Method for vehicle guidance, controller, vehicle and storage medium

Abstract

The invention relates to a method (1000) for guiding a vehicle, comprising the following steps: receiving and / or invoking (150) sensor data, a termination criterion of a vehicle assistance system and a destination; identifying and / or tracking (200) a traffic object based on the sensor data; identifying (300) a driving operation of the traffic object based on the tracking of the traffic object; identifying (400) a congestion situation in the vehicle surroundings (1) by means of the identified driving operation; and taking over (500) autonomous longitudinal and lateral guidance of the vehicle (100) to a target location, the longitudinal and lateral guidance of the vehicle (100) to the target location being taken over (500) as long as a termination criterion of the driver assistance system is satisfied. The invention also relates to a controller, a vehicle, a computer program and a machine-readable storage medium.

Description

TECHNICAL FIELD

[0001] The invention relates to a method for vehicle guidance and to a vehicle having a controller for carrying out such a method. BACKGROUND

[0002] At present, many vehicles have a parking assistance system which is set up to autonomously guide the vehicle into a parking space or a certain surrounding of a parking area by means of longitudinal guidance and lateral guidance until a final position is reached. Here, the parking assistance system has an object recognition of objects in the surrounding. By means of detecting objects in the surrounding of the vehicle and their behavior during the parking process, it can be recognized whether a (further) vehicle is located in the driving trajectory of the (own) vehicle to the parking space. If a (further) vehicle and / or other objects, such as pedestrians or cyclists, are located in the preset driving trajectory of the (own) vehicle, the parking process will be terminated and the system has to be reactivated by the driver.

[0003] Most of the time, the parking area is located in a surrounding with a high traffic flow. For example, parking spaces at the edge of a road are often located in a corresponding traffic situation, so that during the parking-in and parking-out process of the vehicle, other vehicles want to drive past the vehicle from the side, or pedestrians cross the parking space. This is also the case for larger parking areas, for example in shopping centers or parking garages, in which multiple vehicles can be simultaneously maneuvered, parked in and parked out, and pedestrians can cross the driving lanes and driving trajectories. SUMMARY

[0004] In contrast, the method for vehicle guidance according to the invention has the advantage that an early termination of the parking assistance system due to the fulfillment of the termination criterion of the driver assistance system is prohibited. This has the result that the driver does not have to reactivate the driver assistance system. Thus, for the driver, the driving progress of the vehicle from the starting position to the target position in the parking area is significantly more fluent.

[0005] The method for vehicle guidance comprises the following steps. A first step comprises receiving and / or calling sensor data, a termination criterion of a vehicle assistance system and a target location. A second step comprises recognizing and / or tracking traffic objects based on the sensor data. A third step comprises recognizing driving maneuvers of the traffic objects based on the tracking of the traffic objects. A fourth step comprises recognizing a congestion situation in the surrounding of the vehicle by means of the recognized driving maneuvers. A fifth step comprises autonomously longitudinally guiding and laterally guiding the vehicle to the target location. As long as the termination criterion of the driver assistance system is fulfilled, the longitudinal guidance and lateral guidance of the vehicle to the target location is taken over.

[0006] Here, a congestion situation is to be understood as a traffic situation in which, in addition to the own vehicle, further traffic objects are located in the traffic trajectory of the own vehicle to the target location. In particular, a congestion situation is to be understood as a traffic situation in which further traffic objects are parked out of a parking space in which the own vehicle intends to park. In particular, a congestion situation is to be understood as any situation which leads to a termination of the driver assistance system due to the fulfillment of termination criteria of the driver assistance system.

[0007] In other words, the method for vehicle guidance is designed to recognize whether a termination of the driver assistance system exists due to the fulfillment of termination criteria of the driver assistance system. The method for vehicle guidance intervenes in the longitudinal guidance and in the lateral guidance of the vehicle in order to prevent the fulfillment of termination criteria of the driver assistance system. Here, the vehicle guidance for the driver assistance system is described by the method for vehicle guidance and the longitudinal guidance and the lateral guidance are taken over by the method for vehicle guidance as long as otherwise the termination criteria of the driver assistance system are fulfilled. Thus, such a fulfillment of the termination criteria of the driver assistance system is just avoided and the driver assistance system is not switched off. Thereby, the travel of the vehicle from its current position to the target location is more fluent.

