METHOD AND DEVICE FOR AT LEAST ASSISTED LATERAL GUIDANCE OF A MOTOR VEHICLE

Description

[0001] The invention relates to a method and a device for at least assisted lateral guidance of a motor vehicle.

[0002] DE 10 2018 207 869 A1 discloses a method for providing an automation function for a vehicle, in which environmental data is acquired. Depending on the acquired environmental data, the automation function is activated and a quality measure is determined. Based on the quality measure, a quality level is determined on a multi-level scale, and a graphical output is generated and output, the output comprising a quality display element that is formed depending on the quality measure. The environmental data can be acquired using environmental sensors of the vehicle and / or received via a data connection. The environmental data preferably relate to a lane, a lane marking, a road edge, a traffic sign, and / or another vehicle in the vicinity of the vehicle. The automation function executes at least partially autonomous lateral and / or longitudinal guidance of the vehicle.

[0003] DE 10 2015 000 379 A1 discloses a method for assisting a target driver assistance system of a target vehicle on a route section that cannot be measured by the target driver assistance system. A warning signal is received from a third-party driver assistance system of at least one third-party vehicle, indicating that the route section cannot be measured due to an autonomous or semi-autonomous operating mode of the third-party vehicle. Furthermore, a reference signal is received from the at least one third-party vehicle, indicating a current geographical position and current direction of travel of the at least one third-party vehicle. Based on the reference signal, the target vehicle identifies the route section as non-measurable. The third-party vehicle then receives a request signal from the target driver assistance system, wherein the request signal contains a geographical position of the target vehicle and, if applicable, a direction of travel and / or route.Depending on the request signal, it is determined whether the target vehicle is located within a predetermined vicinity of the marked route section. If this is the case, an external control unit determines an operating strategy for the target vehicle, generates control signals, and transmits them to the target vehicle, where the operating strategy is then implemented.

[0004] From DE 10 2019 213 185 A1 a method for the lateral guidance of a vehicle is known with the following method steps: Recording environmental data of a vehicle while driving along a route; obtaining stored environmental data that was recorded by a plurality of other vehicles that are not currently driving along the route while driving along the route, checking the plausibility of the stored environmental data using the recorded environmental data, and performing lateral guidance of the vehicle based on the verified environmental data.

[0005] The stored environmental data is preferably swarm data. Furthermore, if the plausibility check fails, the environmental data recorded by the vehicle is considered as environmental data for lateral guidance.

[0006] From DE 10 2020 202 964 A1 a method for increasing the safety of driving functions in a partially automated or fully autonomous vehicle is known with the following steps: Recording an environmental image or a sequence of environmental images using at least one environmental sensor, detecting lane boundaries in the environmental image or the sequence of environmental images, determining a lane course based on the detected lane boundaries, retrieving a further lane course from a data source, checking the plausibility of the determined lane course by checking a match between the lane courses, determining a degree of match, setting a confidence value based on the degree of match and specifying whether the determined lane course is provided to a driving function.

[0007] From DE 10 2019 206 748 A1 a method for providing environmental information is known, wherein at least one assistance system of at least one road user is provided with position-dependent environmental information based on a map by means of a central sensor, each of which is provided with at least one time stamp that marks a last update and / or review of the provided position-dependent environmental information.

[0008] The invention is based on the technical problem of providing a method for at least assisted lateral guidance of a motor vehicle that enables increased availability. A further technical problem is the creation of a suitable device.

[0009] The solution to the technical problem results from a method having the features of claim 1 and a device having the features of claim 4. Further advantageous embodiments of the invention result from the subclaims.

[0010] The method for at least assisted lateral guidance of a motor vehicle is carried out by means of at least one camera, an evaluation and control unit and an actuator system for implementing steering interventions, whereby the evaluation and control unit determines at least one lane from the data of the at least one camera and generates control commands for the actuator system depending on the determined lane. The evaluation and control unit also takes into account swarm data, which can be used to support the camera data. The swarm data can be in the form of a swarm map, for example, and is preferably downloaded in advance for upcoming route sections from a server or from a cloud. The support can consist of simple verification or plausibility checks.In driving situations where inadequate lane detection using camera data is present or expected, lateral guidance is provided using the swarm data if the swarm data has previously exceeded a predefined confidence level. In extreme cases, lateral guidance is provided exclusively from the swarm data. This increases the availability of lateral guidance. Lateral guidance can also be fully automated, i.e. the entire lateral guidance is provided by the evaluation and control unit or the actuators. Typical driving situations where inadequate lane detection using a camera can occur are motorway exits or highway ears. The reason for this is the frequent occurrence of uphill or downhill gradients as well as obscured or even missing markings. Such a driving situation can now be recognized or expected because, for example, it is known from the navigation data that a motorway exit is to be taken.Additionally or alternatively, this can be achieved by driving in a deceleration lane. If the swarm data then exceeds a specified confidence level, lateral guidance can be maintained. The confidence level also serves as a measure of the quality of the swarm data. The confidence level can be binary (trustworthy or untrustworthy) or multi-level.

