Procedure for parking a vehicle with an overhang

Abstract

Method for parking a vehicle (10) with a driving assistance system integrated into the vehicle (10) for executing the method, wherein during a training mode (T) at least one trajectory (TR) for the vehicle (10) from a starting position (SP) to a parking position (PP) is determined and during a playback mode (R) the at least one trajectory (TR) for a parking operation of the vehicle (10) is provided, taking into account acquired environmental information, vehicle dimensions and overhang dimensions, wherein the vehicle dimensions are prestored in a memory device, comprising the following steps: - if the vehicle (10) is moving from its starting position (SP) to the parking position (PP) for the first time, activating the training mode (T) (T1), which comprises the following steps: - acquiring environmental information by a sensor system (T2), which includes information about ceiling obstacles (14);and- storing the at least one trajectory, the environmental information and the vehicle dimensions in a storage system (T3);- determining and storing a threshold box for acceptable overhang dimensions (T4) taking into account the acquired environmental information;- if the threshold box is stored, when the vehicle (10) moves to its starting position (SP), starting the playback mode (R) which has the following steps:- checking whether an overhang (12) is present; and- simulating a parking operation of the vehicle (10) and its optional overhang (12) along the trajectory (TR) taking into account the environmental information, the vehicle dimensions and the overhang dimensions, characterized in that- checking whether an overhang (12) is present is carried out by detecting the overhang by a sensor device (R1);- if no overhang (12) is present, the vehicle (10) is parked along the at least one stored trajectory (R2); - if an overhang is present, the driver of the vehicle (10) is informed about the overhang (12) of the vehicle (10) and confirmation from the driver is requested that the overhang should be retained during the parking operation (R3); - if the driver does not wish to retain the overhang (12) during the parking operation, the system waits until the driver has removed the overhang (12), and the sensor device then checks again whether the overhang (12) is present by detecting the overhang (12), whereby if no overhang (12) is present, the vehicle (10) is parked along the at least one stored trajectory (R4);- if the driver wishes to maintain the overhang (12) during the parking maneuver, the overhang dimensions are requested by the driving assistance system (R5) to simulate the parking maneuver for the vehicle (10) along the trajectory (TR); - the overhang dimensions (R6) are provided; - a vehicle box (18) is rendered and an overhang box (20) is rendered (R7) to use augmented reality such that the driver can visually verify whether the rendered boxes (18, 20) cover the vehicle (10) and the overhang (12), the rendering of the vehicle box (18) and the rendering of the overhang box (20) being based on the vehicle dimensions and the overhang dimensions; - the rendered vehicle box (18) and the rendered overhang box (20) are combined into a boundary box (22) (R8);- the boundary box (22) is compared with the threshold box (R9); - if the boundary box (22) does not overlap the threshold box, the vehicle (10) is parked along at least one stored trajectory (TR) (R10); - if the boundary box (22) overlaps the threshold box, it is calculated whether an alternative trajectory (ATR) can be used for the parking operation in which the boundary box (22) does not overlap the threshold box (R11); - if no alternative trajectory (ATR) can be used for the parking operation, the driver is informed of the overlap and asked to eliminate the overlap, and the playback mode (R) is restarted (R12); and- if the alternative trajectory (ATR) can be used for the parking operation, the alternative trajectory (ATR) is calculated and the vehicle (10) is parked along the alternative trajectory (ATR) (R13).;

Description

The present invention relates to a method for parking a vehicle with an overhang using a vehicle-integrated driving assistance system for carrying out the method, wherein during a training mode at least one trajectory for the vehicle from a starting position to a parking position is determined and during a playback mode the at least one trajectory for parking the vehicle is provided, taking into account detected environmental information, vehicle dimensions and overhang dimensions, wherein the vehicle dimensions are pre-stored in a storage device. The present invention also relates to a driving assistance system with means for carrying out the steps of the method. Furthermore, the present invention relates to a vehicle that has the driving assistance system. Furthermore, the present invention relates to a computer program with instructions which, when the program is executed by a computer, cause the computer to perform the steps of the method. Furthermore, the present invention relates to a data carrier signal that transmits the computer program. Furthermore, the present invention relates to a computer-readable medium containing instructions which, when executed by a computer, cause the computer to perform the steps of the method. A method for parking a vehicle with an overhang is known, for example, from patent application WO 2016 / 116 246 A1. This document relates to a method for operating a driver assistance system of a motor vehicle, wherein a distance between the at least one distance sensor and an object is determined by means of at least one distance sensor arranged on and / or in a body component of the motor vehicle, wherein the object is arranged