METHOD FOR PROVIDING A FUTURE-PROOF TRAJECTORY FOR A PARTICULARLY ASSISTED MOTOR VEHICLE AND ASSISTANCE SYSTEM

Description

[0001] The invention relates to a method for providing a future trajectory for a motor vehicle that is at least partially assisted by means of an assistance system according to claim 1. The invention further relates to a computer program product and an assistance system.

[0002] A previously known technology is a so-called trained parking system, in which a trajectory to a defined end position can be learned. This learning process is also referred to as teach-in. The vehicle later drives the learned route automatically, a process also known as redrive mode. During this time, the user can be inside or outside the vehicle, monitoring the assisted function, or the vehicle can drive autonomously without driver supervision.

[0003] However, the driver may be unable or unwilling to learn the trajectory for automated parking. The driver may not be sufficiently familiar with the vehicle's functions, or the training process may be too time-consuming or complicated. Consequently, the driver repeatedly drives the route manually, even though it could be driven by an assistance function for parking or the parking maneuver itself.

[0004] DE 10 2013 015 348 A1 relates to a method for operating a vehicle, in particular for the vehicle approaching a parking space in a parking zone that is not visible from the road, in which environmental data of the vehicle is recorded, wherein when approaching a parking space in the parking zone, it is identified whether it is a home parking space or the parking zone is a home parking zone, and if a home parking space or home parking zone is identified and the vehicle approaches the identified home parking space or home parking zone, the recorded environmental data or driving data is stored or updated, wherein in a learning mode, several trajectories for the at least one home parking space or the at least one home parking zone are determined and stored based on the environmental data or driving data.and wherein, in an operating mode, when approaching at least one home parking space or at least one home parking zone, possible drivable trajectories are output for selection and activation, or if only one of the determined trajectories is drivable, it is automatically activated.

[0005] DE 10 2014 018 189 A1 relates to a method for operating a vehicle in at least one parking situation. At least one predefined vehicle-specific or parking situation-specific function is assigned to at least one predefined parking situation of the vehicle. It is determined whether the vehicle is in the at least one predefined parking situation, and the predefined vehicle-specific or parking situation-specific function assigned to this at least one predefined parking situation is offered to a vehicle user for activation or is automatically activated when the vehicle is in the at least one predefined parking situation.

[0006] DE 10 2016 216 157 A1 describes a method for operating a motor vehicle, comprising the steps of: - Determining at least one path data record describing a respective trajectory driven by the or another motor vehicle and sending the path data record to an external storage device, - Providing at least one guidance data record for the motor vehicle by the storage device, wherein each guidance data record is assigned to one of the trajectories and is determined depending on the path data record describing the respective assigned trajectory, and - Controlling the vehicle equipment of the motor vehicle depending on the provided guidance data record or, if several guidance data records are provided by the storage device,a vehicle-side selected from the provided guidance data sets to issue a driving instruction concerning the assigned trajectory to a driver of the motor vehicle and / or to carry out at least one driving intervention.

[0007] The object of the present invention is to create a method and an assistance system by means of which a trajectory for at least partially assisted operation can be provided to a user of the motor vehicle.

[0008] This problem is solved by a method and an assistance system according to the independent claims. Advantageous embodiments are specified in the dependent claims.

[0009] One aspect of the invention relates to a method for providing a future trajectory for a motor vehicle that is at least partially driver-assisted, by means of an assistance system, including the acquisition of the motor vehicle's current position by means of a detection device on the motor vehicle. The current position is compared with at least one position stored in a memory device of the assistance system, wherein the stored position is associated with at least one previously driven trajectory of another motor vehicle. If the current position matches the stored position, at least a partial trajectory of the previously driven trajectory is provided as the future trajectory.

[0010] This allows for an improved, future-proof trajectory to be provided for the user of the motor vehicle.

[0011] In particular, a method is proposed in which trajectories for automated parking and maneuvering, such as a trained parking or reversing assistant, can be independently learned by recording and evaluating trajectories or routes traveled. Recurring segments and sections of the route, such as a driveway, are recognized, and based on repeated journeys, driver information is generated in various forms, culminating in a trajectory that can be followed again. For the identified route segments, the trajectory is offered to the user via a suitable function, such as trained parking.

