DE102019110239A1 - Driving assistance method for a vehicle - Google Patents

Abstract

The present invention relates to a driving assistance method for a vehicle, comprising the method steps:
a) performing a detection of the surroundings of a vehicle (10) during a driving process with at least one surroundings detection sensor (16) with detection of objects (12) located in the surroundings of the vehicle (10) using object features located on the objects (12);
b) generating a representation of the surroundings of the vehicle (10) on the basis of the objects (12) and storing the representation, the representation having at least in part the objects (12) detected in method step a) and their object features;
c) Carrying out driving assistance for the automatic or semi-automatic driving of the vehicle (10) in or adjacent to the surroundings detected in method step a) using the representation generated and stored in method step b); in which
d) In method step a), objects (12) in the vicinity are detected with partial use of object identifications (24) located on the objects (12).

Description

The present invention relates to a driving support method for a vehicle. The present invention relates in particular to a method in which improved recognition, in particular of static objects in the vehicle environment, is made possible. The present invention also relates to a driving assistance system which can at least partially carry out such a method.

A variety of driving assistance systems, such as partially or fully automated systems, are known per se. For example, such systems are used for parking. In particular, systems of this type are known which enable or improve automated driving, such as automated parking, in that in a first learning step the 3D geometry of the static objects in the vicinity of the parking route is recorded and stored in the form of a 3D map, and in a second, later execution step, the information required for automated driving is generated by comparing this 3D map with the actual 3D environment. The mapping is usually based on object features, also known as 'features', which are distinctive points or positions that are present on the surface of objects that can be recognized by the sensor system used and recognized as reliably and precisely as possible in the execution step.

DE 10 2004 047 130 B4 describes a method for orientation in a dynamically changing environment for autonomous mobile systems such as robots, self-steering vehicles, etc., whereby data about existing environmental elements such as objects and free areas are recorded via sensors to record and model the dynamically changing environment while driving and are used to generate or update a digital environmental model, with identified environmental elements being classified according to predetermined criteria and added to the generated environmental model with appropriately assigned attributes, with free areas of the surroundings being classified according to location and dimensions to what extent they are used as a route for the mobile systems are potentially usable, whereby for route planning the identified environmental elements with previously collected empirical values or statistical expected values with regard to the duration of their local whereabouts are added to the digital environmental model hi be added.

DE 10 2010 023 162 A1 describes a method for supporting a driver of a motor vehicle when parking in a parking space, in particular in a garage, with the aid of a driver assistance device of the motor vehicle, wherein: - in a learning mode of the driver assistance device, reference data about an area around the driver assistance device are recorded and stored while the motor vehicle is being driven through the Driver-controlled is parked in the parking space, - a reference target position, which is reached in the learning mode by the motor vehicle, is recorded by the driver assistance device and data with information about this reference target position is stored, - in a subsequent operating mode of the driver assistance device different from the learning mode by the sensor data Sensor device can be detected and compared with the reference data, the surrounding area of the parking space being detected based on the detected sensor data and as a result of this, depending on this comparison a current position of the motor vehicle is determined relative to the reference target position and - depending on the current position of the motor vehicle relative to the reference target position, a parking path is determined by the driver assistance device along which the motor vehicle is parked from the current position into the parking space.

DE 10 2016 100 235 A1 describes a method for recurring parking of a vehicle in a parking area, in which during a first parking in the parking area information about the surroundings of the parking area is recorded with a detection device of the vehicle, with the information about the surroundings being displayed on a display unit during the first parking, whereby a vehicle user selects the the displayed environment information selects at least one object from a first object category as the environment information characterizing the parking area and / or selects from the displayed environment information at least one object from an environment information that is different from the first second object category as the parking area, the selected objects being stored and dependent on recurring parking of selected and stored objects, a currently recorded parking area is recognized as the parking area when parking for the first time.

DE 10 2015 203 016 A1 describes a method for localizing a motor vehicle in an environment, comprising the following steps: in a first method section, executing a learning drive which comprises: receiving odometry data from the motor vehicle via an interface of a camera, capturing at least two images with the camera while driving on different ones Positions of the motor vehicle, extraction of features in the at least two images, finding pairs of identical features in the at least two images, Stereoscopic determination of a three-dimensional position of the features using the odometry data, creating a three-dimensional map and entering the features at their three-dimensional positions, then, in one or more second process sections, executing a follow-up trip, which includes: capturing at least one further image with the camera , Determination of several features in the at least one further map, determination of relative orientations of the several features to the motor vehicle based on the mapping position, finding the multiple features in the map, triangulation based on the features and the relative orientations and inferring localization information of the motor vehicle in the map, output the localization information at the interface, with all process steps of the two process sections being carried out in the camera.

