Driving assistance system and driving assistance method for vehicle

Abstract

To make it possible to reliably identify vulnerable road users.SOLUTION: A driving assistance system 200 for a vehicle Includes: an object identification module 220 which is configured to perform an object identification process in a vehicle environment on the basis of environmental data from an environmental sensor 210 of the vehicle; an analysis module 230 which is configured to validate a categorization of an object as a vulnerable road user, the categorization having been performed by the object identification module 220, wherein the analysis module 230 is configured to perform the validation on the basis of at least one movement property of the object; and a driving assistance module 240 which is configured to perform driving assistance for automated driving on the basis of the validation.SELECTED DRAWING: Figure 2

Description

[Technical field]

[0001] The present disclosure relates to a cruise assist system for a vehicle, a vehicle having such a cruise assist system, a cruise assist method for a vehicle, and a storage medium for performing the cruise assist method.The present disclosure relates in particular to the assessment of movement patterns for recognition and validity check of lower level traffic participants such as pedestrians and cyclists. [Background technology]

[0002] The development of driving assistance functions, e.g. for (partially) autonomous driving, is becoming more and more important. To enable as accurate as possible surroundings sensing for driver assistance systems, sensor measurements from different sensor types, e.g. camera, LiDAR and radar, can be used. Each sensor type is based on a different physical measurement principle. The vehicle surroundings actually consists of a great many different objects / subjects, such as different vehicle types, people and animals, static objects, such as garbage bins, traffic control systems, natural objects and terrain. As the sensing of all these objects / subjects depends on the respective measurement principle used, it is difficult to guarantee an accurate surroundings sensing.

[0003] In particular, despite the large number of sensors, it may be difficult to reliably detect a given traffic participant. If an incorrect recognition occurs, this may lead to a decrease in the performance of the driving assistance system. For example, the traffic jam assistant deactivates the driving assistance if a pedestrian or cyclist is recognized. However, if an object such as a motorcycle is incorrectly recognized as a pedestrian or cyclist, the driving assistance may be deactivated without reason, and the user may no longer use the driving assistance due to poor performance. Since driving assistance often provides a higher level of safety compared to a manual driver, deactivation of the driving assistance may negatively affect safety in road traffic. Summary of the Invention [Problem to be solved by the invention]

[0004] The present disclosure aims to provide a driving assistance system for automated driving of a vehicle, which enables reliable recognition of traffic participants, in particular lower-ranking traffic participants, a vehicle having such a driving assistance system, a driving assistance method for automated driving of a vehicle, and a storage medium for implementing the driving assistance system. In particular, the present disclosure aims to maximize the duration of use of the driving assistance system, thereby improving safety in road traffic. [Means for solving the problem]

[0005] The problem is solved by the subject matter of the independent claims. Preferred embodiments are set forth in the dependent claims.

[0006] According to one independent aspect of the present disclosure, a driving assistance system for a vehicle, in particular a motor vehicle, is provided, the driving assistance system including an object recognition module configured to perform object recognition around the vehicle based on ambient data from ambient sensors of the vehicle, an analysis module configured to perform validation of the classification of the object as a lower level traffic participant performed by the object recognition module, the analysis module being configured to perform the validation based on at least one movement characteristic (motion characteristic) of the object, and a driving assistance module configured to perform driving assistance for automated driving based on the validation.

[0007] According to the invention, a filter algorithm is provided for the plausibility check of lower-ranked traffic participants following object recognition. In the object recognition, lower-ranked traffic participants, such as for example cyclists or pedestrians, are first recognized. The recognition is then validated or plausible based on the movement patterns of the lower-ranked traffic participants identified in the object recognition. If the validation or plausibility check recognizes that the movement patterns of the lower-ranked traffic participants are not typical, it is assumed that the object recognition is erroneous. For example, it can be assumed that the object is not a cyclist but a motorcycle, since a cyclist identified in the object recognition can approach the vehicle from behind at high speed (for example 45 km / h). In this case, for example, no deactivation of the traffic jam assist is required. As a result, a reliable recognition of traffic participants, in particular lower-ranked traffic participants, can be performed.