above a road surface on which the motor vehicle is located, wherein the distance to the object is determined by means of the at least one distance sensor while the object is in front of the motor vehicle in the direction of travel, and wherein, on the basis of the determined distance, a clearance height is calculated by means of a control device that describes a vertical distance between the road surface and a side of the object facing the road surface. Furthermore, DE 10 2015 208 590 A1 discloses a device for determining a space in which a vehicle can drive. Furthermore, DE 10 2013 209 873 A1 discloses a method for determining a passage possibility for a vehicle under an obstacle. Furthermore, DE 10 2018 007 833 A1 discloses a method for determining the height of a motor vehicle. Furthermore, DE 10 2015 100 719 A1 discloses a method for operating a motor vehicle in which the distance between the vehicle and an object is determined, wherein the object is located above a road surface. However, established methods have difficulties in executing an intuitive and safe parking maneuver when obstacles, particularly ceiling obstructions, are encountered. This can involve various situations, such as a vehicle overhang, for example, if a bicycle is attached to the rear of the vehicle; roof-mounted luggage, for example, if a trolley is placed on top of the vehicle; a person standing upright through the vehicle's sunroof; or a trailer attached to the vehicle. The present invention is based on the objective of providing a reliable, cost-effective and safe parking maneuver when obstacles, in particular ceiling obstacles, have been detected. The problem is solved by the independent claims. Advantageous embodiments are specified in the dependent claims. In particular, the present invention provides a method for parking a vehicle with a vehicle-integrated driving assistance system for carrying out the method, wherein during a training mode at least one trajectory for the vehicle from a starting position to a parking position is determined and during a playback mode the at least one trajectory for parking the vehicle is provided, taking into account acquired environmental information, vehicle dimensions and overhang dimensions, wherein the vehicle dimensions are pre-stored in a storage device, with the following steps: Activating the training mode, which comprises the following steps if the vehicle is driving from its starting position to the parking position for the first time: Acquiring environmental information by a sensor system, which includes information about ceiling obstacles, and storing the at least one trajectory.the environmental information and vehicle dimensions in a storage system; determining and storing a threshold box for acceptable overhang dimensions, taking into account the captured environmental information; when the vehicle moves to its starting position, starting the playback mode, which, if the threshold box is stored, includes the following steps: checking if an overhang exists, and simulating a parking maneuver of the vehicle and its optional overhang along the trajectory, taking into account the environmental information, vehicle dimensions, and overhang dimensions. The present invention also provides a driving assistance system comprising means for carrying out at least one step of the method. The present invention also specifies a vehicle that has the driving assistance system. The present invention also provides a computer program containing instructions which, when the program is executed by a computer, cause the computer to perform the steps of the method. The basic idea of ​​the invention is to provide an independent method for reliably and safely guiding a vehicle with an overhang from a starting position to a parking position. The system repeatedly checks whether the given conditions are sufficient to complete the parking maneuver without a collision. The parking maneuver is carried out in a straightforward manner, if possible. This prevents damage to the vehicle, the overhang, and any ceiling obstacles. These obstacles include, in particular, ceiling obstacles, and may also include obstacles at the side of the vehicle. It is essential that a new, alternative trajectory does not have to be calculated immediately in every case. The driver is actively involved and can actively remove the overhang so that the parking maneuver can be carried out using the trajectory initially provided.In particular, carrying out the method requires only minor modifications to the vehicle, so that the method according to the invention offers a cost-effective solution for the safe parking of a vehicle with an overhang. Specifically, it is intended that the vehicle has no overhang in training mode. To put it another way, this means, for example, that during training mode, the vehicle is driven from its starting position to its destination, its parking position. All three-dimensional information about the entire scene is captured using a sensor system, specifically a combination of sensors such as LiDAR and / or stereo cameras. This information is stored in a database as a virtual map, also known as a VMAP. The vehicle's dimensions, calculated at the time of manufacture, are also stored and used to calculate the vehicle's three-dimensional position in the real world. After the training mode is complete, the three-dimensional point cloud from the virtual map is used to calculate a maximum inscribed cuboid that can be fitted into the surrounding point cloud along a parking trajectory.This can be used as a threshold for accepting the size of the overhang, for example, its maximum length, width, and height. During playback mode, the driver preferably drives the vehicle close to the starting