Parking assistance system

Abstract

The invention relates to a method (M) for operating a parking assistance system (110) for a vehicle (100), which includes: providing (S28) a trajectory (190) which specifies at least one waypoint position (180) and at least one environmental position (160, 170) along a path (140), an environmental position (160, 165, 170, 175) being a position of an environmental feature (155); detecting (S32, S46) at least one image-based environmental position (175), which is a position of an environmental feature detected on the basis of an image signal, and at least one radar-based environmental position (165), which is a position of an environmental feature detected on the basis of a radar echo signal; selecting (S34, S36, S38, S40, S42) the image-based environmental position (175) or at least one of the image-based environmental positions (175) if this image-based environmental position (175) meets a position determination requirement; selecting (S48, S50) the radar-based environmental position (165) or at least one of the radar-based environmental positions (165) if this radar-based environmental position (165) meets a position determination requirement; and determining (S52) a position (200) of the vehicle (100) relative to an environment (150) by comparing the at least one selected environmental position (165, 175) with the at least one environmental position (160, 170) on the trajectory (190).

Description

[0001] Parking assistance system

[0002] The present invention relates to a method for operating a parking assistance system for a vehicle, a computer program product, a parking assistance system and a vehicle.

[0003] It is known to determine a vehicle's position using satellite navigation. The typical accuracy is in the range of several meters, making this unsuitable for parking assistance purposes. Determining a position using radar echo signals can be ambiguous. Determining a position using image signals can depend heavily on the achievable image quality in a given situation.

[0004] Methods are known for operating a parking assistance system using a radar echo and a camera image.

[0005] DE 10 2015 210 357 B4 discloses a method for assisted driving. A trajectory from a starting position to a target position is stored, including information about an obstacle. During driving, characteristic features of a vehicle's surroundings in current position information are compared with features in the stored information to determine whether the ego vehicle is within a certain radius relative to the starting position. If the current position is within a certain radius relative to the starting position, a driver is offered the opportunity to activate an assistance function.

[0006] DE 10 2019 133 967 A1 discloses a method for operating a parking assistance system. In a first operating mode, the surroundings of a vehicle and, based on the detected surroundings, a relative position of the vehicle in the surroundings are detected and recorded. In a second operating mode, a relative position of the vehicle is determined based on a driving dynamics parameter. If the relative position detected in the first operating mode is too inaccurate, the surroundings and, based on the relative position, are additionally determined in the second operating mode.

[0007] CN 114 572 196 A discloses a method for autonomous parking. The parking is monitored using camera images. If an ultrasound system fails to find a target point or exceeds an error criterion, and a stationary obstacle is detected in the vehicle's vicinity, the presence of the stationary obstacle is detected using only one camera.

[0008] US 2020 174 1120A1 discloses a sensor fusion system for a driver assistance system and / or an autonomous vehicle. Radar classification capability and the accuracy of estimating speed / distance using the camera are mutually trained. If the camera's performance is limited due to poor visibility, object classification is performed based on the radar data.

[0009] Against this background, it is an object of the present invention to provide a means for stably determining a vehicle position for use by a parking assistance system.

[0010] Accordingly, a method for operating a parking assistance system for a vehicle is proposed, comprising:

[0011] Providing a trajectory indicating at least one waypoint position and at least one environmental position along a route, wherein an environmental position is a position of an environmental feature;

[0012] Detecting at least one radar-based environmental position, which is a position of an environmental feature detected based on a radar echo signal, and at least one image-based environmental position, which is a position of an environmental feature detected based on an image signal; selecting the image-based environmental position or at least one of the image-based environmental positions if this image-based environmental position satisfies a position determination requirement;

[0013] Selecting the radar-based environmental position or at least one of the radar-based environmental positions if this radar-based environmental position satisfies one and / or the position determination requirement; and

[0014] Determining a position of the vehicle relative to an environment by comparing the selected environment position(s) with the at least one environment position of the trajectory.

[0015] This allows the relative position to be determined based on all suitable surrounding positions. This enables the most accurate position determination possible, given the conditions of the respective situation.

[0016] An "environmental feature" can be understood as a feature of a signal that represents the vehicle's surroundings. The feature is recognizable in the signal. Within the framework of the proposed method, a radar echo signal and an image signal are preferred signals for detecting an environmental feature.