[0008] Preferably, the surroundings sensor includes at least one LiDAR system and / or at least one radar system and / or at least one camera and / or at least one ultrasonic system. The surroundings sensor is capable of providing surroundings data (also referred to as "periphery data") describing the surrounding area of ​​the vehicle.

[0009] Preferably, the classification includes or is a classification. In particular, the object recognition module can be configured in object recognition to perform a classification of the vehicle surroundings based on the surrounding data of the surroundings sensor. Classification in surrounding recognition is generally understood as a labeling of objects and / or objects recognized in the surrounding data (e.g. "vehicle", "pedestrian", "cyclist", etc.).

[0010] Preferably, the classification of the vehicle surroundings is performed using semantic segmentation. The notion of "semantic segmentation" is generally understood as the classification of image segments or pixels of an input image into some (fixed) number of classifications. In particular, in semantic segmentation, a semantic meaning is assigned to each pixel of the image in order to distinguish, for example, cars, pedestrians, bicycles, roads, curbs, buildings, poles, signs, etc. In this case, semantic segmentation assigns a meaning to each pixel of the input image both for uncountable "item" classifications (e.g. roads) and for countable "object" classifications (e.g. vehicles or people).

[0011] Preferably, the classification of the vehicle surroundings, in particular the semantic segmentation, uses a neural network.

[0012] Preferably, the lower level traffic participants are selected from the group including or consisting of pedestrians, cyclists, wheelchair users and electric scooters.

[0013] Preferably, the lower level traffic participant may be a vulnerable road user (Vulnerable Road User (VRU)). The concept of "vulnerable road user" as used in this disclosure generally refers to a traffic participant who is particularly at risk of injury or death in road traffic due to the lack of surrounding protective coverings, such as a vehicle interior. In particular, "vulnerable road user" includes pedestrians and / or cyclists.

[0014] Preferably, the driving assistance system, in particular the object recognition module or the analysis module, is configured to recognize at least one movement characteristic (motion characteristic) of an object based on ambient data from the ambient sensor.

[0015] Preferably, the at least one movement characteristic includes a relative position of the object with respect to the vehicle.

[0016] Additionally or alternatively, the at least one movement characteristic includes a movement path or trajectory of the object over time, in particular over multiple frames of the surrounding sensor. For example, since the movement path of the object may be typically that of a motorcyclist (e.g. a snaking line in traffic to overtake a moped), it is possible to infer that a lower level traffic participant identified in the object recognition is not such.

[0017] Additionally or alternatively, the at least one movement characteristic comprises a speed of the object. For example, the object may move at a speed equal to or greater than a threshold, so that it is possible to infer that a lower traffic participant identified in the object recognition is not such. The threshold may for example be equal to or greater than 30km / h, equal to or greater than 35km / h, equal to or greater than 40km / h, equal to or greater than 45km / h or equal to or greater than 50km / h.

[0018] Additionally or alternatively, the at least one movement characteristic includes an absolute position of the object, for example the object may also be located in the path of the motorcycle, so that it is possible to plausibly check that a motorcycle rider identified in the object recognition is in fact not such.

[0019] Preferably, the driving assistance system, in particular the object recognition module or the analysis module, is configured to determine and use for validation a movement pattern of the object based on at least one movement characteristic, which may include, but is not limited to, a movement path (motion path) or a movement trajectory (motion trajectory) and a speed of the object.

[0020] Preferably, the analysis module may be configured to discard the classification of the object as a lower-rank traffic participant made by the object identification module if at least one movement characteristic differs from the characteristic movement behavior of a lower-rank traffic participant, and to confirm the classification of the object as a lower-rank traffic participant made by the object recognition module if at least one movement characteristic corresponds to the characteristic movement behavior of a lower-rank traffic participant. The characteristic movement behavior may for example relate to the movement path and / or the speed.

