Training method for driving assistance system for automatic lateral guidance of motor vehicle

By recording and training the trajectory of the motor vehicle in the section that cannot be managed by the automatic horizontal guidance driving assistance system, the problem of the system being unable to pass at the toll station is solved, and autonomous passage and path determination is achieved without the vehicle driving ahead. System functions.

CN119072424APending Publication Date: 2024-12-03BMW AG
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202380035925.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Priority Date
2022-05-25
Filing Date
2023-05-02
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

The existing automatic transverse guidance driving assistance system cannot pass at the toll station without a vehicle moving forward, and it is impossible to determine which lanes are available for motor vehicles, resulting in system performance degradation and drivers having to take over manually.

Method used

By recording and training the trajectory of motor vehicles in segments that cannot be managed by the automatic transverse guidance driving assistance system, including the use of sensor systems and environmental sensors, recording road widths, payment systems and other limitations, to expand the functionality of the driving assistance system, It can manage the segment independently after training.

Benefits of technology

It realizes that without the vehicle driving ahead, the automatic horizontal guide driving assistance system can pass through the toll station independently and determine the path that the motor vehicle can use, expanding the functional scope of the system and reducing human intervention.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119072424A_ABST
    Figure CN119072424A_ABST
Patent Text Reader

Abstract

The invention relates to a training method for a driving assistance system for automatic lateral guidance of a motor vehicle, the training method comprising recording a trajectory of the motor vehicle when the motor vehicle travels through a section that cannot be managed by the driving assistance system for automatic lateral guidance by means of a deactivated driving assistance system for automatic lateral guidance, and training the driving assistance system for automatic lateral guidance based on the recorded trajectory such that the section can be managed by the driving assistance system for automatic lateral guidance after training.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to a training method for a driver assistance system for automatic lateral guidance of a motor vehicle. Additionally or alternatively, a data processing system or a data processing device is provided, which is designed to at least partially execute the method. Additionally or alternatively, a motor vehicle, in particular an automatic motor vehicle, having a data processing device is provided. Additionally or alternatively, a computer program is provided, which includes commands, which, when the program is executed by a computer, cause the computer to at least partially execute the method. Additionally or alternatively, a computer-readable medium is provided, which includes commands, which, when the command is executed by a computer, cause the computer to at least partially execute the method. Background Art

[0002] A method for operating a steering and / or lane guidance assistance is known from DE 10 2018 204 069 A1. The method comprises determining performance data regarding a reduction in performance of the steering and / or lane guidance assistance during multiple trips of one or more first vehicles along a driving route, assigning the performance data to position data relating to a position along the driving route in connection with which the performance reduction occurred; based on the performance data and the position data, identifying an accumulation of a reduction in performance of the steering and / or lane guidance assistance at at least one specific position of the driving route; and determining adaptation data for adapting at least one operating parameter and / or at least one boundary condition for operating the steering and / or lane guidance assistance of the second vehicle when the second vehicle is driving at the specific position of the driving route.

[0003] At toll booths, there are often places where a drop in the performance of a driver assistance system for automatic lateral guidance of a motor vehicle can be detected. Toll booths often have no lane markings on certain parts of the route. However, a driver assistance system for automatic lateral guidance often follows lane markings in order to follow them. As a result, such driver assistance systems can only bridge limited or short routes without lane markings, for example using the path of the vehicle traveling ahead. Therefore, at toll booths, the automatic lateral guidance often ends in such driver assistance systems and the driver has to manually take over the lateral guidance, i.e. drive himself.

[0004] Toll booths are drawn on the map, but only their locations and the lanes marked on the road are drawn. Therefore, continuous lateral guidance is also impossible. In addition, although it is possible to configure which payment systems the vehicle can use, it is not yet known which payment systems are available on which lanes or which other restrictions (such as height restrictions) exist, so that the vehicle cannot determine which lanes it can or should use.