position and activates an automatic parking function. According to the invention, checking whether a protrusion is present is carried out by detecting a protrusion with a sensor device, wherein, if no protrusion is detected, the vehicle is parked along the at least one stored trajectory, if a protrusion is detected, the driver of the vehicle is informed about the protrusion and confirmation from the driver is requested that the protrusion should be retained during the parking process, if the driver does not wish to retain the protrusion during the parking process, the system waits until the driver has removed the protrusion, and then the sensor device detects the presence of the protrusion again, wherein, if no protrusion is present, the vehicle is parked along the at least one stored trajectory, if the driver wishes to retain the protrusion during the parking process,The driver assistance system requests the overhang dimensions; the overhang dimensions are provided; a vehicle box and an overhang box are rendered for use in augmented reality in such a way that the driver can visually verify whether the rendered boxes cover the vehicle and the overhang, with the rendering of the vehicle box and the rendering of the overhang box being based on the vehicle dimensions and the overhang dimensions; the rendered vehicle box and the rendered overhang box are unified into a boundary box; the boundary box is compared with the threshold box; if the boundary box does not overlap the threshold box, the vehicle is parked along the at least one stored trajectory; if the boundary box overlaps the threshold box, it is calculated whether an alternative trajectory can be used for the parking operation in which the boundary box does not overlap the threshold box.If no alternative trajectory can be used for the parking maneuver, the driver is informed of the overlap and prompted to eliminate it, and playback mode is restarted. If an alternative trajectory can be used for the parking maneuver, the alternative trajectory is calculated and the vehicle is parked along the alternative trajectory. According to a modified embodiment of the invention, the storage of the at least one trajectory, the environmental information, the vehicle dimensions, and / or the threshold box takes place in a storage system of the vehicle and / or in a storage system of an external server. Storage in the vehicle's storage system enables fast data access. Storage on the external server's storage system means that the data does not consume the limited storage capacity of the vehicle's storage system and that the data can always be kept up to date, even if the vehicle has not been parked in its parking position for an extended period of time. According to a modified embodiment of the invention, the sensor system comprises at least one LiDAR sensor and / or one or more stereo cameras and / or the sensor device. It has been found that these sensors are particularly advantageous for obtaining useful data for generating the threshold box and the boundary box. According to a modified embodiment of the invention, the storage system comprises a database such that the at least one trajectory and the environmental information are stored as a virtual map in the database of the storage system. It has been found that using this data in a virtual map is particularly suitable for determining an overlap between the threshold box and the boundary box. According to a modified embodiment of the invention, determining the threshold box for acceptable overhang dimensions is performed by calculating a maximum possible boundary box for the vehicle and its overhang that fits within a point cloud of environmental information. This method has proven to require relatively little computing power for a reliable and collision-safe result. According to a modified embodiment of the invention, the sensor device consists of the vehicle's proximity sensors for detecting the overhang. It has been found that proximity sensors are sufficient to solve the problem of the invention, thus offering a cost-effective solution. According to a modified embodiment of the invention, the sensor device is arranged on the roof of the vehicle, on the tailgate of the vehicle, and / or on at least one of the vehicle's lights. It has been found that arranging the sensor in these locations results in a reliable and collision-proof solution. According to a modified embodiment of the invention, the overhang dimensions are defined as the length, width, and / or height of the overhang. It has been found that considering these dimensions leads to a reliable and collision-proof solution. However, it may be sufficient to consider only the dimensions of the main axis from the vehicle to the obstacle. While this results in less detail, it allows for faster calculations. This means, for example, that with regard to a ceiling object, only the height of the overhang is considered. According to a modified embodiment of the invention, the provision of the overhang dimensions is carried out by the driver manually entering the overhang dimensions and / or by the driver visually viewing the rendered overhang box and modifying or verifying the size of the rendered overhang box and / or by the sensor device and the driving assistance system determining the overhang dimensions. It has been found that these provisioning options are best suited for everyday and intuitive use and enable a reliable and collision-free parking process. Each option is sufficient on its own. However, safety can be increased by combining these options. For example, manual correction by the driver can ensure that they have not made a typo or accidentally used incorrect values ​​during manual input.Manual correction by the driver can