[0012] Artificial intelligence, statistical models, feature assignments through, for example, feature-landmark matching, Monte Carlo association, Markov chain or other machine learning methods can be used to teach the parking or shunting processes.

[0013] In particular, a redrive function based on other vehicles is proposed. The vehicle itself recognizes recurring characteristics and behaviors in the background, which, together with the vehicle's position (especially globally or map-related), are derived from previously performed parking and maneuvering operations by other vehicles with the same or similar destinations. From this, the resulting redrive trajectories are retrieved from the storage device, which can preferably be located on an external electronic computing device. This external electronic computing device can also be referred to as the backend. Alternatively, the electronic computing device or storage device can also be located internally within the vehicle, in which case the corresponding trajectory can be obtained, for example, via C2X (Car-to-Infrastructure) communication.

[0014] The future trajectory is then generated by the storage device and made available to the user, based on trajectories already traversed in the past. Both entire trajectories and partial trajectories can be used or determined.

[0015] According to a further advantageous embodiment, the recording function is automatically offered when a possible starting position is approached repeatedly, provided it is determined that no historical trajectories are yet available for that starting position. In particular, this embodiment eliminates the need for an explicit teach-in, thus making parking or maneuvering more convenient for the user. The recorded trajectory is saved as a historical trajectory and is therefore available for future journeys. The teach-in function is offered after the repeated approach to the possible starting position is detected, and the trajectory, or partial trajectory, is then recorded.Alternatively, the recording can also be done automatically as soon as repeated starting is detected, and after completion of the teach-in, the driver can be offered the option to save the recorded route for future situations.

[0016] At least one previously driven trajectory is stored on an external electronic computing unit of the assistance system. Specifically, the vehicle's current position can be transmitted to this external unit, where it is compared to the position already assigned to a trajectory. The resulting partial trajectory is then provided to the vehicle as a future route. This saves storage capacity and allows for real-time verification of the existence of a corresponding trajectory at multiple locations.

[0017] Furthermore, it is intended that a specific point in time from each of the other historically traveled trajectories is taken into account when determining the approximated trajectory. In particular, it can be stipulated, for example, that older historically traveled trajectories are given less weight than newer ones. This also allows for the consideration of changes within the environment. For example, new signs or objects may have been erected along the trajectory, with the newer historically traveled trajectories bypassing these signs or objects. Thus, a currently and potentially future trajectory can be provided to the user.

[0018] According to an advantageous embodiment, at least one historically traveled trajectory is generated based on a large number of other motor vehicles. In particular, based on swarm data from a large number of motor vehicles that were located in a similar position or location, the corresponding historically traveled trajectory can be generated. This can be achieved, in particular, by combining the trajectories and, for example, approximating them.

[0019] It is further advantageous if, based on the respective historically driven trajectories of the numerous vehicles, an approximate trajectory is determined as at least a partial trajectory and provided to the vehicle. In particular, since not all vehicles follow exactly the same trajectory, it is therefore advantageous if the trajectory is only approximated based on the historically driven trajectories. Specifically, this allows outliers to be identified during the learning or generation process and eliminated from the trajectory used. For example, a single instance of braking or maneuvering around a temporary obstacle can be removed from the redrive trajectory.

[0020] It has also proven advantageous to display at least one partial trajectory to the vehicle user for selection on an output device. In particular, the user can, for example, have the corresponding trajectory, or even a multitude of trajectories, displayed on a screen. The user can then choose whether or not to drive the respective trajectory. This allows the user to intuitively select the trajectory they wish to drive in the future. The cumbersome process of learning a specific trajectory is no longer necessary.

[0021] It has also proven advantageous to use machine learning in the electronic computing system to evaluate the historically traveled trajectory. In particular, artificial intelligence, such as a neural network, can be used for this purpose. Furthermore, statistical models, feature-landmark matching, Monte Carlo association, or Markov chain analysis can also be employed. This provides the user with an improved, future trajectory.