[0021] Preferably, the driving assistance module can be configured to deactivate the driving assistance for automated driving, or for example prevent activation by a user, when the classification of an object as a lower-level traffic participant made by the object recognition module is confirmed by the analysis module, and to activate the driving assistance for automated driving, or for example allow activation by a user, when the classification of an object as a lower-level traffic participant made by the object recognition module is discarded by the analysis module.

[0022] Preferably, the analysis module is configured to discard the classification of an object as a lower-level traffic participant made by the object recognition module if the object speed of the object is equal to or greater than the threshold and the object is moving away from or towards the vehicle, for example, an object may be moving away from or towards the vehicle at a speed equal to or greater than the threshold (e.g. a motorcycle approaching from behind at high speed), and so it is possible to infer that the lower-level traffic participant identified in the object recognition is not such.

[0023] In some embodiments the threshold may be, for example, 30km / h or more, 35km / h or more, 40km / h or more, 45km / h or more, or 50km / h or more.

[0024] Preferably, the analysis module is configured to determine in the validation whether the lower-ranked traffic participant recognized in the object recognition is a lower-ranked traffic participant related to the driving behavior of the vehicle, if the lower-ranked traffic participant recognized in the object recognition is validated as a lower-ranked traffic participant related to the driving behavior of the vehicle. In particular, an object that may be in danger of collision based on the driving behavior of the vehicle (e.g., driving trajectory and speed) and the movement behavior of the object (e.g., movement trajectory and speed) is deemed to be relevant.

[0025] In one example, the analysis module may determine that a lower-ranked traffic participant identified in the object recognition is in fact such and that the lower-ranked traffic participant and the ego vehicle move away from each other, which may be an unrelated lower-ranked traffic participant, and for example, a driving assist, such as traffic jam assist, may not be turned off.

[0026] In another example, the analysis module can determine that a lower-ranked traffic participant identified in the object recognition is in fact such and that the lower-ranked traffic participant and the ego-vehicle are moving towards each other, in which case it may be the lower-ranked traffic participant that is involved and a driving assist, such as for example a traffic jam assist, may be switched off.

[0027] According to another independent aspect of the present disclosure, there is provided a vehicle, in particular a motor vehicle, including a driving assistance system according to an embodiment of the present disclosure.

[0028] The term vehicle includes cars, lorries, buses, campers, motorbikes, etc., used for the transport of people, goods, etc. In particular, the term includes motor vehicles for transporting people.

[0029] The driving assistance system is configured for automated driving.

[0030] The term (concept) "automated driving" is understood in this specification as driving with automated longitudinal driving (longitudinal guide) and / or lateral driving (lateral guide). Automated driving can be, for example, a relatively long drive on a highway or a time-limited drive in parking. The term "automated driving" includes automated driving with an appropriate degree of automation. Exemplary degrees of automation are assisted driving, partially automated driving, conditionally automated driving, highly automated driving, and fully automated driving (in order of increasing degrees of automation). The above five degrees of automation correspond to SAE Levels 1 to 5 of the standard SAE J3016 (SAE: Society of Automotive Engineering) dated April 30, 2021.

[0031] In assisted driving (SAE Level 1), the system performs longitudinal or lateral driving in a given driving situation. In partially automated driving (SAE Level 2), the system assumes longitudinal and lateral driving in a given driving situation, and the driver must continuously monitor the system as in assisted driving. In conditionally automated driving (SAE Level 3), the system assumes longitudinal and lateral driving in a given driving situation without the driver needing to continuously monitor the system, but the driver must be able to assume vehicle driving upon request by the system for a certain period of time. In highly automated driving (SAE Level 4), the driver is omitted as a backup level, since the system assumes vehicle driving in a given driving situation without the driver responding upon request for intervention. In fully automated driving (SAE Level 5), all aspects of the dynamic driving task can be performed by the system under all road and ambient conditions that are also handled by a human driver.

[0032] Furthermore, the term "at least partially automated driving or operation" in this specification is understood to mean partially automated driving, conditionally automated driving, highly automated driving, and fully automated driving. In other words, therefore, "at least partially automated driving" is understood to mean an automation level of SAE Level 2 or higher.

