DE102016202317A1 - METHOD FOR CONTROLLING VEHICLE FUNCTIONS THROUGH A DRIVER ASSISTANCE SYSTEM, DRIVER ASSISTANCE SYSTEM AND VEHICLE - Google Patents

Abstract

The invention relates to a method for controlling vehicle functions by a driver assistance system (20) of a vehicle (7), comprising the steps of: providing (S1) sensor data relating to a vehicle environment of the vehicle (7) by a plurality of vehicle sensors (21) of the vehicle ( 7); Classifying (S2) the vehicle sensors (21) into different vehicle sensor type classes; Creating (S3) an occupancy grid (1) representing the vehicle environment of the vehicle (7), grid cells (6) of the occupancy grid (1) being assigned grid cell information based on the provided sensor data, and grid cells (6) of the occupancy grid (1) the vehicle sensor type classes of those vehicle sensors (21) whose sensor data are used to create the grid cell information of the respective grid cell (6) are assigned meta information; and controlling (S4) vehicle functions of the vehicle (7) by the driver assistance system (20) using the created occupancy grid (1).

Description

The present invention relates to a method for controlling vehicle functions by a driver assistance system of a vehicle, a driver assistance system for a vehicle and a vehicle.

Increasingly, driver assistance systems assist the driver in controlling the vehicle or take over individual driving functions of the vehicle or the complete control of the vehicle. In order to ensure safety in (semi-) autonomous driving, it is necessary to ensure a precise recognition of the vehicle environment of the vehicle.

A widely used method is to create an occupancy grid that represents the vehicle environment of the vehicle. The allocation grid can comprise a multiplicity of levels, wherein information relating to the traversability of the area corresponding to the cell or also height information of this area is entered into the grid cells of the occupation grid. So is out of the DE 10 2012 109 377 A1 discloses a method for representing environmental structures in an occupancy grid, wherein values for a criticality are entered to classify a hazard.

Next is from the DE 10 2013 217 488 A1 an occupancy grid known, wherein the occupancy grid comprises a plurality of levels, wherein in a further level information is deposited only when the information of the grid cell in the first level occupies a predetermined value.

In most cases, a particular area of the vehicle environment is monitored by a variety of different vehicle sensors, such as radar sensors, vehicle cameras or ultrasonic sensors. The quality of the information provided by the sensors may depend on the weather conditions or the quality of the vehicle sensors themselves. In some cases, erroneous information is also entered in the allocation grid. Thus, it may happen that objects are detected which do not exist in reality, thereby making it difficult to control vehicle functions by the driver assistance system.

It is therefore an object of the present invention to provide an improved method for controlling vehicle functions by a driver assistance system of a vehicle.

This object is achieved by a method for controlling vehicle functions by a driver assistance system of a vehicle having the features of patent claim 1, a driver assistance system for a vehicle having the features of claim 9 and a vehicle having the features of claim 14.

Accordingly, the present invention provides a method for controlling vehicle functions by a driver assistance system of a vehicle, wherein sensor data relating to a vehicle environment of the vehicle is provided by a plurality of vehicle sensors of the vehicle. Further, the vehicle sensors are classified into different vehicle sensor type classes. An occupancy grid, which represents the vehicle environment of the vehicle, is created, wherein grid cells of the occupancy grid are assigned grid cell information on the basis of the provided sensor data. Furthermore, grid cells of the occupancy grid are assigned meta information on the basis of the vehicle sensor type classes of those vehicle sensors whose sensor data are used to generate the grid cell information of the respective grid cell. Using the created occupancy grid, vehicle functions of the vehicle are controlled by the driver assistance system.

Further, a driver assistance system for a vehicle is provided, which is designed to receive from a plurality of vehicle sensors of the vehicle provided sensor data relating to a vehicle environment of the vehicle. The driver assistance system is hereby designed to classify the vehicle sensors into different vehicle sensor type classes, and to create an occupancy grid which represents the vehicle surroundings of the vehicle. Grid cells of the occupancy grid are assigned grid cell information on the basis of the provided sensor data, wherein grid cells are assigned meta information on the basis of the vehicle sensor type classes of those vehicle sensors whose sensor data are used to generate the grid cell information of the respective grid cell. The driver assistance system is further configured to control vehicle functions of the vehicle using the created occupancy grid.

