Procedure for identifying a motor vehicle

Abstract

The invention relates to a method for identifying a motor vehicle located within a parking lot and performing an AVP process, comprising the following steps: Capturing a reference identification feature of the vehicle during the AVP process, Capturing an identification feature of the motor vehicle during a journey of the motor vehicle from an AVP type 1 area of ​​the parking lot, which is only set up for an AVP process according to AVP type 1, to an AVP type 2 area of ​​the parking lot, which is set up for an AVP process according to AVP type 2, or to an AVP type 3 area of ​​the parking lot, which is set up for an AVP process according to AVP type 3, Comparing the identification feature with the reference identification feature to identify the motor vehicle. The invention relates to a system, a computer program and a machine-readable storage medium.

Description

State of the art

[0001] The invention relates to a method for identifying a motor vehicle located within a parking space and performing an AVP process, a system, a computer program and a machine-readable storage medium.

[0002] The published patent application DE 10 2012 222 562 A1 shows a system for managed parking areas for transferring a vehicle from a starting position to a destination position. Disclosure of the invention

[0003] The object underlying the invention is to provide a concept for identifying a motor vehicle located within a parking space and performing an AVP process.

[0004] This object is achieved by means of the respective subject matter of the independent claims. Advantageous embodiments of the invention are the subject matter of the respective dependent subclaims.

[0005] According to a first aspect, a method is provided for identifying a motor vehicle located within a parking space and performing an AVP process, comprising the following steps: Recording a reference identification feature of the motor vehicle during the AVP process, Capturing an identification feature of the motor vehicle during a journey of the motor vehicle from an AVP Type 1 area of ​​the parking lot, which is only set up for an AVP process according to AVP Type 1, to an AVP Type 2 area of ​​the parking lot, which is set up for an AVP process according to AVP Type 2, or to an AVP Type 3 area of ​​the parking lot, which is set up for an AVP process according to AVP Type 3, Comparing the identification feature with the reference identification feature to identify the motor vehicle.

[0006] According to a second aspect, a system is provided for identifying a motor vehicle located within a parking space and performing an AVP process, comprising: a detection device configured to detect a reference identification feature of the motor vehicle during the AVP process and to detect an identification feature of the motor vehicle during a journey of the motor vehicle from an AVP Type 1 area of ​​the parking lot, which is only configured for an AVP process according to AVP Type 1, to an AVP Type 2 area of ​​the parking lot, which is configured for an AVP process according to AVP Type 2, or to an AVP Type 3 area of ​​the parking lot, which is configured for an AVP process according to AVP Type 3, and a comparison device which is configured to compare the identification feature with the reference identification feature in order to identify the motor vehicle.

[0007] According to a third aspect, a computer program is provided which comprises instructions which, when the computer program is executed by a computer, for example by the system according to the second aspect, cause the computer to carry out a method according to the first aspect.

[0008] According to a fourth aspect, a machine-readable storage medium is provided on which the computer program according to the third aspect is stored.

[0009] The invention is based on and includes the finding that the above object is achieved by detecting a reference identification feature of the motor vehicle at a first time point in the AVP process. At a second time point in the AVP process, which is subsequent to the first time point in time, an identification feature of the motor vehicle is detected while the motor vehicle is traveling from an AVP type 1 area of ​​the parking lot to an AVP type 2 area or to an AVP type 3 area of ​​the parking lot. The identification feature is compared with the reference identification feature in order to identify the motor vehicle. This provides the particular technical advantage that the motor vehicle can be identified efficiently. This is because there is a reference identification feature of the motor vehicle, which was detected at the first time point in time, on the basis of which the motor vehicle can be identified.Using such a reference identification feature, the motor vehicle can be efficiently identified.

[0010] For example, it is provided that if the identification feature matches the reference identification feature, the motor vehicle is identified. This means, in particular, that if the identification feature matches the reference identification feature, it is determined that the motor vehicle whose identification feature was recorded is the motor vehicle whose reference identification feature was recorded.

[0011] The fact that this identification is carried out during the journey from the AVP Type 1 area to the AVP Type 2 area or to the AVP Type 3 area of ​​the parking lot can have the technical advantage in particular that the infrastructure has then already identified the motor vehicle, for example, before the responsibility for the AVP process is transferred at least partially, in particular completely, to the infrastructure.