[0033] Preferably, the driving assistance system is configured for automated driving according to SAE Level 2. The driving assistance system may be, for example, a traffic jam assist or may implement a traffic jam assist.

[0034] According to another independent aspect of the present disclosure, there is provided a driving assistance method for a vehicle, in particular a motor vehicle, comprising: performing, by an object recognition module, object recognition in the surroundings of the vehicle based on surrounding data of a surrounding sensor of the vehicle, performing, by an analysis module, validation of a classification of the object as a lower level traffic participant performed by the object recognition module, where the analysis module is configured to perform the validation based on at least one movement characteristic of the object, and performing driving assistance for automated driving based on the validation.

[0035] A cruise assist method for a vehicle may implement aspects of the cruise assist system described herein.

[0036] According to another independent aspect of the present disclosure, there is provided a software (SW) program that can be configured to run on one or more processors and thereby perform the vehicle driving assistance method described herein.

[0037] According to another independent aspect of the present disclosure, a storage medium is provided, which may include a software (SW) program configured to be executed on one or more processors and thereby perform the vehicle driving assistance method described herein.

[0038] According to another independent aspect of the present disclosure, there is provided software having program code configured to perform a method of cruise assistance for a vehicle when the software is run on one or more software controlled devices.

[0039] According to another independent aspect of the present disclosure, there is provided a driving assistance system for a vehicle, the driving assistance system including one or more processors and at least one memory coupled to the one or more processors for receiving instructions executable by the one or more processors to perform a driving assistance method for a vehicle as described herein.

[0040] A processor or processor module is a programmable computing unit, ie a machine or electronic circuit that controls other elements according to commands transmitted to it and in so doing executes an algorithm (process).

[0041] The disclosed embodiments are illustrated in the drawings and are described in detail below. [Brief description of the drawings]

[0042] [Figure 1] FIG. 1 is a schematic diagram of a vehicle having a driving assistance system for automated driving according to an embodiment of the present disclosure. [Diagram 2] FIG. 1 is a diagram illustrating a schematic diagram of a driving assistance system for a vehicle according to an embodiment of the present disclosure. [Figure 3A] 1 is a schematic diagram of a vehicle and an object according to an embodiment of the present disclosure; [Figure 3B]FIG. 2 is a schematic diagram of a vehicle and an object according to another embodiment of the present disclosure. [Figure 4] 4 is a flowchart of a driving assistance method according to an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0043] In the following, unless otherwise stated, the same reference numerals are used for the same and similarly acting elements.

[0044] FIG. 1 illustrates a schematic diagram of a vehicle 10 having a driving assistance system 100 for automated driving according to an embodiment of the present disclosure.

[0045] During automated driving, longitudinal driving (longitudinal guidance) and / or lateral driving (lateral guidance) of the vehicle 10 is performed automatically. Thus, the driving assistance system 100 takes over vehicle driving (vehicle guidance). To this end, the driving assistance system 100 controls the drive unit 20, the transmission 22, the (e.g., hydraulic) foot brake 24, and the steering unit 26 via an intermediate unit (not shown).

[0046] For planning and executing automated driving, ambient information from ambient sensors monitoring the vehicle's surroundings is received by the driving assistance system 100. In particular, the vehicle may include at least one ambient sensor 12 configured to receive ambient data representative of the vehicle's surroundings. The at least one ambient sensor 12 may include, for example, one or more LiDAR systems, one or more radar systems, one or more ultrasonic sensors, and / or one or more cameras.

[0047] Preferably, the driving assistance system 100 is configured for automated driving according to SAE Level 2. The driving assistance system 100 may be or be capable of implementing, for example, a traffic jam assist.

[0048] 2 is a schematic diagram of a driving assistance system 200 according to an embodiment of the present disclosure. The driving assistance system 200 may be the driving assistance system described with respect to FIG.

