or shape. Road markings that are glued to the road surface usually differ in their color, while temporary road markings differ from normal road markings in their shape and, in particular, in their position.

[0020] According to one embodiment, the at least two different lane markings are detected by a sensor of the ego vehicle.

[0021] The road markings are detected by one or more sensors, the sensor preferably being a camera.

[0022] According to one embodiment, the lane markings are assigned a priority depending on their color and / or their shape, which priority is taken into account in the comparison in step d).

[0023] Accordingly, temporary lane markings, for example, have a higher priority than regular lane markings. Prioritizing a lane marking is also advantageous in that, if more than two lane markings are present, the trajectory of the vehicle ahead only needs to be compared with the trajectories of the two highest-priority lane markings. This saves computing power, and the created virtual lane is available to the driver of the ego vehicle or the driver assistance system more quickly.

[0024] According to one embodiment, a driver assistance system of the ego vehicle is configured to receive the virtual lane created in step d) and to steer the ego vehicle according to the virtual lane. The created virtual lane is output, for example, to the control unit of the ego vehicle, and the control unit is configured to steer the vehicle according to the virtual lane.

[0025] According to a second aspect, a computer program product is proposed which comprises instructions which, when the program is executed by a computer, cause the computer to carry out the method described above according to the first aspect.

[0026] A computer program product according to the second aspect, such as a computer program means, can be provided or delivered, for example, as a storage medium, such as a memory card, USB stick, CD-ROM, DVD, or in the form of a downloadable file from a server in a network. This can be done, for example, in a wireless communications network by transmitting a corresponding file with the computer program product or the computer program means.

[0027] According to a third aspect, a control unit for a vehicle for creating a virtual lane is provided. The control unit comprises a processor unit and a memory unit on which means for executing the method according to the preceding embodiments are stored.

[0028] The control unit (for example in the form of the central vehicle control unit or electronic control unit - "ECU") is particularly designed to process the computer program product described above for creating a virtual lane, for example on the processor unit of the control unit.

[0029] The respective unit, for example, the processor unit, can be implemented in hardware and / or software. In a hardware implementation, the respective unit can be configured, for example, as a computer or a microprocessor. In a software implementation, the respective unit can be configured as a computer program product, as a function, as a routine, as an algorithm, as part of a program code, or as an executable object. Furthermore, each of the units mentioned here can also be configured as part of a higher-level control system of the vehicle, such as a central electronic control device and / or an engine control device.

[0030] According to a fourth aspect, a vehicle is provided. The vehicle comprises one or more sensors and a control unit according to the third aspect.

[0031] The sensors of the ego vehicle can be, for example, radar sensors, LiDAR sensors, ultrasonic sensors, and / or cameras (as already described above). The ego vehicle can have one sensor of one type, multiple sensors of one type, and / or multiple sensors of multiple types. Advantageously, the ego vehicle has multiple sensors of multiple types. In particular, the ego vehicle has a camera, which is advantageously arranged in the center of the front of the ego vehicle, oriented in the direction of travel. Such a front camera can be arranged, for example, at the upper end of the windshield in the region of the rearview mirror.

[0032] Steps a), b), c), etc., can also occur in a different order. The presence of steps a) and c) does not require an intermediate step b), etc. "One" does not exclude a plurality.

[0033] Further possible implementations of the invention also include combinations of features or embodiments described above or below with respect to the exemplary embodiments that are not explicitly mentioned. In this case, the person skilled in the art will also add individual aspects as improvements or additions to the respective basic form of the invention.

[0034] Further advantageous embodiments and aspects of the invention are the subject of the dependent claims and the exemplary embodiments of the invention described below. The invention will be explained in more detail below using preferred embodiments with reference to the accompanying figures.

[0035] Fig. 1 shows a schematic plan view of a vehicle with a control unit configured to carry out a method for creating a virtual lane according to one embodiment;

[0036] Fig. 2 shows a schematic view of a situation in which the method for creating a virtual lane is carried out according to an embodiment;

[0037] Fig. 3 shows a flowchart of a method for creating a virtual lane according to an embodiment;

[0038] Fig. 4 shows a further schematic view of a situation in which the method for creating a virtual lane is carried out according to an embodiment; and

[0039] Fig. 5 shows another flowchart of a method for creating a virtual lane according to an embodiment.

[0040] In the figures, identical or functionally equivalent elements have been given the same reference numerals unless otherwise stated.

