A method and a parking assistance device for dynamically planning a parking trajectory of a vehicle during a parking process that is at least partially automatically executed

Abstract

The present invention relates to a method for dynamically planning a parking trajectory of a vehicle (1) during a parking process that is at least partially automatically executed, comprising the steps of: detecting (S10) the surrounding environment of the vehicle (1) by means of at least one sensor device; calculating and setting (S11) a target position (Z1) of the vehicle (1) based on the surrounding environment data detected by the at least one sensor device; planning (S12) a parking trajectory based on the set target position (Z1); during the parking process, recalculating (Z2, Z3, Zx) the target position based on the surrounding environment data updated during the parking process (S13); a step of differentially comparing the set target position (Z1) with an average value calculated from at least one subset of the target positions (Z2, Z3, Zx) recalculated during the parking process, wherein if the difference between the set target position and the calculated average value exceeds a predetermined threshold, the set target position (Z1) is updated (S14); and dynamically replanning (S15) the parking trajectory based on the updated target position (Z2, Z3, Zx).

Description

Technical Field

[0001] The present invention relates to a method for dynamically planning a parking trajectory of a vehicle during a parking process that is at least partially automatically executed, detecting the surrounding environment of the vehicle by at least one sensor device, and calculating and setting a target position of the vehicle based on the surrounding environment data detected and transferred by the at least one sensor device. The present invention also relates to a parking assistance device and a vehicle.

Background Art

[0002] In the prior art, based on the current driving scenario created based on a surrounding environment model, a parking assistance system that can calculate, at least partially automatically, that is, for example, without the driver intervening in steering and / or without the driver operating the accelerator pedal or the brake pedal, the trajectory along which the vehicle moves is already known.

[0003] While the parking process is being executed at least partially automatically, the surrounding environment model provided by the vehicle's driving assistance system may change. Various causes can be considered for changes in the surrounding environment model. For example, due to a decrease in speed during the parking process, the surrounding environment detection becomes more accurate (compared to the detection when passing through the parking space), when entering the parking space, new details of the surrounding environment that were not detected by the vehicle's sensor system when passing through the parking space are detected, a change in the parking situation (for example, the parking space is larger or smaller than at the time of the initial planning of the parking process), and / or a temporary change occurs in the situation of the surrounding environment, for example, due to the intrusion of pedestrians to the edge of the parking space.

[0004] As a result, it may become impossible to execute the initially set parking trajectory while avoiding collisions, or the vehicle may obtain an unfavorable target final position or an inaccurately aligned target final position.

[0005] In such a situation, in a known parking assistance system, the parking process is ended or at least the vehicle is stopped. Alternatively, in order to reach a more optimal parking or departure position, it is conceivable to update the calculated target position based on the details of the new surrounding environment. However, this may result in the target position being continuously updated, for example, in each measurement cycle of the sensor device. Since the change of the target position is associated with the recalculation of an alternative parking trajectory, in many cases, steering is required, that is, the vehicle is moved not on a series of consecutive parking trajectories but on a plurality of consecutive parking trajectories. This type of plan change is not very comfortable for the vehicle occupants.

Summary of the Invention

Problems to be Solved by the Invention

[0006] Accordingly, an object of the present invention is to provide a method for dynamically planning a parking trajectory of a vehicle during a parking process that is at least partially automatically executed, which can respond to changes in the parking situation and has high parking comfort, and thus high user acceptance.

Means for Solving the Problems

[0007] This problem is solved by a method having the features of independent claim 1. Preferred embodiments are the subject matter of the dependent claims. A parking assistance device for planning a parking trajectory of a vehicle is the subject matter of parallel independent claim 9.

[0008] According to a first aspect, the present invention relates to a method for dynamically planning a parking trajectory of a vehicle during a parking process that is at least partially automatically executed, particularly during a parking or departure process. The vehicle may be, for example, a passenger car having four wheels. Also, the configuration of the vehicle may be, as another type of motor vehicle or as a vehicle without a prime mover, for example, as a trailer. In particular, the vehicle may be a set of a motor vehicle and a trailer. The method comprises the following steps.

