System for adjusting the external appearance of a vehicle

Abstract

The present disclosure relates to a system (100) for adjusting the external appearance of a vehicle (10), comprising: - an input module (110) configured to receive context data (KD1, KD2, KD3, KD4), wherein the context data (KD1, KD2, KD3, KD4) relates to the vehicle (10) and / or a vehicle environment and / or a vehicle user; - an analysis module (120) configured for processing the context data (KD1, KD2, KD3, KD4) using a generative model (GM) to generate output data (AD) indicative of the vehicle's (10) external appearance; and - at least one control module (130) configured to control at least one external optical device of the vehicle (10) based on the output data (AD) or to cause the control of the at least one external optical device in order to adjust the external appearance of the vehicle (10) according to the output data (AD).

Description

[0001] The present disclosure relates to a system for adjusting the external appearance of a vehicle, a vehicle with such a system, a method for adjusting the external appearance of a vehicle, and a storage medium for executing the method. The present disclosure relates in particular to a modifiable vehicle appearance achieved by means of generative artificial intelligence. State of the art

[0002] Customizing a vehicle's exterior appearance, such as color and design, offers numerous advantages. Vehicle owners can make their vehicles unique, reflecting their personal style and taste. Such personalization can lead to greater customer satisfaction, as the vehicles better meet the individual preferences of buyers. However, current technologies for customizing a vehicle's appearance are limited, such as LED lighting systems. These technologies are restricted in their adaptability and often require manual adjustments. Disclosure of the invention

[0003] It is an object of the present disclosure to specify a system for adjusting the external appearance of a vehicle, a vehicle with such a system, a method for adjusting the external appearance of a vehicle, and a storage medium for executing the method, all of which are capable of flexibly adjusting the external appearance of a vehicle. In particular, it is an object of the present disclosure to automatically adapt the external appearance of a vehicle to a current situation.

[0004] This problem is solved by the subject matter of the independent claims. Advantageous embodiments are specified in the dependent claims.

[0005] According to an independent aspect of the present disclosure, a system for adjusting the external appearance of a vehicle, in particular a motor vehicle, is to be specified. The system comprises an input module configured to receive context data, wherein the context data relates to the vehicle and / or a vehicle environment and / or a vehicle user; an analysis module configured to process the context data using a generative model in order to generate output data indicative of the vehicle's external appearance; and at least one control module configured to control, or to cause the control of, at least one external optical device of the vehicle based on the output data in order to adjust the vehicle's external appearance in accordance with the output data.

[0006] According to the invention, a generative model is used to variably and automatically adapt the external appearance of a vehicle based on contextual data using external display elements. This allows the vehicle's appearance to adapt to different environments, driving styles, and / or driver profiles, creating an individual and personalized vehicle aesthetic. Adapting the vehicle's appearance can be particularly advantageous when the vehicle is in a so-called "cold" state, i.e., when not in use. In this state, but also during operation, the vehicle should have an appealing and individual look, for example, to make an impression in a parking lot or garage. Overall, this can improve user satisfaction.

[0007] The input module, the analysis module, and the at least one control module may include software components / algorithms that are set up to run on at least one processor and thereby perform the functionalities of the respective module.

[0008] The input module and / or the analysis module and / or the at least one control module can be implemented in a single software and / or hardware module. Alternatively, the input module and / or the analysis module can each be implemented in separate software and / or hardware modules.

[0009] Preferably, the generative model includes or is a Generative Adversarial Network. A Generative Adversarial Network (GAN) is a type of artificial neural network consisting of two competing networks: a generator and a discriminator. These two networks are trained concurrently and improve each other in a minimax game.

[0010] In some embodiments of the present disclosure, the generative model can receive context data as input (e.g., in text form) and output image-related data as output data ("text-to-image"). The output data is configured such that it enables the at least one external optical device of the vehicle to adjust the vehicle's external appearance according to the context data.