also ensure that the sensor system has not made any incorrect measurements. It is also possible to use the sensor system for determination while simultaneously making a manual input to prevent the driver from making typos or accidentally using incorrect values ​​during manual entry. According to a modified embodiment of the invention, if the boundary box does not overlap the threshold box, the at least one stored trajectory is updated, and the vehicle is then parked along this at least one stored trajectory. In this way, the available information can be continuously updated so that existing data can be used in subsequent parking situations, instead of performing new calculations that would burden the system. According to a modified embodiment of the invention, it is provided that, in order to check whether a protrusion is present, the sensor device detects a protrusion, if a mirror and its specular reflections are available, and the processing of the specular reflections by a processing unit comprises the following steps: detecting a mirror that reflects the vehicle and its protrusion, segmenting the mirror into different areas containing an area of ​​interest, and preferably extracting the area for preprocessing, calculating the mirror geometry and calculating lens distortion coefficients, correcting the area of ​​interest, in particular by performing a fisheye correction, and detecting the vehicle in the area of ​​interest, in particular by extracting the top and / or the rear of the vehicle.Determining an overhang on the top and / or rear of the vehicle using an artificial neural network, in particular a convolutional neural network. The use of a mirror and its reflection allows for the reliable detection of protrusions. This can be used as an alternative to vehicle-mounted sensors or in addition to them to reduce the probability of errors. Traffic mirrors are the most commonly used type of mirror. These are permanently installed convex mirrors and are a standard feature of road infrastructure. They are primarily used in areas with poor visibility and are designed to improve visibility. The appearance of traffic mirrors is not uniformly defined. They typically consist of a convexly curved reflective surface mounted on a rectangular or round base plate. This allows more of the obscured area to be reflected in the mirror, but the reflection is distorted.This distorted representation is always compensated for to ensure reliable protrusion detection focused on the area of ​​interest. The use of an artificial neural network then helps to reliably evaluate the captured image. Depending on the system's complexity, it is also possible to determine the protrusion dimensions. Artificial neural networks are computing systems loosely inspired by the biological neural networks that make up animal brains. The neural network itself is not an algorithm, but rather a framework for many different machine learning algorithms to work together and process complex data inputs. Such systems learn to perform tasks from examples, generally without being programmed with task-specific rules. An artificial neural network is based on a collection of connected units or nodes called artificial neurons, which freely model the neurons in a biological brain. Each connection, like the synapses in a biological brain, can transmit a signal from one artificial neuron to another. An artificial neuron that receives a signal can process it and then signal additional connected artificial neurons.In typical implementations of artificial neural networks, the signal at a connection between artificial neurons is a real number, and the output of each artificial neuron is calculated as a nonlinear function of the sum of its inputs. The connections between artificial neurons are called edges. Artificial neurons and edges usually have a weight that adjusts during learning. The weight increases or decreases the strength of the signal at a connection. Artificial neurons may have a threshold, so the signal is only transmitted if the total signal crosses this threshold. Typically, artificial neurons are grouped into layers. Different layers can perform different types of transformations on their inputs.Signals travel from a first layer, also called the input layer, to a final layer, also called the output layer, possibly after traversing the layers multiple times. The original goal of the artificial neural network approach is to solve problems in the same way a human brain would. Convolutional neural networks use a variation of multilayer perceptrons designed to require minimal preprocessing. Compared to other image classification algorithms, convolutional neural networks use relatively little preprocessing. This means the network learns the filters that, in traditional algorithms, would have been developed manually. This independence from prior knowledge and human effort in feature design is a significant advantage. According to a modified embodiment of the invention, an external optical camera system is used to detect protrusions by means of a sensor device, in order to check whether a protrusion is present. The following steps are performed: the optical camera system, preferably a video surveillance system installed near the parking position, detects the protrusion, and the acquired data is transmitted from the optical camera system to the vehicle via a separate V2X-based control system. Careful and regular maintenance of the external optical camera system ensures reliable protrusion detection. Defective components of the external optical camera system can be quickly identified, thus increasing the likelihood of avoiding collisions compared to sensor devices located solely on the vehicle. A video surveillance system, also known as a