[0017] An "environmental position" is understood to be the position of an environmental feature. An environmental position can be understood, in particular, as the position of a detected and / or recognizable environmental feature. An environmental position can be understood, in particular, as an absolute position or a relative position.

[0018] An "absolute" position can be understood as a spatial relationship in a global and / or standardized coordinate system. An absolute position can be determined, for example, using a satellite signal. A "relative" position can be understood as a spatial relationship in relation to another position or several other positions. A relative position can preferably contain a distance specification and an angle specification. A relative position can preferably be a position in a coordinate system related to the vehicle's own vehicle.

[0019] The method preferably provides for selecting a single environmental position or a subset of environmental positions from an even larger set of environmental positions or all environmental positions of a set of environmental positions.

[0020] The trajectory preferably contains a plurality of environmental positions. Preferably, a plurality of radar-based environmental positions and / or a plurality of image-based environmental positions are detected. Preferably, a plurality of radar-based environmental positions and / or a plurality of image-based environmental positions are selected. If the trajectory contains a plurality of environmental positions, the selected environmental position(s) is / are preferably compared with at least some of the environmental positions of the trajectory.

[0021] The trajectory is preferably provided as a trajectory data set, in particular a digital trajectory data set, for better interchangeability. The provided trajectory is preferably a trained trajectory. For example, the parking assistance system or another system of the vehicle is configured to record and store a manually driven trajectory in a training mode. For example, various sensor signals are recorded that characterize a driving state of the vehicle, such as speed, position, steering angle, and the like, as clearly as possible. The trajectory takes the form of a digital environmental map, for example, in which detected obstacles in the environment are plotted. The radar-based environmental position(s) is / are preferably provided and recorded by a radar sensor and / or a sensor control unit.The radar-based environmental position(s) is / are preferably acquired on the basis of a radar return signal.

[0022] The image-based environmental position / the image-based environmental positions are preferably provided and detected by a camera and / or a sensor control unit. The image-based environmental position / the image-based environmental positions are preferably detected based on an image signal. An image signal can, for example, be indicative of a single image. An image signal can, for example, be indicative of a sequence of images. An image signal can, for example, be an image stream. An image signal can preferably be provided by a VSLAM system (visual simultaneous localisation and mapping). In particular, the VSLAM system can be an SVS (surround view system).In other words: Preferably, a vehicle is provided with an SVS, wherein the SVS is preferably used for VSLAM, wherein the SVS provides image data or images on the basis of which the image-based environmental positions are recognized.

[0023] Optionally, at least one radar-based environmental position may not be selected if the at least one image-based environmental position is selected. Optionally, at least in one area of ​​the environment, for example an angular range of at least 30° around a vehicle vertical axis, no radar-based environmental position is selected if at least one image-based environmental position, preferably a plurality of image-based environmental positions, is or are selected in the same area. Optionally, no radar-based environmental position is selected if a plurality of image-based environmental positions are selected. Optionally, no radar-based environmental position is selected if the at least one image-based environmental position is selected. This step may, for example, precede the selection of the at least one radar-based environmental position as a condition.The reason for these variants may be, for example, that image-based environmental positions are often more accurate the closer the camera is to the respective environmental feature during recording. This way, for example, additional effort for processing the radar-based environmental position(s) can be avoided if the relative position of the vehicle is determined based on the image-based environmental position(s).

[0024] Optionally, the method may include: Checking, as the positioning requirement for the radar-based environmental positions or one of the positioning requirements, whether there is a minimum agreement between a relative arrangement of the radar-based environmental positions and a relative arrangement of the environmental positions of the trajectory. Thus, for example, the trajectory can be used to assess whether the radar-based environmental positions are similar enough to the environmental positions to reliably determine a current position. Geometric similarity algorithms can be used for this purpose, for example.

[0025] Optionally, the method may include: Checking, as the positioning requirement for the radar-based environmental positions or one of the positioning requirements, whether there is a minimum agreement between a relative arrangement of the image-based environmental positions and a relative arrangement of the environmental positions of the trajectory. Thus, for example, based on the trajectory, it can be assessed whether the image-based environmental positions are similar enough to the environmental positions to reliably determine a current position by comparison. Geometric similarity algorithms can be used for this purpose, for example.