[0011] The confidence level of the swarm data is determined by at least one comparison of the swarm data with the data from at least one camera. The advantage is that the data from at least one camera is usually very reliable and accurate. The determination can be performed periodically or on a situational basis (e.g., 1 km or another predetermined distance before a planned exit from the highway).

[0012] Furthermore, a curve for a lane demarcation is determined based on the data from at least one camera and the swarm data for a predetermined route, whereby the area between the curves is determined in terms of amount and compared with a threshold value. "Amount" means that areas are taken into account both when the curve for the swarm data lies to the left of the curve from the camera data and when the curve lies to the right of the curve. All areas are added together. In addition to the lane demarcation, a curve for a lane center can also be determined and compared. In addition, a maximum distance between the two curves along the route is determined, whereby the maximum distance is compared with a threshold value. If this maximum distance is greater than the threshold value (e.g.80 cm), it cannot be ruled out that such a deviation also exists in data in the area of ​​the motorway exit or a similar traffic situation, which may only be singular but could nevertheless be critical.

[0013] In one embodiment, a takeover request is generated for the motor vehicle driver when the swarm data falls below the specified confidence level. The takeover request can be acoustic, haptic, and / or visual. Preferably, the takeover request is at least acoustic.

[0014] In a further embodiment, holding or gripping of a steering handle is detected, whereby a warning signal is generated if lateral guidance is carried out using the swarm data and no re-gripping of the steering handle has been detected. Holding of the steering handle can be detected, for example, using a capacitive or pressure-sensitive sensor in the steering handle and / or using a vehicle occupant camera. The basic idea here is that with lateral guidance based on the swarm data, there may be situations in which the driver must intervene manually. If it is now detected that the driver does not have his hands on the steering handle at all and is only lightly supporting them on the steering handle, the warning signal alerts him to the fact that he may have to take over lateral guidance very quickly, thus shortening the driver's reaction time.

[0015] With regard to the device design, reference is made in full to the preceding statements.

[0016] The invention is explained in more detail below using a preferred embodiment. The figures show: Fig. 1 shows a schematic block diagram of a device for at least assisted lateral guidance of a motor vehicle and Fig. 2 shows two curves of a lane boundary using the data of at least one camera and swarm data.

[0017] In the Fig. 11 shows a device 1 for at least assisted lateral guidance of a motor vehicle in a highly simplified manner, wherein preferably fully automated lateral guidance is also possible by means of the device. The device 1 has at least one camera 2, an evaluation and control unit 3 and an actuator 4 for implementing steering interventions, wherein the evaluation and control unit 3 is designed to determine at least one lane from the data D of the at least one camera 2 and to generate control commands for the actuator 4 depending on the determined lane. The actuator 4 is a steering system of the motor vehicle. The device 1 also has a receiving device 6, via which swarm data SD can be received from an external server or a cloud and stored in a memory 7. The evaluation and control unit 3 can access the swarm data SD.Furthermore, the device 1 has a position determination unit 8, which is designed, for example, as a satellite-based positioning system such as GPS. The evaluation and control unit 3 can also access the data from the position determination unit 8 in order to locate the swarm data SD, for example. The device 1 also has output means 9, by means of which a motor vehicle driver can be warned or informed visually, acoustically, and / or haptically. Finally, the device 1 has a steering handle 10 in the form of a steering wheel, with a rotation angle or torque sensor 11 assigned to the steering handle, the signals from which are fed to the actuator system 4 when the motor vehicle driver steers manually. Capacitive sensors 12 are arranged on the steering handle 10, by means of which hands-on detection can be carried out. It can therefore be detected whether the motor vehicle driver is gripping the steering handle or not.

[0018] The data from the sensors 12 are also fed to the evaluation and control unit 3.

[0019] Under normal circumstances or standard operation, automated lateral guidance of the motor vehicle is carried out based on the data from at least one camera 2, the data from which is generally highly accurate. The swarm data SD are used to support the data D if necessary, but this is not mandatory. If the evaluation and control unit 3 now detects a driving situation in which inadequate lane detection is to be expected using the data from camera 2 (e.g., a motorway exit), a confidence level for the swarm data SD is checked. The upcoming motorway exit can be determined, for example, from navigation data of a calculated route or from a turn into a deceleration lane.

