DE102016217718A1 - METHOD, DEVICE AND COMPUTER READABLE STORAGE MEDIUM WITH INSTRUCTIONS FOR DETERMINING A POSITION OF A VEHICLE WITHIN A PARK SURFACE - Google Patents

Abstract

A method, apparatus (20) and computer readable storage medium having instructions for determining a position of a vehicle within a parking area. The apparatus (20) has an image processing unit (22) for detecting (10) one or more standing objects within the parking area and for detecting (13) a drivable area within the parking area. The apparatus (20) further has a position estimation unit (23) for determining (11) an estimated position of the vehicle relative to the detected stationary objects. A transformation unit (24) transforms (12) the detected standing objects and the estimated position of the vehicle into an environment map and inserts (14) the detected passable area into the surrounding map from the estimated position of the vehicle. A position determination unit (25) determines (15) possible positions of the vehicle by assigning the environment map to a map of the parking area and determines (16) a final position of the vehicle from the possible positions.

Description

Field of the invention

The present invention relates to a method, apparatus and computer readable storage medium having instructions for determining a position of a vehicle within a parking area. The present invention further relates to a vehicle in which such a method or device is used.

Background of the invention

Modern vehicles are becoming increasingly autonomous, i. The vehicles provide the driver with more and more functions and systems that assist him with control of the vehicle by indicating or taking over parts of the vehicle control. Such functions and systems require a great deal of information about the vehicle and its surroundings.

For example, from the document DE 10 2011 056 413 A1 a driver assistance system with a sensor system for environment detection known. Surrounding information that is recorded with the Umfeldfasungssystem be entered in an occupancy grid. The allocation information includes a statement as to whether an object is located in the area or whether the area belongs to a lane of its own or of an adjacent lane or, in general, the information as to whether an area can be overrun, possibly can be overrun or can not be overrun to a limited extent. Such a representation allows an indirect assessment of the available maneuver space for future maneuvers.

The publication DE 10 2013100 371 A1 describes a vehicle control device that performs automatic steering control. For steering control, the lane of an ego vehicle and obstacles outside this lane are determined, such as other vehicles. Based on the detected obstacles, an optimal ratio of the distances of both the left and right edges of the lane is calculated, which should be kept to avoid stress on the vehicle occupants.

The publication DE 10 2014 212 478 A1 discloses a method for creating an environment model of a vehicle. Based on objects, free space boundaries and lane boundaries, an alley is determined which indicates the freely drivable area around the vehicle. It can be used on map material in which the course of lanes or lanes is entered.

For the "lane-exact navigation" function within a parking area, e.g. a parking space or a parking garage, for example, knowledge is needed on which lane the vehicle to be navigated, the "ego vehicle", is located. This lane is also referred to as "ego lane". Furthermore, information about the current vehicle position relative to a lane is needed for automatic driving and car-to-car-based applications in addition to the knowledge of the Ego lane.

One approach to solving this problem is to use a highly accurate digital lane geometry map with absolute accuracy in the centimeter range in conjunction with a highly accurate intrinsic motion estimation. Here, the position in the map is determined using the Eigenbewegungsschätzung without imaging sensors. Due to inaccuracies of the eigenmovement estimation and inaccuracies of the maps with regard to the absolute position, it is often impossible to assign the ego vehicle to the correct lane. In particular, there are no GPS positioning methods available in covered car parks. Furthermore, a solution with high accuracy self-motion estimation and a highly accurate map is very costly.

Summary of the invention

It is an object of the invention to provide a method and a device for determining a position of a vehicle within a parking area, which also function reliably in covered parking garages and do without a costly, highly accurate intrinsic motion estimation.

This object is achieved by a method having the features of claim 1, by an apparatus having the features of claim 10, and by a computer-readable storage medium having instructions according to claim 11. Preferred embodiments of the invention are the subject of the dependent claims.

• – Detektieren von einem oder mehreren stehenden Objekten innerhalb der Parkfläche;
• – Bestimmen einer geschätzten Position des Fahrzeugs relativ zu den detektierten stehenden Objekten;
• – Transformieren der detektierten stehenden Objekte und der geschätzten Position des Fahrzeugs in eine Umgebungskarte;
• – Detektieren eines befahrbaren Bereichs innerhalb der Parkfläche;
• – Einfügen des detektierten befahrbaren Bereichs in die Umgebungskarte ausgehend von der geschätzten Position des Fahrzeugs;
• – Ermitteln von möglichen Positionen des Fahrzeugs durch Zuordnen der Umgebungskarte zu einer Karte der Parkfläche; und
• – Bestimmen einer endgültigen Position des Fahrzeugs aus den möglichen Positionen.