[0005] This means that, in toll booths, there are currently no guidance parameters for the transversely guided driver assistance system, so that the driver assistance system must be switched off when passing through the toll booth. In addition, it is not clear which lanes of the toll booth are usable for motor vehicles. Summary of the invention

[0006] Against the background of the prior art, the object of the disclosure is to provide a device and a method which are respectively suitable for at least enriching the above-mentioned prior art. In particular, the possibility of driving through a toll booth with automatic lateral guidance even without a vehicle ahead should be described.

[0007] This object is achieved by the features of the independent claim. The dependent claims contain preferred developments of the invention.

[0008] The object is therefore achieved by a method for training a driver assistance system for automatic lateral guidance of a motor vehicle.

[0009] A driver assistance system may be understood as a device in a motor vehicle for assisting the driver in certain driving situations. In addition to hardware components, a driver assistance system may also have software components.

[0010] A driver assistance system for automatic lateral guidance can be designed to actively intervene in the lateral guidance of a motor vehicle in order to keep the motor vehicle in the center of the (driving) lane. A driver assistance system can also be referred to as a steering and / or lane guidance assistant.

[0011] A training method can be understood as a method for teaching or expanding the functionality of a driver assistance system to be trained. That is, the driver assistance system is modified by the method so that it is usable or can be used in driving situations in which it could not (or could not be used to the extent) before the method was performed.

[0012] The method may be a computer-implemented method, ie one or more or all steps of the method may be at least partially performed by a computer or a data processing system.

[0013] The training method includes recording the trajectory of the motor vehicle when driving with the driver assistance system for automatic lateral guidance deactivated through a section that cannot be managed by the driver assistance system for automatic lateral guidance.

[0014] It is conceivable that the driver assistance system uses the road surface markings to keep the motor vehicle in the middle of the lane in the manner described above. This section, which may also be referred to as an area, may be a route section without road surface markings or lane markings. Therefore, the driver assistance system cannot be used in such an area without road surface markings before the training method is performed.

[0015] Trajectory can be understood as the path that the motor vehicle moves or has moved through the section. It is conceivable that the trajectory also has a time component in addition to the position information, that is, when, where and / or at what speed and / or acceleration the motor vehicle travels at which position.

[0016] Recording the trajectory may include, for example, storing the trajectory in the motor vehicle. The trajectory may be recorded by a sensor system, which may include, for example, a camera, a lidar sensor, an ultrasonic sensor, a wheel speed sensor, an acceleration sensor, a yaw rate sensor, and / or a radar sensor.

[0017] The trajectory can also be defined as the movement path of the motor vehicle. It can be detected by the motion sensors of the motor vehicle, such as wheel speed sensors, acceleration sensors and / or yaw rate sensors. In order to locate the trajectory in reality, the motor vehicle can be located. This can be achieved by a GNSS system or additionally or alternatively also by landmarks, which can be detected, for example, by the above-mentioned environmental sensors (such as cameras, lidar sensors, ultrasonic sensors and / or radar sensors).

[0018] Furthermore, it can be recorded which payment system the motor vehicle uses when driving through the section and / or whether other restrictions (eg height restrictions) exist.

[0019] It is also conceivable to record the free space or road width, for example the width of a side street for driving through the section, by means of environmental sensors while driving or recording the trajectory. This can be used to determine the speed of the motor vehicle when driving through the section automatically using the trained driver assistance system, i.e. the speed can thus be adapted to a speed that is appropriate for the road width, in particular the width of the side street.

[0020] The training method further comprises training a driver assistance system for automatic lateral guidance based on the recorded trajectory, so that the segment can be managed by the driver assistance system for automatic lateral guidance after the training.

[0021] Here, the training method is not limited to a single pass through the section, but can also be performed multiple times. This means that multiple trajectories can be recorded and multiple trajectories can be used to train the driver assistance system.

[0022] The training method offers the advantage that a functional expansion of the driver assistance system can be performed, so that the driver assistance system can be used after the training method in driving situations or (route) sections that were not available before the training method. The motor vehicle can thus determine which path or trajectory it can or should use based on the training method. The method can be performed by the motor vehicle itself and / or with the support of data from a plurality of vehicles in the cloud, i.e. no human development work is required for the functional expansion. It is also conceivable that driver assistance systems of other motor vehicles also receive an improved driver assistance system, for example, via vehicle-to-vehicle communication and / or via the cloud (e.g. over-the-air updates and / or vehicle-to-infrastructure transmission).