[0026] Optionally, the method may include: Checking, as the positioning request for the radar-based environmental positions or one of the positioning requests, whether an image acquisition value of the image-based environmental position(s) and an image acquisition value of the environmental position(s) of the trajectory correspond to each other. This allows an assessment of whether the acquisition conditions of the images are similar enough to reliably determine a current position by comparison. "Correspond," for example, can mean that the image acquisition values ​​may differ from each other in magnitude by up to 50%, preferably up to 30%, and preferably up to 20%.

[0027] Preferably, the image capture value is indicative of a brightness. If the brightness of an image on the basis of which an environmental position of the trajectory is detected and an image on the basis of which the image-based environmental position is detected correspond to one another, this can force the use of images with similar colors so that the same features can be detected with a high degree of reliability. The requirement for similar brightness of the images can, for example, prevent different features from being detected when driving into or out of a garage despite being in close spatial proximity. The requirement for similar brightness of the images can, for example, prevent different features from being detected when driving in snow or during or after rain than in a dry environment. The same advantages can be achieved, for example, if the image capture value contains a measure of contrast.If the image capture value is indicative of a time of day, it can be avoided, for example, that different features are detected due to backlighting, twilight, day and night, and / or different recognizable colors. If the image capture value is indicative of a season, it can be avoided, for example, that different features are detected due to different foliage.

[0028] Optionally, the method may include: checking, as the positioning request for the radar-based environmental positions or one of the positioning requests, whether weather information of the image-based environmental positions and weather information of the environmental positions of the trajectory correspond to one another. The weather information may be provided, for example, by a temperature sensor, a rain sensor, and / or an anti-slippery detector, such as an ABS. This can prevent, for example, different features from being detected as a result of rain and / or snow. The weather information may, for example, be implemented as a classification, such as "dry," "humid," "rain-soaked," "icy," and "snow-covered."

[0029] Optionally, the method may include: checking, as the positioning request for the radar-based environmental positions or one of the positioning requests, whether a respective image-based environmental position is at most a preset maximum distance from the host vehicle. For example, the maximum distance may be up to 50 m, more preferably up to 30 m, even more preferably up to 15 m, and preferably up to 10 m. In particular, determining a distance to an environmental feature by means of image analysis is often less accurate the further the environmental position is from the camera or image recording device and / or the vehicle. By means of this request, for example, a particularly precisely known environmental position of the image-based environmental position(s) can be selected.

[0030] Optionally, the environmental positions can be treated as points or coordinates of a two-dimensional or, preferably, three-dimensional point cloud. This makes it particularly easy to compare, for example, radar-based environmental positions and image-based environmental positions. "Treatment" can be understood, for example, as detecting, capturing, selecting, and / or storing.

[0031] Optionally, the proposed method may provide that the following steps are only performed if a distance between an absolute position of the vehicle and a waypoint of the trajectory is smaller than a preset minimum distance: the above-described selection of the surrounding positions and the above-described determination of the relative position. Thus, for example, executing the vehicle in unnecessary situations can be avoided, which can, for example, save energy and / or computing power. The proposed method preferably includes: determining the absolute position of the vehicle.

[0032] Optionally, the proposed method may also include following the trajectory in a recording direction of the trajectory or against the recording direction of the trajectory based on the determined relative position of the vehicle. Thus, the proposed method can, for example, partially / autonomously park or exit the vehicle.

[0033] Optionally, the proposed method may additionally include a recording mode, which may also be called a training mode, and a tracking mode. In the recording mode, a vehicle position, as well as radar-based and / or image-based environmental positions, are preferably repeatedly recorded and stored in a trajectory. In the tracking mode, the described steps of the proposed method are preferably executed. This allows, for example, the trajectory to be obtained.

[0034] The trajectory may be part of a digital map. The recording module may be in VSLAM mode.

[0035] In a further development, the method, or even the tracking mode of the method, may repeatedly detect a vehicle position, as well as radar-based and / or image-based environmental positions, and store them in the provided trajectory. Thus, the provided trajectory can be refined, updated, and / or refined.

[0036] Optionally, the procedure may only be started and / or executed if a

[0037] The vehicle speed does not exceed a threshold. The threshold can be up to 55 km / h, for example, and preferably up to 35 km / h. This allows the process to be easily restricted to typical parking and exiting scenarios, for example.