[0041] Fig. 1 shows a schematic top view of a vehicle 100 with a control unit 103 and a sensor 102 according to one embodiment. In the example of Fig. 1, the vehicle 100 is a motor vehicle, in particular a passenger car. The sensor 102 is designed, for example, as part of a driver assistance system. A method for creating a virtual lane is designed, for example, as a software component of a driver assistance system. The driver assistance system serves, for example, to support a driver of the vehicle 100. Furthermore, the driver assistance system can be designed for semi-autonomous or fully autonomous operation of the vehicle 100.The driver assistance system is configured, for example, to control components of the vehicle, such as an engine control unit 104, a braking unit 106, and in particular a steering unit 107, so that driver assistance, semi-autonomous operation, and / or fully autonomous operation can be performed. The driver assistance system is configured, for example, for operation at higher speeds, such as those encountered on a country road or a highway. Furthermore, the driver assistance system is configured for operation at lower speeds, such as those encountered on inner-city roads.

[0042] Sensor 102 here is a camera, in particular a front camera, and, as shown in Fig. 1, is arranged in the center of the front of vehicle 100. Sensor 102 is connected wirelessly and / or by wire to control unit 103 for transmitting sensor data. Vehicle 100 preferably includes additional sensors (not shown in Fig. 1) configured to detect the driving state of vehicle 100 and to detect the surroundings of vehicle 100. Examples of such sensors of vehicle 100 are a radar (radio detection and ranging) or a lidar (light detection and ranging), ultrasonic sensors, location sensors, wheel angle sensors, and / or wheel speed sensors. The additional sensors are each configured to provide sensor data, for example, to control unit 103 and / or to the driver assistance system.

[0043] The control unit 103 has a processor unit and a memory unit (not shown in Fig. 1), which are configured to carry out the method described below for creating a virtual lane during operation of the vehicle 100. The control unit 103 is configured to receive sensor data, in particular from the sensor 102. Data connections of the control unit 103 to vehicle components are identified by the reference numeral 105, wherein data connections represent lines, data lines, a vehicle bus and / or wireless data transmission. In the exemplary representation of the vehicle 100 in Fig. 1, the control unit 103 is connected to the engine control device 104 and configured to transmit data to the engine control device 104 wirelessly and / or via a wire.The transmitted data contains, for example, control signals which cause the engine control device 104 to accelerate and / or decelerate the vehicle 100.

[0044] Furthermore, the control unit 103 in Fig. 1 is connected to the braking device 106. The control unit 103 transmits data wirelessly and / or wired to the braking device 106 of the vehicle 100, wherein the data contains, for example, control signals. These control signals cause the braking device 106 to brake the vehicle 100.

[0045] The control unit 103 in Fig. 1 is connected, in particular, to a steering device 107 of the vehicle 100. The control unit 103 transmits data wirelessly and / or wired to the steering device 106 of the vehicle 100, wherein the data contains, for example, control signals. These control signals cause the steering device 107 to change a steering angle of the vehicle 100, for example, depending on the created virtual lane.

[0046] Furthermore, the control unit 103 has a computer program product which has program code means stored on a computer-readable medium in order to be able to carry out the method for creating a virtual lane described below.

[0047] Fig. 2 shows a situation in which the method for creating a virtual lane is implemented. Fig. 3 shows a flowchart illustrating the individual process steps.

[0048] Fig. 2 is a plan view of a situation often encountered at construction sites on motorways, but also on country roads or in built-up areas. On the roadway there is a first lane marking 400 and a second lane marking 500. The first lane marking 400 is the normal lane marking (permanent lane marking), while the second lane marking 500 (temporary lane marking) was applied to guide the traffic within the construction site. The two lane markings differ, for example, in their colors; for example, the first lane marking 400 is white and the second lane marking is yellow. In Fig. 2, the two lane markings also differ in their shapes. The first lane marking 400 is a dashed line, while the second lane marking 500 is a solid line. The ego vehicle 100, which corresponds to the ego vehicle 100 from Fig.

[0049] 1, detects the two different lane markings using the sensor 102. The sensor 102 is, for example, a camera, and the lane markings are detected in the captured image using an image recognition routine or an image recognition program.

[0050] For each of the two detected lane markings 400, 500, a trajectory 401, 501 is determined (see S1 in Fig. 3). The trajectory of the lane marking represents the course of the lane resulting from the lane markings. Fig. 2 shows, as examples, the trajectory 401 of the first lane marking 400 and the trajectory 501 of the second lane marking 500.