Such solutions known from the prior art can offer further potential for improvement, in particular with regard to robust and precise detection and recognition of objects.

It is the object of the present invention to at least partially overcome the disadvantages known from the prior art. It is in particular the object of the present invention to provide a solution by means of which recognition and recognition of objects can be improved.

The object is achieved according to the invention by a method with the features of claim 1. The object is also achieved according to the invention by a driving support system with the features of claim 15. Preferred embodiments of the invention are described in the subclaims, in the description or the figures, further features described or shown in the dependent claims or in the description or the figures, individually or in any combination, may constitute an object of the invention if the context does not clearly indicate the contrary.

1. a) Durchführen einer Erfassung der Umgebung eines Fahrzeugs während eines Fahrvorgangs mit wenigstens einem Umfelderfassungssensor unter Detektion von in der Umgebung des Fahrzeugs befindlicher Objekte unter Verwendung von an den Objekten befindlicher Objektmerkmale;
2. b) Generieren einer Repräsentation der Umgebung des Fahrzeugs auf Basis der Objekte und Speichern der Repräsentation, wobei die Repräsentation zumindest zum Teil die in Verfahrensschritt a) erfassten Objekte und deren Objektmerkmale aufweist;
3. c) Durchführen einer Fahrunterstützung zum automatischen oder teilautomatischen Fahren des Fahrzeugs in oder benachbart zu der in Verfahrensschritt a) erfassten Umgebung unter Nutzung der in Verfahrensschritt b) generierten und gespeicherten Repräsentation; wobei
4. d) bei Verfahrensschritt a) eine Detektion von in der Umgebung befindlicher Objekte erfolgt unter teilweiser Verwendung von an den Objekten befindlichen Objektkennzeichnungen.

A driving assistance method for a vehicle is proposed, having the following method steps:

1. a) performing a detection of the surroundings of a vehicle during a driving process with at least one surroundings detection sensor with detection of objects located in the surroundings of the vehicle using object features located on the objects;
2. b) generating a representation of the surroundings of the vehicle on the basis of the objects and storing the representation, the representation having at least in part the objects detected in method step a) and their object features;
3. c) Carrying out driving assistance for automatic or semi-automatic driving of the vehicle in or adjacent to the environment recorded in method step a) using the representation generated and stored in method step b); in which
4. d) In method step a), objects located in the vicinity are detected with partial use of object identifiers located on the objects.

A method described above can in a particularly advantageous manner improve the detection of objects located in the vicinity of the vehicle and thus provide an improved driving assistance method.

The present invention thus relates to a driving assistance method, in particular for driving a vehicle through a vehicle environment using a driving assistance system. Driving assistance and the method described here can relate to completely autonomous driving, so the method can be designed for driving the vehicle without a driving intervention by a driver. Alternatively, it is possible that the method is only used to support the driver while driving, that is to say, for example, to output driving instructions or to take over certain driving interventions, but the driver must carry out certain driving interventions himself.

The method can thus be carried out at least partially by a driving assistance system which is part of the vehicle. In particular, the vehicle can be a motor vehicle.

In order to carry out the method, the method described here has the following method steps, the method steps described below basically being able to run in the described order chronologically or in an at least partially different order if this is not clearly excluded from the context.

First of all, according to method step, the described method includes a) performing a detection of the surroundings of a vehicle during a driving process with at least one surroundings detection sensor with detection of in the Objects located in the vicinity of the vehicle using object features located on the objects.

This step can in principle be known for driving assistance systems, for example, in order to observe the surroundings of the vehicle and detect objects. In principle, this step can also be carried out by means of environment detection sensors known per se, which can be part of the driving support system. Method step a) can preferably be carried out using at least one or a plurality of surroundings detection sensors which is selected or which are selected from the group consisting of ultrasonic sensors, infrared sensors, radar-based sensors, LIDARs, or cameras. Such environment detection sensors are widely known and can enable the environment to be monitored in a safe and effective manner, with corresponding objects being able to be detected.