[0049] The driving assistance system 200 includes an object recognition module 220 configured to perform object recognition around the vehicle based on ambient data from the vehicle's ambient sensors 210, an analysis module 230 configured to validate the classification of an object as a lower-level traffic participant performed by the object recognition module 220, the analysis module 230 configured to perform the validation based on at least one movement characteristic (motion characteristic) of the object, and a driving assistance module 240 configured to perform driving assistance for automated driving based on the validation.

[0050] The object recognition module 220, the analysis module 230, and / or the driving assistance module 240 may be implemented in a common software and / or hardware module. Alternatively, the object recognition module 220, the analysis module 230, and / or the driving assistance module 240 may be implemented in separate software and / or hardware modules.

[0051] The lower level traffic participants may be, for example, pedestrians, cyclists, wheelchair users or electric scooters. In particular, the lower level traffic participants may be vulnerable road users (Vulnerable Road Users (VRUs)).

[0052] The driving assistance system 200 can be configured to recognize at least one movement characteristic of the object based on the surrounding data of the surrounding sensor 210. The driving assistance system 200 can determine, for example, a movement pattern (motion pattern) of the object based on the at least one movement characteristic and use it for validation. The movement pattern can include, for example, a movement path (motion path) or a movement trajectory (motion trajectory) and a speed of the object, but is not limited to this.

[0053] Preferably, the at least one movement characteristic includes a relative position of the object with respect to the vehicle.

[0054] Additionally or alternatively, the at least one movement characteristic includes the object's movement path or trajectory over time, in particular over multiple frames of the surrounding sensor 210. For example, since the object's movement path may be typical of a motorcyclist (e.g., snaking lines in traffic to overtake a moped), it is possible to infer that a lower level traffic participant identified in the object recognition is not such.

[0055] Additionally or alternatively, the at least one movement characteristic comprises a speed of the object. For example, the object may move at a speed equal to or greater than a threshold, so that it is possible to infer that a lower traffic participant identified in the object recognition is not such. The threshold may for example be equal to or greater than 30km / h, equal to or greater than 35km / h, equal to or greater than 40km / h, equal to or greater than 45km / h or equal to or greater than 50km / h.

[0056] Additionally or alternatively, the at least one movement characteristic includes an absolute position of the object, for example the object may also be located in the path of the motorcycle, so that it is possible to plausibly check that a motorcycle rider identified in the object recognition is in fact not such.

[0057] In some embodiments, the analysis module 230 can be configured to discard the classification of the object as a lower-level traffic participant made by the object identification module 220 if at least one movement characteristic differs from the characteristic movement behavior of a lower-level traffic participant, and to confirm the classification of the object as a lower-level traffic participant made by the object recognition module 220 if at least one movement characteristic corresponds to the characteristic movement behavior of a lower-level traffic participant. The characteristic movement behavior may relate, for example, to the movement path and / or the speed.

[0058] In some embodiments, the driving assistance module 240 can be configured to deactivate driving assistance for automated driving, or for example prevent activation by a user, when the classification of an object as a lower-level traffic participant made by the object recognition module 220 is confirmed by the analysis module 230, and to activate driving assistance for automated driving, or for example allow activation by a user, when the classification of an object as a lower-level traffic participant made by the object recognition module 220 is discarded by the analysis module 230.

[0059] Preferably, the analysis module 230 is further configured to determine in the validation whether the lower-level traffic participant recognized in the object recognition is a lower-level traffic participant related to the driving behavior of the vehicle, when the lower-level traffic participant recognized in the object recognition is validated as a lower-level traffic participant related to the driving behavior of the vehicle. In particular, an object that may be in danger of collision based on the driving behavior of the vehicle (e.g., driving trajectory and speed) and the movement behavior of the object (e.g., movement trajectory and speed) is deemed to be relevant.

[0060] In one example, the analysis module 230 may determine that a lower-ranked traffic participant identified in the object recognition is in fact such and that the lower-ranked traffic participant and the ego vehicle move away from each other, which may be an unrelated lower-ranked traffic participant, and for example, driving assists such as traffic jam assist may not be turned off.