[0023] Possible refinements of the above-described method are explained in detail below.

[0024] The training method may include determining that a section that cannot be managed by a driving assistance system for automatic lateral guidance is located a predetermined distance from the motor vehicle on a planned route of the motor vehicle; driving the motor vehicle using an activated driving assistance system for automatic lateral guidance at a time point when it is determined that the section that cannot be managed by the driving assistance system for automatic lateral guidance is located a predetermined distance from the motor vehicle on the planned route of the motor vehicle; and deactivating the driving assistance system for automatic lateral guidance when the motor vehicle outputs a takeover request before the motor vehicle reaches the section.

[0025] The training method may include recording further trajectories of further motor vehicles when driving through the section with the deactivated driver assistance system for automatic lateral guidance, and training the driver assistance system for automatic lateral guidance based on the further recorded trajectories, so that the driver assistance system for automatic lateral guidance can manage the section after the training.

[0026] The training method may include checking the trajectory of the motor vehicle for plausibility using the trajectory of another motor vehicle and training the driver assistance system for automatic lateral guidance based on the trajectory of the motor vehicle that has been checked for plausibility, so that the driver assistance system for automatic lateral guidance can manage the section after training.

[0027] Training the driver assistance system for automatic lateral guidance may include determining a driving trajectory or a passing trajectory for a section starting from the first predetermined lane to the second predetermined lane.

[0028] In other words, instead of the road markings, the driver assistance system can now use as a guide variable a determined trajectory, the so-called driving trajectory, along which the motor vehicle should or can be driven in the section in a controlled manner by the driver assistance system.

[0029] Furthermore, the present invention relates to the use of a driver assistance system trained using the above-mentioned training method for controlling the lateral guidance of a motor vehicle.

[0030] Here, before and / or during driving through the section, it can be checked with the help of the driving assistance system whether the environment (e.g. height restrictions, payment systems, etc.) and / or the state of the motor vehicle (e.g. driving with or without a trailer) has changed in a predetermined manner compared to the time when the driving assistance system was trained, and if the environment and / or the state of the motor vehicle has changed in a predetermined manner compared to the time when the driving assistance system was trained, the driving assistance system is not used.

[0031] The above description regarding the training method similarly applies to the usage, and vice versa.

[0032] In other words and with respect to the specific designs described as not limiting the present disclosure, the above description can be summarized as follows:

[0033] The driver of the motor vehicle can be informed that there is a section ahead, for example a toll booth, but that this section cannot (yet) be driven through.

[0034] The driver can then be offered the opportunity to teach the system the segment or in particular the toll booth by driving past it manually one or more times.

[0035] When the driver manually drives through a segment or in particular a toll booth, the driving assistance system can store the track traveled and information about the exit lane (i.e. the lane the motor vehicle was in before reaching the segment), the selected target lane (i.e. the lane the motor vehicle is in after the segment) and the path traveled by the driver (the so-called track). It can also be stored here which road boundaries are present in or at the segment, which tracks other vehicles use, and / or whether the motor vehicle can drive through the segment with or without a toll booth and optionally which vehicle-integrated payment system is used.

[0036] If sufficient and / or accurate data are collected after the motor vehicle has traveled through the segment once or more times, the vehicle's own trajectory and, if necessary, also the trajectories of other vehicles can be used to create a map in which the trajectories are checked for plausibility with one another.

[0037] If there is a sufficiently plausible trajectory from the current exit lane to the target lane (which may also be referred to as the passing lane), this can be used by the driver assistance system in order to control the motor vehicle through this section.

[0038] If a sufficiently plausible trajectory is learned, it is additionally or alternatively conceivable to load it into the cloud and make it available to other or further vehicles, for example via an online service and / or via an improved or updated map version.

[0039] In a possible embodiment, it is conceivable that the driver assistance system provides the driver with the instruction to drive the vehicle through the segment at a predetermined distance before the segment. The driver can confirm or reject this and teach the driver assistance system further. However, it is also conceivable that the driver's confirmation before the toll booth can be omitted, assuming a good teaching quality and if the vehicle drives through the segment several times without driver intervention.

