Driver assistance system and driver assistance method for a vehicle
The driver assistance system addresses the challenge of recognizing recurring vehicle locations by using route characteristics to identify destinations without GPS data, enabling automatic action execution and maintaining data privacy, thus enhancing personalized assistance in vehicle assistance systems.
Patent Information
- Application Number
- PCT/DE2024/100333
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2023-05-26
- Filing Date
- 2024-04-17
- Publication Date
- 2024-12-05
AI Technical Summary
Existing vehicle assistance systems require manual storage of exact GPS positions and knowledge of specific locations, which is time-consuming and problematic in terms of data protection, to offer personalized and context-sensitive assistance, especially in recognizing recurring vehicle locations like parking scenarios.
A driver assistance system that uses a history module to store and recognize driving paths divided into discrete route sections with unique route characteristics, allowing the vehicle to automatically identify destinations without relying on GPS positions or explicit labels, using a recognition module to match current paths with stored history information and control vehicle functions accordingly.
Enables robust and data protection-compliant recognition of vehicle destinations, allowing automatic execution of actions without user-defined GPS positions, enhancing personalized assistance while maintaining privacy by using route characteristics as 'fingerprints' for destination identification.
Smart Images

Figure DE2024100333_05122024_PF_FP_ABST
Abstract
Description
[0001]23-0981 Driver assistance system and driver assistance method for a vehicle The present disclosure relates to a driver assistance system for a vehicle, a vehicle with such a driver assistance system, a driver assistance method for a vehicle and a storage medium for carrying out the driver assistance method. The present disclosure particularly relates to robust and data protection-compliant detection and classification of recurring vehicle locations, e.g. in parking scenarios. State of the art Modern vehicles are increasingly being fitted with assistance systems that are intended to proactively support the user in a wide variety of ways. Such assistance systems can, for example, use GPS positions to carry out certain actions at specific locations. For example, upon reaching a specific GPS position, a window in front of an underground parking garage entrance or an underground parking garage gate can be automatically opened.Here, the GPS positions and the associated actions are defined and saved directly by the user. The acquisition and manual storage of precise GPS positions is complex for the user, and automatic assignment to people and / or specific locations is problematic or even impossible from a data protection perspective. However, many assistance systems require knowledge of the local context in order to offer personalized and context-sensitive assistance. Disclosure of the Invention It is an object of the present disclosure to specify a driver assistance system for a vehicle, a vehicle having such a driver assistance system, a driver assistance method for a vehicle, and a storage medium for executing the driver assistance method, which can determine a travel destination of the vehicle.In particular, it is an object of the present disclosure to determine a destination of the vehicle 23-0981 without stored GPS positions and / or knowledge of specific locations. This object is achieved by the subject matter of the independent claims. Advantageous embodiments are specified in the subclaims. According to an independent aspect of the present disclosure, a driver assistance system for a vehicle, in particular a motor vehicle, is specified.The driver assistance system comprises a history module configured to store history information relating to driving paths traveled by the vehicle, each driving path being divided into a plurality of discrete route sections, and the history module configured to store route characteristics for each discrete route section as the history information; a recognition module configured to compare the history information with a current driving path in order to recognize a current destination of the vehicle; and a control module configured to control at least one vehicle function based on the determined current destination. According to the invention, a destination or location, e.g., in a parking scenario, is generically represented as the end position of a discretized progression of predefined and spatially limited history data.Discretized means that the path traveled by the vehicle to the destination for a specified distance is divided into sub-sections. These sub-sections, in turn, contain route characteristics which, taken together, serve as unique characteristics of the final position. The destinations are therefore not recognized based on GPS positions and / or an explicit label, but rather by the route there, which has a unique "fingerprint" due to its characteristics. This means that destinations at which certain actions are to be automatically carried out by the vehicle do not have to be defined by the user, but can be recognized automatically by the vehicle. The destinations are also recognized based on characteristics that are unproblematic from a data protection