[0008] In particular, the intervention in the longitudinal guidance and in the lateral guidance of the vehicle in order to prevent the fulfillment of the termination criteria of the driver assistance system can comprise reducing the vehicle speed up to a standstill and re-increasing the vehicle speed from the standstill of the vehicle.

[0009] In particular, the termination criteria comprise a predicted collision time of the own vehicle with the further traffic object being below a predefined collision time.

[0010] The preferred embodiment shows a preferred extension of the application.

[0011] Preferably, the driver assistance system is a parking assistance system and the target location is a target parking position. The termination criteria of the driver assistance system comprise a predefined minimum distance between the vehicle and a traffic object in the surroundings of the vehicle. The termination criteria are fulfilled if the predefined minimum distance between the own vehicle and the further traffic object is below. In particular, the termination criteria comprise a predefined minimum distance between the vehicle and a traffic object along the travel trajectory. An advantage of this embodiment can be that a parking process, in particular with complex travel maneuvers and many surrounding objects possibly crossing the trajectory of the vehicle, is not interrupted and the parking assistance system is not switched off. Here, the parking assistance system is provided for autonomously guiding the vehicle from a current starting position to the target parking position from a predefined distance to the target parking position.

[0012] Preferably, the identification and tracking of the traffic objects on the basis of the sensor data comprises the following steps. In a sixth step, the sensor data is recorded over a plurality of time steps. In a seventh step, object reflections in the sensor data are identified. In an eighth step, the object reflections over the plurality of time steps are mutually assigned to an object reflection group. In a ninth step, an object hypothesis is proposed on the basis of the object reflections. In a tenth step, the object reflection groups are assigned to the object hypothesis. The advantage of this embodiment can be that it enables reliable identification and tracking of the objects in the surroundings.

[0013] Preferably, the identification and tracking of the traffic objects on the basis of the sensor data comprises the following steps. An eleventh step comprises receiving and / or calling further sensor data. A twelfth step comprises identifying further object reflections in the further sensor data and, in the case of application of a Kalman filter, assigning the further reflections to the object hypothesis. The advantage of this embodiment can be that, by assigning further sensor data to the existing object hypothesis, the assignment can be reliably carried out. This improves the reliable tracking of the objects over a plurality of time steps.

[0014] Preferably, the identification of the driving maneuver of the traffic object on the basis of the tracking is carried out by means of a classifier and / or artificial intelligence. The advantage of this embodiment can be that, by applying a classifier and / or artificial intelligence, the driving maneuver of the traffic object in the surroundings can be reliably identified.

[0015] Preferably, a reduction in the distance between the ego vehicle and a traffic object driving in front and / or a traffic object following behind is identified as a driving maneuver of the traffic object. Preferably, a cut-in of the traffic object into the driving trajectory of the ego vehicle and / or a cut-out of the traffic object from the driving trajectory of the ego vehicle is identified as a driving maneuver of the traffic object. Preferably, a departure of the traffic object from a parking space into the driving trajectory of the ego vehicle is identified as a driving maneuver of the traffic object. The advantage of this embodiment can be that, by means of these identified driving maneuvers, dangerous situations which can lead to a termination of the driver assistance system can be reliably identified.

[0016] Preferably, the identification of the congestion situation comprises at least a consideration of the distance between the ego vehicle and a traffic object driving in front and / or a traffic object following behind. Preferably, the identification of the congestion situation comprises a cut-in of the traffic object into the driving trajectory of the ego vehicle and / or a cut-out of the traffic object from the driving trajectory of the ego vehicle. The advantage of this embodiment can be that, in the case of consideration of the above-mentioned congestion situations, the reliability of avoiding the fulfillment of the termination criterion of the driver assistance system is improved.

[0017] Preferably, in the case of recognition of a congestion situation, the recognition of the congestion situation is output to the driver of the vehicle. Preferably, the autonomous longitudinal guidance and / or lateral guidance of the vehicle is only taken over in the presence of a driver release. The advantage of this embodiment can be that the behavior of the vehicle is predictable and the driver does not need to intervene in the longitudinal guidance and lateral guidance of the vehicle.

[0018] Furthermore, the application comprises a controller which is designed to carry out the method according to one of the above embodiments. The controller thus has all the advantages of the respective embodiment of the method.

[0019] Furthermore, the application comprises a vehicle which has sensors and a controller according to the previous embodiment. The sensors and the controller are connected to one another to exchange signals. The sensors are designed to detect the surroundings of the vehicle. The vehicle thus has all the advantages of the controller and all the advantages of the method for the guidance of the vehicle.