[0022] In a further advantageous embodiment, the future drivable trajectory is provided for an assisted maneuvering operation of the vehicle and / or for an assisted parking operation. This is particularly possible for recurring positions. Thus, for example, a corresponding assisted maneuvering operation can be provided for a frequently used drive-in. Furthermore, a parking operation, for example in a home zone, can also be provided.

[0023] The presented method is a computer-implemented method. A further aspect of the invention relates to a computer program product with program code means which, when executing the program code means, cause an electronic computing device to carry out a method according to the preceding aspect.

[0024] The electronic computing device includes, in particular, electronic components, processors and, for example, integrated circuits in order to carry out the corresponding procedure.

[0025] A further aspect of the invention relates to an assistance system for providing a future trajectory for a motor vehicle that is at least partially driven by an assisted motor vehicle, with at least one storage device, wherein the assistance system is configured to carry out a method according to the preceding aspect. In particular, the method is carried out by means of an assistance system.

[0026] The assistance system is preferably implemented externally within the vehicle. Alternatively, however, the assistance system can also be provided internally within the vehicle. Furthermore, some features of the assistance system can be implemented externally, while others can be implemented internally.

[0027] Advantageous embodiments of the process are to be regarded as advantageous embodiments of the computer program product and the assistance system. The assistance system possesses tangible features that enable the execution of the process or an advantageous embodiment thereof.

[0028] The invention also includes further developments of the assistance system according to the invention, which have features already described in connection with the further developments of the method according to the invention. For this reason, the corresponding further developments of the assistance system according to the invention are not described again here.

[0029] The invention also includes the combination of the features of the described embodiments.

[0030] The following describes exemplary embodiments of the invention. This is illustrated by: Fig. 1 a schematic top view of an embodiment of an assistance system; and Fig. 2 a schematic flowchart according to an embodiment of the method.

[0031] The embodiments described below are preferred embodiments of the invention. In these embodiments, the described components each represent individual features of the invention that can be considered independently of one another. Each of these features further develops the invention independently and can therefore be considered part of the invention individually or in a combination other than that shown. Furthermore, the described embodiments can also be supplemented by other features of the invention already described.

[0032] In the figures, functionally identical elements are each provided with the same reference symbols.

[0033] Fig. 1 Figure 1 shows a schematic top view of an embodiment of an assistance system 1. In this case, the assistance system 1 comprises an external electronic computing unit 2. The external electronic computing unit 2 also comprises a storage device 3. The assistance system 1 is designed to provide a future trajectory 4 for a motor vehicle 5 that is at least partially assisted.

[0034] In the process for providing the future trajectory 4 for the at least partially assisted-driven motor vehicle 5, the current position P of the motor vehicle 5 is recorded by a recording device 6 of the motor vehicle 5. The current position P is then transmitted, in particular, to the external electronic computing device 2. The current position P is then compared with at least one position 9 stored in the storage device 3, whereby at least one previously driven trajectory 7, 8 of another motor vehicle is assigned to the stored position 9. If the current position P matches the stored position 9, at least one partial trajectory of the previously driven trajectories 7, 8 is provided as the future trajectory 4.

[0035] In particular, it is planned that at least one historically traveled trajectory 7, 8 will be generated based on a large number of other motor vehicles. Furthermore, based on the respective additional historically traveled trajectories 7, 8 of the large number of motor vehicles, an approximate trajectory will be determined as at least the partial trajectory and provided to motor vehicle 5.

[0036] In particular, two historically traveled trajectories 7 and 8 are shown. Specifically, a first historically traveled trajectory 7 by, for example, a first additional motor vehicle and a second historically traveled trajectory 8 by a second additional motor vehicle are shown.

[0037] Furthermore, it may be provided that a respective point in time from the respective further historically traveled trajectories 7, 8 is taken into account when determining the approximate trajectory.

[0038] It may also be provided that at least one partial trajectory is displayed to a user of the motor vehicle 5 for selection on an output device 10.