[0051] The ego vehicle 100 then determines a trajectory 201 of a first preceding vehicle 200 (see step S2 in Fig. 3). This trajectory 201 is also determined using sensor data from the ego vehicle 100. For example, the orientation, wheel angle, and the like are used as parameters for determining the trajectory of the preceding vehicle.

[0052] The trajectory 201 of the first preceding vehicle 200 thus determined is then compared in step S3 (see Fig. 3) with the two trajectories 401, 501 of the lane markings 400, 500. This comparison determines a similarity or correspondence between the trajectory 201 of the first preceding vehicle 200 and the respective trajectory 401, 501 of the first and second lane markings 400, 500. In the example illustrated in Fig. 2, a greater similarity or correspondence is found between the trajectory 201 of the first preceding vehicle and the trajectory 501 of the second lane marking 500 than with the trajectory 401 of the first lane marking 400.

[0053] Depending on the comparison in step S3, a virtual lane is created in step S4. Based on the greater similarity between the trajectory 201 of the first preceding vehicle 200 and the trajectory 501 of the second lane marking 500, a virtual lane is created that corresponds to the second lane marking 500.

[0054] The created virtual lane has at least a minimum width b. This minimum width b is used to check whether the created virtual lane is a valid virtual lane that can be driven by the ego vehicle 100.

[0055] Furthermore, if, as in Fig. 2, a second preceding vehicle 300 is detected, for example, in a lane next to the ego vehicle, the trajectory 301 of the second preceding vehicle 300 is also determined. The trajectory 301 of the second preceding vehicle 300 can be determined in the same way as the trajectory 201 of the first preceding vehicle 200. The trajectory 301 of the second preceding vehicle 300 thus determined is then compared with the trajectory of the created virtual lane. A match between the two trajectories is also determined. This allows the created virtual lane to be checked again for validity.

[0056] The virtual lane thus created can then be output to the driver of the ego vehicle 100, for example, via a display unit. Furthermore, the created virtual lane can be output, for example, to the control unit 103 of the ego vehicle 100, wherein the driver assistance system or a lane keeping assistance system (here also referred to as "lane keeping assistant") is configured to steer the ego vehicle 100 semi- and / or fully autonomously along the created virtual lane. Furthermore, the control unit 103 of the ego vehicle 100 can be configured to assist the driver in steering and to control the steering device 107 of the ego vehicle in such a way that the driver is supported in maintaining the created virtual lane. The lane keeping assistance system can be configured as part of the driver assistance system.

[0057] Fig. 4 shows a similar situation to Fig. 2, also with the ego vehicle 100 from Fig. 1. In addition or alternatively to the temporary second lane marking 500, as also present in Fig. 2, in other embodiments, a lane is also separated by colored, for example, orange, cones, i.e., a third lane marking 600. The method steps for determining a virtual lane are shown in Fig. 5.

[0058] A preceding vehicle 200 is located in the same lane as the ego vehicle 100. In step S10 (see Fig. 5), the ego vehicle determines the trajectory 201 of the preceding vehicle 200. The trajectory of the preceding vehicle 200 can be determined depending on sensor data of the ego vehicle 100.

[0059] In a second step S11, the ego vehicle 100 detects the three different lane markings 400, 500, 600. The ego vehicle 100 is configured to detect the different lane markings, for example, using image recognition software. Furthermore, the ego vehicle 100 is configured to prioritize the lane markings depending on their color and / or shape. A priority for the lane markings can be stored, for example, in the driver assistance system. For example, normal lane markings have a low priority, lane markings used in construction sites have a medium priority, and lane markings that are only temporarily installed, such as cones or warning beacons, have a high priority. Accordingly, the ego vehicle 100 assigns a higher priority to the third lane marking 600 than to the second lane marking 500.The second lane marking 500 is assigned a higher priority than the first lane marking 400.

[0060] The prioritization is advantageous, for example, in that a virtual lane can be created more quickly because the trajectory 201 of the preceding vehicle 200 only needs to be compared with the trajectories 501, 601 of the highest-priority lane markings 500, 600.

[0061] Accordingly, in step S12 (see Fig. 5), the trajectories 501, 601 for the second lane marking 500 and the third lane marking 600 are determined. The trajectories can be determined using sensor data from the ego vehicle 100. Due to the assigned low priority, preferably no trajectory for the first lane marking 400 is created.