According to a first aspect of the invention, a method for determining a position of a vehicle within a parking area comprises the steps:

• - detecting one or more stationary objects within the parking area;
• Determining an estimated position of the vehicle relative to the detected stationary objects;
• - transforming the detected stationary objects and the estimated position of the vehicle into an environment map;
• - detecting a drivable area within the parking area;
• - inserting the detected passable area into the map of the surroundings from the estimated position of the vehicle;
• Determining possible positions of the vehicle by associating the environment map with a map of the parking area; and
• Determining a final position of the vehicle from the possible positions.

• – Eine Bildverarbeitungseinheit zum Detektieren von einem oder mehreren stehenden Objekten innerhalb der Parkfläche und zum Detektieren eines befahrbaren Bereichs innerhalb der Parkfläche;
• – Eine Positionsschätzungseinheit zum Bestimmen einer geschätzten Position des Fahrzeugs relativ zu den detektierten stehenden Objekten;
• – Eine Transformationseinheit zum Transformieren der detektierten stehenden Objekte und der geschätzten Position des Fahrzeugs in eine Umgebungskarte und zum Einfügen des detektierten befahrbaren Bereichs in die Umgebungskarte ausgehend von der geschätzten Position des Fahrzeugs; und
• – Eine Positionsbestimmungseinheit zum Ermitteln von möglichen Positionen des Fahrzeugs durch Zuordnen der Umgebungskarte zu einer Karte der Parkfläche und zum Bestimmen einer endgültigen Position des Fahrzeugs aus den möglichen Positionen.

According to another aspect of the invention, an apparatus for determining a position of a vehicle within a parking area comprises:

• An image processing unit for detecting one or more standing objects within the parking area and for detecting a drivable area within the parking area;
• A position estimating unit for determining an estimated position of the vehicle relative to the detected stationary objects;
• A transformation unit for transforming the detected stationary objects and the estimated position of the vehicle into an environment map and for inserting the detected drivable area into the surroundings map based on the estimated position of the vehicle; and
• A position determination unit for determining possible positions of the vehicle by associating the environment map with a map of the parking area and determining a final position of the vehicle from the possible positions.

• – Detektieren von einem oder mehreren stehenden Objekten innerhalb der Parkfläche;
• – Bestimmen einer geschätzten Position des Fahrzeugs relativ zu den detektierten stehenden Objekten;
• – Transformieren der detektierten stehenden Objekte und der geschätzten Position des Fahrzeugs in eine Umgebungskarte;
• – Detektieren eines befahrbaren Bereichs innerhalb der Parkfläche;
• – Einfügen des detektierten befahrbaren Bereichs in die Umgebungskarte ausgehend von der geschätzten Position des Fahrzeugs;
• – Ermitteln von möglichen Positionen des Fahrzeugs durch Zuordnen der Umgebungskarte zu einer Karte der Parkfläche; und
• – Bestimmen einer endgültigen Position des Fahrzeugs aus den möglichen Positionen.

In accordance with another aspect of the invention, a computer-readable storage medium includes instructions that, when executed by a computer, cause the computer to perform the following steps to determine a position of a vehicle within a parking area:

• - detecting one or more stationary objects within the parking area;
• Determining an estimated position of the vehicle relative to the detected stationary objects;
• - transforming the detected stationary objects and the estimated position of the vehicle into an environment map;
• - detecting a drivable area within the parking area;
• - inserting the detected passable area into the map of the surroundings from the estimated position of the vehicle;
• Determining possible positions of the vehicle by associating the environment map with a map of the parking area; and
• Determining a final position of the vehicle from the possible positions.

The method according to the invention for determining a position of a vehicle within a parking area is based on an alignment of passable areas and stationary objects, for example vehicles and / or components, which were detected by an imaging sensor system, with information from a digital map of the parking area. This contains data previously collected for the parking area on accessible areas, parking spaces, lane information and / or components. Based on a comparison between the detected stationary objects and the detected drivable area with the data of the map, possible positions of the vehicle are determined. From the possible vehicle positions finally a final position of the vehicle is determined. The solution according to the invention advantageously uses information about stationary objects and passable areas, which are detected very reliably by common camera systems installed in vehicles, for position determination within parking areas. Therefore, it does not require any additional cost-intensive sensor technology, in particular without a highly accurate eigenmovement estimation.