CCTV camera system, can generate images or recordings for surveillance or other private purposes. Cameras can be either video cameras or digital cameras. V2X is a well-known abbreviation for Vehicle-to-Everything communication. Vehicle-to-Everything communication is the exchange of information between a vehicle and an entity that the vehicle can influence, and vice versa. It is a vehicle communication system that encompasses other, more specific communication types such as V2I (Vehicle-to-Infrastructure), V2N (Vehicle-to-Network), V2V (Vehicle-to-Vehicle), V2P (Vehicle-to-Pedestrian), V2D (Vehicle-to-Device), and V2G (Vehicle-to-Grid). The main motivations for V2X are road safety, traffic efficiency, and energy savings. There are two types of V2X communication technologies, depending on the underlying technology used: Wi-Fi-based and cellular-based. According to a modified embodiment of the invention, the computer-readable medium is either integrated into the vehicle or external for simulating the vehicle's parking maneuver along the trajectory. For a computer-readable medium integrated into the vehicle, the medium is preferably a component of the driver assistance system. In particular, in the case of an external computer-readable medium, it is intended that the medium be a mobile device. Mobile devices can be smartphones, smartwatches, smart glasses, tablets, laptops, or similarly functional mobile devices. These and other aspects of the invention will become apparent and be explained with reference to the embodiments described below. Individual features illustrated in the embodiments can, on their own or in combination, constitute an aspect of the present invention. Features of the different embodiments can be transferred from one embodiment to another. The figures show: Fig. 1 a two-part flowchart of the method according to the invention; Fig. 2 a schematic representation of a specular reflection for a preferred embodiment of the method according to the invention; Fig. 3 a schematic three-dimensional representation of a vehicle with an overhang on its upper side in a parking garage, wherein the vehicle forms a vehicle box and the overhang forms an overhang box, which together form a boundary box, according to a first embodiment of the invention; Fig. 4 the schematic three-dimensional representation of the vehicle with its overhang according to Fig. 3 during a training mode, wherein lamp bodies form ceiling obstacles; and Fig. 5 the schematic three-dimensional representation of the vehicle with its overhang according to Fig. 3 during a playback mode, wherein lower edges of lamp body boxes form an upper edge of a threshold box. Fig. 1 shows a method for parking a vehicle 10 with an overhang 12 using a driving assistance system integrated into the vehicle 10. During a training mode T, at least one trajectory TR for the vehicle 10 from a starting position SP to a parking position PP is determined, and during a playback mode R, the at least one trajectory TR for a parking operation of the vehicle 10 is provided, taking into account acquired environmental information, vehicle dimensions, and overhang dimensions. The vehicle dimensions are pre-stored in a memory device. For this purpose, Fig. 1 includes two figures, namely Fig. 1a and Fig. 1b. Fig. 1a shows a training mode T. Fig. 1b shows a playback mode R. This means that the method according to the invention according to Fig. 1a precedes the method according to the invention according to Fig. 1b at least once in order to determine the threshold box. According to Fig. 1a, the training mode T is activated if the vehicle 10 travels for the first time from its starting position SP to the parking position PP, whereby the training mode T1 is activated, in which the following steps are performed: - Acquisition of environmental information by a sensor system T2, wherein the environmental information includes information about ceiling obstacles 14, - Storage of the at least one trajectory, the environmental information and the vehicle dimensions in a storage system T3, and - Determination and storage of a threshold box for acceptable overhang dimensions taking into account the acquired environmental information T4. According to Fig. 1b, playback mode R is started, if the threshold box is already stored, when the vehicle 10 moves to its starting position SP, performing the following steps: - Checking whether an overhang 12 is present by detecting the overhang with a sensor device R1, - if no overhang 12 is detected, parking the vehicle 10 along the at least one stored trajectory R2, - if an overhang is detected, informing a driver of the vehicle 10 about the overhang 12 of the vehicle 10 and requesting confirmation from the driver that the overhang should be maintained during the parking operation R3, - if the driver does not want to maintain the overhang 12 during the parking operation, waiting until the driver has removed the overhang 12, and checking again whether the overhang 12 is present by detecting the overhang 12 with the sensor device, whereby, if no overhang 12 is present,the vehicle 10 is parked along at least one stored trajectory R4,- if the driver wishes to maintain the overhang 12 during the parking process, request the overhang dimensions via the driving assistance system R5,- provide the overhang dimensions R6,- render a vehicle box 18 and render an overhang box 20 R7 to use augmented reality such that the driver can visually check whether the rendered boxes 18, 20 cover the vehicle 10 and the overhang 12, the rendering of the vehicle box 18 and the rendering of the overhang box 20 being based on the vehicle dimensions and the overhang dimensions,- combine the rendered vehicle box 18 and the rendered overhang box 20 into a