Method step a) can take place continuously during a driving process, for example in the case of autonomous driving, or can be triggered by a specific event, be it automated or manual. The event that can trigger method step a) can be, for example, the initiation or termination of a driving sequence which includes, for example, parking or maneuvering. For example, the driver of the vehicle can enter that a parking process should take place or it can be determined on the basis of navigation data, for example an entered destination and the current position, that a parking process should take place or has taken place due to the reaching of the destination, so a survey of the surroundings can start or continue. It should be noted, however, that the method described here is not intended to be limited to a parking process or parking process.

This method step a) thus allows in particular the acquisition of environmental data, wherein the environmental data can relate in particular to the position and type of objects in the vicinity of the vehicle, as is described in greater detail below. In this case, the detection of the objects can include, for example, object features referred to as features, which are positions or features of the objects that are sufficiently easily recognizable by the sensor or sensors used.

According to the further method step b), the method further comprises generating a representation of the surroundings of the vehicle on the basis of the objects, in particular the object features and, if applicable, the object identifications, and storing the representation, the representation being at least partially the objects recorded in method step a) and whose object features.

In this step, the objects detected, in particular on the basis of their object features, are thus combined to form a representation or map which represents or represents the surroundings of the vehicle. This map or representation is then stored in a memory, in particular of the driving assistance system. This allows the representation to be used in further steps.

Furthermore, the method according to method step c) comprises the implementation of driving assistance for the automatic or semi-automatic driving of the vehicle in or adjacent to the environment recorded in method step a) using the representation generated and stored in method step b).

Thus, according to this method step, driving assistance takes place which, as described above, can include the mere output of driving instructions but can also extend to fully autonomous driving of the vehicle. The driving assistance is used in particular to drive the vehicle in the vicinity or through the environment or adjacent to it, the detected objects being displayed and / or used in the map or representation to be used. Thus, the driving assistance can relate in particular to maintaining or changing the speed and direction of travel and thereby include, for example, steering interventions or speed interventions or also selective driving forwards or backwards. In other words, the driving assistance can include, in particular, following a trajectory.

It is further provided that in method step a) a detection of objects located in the environment takes place with partial use of object identifiers located on the objects. This step in particular can bring about significant advantages over the solutions known from the prior art.

Because according to this step, the object as such is not or not exclusively detected, but rather the object detection comprises the detection of one or more defined object identifications, which can also be referred to as object markings, for each of the objects.

An object identification is to be understood in particular as an additional feature of the surrounding objects, which is specifically provided on the object in order to improve its detectability. Accordingly, it can be part of the method to arrange such an object identifier or a plurality of such object identifiers on one or preferably on several objects and to train the driving support system with regard to these object identifications. This makes it possible for the driving assistance system to recognize the object identification and, if necessary, to assign it to a specific object. Thus, an object identification is not a mere feature of the object but rather an additional feature with which the object has been provided in order to improve the detectability.

In particular, an object identifier can be an optical configuration that is arranged on an object. Examples of object identifications include, for example, crosshairs or other shapes, in particular with good contrasts, in order to be able to ensure effective detectability even in poor visibility conditions.

Correspondingly, the object identification can be designed in such a way that it can be easily detected, for example, under normal conditions or also with comparatively poor visibility, or in particular to enable improved detectability compared to the bare object.

The method described here thus creates the advantage that a driving support system can enable improved detection of objects in the vicinity of the vehicle even under adverse conditions and thereby enables an improved representation of the environment.

As a result, driving assistance in this regard can be significantly improved. Because objects can be detected with increased security or with increased probability, a trajectory determined and used on the basis of the objects can be driven more safely, which can thus significantly reduce the risk of accidents. In addition, the basic generation of a trajectory can be improved, since with an increased probability there will always be a sufficient number of objects available to reliably plan the trajectory.

In particular, it can be particularly effectively possible that the detected objects are summarized in a map as described above or that a generated map is based on the detected objects. The generated map can be created much more precisely and reliably, which can significantly improve the driving assistance as described above.

In particular, driving assistance can be improved in complex situations or in complex environments, since trajectory planning also becomes more complex with an increasing number of objects, particularly in complex environments, for example in environments that have a large number of objects. Because the probability of correct detection of the objects increases using the method described here, a significant improvement can thus be made possible, particularly in such environments.