[0011] Preferably, the context data includes first context data and / or second context data and / or third context data and / or fourth context data.

[0012] Preferably, the first context data relates to the vehicle. In some embodiments, the first context data may include or be driving mode information. In particular, the driving mode information may indicate which driving mode from a variety of different driving modes is currently selected and / or preferred by the driver. Driving modes of a vehicle are preset programs that adapt the vehicle's performance and behavior to different driving conditions and driver preferences. Common driving modes include a sport mode, an eco mode, and a comfort mode. However, the present disclosure is not limited to these, and the driving modes may additionally or alternatively include other driving modes, such as an off-road mode and / or a snow mode.These driving modes may vary depending on the vehicle manufacturer and model, but generally offer the possibility to adapt the vehicle's driving behavior to different driving conditions and the driver's preferences.

[0013] Preferably, the second set of contextual data relates to the vehicle's environment.

[0014] In some embodiments, the second context data may include or be data about objects in the vehicle's environment. Examples of objects in the vehicle's environment include, but are not limited to, other road users (e.g., vehicles, pedestrians, cyclists, etc.), obstacles (e.g., barriers, bollards, etc.), animals, objects on the roadway, etc.

[0015] Additionally or alternatively, the second set of contextual data can include data on structures in the vehicle's environment. Examples of such structures include, but are not limited to, traffic infrastructure (roads, curbs, sidewalks, etc.), buildings, and so on.

[0016] Additionally or alternatively, the second set of contextual data can include data about vegetation in the vehicle's surroundings. Examples of vegetation include, but are not limited to, plants, trees, meadows, etc.

[0017] Preferably, the system further comprises an environment sensing module configured to analyze environmental data from the vehicle's environmental sensors using an environment sensing algorithm to generate the second set of contextual data. Preferably, the environmental sensors comprise 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 environmental sensors can provide the environmental data (also referred to as "surrounding data") that maps an area surrounding the vehicle.

[0018] Preferably, the environmental perception algorithm implements a Mask Region-Based Convolutional Neural Network (Mask R-CNN). For example, the vehicle's surroundings can be captured using the vehicle's external cameras, such as those used for parking assistance. The generated data can be analyzed by the Mask R-CNN algorithm to detect, and in particular classify, objects, structures, and / or vegetation in the vehicle's environment.

[0019] Preferably, the third contextual data relates to the vehicle user, in particular the driver of the vehicle.

[0020] In some embodiments, the third contextual data may relate to or indicate a driver's driving style. A driver's driving style describes the characteristic behaviors and patterns exhibited by the driver while operating the vehicle. These behaviors can be influenced by various factors, including personal preferences, experience level, emotional states, and external conditions. Examples of driving styles include, but are not limited to, an aggressive driving style, a defensive driving style, an energy-efficient driving style, a sporty driving style, a rule-abiding driving style, and so on.

[0021] Preferably, the system further comprises a dynamic analysis module configured to analyze vehicle dynamic data (e.g., steering behavior, longitudinal acceleration, lateral acceleration, braking behavior, etc.) using a dynamic analysis algorithm to generate third-party contextual data relating to the driver's driving style. The dynamic analysis algorithm can, for example, be a convolutional neural network (CNN). For instance, the driving style can be determined from data recorded in electronic control units (ECUs), with the CNN being used to derive the driving style from various pieces of information such as steering behavior, longitudinal acceleration, lateral acceleration, and braking behavior.

[0022] Preferably, the fourth set of contextual data also relates to the vehicle user, in particular the driver of the vehicle.

[0023] In some embodiments, the fourth set of contextual data may include or be the driver's personal data. This personal data may, for example, be stored in a user profile and / or elsewhere and be available to the system. For instance, the personal data may include, but is not limited to, demographic data such as age, origin, and other demographic information.

[0024] Preferably, the system further includes a user interface module configured for driver interaction to capture at least some of the driver's personal data. For this purpose, the user interface module can, for example, implement a Large Language Model. The Large Language Model can use the driver interaction and, optionally, the aforementioned information sources (e.g., user profiles, customer master data, etc.) as input to generate the fourth set of contextual data.