[0009] First, the surrounding environment of the vehicle, purely as an example, a parking lot, a parking space or an inductive charging plate, is detected by at least one sensor device of the vehicle. Based on the surrounding environment data detected by the at least one sensor device, the target position of the vehicle is calculated and set. Next, a parking trajectory is planned and, in particular, controlled based on the set target position. In particular, the parking trajectory indicates the movement of the vehicle towards the target position. The surrounding environment data includes, for example, information on the road model, object information in the vehicle's surrounding environment and the driving dynamics model of the vehicle.

[0010] During the parking process that is at least partially automatically executed along the planned, initially or finally set parking trajectory, the target position is recalculated based on the surrounding environment data updated during the parking process. The recalculation of the target position is used to determine whether to move the vehicle towards a new target position that is different from the initial target position. Particularly preferably, the recalculation is performed continuously, that is, at regular time intervals.

[0011] After recalculating the target position, a differential comparison is made between the initially or finally set target position and the average value calculated from at least one subset of the target positions recalculated during the parking process. Preferably, outliers are not considered when calculating the average value from the recalculated target positions.

[0012] If the difference between the initially or finally set target position and the calculated average value exceeds a predetermined threshold, the initially or finally set target position is updated. In other words, the parking situation and / or the position of the recalculated target position are evaluated with respect to the initially or finally set target position, and adjusted according to the evaluation result. The dynamic replanning of the parking trajectory is performed based on the updated target position.

[0013] When recalculating the target position, the automatic parking process may not have started yet, that is, for example, at the start of parking, the updated surrounding environment may already have been detected. On the other hand, when a part of the current parking trajectory has already been traveled, the target position may be recalculated.

[0014] By the method according to the present invention, it is possible to advantageously determine whether a new target position appears via a set of recalculated target positions during the parking process, or whether the new target position is generated only due to measurement tolerances. Also, a larger deviation can be reliably calculated via the calculation of the average value of the recalculated target positions, and it is possible to respond to this larger deviation in a time-efficient manner. On the other hand, when the change in the surrounding environment is small, the target position and the parking trajectory are maintained so as to ensure a robust automatic parking behavior. In this way, it is possible to prevent a continuous change in the planned parking trajectory that requires a high computational complexity.

[0015] According to a preferred embodiment, the recalculated target positions during the parking process are weighted according to timeliness during the calculation of the average value. In particular, a higher weight is given to newer data so as to enable adjustment of the target position to the current surrounding environment.

[0016] When it is necessary to update the set target position, it is preferably the last recalculated target position that is selected as the updated target position. This is advantageous, for example, when the deviation from the preceding target position is small and the last calculated target position can be considered to indicate an accurate value. On the other hand, it can also be configured such that the calculated average value is selected as the updated target position.

[0017] Preferably, the average value is calculated from at least three recalculated target positions that do not necessarily have to be evaluated continuously with respect to each other. Rather, preferably, the average value of at least three recalculated target positions is used that takes into account the parking space detected as completely as possible, for example, the entire lateral boundary of the parking space. In this way, it is possible to reduce the case where it becomes necessary to update the target position again because the detected surrounding environment is insufficient or incomplete.

[0018] Particularly preferably, the set target position includes the position and orientation of the vehicle with respect to the space-fixed coordinate system, and the update of the target position can relate to the position and / or orientation. Checking whether to update the set target position includes, for example, calculating the difference between the set lateral target position value and the recalculated lateral target position value.

[0019] According to an example embodiment, during the parking process, the target position is recalculated in each measurement cycle of at least one sensor device.

[0020] According to an example embodiment, the parking process is a diagonal parking process or a perpendicular parking process. These parking processes are characterized in that due to the large depth of the parking lot, the initial detection of the parking situation when passing through the parking space is often insufficient, and the surrounding environment model is updated at least partially when entering the parking space, and it is necessary to change the planned first parking trajectory.

[0021] According to an example embodiment, the speed of the vehicle when traveling along the set parking trajectory is 0.2 m / s to 3 m / s. Due to the low speed of the vehicle, the updated parking trajectory can have a relatively small radius of curvature, and thus it is possible to reach the new target position even in the case of a relatively short new parking trajectory.

[0022] According to a further aspect, the present invention relates to a parking assistance device that dynamically plans the parking trajectory of a vehicle during a parking process that is at least partially automatically executed. The present invention is particularly advantageous for automation levels of SAE level 2 or higher.