[0040] In other possible additional or alternative designs, it is conceivable that changes in the vehicle (the so-called motor vehicle state), such as a suspended trailer or changes in the infrastructure (the so-called environment), such as a payment possibility that has been cancelled but previously used in this lane, may lead to the learned or determined passing lane in the above manner being discarded.

[0041] In addition, a data processing system is provided, which is characterized in that it is designed to at least partially execute the above method.

[0042] The system may include a data processing device in the vehicle. Here, it may be, for example, an electronic control unit or a controller (English: ECU=electronic control unit). The electronic controller may be an intelligent unit controlled by a processor, which may communicate with other modules, for example, via a central gateway (CGW) and may form an on-board network, for example, via a field bus, such as a CAN bus, a LIN bus, a MOST bus and a FlexRay, or via automotive Ethernet, for example, together with a communication controller. It is conceivable that the controller controls functions related to the driving characteristics of the motor vehicle, such as engine control, power transmission, a brake system and / or a tire pressure control system, and / or may access relevant data. In addition, driving assistance systems, such as parking assistance, adaptive cruise control system (ACC), lane keeping assistance, lane change assistance, traffic sign recognition, light signal recognition, start assistance, night vision assistance, emergency brake assistance and / or intersection assistance may be controlled by the controller and / or access relevant data.

[0043] Furthermore, a vehicle, in particular an autonomous motor vehicle, having a data processing device may be provided. The vehicle is characterized in that it has a data processing device.

[0044] The motor vehicle may be a passenger vehicle, in particular a car and / or a commercial vehicle. The automated motor vehicle may be designed to at least partially and / or at least temporarily take over the longitudinal guidance and / or the transverse guidance during automatic driving of the motor vehicle. Automatic driving may be achieved in such a way that the forward movement of the motor vehicle is (largely) autonomous. The automatic driving may be controlled at least partially and / or temporarily by a data processing device.

[0045] The motor vehicle may be a motor vehicle of autonomy level 0, ie the driver takes over the task of dynamic driving even when supporting systems (eg ABS or ESP) are present.

[0046] The motor vehicle may be an autonomy level 1 motor vehicle, ie, has a specific driver assistance system, such as an adaptive cruise control system (ACC), which supports the driver in the operation of the vehicle.

[0047] The motor vehicle may be an autonomy level 2 motor vehicle, ie semi-autonomous, such that the driver assistance system takes over functions such as automatic parking, lane keeping or lateral guidance, general longitudinal guidance, acceleration and / or deceleration.

[0048] The motor vehicle may be a motor vehicle of autonomy level 3, i.e. conditionally automated, so that the driver does not have to continuously monitor the vehicle systems. The motor vehicle automatically performs functions such as triggering a turn signal, changing lanes and / or keeping lanes. The driver may be engaged in other matters but may take over the steering if necessary at the request of the system within the warning time.

[0049] The motor vehicle may be a motor vehicle of autonomy level 4, ie highly automated, so that the guidance of the vehicle is continuously taken over by the vehicle system. If the system no longer manages the driving task, the driver may be requested to take over the guidance.

[0050] The vehicle may be a vehicle of autonomy level 5, ie fully automated, such that the driver is not required to perform driving tasks. No human intervention is required other than determining the destination and activating the system.

[0051] It is conceivable that the data processing device of the motor vehicle collects data based on the output of the sensor system according to a specification and outputs it to the first and / or second cloud component.

[0052] A cloud component may be understood as a part of a cloud. A cloud may be understood as a system comprising one or more data processing devices, which is in particular wirelessly connected or connectable to a vehicle.

[0053] The above description regarding the method also applies analogously to the data processing system, and vice versa.

[0054] A computer program is also provided. The computer program is characterized in that the computer program includes commands, which cause the computer to at least partially execute at least one of the above methods when the computer executes the program.

[0055] The program code of the computer program may be present as any desired code, in particular a code suitable for controlling a motor vehicle.