[0039] Furthermore, it may be provided that the already historically traveled trajectories 7, 8 are evaluated by means of machine learning of the electronic computing device 2.

[0040] Furthermore, it may be provided that the future drivable trajectory 4 is made available for an assisted maneuvering operation of the motor vehicle 5 or, as shown here, for an assisted parking operation of the motor vehicle 5, for example, in a parking space 11.

[0041] In particular, a method for the autonomous learning of trajectories for automatic parking and maneuvering is proposed, in which the historically driven trajectories 7 and 8 are recorded and evaluated. Recurring segments and sections of the route, such as a driveway, are recognized, and based on the repeated journeys, driver information is generated in various forms, culminating in the future trajectory 4. For the identified route segments, the future trajectory 4 is offered to the user via a suitable function, such as "trained parking."

[0042] The vehicle 5 recognizes recurring features and behavior in the background, along with the position P, particularly globally or map-related, from previously performed parking and maneuvering operations of other vehicles with the same or similar destinations. From this, it retrieves the resulting future trajectory 4 from the vehicle-external electronic computing unit 2 in this embodiment. The so-called "redrive" of the trajectory generated and provided by the vehicle-external electronic computing unit 2 is offered to the user. This function is offered automatically when a possible starting position is approached repeatedly. Thus, explicit teach-in for the vehicle user is unnecessary.

[0043] The function can be executed within the vehicle 5, so that potentially personal data does not leave the vehicle 5. Alternatively or additionally, depending on customer requirements, the data, such as positions, trajectories, times of recording, etc., can also be processed on the vehicle-external electronic computing device 2 or made directly usable with other vehicles via C2X (Car-to-Infrastructure) methods.

[0044] The various learning processes are used to identify outliers in particular and eliminate them from the trajectory being used. For example, a single braking maneuver or driving around a temporary obstacle can be removed from the Redrive trajectory.

[0045] The information that the motor vehicle 5 or, in this case, the motor vehicle-external electronic computing device 2 can provide or use includes, among other things, map data, environmental data or trajectories of other motor vehicles or about other road users, as well as landmarks and features for localization.

[0046] In particular, the entire parking process can be assumed in this case, although alternatively or additionally, the application can be further developed so that only segments of trajectories, i.e., partial trajectories, need to be compared and recognized. Accordingly, not only can a complete redrive trajectory be used, but also segments of other trajectories.

[0047] In particular, the assistance system 1 can also be configured to recognize recurring driving maneuvers and inform the user of the vehicle 5, depending on the situation, for example via the output device 10, whereby a corresponding teach-in function can then be provided. The vehicle 5 records recurring characteristics and behavior in the background, possibly together with the position P, in order to recognize frequently used, repetitive parking and maneuvering operations. When a recurring operation is detected, the user of the vehicle 5 is informed about the availability of the function, and the teaching of an optimal trajectory can be offered. Recognition and driver interaction can occur both at the start and at the end of the maneuver. However, explicit teach-in by the driver is necessary for this.The trajectory learned during teach-in can be enriched with previously executed maneuvers and / or existing backend data. This learned trajectory can then be used for redrives.

[0048] Alternatively, the assistance system 1 can recognize repeated driving maneuvers and offer the user the option to save the trajectory generated in the background. The vehicle 5 records recurring characteristics and behaviors in the background, possibly along with position P, to recognize frequently used, repetitive parking and maneuvering operations. If a repeated operation is recognized sufficiently well for a redrive, the driver is informed of the function's availability and offered the option to save the generated trajectory. Recognition and driver interaction can occur both at the start and end of the maneuver. The redrive of the learned and / or backend-enriched trajectory is offered to the driver, for example, from output device 10. The function is offered automatically when the starting position is approached repeatedly.This also eliminates the need for an explicit, manual teach-in performed by the driver.