[0025] Language language management systems (LLMs) are artificial neural networks distinguished by their ability to generate and understand language. LLMs acquire these abilities by learning statistical relationships from training data, for example, during a self-supervised or semi-supervised training process.

[0026] Preferably, the Large Language Model is implemented in a central unit (e.g., server or backend) and / or in the cloud.

[0027] Preferably, the vehicle, and in particular the system, comprises a communication module. The vehicle's communication module can be configured for communication via a mobile network. The mobile network can be, for example, an LTE network or a 5G network. This allows the vehicle to communicate with the Large Language Model (or the central unit and / or the cloud) via the mobile network in order to implement the functionalities according to the invention.

[0028] The user interface module can comprise at least one output device and at least one input device. For example, the user interface module can be a central information output and input device of an infotainment system, such as a head unit or a pillar-to-pillar display. Preferably, the user interface module is permanently installed in the vehicle.

[0029] The at least one output device may comprise at least one display device and / or at least one loudspeaker. The at least one display device may comprise a display, in particular an LCD display, a plasma display, or an OLED display. Additionally or alternatively, the at least one display device may comprise a projection device configured to display information directly in the driver's field of vision, in particular to project it onto a windshield.

[0030] The at least one input device may include a speech input device and / or a touch-sensitive input device, such as a touch panel or touch pad, and / or a tactile input device, such as a switch (e.g. push button and / or rotary switch) or other mechanically actuated key elements.

[0031] Preferably, the user interface module comprises, or is, a touchscreen that provides at least one output device and at least one input device.

[0032] The at least one control module is configured to control, or to initiate the control of, at least one external optical device of the vehicle based on the output data of the generative model, which is generated based on the context data, in order to adjust the external appearance of the vehicle according to the output data.

[0033] Preferably, it comprises at least one external optical device: - at least one projector; and / or - at least one display; and / or - at least one lamp; and / or - an electrochromic lacquer.

[0034] According to another independent aspect of the present disclosure, a vehicle, in particular a motor vehicle, is specified. The vehicle comprises the system according to the embodiments of the present disclosure.

[0035] The term "vehicle" includes cars, trucks, vans, buses, motorhomes, motorcycles, etc., used for the transport of people, goods, etc. In particular, the term includes motor vehicles for passenger transport.

[0036] According to a further independent aspect of the present disclosure, a method for adjusting the external appearance of a vehicle, in particular a motor vehicle, is specified. The method comprises receiving, by an input module, context data, wherein the context data relates to the vehicle and / or a vehicle environment and / or a vehicle user; processing, by an analysis module, the context data using a generative model to generate output data indicative of the vehicle's external appearance; and controlling, by a control module, at least one external optical device of the vehicle based on the output data to adjust the vehicle's external appearance in accordance with the output data.

[0037] The procedure for adjusting the external appearance of a vehicle can implement aspects of the system for adjusting the external appearance of a vehicle described in this document.

[0038] According to another 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 and to perform the method described in this document for adjusting the external appearance of a vehicle.

[0039] According to another independent aspect of the present disclosure, a storage medium is specified. The storage medium may include a software program configured to run on one or more processors and to execute the method described in this document for setting the external appearance of a vehicle.

[0040] According to another independent aspect of the present disclosure, software with program code is specified. The software is designed to carry out the method for adjusting the external appearance of a vehicle when the software runs on one or more software-controlled devices.

[0041] According to another independent aspect of the present disclosure, a system for adjusting the external appearance of a vehicle is specified. The system comprises one or more processors; and at least one memory connected to the one or more processors and containing instructions that can be executed by the one or more processors to perform the method for adjusting the external appearance of a vehicle described in this document.