In principle, it can be provided that only individual objects, a number of objects to be determined, or all objects in the vicinity of the vehicle and in particular in a specific vehicle environment of any extent, such as in the home environment, with one or a plurality of the corresponding object identification are provided. The objects to be determined with regard to an object identification to be attached can be selected manually by the driver, for example, or the driving support system can select such objects to be determined and provide the driver with appropriate information, as will be described below. This can take place, for example, in a learning drive in which the position of object identifications is determined, the learning drive taking place before method step a).

It can be preferred that the method takes place in the context of a learning driving assistance method. A learning driving assistance method is to be understood in particular as such a method in which a vehicle drives through an environment, stores sensor data, and driving assistance takes place based on the stored data. In this embodiment, the method can thus be used in particular when the same surroundings are often traveled or when the vehicle often drives repetitive routes.

The method described here can have advantages in particular in the case of learning systems. This is because a system can be used that is used to drive a vehicle even in complex situations and in which, for example, a driver of the vehicle carries out a driving maneuver or driving around an environment or a trajectory once or several times in the sense of a learning drive and the system automatically stores the trajectory and objects surrounding it and based on this a sensor-generated map of the environment. The system can then offer driving assistance based on the stored data when driving through this environment again, for example as “trained driving”, for example as “trained parking”.

The maps created in this way are based on sensor data from objects that are in the vicinity of the vehicle. With a sufficient detection of objects, such a method can run safely and reliably. If, however, not enough objects are detected that are stored with high quality and reliably and then used, such learning methods can still have potential for improvement, which can be filled by a method according to the invention. Because, as described above, the detectability of objects can be significantly improved by the method described, which can thus also significantly improve learning systems.

• e) Auswerten der Objektmerkmale der Objekte mit Bezug auf wenigstens eines von deren Detektierbarkeit, Anzahl und Position; und gegebenenfalls f) basierend auf der Auswertung gemäß Verfahrensschritt e), Ausgeben von Information über wenigstens ein mit wenigstens einer Objektkennzeichnung zu versehenes Objekt.

In particular with regard to the learning process, it may be possible in detail for the process to have the further process steps:

• e) evaluating the object features of the objects with reference to at least one of their detectability, number and position; and optionally f) based on the evaluation according to method step e), outputting information about at least one object to be provided with at least one object identifier.

• g) Durchführen einer Umfelderfassung der Umgebung des Fahrzeugs mit wenigstens einem Umfelderfassungssensor unter Detektion von in der Umgebung befindlichen Objekten.

Process step e) can be carried out in particular during process step a) or, if process step a) takes place after teaching, before process step a). In this case of learning, provision can be made for the further step to be provided before method step e) and in particular before method step a):

• g) Carrying out a surroundings detection of the surroundings of the vehicle with at least one surroundings detection sensor with detection of objects in the surroundings.

Thus, in this embodiment it can be made possible that based on detected objects the driving support system examines the detected objects with regard to at least one of their detectability, number and position, possibly all of the detectability, number and position. Based on the result of this examination, it can be indicated according to method step f) whether and where or on which objects and possibly further object identifications can be advantageous in order to improve the effectiveness of the object recognition. For example, if a large number of objects can be easily detected in a first local area in an environment or a large number of object identifications are already available, but fewer objects can be easily detected in a second local area or there is no large number of object identifications, it can be proposed that in object markings can be retrofitted in the second local area. A detectability can be determined by examining whether objects are always detected or are detected with a high probability when a trajectory is traveled several times. Furthermore, it can be investigated whether corresponding stored objects can be detected even in poor visibility conditions.

The same can be done, for example, if a complex trajectory is to be followed due to the large number of objects that are basically present, but only a limited number of object markings is present. In this case, too, it can be proposed that object markings, for example, be retrofitted on particularly relevant objects in order to obtain a more precise map or to be able to plan and follow the trajectory more reliably.

The display of whether and where or on which objects further object identifications can be advantageous in order to improve the effectiveness of the object recognition, for example using a head-up display or another display or screen of the vehicle or the driving support system to to enable good visibility for the driver. In other words, information about at least one object to be provided with at least one object identifier can be output at least partially through a screen located in the vehicle.

Furthermore, the display of whether and where or on which objects further object identifications can be advantageous in order to improve the effectiveness of the object recognition, or the output of information about an object to be provided with an object identification, for example, take place at least partially by sending a message to a mobile device of the driver, for example. For example, a message can be sent to a mobile phone and receive, for example, a picture or other information about which objects should still be provided with an object identifier. Sending can take place, for example, to a mobile device, in particular to a mobile phone or a tablet computer.