boundary box 22 R8,- compare the boundary box 22 with the threshold box R9,- if the boundary box 22 the Threshold box not overlapping, parking of vehicle 10 along at least one stored trajectory TR R10,- if the boundary box 22 overlaps the threshold box, calculate whether an alternative trajectory ATR can be used for the parking operation where the boundary box 22 does not overlap the threshold box R11,- if no alternative trajectory ATR can be used for the parking operation, inform the driver about the overlap, prompt them to eliminate the overlap and restart playback mode R R12,- if the alternative trajectory ATR can be used for the parking operation, calculate the alternative trajectory ATR and park the vehicle 10 along the alternative trajectory ATR R13., Fig. 3 shows a schematic three-dimensional representation of the vehicle 10 with its overhang 12 on its upper side in a parking garage, wherein the vehicle is at its starting position SP, and wherein the vehicle 10 forms a vehicle box 18 and the overhang 12 forms an overhang box 20, which together form the boundary box 22, according to a first embodiment of the invention. Fig. 4 shows a schematic three-dimensional representation of the vehicle 10 with its overhang 12 according to Fig. 3 during a training mode T, where lamp housings form ceiling obstacles 14. According to Fig. 1a, the training mode T is activated because the vehicle 10 initially travels from its starting position SP to the parking position PP T1 with the training mode T activated. This means that the sensor system acquires the environmental information T2, which includes information about the ceiling obstacles 14. Subsequently, the at least one trajectory, the environmental information, and the vehicle dimensions are stored in a memory system T3. As a final step of the process, the threshold value box for acceptable overhang dimensions is determined and stored T4, taking into account the acquired environmental information. This completes the training mode T. Fig. 5 shows a schematic three-dimensional representation of the vehicle 10 with its overhang 12 according to Fig. 3 during a playback mode R, where the lower edges of ceiling obstacles 14, designed as lamp housings, form an upper edge of the threshold box. In the scene depicted, one step consists of comparing the boundary box 22 with the threshold box R9. It should be noted that the boundary box 22 is not shown in its entirety in Fig. 5, but only the overhang box 20, which overlaps the threshold box, is shown as part of the boundary box 22. Therefore, an alternative trajectory ATR is calculated in which the boundary box 22 does not overlap the threshold box R11. After the alternative trajectory ATR has been calculated, a parking operation of the vehicle 10 is performed along the alternative trajectory ATR at the parking position PP R13. According to a modified embodiment of the invention, it is provided that the storage of the at least one trajectory TR, the environmental information, the vehicle dimensions T3 and / or the threshold box is carried out in a storage system of the vehicle 10 and / or in a storage system of an external server. According to a modified embodiment of the invention, the sensor system comprises at least one LIDAR sensor and / or one or more stereo cameras and / or the sensor device. According to a modified embodiment of the invention, the storage system has a database such that the at least one trajectory TR and the environmental information are stored as a virtual map in the database of the storage system. According to a modified embodiment of the invention, it is provided that the determination of the threshold box for acceptable overhang dimensions T4 is carried out by calculating a maximum possible limit box 22 for the vehicle 10 and its overhang 12 that fits into a point cloud of the environmental information. According to a modified embodiment of the invention, the sensor device includes proximity sensors of the vehicle 10 for detecting the protrusion 12. According to a modified embodiment of the invention, the sensor device is arranged on the roof of the vehicle 10, on the tailgate of the vehicle 10 and / or on at least one lamp of the vehicle 12. According to a modified embodiment of the invention, the overhang dimensions are provided to have a length, a width and / or a height. According to a modified embodiment of the invention, the provision of the overhang dimensions R6 is carried out by manually providing the overhang dimensions by the driver and / or by visually viewing the rendered overhang box 20 by the driver and correcting or verifying the size of the rendered overhang box 20 and / or by determining the overhang dimensions by the sensor device and the driving assistance system. According to a modified embodiment of the invention, it is provided that in the event that the limiting box 22 does not overlap the threshold box, the at least one stored trajectory TR is updated and subsequently the vehicle 10 is parked along the at least one stored trajectory TR R10. According to a modified embodiment of the invention, as schematically illustrated in Fig. 2, it is provided that, in order to check whether a protrusion 12 is present, the protrusion 12 is detected by the sensor device R1, if a mirror 24 and its specular reflections 26 are available, the specular reflections 26 are detected by the sensor device and processed by a processing unit, wherein the following steps are carried out: - Detection of a mirror 24 that reflects the vehicle 10 and its protrusion 12, - Segmentation of the mirror 24 into different areas, which contain an area of ​​interest, and preferably extraction of the area for preprocessing, - Calculation of the mirror geometry and calculation of lens distortion coefficients, - Rectification of the area of ​​interest, in particular by performing a fisheye correction.