perspective, meaning that no GPS positions of the 23-0981 destinations assigned to the user or other sensitive information need to be used to recognize the destinations.The history module and / or the recognition module and / or the control module can be implemented in a common software and / or hardware module. Alternatively, the history module and / or the recognition module and / or the control module can each be implemented in separate software and / or hardware modules. Furthermore, the history module and / or the recognition module and / or the control module can each be partitioned onboard in the vehicle and / or offboard in a backend. Preferably, the recognition module is configured to recognize the current travel destination if the comparison of the current travel path with the history information indicates a complete match. However, the present disclosure is not limited to this, and the recognition module can also recognize the current travel destination if the comparison of the current travel path with the history information indicates a partial match, such asa partial match that is equal to or greater than a threshold. In other words, a minimum level of match can be specified so that recognition of the destination is possible even with a certain level of misrecognitions and / or non-recognition of certain route characteristics along the current travel path. Preferably, the recognition module is configured to recognize the current destination by recognizing a sequence of route sections of the current travel path using the history information. The sequence of route sections is recognized by their unique route characteristics, such as events and attributes. This allows the destination to be determined as the end point of the recognized sequence of route sections of the current travel path, so that no identity information of the destination is required to determine the destination of the current travel path.23-0981 Preferably, the history module is configured not to store identification labels for destinations of the traveled paths. In particular, since the destination is recognized based on the route characteristics of the route there, it is not necessary to know a unique label for the destination. A strict classification of all destinations into classes (e.g., "home," "work," etc.) is also not necessary, since the embodiments of the present disclosure do not concern the destinations themselves, but rather a robust recognition of them, for example, in order to be able to annotate them with corresponding user interactions. The term "label," as used in the present disclosure, refers to a unique designation or identification of the destination, such as "supermarket," "school," "work," "home," etc.Preferably, the recognition module does not use any position data of the destination, in particular no GPS data, to recognize the current destination. In particular, because the destination is recognized based on the route characteristics of the path there, it is not necessary to know the GPS position of the destination. Preferably, the route characteristics comprise events, wherein the events divide the travel path into the plurality of discrete route sections. In other words, two consecutive route sections can be separated by at least one event. In some embodiments, the events comprise (or are) - a navigation event, in particular an intersection; and / or - a driving dynamics event, in particular a turn; and / or - a traffic sign, in particular a stop sign; and / or - a traffic signal, in particular a traffic light.However, the present disclosure is not limited thereto, and other types of events are conceivable that are suitable for dividing the travel path into the route sections. 23-0981 Preferably, the route characteristics comprise route attributes. Route attributes are properties that relate to the route itself and / or an area surrounding the route. In some embodiments, the route attributes comprise (or are): - a length of the route section; and / or - a road type (e.g., motorway, country road, track, bridge, etc.); and / or - a mapped speed limit; and / or - a road curvature (e.g., a straight stretch or a curve); and / or - at least one landmark (topographical objects such as roundabouts, pedestrian crossings, exits, toll stations, etc.). However, the present disclosure is not limited thereto, and other types of route attributes are conceivable that are suitable for characterizing the route section.Preferably, the driver assistance system is configured to divide the route characteristics into categories and to perform fuzzy matching based on the categories. In particular, the individual events and / or route attributes can be divided into broad categories so that fuzzy matching is possible. Fuzzy matching is particularly advantageous when navigation data changes slightly (remapping) and / or route characteristics, such as landmarks, are missed in certain situations, e.g., due to a restricted view of the vehicle's environmental sensors. The control module of the driver assistance system is configured to control at least one vehicle function based on the determined current destination. In particular, the destination can be annotated with corresponding actions that can be executed automatically, for example, in vehicle entry and / or exit scenarios in parking situations.In some embodiments, the at least one vehicle function relates to or is a seat