[0042] A processor or processor module is a programmable computing unit, i.e., a machine or an electronic circuit that controls other elements according to given instructions and thereby advances an algorithm (process). Brief description of the drawings

[0043] Examples of the manifestation of the revelation are shown in the figures and are described in more detail below. They show: Fig. 1 schematically a vehicle with a system for adjusting the external appearance of a vehicle according to embodiments of the present disclosure, Fig. 2. Schematically, a setting of an external appearance of a vehicle based on context data according to embodiments of the present disclosure, and Fig. 3 a flowchart of a method for adjusting the external appearance of a vehicle according to embodiments of the present disclosure. Implementations of the revelation

[0044] Unless otherwise noted, the same reference symbols are used for identical and equivalent elements in the following.

[0045] Fig. Figure 1 schematically shows a vehicle with a system 100 for adjusting the external appearance of a vehicle 10 according to embodiments of the present disclosure. Fig. Figure 2 schematically shows a setting of an external appearance of a vehicle 10 based on context data KD1, KD2, KD3, KD4.

[0046] The system 100 comprises an input module 110 configured to receive context data KD1, KD2, KD3, KD4, wherein the context data KD1, KD2, KD3, KD4 relate to the vehicle 10 and / or a vehicle environment and / or a vehicle user; an analysis module 120 configured to process the context data KD1, KD2, KD3, KD4 using a generative model GM to generate output data AD indicative of an external appearance of the vehicle 10; and at least one control module 130 configured to control at least one external optical device of the vehicle 10 based on the output data AD, or to initiate the control of the at least one optical device in order to adjust the external appearance of the vehicle 10 according to the output data AD.

[0047] The at least one external optical device may, for example, comprise at least one projector, at least one display, at least one lamp and / or an electrochromic paint; however, the present disclosure is not limited to these.

[0048] The generative model GM can comprise or be a Generative Adversarial Network (GAN). In some embodiments of the present disclosure, the generative model GM, in particular the GAN, can receive the context data KD1, KD2, KD3, KD4 as input (e.g., in text form) and output image-related data as the output data AD ("text-to-image"). The output data AD is configured such that it enables the at least one external optical device of the vehicle 10 to adjust the external appearance of the vehicle 10 according to the context data.

[0049] In a first example, the vehicle can park in a parking space surrounded by autumnal trees. Golden leaves fall from the trees, creating a typical autumnal scene. The vehicle's camera systems recognize this autumnal landscape and interpret it accordingly. The vehicle, an electric and sustainable model, attempts to blend into the landscape like a chameleon. This is achieved by projecting falling leaves onto the sides, screens, projectors, and rear lights.

[0050] In a second example, a sports car can be parked in a snow-covered landscape. As soon as the car approaches or the engine is started, a red glow is projected onto the radiator grille. This creates an effect contrary to the chameleon principle and suits the striking appearance of the sports car.

[0051] In a third example, a vehicle can adapt its appearance to the respective season. In winter, for instance, snowflakes are projected, and in spring, flowers. It reacts to its surroundings and adapts to the colors and patterns of the surrounding buildings or landscape.

[0052] In a fourth example, the appearance of the vehicle can change during sporty driving through dynamic lighting effects or projected speed lines.

[0053] However, the present disclosure is not limited to this example and numerous other possibilities are conceivable in which the vehicle could adapt its external appearance based on the context data KD1, KD2, KD3, KD4.

[0054] The following describes in detail exemplary context data KD1, KD2, KD3, KD4 and their generation.

[0055] Preferably, the context data KD1, KD2, KD3, KD4 comprise first context data KD1 and / or second context data KD2 and / or third context data KD3 and / or fourth context data KD4. First context data KD1

[0056] The initial context data KD1 can relate to the vehicle 10. In some embodiments, the initial context data KD1 can include or be driving mode information. In particular, the driving mode information can indicate which driving mode from a variety of different driving modes is currently selected and / or preferred by the driver. The driving mode information, or the initial context data, can be provided by a corresponding control unit A of the vehicle. Second context data KD2

[0057] The second context data KD2 can relate to the vehicle environment, such as objects (e.g. other road users, obstacles, etc.), structures (e.g. roads, curbs, sidewalks, etc.) and / or vegetation (e.g. plants, trees, meadows, etc.).