- Capturing the vehicle 10 in the area of ​​interest and in particular extracting the top and / or rear of the vehicle 10,- Determining a protrusion 12 on the top and / or rear of the vehicle using an artificial neural network, in particular a convolutional neural network. According to a modified embodiment of the invention, although this is not shown in detail in any of the figures, an external optical camera system is used as a sensor device for detecting the protrusion 12 in order to check whether a protrusion 12 is present by detecting the protrusion 12 with the sensor device R1, wherein the following steps are carried out: - Detection of the protrusion 12 by the optical camera system, preferably a video surveillance system installed near the parking position PP, and - Transmission of the detected data from the optical camera system to the vehicle 10 via a separate V2X-based control system. Reference symbol list 10 Vehicle 12 Overhang 14 Ceiling obstacle 18 Vehicle box 20 Overhang box 22 Boundary box 24 Mirror 26 Mirror reflections TR Trajectory SP Starting position PP Parking position ATR Alternative trajectory T Training mode T1 Activate training mode T2 Capture environmental information T3 Save at least one trajectory, environmental information, and vehicle dimensions T4 Determine and save a threshold box for acceptable overhang dimensions R Playback mode R1 Check if an overhang exists by capturing an overhang R2 If no overhang is captured, park the vehicle along the at least one saved trajectory R3 If an overhang is captured, inform the vehicle's driver about the vehicle's overhang and request confirmation from the driver that the overhang should be maintained during the parking process R4 If the driver does not wish to maintain the overhang during the parking process, waituntil the driver has removed the overhang, and the sensor device checks again whether the overhang is present, whereby, if no overhang is present, the vehicle is parked along the at least one stored trajectory. R5 If the driver wishes to retain the overhang during the parking operation, the driver assistance system requests the overhang dimensions. R6 Provides the overhang dimensions. R7 Renders a vehicle box and an overhang box. R8 Unifies the rendered vehicle box and the rendered overhang box into a boundary box. R9 Compares the boundary box with the threshold box. R10 If the boundary box does not overlap the threshold box, parks the vehicle along the at least one stored trajectory. R11 If the boundary box overlaps the threshold box, calculates whether an alternative trajectory can be used for the parking operation.where the boundary box does not overlap the threshold box R12 If no alternative trajectory can be used for the parking operation, inform the driver about the overlap, request that the overlap be eliminated and restart playback mode R13 If an alternative trajectory can be used for the parking operation, calculate the alternative trajectory and park the vehicle along the alternative trajectory,

Claims

Method for parking a vehicle (10) with a driving assistance system integrated into the vehicle (10) for executing the method, wherein during a training mode (T) at least one trajectory (TR) for the vehicle (10) from a starting position (SP) to a parking position (PP) is determined and during a playback mode (R) the at least one trajectory (TR) for a parking operation of the vehicle (10) is provided, taking into account acquired environmental information, vehicle dimensions and overhang dimensions, wherein the vehicle dimensions are prestored in a memory device, comprising the following steps: - if the vehicle (10) is moving from its starting position (SP) to the parking position (PP) for the first time, activating the training mode (T) (T1), which comprises the following steps: - acquiring environmental information by a sensor system (T2), which includes information about ceiling obstacles (14);and- storing the at least one trajectory, the environmental information and the vehicle dimensions in a storage system (T3);- determining and storing a threshold box for acceptable overhang dimensions (T4) taking into account the acquired environmental information;- if the threshold box is stored, when the vehicle (10) moves to its starting position (SP), starting the playback mode (R) which has the following steps:- checking whether an overhang (12) is present; and- simulating a parking operation of the vehicle (10) and its optional overhang (12) along the trajectory (TR) taking into account the environmental information, the vehicle dimensions and the overhang dimensions, characterized in that- checking whether an overhang (12) is present is carried out by detecting the overhang by a sensor device (R1);- if no overhang (12) is present, the vehicle (10) is parked along the at least one stored trajectory (R2); - if an overhang is present, the driver of the vehicle (10) is informed about the overhang (12) of the vehicle (10) and confirmation from the driver is requested that the overhang should be retained during the parking operation (R3); - if the driver does not wish to retain the overhang (12) during the parking operation, the system waits until the driver has removed the overhang (12), and the sensor device then checks again whether the overhang (12) is present by detecting the overhang (12), whereby if no overhang (12) is present, the vehicle (10) is parked along the at least one stored trajectory (R4);- if the driver wishes to maintain the overhang (12) during the parking maneuver, the overhang dimensions are requested by the driving assistance system (R5) to simulate the parking maneuver for the