[0020] Preferably, the sensors comprise ultrasonic sensors, cameras and / or lidar. The advantage of this embodiment can be that the existing sensors of the vehicle can be utilized. This reduces the manufacturing expenditure and manufacturing costs of the vehicle.

[0021] Furthermore, the application comprises a computer program which is designed to carry out the method according to one of the above embodiments.

[0022] Furthermore, the application comprises a machine-readable storage medium on which the computer program of the previous embodiment is stored. BRIEF DESCRIPTION OF DRAWINGS

[0023] In the following, embodiments of the application are described in detail with reference to the attached drawings. In the drawings:

[0024] Figure 1 a schematic diagram of a vehicle according to a first embodiment of the application is shown,

[0025] Figure 2 a schematic diagram of a method according to a first embodiment of the application is shown, and

[0026] Figure 3 a schematic diagram of a method according to a second embodiment of the application is shown.

[0027] Preferably, all identical elements, units and / or components have the same reference signs in all the figures. DETAILED DESCRIPTION

[0028] Figure 1A schematic diagram of a vehicle 100 according to a first embodiment of the application is shown. The vehicle 100 has sensors 10, 20 and a controller 30. The sensors 10, 20 are connected with the controller 30 to exchange signals. The sensors 10, 20 are arranged for detecting a vehicle surrounding 1. In particular, the sensors 10, 20 comprise a camera 10 and an ultrasonic sensor 20. The controller 30 is arranged for performing a method 1000 according to the first embodiment or according to the second embodiment.

[0029] Figure 2 A schematic diagram of a method 1000 according to the first embodiment of the application is shown. The method 1000 for vehicle guidance has the following steps. A first step 100 comprises receiving and / or calling sensor data, a termination criterion of a driver assistance system and a target location. A second step 200 comprises identifying and / or tracking a traffic object based on the sensor data. A third step 300 comprises identifying a driving maneuver of the traffic object based on the tracking of the traffic object. A fourth step 400 comprises identifying a congestion situation in the vehicle surrounding 1 by means of the identified driving maneuver of the traffic object. A fifth step 500 comprises taking over an autonomous longitudinal guidance and lateral guidance of the vehicle 100 to the target location. Here, the longitudinal guidance and lateral guidance of the vehicle 100 to the target location is taken over as soon as the termination criterion of the driver assistance system is fulfilled.

[0030] The driver assistance system is a parking assistance system and the target location is a target parking position. The termination criterion of the driver assistance system comprises a predefined minimum distance between the vehicle 100 and the traffic object in the vehicle surrounding 1. The termination criterion is fulfilled if the distance between the own vehicle 100 and the traffic object is below the predefined minimum distance. The parking assistance system is arranged for autonomously guiding the vehicle 100 from a current vehicle position into the target parking position up to a final parking position from a predefined distance to the target parking position on. The identification 300 of the driving maneuver of the traffic object based on the tracking of the traffic object is performed by means of a classifier.

[0031] Further, the identification 300 of the driving maneuver of the traffic object comprises identifying a reduction of the distance between the own vehicle and a traffic object driving in front and / or a traffic object following behind. Further, the identification 300 of the driving maneuver of the traffic object comprises identifying a traffic object cutting out of (a lane / driving track) and / or a traffic object cutting into (a lane / driving track). Further, the identification 300 of a driving maneuver of a traffic object from a parking surface off into the driving track of the (own) vehicle.

[0032] The identification of a congestion situation is based at least on consideration of the distance between the preceding and / or following traffic objects and the vehicle. This means that a congestion situation is identified if the preceding or following traffic objects fall below a predetermined minimum distance from the vehicle when exiting. Furthermore, the identification of a congestion situation is based on the entry and / or exit of traffic objects. This means that a congestion situation is identified if (another) vehicle is identified as entering the vehicle's driving trajectory from another lane and / or from a parking surface. Furthermore, a congestion situation is identified if an exiting traffic object exits the vehicle's current driving trajectory into the parking surface and / or onto a parallel lane.

[0033] Figure 3 FIG2 is a schematic diagram of a method 1000 according to a second embodiment of the present invention. The second embodiment has similar method steps to the first embodiment.