[0056] In addition, a computer-readable medium, in particular a computer-readable storage medium, is provided. The computer-readable medium is characterized in that the computer-readable medium comprises instructions, which cause the computer to at least partially perform at least one of the above methods when the computer executes the program.

[0057] That is, a computer-readable medium comprising the computer program defined above can be provided. The computer-readable medium can be any digital data storage, such as a USB stick, hard disk, CD-ROM, SD card or SSD card. The computer program does not necessarily have to be stored on such a computer-readable storage medium in order to be provided to the motor vehicle, but can also be obtained externally via the Internet or other means.

[0058] The above description regarding the method and the data processing system also applies analogously to the computer program and the computer-readable medium, and vice versa. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Subsequent reference Figure 1 and Figure 2 An implementation scheme is described.

[0060] Figure 1 A motor vehicle is schematically shown which is designed to carry out a training method for a driver assistance system for automatic lateral guidance of a motor vehicle and the use thereof in a motor vehicle, and

[0061] Figure 2 A flow chart of the training method is schematically shown. DETAILED DESCRIPTION

[0062] Figure 1 A driving situation is schematically shown in a top view, in which a motor vehicle 1 is located on a road 2 having lane markings 8 and, with an activated driver assistance system for automatic lateral guidance, moves behind a vehicle 7 traveling in front to a toll booth 3 having three lanes 4, 5, 6. In the area of ​​the road 2, the driver assistance system uses the lane markings 8 in order to determine the position of the motor vehicle 1 in the lane and to keep the motor vehicle 1 in the lane by means of steering interventions. Since the toll booth 3 has no lane markings, it is a section that cannot be managed by the driver assistance system for automatic lateral guidance. In order to improve this, a training method for the driver assistance system is carried out by the motor vehicle 1, the flow chart of the training method being shown in FIG. Figure 2 The training method is shown on the left and has steps S1 -S . . . .

[0063] In a first step S1 of the training method, it is determined from map data that a toll booth 3 which cannot (at this point in time) be managed by the driver assistance system for automatic lateral guidance is located at a predetermined distance from the motor vehicle 1 on the planned route of the motor vehicle 1 (see also Figure 1At the point in time at which it is determined that the toll booth 3 is located in front of the motor vehicle 1 , the driver assistance system for automatic lateral guidance is activated.

[0064] In a second step S2 of the training method, before the motor vehicle 1 reaches the toll booth 3 , the driver assistance system for automatic lateral guidance is deactivated in the event of a takeover request output by the motor vehicle.

[0065] The driver now takes over control of the lateral guidance and guides the motor vehicle 1 through the toll booth 3 , so that the motor vehicle passes the toll booth 3 with the driver assistance system for automatic lateral guidance deactivated.

[0066] In a third step S3 of the training method, the trajectory of the motor vehicle 1 is detected and recorded when passing through the toll station 3 with the driver assistance system for automatic lateral guidance deactivated. In addition, the trajectory of the motor vehicle 7 traveling ahead is detected and recorded when passing through the section with the driver assistance system for automatic lateral guidance deactivated. In addition, before and / or during the passage through the toll station 3, the circumstances (e.g., which payment system was used when passing through the toll station 3) and / or the state of the motor vehicle (e.g., towing a trailer when passing) are recorded and recorded.

[0067] In a fourth step S4 of the training method, the recorded trajectory of the motor vehicle 1 is subjected to a plausibility check, in particular the recorded trajectory of the motor vehicle is compared with the recorded trajectory of the preceding motor vehicle 7. In the present case, the two motor vehicles 1, 7 move along essentially the same trajectory (for example, indicated by a dashed line) through the same passage 6 of the toll booth 3, so that the trajectory is classified as plausible. For the same toll booth 3, the motor vehicle 1 can repeatedly perform steps S3 and S4.

[0068] In a fifth step S5 of the training method, a driver assistance system for automatic lateral guidance is trained based on the plausibility-checked trajectory of the motor vehicle 1, wherein the plausibility-checked trajectory obtained by steps S3 and S4 is determined as a passing trajectory for the right lane (as exit lane and target lane) of the road 2 or is stored in the driver assistance system. By automatically following the passing trajectory with the aid of the driver assistance system, it is now possible to pass the toll booth 3, so that the toll booth is now considered a manageable section.