In most cases, a vehicle includes a plurality of vehicle sensors, the vehicle having a plurality of vehicle sensors from the same vehicle sensor class. For example, the vehicle may include a plurality of vehicle cameras that may be associated with the vehicle camera sensor class. Often, the quality and reliability of sensed sensor data depends on the specific vehicle sensor type class of the vehicle sensor. For example, the quality of vehicle cameras is of lower quality in the dark. However, it is by the invention it is possible to store corresponding meta-information in the allocation grid, so that the quality and the origin of the grid-cell information can be taken into account when controlling driving functions of the vehicle by the driver assistance system. Thus, in particular, sensor data from degenerate or non-reliably operating vehicle sensors can be corrected or removed. This increases the accuracy of the occupancy grid and thus improves the reliability of the driver assistance system and increases safety.

According to a preferred embodiment of the method according to the invention, the grid cell information includes values relating to a roadway height and / or an occupying state. In the occupancy state, it is possible, for example, to differentiate between occupied and unoccupied, in order thus to specify a mobility of the area corresponding to the grid cell in the vehicle surroundings of the vehicle.

According to a preferred embodiment of the method according to the invention, the meta-information may comprise a percentage contribution of the respective vehicle sensor type class to the grid cell information of the respective grid cell. The reliability of the grid cell information of the corresponding grid cell can thus be calculated on the basis of the quality of the vehicle sensors of the corresponding vehicle sensor type classes.

According to a preferred development of the method according to the invention, the meta-information comprises acquisition time information and / or self-diagnosis information of the vehicle sensors of the vehicle sensor type class. The detection time information preferably includes an accurate detection timing at which the sensor data was acquired. If the sensor data are detected, for example, after dark, then for those grid cells for which grid cell information was generated based on vehicle cameras of the vehicle camera sensor class, it can be stored in the meta information that an accuracy of the grid cell information is reduced.

Self-diagnosis information may include, for example, information about the condition of the vehicle sensor included in the vehicle sensors themselves. For example, a vehicle sensor can detect if the quality of the vehicle sensor is reduced. For example, a vehicle sensor can detect that the sensor is due to snowfall conditionally or not operational.

According to a preferred embodiment of the method according to the invention, the vehicle sensor type classes comprise radar sensor classes and / or vehicle camera sensor classes and / or laser sensor sensor classes and / or ultrasound sensor classes and / or lidar sensor classes and / or depth image sensor type classes.

According to a preferred development of the method according to the invention, an object recognition is carried out on the basis of the grid cell information. The recognition accuracy of the detected objects is calculated by evaluating the meta-information. This has the advantage that not only the objects themselves are recognized, but also information about the quality of the recognition is available. If an object is detected, for example, only with a low recognition accuracy, then the driver assistance system can, for example, control vehicle sensors of the vehicle sensor, so that a corresponding area is additionally monitored and evaluated in order to increase the accuracy of the object recognition. Then it can be confirmed or rejected whether an object exists.

According to a preferred embodiment of the method according to the invention recognized objects are rejected as erroneously recognized objects, if the recognition accuracy is below an adjustable predetermined threshold. Thus it can be prevented that non-existing objects are detected. The precision and safety of the driver assistance system is further improved.

According to a preferred embodiment of the method according to the invention, a lane boundary detection is performed based on the grid cell information. Spatially adjacent recognized lane boundaries are merged into a single lane boundary if meta information is used to detect that the spatially adjacent detected lane boundaries were detected from sensor data of different vehicle sensor classifications. This has the advantage that redundant information can be eliminated, and thus the allocation grid is clearer and easier to evaluate.

According to a preferred development of the driver assistance system according to the invention, the grid cell information includes values relating to a roadway height and / or an occupancy state.

According to a preferred refinement of the driver assistance system, the meta information comprises a percentage contribution of the respective vehicle sensor type class to the grid cell information of the respective grid cell.

According to a preferred embodiment of the driver assistance system include the Meta information acquisition time information and / or self-diagnosis information of the vehicle sensor class vehicle sensors.

According to a preferred refinement, the driver assistance system is further designed to perform object recognition on the basis of the grid cell information and to calculate a recognition accuracy of the detected objects by evaluating the meta information.

According to a preferred development of the vehicle, the vehicle sensors include radar sensors and / or vehicle cameras and / or laser sensor and / or ultrasound sensors and / or lidar sensors.

The present invention will be explained in more detail with reference to the exemplary embodiments indicated in the schematic figures of the drawings.