[0061] In another example, the analysis module 230 may determine that a lower-ranked traffic participant identified in the object recognition is in fact such and that the lower-ranked traffic participant and the ego-vehicle are moving towards each other, in which case it may be the lower-ranked traffic participant that is associated and a driving assist, such as traffic jam assist, may be turned off.

[0062] FIG. 3A shows a schematic diagram of a vehicle 10 and an object 30A according to an embodiment of the present disclosure.

[0063] In some embodiments, the driving assistance system may be configured to discard the classification of the object 30A as a lower-ranked traffic participant made in the object recognition if the object speed OBG1 of the object 30A is equal to or greater than a threshold and the object 30A is driving towards the vehicle 10. The threshold may be, for example, 30 km / h or more, 35 km / h or more, 40 km / h or more, 45 km / h or more, or 50 km / h or more.

[0064] For example, an object 30A may move toward the vehicle 10 at a speed OBG1 above the threshold, such as the motorcycle approaching from behind at high speed shown in Fig. 3A. It is therefore possible to assume that the lower traffic participants identified in the object recognition are not of this type. In this case, a driving assist such as, for example, a traffic jam assist may not be switched off.

[0065] FIG. 3B shows a schematic diagram of a vehicle 10 and an object 30B according to another embodiment of the present disclosure.

[0066] In some embodiments, the driving assistance system may be configured to confirm the classification of the object 30B as a lower-ranked traffic participant made in the object recognition if the object speed OBG2 of the object 30B is below a threshold value, which may be, for example, below 30 km / h, below 35 km / h or below 40 km / h.

[0067] For example, an object 30B, such as the motorcycle shown in Fig. 3B, may be present in front of the vehicle 10 at a speed OBG2 below the threshold. It can therefore be assumed that the lower traffic participant identified in the object recognition is indeed such. In this case, driving assistance, such as traffic jam assistance, may be switched off and vehicle driving may be handed over to the driver.

[0068] 4 shows a flowchart of a driving assistance method 400 according to an embodiment of the present disclosure. The driving assistance method 400 may be implemented by corresponding software executable by one or more processors (e.g., CPUs).

[0069] The driving assistance method 400 includes, in block 410, performing object recognition around the vehicle by an object recognition module based on ambient data from the vehicle's ambient sensors, in block 420, performing validation of the classification of the object as a lower-level traffic participant performed by the object recognition module by an analysis module, where the analysis module is configured to perform the validation based on at least one movement characteristic of the object, and performing driving assistance for automated driving based on the validation in block 430.

[0070] According to the invention, a filter algorithm is provided for the plausibility check of lower-ranked traffic participants following object recognition. In the object recognition, lower-ranked traffic participants, such as for example cyclists or pedestrians, are first recognized. The recognition is then validated or plausible based on the movement patterns of the lower-ranked traffic participants identified in the object recognition. If the validation or plausibility check recognizes that the movement patterns of the lower-ranked traffic participants are not typical, it is assumed that the object recognition is erroneous. For example, it can be assumed that the object is not a cyclist but a motorcycle, since a cyclist identified in the object recognition can approach the vehicle from behind at high speed (for example 45 km / h). In this case, for example, no deactivation of the traffic jam assist is required. As a result, a reliable recognition of traffic participants, in particular lower-ranked traffic participants, can be performed.

[0071] Although the present invention has been illustrated and described in detail by preferred embodiments, the present invention is not limited to the disclosed examples, and other modifications can be derived by those skilled in the art without departing from the scope of protection of the present invention. Therefore, it is clear that there are many possible modifications. Similarly, it is clear that the exemplary embodiments are merely examples, and the examples should not be understood as limiting the scope of protection, application or configuration of the present invention in any manner, for example. Rather, the above description and the description of the drawings (description by the drawings) enable those skilled in the art to specifically implement the exemplary embodiments, and those skilled in the art can make various modifications, for example, regarding the function or arrangement of individual elements listed in the exemplary embodiments, without departing from the scope of protection defined in the claims and their legal counterparts, such as further descriptions in the specification, after knowing the concept of the present invention disclosed.