[0023] The parking assistance device includes a sensor device that detects the surrounding environment of the vehicle, and an evaluation unit that is configured to calculate and set the target position of the vehicle based on the surrounding environment data detected and transferred by at least one sensor device. Further, the evaluation unit is configured to plan a parking trajectory based on the set target position. The parking trajectory is particularly a combination of an arc, a straight line and / or a cycloid, and the set target position is reached using the parking trajectory.

[0024] The evaluation unit is configured to recalculate the target position based on the surrounding environment data updated during the parking process during the parking process. Further, the evaluation unit performs a differential comparison between the set target position and the average value calculated from at least one subset of the target positions recalculated during the parking process, and outputs an update of the set target position when the difference between the set target position and the calculated average value exceeds a predetermined threshold. The evaluation unit is configured to dynamically replan the parking trajectory based on the updated target position. In particular, the calculation unit is configured to automatically control the vehicle to be parked along the replanned parking trajectory.

[0025] According to a further aspect, the present invention relates to a vehicle provided with the above parking assistance device.

[0026] In the context of the present invention, the expressions "about", "substantially" or "approximately" mean a deviation of + / - 10% from the exact value, preferably + / - 5%, and / or a deviation due to a negligible change with respect to the function.

[0027] The development forms, advantages and applicability of the present invention will also become apparent from the following description of the embodiments and the figures. Here, all features described and / or illustrated are in principle the subject matter of the present invention, independently or in any combination, regardless of the combination of features in the claims or the relevance of the claims. Also, the content of the claims forms part of this description.

Brief Description of the Drawings

[0028] Hereinafter, the present invention will be described in detail with reference to the drawings related to the embodiments.

Figure 1

Figure 2

Figure 3

Figure 4

DETAILED DESCRIPTION OF THE INVENTION

[0029] The present invention relates to a method for dynamically planning a parking trajectory of a vehicle during a parking process that is at least partially automatically executed using a parking assistance device. Here, "dynamically planning" means that after calculating a new target position taking into account changes in the situation of the vehicle's surrounding environment, the vehicle is further moved along a parking trajectory adjusted to the new target position. The trigger for changing the planned parking trajectory can be automatically generated by the evaluation unit of the vehicle, for example, when the sensor device of the vehicle detects that the parking situation has changed and the vehicle needs to acquire a new target position. Such changes in the parking situation exist, for example, when the parking space planned to be parked using the parking process expands or shrinks, when an object that was not initially detected limits the parking space, or when the orientation of the parking space was initially acquired differently.

[0030] FIG. 1 illustratively and schematically shows the initially set target position Z1 regarding the parking process of the vehicle 1 parked in the parking space PL. The parking space PL is limited, for example, by an object, for example, a third-party vehicle, a curb, or a boundary line.

[0031] For example, due to the speed of the vehicle 1 when passing through the parking space PL and / or the distance between the vehicle 1 and the parking space PL, the parking trajectory may be planned based on a surrounding environment model that does not correspond to the general situation of the actual parking situation. For example, when entering the parking space, an obstacle that becomes an obstacle when the vehicle 1 is placed at the initially set target position Z1 may be detected for the first time. As a result, it is necessary to change the planned target position Z1 to a new target position Z2 of a new parking trajectory accordingly.

[0032] The first target position Z1 is generated based on a surrounding environment model created particularly before the start of the parking process. When the parking process is started, particularly when the vehicle 1 is moved on the initial parking trajectory using the parking assistance device, the recalculation of the target position is performed at regular intervals based on the surrounding environment data updated during the parking process.

[0033] FIG. 2 shows the updated target position Z2, which is different from the initial target position Z1. Regarding the updated target position Z2, the vehicle 1 is maneuvered along the replanned parking trajectory.

[0034] FIG. 3 shows, as a mere example, seven recalculated lateral target positions Z2 to Z8. An average value is calculated from at least one subset of these recalculated target positions Z2 to Z8. In the case of this embodiment example, since the measured value 3 is shown as an outlier, it is not considered in the average value calculation. The target positions Z2 to Z8 are recalculated, for example, at each measurement cycle of at least one sensor device of the vehicle 1.