Show it:

1 a flowchart for explaining a method according to the invention for controlling vehicle functions by a driver assistance system;

2 an exemplary occupancy grid according to an embodiment of the invention;

3 to 5 exemplary levels of an occupancy grid according to an embodiment of the invention;

6 a block diagram of a driver assistance system according to the invention; and

7 a block diagram of a vehicle according to the invention.

1 shows a flowchart for explaining a method for controlling vehicle functions by a driver assistance system of a vehicle according to a first embodiment of the invention.

Under vehicle here is a motor vehicle, such as a passenger car or a truck, a watercraft or an aircraft to understand.

Vehicle functions include active vehicle functions, such as steering, accelerating, or braking the vehicle, and passive vehicle functions, such as activating actuators of the vehicle, displaying information or images in an interface of the vehicle, or wirelessly broadcasting information to other road users or a traffic center.

In a first method step S1, sensor data regarding a vehicle environment of the vehicle are provided by a plurality of vehicle sensors of the vehicle. Vehicle sensors include, for example, radar sensors and / or vehicle cameras and / or laser sensors, in particular laser scanners, and / or ultrasound sensors and / or lidar sensors.

In a second method step S2, the vehicle sensors are classified or classified into different vehicle sensor type classes. For example, if the vehicle has four radar sensors, five vehicle cameras, three laser sensors, six ultrasonic sensors, and two lidar sensors, the radar sensors become a radar sensor class, the vehicle cameras into a vehicle camera sensor class, the laser sensor into a laser sensor sensor class, the ultrasonic sensors into an ultrasonic sensor class, and the lidar sensors into one Divided Lidarsensorklasse.

According to other embodiments, a detailed classification of the vehicle sensors may be performed. For example, the radar sensors of the vehicle may be classified into a far field radar sensor class, a near field radar sensor class, and a residual radar sensor class. According to further embodiments, the vehicle sensors may also be grouped into a smaller number of vehicle sensor type classes, for example, the vehicle sensor type classes may include an optical vehicle sensor class, wherein vehicle cameras and laser sensor are classified into the optical vehicle sensor class.

According to further embodiments, the vehicle sensor type classes may be selected independently of a physical sensor measurement principle. For example, vehicle sensors that contribute to a depth or distance image, such as stereo cameras, laser sensors or ultrasound sensors, can be classified into a separate vehicle sensor class, such as a depth image sensor class, depth image type classes, depth image type classes. In particular, vehicle type classes can be selected on the basis of already prepared or preprocessed sensor data and the vehicle sensors can be classified accordingly.

The vehicle sensor type classes may be classified according to one embodiment by physical measurement principles. For example, the vehicle sensor type classes may include an optical vehicle sensor type class and a radar sensor type class. Furthermore, the sensors can be classified according to the quality of the sensor data For example, the vehicle sensor type classes may include a rough data vehicle sensor type class and a precision data vehicle sensor type class, for example. Further, the vehicle sensors may be classified based on a range of the sensors, for example, the vehicle sensor type classes may include a near field radar sensor type class and a far field radar sensor class class.

In a further method step S3, an allocation grid 1 created, which represents the vehicle environment of the vehicle, as in 2 shown. The allocation grid 1 in this case comprises a plurality of grid cells 6 , where grid cells 6 of the allocation grid 1 Grid information is assigned based on the provided sensor data. The grid cell information may hereby level in a plurality of grid cell information 2 . 3 . 4 be registered. For example, in a first grid cell information level 2 the roadway height of the respective grid cell 6 corresponding area of the vehicle environment of the vehicle 7 be entered in a second grid cell information level 3 an information can be entered if one of the respective grid cell 6 corresponding area of the vehicle environment of the vehicle 7 free, that is for the vehicle 7 is traversable, and in a third grid cell information level 4 an information can be entered if one of the respective grid cell 6 corresponding area of the vehicle environment of the vehicle 7 occupied, that is for the vehicle 7 is not traversable. If there are no sensor data, preferably no grid cell information is entered.

Next are grid cells 6 of the allocation grid 1 based on the vehicle sensor type classes of those vehicle sensors 21 , their sensor data for creating the grid cell information of the respective grid cell 6 used to map meta-information. The meta-information is put into a meta-information-level 5 of the allocation grid 1 entered.

According to one embodiment, the meta information includes a percentage contribution of the respective vehicle sensor type class to the grid cell information of the respective grid cell.