With regard to the information about the object to be provided with an object identifier, it can be provided, for example, that the information output includes one or more images or one or more videos. In principle and particularly effectively in this embodiment, the information can output in which areas of which objects in which environment one or more object identifications are advantageous and should be attached so that the function of the method in this environment is improved or even possible in the first place.

Finally, provision can be made for a link to an online shop to be displayed or transmitted together with a suggestion for a position for an object identifier and, if necessary, a color design, in which such optically suitable object identifiers are advertised, for example by means of a video, and also acquired there directly can be, for example by means of an option to visually test the selected object identifications in the environment and / or by means of instructions for attaching the object identifications. In particular, the option can include differently designed and selectable object identifications.

It can thus be provided that, in addition to outputting information about at least one object to be provided with at least one object identifier, an option is displayed to order object identifications or to print out object identifications with 2D or 3D printing methods. The latter can be done by a service provider or even yourself by establishing a direct connection to a corresponding printer. It can be provided that the option includes differently designed and selectable object identifications.

It can furthermore be advantageous that the method is part of a parking assistance method or a maneuvering assistance method. Such methods or parking processes or maneuvering processes include numerous maneuvers, such as forward or reverse right-angled parking, forward or reverse parallel parking or herringbone parking or corresponding maneuvers and especially driving in confined spaces. The advantages described above can be implemented advantageously in particular with a parking assistance method or maneuvering assistance method, since, in particular with methods of this kind, such as parking at home or at a work place, a trajectory can often be traveled in the same environment and thus targeted objects with object identifications can be provided. Furthermore, a particularly effective learning of the method or the system can take place in this way.

It can further be provided that the object identifications are selected from the group consisting of stickers, signs or defined marking areas of the objects themselves, that is to say in particular defined color designs, in particular on the surface of the objects. In this refinement, it is particularly easy to apply the object identifications since, for example, stickers or signs can be attached particularly easily to corresponding positions on the objects. Furthermore, a defined marking area, that is to say for example a specific color design, can also be implemented in a simple and unproblematic manner at a specific position of the object or the objects.

In addition, a particularly adaptable implementation of the object identifications can take place in this embodiment, since the object identifications defined here can be designed in very different ways, so that they can easily allow a particularly effective interaction with the environment detection sensor and thus a particularly effective detectability. In particular, it can be provided that the object identifications are designed in such a way that they are, for example, decorative and not geared towards the mere detectability, so that an improved acceptance of the application of the object identifications can be made possible, or the object surface is not impaired too much, especially optically becomes. This can also be improved by the fact that the object identifications can in principle be offered in the most varied of configurations and designs, so that adaptivity with regard to the object surfaces to be used is possible without any problems.

It can also be provided that, for example by means of a camera and by examining the colors of the object, it is examined how an optically suitable object identification can look and that a corresponding proposal is made to the driver.

It can also be provided that the object identifications are adapted to the detection properties of the at least one surroundings detection sensor. In particular, it can be provided that the object identifications are adapted to the spectral properties of the surroundings detection sensor. For example, it can be provided that the object identifications have a high contrast in the infrared wavelength, for example, but less in the visible range Contrast or have a decorative appearance. This can increase customer acceptance, since the structure, which is tailor-made for detection but may not be attractive, is not or less clearly visible in the visible area. On the other hand, detectability for the corresponding surroundings detection sensors such as IR sensors can be further improved.

Furthermore, it can be preferred that, in method step b), prioritization takes place in such a way that any object identifications that may be present are taken into account with a higher priority compared to other object features. In this refinement, the recorded data is therefore evaluated to determine whether the recorded data is to be assigned to an object identifier or to another feature of the respective object. Since the object identifications, as stated above, can be detected and assigned with a high degree of efficiency and a high degree of security, the method can be particularly safe and effective by using the object identifications with a particularly high prioritization. In other words, if, for example, an object identifier indicates a certain object, but a further feature of the object excludes this, the presence of the object can nevertheless be assumed based on the detection of the object identifier.

Furthermore, it can be preferred that, in particular in method step a), the objects are classified into static and dynamic objects and that the prioritization of the object identifications only takes place for object identifications of static objects. In this embodiment, the reliability and the effectiveness of the method can be further improved. If, in particular, static objects are used for the detection, it can be particularly ensured that these are also present and detectable during the desired driving through the surroundings of the vehicle. In this way, objects can be detected in a particularly error-free and reliable manner, particularly in the case of a learning method. This refinement can take place regardless of whether the dynamic objects have object identifications or not.