[0012] In AVP Type 1 of the AVP process, the responsibility for driving the vehicle lies with the vehicle. In contrast, in AVP Type 2, the responsibility for driving the vehicle lies with the infrastructure. In AVP Type 3, the responsibility lies with both the vehicle and the infrastructure, thus sharing responsibility. In both cases, AVP Type 2 and AVP Type 3, it is sensible and advantageous for the infrastructure to know exactly for which vehicle it is assuming responsibility before responsibility is transferred, at least partially, or especially completely, so that the AVP process can then continue efficiently and safely.

[0013] In particular, it is advantageous and expedient to identify the motor vehicle in order to localize it, i.e., to determine or ascertain its position. For example, according to one embodiment of the method, the motor vehicle is located within the parking space, i.e., in particular, the position of the motor vehicle within the parking space is determined.

[0014] Procedural steps of the procedure according to the first aspect are procedural steps that are carried out on the infrastructure side, i.e. by an infrastructure.

[0015] The abbreviation "AVP" stands for "Automated Valet Parking" and can be translated into German as "automatic parking service." An AVP process includes, for example, at least highly automated driving of the motor vehicle from a drop zone, also called a drop-off location, to a parking location and, for example, at least highly automated driving of the motor vehicle from a parking location to a pick-up location, also called a pickup zone. At the drop-off location, i.e. the drop zone, a driver of the motor vehicle drops off the motor vehicle for an AVP process. At a pick-up location, i.e. the pickup zone, the motor vehicle is picked up after the end of the AVP process. An AVP process therefore starts, in particular, at the drop zone. An AVP process therefore ends, in particular, at the pickup zone.

[0016] An AVP motor vehicle is therefore a motor vehicle that can participate in an AVP process. Whenever reference is made to a motor vehicle above and below, it should always be understood that this is an AVP motor vehicle, even if the term "AVP" is not explicitly used.

[0017] In one embodiment of the method, an infrastructure-side AVP system is provided. The AVP process is carried out, in particular, using the infrastructure-side AVP system.

[0018] An AVP process can be an AVP process according to one of the following AVP types: AVP Type 1, AVP Type 2, and AVP Type 3. However, the AVP types can also change within an AVP process. This means, for example, that part of an AVP process is performed according to AVP Type 1, and another part of the AVP process is performed according to AVP Type 2 or AVP Type 3. This means, for example, that an AVP process can be divided into sub-AVP processes, each of which is performed according to one of the AVP types 1, 2, and 3.

[0019] AVP Type 1 designates a vehicle-centric AVP process. Primary responsibility for the AVP process lies with the vehicle.

[0020] AVP Type 2 characterizes an infrastructure-centric AVP process. The primary responsibility for the AVP process lies with the infrastructure, i.e., the AVP system.

[0021] AVP Type 3 designates a vehicle-infrastructure shared AVP process. Here, primary responsibility for the AVP process is shared between the vehicle and the AVP system.

[0022] An AVP process includes the following operations or functions: 1. Determine a target position for the motor vehicle, which lies within the parking space. 2. Planning a route from a starting position, which is enclosed by the parking lot, to the destination position. 3. Detecting an object and / or an event and reacting accordingly to a detected object and / or a detected event. 4. Locate the vehicle within the parking space. 5. Calculate a target trajectory for the vehicle based on the planned route. 6. Control of the lateral and longitudinal guidance of the motor vehicle based on the calculated target trajectory.

[0023] The following table indicates which of these processes or functions are performed by the motor vehicle or the infrastructure-side AVP system, depending on the AVP type, where "I" stands for "infrastructure", i.e., the infrastructure-side AVP system, and "K" for "motor vehicle", so that "I" indicates that the process is performed by the AVP system, and "K" indicates that the process is performed by the motor vehicle: Functions AVP type 1 AVP type 2 AVP type 3 Determining a target position for the motor vehicle, which lies within the parking space. I & K I I Planning a route from a starting position, which is enclosed by the parking lot, to the destination position. K I I Detecting an object and / or an event and reacting accordingly to a detected object and / or a detected event. K (& optionally I) I I & K Locating the motor vehicle within the parking space. K I K Calculate a target trajectory for the vehicle based on the planned route. K I K Control of a transverse and longitudinal guidance of the K K K Motor vehicle based on the calculated target trajectory.

[0024] The table above indicates, for each function, whether the function is performed by the infrastructure (i.e., the infrastructure-side AVP system) or by the motor vehicle, specifically for each AVP type. In some cases, the function may be performed by both the AVP system and the motor vehicle.

[0025] With regard to object and event detection for AVP type 1, it can optionally be provided that in addition to the motor vehicle, the AVP system of the infrastructure also performs this function.