[0038] Optionally, the procedure can be initiated and / or executed only upon user input. This can, for example, help achieve high acceptance.

[0039] One could say that it is proposed to use radar information to reduce, for example, dependence on lighting conditions. Thus, in cases where, for example, offering a parking assistance function would be prevented by deviating lighting conditions, radar-based positioning can be used to locate the vehicle in an environment.

[0040] Radar is naturally invariant to lighting and weather conditions. Therefore, it may be advantageous to determine a relative position of the vehicle based on currently determined point cloud information from a radar system and map information and / or point cloud information during a recording run, in particular from the radar system during the recording run.

[0041] It can be said that a radar can thus be used as an additional or independent source of information to an SVS to determine a relative position of the vehicle.

[0042] It can be said that during tracking, the determination of the relative position based on an SVS can be improved using radar data if a position determination using SVS is judged to be unreliable due to lighting conditions, shadows or the like.

[0043] One advantage of the proposed method can be that a relative position can be determined using radar signals while approaching a trajectory. For example, a match between point cloud information in a map and / or trajectory and currently acquired point cloud information can be determined. For this purpose, feature matching can be used. For example, a position determination can start with a rough or imprecise position and become more precise or accurate. For example, a search window approach can be used, whereby, in particular, the search window size can be varied.

[0044] It can be said that combining a VS with radar information results in an improvement in performance.

[0045] Furthermore, a computer program product for operating a parking assistance system is proposed, which comprises instructions which, when the program is executed by a computer, cause the computer to carry out the above-described, proposed method for operating a parking assistance system for a vehicle.

[0046] A computer program product, such as a computer program means, can be provided or delivered, for example, as a storage medium, such as a memory card, USB stick, CD-ROM, DVD, or in the form of a downloadable file from a server in a network. This can be done, for example, in a wireless communications network by transmitting a corresponding file with the computer program product or the computer program means.

[0047] According to a next aspect of the invention, a control device for a vehicle is proposed. The proposed control device is configured to execute the proposed method for operating a parking assistance system and / or the proposed computer program product for operating a parking assistance system. The embodiments and features described for the proposed method apply accordingly to the proposed control device. The proposed control device is preferably a parking assistance system or part of a parking assistance system. The parking assistance system is configured, in particular, for semi-autonomous or fully autonomous driving of the vehicle. Semi-autonomous driving is understood, for example, to mean that the parking assistance system controls a steering device and / or an automatic gearshift.Fully autonomous driving means, for example, that the parking assistance system also controls a drive system and a braking system.

[0048] The proposed control device may, for example, contain a computing unit, such as a computer, configured to execute the steps of the method. The proposed control device may, for example, contain a radar sensor and / or an interface for exchanging data with a radar sensor. The proposed control device may, for example, contain an image sensor, such as a camera, and / or an interface for exchanging data with an image sensor.

[0049] According to a next aspect of the invention, a vehicle is proposed that includes a proposed control device. The embodiments and features described for the proposed method and / or the proposed control device apply accordingly to the proposed vehicle.

[0050] The vehicle is, for example, a passenger car or a truck. The vehicle preferably has a number of sensor units configured to detect the driving state of the vehicle and to detect the vehicle's surroundings. Examples of such sensor units of the vehicle are image recording devices such as a camera, a radar (radio detection and ranging) or a lidar (light detection and ranging), ultrasonic sensors, location sensors, wheel angle sensors, and / or wheel speed sensors. The sensor units are each configured to output a sensor signal, for example, to the parking assistance system or driver assistance system, which performs semi-autonomous or fully autonomous driving depending on the detected sensor signals.Further possible implementations of the invention also include combinations of features or embodiments described above or below with respect to the exemplary embodiments that are not explicitly mentioned. In this case, the person skilled in the art will also add individual aspects as improvements or additions to the respective basic form of the invention.

[0051] Further advantageous embodiments and aspects of the invention are the subject of the dependent claims and the exemplary embodiments of the invention described below. The invention will be explained in more detail below using preferred embodiments with reference to the accompanying figures.