adjustment. For example, at least one vehicle seat, such as a driver's seat and / or 23-0981 a passenger seat, can be automatically moved into an entry and exit position to allow people to enter the rear of the vehicle. Additionally or alternatively, the at least one vehicle function relates to or is a window lifter. For example, a window can be opened to allow the driver to operate a barrier at a parking garage. Additionally or alternatively, the at least one vehicle function relates to or is an opening and closing mechanism of a trunk. For example, the trunk can be opened automatically and as appropriate to the situation to allow the driver to load or unload.Additionally or alternatively, the at least one vehicle function relates to or is an opening and / or closing mechanism of at least one vehicle door. For example, at least one vehicle door can be opened automatically to allow at least one vehicle occupant to get in or out. Additionally or alternatively, the at least one vehicle function relates to or is an optical output means and / or an acoustic output means. For example, interior lighting and / or exterior lighting can be adjusted depending on the destination. In a further example, driver instructions relating to the destination can be output ("You will soon reach your destination" and / or "You have reached your destination"). According to a further independent aspect of the present disclosure, a vehicle, in particular a motor vehicle, is specified.The vehicle comprises the driver assistance system for a vehicle according to the embodiments of the present disclosure. The term "vehicle" encompasses cars, trucks, buses, mobile homes, motorcycles, etc., which serve to transport people, goods, etc. In particular, the term "motor vehicles" encompasses motor vehicles for transporting people. 23-0981 According to a further independent aspect of the present disclosure, a driver assistance method for a vehicle, in particular a motor vehicle, is specified.The driver assistance method comprises storing, in a history module, history information relating to travel paths that the vehicle has traveled, wherein each travel path is divided into a plurality of discrete route sections and route characteristics are stored as the history information for each discrete route section; comparing the history information with a current travel path in order to recognize a current travel destination of the vehicle; and controlling at least one vehicle function based on the determined current travel destination. The driver assistance method can implement the aspects of the driver assistance system described in this document. According to a further independent aspect of the present disclosure, a software (SW) program is specified. The SW program can be configured to run on one or more processors orECUs, and in order to thereby carry out the driver assistance method for a vehicle described in this document. According to a further independent aspect of the present disclosure, a storage medium is specified. The storage medium can comprise a SW program which is configured to be executed on one or more processors or ECUs, and in order to thereby carry out the driver assistance method for a vehicle described in this document. According to a further independent aspect of the present disclosure, software with program code is specified. The software is configured to carry out the driver assistance method for a vehicle when the software runs on one or more software-controlled devices.It should be understood that the functionalities of the subject matter according to the invention can be implemented entirely in the vehicle, or the functionalities of the subject matter according to 23-0981 can be suitably divided between the vehicle and a central unit, such as a backend. According to a further independent aspect of the present disclosure, a driver assistance system for a vehicle is specified. The driver assistance system comprises one or more processors or ECUs; and at least one memory which is connected to the one or more processors or ECUs and contains instructions which can be executed by the one or more processors or ECUs in order to carry out the driver assistance method for a vehicle described in this document. A processor orAn ECU is a programmable computer, i.e., a machine or electronic circuit that controls other elements according to transmitted commands, thereby advancing an algorithm (process). The processor or ECU may be suitable for use in vehicles. Brief Description of the Drawings: Embodiments of the disclosure are illustrated in the figures and are described in more detail below.1A schematically shows a vehicle with a driver assistance system according to embodiments of the present disclosure, Figure 1B schematically shows a vehicle and a backend according to embodiments of the present disclosure, Figure 2 schematically shows a travel path with route sections according to embodiments of the present disclosure, Figure 3 schematically shows a travel path to a travel destination according to embodiments of the present disclosure, and Figure 4 shows a flowchart of a driver assistance method according to embodiments of the present disclosure. Embodiments of the Disclosure In the following, unless otherwise stated, the same reference numerals are used for the same elements and elements with the same effect. Figure 1 schematically shows a vehicle 10 with a driver assistance system 