[0026] The AVP types 1, 2 and 3 described here are further described in detail in ISO 23374.

[0027] According to one embodiment of the method, the motor vehicle is at least a highly automated motor vehicle. Such a motor vehicle is configured for at least highly automated driving. Highly automated driving corresponds to automation level 4 according to the definition of the Federal Highway Research Institute (BASt).

[0028] The fact that the motor vehicle is equipped for at least highly automated driving includes both the case of the motor vehicle being equipped for highly automated driving and the case of fully automated driving. Fully automated driving corresponds to automation level 5 according to the BASt definition.

[0029] Highly automated guidance means that for a certain period of time in a specific situation (for example: driving on a motorway, driving in a parking lot, overtaking an object, driving in a lane defined by lane markings), the longitudinal and lateral guidance of the motor vehicle are automatically controlled. The driver of the motor vehicle does not have to manually control the longitudinal and lateral guidance of the vehicle. The driver does not have to constantly monitor the automatic control of the longitudinal and lateral guidance in order to be able to intervene manually if necessary. If necessary, a takeover request is automatically issued to the driver to take over control of the longitudinal and lateral guidance, in particular with a sufficient time reserve. The driver must therefore potentially be able to take over control of the longitudinal and lateral guidance.Limits of the automatic control of lateral and longitudinal guidance are automatically detected. With highly automated guidance, it is not possible to automatically achieve a minimal-risk state in every initial situation.

[0030] Fully automated guidance means that in a specific situation (e.g. driving on a motorway, driving within a parking lot, overtaking an object, driving within a lane defined by lane markings), the longitudinal and lateral guidance of the vehicle are automatically controlled. The driver of the vehicle does not have to manually control the longitudinal and lateral guidance of the vehicle. The driver does not have to monitor the automatic control of the longitudinal and lateral guidance in order to intervene manually if necessary. Before the automatic control of the lateral and longitudinal guidance is terminated, the driver is automatically prompted to take over the driving task (controlling the lateral and longitudinal guidance of the vehicle), particularly with a sufficient time reserve. If the driver does not take over the driving task, the vehicle automatically returns to a state with minimal risk.Limits of the automatic control of lateral and longitudinal guidance are automatically detected. In all situations, it is possible to automatically return to a system state with minimal risk.

[0031] In one embodiment of the method, it is provided that this is a computer-implemented method.

[0032] In one embodiment of the method, it is provided that it is carried out by means of the system according to the second aspect.

[0033] Technical functionalities of the method according to the first aspect result analogously from corresponding technical functionalities of the system according to the second aspect, and vice versa. This means, in particular, that the method features result from corresponding system features, and vice versa.

[0034] An environmental sensor within the meaning of the description is, for example, an infrastructure environmental sensor, i.e., one assigned to an infrastructure, in this case, the parking lot. Within the parking lot, for example, several infrastructure environmental sensors are spatially distributed. At least one infrastructure environmental sensor is arranged in such a way that it can detect the drop zone and / or the surroundings of the drop zone.

[0035] An environmental sensor within the meaning of the description is, for example, a motor vehicle environmental sensor, i.e. assigned to the AVP motor vehicle, i.e. included in it.

[0036] The abbreviation “at least one” means “one or more”.

[0037] An environmental sensor within the meaning of the description is, for example, one of the following environmental sensors: radar sensor, image sensor, in particular image sensor of a video camera, for example image sensor(s) of a stereo video camera, ultrasonic sensor, LiDAR sensor, magnetic field sensor and infrared sensor.

[0038] An environmental sensor is particularly configured to detect its surroundings, i.e. its environment, and to output environmental sensor data based on the detection, in particular raw environmental sensor data, which represent the detected environment.

[0039] Environmental sensor data within the meaning of the description includes, for example, or is, for example, raw environmental sensor data. Environmental sensor data within the meaning of the description includes, for example, or is, for example, processed, e.g., evaluated, raw environmental sensor data.

[0040] In one embodiment of the method, it is provided that the respective detection of the reference identification feature and / or the identification feature each comprises a detection of the motor vehicle by means of an infrastructure environment sensor arranged within the parking space, in particular a visual environment sensor, in order to determine environment sensor data based on the respective detection, wherein the corresponding feature is determined based on the corresponding environment sensor data.

[0041] This results in the technical advantage, for example, that the reference identification feature or the identification feature can be recorded efficiently.