In this context, static objects are to be understood, in a manner known per se, in particular to be understood as objects which do not move. Such objects include, for example, buildings or parts of buildings, trees, bushes, walls, etc. In contrast to this, dynamic objects are to be understood in particular as moving objects, for example cyclists, pedestrians and moving motor vehicles. For the purposes of this invention, dynamic objects are also to be understood as those that may be static at a certain point in time, but can basically move, such as parked vehicles, garbage cans, etc.

Among the reasons described above, it can also be advantageous that, in particular in method step a), the objects are classified into static and dynamic objects and that in method step b) object identifications are only considered from static objects.

• f) Auswerten der Detektierbarkeit der Objektkennzeichnungen.

Furthermore, it can be preferred that the method has the further method step:

• f) Evaluation of the detectability of the object identifications.

In this refinement, it can be made possible to react if, for example, object identifications that already exist or are arranged on objects have been damaged or have become difficult to detect. In this case, a message can in turn be output to the driver, which states that an object identifier should be renewed. A detectability can in turn be assessed based on a repetitive and possibly deviating detection, or based on the probability that a detected object marking is detected as such. In this regard, it is sufficiently known in the technical field that assignments of detected objects are carried out on a probability basis.

With regard to further advantages and features of the method, reference is made to the description of the driving assistance system, the figures and the description of the figures, and vice versa.

Furthermore, a driving support system for a vehicle is described, the driving support system having at least one surroundings detection sensor and a control unit which can be fed with data from the at least one surroundings detection sensor, the control unit also being designed to at least partially carry out a method as described above in Detail is described.

The driving assistance system can be part of a vehicle, such as a car. The driving assistance system can in particular be provided for generating environmental data as the basis for driving assistance, such as generating a driving trajectory, as described in detail above.

For an environment observation or environment detection, this shows Driving support system on at least one environment detection sensor. The at least one surroundings sensing sensor can be any suitable sensor known in the art, for example. Furthermore, only one or several different or identical sensors can be used to monitor the environment, which sensors form a sensor arrangement from one or more environment sensors. The at least one environment detection sensor can, for example, have or consist of one or more identical or different sensors selected from the group consisting of ultrasonic sensors, infrared sensors, radar-based sensors, LIDARs, cameras or other sensors that are known in the field for monitoring the environment .

A control unit such as a processor is also provided. The control unit is suitable for evaluating the sensor data supplied by the sensor or sensors and for acquiring, storing and retrieving environmental data and, if necessary, for classifying objects. Accordingly, there is a data connection between the at least one surroundings detection sensor and the control unit. In particular, the control unit has information by means of which object identifications can be recorded and classified as objects. For this purpose, the control unit can be provided with a corresponding computer program product which is designed to carry out the method described in detail above.

The driving assistance system described here can thus effectively and reliably improve the detection of objects in the vicinity of the vehicle and thereby improve driving assistance, for example in the sense of partially autonomous or autonomous driving.

With regard to further advantages and features of the driving assistance system, reference is made to the description of the method, the figure and the description of the figure, and vice versa.

• 1 eine schematische Darstellung darstellend eine Umgebung eines Fahrzeugs; und
• 2 eine schematische Darstellung zeigend ein Fahrzeug mit einem Fahrunterstützung ssystem.

Further advantages and advantageous configurations of the subject matter according to the invention are illustrated by the drawings and explained in the following description. It should be noted that the drawings are only of a descriptive nature and are not intended to restrict the invention in any way. Show it:

• 1 a schematic representation depicting an environment of a vehicle; and
• 2 a schematic representation showing a vehicle with a driving assistance system.

In the 1 is shown purely schematically an environment in which a vehicle 10 moves. In particular, the environment is that of the vehicle 10 is driven repeatedly.

It is also shown in front of the vehicle 10 an object 12 is provided, which is in particular a static object. In the design according to 1 is the object 12 a building.

The vehicle 10 further comprises a driving assistance system 14th like this in the 2 is shown in greater detail. The driving support system 14th comprises at least one surroundings detection sensor 16 and also a control unit 18th . The at least one environment detection sensor 16 may for example have or consist of one or more identical or different sensors selected from the group consisting of ultrasonic sensors, infrared sensors, radar-based sensors, LIDARs, cameras or other sensors known in the art for monitoring the environment.