In a further method step S4, vehicle functions of the vehicle are adjusted by the driver assistance system using the created occupancy grid 1 controlled. For example, the driver assistance system as a lane departure warning system can control the vehicle based on the grid cell information and meta information.

In 3 is the third grid cell information plane 4 of the allocation grid 1 illustrated for an exemplary scenario. The vehicle 7 This includes, for example, three radar sensors and four vehicle cameras. The three radar sensors are classified into a radar sensor class and the four vehicle cameras are classified into a vehicle camera sensor class.

On the basis of the sensor data of the vehicle sensors of the radar sensor class becomes a first grid cell area 8th as "busy" in the third grid cell information plane 4 entered. Grid information created based on the sensor data of the vehicle sensors of the vehicle camera sensor class becomes a second grid cell area 9 as "busy" in the third grid cell information plane 4 entered. Next becomes a third grid cell area 10 based on the sensor data of the vehicle sensors of the vehicle camera sensor class as well as on the basis of the sensor data of the vehicle sensors of the radar sensor class as "occupied" in the object plane 30 entered. The percentage contribution of the vehicle sensors of the radar sensor class to the detection that the third grid cell area 10 corresponding area of the vehicle environment of the vehicle 7 is 20% and the percentage contribution of the vehicle camera sensor class is 80%. This percentage breakdown is called meta-information in the meta-information level 5 entered in the corresponding grid cells. Based on the meta-information, the driver assistance system recognizes that the third grid cell area 10 was entered as "occupied" based on sensor data from two different vehicle sensor class categories. Thus, for the third grid cell area 10 calculates a higher recognition accuracy than for the first grid cell area 8th and the second grid cell area 9 ,

According to further embodiments, the recognition accuracy can be calculated on the basis of the percentage contributions of the respective vehicle sensor class categories and / or on the basis of properties of the respective vehicle sensor class categories.

According to another embodiment, the meta information additionally includes detection time information and self-diagnosis information of the vehicle sensor type class vehicle sensors. If it is detected on the basis of the detection time information of the vehicle sensors that the vehicle is already traveling after dark, the grid cell information that is created using vehicle sensors of the vehicle camera sensor class can be assigned a lower accuracy. Thus, for the second grid cell area 9 a lower recognition accuracy can be calculated than for the first grid cell area 8th ,

4 shows an additional object plane 30 of the allocation grid 1 according to a further embodiment. The vehicle 7 includes three laser sensor and two ultrasonic sensors. The laser sensors are classified into a laser sensor sensor class and the ultrasonic sensors into an ultrasonic sensor class. On the basis of sensor data of the vehicle sensors of the vehicle, grid cell information is created, which includes an occupancy state of the grid cell. Based on the grid cell information, the driver assistance system performs an object recognition. On the basis of grid cell information, which was created on the basis of sensor data from vehicle sensors of the laser sensor sensor class, becomes a first object 11 and a first lane boundary 13 detected and in the object plane 30 entered. Furthermore, based on grid cell information, which were created on the basis of sensor data from vehicle sensors of the ultrasonic sensor class, a second object 12 and a second lane boundary 14 detected and in the object plane 30 entered. Next recognizes the driver assistance system that the first lane boundary 13 and the second lane boundary 14 spatially adjacent, since, for example, a maximum distance between the first lane boundary 13 and second lane boundary 14 is below a predetermined threshold. Next recognizes the driver assistance system that the first lane boundary 13 and the second lane boundary 14 were detected based on grid cell information based on vehicle sensors of the laser sensor sensor class or ultrasound sensor class, that is to say of different vehicle sensor class categories. The driver assistance system therefore combines the first road boundary 13 and the second lane boundary 14 to a single lane boundary. For example, the second lane boundary becomes 14 from the object level 30 removed and only the first lane boundary 13 saved further.

Based on the single lane boundary, the vehicle can control active driving functions of the vehicle as lane departure warning, for example steer, decelerate or accelerate the vehicle.