[0042] This means that, according to this embodiment, it is provided, for example, that the reference identification feature is detected by means of one or more infrastructure environment sensors. This means, for example, that the identification feature is detected using one or more infrastructure environment sensors. This means, in particular, that the motor vehicle is detected using one or more such infrastructure environment sensors, i.e., is detected by sensors, in order to determine environmental sensor data based on the respective detection. Such environmental sensor data therefore describe, in particular, the motor vehicle at the time the reference identification feature is detected, i.e., in particular, at the aforementioned first time of the AVP process.Such environmental sensor data therefore describes, in particular, the motor vehicle at the time the identification feature is detected, i.e., in particular at the aforementioned second time of the AVP process. The environmental sensor data can therefore be evaluated or analyzed in particular to determine the corresponding feature. For example, such an evaluation or determination can include image analysis, which can be provided in particular if the environmental sensor is a visual environmental sensor. A visual environmental sensor is, for example, an image sensor.

[0043] In one embodiment of the method, it is provided that the reference identification feature is detected before or at the start of the AVP process, in particular while the motor vehicle is located in a drop zone of the parking lot.

[0044] This provides the technical advantage, for example, of ensuring a particularly suitable time for capturing the reference identification feature. Thus, the vehicle can be efficiently identified by the infrastructure immediately after the AVP process has started, based on the concept described here.

[0045] In one embodiment of the method, it is provided that upon detection of at least one active direction indicator, in particular of at least one flashing direction indicator, of a motor vehicle located within the parking space, it is determined that this motor vehicle is the motor vehicle to be identified.

[0046] This provides the technical advantage, for example, that the motor vehicle to be identified can be efficiently determined or identified. This is particularly advantageous when there are multiple motor vehicles within the parking space, but only one of them has at least one active turn signal. Thus, by detecting such an active turn signal, it can be efficiently determined that this is precisely the motor vehicle that is to be identified for an AVP process.

[0047] In one embodiment of the method, it is provided that the environmental sensor data are evaluated in order to detect at least one active direction indicator, in particular at least one flashing direction indicator, in a motor vehicle located within the parking space.

[0048] This provides the technical advantage, for example, that an active direction indicator of a motor vehicle can be efficiently detected.

[0049] In one embodiment of the method, it is provided that the reference identification feature and the identification feature are each an element selected from the following group of features: license plate, dimension, in particular length, height, width, color, structure or structures, damage, in particular dent, scratch, shape, type.

[0050] This results in the technical advantage, for example, that particularly suitable reference identification features or identification features can be selected.

[0051] In one embodiment of the system, it is provided that the detection device comprises one or more infrastructure environment sensors, in particular one or more visual environment sensors, which are configured to determine the corresponding feature, i.e. the reference identification feature and / or the identification feature, based on environment sensor data based on the respective detection.

[0052] In one embodiment, it is provided that the system is programmatically configured to execute the computer program according to the third aspect.

[0053] In one embodiment, it is provided that the system is configured to carry out all steps of the method according to the first aspect.

[0054] The embodiments and exemplary embodiments described in the description can be combined with one another, even if this is not explicitly described.

[0055] The invention is explained in more detail below using preferred embodiments. These show: Fig. 1 a flowchart of a method according to the first aspect, Fig. 2 a system according to the second aspect, Fig. 3 a machine-readable storage medium according to the fourth aspect and Fig. 4 a parking space.

[0056] Fig. 1 shows a flowchart of a method for identifying a motor vehicle located within a parking space and performing an AVP process, comprising the following steps: Capturing 101 a reference identification feature of the motor vehicle during the AVP process, Detecting 103 an identification feature of the motor vehicle during a journey of the motor vehicle from an AVP type 1 area of ​​the parking lot, which is only set up for an AVP process according to AVP type 1, to an AVP type 2 area of ​​the parking lot, which is set up for an AVP process according to AVP type 2, or to an AVP type 3 area of ​​the parking lot, which is set up for an AVP process according to AVP type 3, Comparing 105 the identification feature with the reference identification feature to identify the motor vehicle.

[0057] Fig. 2 shows a system 201 for identifying a motor vehicle located within a parking space and performing an AVP process, comprising: a detection device 203 which is configured to detect a reference identification feature of the motor vehicle during the AVP process and to record an identification feature of the motor vehicle during a journey of the motor vehicle from an AVP Type 1 area of ​​the parking lot, which is only set up for an AVP process according to AVP Type 1, to an AVP Type 2 area of ​​the parking lot, which is set up for an AVP process according to AVP Type 2, or to an AVP Type 3 area of ​​the parking lot, which is set up for an AVP process according to AVP Type 3, and a comparison device 205 which is configured to compare the identification feature with the reference identification feature in order to identify the motor vehicle.