The control unit 18th is by means of a data connection 20th with the surroundings detection sensor 16 connected and is thus data of the at least one environment detection sensor 16 edible. In particular, the surroundings detection sensor 16 Environment data to the control unit 18th send which the position and type in the area of the vehicle 10 objects located 12 include. The control unit 18th can save the environment data, for example, in the form of a map of the environment and thus, for example, travel trajectories for the vehicle 10 to plan.

Coming back to 1 it is also shown that the surroundings detection sensor 16 a detection area 22nd has, within which the object 12 is arranged. So the object is 12 basically by the surroundings detection sensor 16 detectable, for example using object features of the object 12 . About the detectability of the object 12 to improve it is also provided that on the object 12 an object identifier 24 is provided. In principle, it can be provided that on an object 12 only one or a plurality of object identifications 24 are provided.

1. a) Durchführen einer Erfassung der Umgebung eines Fahrzeugs 10 während eines Fahrvorgangs mit wenigstens einem Umfelderfassungssensor 16 unter Detektion von in der Umgebung des Fahrzeugs 10 befindlicher Objekte 12 anhand von an den Objekten 12 befindlicher Objektmerkmale;
2. b) Generierung einer Repräsentation der Umgebung des Fahrzeugs 10 auf Basis der Objektmerkmale und Speichern der Repräsentation, wobei die Repräsentation zumindest zum Teil die in Verfahrensschritt a) erfassten Objekte 12 und deren Objektmerkmale aufweist;
3. c) Durchführen einer Fahrunterstützung zum automatischen oder teilautomatischen Fahren des Fahrzeugs 10 in oder benachbart zu der in Verfahrensschritt a) erfassten Umgebung unter Nutzung der in Verfahrensschritt b) generierten und gespeicherten Repräsentation; wobei
4. d) bei Verfahrensschritt a) eine Detektion von in der Umgebung befindlicher Objekte 12 erfolgt unter teilweiser Verwendung von an den Objekten 12 befindlicher Objektkennzeichnungen 24.

A particularly good detectability of the object 12 to enable it is provided that the control unit 18th is designed to provide a driving assistance method, such as a Carrying out a parking assistance procedure, which comprises the following procedural steps:

1. a) Carrying out a detection of the surroundings of a vehicle 10 during a driving process with at least one surroundings detection sensor 16 with detection of in the vicinity of the vehicle 10 objects located 12 based on at the objects 12 located property features;
2. b) Generation of a representation of the surroundings of the vehicle 10 on the basis of the object features and storage of the representation, the representation at least partially being the objects recorded in method step a) 12 and has their object features;
3. c) Carrying out driving assistance for automatic or semi-automatic driving of the vehicle 10 in or adjacent to the environment recorded in method step a) using the representation generated and stored in method step b); in which
4. d) in method step a) a detection of objects in the vicinity 12 takes place with partial use of the objects 12 object labels located 24 .

• e) Auswerten der detektierten Objektmerkmale der Objekte 12 mit Bezug auf wenigstens eines von deren Detektierbarkeit, Anzahl und Position; und gegebenenfalls
• f) basierend auf der Auswertung gemäß Verfahrensschritt e), Ausgeben von Information über wenigstens ein mit wenigstens einer Objektkennzeichnung 24 zu versehendes Objekt.

As described above, the method can in particular be a learning method such that when driving through the surroundings it is determined whether there are specific objects 12 Object identifications 24 should be supplemented so that they can be supplemented or attached accordingly. In this regard, it can thus be provided that the method has the further method steps:

• e) Evaluation of the detected object features of the objects 12 with respect to at least one of their detectability, number and position; and if necessary
• f) based on the evaluation according to method step e), outputting information about at least one object with at least one object identifier 24 object to be provided.

Regarding the object identification 24 with which objects 12 if necessary, it can be provided that the object identifications 24 are selected from the group consisting of stickers, signs or defined marking areas of the object itself. Furthermore, it can be provided that the object identifications 24 the detection properties of the surroundings detection sensor 16 are adapted. For example, there can be a high contrast in a spectral range that corresponds to the detection radiation of the surroundings detection sensor 16 corresponds. In principle, such object identifications 24 have defined and easily detectable features in order to enable effective detectability.