[0049] Fig. 2Figure 1 shows a schematic flowchart according to one embodiment of the method. The method begins in a first step, S1. In a second step, S2, recurring trajectories are searched for. Alternatively, starting from the second step, S2, the process can proceed to a third step, S3, in which the recurring trajectory is identified and its quality for redrive is verified. In a fourth step, S4, the redrive is offered, and in a fifth step, S5, the redrive is executed. Starting from the second step, S2, a sixth step, S6, can be performed, verifying whether a recurring trajectory is identified. If so, a teach-in can be offered in a seventh step, S7.In an eighth step, S8, the teach-in process is carried out again, from which step S8 can proceed to step five, S5. Alternatively, starting from step two, S2, one can proceed to step nine, S9, in which step nine detects the start of another vehicle's trajectory, matching the user's own destination. In step ten, S10, the redrive option is offered, and from step ten, S10, one can proceed back to step five, S5, and execute the redrive. Reference symbol list

[0050] 1 Assistance system 2 Electronic computing device 3 Storage device 4 Future trajectory 5 Motor vehicle 6 Recording device 7 First historically traversed trajectory 8 Second historically traversed trajectory 9 Stored position 10 Output device 11 Parking lot P Position S1 First step S2 Second step S3 Third step S4 Fourth step S5 Fifth step S6 Sixth step S7 Seventh step S8 Eighth step S9 Ninth step S10 Tenth step

Claims

1. Method for providing, by means of an assistance system (1), a trajectory (4) that can be traveled in future for an at least partially assisted motor vehicle (5), which method comprises the steps of: - detecting a current position (P) of the motor vehicle (5) by means of a detection device (6) of the motor vehicle (5); - comparing the current position (P) with at least one position (9) saved in a storage device (3) of the assistance system (1), wherein the saved position (9) is assigned at least one trajectory (7, 8) that has already been traveled in the past of at least one other motor vehicle; and - if the current position (P) matches the saved position (9), providing at least one partial trajectory of the trajectory (7, 8) that has already been traveled in the past as a trajectory (4) that can be traveled in future, wherein the at least one trajectory (7, 8) that has already been traveled in the past is provided on a vehicle-external electronic computing device (2) of the assistance system (1), wherein a time of each of the further trajectories (7, 8) that have been traveled in the past is taken into account when determining the approximated trajectory, and wherein older trajectories (7, 8) that have been traveled in the past are given less weight than new ones.

2. Method according to claim 1, characterized in that the at least one trajectory (7, 8) that has already been traveled in the past is generated on the basis of a large number of other motor vehicles.

3. Method according to claim 2, characterized in that on the basis of the respective other trajectories (7, 8) that have already been traveled in the past of the large number of motor vehicles, an approximated trajectory is determined as at least the partial trajectory and is provided to the motor vehicle (5).

4. Method according to any of the preceding claims, characterized in that the at least one partial trajectory is output on an output device (10) to a user of the motor vehicle (5) for selection.

5. Method according to any of the preceding claims, characterized in that the trajectory (7, 8) that has already been traveled in the past is evaluated by means of machine learning of an electronic computing device (2).

6. Method according to any of the preceding claims, characterized in that the trajectory (4) that can be traveled in future is provided for an assisted maneuvering operation of the motor vehicle (5) and / or for an assisted parking operation of the motor vehicle (5).

7. Method according to any of the preceding claims, characterized in that after the current position (P) has been detected and a match between the current position (P) and at least one previously saved position has been established, and in the absence of a trajectory (7,8) that has already been traveled in the past for the current position (P) in the storage device (3) of the assistance system (1), at least one of the following steps is performed: - recording a trajectory traveled from the current position (P) and offering to store the recorded trajectory as a trajectory that has been traveled in the past in the storage device (3) of the assistance system (1), or - offering to store the trajectory yet to be traveled, recording the trajectory traveled from the current position (P) and storing the recorded trajectory as a trajectory that has been traveled in the past in the storage device (3) of the assistance system (1).

8. Computer program product comprising program code means which cause an electronic computing device (2) to carry out a method according to any of claims 1 to 7 when the program code means are processed by the electronic computing device.

9. Assistance system (1) for providing a trajectory (4) that can be traveled in future for an at least partially assisted motor vehicle (5), which assistance system comprises at least one storage device (3), wherein the assistance system (1) is designed to carry out a method according to any of claims 1 to 7.