[0058] In some embodiments, the system can analyze environmental data from vehicle 10's environmental sensors B using an environmental perception algorithm N1 to generate the second set of contextual data KD2. The environmental perception algorithm N1 can, for example, be a Mask Region-Based Convolutional Neural Network (Mask R-CNN). For instance, the vehicle's surroundings can be captured using the vehicle's external cameras. The generated data can be analyzed by the Mask R-CNN algorithm to detect, and in particular classify, objects, structures, and / or vegetation in the vehicle's environment. Third context data KD3

[0059] The third contextual data KD3 can relate to the vehicle user, especially the driver of the vehicle.

[0060] In some embodiments, the third context data KD3 may relate to or specify a driver's driving style. Examples of driving styles include, but are not limited to, an aggressive driving style, a defensive driving style, an energy-efficient driving style, a sporty driving style, a rule-abiding driving style, etc.

[0061] In some embodiments, the system can analyze 100 dynamic data points from the vehicle using a dynamic analysis algorithm N2 to generate the third contextual data point KD3 relating to the driver's driving style. The dynamic analysis algorithm N2 can, for example, be a convolutional neural network (CNN). For instance, the driving style can be determined from data recorded in control units C, with the CNN being used to derive the driving style from various pieces of information such as steering behavior, longitudinal acceleration, lateral acceleration, and braking behavior. Fourth context data KD4

[0062] The fourth contextual data KD4 can relate to the vehicle user, especially the driver of the vehicle.

[0063] In some embodiments, the fourth context data KD4 may include or be the driver's personal data. This personal data may, for example, be stored in a driver profile FP. The driver profile FP can be, as in the example of... Fig. 2 shown by the system 100 according to the invention. However, the present disclosure is not limited to this and in other embodiments the driver profile FP can be provided externally.

[0064] In some embodiments, a Large Language Model (LLM) can be used to generate the driver profile (FP) and / or the fourth context data (KD4). The Large Language Model (LLM) can take one or more sources (D, E) as input, such as a driver interaction (D) performed via a user interface module. Additionally, demographic data (e.g., customer master data) can be retrieved from a corresponding source (e.g., a central unit (E) of the vehicle manufacturer).

[0065] The Large Language Model can use the driver interaction D and / or the demographic data of the vehicle manufacturer's central unit E as input to generate the driver profile FP and / or the fourth context data KD4.

[0066] Fig.Figure 3 schematically shows a flowchart of a method 300 for adjusting the external appearance of a vehicle according to embodiments of the present disclosure. The method 300 can be implemented by appropriate software that can be executed by one or more processors (e.g., a CPU).

[0067] Method 300 comprises, in block 310, receiving context data by an input module, wherein the context data relates to the vehicle and / or a vehicle environment and / or a vehicle user; in block 320, processing the context data by an analysis module using a generative model to generate output data indicative of an external appearance of the vehicle; and in block 330, controlling at least one external optical device of the vehicle by a control module based on the output data to adjust the external appearance of the vehicle according to the output data.

[0068] According to the invention, a generative model is used to variably and automatically adapt the external appearance of a vehicle based on contextual data using external display elements. This allows the vehicle's appearance to adapt to different environments, driving styles, and / or driver profiles, creating an individual and personalized vehicle aesthetic. Adapting the vehicle's appearance can be particularly advantageous when the vehicle is in a so-called "cold" state, i.e., when not in use. In this state, but also during operation, the vehicle should have an appealing and individual look, for example, to make an impression in a parking lot or garage. Overall, this can improve user satisfaction.