In 5 is the object plane 30 of the allocation grid 1 illustrated for another exemplary scenario. The vehicle 7 This includes two far-field radar sensors, which are classified into a far field radar sensor class, and four vehicle cameras, which are classified into a vehicle camera sensor class. Lattice cell information, which was generated based on sensor data from vehicle sensors of the far field radar sensor class, becomes third objects 18 , fourth objects 15 and fifth objects 16 detected and in the object plane 30 entered. Further, based on grid cell information which has been created based on sensor data of vehicle sensors of the vehicle camera type class, sixth objects become 19 and seventh objects 17 detected and in the object plane 30 entered. By calculating a distance, it is recognized that the third objects 18 and the sixth objects 19 as well as the fifth objects 16 and the seventh objects are spatially adjacent and these are each identified with each other. Based on the meta-information, it is further recognized that the objects thus identified with each other were detected on the basis of grid cell information, which was created on the basis of sensor data from vehicle sensors of two different vehicle sensor type classes. Therefore, a high recognition accuracy is calculated for the objects identified with each other. Next it is recognized that the fourth object 15 were detected only on the basis of grid cell information, which was created on the basis of sensor data from vehicle sensors of a single vehicle sensor class. It will further be appreciated that the corresponding vehicle sensor type class corresponds to the far field radar sensor class. Additionally it is recognized that a distance of the fourth object 15 from the vehicle 7 is below a predetermined threshold. For a distance below this threshold is for the fourth object 15 therefore calculates a low recognition accuracy based on the meta-information. If the recognition accuracy is below an adjustable predetermined threshold value, then the detected object can be rejected as faulty. In the in 5 The scenario shown becomes the fourth object 15 rejected as faulty and out of the object plane 15 deleted.

In 6 is a driver assistance system 20 for a vehicle 7 illustrated, which is adapted to a variety of vehicle sensors 21 of the vehicle 7 provided sensor data regarding a vehicle environment to receive. The driver assistance system 20 is preferably adapted to one of the above-described methods for controlling vehicle functions of the vehicle 7 perform. The vehicle sensors may include radar sensors, vehicle cameras, laser sensor, ultrasound sensors and / or lidar sensors. Next is the driver assistance system 20 designed to be the vehicle sensors 21 and classify various vehicle sensor type classes, and an occupancy grid 1 to create what the vehicle environment of the vehicle 7 represents. grid cells 6 of the allocation grid 1 are assigned grid cell information based on the provided sensor data. Next are grid cells 6 of the allocation grid 1 based on the vehicle sensor type classes of those vehicle sensors 21 , their sensor data for creating the grid cell information of the respective grid cell 6 be used, Associated with meta-information. Next is the driver assistance system 20 adapted to vehicle functions of the vehicle 7 using the created allocation grid 1 to control. The driver assistance system 20 may for this purpose have a microcontroller, which for classifying the vehicle sensors and for creating the occupancy grid 1 is trained. The allocation grid 1 can continue in a memory device of the driver assistance system 20 get saved.

Furthermore, the driver assistance system can be designed to perform an object recognition on the basis of the grid cell information and to calculate a recognition accuracy of the detected objects by evaluating the meta information.

Next is the driver assistance system 20 adapted to vehicle functions of the vehicle 7 using the created allocation grid 1 to control. For example, the driver assistance system can perform distance measurements on detected objects, can steer the vehicle semi-autonomously or fully autonomously as a lane departure warning system, with detected objects or in the occupancy grid 1 areas marked as occupied are bypassed. In particular, the grid cell information may include values relating to a roadway height and / or occupancy state. The meta information may include a percentage contribution of the respective vehicle sensor type class to the grid cell information of the respective grid cell. Further, the meta-information may include acquisition time information and / or self-diagnostic information of the vehicle sensors of the respective vehicle sensor type class.

In 7 is a block diagram of a vehicle 7 illustrated in accordance with an embodiment of the present invention. The vehicle 7 includes a variety of vehicle sensors 21 , For example, radar sensors and / or vehicle cameras and / or laser sensor and / or ultrasonic sensors and / or Lidarsensoren. The vehicle 7 further includes a driver assistance system 20 according to one of the embodiments described above.

QUOTES INCLUDE IN THE DESCRIPTION

This list of the documents listed by the applicant has been generated automatically and is included solely for the better information of the reader. The list is not part of the German patent or utility model application. The DPMA assumes no liability for any errors or omissions.