100 according to embodiments of the present disclosure. In the example of Figure 1A, the functionalities of the subject matter according to the invention are fully implemented in the vehicle.The driver assistance system 100 comprises a history module 110 configured to store history information relating to driving paths traveled by the vehicle 10, wherein each driving path is divided into a plurality of discrete route sections, and the history module 110 is configured to store route characteristics for each discrete route section as the history information; a recognition module 120 configured to compare the history information with a current driving path to recognize a current destination of the vehicle 10; and a control module 130 configured to control at least one vehicle function based on the determined current destination. The driver assistance system 100 recognizes a destination generically, for example, in a parking scenario, as the end position of a discretized progression of predefined and spatially limited history data.The route characteristics of the route sections, taken together, serve as unique features of the final position. Destinations are thus not identified based on GPS positions and / or an explicit label, but rather by the route there, which has a unique "fingerprint" due to its characteristics. 23-0981 The history module 110 can be configured not to store identification labels for destinations of the traveled paths. In particular, because the destination is identified based on the route characteristics of the route there, it is not necessary to know a unique label of the destination. Furthermore, the recognition module 120 does not use any position data of the destination, in particular no GPS data, to recognize the current destination. In particular, because the destination is identified based on the route characteristics of the route there, it is not necessary to know a GPS position of the destination.The destinations are thus recognized based on features that do not pose any problems under data protection law. In some embodiments, the recognition module 120 is configured to recognize the current destination if the comparison of the current travel path with the history information indicates a complete match. However, the present disclosure is not limited thereto, and the recognition module 120 can also recognize the current destination if the comparison of the current travel path with the history information indicates a partial match, such as a partial match that is equal to or greater than a threshold. In other words, a minimum level of match can be specified so that recognition of the destination is possible even with a certain level of misrecognitions and / or non-recognitions of certain route characteristics along the current travel path.Figure 1B schematically shows a vehicle 10 and a backend 20 according to embodiments of the present disclosure. In the example of Figure 1B, the functionalities of the subject matter according to the invention are suitably distributed between the vehicle and a backend 20. In particular, the backend comprises the history module 110 and the recognition module 120, and the vehicle comprises the control module 130. 23-0981 The vehicle 10 and the backend 20 communicate with each other via a communication connection 1 in order to fully implement the functionalities of the subject matter according to the invention. In some embodiments, the communication between the vehicle 10 and the backend 20 can take place via a mobile network, such as an LTE or 5G network. Figure 2 schematically shows a travel path FP with route sections SA1, SA2, SA3, SA4 according to embodiments of the present disclosure.The driver assistance system determines the current destination by recognizing a sequence of route sections SA1, SA2, SA3, SA4 of the current travel path FP. The sequence of route sections SA1, SA2, SA3, SA4 is recognized by their unique route characteristics. Thus, the destination can be determined as the end point of the recognized sequence of route sections SA1, SA2, SA3, SA4 of the current travel path FP, so that no identity information of the destination FZ is required to determine the destination FZ of the current travel path FP. The route characteristics can include events EV1, EV2, EV3, EV4 that divide the travel path FP into the plurality of discrete route sections SA1, SA2, SA3, SA4. In other words, two consecutive route sections can be separated by at least one event. In some embodiments, the events EV1, EV2, EV3, EV4 include an intersection and / or a vehicle dynamics event (e.g.a turn) and / or a traffic sign (e.g., a stop sign) and / or a light signal (e.g., a traffic light). However, the present disclosure is not limited thereto, and other types of events are conceivable that are suitable for dividing the travel path FP into the route sections SA1, SA2, SA3, SA4. The route characteristics may further include route attributes AT1, AT2, AT3, AT4 for each route section SA1, SA2, SA3, SA4. In some embodiments, the route attributes AT1, AT2, AT3, AT4 include a length of the route section and / or a 23-0981 road type (e.g., motorway, country road, dirt road, bridge, etc.) and / or a speed limit on the route section and / or a road curvature of the route section (e.g., a straight stretch or a curve) and / or landmarks on the route section (topographical objects such as roundabouts, pedestrian