[0069] Although the invention has been further illustrated and explained in detail by means of preferred embodiments, the invention is not limited by the disclosed examples, and other variations can be derived from them by a person skilled in the art without departing from the scope of protection of the invention. It is therefore clear that a multitude of possible variations exist. It is also clear that the embodiments mentioned as examples are truly only examples and are not to be understood in any way as limiting, for example, the scope of protection, the possible applications, or the configuration of the invention.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 leaving the scope of protection defined by the claims and their legal equivalents, such as further explanations in the description.

Claims

[1] System (100) for adjusting the external appearance of a vehicle (10), comprising: - an input module (110) configured to receive context data (KD1, KD2, KD3, KD4), wherein the context data (KD1, KD2, KD3, KD4) relates to the vehicle (10) and / or a vehicle environment and / or a vehicle user; - an analysis module (120) configured for processing the context data (KD1, KD2, KD3, KD4) using a generative model (GM) to generate output data (AD) indicative of the vehicle's (10) external appearance; and - at least one control module (130) configured to control at least one external optical device of the vehicle (10) based on the output data (AD) or to cause the control of the at least one external optical device in order to adjust the external appearance of the vehicle (10) according to the output data (AD). [2] System (100) according to claim 1, wherein the generative model (FM) comprises or is a Generative Adversarial Network. [3] System (100) according to claim 1 or 2, wherein the context data (KD1, KD2, KD3, KD4) comprise first context data (KD1) relating to the vehicle (10), wherein the first context data (KD1) comprise or are driving mode information. [4] System (100) according to any one of claims 1 to 3, wherein the context data (KD1, KD2, KD3, KD4) comprise second context data (KD2) relating to the vehicle environment, wherein the second context data (KD2) comprise: - Data on objects in the vehicle's environment; and / or - Data on structures in the vehicle's environment; and / or - Data on vegetation in the vehicle's surroundings. [5] System (100) according to claim 4, further comprising an environment detection module, wherein the environment detection module is configured to analyze environment data from an environment sensor by means of an environment detection algorithm (N1) in order to generate the second context data (KD2), in particular wherein the environment detection algorithm (N1) implements a Mask Region-Based Convolutional Neural Network. [6] System (100) according to any one of claims 1 to 5, wherein the context data (KD1, KD2, KD3, KD4) comprise third context data (KD3) relating to the vehicle user, wherein the third context data (KD3) relates to a driver's driving style. [7] System (100) according to claim 6, further comprising a dynamic analysis module configured to analyze dynamic data of the vehicle (10) using a dynamic analysis algorithm (N2) to generate the third context data (KD3) relating to the driver's driving style, in particular wherein the dynamic analysis algorithm (N2) implements a Convolutional Neural Network. [8] System (100) according to any one of claims 1 to 7, wherein the context data (KD1, KD2, KD3, KD4) comprise fourth context data (KD4) relating to the vehicle user, wherein the fourth context data (KD4) comprise personal data of the driver. [9] System (100) according to claim 8, further comprising a user interface module (140) configured for driver interaction to capture at least some of the driver's personal data, in particular wherein the user interface module (140) implements a Large Language Model (LLM). [10] Vehicle (10), in particular motor vehicle, comprising the system (100) according to any one of claims 1 to 9. [11] Method (300) for adjusting the external appearance of a vehicle (10), comprising: - Receiving (310) through an input module (110) context data (KD1, KD2, KD3, KD4), wherein the context data (KD1, KD2, KD3, KD4) relate to the vehicle (10) and / or a vehicle environment and / or a vehicle user; - Processing (320), by an analysis module (120), the context data (KD1, KD2, KD3, KD4) using a generative model (GM) to generate output data (AD) that is indicative of an external appearance of the vehicle (10); and - Control (330), by means of a control module (130), at least one external optical device of the vehicle (10) based on the output data (AD) in order to adjust the external appearance of the vehicle (10) according to the output data. [12] Storage medium comprising a software program configured to run on one or more processors and thereby to perform the method (300) according to claim 11.

Images