Cited patent literature

• DE 102012109377 A1 [0003]
• DE 102013217488 A1 [0004]

Claims (15)

Method for controlling vehicle functions by a driver assistance system ( 20 ) of a vehicle ( 7 ), comprising the steps of providing (S1) sensor data relating to a vehicle environment of the vehicle ( 7 ) by a plurality of vehicle sensors ( 21 ) of the vehicle ( 7 ); Classifying (S2) the vehicle sensors (S2) 21 in different vehicle sensor type classes; Create (S3) an occupancy grid ( 1 ), which the vehicle environment of the vehicle ( 7 ), where grid cells ( 6 ) of the assignment grid ( 1 ) are assigned grid cell information based on the provided sensor data, and wherein grid cells ( 6 ) of the assignment grid ( 1 ) based on the vehicle sensor type classes of those vehicle sensors ( 21 ), the sensor data for creating the grid cell information of the respective grid cell ( 6 ) are used to map meta-information; and controlling (S4) vehicle functions of the vehicle (S4) 7 ) by the driver assistance system ( 20 ) using the created occupancy grid ( 1 ). The method of claim 1, wherein the grid cell information includes values regarding a roadway height and / or occupancy state. Method according to one of claims 1 or 2, wherein the meta-information contains a percentage contribution of the respective vehicle sensor type class to the grid cell information of the respective grid cell ( 6 ). Method according to one of the preceding claims, wherein the meta-information acquisition time information and / or self-diagnosis information of the vehicle sensors ( 21 ) of the vehicle sensor type class. Method according to one of the preceding claims, wherein the vehicle sensor type classes radar sensor and / or Fahrzeugkamerasensorklass and / or laser sensor sensor and / or ultrasound sensor classes and / or Lidarsensorklassen and / or Tiefenbildsensortypklassen include. Method according to one of the preceding claims, wherein based on the grid cell information, an object recognition is performed, and wherein by evaluation of the meta-information a recognition accuracy of the detected objects ( 11 to 14 ; 15 to 19 ) is calculated. Method according to claim 6, wherein recognized objects ( 15 ) are rejected as erroneously recognized objects if the recognition accuracy is below an adjustable predetermined threshold. Method according to one of the preceding claims, wherein based on the grid cell information, a lane boundary detection is carried out, wherein spatially adjacent recognized lane boundaries ( 13 . 14 ) are combined to a single lane boundary, if it is detected on the basis of the meta-information that the spatially adjacent recognized lane boundaries ( 13 . 14 ) were collected from sensor data of different vehicle sensor type classes. Driver assistance system ( 20 ) for a vehicle ( 7 ), which is designed to be used by a plurality of vehicle sensors ( 21 ) of the vehicle ( 7 ) provided sensor data relating to a vehicle environment of the vehicle ( 7 ) to recieve; the driver assistance system ( 20 ) is further adapted to the vehicle sensors ( 21 ) into different vehicle sensor type classes, and an occupancy grid ( 1 ), which defines the vehicle environment of the vehicle ( 7 ), where grid cells ( 6 ) of the assignment grid ( 1 ) are assigned grid cell information based on the provided sensor data, and wherein grid cells ( 6 ) of the assignment grid ( 1 ) based on the vehicle sensor type classes of those vehicle sensors ( 21 ), the sensor data for creating the grid cell information of the respective grid cell ( 6 ) are used to map meta-information; and wherein the driver assistance system ( 20 ) is further adapted to vehicle functions of the vehicle ( 7 ) using the created occupancy grid ( 1 ) to control. Driver assistance system ( 20 ) according to claim 9, wherein the grid cell information comprises values relating to a roadway height and / or an occupancy state. Driver assistance system ( 20 ) according to one of claims 9 or 10, wherein the meta-information comprises a percentage contribution of the respective vehicle sensor type class to the grid cell information of the respective grid cell ( 6 ). Driver assistance system ( 20 ) according to one of claims 9 to 11, wherein the meta-information acquisition time information and / or self-diagnosis information of the vehicle sensors ( 21 ) of the vehicle sensor type class. Driver assistance system ( 20 ) according to one of claims 9 to 12, which is further adapted to carry out an object recognition on the basis of the grid cell information and by evaluation the metainformation a recognition accuracy of the detected objects ( 11 to 14 ; 15 to 19 ) to calculate. Vehicle ( 7 ) with a plurality of vehicle sensors ( 21 ) and a driver assistance system ( 20 ) according to one of claims 9 to 13. Vehicle ( 7 ) according to claim 14, wherein the vehicle sensors ( 21 ) Radar sensors and / or vehicle cameras and / or laser sensor and / or ultrasonic sensors and Lidarsensoren.

Images