[0062] In step S13 (see Fig. 5), the determined trajectory 201 of the first preceding vehicle 200 is compared with the two trajectories 501, 601 of the second and third lane markings 500, 600. For this purpose, the trajectory of the preceding vehicle 200 is compared with one of the trajectories 501, 601 of the second and third lane markings 500, 600, or a similarity is determined. According to the example shown in Fig. 4, there is a greater similarity between the trajectory 201 of the first preceding vehicle 200 and the trajectory 601 of the third lane marking 600 than between the trajectory 201 of the preceding vehicle 200 and the trajectory 501 of the first lane marking 500.

[0063] Based on this comparison and the determined similarity or correspondence, a virtual lane is created in step S15. Based on the greater similarity between the trajectory 201 of the first preceding vehicle and the trajectory 601 of the third lane marking 600, a virtual lane is created that corresponds to the third lane marking 600.

[0064] As explained with reference to Figs. 2 and 3, the virtual lane created in this way is output to the driver of the ego vehicle 100, for example, via a display unit.

[0065] Furthermore, the created virtual lane can be used, for example, by a driver assistance system to control the ego vehicle.

[0066] Although the present invention has been described using exemplary embodiments, it can be modified in many ways.

[0067] LIST OF REFERENCE SYMBOLS

[0068] 100 Ego Vehicle

[0069] 102 Sensor

[0070] 103 Control unit

[0071] 104 Engine control unit

[0072] 105 Data connection

[0073] 106 Braking device

[0074] 107 Steering device

[0075] 200 first vehicle ahead

[0076] 201 Trajectory (of the first vehicle ahead)

[0077] 300 second vehicle ahead

[0078] 301 Trajectory (of the second vehicle ahead)

[0079] 400 first lane marking

[0080] 401 Trajectory (of the first lane marking)

[0081] 500 second lane marking

[0082] 501 Trajectory (of the second lane marking)

[0083] 600 third lane marking

[0084] 601 Trajectory (of the third lane marking) b minimum width

[0085] S1 to S4 process steps

[0086] S10 to S14 process steps

Claims

PATENT CLAIMS 1. Method for creating a virtual lane of an ego vehicle (100) with the steps: a) determining (S1) trajectories (401, 501, 601) of at least two different lane markings (400, 500, 600) in the surroundings of the ego vehicle (100); b) determining (S2) a trajectory (201, 301) of at least one vehicle (200, 300) traveling ahead; c) comparing (S3) the determined trajectory (201, 301) of the at least one vehicle (200, 300) traveling ahead with trajectories (401, 501, 601) of the at least two different lane markings (400, 500, 600); d) Creating (S4) the virtual lane depending on the comparison in step c).

2. The method according to claim 1, wherein the trajectory (201, 301) of the preceding vehicle (200, 300) is determined using one or more sensors of the ego vehicle (100).

3. The method according to claim 1, wherein the trajectory (201, 301) of the preceding vehicle (200, 300) is determined from data received from the ego vehicle (100).

4. Method according to one of the preceding claims, wherein the created virtual lane has virtual lane markings that correspond to one of the at least two different recognized lane markings (400, 500, 600).

5. Method according to one of the preceding claims, wherein the virtual lane has at least a specified minimum width (b).

6. Method according to one of the preceding claims, wherein in step d) the virtual lane is determined as a function of the correspondence of the trajectory (201, 301) of the preceding vehicle (200, 300) with the trajectories (401, 501, 601) of the at least two different lane markings (400, 500, 600).

7. Method according to one of the preceding claims, wherein the different lane markings (400, 500, 600) differ in their color and / or shape.

8. The method according to any one of the preceding claims, wherein the at least two different lane markings (400, 500, 600) are detected by a sensor (102) of the ego vehicle (100).

9. Method according to one of the preceding claims, wherein the lane markings (400, 500, 600) are assigned a priority depending on their color and / or their shape, which priority is taken into account in the comparison in step d).

10. The method according to any one of the preceding claims, wherein a driver assistance system of the ego vehicle (100) is configured to receive the virtual lane created in step d) and to control the ego vehicle (100) according to the virtual lane.

11. A computer program product comprising instructions which, when executed by a computer, cause the computer to carry out the method according to any one of claims 1-10.

12. A control unit (103) for a vehicle (100) for creating a virtual lane, comprising: a processor unit; and a memory unit on which means for executing the method according to one of claims 1-10 are stored.

13. A vehicle (100) comprising: one or more sensors (102); and a control unit (103) according to claim 12.

Images