crossings, exits, toll stations, etc.).However, the present disclosure is not limited thereto, and other types of route attributes are conceivable that are suitable for characterizing the respective route section. In some embodiments, the driver assistance system can be configured to divide the route characteristics into categories and to perform fuzzy matching based on the categories. In particular, the individual events EV1, EV2, EV3, EV4 and / or route attributes AT1, AT2, AT3, AT4 can be divided into rough categories so that fuzzy matching is possible. Fuzzy matching is particularly advantageous when navigation data change slightly (remapping) and / or route characteristics, such as landmarks, are missed in certain situations, e.g., due to a limited view of the vehicle's environmental sensors. Figure 3 schematically shows a travel path FP to a travel destination FZ according to embodiments of the present disclosure.The travel path FP to the travel destination FZ is characterized by route characteristics, so that by recognizing them, an end point of the travel path FP can be determined as the travel destination FZ. In the example in Figure 3, the travel path FP is characterized by driving dynamics events FD1, FD2 and a landmark LM. The driving dynamics events FD1, FD2 can be turning maneuvers, for example. The landmark LM can be a topographical object such as a roundabout or a pedestrian crossing. However, the present disclosure is not limited to these examples, and the route characteristics can additionally or alternatively include, for example, traffic signs (e.g., a stop sign) and / or light signals (e.g., a traffic light). 23-0981 The driver assistance system controls at least one vehicle function based on the determined current travel destination FZ.In particular, the travel destination FZ can be annotated with corresponding actions that can be carried out automatically, for example, in vehicle entry and / or exit scenarios in parking situations. Example sequences of actions are listed below: 1. Open trunk → close trunk → wait → open driver's door → close driver's door 2. Open driver's door → close driver's door → wait → open rear door → close rear door → open driver's door → close driver's door 3. Open driver's door → close driver's door → wait → open trunk → light staging for loading the trunk → close trunk → lock vehicle Figure 4 shows a flowchart of a driver assistance method 400 according to embodiments of the present disclosure. The driver assistance method 400 can be implemented by appropriate software that can be executed by one or more processors (e.g. a CPU) or ECUs.The driver assistance method 400 comprises, in block 410, storing, in a history module, historical information relating to travel paths traveled by the vehicle, wherein each travel path is divided into a plurality of discrete route sections and route characteristics are stored as the historical information for each discrete route section; in block 420, comparing the historical information with a current travel path in order to identify a current travel destination of the vehicle; and, in block 430, controlling at least one vehicle function based on the determined current travel destination. According to the invention, a travel destination or a location, e.g., in a parking scenario, is generically represented as the end position of a discretized course of predefined and spatially limited historical data. Discretized means that the path traveled by the vehicle to the travel destination 23-0981 is divided into subsections for a specified distance.These subsections, in turn, contain route characteristics that, taken together, serve as unique features of the final position. Destinations are thus not identified based on GPS positions and / or an explicit label, but rather by the route to them, which, due to its characteristics, has a unique "fingerprint." This means that destinations at which certain actions are to be automatically performed by the vehicle do not need to be defined by the user; instead, they can be identified automatically by the vehicle. Furthermore, the destinations are identified based on features that are unproblematic from a data protection perspective, meaning that no GPS positions of the destinations or other sensitive information need to be used to identify the destinations.Although the invention has been illustrated and explained in detail by means of preferred embodiments, the invention is not limited by the disclosed examples, and other variations may be derived therefrom by those skilled in the art without departing from the scope of the invention. It is therefore clear that a multitude of possible variations exist. It is also clear that the embodiments mentioned by way of example are truly only examples and should not be construed as limiting the scope, possible applications, or configuration of the invention in any way.Rather, the preceding description and the description of the figures enable the person skilled in the art to implement the exemplary embodiments in concrete terms, whereby the person skilled in the art, with knowledge of the disclosed inventive concept, can make various changes, for example with regard to the function or the arrangement of individual elements mentioned in an exemplary embodiment, without departing from the scope of protection defined by the claims and their legal equivalents, such as further explanations in the description.