[0058] Fig. 3 shows a machine-readable storage medium 301 on which a computer program 303 is stored. The computer program 303 includes instructions that, when executed by a computer, cause the computer program 303 to execute a method according to the first aspect.

[0059] Fig.4 shows a parking space 401.

[0060] The parking space 401 includes a drop zone, identified by a curly bracket with the reference numeral 403. The drop zone 403 is monitored by a first video camera 405 comprising a first image sensor 407. This means that the first video camera 405 captures the drop zone 403 and outputs video data based on the capture, i.e., environmental sensor data within the meaning of the description.

[0061] On the drop zone 403 there is a motor vehicle 409 comprising a second video camera 411 having a second image sensor 413.

[0062] In an embodiment not shown, it is provided that instead of or in addition to the first video camera 405 and / or the second video camera 411, one or more further environmental sensors are provided for monitoring.

[0063] Motor vehicle 409 is an AVP motor vehicle and is intended to carry out an AVP process within parking space 401.

[0064] While the motor vehicle 409 is still on the drop zone 403, the first video camera 405 records the motor vehicle 409. Based on the video data, a reference identification feature is determined or recorded.

[0065] Subsequently, the motor vehicle 409 departs from the drop zone 403 as part of the AVP process. The AVP process can therefore begin.

[0066] The AVP process requires motor vehicle 409 to drive through an AVP Type 1 area of ​​parking space 401. This AVP Type 1 area is symbolically identified by a curly bracket with the reference numeral 415.

[0067] A direction of travel of the motor vehicle is indicated by an arrow with the reference number 417.

[0068] According to the direction of travel 417, it is intended that motor vehicle 409 travels from the AVP type 1 area 415 to an AVP type 2 or an AVP type 3 area within the scope of the AVP process, symbolically identified by a curly bracket with the reference number 419.

[0069] No infrastructure environment sensors are present within the AVP Type 1 area 415. This means that the infrastructure cannot locate or identify the motor vehicle 409 within the AVP Type 1 area 415 itself.

[0070] This is not absolutely necessary in this area, since the responsibility for driving the vehicle lies with the vehicle 409.

[0071] However, if motor vehicle 409 is traveling within the AVP Type 2 area or AVP Type 3 area 419 as part of the AVP process, the responsibility for driving the vehicle lies at least partially with the infrastructure. Therefore, it is necessary for the vehicle 409 to be identified by the infrastructure before responsibility is transferred.

[0072] For this purpose, a third video camera 421 comprising a third image sensor 423 is provided. The third video camera 421 is arranged within the AVP Type 2 area or AVP Type 3 area 419.

[0073] During the journey from the AVP type 1 area 415 to the AVP type 2 area or AVP type 3 area 419, the third video camera 421 records the motor vehicle 409. For example, the motor vehicle 409 is correspondingly recorded when it travels through a transition area, which is symbolically marked by a curly bracket with the reference number 425.

[0074] This transition region may include subregions of the AVP type 1 region 415 and the AVP type 2 or AVP type 3 region 419.

[0075] It is intended that an identification feature of the motor vehicle 409 is detected or determined based on the video data from the third video camera 421. The reference identification feature, which was detected when the motor vehicle 409 was still in the drop zone 403, is compared with the identification feature detected in the transition area 425. If there is a match, the motor vehicle 409 is identified.

[0076] The video data from the first video camera 405 and the third video camera 421 are sent, for example, to a data processing device 427, which can perform the steps of determining the identification feature or the reference identification feature based on the corresponding video data. The comparison step is also performed by the data processing device 427.

[0077] The data processing device 427 may, for example, be part of a cloud infrastructure.

[0078] In summary, the concept described here is based in particular on the fact that the motor vehicle is identified for the first time by the infrastructure at the start of or even before the start of an AVP process, i.e., a reference identification feature of the motor vehicle is recorded. At a later point in the AVP process, the motor vehicle can be identified again by the infrastructure using the reference identification feature. This identification feature is then recorded by the infrastructure at a later point in time, and compared with the previously recorded reference identification feature.

[0079] Thus, after driving through an AVP Type 1 area, within which no infrastructure environment sensors are present, the motor vehicle can be identified again if the motor vehicle is subsequently to drive through an AVP Type 2 area or an AVP Type 3 area according to the AVP process. In such areas for which the infrastructure has at least partial responsibility for motor vehicle guidance, the infrastructure must have identified the motor vehicle; in particular, the infrastructure must know the position and / or trajectory of the motor vehicle.