According to one aspect of the invention, the standing objects and the drivable area are detected at two or more times. The detection at several times, and thus typically at several positions, leads to a significant increase in the quality of the environment map. In particular, misdetections of stationary objects can be eliminated, since such misdetections usually do not occur several times in succession.

According to one aspect of the invention, a trajectory of the estimated positions of the vehicle is inserted into the environment map, i. a history of the eigenposition relative to the detected objects. This trajectory can be used to achieve greater accuracy in determining the estimated position of the vehicle.

According to one aspect of the invention, the environment map is based on a vector-based local coordinate system and the passable region is determined as a polygon. The map of the parking area in this case contains information in the form of vector-based polygons. This makes it possible to carry out the assignment between the area map and map of the parking area with little computational effort.

According to one aspect of the invention, to determine the final position of the vehicle, the possible positions are weighted to a total position. The weighting makes it possible to consider different confidences of the possible positions. For example, the vehicle accessible from the detected range certain position be more reliable than the determined from the detected stationary objects positions. In addition, with the help of the map knowledge, non-accessible areas and parking spaces can be weighted lower and therefore considered as not very likely vehicle positions.

According to one aspect of the invention, for determining possible positions of the vehicle, the detected passable area is assigned to a passable area noted in the map of the parking area. Likewise, the detected stationary objects in the map of the parking area are assigned parking spaces and / or components. Optionally, a trajectory of the estimated positions of the vehicle in the area map is compensated with lane geometries noted in the map of the parking area. By way of example, detected vehicles are allocated to the most suitable parking spaces of the card via a compensation calculation, or detected columns and walls are assigned to the most suitable components of the card by way of a compensation calculation. Accordingly, the passable areas are assigned to the passable areas of the map via a compensation calculation. In this way, several possible positions can be determined with little computational effort.

According to one aspect of the invention, in determining the estimated position of the vehicle relative to the detected stationary objects, self-motion estimation data is utilized. By a simple self-motion estimation, the assignment of the detected objects to the area map can be facilitated.

According to one aspect of the invention, the determined final position of the vehicle for a subsequent passage of the method serves as an input for the mapping of the surroundings map to the map of the parking area. This has the advantage that the search space for the association between the area map and the map of the parking area can thus be reduced.

Preferably, a method according to the invention or a device according to the invention are used in an autonomously or manually controlled vehicle, in particular a motor vehicle.

Further features of the present invention will become apparent from the following description and the appended claims, taken in conjunction with the figures.

Brief description of the figures

1 schematically shows a method for determining a position of a vehicle within a parking area;

2 shows a first embodiment of an apparatus for determining a position of a vehicle within a parking area;

3 shows a second embodiment of an apparatus for determining a position of a vehicle within a parking area;

4 shows a preferred embodiment of the in 1 represented method;

5 shows a simplified example of a map of the parking area;

6 schematically represents the real situation of the parking area;

7 shows a simplified example of an environment map of the vehicle;

8th illustrates the superimposition of the map of the parking area and the area map of the vehicle without compensation calculation;

9 shows the superimposition of the map of the parking area and the area map of the vehicle after a compensation calculation;

10 illustrates the overlapping of the real situation and the environment map of the vehicle without compensation calculation; and

11 shows the superimposition of the real situation and the area map of the vehicle after a compensation calculation.

Detailed description of the embodiments

For a better understanding of the principles of the present invention, embodiments of the invention will be explained in more detail below with reference to the figures. It is understood that the invention is not limited to these embodiments, and that the features described can also be combined or modified without departing from the scope of the invention as defined in the appended claims.

1 schematically shows a method for determining a position of a vehicle within a parking area. In a first step, one or more stationary objects within the parking area are detected 10 For example, parked vehicles or components. Furthermore, a estimated position of the vehicle relative to the detected stationary objects 11 , For this purpose, optional data of a self-motion estimation can be used. Subsequently, the detected stationary objects and the estimated position of the vehicle are transformed into an environment map 12 , In addition, a passable area within the parking area is detected 13 and inserted into the environment map from the estimated position of the vehicle 14 , Subsequently, by assigning the environment map to a map of the parking area, possible positions of the vehicle are determined 15 , Finally, a final position of the vehicle is determined from the possible positions 16 , For this purpose, for example, the possible positions are weighted to a total position merged.