vehicle (10) along the trajectory (TR); - the overhang dimensions (R6) are provided; - a vehicle box (18) is rendered and an overhang box (20) is rendered (R7) to use augmented reality such that the driver can visually verify whether the rendered boxes (18, 20) cover the vehicle (10) and the overhang (12), the rendering of the vehicle box (18) and the rendering of the overhang box (20) being based on the vehicle dimensions and the overhang dimensions; - the rendered vehicle box (18) and the rendered overhang box (20) are combined into a boundary box (22) (R8);- the boundary box (22) is compared with the threshold box (R9); - if the boundary box (22) does not overlap the threshold box, the vehicle (10) is parked along at least one stored trajectory (TR) (R10); - if the boundary box (22) overlaps the threshold box, it is calculated whether an alternative trajectory (ATR) can be used for the parking operation in which the boundary box (22) does not overlap the threshold box (R11); - if no alternative trajectory (ATR) can be used for the parking operation, the driver is informed of the overlap and asked to eliminate the overlap, and the playback mode (R) is restarted (R12); and- if the alternative trajectory (ATR) can be used for the parking operation, the alternative trajectory (ATR) is calculated and the vehicle (10) is parked along the alternative trajectory (ATR) (R13).; Method according to claim 1, characterized in that the storage of the at least one trajectory (TR), the environmental information, the vehicle dimensions (T3) and / or the threshold box is performed in a storage system of the vehicle (10) and / or in a storage system of an external server. Method according to one of the preceding claims, characterized in that the sensor system comprises at least one LIDAR sensor and / or one or more stereo cameras and / or the sensor device. Method according to one of the preceding claims, characterized in that the storage system has a database such that the at least one trajectory (TR) and the environment information are stored as a virtual map in the database of the storage system. Method according to one of the preceding claims, characterized in that the determination of the threshold box for acceptable overhang dimensions (T4) is carried out by calculating a maximum possible limit box (22) for the vehicle (10) and its overhang (12) that fits into a point cloud of environmental information. Method according to one of the preceding claims, characterized in that the sensor device has proximity sensors of the vehicle (10) for detecting the protrusion (12). Method according to one of the preceding claims, characterized in that the sensor device is arranged on a roof of the vehicle (10), on a tailgate of the vehicle (10) and / or on at least one lamp of the vehicle (12). Method according to one of the preceding claims, characterized in that the overhang dimensions have a length, a width and / or a height. Method according to one of the preceding claims, characterized in that the provision of the overhang dimensions (R6) is carried out by manually providing the overhang dimensions by the driver and / or by visually viewing the rendered overhang box (20) by the driver and correcting or verifying the size of the rendered overhang box (20) and / or by determining the overhang dimensions by the sensor device and the driving assistance system. Method according to one of the preceding claims, characterized in that, in the event that the limiting box (22) does not overlap the threshold box, the at least one stored trajectory (TR) is updated and then the vehicle (10) is parked along the at least one stored trajectory (TR) (R10). A method according to one of the preceding claims, characterized in that, to check whether a protrusion (12) is present, the protrusion (12) is detected by the sensor device (R1), if a mirror (24) and its specular reflections (26) are available, the specular reflections (26) are detected by the sensor device and the specular reflections (26) are processed by a processing unit, wherein the following steps are performed: - Detection of a mirror (24) that reflects the vehicle (10) and its protrusion (12); - Segmentation of the mirror (24) into different areas containing an area of ​​interest, and preferably extraction of the area for preprocessing; - Calculation of the mirror geometry and calculation of lens distortion coefficients; - Rectification of the area of ​​interest, in particular by performing a fisheye correction;- Capturing the vehicle (10) in the area of ​​interest and in particular extracting the top and / or rear of the vehicle (10); and - Determining a protrusion (12) on the top and / or rear of the vehicle (10) using an artificial neural network, in particular a convolutional neural network.; A method according to one of the preceding claims, characterized in that, in order to check whether a protrusion (12) is present by detecting the protrusion (12) by the sensor device (R1), an external optical camera system is used as a sensor device for detecting the protrusion (12), comprising the following steps: - detecting the protrusion (12) by the optical camera system, preferably a video surveillance system installed near the parking position (PP); and - transmitting the detected data from the optical camera system to the vehicle (10) via a separate V2X-based control system. Driving assistance system comprising means for carrying out the method according to at least one of the preceding claims. Vehicle (10) with a driving assistance system according to the preceding claim. Computer program with instructions which, when the program is executed by a computer, cause the computer to perform the steps of the method according to at least one of claims 1 to 12.

Images