[0052] Fig. 1 shows schematically in a plan view a proposed vehicle containing a proposed control device configured to carry out a proposed method for operating a parking assistance system for the vehicle, according to an embodiment of the invention;

[0053] Fig. 2 shows a schematic plan view of a training drive of a vehicle for training a trajectory for parking in a parking space within a recording mode of the proposed method;

[0054] Fig. 3 shows schematically in a plan view a tracking of the trained trajectory according to the proposed method for operating a parking assistance system for the vehicle according to the embodiment of the invention;

[0055] Fig. 4 schematically shows, in a top view, an approach of the vehicle to a starting point of the trained trajectory according to the proposed method for operating a parking assistance system for the vehicle according to the embodiment of the invention; and Fig. 5 schematically shows a flowchart of the proposed method for operating a parking assistance system for the vehicle according to the embodiment of the invention.

[0056] In the figures, identical or functionally equivalent elements have been given the same reference numerals unless otherwise stated.

[0057] Fig. 1 shows a schematic view of a vehicle 100 from a bird's eye view. The vehicle 100 is, for example, a car arranged in an environment 150. The car 100 has a parking assistance system 110, which is designed, for example, as a control device. In addition, a plurality of environmental sensor devices 120, 130 are arranged on the car 100, which are, for example, camera sensors 120 and radar sensors 130. The camera sensors 120 comprise, for example, visual cameras. The camera sensors 120 can each capture an image of a respective area from the environment 200 of the car 100 and output it as an optical sensor signal. The radar sensors 130 are configured to capture a radar echo from objects arranged in the environment 150 and to output a corresponding radar echo signal.Using the sensor signals detected by sensors 120, 130, parking assistance system 110 is capable of driving vehicle 100 semi-autonomously or fully autonomously. In addition to the camera sensors 120 and radar sensors 130 shown in Fig. 1, vehicle 100 may be provided with various additional sensor devices 120, 130. Examples include a microphone, an acceleration sensor, an antenna with a coupled receiver for receiving electromagnetically transmittable data signals, and the like.

[0058] A proposed method M for operating the parking assistance system 110 for the vehicle 100 is explained below using the flowchart in Fig. 5 and the top view in Fig. 2. The method M is preferably computer-implemented. The method M takes the form of a computer program product that can be executed by the parking assistance system 110. The method M is started, for example, upon user input.

[0059] In step S10, a check is made to determine whether the vehicle speed exceeds a threshold. The threshold is, for example, 35 km / h. If the vehicle is traveling 100 km / h too fast, the method is terminated.

[0060] In step S12, a recording mode is executed. The recording mode comprises, for example, steps S14 to S22 and is illustrated in Fig. 2. The recording mode is started, for example, upon user input. The vehicle 100 travels along a route 140 in the environment 150 from a starting position 142 to a destination position 144. The environment 150 is, for example, a parking area with a driveway and at least one parking space.

[0061] In a step S14, a position of the vehicle 100 is repeatedly detected.

[0062] In a step S16, radar-based environmental positions 160 are repeatedly detected using the radar sensors 130. The detected environmental positions 160 are treated as points in a three-dimensional point cloud.

[0063] For example, environmental features 155 are detected in radar echo signals and their position is determined to obtain the environmental positions 160.

[0064] In a step S18, image-based environmental positions 170, including an image acquisition value and weather information, are repeatedly acquired by the camera sensors 120. For example, an overall brightness of the respective received image from the respective camera sensor 120 is used as the image acquisition value. The acquired environmental positions 170 are also treated as points in the same three-dimensional point cloud. In a step S22, the acquired positions in the form of waypoint positions 180, the acquired environmental positions 170, 160, as well as the acquired image acquisition values ​​and the acquired weather information, are stored in a trajectory 190. The trajectory 190 preferably takes the form of a trajectory data set, which is readable, for example, by the parking assistance system 110.

[0065] In step S26, a tracking mode is executed. Tracking mode S26 comprises, for example, steps S28 to S56. Tracking mode S26 is initiated, for example, upon user input.

[0066] In a step S28, the trajectory 190 is provided, which indicates the waypoint positions 180 and the surrounding positions 160, 170 along a route

[0067] In step S30, it is determined whether the distance between an absolute position of the vehicle 100 and a waypoint position 180 is less than a preset minimum distance. The minimum distance is, for example, 10 meters. If the vehicle 100 is farther than the minimum distance from the trajectory 190, the method M is terminated, for example.