To determine 15 From possible positions of the vehicle, the detected passable area is preferably assigned to a passable area noted in the map of the parking area. Furthermore, the detected stationary objects in the map of the parking area are assigned to parking spaces and / or components.

To increase the reliability of the position determination, the stationary objects and the drivable area can be detected at two or more times. In addition, a trajectory of the estimated positions of the vehicle can be inserted into the area map, which can be compensated with lane geometries noted in the map of the parking area. Furthermore, the determined final position of the vehicle can serve as an input for the mapping of the surroundings map to the map of the parking area for a subsequent passage of the method in order to be able to perform the mapping with little computational effort.

2 shows a simplified schematic representation of a first embodiment of a device 20 for determining a position of a vehicle within a parking area. The device 20 has an image processing unit 22 to detect 10 of one or more stationary objects within the parking area, such as parked vehicles or components, and for detecting 13 a passable area within the parking area. For this purpose, the image processing unit uses 22 For example, image information of a camera unit 28 that have an entrance 21 the device 20 be received. The device 20 still has a position estimation unit 23 for determining 11 an estimated position of the vehicle relative to the detected stationary objects. For this, the position estimation unit 23 optionally use data from a self-motion estimation. A transformation unit 24 transformed 12 the detected stationary objects and the estimated position of the vehicle in an environment map and adds 14 enter the detected drivable area from the estimated position of the vehicle into the area map. A position determination unit 25 determined 15 possible positions of the vehicle by assigning the area map to a map of the parking area and determined 16 a final position of the vehicle from the possible positions. For this purpose, the position determination unit merges 25 For example, the possible positions weighted to a total position.

To determine 15 From possible positions of the vehicle, the detected passable area is preferably assigned to a passable area noted in the map of the parking area. Furthermore, the detected stationary objects in the map of the parking area are assigned to parking spaces and / or components.

To increase the reliability of the position determination, the stationary objects and the drivable area can be detected at two or more times. In addition, a trajectory of the estimated positions of the vehicle can be inserted into the area map, which can be compensated with lane geometries noted in the map of the parking area. Furthermore, the determined final position of the vehicle can serve as an input for the mapping of the surroundings map to the map of the parking area for a subsequent passage of the method in order to be able to perform the mapping with little computational effort.

The from the position determination unit 25 certain position of the vehicle is preferably via an output 26 the device 20 made available for further processing, for example for processing in a navigation system. It can also be stored in a memory 27 the device 20 be stored, for example, for a later evaluation. The entrance 21 and the exit 26 may be implemented as separate interfaces or as a combined bidirectional interface. The image processing unit 22 , the position estimation unit 23 , the transformation unit 24 as well as the position determination unit 25 can be implemented as dedicated hardware, such as integrated circuits. Of course, they can also be partially or fully combined or implemented as software running on a suitable processor.

3 shows a simplified schematic representation of a second embodiment of a device 30 for determining a position of a vehicle within a parking area. The contraption 30 has a processor 32 and a memory 31 on. For example, the device is 30 to a computer or a controller. In the storage room 31 are filed instructions that the device 30 when executed by the processor 32 to perform the steps according to one of the described methods. The in the store 31 filed instructions thus embody one by the processor 32 executable program that realizes the inventive method. The device has an entrance 33 for receiving information. From the processor 32 generated data will be via an output 34 provided. In addition, they can be stored in memory 31 be filed. The entrance 33 and the exit 34 can be combined to a bidirectional interface.

The processor 32 may include one or more processing units, such as microprocessors, digital signal processors, or combinations thereof.

The stores 27 . 31 The embodiments described may have volatile and / or non-volatile memory areas and include a wide variety of memory devices and storage media, for example hard disks, optical storage media or semiconductor memories.

Description of a preferred embodiment

Hereinafter, a preferred embodiment of the invention in detail with reference to 4 to 11 to be discribed.