[0034] A method 1000 for vehicle guidance according to a second embodiment of the present invention comprises the following steps. A first step 100 includes receiving and / or retrieving sensor data, termination criteria for a driver assistance system, and a target location. A second step 200 includes identifying and / or tracking traffic objects based on the sensor data. The second step comprises the following steps 6 to 12. A sixth step 210 includes recording sensor data in multiple time steps. A seventh step 220 includes identifying object reflections in the sensor data. An eighth step 230 includes assigning object reflections in the multiple time steps to one object reflection group. A ninth step 240 includes developing an object hypothesis based on the object reflections. A tenth step 250 includes assigning the object reflection group to the object hypothesis. An eleventh step 260 includes receiving and / or retrieving additional sensor data. A twelfth step 270 includes identifying additional object reflections in the additional sensor data and assigning the additional object reflections to the object hypothesis by applying a Kalman filter. A third step 300 includes identifying the driving maneuvers of the traffic objects based on tracking of the traffic objects. A fourth step 400 includes identifying a congestion situation in vehicle surroundings 1 using the identified driving maneuvers of these traffic objects. A thirteenth step includes outputting 450 the identification (result) of the congestion situation to the driver. A fifth step 500 includes taking over the autonomous longitudinal driving and lateral guidance of vehicle 100 to the destination, if the driver has given permission.

Claims

1. A method (1000) for vehicle guidance, the method having the steps of: receiving and / or calling (150) sensor data, termination criteria of a vehicle assistance system and a target location; identifying and / or tracking (200) a traffic object on the basis of the sensor data; identifying (300) a driving maneuver of the traffic object on the basis of the tracking of the traffic object; identifying (400) a congestion situation in the vehicle surroundings (1) by means of the identified driving maneuver; and autonomously longitudinally and laterally guiding (500) the vehicle (100) to the target location, wherein the longitudinal and lateral guidance of the vehicle (100) to the target location is taken over as soon as the termination criteria of the driver assistance system are met.

2. The method (1000) of claim 1, wherein The driver assistance system is a parking assistance system and the target location is a target parking position, wherein the termination criteria of the driver assistance system comprise a predefined minimum distance of the vehicle (100) from a traffic object in the vehicle surroundings (1).

3. The method (1000) according to one of the preceding claims, wherein The identification and tracking (200) of a traffic object on the basis of sensor data has the steps of: recording (210) the sensor data in a plurality of time steps; identifying (220) object reflections in the sensor data; mutually attributing (230) the object reflections in a plurality of time steps to object reflection groups; formulating (240) object hypotheses on the basis of the object reflections; and attributing (250) the object reflection groups to the object hypotheses.

4. The method (1000) of claim 3, wherein, The identification and tracking (200) of a traffic object on the basis of sensor data has the steps of: receiving and / or calling (260) further sensor data; identifying (270) further object reflections in the further sensor data and, in the case of an applied Kalman filter, attributing the further object reflections to the object hypotheses.

5. The method (1000) according to one of the preceding claims, wherein The identification (300) of a driving maneuver of a traffic object on the basis of the tracking of the traffic object is carried out by means of a classifier and / or artificial intelligence.

6. The method (1000) of claim 5, wherein, The following driving maneuvers of the traffic object are identified: a reduction in the distance between the vehicle (100) and a traffic object driving in front and / or a traffic object following behind; and / or a cut-in of the traffic object into the driving trajectory of the vehicle (100) and / or a cut-out of the traffic object from the driving trajectory of the vehicle (100); and / or a driving out of the traffic object from a parking surface into the driving trajectory of the vehicle (100).

7. The method (1000) according to any one of the preceding claims, characterized in that The identification (400) of the congestion situation is based at least on the distance between the vehicle (100) and a traffic object driving in front and / or a traffic object following behind and / or on a cut-in of the traffic object into the driving trajectory of the vehicle (100) and / or a cut-out of the traffic object from the driving trajectory of the vehicle (100).

8. The method (1000) according to one of the preceding claims, wherein The identification (400) of the congestion situation is output (450) to the driver and the autonomous longitudinal and / or lateral guidance is only taken over (500) in the presence of a driver approval.

9. A controller (30) configured to perform the method (1000) according to one of the preceding claims 1 to 8.

10. A vehicle (100) having: - a sensor (10, 20); and - a controller (30) according to claim 9; wherein - the sensor (10, 20) is configured to detect a vehicle surrounding (1), and - wherein the sensor (10, 20) is connected to the controller (30) to exchange signals.

11. A computer program configured to perform the method (1000) according to one of the preceding claims 1 to 8.

12. A machine-readable storage medium having stored the computer program according to claim 11.

Images