[0068] In a step S32, at least one image-based environmental position 175 is acquired, including at least one image acquisition value and weather information. The image acquisition value is of the same type as the image acquisition values ​​contained in the trajectory. The environmental positions 175 are treated as points in a three-dimensional point cloud.

[0069] In a step S34, at least one of the image-based environmental positions 175 is selected if this image-based environmental position 175 satisfies a positioning requirement. In a step S36, a positioning requirement for the image-based environmental positions 175 is checked, namely, for example, whether there is a minimum match between a relative arrangement of the image-based environmental positions 175 and a relative arrangement of the 160, 170 of the trajectory 190.

[0070] In a step S38, a position determination request for the image-based environmental positions 175 is checked, namely, for example, whether an image recording value of the image-based environmental positions 175 and an image recording value of the environmental positions 170 of the trajectory 190 correspond to each other

[0071] In a step S40, a position determination request for the image-based environmental positions 175 is checked, namely, for example, whether weather information of the image-based environmental positions 175 and weather information of the environmental positions 170 of the trajectory 190 correspond to each other

[0072] In a step S42, a position determination request for the image-based environmental positions 175 is checked, namely, for example, whether the image-based environmental positions 175 are further than a preset maximum distance from the own vehicle 100.

[0073] If the image-based environmental positions 175 satisfy or correspond to the position determination requirements, detecting radar-based environmental positions is not required to determine a relative position of the vehicle 100. Therefore, the method M continues with a position determination in a step S52. Otherwise, the method M continues with a step S46 to detect radar-based environmental positions 165. This decision as to whether radar-based environmental positions 165 should be detected or whether the position should be based on the image-based environmental positions 175 is made in a step S44. Step S44 thus causes a radar-based environmental position 165 not to be selected if the at least one image-based environmental position 175 is selected.If step S44 is omitted, the position determination can be carried out on the basis of radar-based environmental positions 165 and image-based environmental positions 175.

[0074] In step S46, at least one radar-based environmental position 165 is detected.

[0075] In a step S48, at least one of the radar-based environmental positions 165 is selected if this radar-based environmental position 165 satisfies a position determination requirement.

[0076] In a step S50, a position determination requirement for the radar-based environmental positions is checked, namely, for example, whether there is a minimum agreement between a relative arrangement of the radar-based environmental positions 165 and a relative arrangement of the environmental positions 160, 170 of the trajectory 190.

[0077] In a step S52, a position 200 of the vehicle 100 relative to the environment 150 is determined by comparing the selected environment positions 165, 175 with the environment positions 160, 170 of the trajectory 190. Thus, the relative position 200 of the vehicle 100 is determined. Using this method, the relative position can have an accuracy of less than 50 cm, often less than 20 cm. In comparison, the absolute position based on a satellite signal typically has an accuracy of over 1 m. The relative position 200 determined using the proposed method is therefore significantly more accurate than the absolute position.

[0078] In a step S54, the vehicle 100, under the control of the parking assistance system 110, autonomously follows the trajectory 190 in the recording direction based on the determined relative position 200 of the vehicle 100.

[0079] In a step S56, the relative position 200 of the vehicle 100, the at least one acquired radar-based environmental position(s) 165, and the at least one acquired image-based environmental position(s) 175 are stored in the trajectory 190. Preferably, the image acquisition value(s) acquired in step S32 and / or the weather information acquired in step S32 are also stored in association with the image-based environmental position(s) 175.

[0080] If the image-based environmental positions 175 were discarded in steps S34, S38, S40, and S44 due to different image acquisition values ​​and / or due to different weather information, these image-based environmental positions 175 are preferably stored in the trajectory 190 in step S56. Thus, image-based environmental positions 170, 175 are subsequently present in the trajectory 190, to which different image acquisition values ​​and / or weather information are assigned. Therefore, the next time method M is executed, a known image acquisition situation can be encountered with a higher probability, making it more likely that the vehicle can navigate precisely based on a comparison with the image-based environmental positions 170, 175 then contained in the trajectory 190.

[0081] Fig. 3 shows an advantageous application of method M in a situation in which the vehicle 100 is approaching the trajectory 190 laterally. Fig. 3 shows the situation in which the parking assistance system 110, in step S52, first determines the relative position 200 based on a comparison of the selected surrounding positions 165, 175 with the surrounding positions 160, 170 of the trajectory 190. Subsequently, a trajectory 192 is determined for this journey in order to reliably travel from the current relative position 200 to the target position 146 of the provided trajectory 190 in step S54.