4 shows a preferred embodiment of the in 1 illustrated method. Optional features are shown in dashed lines. Provided is a memory with previously measured passable areas, parking lots, lane information and possibly components, ie a digital map K of the parking area. The contents of the map are preferably present as vector-based polygons in order to carry out the localization with little computational effort. For the purpose of localization, initially stationary objects, for example vehicle fronts and vehicle rear ends or even components, are detected on the basis of an imaging sensor system 10 , For the sake of simplicity, vehicles are described on the basis of a selected standard vehicle length as bounding boxes, based on the detected vehicle fronts and vehicle rear ends, ie as bounding rectangles. The detected objects are then transformed into a local coordinate system, preferably a vector-based coordinate system. To increase the accuracy of the localization can be a new detection 10 the objects take place at additional times. The objects are temporally assigned in the coordinate system, moreover, a determination of the intrinsic position of the vehicle relative to the detected objects takes place 11 . 12 . 14 , Optionally, a simple self-motion estimate 17 be merged to facilitate the assignment. The result is an environment map with the detected objects including the estimated relative own vehicle position. At any time, the passable range is still determined on the basis of the imaging sensor 13 , ie the open spaces, for example as a polygon. This is inserted as a snapshot in the map. The starting point for this is the associated estimated eigenposition. Optionally, the trajectory traveled, ie the history of the eigenpositions relative to the detected objects, can also be inserted into the environment map 18 , In a subsequent assignment step, the area map and the map K of the parking area are assigned to each other 15 , For this purpose, the stationary objects or their bounding boxes are assigned to the most suitable parking spaces and components of the map K via a compensation calculation. For example, the method of least squares can be used for this purpose. Furthermore, the passable areas are also assigned to the passable areas of the map K via a compensation calculation. Optionally, the trajectory can be compensated with the lane geometries stored in the map K. The assignments result in possible vehicle positions relative to the map K of the parking area. The possible vehicle positions as well as an optional eigen motion estimation can be put together variably weighted into an overall position, ie a fusion of the possible vehicle positions into an overall position takes place. Optionally, non-accessible areas and parking spaces can be weighted lower via the map knowledge and therefore considered as not very likely vehicle positions. The resulting overall position is also an input to the mapping step in the preferred embodiment 15 to restrict the search space. The result of the method is the vehicle position relative to the lane geometries of the map K. This can be provided to other functions, such as for automatic driving.

5 shows a simplified example of a map K of the parking area. The map K includes information on accessible areas BB, the existing parking spaces PP and the lane geometries FG. In addition, information about components BT can be present within the parking area or adjacent to the parking area. In this example, the parking area is a level of a parking garage, so that the components BT may be, for example, the supporting pillars. Of course, other components may be noted, such as walls, ramps or curbs.

6 represents schematically the real situation of the parking area. On some of the parking lots PP are vehicles 2 parked while other parking PP are unoccupied. Shown is also the ego vehicle 1 at its real position and a trajectory T of the ego vehicle 1 ie a history of the previous positions of the vehicle 1 ,

7 shows a simplified example of a map U of the vehicle. Origin of the coordinate system used for the environment map U is the ego vehicle 1 , The environment map generated from the acquired data in this example comprises the detected standing objects 3 , the detected passable areas BB 'and detected lane geometries FG'. At the detected standing objects 3 These are both parked vehicles represented by bounding boxes and detected components.

8th illustrates the superimposition of the map of the parking area and the area map of the vehicle before a compensation calculation. The superimposing is based on a coarse vehicle position. In some cases there are clear deviations between the detected stationary objects 3 and the parking spaces PP and components BT noted on card K. The detected passable areas BB 'agree incompletely with the marked in the map K passable areas BB match. After a compensation calculation, the result is a much better match, as in 9 you can see. The detected parked vehicles are now almost completely within the associated parking lots. The detected components and the detected passable areas BB 'also largely coincide with the information in the map K of the parking area.

10 and 11 illustrate the overlapping of the real situation and the map of the surroundings of the vehicle before a compensation calculation or after the execution of a compensation calculation. How to get in 11 can see true from the assignment of the map U and the map K of the parking area determined position of the ego vehicle 1 quite exactly with the real position of the vehicle 1 match.