[0080] In particular, it is intended that an infrastructure-side AVP system, using one or more, in particular visual, environmental sensors, recognises the motor vehicle by one or more of the following attributes: License plate of the motor vehicle, dimensions of the motor vehicle, color of the motor vehicle, one or more special features of the motor vehicle, for example superstructure, damage, shape / type of the motor vehicle. This includes, for example, information on whether the motor vehicle is a passenger car (PKW), a motorcycle or, for example, a truck (HGV). Other shapes and types of motor vehicle can include, for example, the following information: small, medium, large. For example, an attribute can be a motor vehicle type. A motor vehicle type indicates, for example, whether the motor vehicle is a convertible, a sport utility vehicle (SUV), a sedan or a station wagon.

[0081] For example, the infrastructure system can also identify the motor vehicle based on a known trajectory and / or route of the motor vehicle. Such trajectories or routes can, for example, be sent from the motor vehicle to the infrastructure system.

[0082] Whenever an identification feature or a reference identification feature is mentioned in the description, the plural should always be included, or vice versa. This means, in particular, that the concept described here can also be implemented using multiple reference identification features and multiple identification features. QUOTES CONTAINED IN THE DESCRIPTION

[0000] This list of documents submitted by the applicant was generated automatically and is included solely for the convenience of the reader. This 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

[0000] DE 10 2012 222 562 A1

[0002]

Claims

[1] Method for identifying a motor vehicle (409) located within a parking space (401) and performing an AVP process, comprising the following steps: detecting (101) a reference identification feature of the motor vehicle (409) during the AVP process, Detecting (103) an identification feature of the motor vehicle (409) during a journey of the motor vehicle (409) from an AVP type 1 area of ​​the parking lot (401), which is only set up for an AVP process according to AVP type 1, to an AVP type 2 area of ​​the parking lot (401), which is set up for an AVP process according to AVP type 2, or to an AVP type 3 area of ​​the parking lot (401), which is set up for an AVP process according to AVP type 3, Comparing (105) the identification feature with the reference identification feature to identify the motor vehicle (409). [2] Method according to claim 1, wherein the respective detection of the reference identification feature and / or the identification feature comprises in each case a detection of the motor vehicle (409) by means of an infrastructure environment sensor (407, 423) arranged within the parking space (401), in particular a visual environment sensor (407, 423), in order to determine environment sensor data based on the respective detection, wherein the corresponding feature is determined based on the corresponding environment sensor data. [3] Method according to claim 1 or 2, wherein the reference identification feature is detected before or at the start of the AVP process, in particular while the motor vehicle (409) is located on a drop zone (403) of the parking lot (401). [4] Method according to one of the preceding claims, wherein upon detection of at least one active direction indicator, in particular of at least one flashing direction indicator, of a motor vehicle (409) located within the parking space (401), it is determined that this motor vehicle (409) is the motor vehicle (409) to be identified. [5] Method according to claim 4 as far as dependent on claim 2, wherein the environmental sensor data are evaluated in order to detect at least one active direction indicator, in particular at least one flashing direction indicator, in a motor vehicle (409) located within the parking space (401). [6] Method according to one of the preceding claims, wherein the reference identification feature and the identification feature are each an element selected from the following group of features: license plate, dimension, in particular length, height, width, colour, structure or structures, damage, in particular dent, scratch, shape, type. [7] System (201) for identifying a motor vehicle (409) located within a parking space (401) and performing an AVP process, comprising: a detection device (203) which is configured to detect a reference identification feature of the motor vehicle (409) during the AVP process and to detect an identification feature of the motor vehicle (409) during a journey of the motor vehicle (409) from an AVP type 1 area of ​​the parking space (401), which is configured only for an AVP process according to AVP type 1, to an AVP type 2 area of ​​the parking space (401), which is configured for an AVP process according to AVP type 2, or to an AVP type 3 area of ​​the parking space (401), which is configured for an AVP process according to AVP type 3, and a comparison device (205) which is configured to compare the identification feature with the reference identification feature in order to identify the motor vehicle (409). [8] Computer program (303) comprising instructions which, when the computer program (303) is executed by a computer, cause the computer to carry out a method according to one of claims 1 to 6. [9] Machine-readable storage medium (301) on which the computer program (303) according to claim 8 is stored.

Images