[0082] Fig. 4 shows a further advantageous application of method M in a situation in which vehicle 100 is approaching trajectory 190 from a great distance. Vehicle 100 has not yet reached starting position 142 of the provided trajectory 190, but is, for example, still several meters behind starting position 142. In steps S34 to S44, it is assessed that the currently acquired image-based environmental positions 175 do not meet the positioning requirements. Furthermore, in steps S48 and S50, it is assessed that the currently acquired radar-based environmental positions 165 already meet the positioning requirements despite the great distance from trajectory 190. Subsequently, in step S52, the current relative position 200 is determined with high accuracy.Then, in step S54, the vehicle 100 travels autonomously under the control of the parking assistance system 110 along the provided trajectory 190 to the target position 144. Although the present invention has been described using exemplary embodiments, it can be modified in many ways.

[0083] LIST OF REFERENCE SYMBOLS

[0084] 100 vehicles

[0085] 110 Control device

[0086] 120 camera sensor

[0087] 130 radar sensor

[0088] 140 route

[0089] 142 starting position

[0090] 144 Target position

[0091] 150 surroundings

[0092] 155 Environmental feature

[0093] 160 Radar-based environmental position of the trajectory

[0094] 165 recorded radar-based environmental positions

[0095] 170 Image-based environmental position of the trajectory

[0096] 175 captured image-based environmental positions

[0097] 180 Waypoint position

[0098] 190 Trajectory

[0099] 200 relative position of the vehicle

[0100] M Method for operating a parking assistance system for a vehicle

[0101] S10 Check whether a vehicle speed does not exceed a threshold

[0102] S12 Executing a recording mode

[0103] S14 Repeated detection of a vehicle position

[0104] S16 Repeated acquisition of radar-based environmental positions

[0105] S18 Repeated acquisition of image-based environmental positions including a

[0106] Image capture value and weather information

[0107] S22 Saving the recorded positions in the form of waypoints, the recorded surrounding positions, the recorded image values ​​and the recorded weather information in a trajectory

[0108] S26 Executing a tracking mode S28 Providing a trajectory that indicates waypoint positions and surrounding positions along a route

[0109] S30 Detect whether a distance of the absolute position of the vehicle to a waypoint is less than a preset minimum distance

[0110] S32 Detecting at least one image-based environmental position including an image capture value and weather information

[0111] S34 Selecting at least one of the image-based environmental positions if this image-based environmental position satisfies a positioning requirement

[0112] S36 Checking a positioning request for the image-based environmental positions to determine whether there is a minimum match between a relative arrangement of the image-based environmental positions and a relative arrangement of the environmental positions of the trajectory

[0113] S38 Checking a positioning request for the image-based environmental positions, whether an image acquisition value of the image-based environmental positions and an image acquisition value of the environmental positions of the trajectory correspond to each other

[0114] S40 Checking a positioning request for the image-based environmental positions, whether weather information of the image-based environmental positions and weather information of the environmental positions of the trajectory correspond to each other

[0115] S42 Checking a positioning request for the image-based environmental positions, whether the image-based environmental positions are at most a preset maximum distance from the own vehicle

[0116] S44 Non-selection of a radar-based environment position is not selected if at least one image-based environment position is selected

[0117] S46 Detecting at least one radar-based environmental position

[0118] S48 Selecting at least one of the radar-based environmental positions if this radar-based environmental position satisfies a position determination requirement S50 Checking a position determination requirement for the radar-based environmental positions to determine whether there is a minimum agreement between a relative arrangement of the radar-based environmental positions and a relative arrangement of the environmental positions of the trajectory S52 Determining a position of the vehicle relative to an environment by comparing the selected environmental positions with the environmental positions of the trajectory

[0119] S54 Tracing the trajectory in the recording direction or against the recording direction based on the determined relative position of the vehicle S56 Storing the position of the vehicle, the at least one detected radar-based environmental position and / or the at least one detected image-based environmental position in the trajectory