Claims
23-0981 Patent claims 1. Driver assistance system (100) for a vehicle (10), comprising: a history module (110) configured to store history information relating to travel paths (FP) traveled by the vehicle (10), each travel path (FP) being divided into a plurality of discrete route sections (SA1, SA2, SA3, SA4), and the history module (110) configured to store route characteristics (EV1, EV2, EV3, EV4; AT1, AT2, AT3, AT4) as the history information for each discrete route section (SA1, SA2, SA3, SA4); a recognition module (120) configured to compare the history information with a current travel path (FP) in order to recognize a current travel destination (FZ) of the vehicle (10); and a control module (130) configured to control at least one vehicle function based on the determined current destination (FZ). 2.The driver assistance system (100) according to claim 1, wherein the recognition module (120) is configured to recognize the current destination (FZ) by recognizing a sequence of route sections (SA1, SA2, SA3, SA4) of the current travel path (FP) using the history information.
3. The driver assistance system (100) according to claim 1 or 2, wherein: - the history module (120) is configured not to store any identification labels of the destinations (FZ) for destinations (FZ) of the traveled travel paths (FP); and / or - the recognition module (120) does not use any position data of the destination (FZ), in particular no GPS data, to recognize the current destination (FZ). 4.Driver assistance system (100) according to one of claims 1 to 3, wherein the route characteristics (EV1, EV2, EV3, EV4; AT1, AT2, AT3, AT4) comprise events (EV1, EV2, EV3, EV4), and wherein the events (EV1, EV2, EV3, EV4) divide the travel path (FP) into the plurality of discrete route sections (SA1, SA2, SA3, SA4), in particular wherein the events (EV1, EV2, EV3, EV4) comprise:. 23-0981 - a navigation event, in particular an intersection; and / or - a driving dynamics event (FD1, FD2), in particular a turn; and / or - a traffic sign, in particular a stop sign; and / or - a light signal, in particular a traffic light.
5. The driver assistance system (100) according to one of claims 1 to 4, wherein the route characteristics (EV1, EV2, EV3, EV4; AT1, AT2, AT3, AT4) comprise route attributes (AT1, AT2, AT3, AT4), in particular wherein the route attributes (AT1, AT2, AT3, AT4) comprise: - a length of the route section; and / or - a road type; and / or - a mapped speed limit; and / or - a road curvature; and / or - at least one landmark (LM).
6. The driver assistance system (100) according to one of claims 1 to 5, wherein the driver assistance system (100) is configured to divide the route characteristics (EV1, EV2, EV3, EV4; AT1, AT2, AT3, AT4) into categories and to perform fuzzy matching based on the categories.Driver assistance system (100) according to one of claims 1 to 6, wherein the at least one vehicle function relates to or is: - a seat adjustment; and / or - a window lifter; and / or - an opening and closing mechanism of a trunk; and / or - an opening and / or closing mechanism of at least one vehicle door; and / or - optical output means and / or acoustic output means.
8. Vehicle (10), in particular a motor vehicle, comprising the driver assistance system (100) according to one of claims 1 to 7. 23-0981 9. A driver assistance method (400) for a vehicle (10), comprising: storing (410), in a history module (120), history information relating to travel paths (FP) that the vehicle (10) has traveled, wherein each travel path (FP) is divided into a plurality of discrete route sections (SA1, SA2, SA3, SA4) and route characteristics (EV1, EV2, EV3, EV4; AT1, AT2, AT3, AT4) are stored as the history information for each discrete route section (SA1, SA2, SA3, SA4); comparing (420) the history information with a current travel path (FP) in order to recognize a current travel destination (FZ) of the vehicle (10); and controlling (430) at least one vehicle function based on the determined current travel destination (FZ).
10. A storage medium comprising a software program configured to be executed on one or more processors and thereby to execute the driver assistance method (400) according to claim 9.
Citation Information
Patent Citations
systems, methods and apparatus for communicating driving history path attributes
DE102017105792A1
Prediction of vehicle operator destinations
US20050125148A1
System, method and device for predicting navigational decision-making behavior
US20100106603A1