[0020] The determination and verification of the confidence level of the swarm data SD will now be briefly described using Fig. 2be briefly explained. To do this, the evaluation and control unit 3 first determines a lane boundary Y1 from the data D of camera 2 and a lane boundary Y2 from the swarm data SD. The two curves Y1, Y2 can also intersect. The two curves Y1, Y2 are then compared with each other over a specified distance ΔX of, for example, 50 m - 100 m, where X is oriented in the direction of travel. The comparison consists, on the one hand, of determining the area between the two curves Y1, Y2 and comparing it with a first threshold value S1. If the area is smaller than the threshold value S1, this indicates that the confidence level is high. In addition, the maximum distance ΔY max between the two curves is also determined and compared with a second threshold value S2.The swarm data SD are considered trustworthy if the area is smaller than the first threshold S1 and the maximum distance ΔY max is smaller than the second threshold S2 (confidence level is greater than a threshold). If the swarm data SD are reliable, fully automated lateral guidance can be performed based on the swarm data SD. However, the driver is informed of this, as they may need to take over lateral guidance or intervene if necessary. The information can be provided more urgently if it is determined that the driver is not currently grasping the steering handle 10.

[0021] However, if the swarm data SD is not trustworthy, the driver is asked to take over lateral guidance again. List of reference symbols

[0022] 1Device 2Camera 3Evaluation and control unit 4Actuator 6Receiving device 7Memory 8Position determination unit 9Output device 10Steering handle 11Torque sensor 12Sensor SDSwarm data DCamera data S1, S2Threshold values ​​Y1, Y2Curves ΔXExtension ΔY max maximum distance

Claims

1. A method for at least assisted lateral guidance of a motor vehicle, by means of at least one camera (2), an evaluation and control unit (3) and a set of actuators (4) for implementing steering interventions, wherein the evaluation and control unit (3) determines at least one lane from the data (D) of the camera (2) and generates control commands for the set of actuators (4) depending on the determined lane, wherein the evaluation and control unit (3) additionally takes swarm data (SD) into account, wherein, in driving situations in which insufficient lane recognition by means of the data (D) of the camera (2) exists or is to be expected, the lateral guidance is carried out by means of the swarm data (SD) if the swarm data (SD) have previously exceeded a predetermined confidence level, wherein the confidence level of the swarm data (SD) is determined by at least one comparison of the swarm data (SD) to the data (D) of the at least one camera (2), wherein in each case a curve (Y1, Y2) for a lane boundary is determined on the basis of the data (D) of the at least one camera (2) and of the swarm data (SD) for a given distance (ΔX), wherein the area between the curves (Y1, Y2) is determined and compared to a threshold value S1, and a maximum distance (ΔYmax) between the two curves (Y1, Y2) along the distance (ΔX) is determined, wherein the maximum distance (ΔYmax) is compared to a threshold value S2.

2. The method according to claim 1, characterized in that a takeover prompt is generated for the driver if the swarm data (SD) have fallen below the specified confidence level.

3. The method according to claim 1 or 2, characterized in that a holding of a steering handle (10) by the motor vehicle driver is detected, wherein a warning signal is generated if the lateral guidance is carried out by means of the swarm data (SD) and no gripping of the steering handle (10) has been detected.

4. A device (1) for at least assisted lateral guidance of a motor vehicle, comprising at least one camera (2), an evaluation and control unit (3) and a set of actuators (4) for implementing steering interventions, wherein the evaluation and control unit (3) is designed to determine at least one lane from the data (D) of the at least one camera (2) and to generate control commands for the set of actuators (4) depending on the determined lane, wherein the evaluation and control unit (3) additionally takes swarm data (SD) into account, wherein the evaluation and control unit (3) is further designed such that in driving situations in which insufficient lane detection by means of the data (D) of the camera (2) is present or is to be expected, the lateral guidance is carried out by means of the swarm data (SD) if the swarm data (SD) have exceeded a predetermined confidence level, wherein the evaluation and control unit (3) is designed to determine the confidence level of the swarm data (SD) by at least one comparison of the swarm data (SD) to the data (D) of the at least one camera (2), wherein the evaluation and control unit (3) is designed such that a curve (Y1, Y2) for a lane boundary is determined on the basis of the data (D) of the at least one camera (2) and the swarm data (SD) for a predetermined distance (ΔX), wherein the area between the curves (Y1, Y2) is determined during operation and compared to a threshold value S1, and a maximum distance (ΔYmax) between the two curves (Y1, Y2) along the distance (ΔX) is determined, wherein the maximum distance (ΔYmax) is compared to a threshold value S2.

5. The device according to claim 4, characterized in that the evaluation and control unit (3) is designed to generate a takeover prompt for the motor vehicle driver if the swarm data (SD) have fallen below the specified level of confidence.

6. The device according to claim 4 or 5, characterized in that the device (1) has at least one sensor system for detecting a holder of a steering handle, wherein the evaluation and control unit (3) is designed to generate a warning signal if the lateral guidance is carried out by means of the swarm data (SD) and no gripping of the steering handle (10) has been detected.