LIST OF REFERENCE NUMBERS

1

vehicle

2

Parked vehicle

3

Detected standing object

10

Detecting stationary objects

11

Determining an estimated position of the vehicle

12

Transform objects and position in map

13

Detecting a drivable area

14

Insert the passable area in the area map

15

Determining possible positions of the vehicle

16

Determining a final position of the vehicle

17

Self-motion estimation

18

Determination of the trajectory traveled

20

contraption

21

entrance

22

Image processing unit

23

Position estimation unit

24

transformation unit

25

Position Determination Entity

26

output

27

Storage

28

camera unit

30

contraption

31

Storage

32

processor

33

entrance

34

output

K

Map of the parking area

PP

parking spot

BT

component

BB

Trafficable area

FG

lane geometry

U

map

BB '

Detected passable area

FG '

Detected lane geometry

T

trajectory

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 102011056413 A1 [0003]
• DE 102013100371 A1 [0004]
• DE 102014212478 A1 [0005]

Claims (12)

Method for determining a position of a vehicle ( 1 ) within a parking area, with the steps: - Detecting ( 10 ) of one or more standing objects ( 3 ) within the parking area; - Determine ( 11 ) an estimated position of the vehicle ( 1 ) relative to the detected stationary objects ( 3 ); - Transform ( 12 ) of the detected stationary objects ( 3 ) and the estimated position of the vehicle ( 1 ) in an environment map (U); - Detect ( 13 ) of a drivable area (BB ') within the parking area; - Insert ( 14 ) of the detected drivable area (BB ') in the area map (U) based on the estimated position of the vehicle ( 1 ); - Determine ( 15 ) of possible positions of the vehicle ( 1 by associating the environment map (U) with a map (K) of the parking area; and - determining ( 16 ) a final position of the vehicle ( 1 ) from the possible positions. Method according to claim 1, wherein the standing objects ( 3 ) and the drivable area (BB ') are detected at two or more times. Method according to claim 2, wherein a trajectory (T) of the estimated positions of the vehicle ( 1 ) is inserted into the environment map (U).  Method according to one of the preceding claims, wherein the environment map (U) is based on a vector-based local coordinate system and the passable area (BB ') is determined as a polygon, and wherein the map (K) of the parking area contains information in the form of vector-based polygons. Method according to one of the preceding claims, wherein for determining ( 16 ) the final position of the vehicle ( 1 ) the possible positions are weighted to be merged into an overall position. Method according to one of the preceding claims, wherein the detected stationary objects ( 3 ) Vehicles and / or components are. Method according to claim 6, wherein for determining ( 15 ) of possible positions of the vehicle ( 1 ) the detected passable area (BB ') is allocated to a passable area (BB) marked in the map (K) of the parking area, the detected stationary objects ( 3 ) parking areas (PP) and / or components (BT) are noted in the map (K) of the parking area and optionally a trajectory (T) of the estimated positions of the vehicle ( 1 ) in the area map (U) is compensated with lane geometries (FG) noted in the map (K) of the parking area. Method according to one of the preceding claims, wherein in determining ( 11 ) of the estimated position of the vehicle ( 1 ) relative to the detected stationary objects ( 3 ) Data from a self-motion estimation can be used. Method according to one of the preceding claims, wherein the determined final position of the vehicle ( 1 ) is used for a subsequent passage of the method as an input for the mapping of the area map (U) to the map (K) of the parking area. Contraption ( 20 ) for determining a position of a vehicle ( 1 ) within a parking area, the device ( 20 ) comprises: - an image processing unit ( 22 ) for detecting ( 10 ) of one or more standing objects ( 3 ) within the parking area and to detect ( 13 ) of a drivable area (BB ') within the parking area; A position estimation unit ( 23 ) for determining ( 11 ) an estimated position of the vehicle ( 1 ) relative to the detected stationary objects ( 3 ); - A transformation unit ( 24 ) for transforming ( 12 ) of the detected stationary objects ( 3 ) and the estimated position of the vehicle ( 1 ) into an environment map (U) and to insert ( 14 ) of the detected drivable area (BB ') in the area map (U) based on the estimated position of the vehicle ( 1 ); and - a position determination unit ( 25 ) for determining ( 15 ) of possible positions of the vehicle ( 1 by assigning the environment map (U) to a map (K) of the parking area and determining ( 16 ) a final position of the vehicle ( 1 ) from the possible positions.  A computer-readable storage medium having instructions which, when executed by a computer, cause the computer to perform the steps of a method according to any one of claims 1 to 9. Autonomous or manually controlled vehicle ( 1 ), characterized in that it comprises or is arranged a device according to claim 10, a method according to one of claims 1 to 9 for determining a position of the vehicle ( 1 ) within a parking area.

Images