Claims

1. A driving assistance system (100, 200) for a vehicle (20), comprising: an object recognition module (220) configured to perform object recognition in the vehicle's surroundings based on surrounding data from surrounding sensors (12, 210) of the vehicle (10); an analysis module (230) configured to validate the classification of the object (30A, 30B) as a lower level traffic participant performed by the object recognition module (220), the analysis module (230) being configured to perform the validation based on at least one movement characteristic of the object (30A, 30B); a driving assistance module (240) configured to perform driving assistance for automated driving based on the validation; A driving assistance system (100, 200) comprising:

2. The at least one movement characteristic is the relative position of the objects (30A, 30B) with respect to the vehicle (10), and / or the movement path of the object (30A, 30B) over time, in particular over multiple frames of the ambient sensor (12, 110), and / or the velocities (OBG1, OBG2) of said objects (30A, 30B), and / or the absolute position of said objects (30A, 30B); The driving assistance system (100, 200) according to claim 1, further comprising:

3. The analysis module includes: - to discard the classification of said object (30A, 30B) as a lower-rank traffic participant made by said object identification module if said at least one movement characteristic differs from the characteristic movement manner of a lower-rank traffic participant; and - to confirm the classification of said object (30A, 30B) as a lower-rank traffic participant, performed by said object recognition module, if said at least one movement characteristic corresponds to a characteristic movement manner of a lower-rank traffic participant.

3. The driving assistance system (100, 200) according to claim 1 or 2, characterized in that it is configured as follows.

4. The driving assist module is - deactivating or blocking the activation of a driving assistance for automated driving if the classification of the object (30A, 30B) as a lower-level traffic participant made by the object recognition module (220) is confirmed by an analysis module (230); and - to activate or allow the activation of a driving assistance for automated driving if the classification of the object (30A, 30B) as a lower-level traffic participant made by the object recognition module (220) is overruled by the analysis module (230), 4. The driving assistance system (100, 200) according to claim 3, characterized in that it is configured

5. The driving assistance system (100, 200) according to any one of claims 1 to 4, characterized in that the analysis module (230) is configured to discard the classification of the object (30A, 30B) as a lower-rank traffic participant made by the object recognition module (220) when the object speed (OBG1) of the object (30A, 30B) is equal to or greater than a threshold value and the object (30A, 30B) is moving away from the vehicle (10) or moving towards the vehicle (10), the threshold value being equal to or greater than 30 km / h, 35 km / h, 40 km / h, 45 km / h, or 50 km / h.

6. The driving assistance system (100, 200) according to any one of claims 1 to 5, characterized in that the analysis module (230) is configured to determine in the validation whether a lower-level traffic participant recognized in the object recognition is a lower-level traffic participant related to the driving behavior of the vehicle (10) when the lower-level traffic participant recognized in the object recognition is validated as a lower-level traffic participant related to the driving behavior of the vehicle (10).

7. The driving assistance system (100, 200) according to any one of claims 1 to 6, characterized in that the lower level traffic participants are selected from the group consisting of pedestrians, cyclists, wheelchair users and electric scooters, and in particular, the lower level traffic participants are vulnerable road users.

8. A vehicle (10), in particular a motor vehicle, comprising a driving assistance system (100, 200) according to any one of the preceding claims.

9. A driving assistance method (400) for a vehicle (10), comprising: performing (410) object recognition in the vehicle's surroundings based on surrounding data from surrounding sensors (12, 210) of the vehicle (10) using an object recognition module (220); performing (420) a validation of the classification of the object (30A, 30B) as a lower level traffic participant performed by the object recognition module (220) by an analysis module (230), the analysis module (230) being configured to perform the validation based on at least one movement characteristic of the object (30A, 30B); Executing driving assistance for automated driving based on the validation (430). A driving assistance method (400) comprising:

10. 10. A storage medium containing a software program configured, when executed on one or more processors, to thereby perform the method (400) of driving assistance according to claim 9.

Images