[0069] Therefore, in step S6 (see Figure 2), passing the toll booth 3, wherein the driver assistance system hereby takes over the control of the lateral guidance of the motor vehicle 1 so that the motor vehicle follows the passing trajectory. Here, before and / or during passing the toll booth 3, it is checked with the aid of the activated driver assistance system whether the environment and / or the state of the vehicle has changed in a predetermined manner compared to the time point at which the driver assistance system was trained (see step S3) (for example, another payment method has been used or there is no longer an unknown journey). If the environment and / or the state of the motor vehicle has changed in a predetermined manner compared to the time point at which the driver assistance system was trained, the driver assistance system is either not used or the control of the lateral guidance is transferred to the driver during passing the toll booth. The learned or stored passing trajectory is discarded.

[0070] Reference numerals list

[0071] 1 Motor Vehicle

[0072] 2 Roads

[0073] 3 Toll booths

[0074] Channels 4-6

[0075] 7 Vehicles ahead

[0076] 8 Lane markings or road markings

[0077] S1-S6 Method Steps

Claims

1. A method for training a driver assistance system for automatic lateral guidance of a motor vehicle (1), in, The training method comprises: - recording the trajectory of the motor vehicle (1) when driving through a section (3) that cannot be managed by the driver assistance system for automatic lateral guidance with the driver assistance system for automatic lateral guidance deactivated, and - The driver assistance system for automatic lateral guidance is trained based on the recorded trajectory, so that the segment (3) can be managed by the driver assistance system for automatic lateral guidance after training.

2. The training method according to claim 1, in, The training method comprises: - determining that a section (3) which cannot be managed by the driver assistance system for automatic lateral guidance is located at a predetermined distance from the motor vehicle (1) on the planned route of the motor vehicle, - driving the motor vehicle (1) with the activated driving assistance system for automatic lateral guidance at a point in time at which it is determined that a section that cannot be managed by the driving assistance system for automatic lateral guidance is located at a predetermined distance from the motor vehicle on the planned route of the motor vehicle (1); and - before the motor vehicle (1) reaches the section, deactivating the driver assistance system for automatic lateral guidance when the motor vehicle outputs a takeover request.

3. The training method according to claim 1 or 2, in, The method comprises: - recording a further trajectory of a further motor vehicle (7) when driving through the section (3) with the driver assistance system for automatic lateral guidance deactivated, and - Training the driver assistance system for automatic lateral guidance based on further recorded trajectories, so that the segment can be managed by the driver assistance system for automatic lateral guidance after the training.

4. The training method according to claim 3, in, The training method comprises: - performing a plausibility check on the trajectory of the motor vehicle (1) using the trajectory of the further motor vehicle (7), and - the driver assistance system for automatic lateral guidance is trained on the basis of the plausibility-checked trajectory of the motor vehicle (1), so that the driver assistance system for automatic lateral guidance can manage the segment after training.

5. The training method according to any one of claims 1 to 4, in, The training of the driver assistance system for automatic lateral guidance includes determining a driving trajectory for a section (3) starting from a first predetermined lane to a second predetermined lane.

6. Use of a driver assistance system trained using a training method according to any one of claims 1 to 5 for controlling the lateral guidance of a motor vehicle (1).

7. The use according to claim 6, in, Before and / or during driving through the section (3), it is checked with the aid of the driver assistance system whether the environment and / or state of the motor vehicle (1) has changed in a predetermined manner compared to the time when the driver assistance system was trained, and if the environment and / or state of the motor vehicle (1) has changed in a predetermined manner compared to the time when the driver assistance system was trained, the driver assistance system is not used.

8. A data processing system comprising means for executing the method according to any one of claims 1 to 7.

9. A computer program comprising instructions for causing a computer to execute the method according to any one of claims 1 to 7 when the computer executes the program.

10. A computer-readable medium comprising instructions which, when executed by a computer, cause the computer to perform the method according to any one of claims 1 to 7.