Claims

PATENT CLAIMS 1 . Method (M) for operating a parking assistance system (110) for a vehicle (100), comprising: Providing (S28) a trajectory (190) indicating at least one waypoint position (180) and at least one environmental position (160, 170) along a route (140), wherein an environmental position (160, 165, 170, 175) is a position of an environmental feature (155); detecting (S32, S46) at least one image-based environmental position (175), which is a position of an environmental feature detected on the basis of an image signal, and at least one radar-based environmental position (165), which is a position of an environmental feature detected on the basis of a radar echo signal; Selecting (S34, S36, S38, S40, S42) the image-based environmental position (175) or at least one of the image-based environmental positions (175) if this image-based environmental position (175) satisfies a position determination requirement; Selecting (S48, S50) the radar-based environmental position (165) or at least one of the radar-based environmental positions (165) if this radar-based environmental position (165) satisfies a position determination requirement; and Determining (S52) a position (200) of the vehicle (100) relative to an environment (150) by comparing the at least one selected environment position (165, 175) with the at least one environment position (160, 170) of the trajectory (190).

2. The method according to claim 1, characterized in that at least one radar-based environmental position (165) is not selected if the at least one image-based environmental position (175) is selected.

3. A method according to claim 1 or 2, characterized in that the method (M) comprises: Checking (S50) as the positioning request or one of the positioning requests for the radar-based environmental positions (165) whether a Minimum agreement exists between a relative arrangement of the radar-based environmental positions (165) and a relative arrangement of the environmental positions (160) of the trajectory (190), and / or Checking (S36) as the position determination request or one of the position determination requests for the image-based environmental positions (175) whether there is a minimum agreement between a relative arrangement of the image-based environmental positions (175) and a relative arrangement of the environmental positions (170) of the trajectory (190).

4. Method according to one of the preceding claims, characterized in that the method (M) comprises: Checking (S38) as the position determination request or one of the position determination requests for the image-based environmental positions (175) whether an image recording value of the image-based environmental positions (175) and an image recording value of the environmental positions (170) of the trajectory (190) correspond to one another, wherein the image recording value is indicative of a brightness, a contrast, a time of day and / or a season.

5. Method according to one of the preceding claims, characterized in that the method (M) comprises: Checking (S40) as the positioning request or one of the positioning requests for the image-based environmental positions (175) whether weather information of the image-based environmental positions (175) and weather information of the environmental positions (170) of the trajectory (190) correspond to each other.

6. Method according to one of the preceding claims, characterized in that the method (M) comprises: Checking (S42) as the positioning request or one of the positioning requests for the image-based environmental positions (175) whether the respective image-based environmental position (175) is at most a preset maximum distance from the own vehicle (100).

7. Method according to one of the preceding claims, wherein the surrounding positions (160, 165, 170, 175) are treated as points of a two-dimensional or preferably three-dimensional point cloud.

8. Method according to one of the preceding claims, comprising: carrying out at least the following steps (S34, S48, S50) if a distance of an absolute position of the vehicle (100) to a waypoint position (180) is smaller than a minimum distance: selecting (S34, S48) the surrounding positions (165, 175) and determining the relative position (200).

9. Method according to one of the preceding claims, comprising: following (S54) the trajectory (190) in the recording direction or against the recording direction on the basis of the determined relative position (200) of the vehicle (100).

10. The method according to one of the preceding claims, comprising: a recording mode (S12), wherein a position of the vehicle (100), as well as radar-based and / or image-based environmental positions (160, 170) are repeatedly recorded (S14, S16, S18) and stored in the trajectory (S22); and a tracking mode (S26), wherein the method (M) according to one of the preceding claims is carried out in the tracking mode (S26).

11. Method according to one of the preceding claims, wherein the determined relative position (200) of the vehicle (100), the at least one detected radar-based environmental position (165) and / or the at least one detected image-based environmental position (175) are stored in the trajectory (190).

12. The method according to any one of the preceding claims, wherein the method (M) is only executed if a vehicle speed does not exceed a threshold value.

13. A computer program product comprising instructions which, when executed by a computer, cause the computer to execute the method (M) according to any one of claims 1-12.

14. Parking assistance system (110) for a vehicle (100), which is configured to carry out the method (M) according to one of claims 1 - 12.

15. Vehicle (100) comprising a parking assistance system (110) according to claim 14.

Images