[0035] In order to determine whether or not an update of the planned parking trajectory is necessary with a small amount of calculation, a difference comparison is made between the set target position Z1 and the average value calculated from at least one subset of the recalculated target positions Z2 to Z8. When the difference between the set target position Z1 and the calculated average value exceeds a predetermined threshold value, the set target position Z1 is updated. In this way, a dynamic and robust correction of the target position is achieved, thereby avoiding an unfavorable parking position.

[0036] Figure 4 shows a schematic block diagram explaining the dynamic planning of the parking trajectory of vehicle 1 during a parking process that is at least partially automatically executed. First, the surrounding environment of vehicle 1 is detected by at least one sensor device (S10). In the next step, based on the surrounding environment data detected by the at least one sensor device, the target position Z1 of vehicle 1 is calculated and set (S11), and based on the set target position Z1, a parking trajectory is planned (S12). During the parking process, based on the surrounding environment data updated during the parking process, the target position is recalculated (S13). In the next step, a differential comparison is made between the set target position and the average value calculated from at least one subset of the target positions Z2 to Zx recalculated during the parking process. If the difference between the set target position and the calculated average value exceeds a predetermined threshold, the set target position is updated (S14). Based on the updated target position, the parking trajectory is dynamically replanned (S15).

[0037] The above method is suitable for parallel parking situations, perpendicular parking situations, or diagonal parking situations.

Claims

1. A method for dynamically planning a parking trajectory of a vehicle (1) during a parking process that is at least partially automatically executed, comprising: - detecting the surrounding environment of the vehicle (1) by means of at least one sensor device (step S10); - calculating and setting a target position (Z1) of the vehicle (1) based on the surrounding environment data detected by the at least one sensor device (step S11); - planning a parking trajectory based on the set target position (Z1) (step S12); - during the parking process, recalculating (Z2, Z3, Zx) the target position based on the surrounding environment data updated during the parking process (step S13); - a step of differentially comparing the set target position (Z1) with an average value calculated from at least one subset of the recalculated target positions (Z2, Z3, Zx) during the parking process, wherein if the difference between the set target position (Z1) and the calculated average value exceeds a predetermined threshold value, the set target position (Z1) is updated (step S14) and - dynamically replanning the parking trajectory based on the updated target positions (Z2, Z3, Zx) (step S15).

2. The method according to claim 1, wherein the average value calculated during the recalculation during the parking process is weighted according to timeliness.

3. The method according to claim 1 or 2, wherein the set target position includes the position and orientation of the vehicle with respect to a spatially fixed coordinate system, and the update of the target position can relate to the position and / or the orientation.

4. The method according to any one of claims 1 to 3, wherein the average value is calculated from at least three recalculated target positions that take into account the parking space detected as completely as possible.

5. The method according to any one of claims 1 to 4, wherein the last recalculated target position is selected as the updated target position.

6. The method according to any one of claims 1 to 5, wherein during the parking process, the target positions (Z2, Z3, Zx) are recalculated in each measurement cycle of the at least one sensor device.

7. The method according to any one of claims 1 to 6, wherein the parking process is a diagonal parking process or a perpendicular parking process.

8. The method according to any one of claims 1 to 7, wherein the speed of the vehicle (1) when traveling on the set parking trajectory is 0.2 m / s to 3 m / s.

9. In a parking assistance device that dynamically plans the parking trajectory of a vehicle (1) during a parking process that is at least partially automatically executed, a sensor device that detects the surrounding environment of the vehicle; an evaluation unit configured to calculate and set a target position of the vehicle based on the surrounding environment data detected and transferred by the at least one sensor device, wherein the evaluation unit is configured to plan a parking trajectory based on the set target position; wherein the evaluation unit is configured to recalculate the target position based on the surrounding environment data updated during the parking process during the parking process; the evaluation unit calculates a difference comparison between the set target position (Z1) and an average value calculated from at least one subset of the target positions (Z2, Z3, Zx) recalculated during the parking process, and when the difference between the set target position (Z1) and the calculated average value exceeds a predetermined threshold value, the evaluation unit is configured to output an update of the set target position, and the evaluation unit is configured to dynamically replan the parking trajectory based on the updated target position (Z2, Z3, Zx). A parking assistance device.

10. A vehicle comprising the parking assistance device according to claim 9.

Images