Furthermore, it can in particular be provided that in method step b) a prioritization takes place in such a way that any object identifications are present 24 can be used with a higher priority compared to other object features. Thus, object identifications 24 for example, can be used with a higher priority than other identifications of the objects 12 , by means of which the objects 12 can be recognized or assigned. With regard to the prioritization, provision can also be made for the objects 12 can be classified into static and dynamic objects and that the prioritization of the object identifications 24 only for object identification 24 on static objects 12 he follows.

In addition, particularly reliable object recognition or trajectory planning can be made possible if, for example in method step a), the objects 12 be classified into static and dynamic objects and if in process step b) object identifications 24 only from static objects 12 to be viewed as. In this way it can be made possible, for example in a learning method, that only such objects 12 can be used for driving assistance, in particular for trajectory planning, in which it is ensured that they can actually be detected in a subsequent detection.

List of reference symbols

10

vehicle

12

object

14th

Driving support system

16

Environment detection sensor

18th

Control unit

20th

Data Connection

22nd

Detection area

24

Object identification

QUOTES INCLUDED IN THE DESCRIPTION

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

Patent literature cited

• DE 102004047130 B4 [0003]
• DE 102010023162 A1 [0004]
• DE 102016100235 A1 [0005]
• DE 102015203016 A1 [0006]

Claims (14)

Driving assistance method for a vehicle, comprising the procedural steps: a) performing a detection of the surroundings of a vehicle (10) during a driving process with at least one surroundings detection sensor (16) with detection of objects (12) located in the surroundings of the vehicle (10) using object features located on the objects (12); b) generating a representation of the surroundings of the vehicle (10) on the basis of the objects (12) and storing the representation, the representation having at least in part the objects (12) detected in method step a) and their object features; c) Carrying out driving assistance for the automatic or semi-automatic driving of the vehicle (10) in or adjacent to the surroundings detected in method step a) using the representation generated and stored in method step b); in which d) In method step a), objects (12) in the vicinity are detected with partial use of object identifications (24) located on the objects (12). Procedure according to Claim 1 , characterized in that the method takes place in the context of a learning driving assistance method. Procedure according to Claim 1 or 2 , characterized in that the method has the further method steps: e) evaluating the object features of the objects (12) with reference to at least one of their detectability, number and position; and optionally f) based on the evaluation according to method step e), outputting information about at least one object (12) to be provided with at least one object identifier (24). Procedure according to Claim 3 , characterized in that the output of information about at least one object (12) to be provided with at least one object identifier (24) takes place at least partially through a screen located in the vehicle (10). Method according to one of the Claims 3 or 4th characterized in that information about at least one object (12) to be provided with at least one object identifier (24) takes place at least partially by sending a message to a mobile device, in particular a mobile phone or a tablet computer. Method according to one of the Claims 3 to 5 , characterized in that the output of information about at least one object (12) to be provided with at least one object identifier (24) comprises at least partially that one or more images or one or more videos are output. Method according to one of the Claims 1 to 6 , characterized in that the method is part of a parking assistance method or a maneuvering assistance method. Method according to one of the Claims 1 to 7th , characterized in that, in addition to outputting information about at least one object (12) to be provided with at least one object identifier (24), an option is displayed to order object identifiers (24) or to print out object identifiers (24) using 2D or 3D printing processes . Procedure according to Claim 8 , characterized in that the option comprises differently designed and selectable object identifications (24). Method according to one of the Claims 1 to 9 characterized in that the object identifications (24) are adapted to the detection properties of the at least one surroundings detection sensor (16). Method according to one of the Claims 1 to 10 , characterized in that in method step b) a prioritization takes place in such a way that any object identifications (24) that may be present are used with a higher priority compared to other object features. Method according to one of the Claims 1 to 11 , characterized in that the objects (12) are classified into static and dynamic objects and that the prioritization of the object identifications (24) only takes place for object identifications (24) on static objects (12). Method according to one of the Claims 1 to 12 , characterized in that the objects (12) are classified into static and dynamic objects and that in method step d) object identifications (24) are only viewed from static objects (12). Driving support system for a vehicle (10), wherein the driving support system (14) has at least one surroundings detection sensor (16) and wherein the driving support system (14) further comprises a control unit (18) which can be fed with data from the at least one surroundings detection sensor (16), thereby characterized in that the control unit (18) is designed to implement a method according to one of the Claims 1 to 13 at least partially.

Images