Method, apparatus, vehicle, and computer program for improving the opening of vehicle flaps.

Abstract

Improve the opening of the vehicle's flaps. [Solution] A method 100 for improving the opening of a vehicle's flaps includes: identifying a user's movement profile relative to the vehicle, which shows a trajectory and the user's movement speed on the trajectory; comparing the user's movement profile with a predetermined movement profile; opening the vehicle's flaps if the user's movement profile matches the predetermined movement profile; saving the identified user's predetermined movement profile; and using the saved user's movement profile to train artificial intelligence to compare the user's movement profiles.

Description

Technical Field

[0001] This disclosure relates to the field of digital vehicle access. Embodiments relate to a method, an apparatus, a vehicle, and a computer program for improving the opening of flaps of a vehicle.

Background Art

[0002] Existing systems for unlocking / opening flaps of a vehicle, such as a tailgate of a trunk or a front edge of a frunk, use so-called smart openers that enable opening, for example, by gestures performed with the foot. In particular, this makes it possible to open the flap without using the hands. Another method uses the detection of the time when a user device is in the immediate vicinity of the door to be opened. In this case, the door can be opened after a predetermined period of time has elapsed.

Summary of the Invention

Problems to be Solved by the Invention

[0003] The user may feel uncomfortable with both the gestures to be performed with the foot and waiting for the door to open. Therefore, there may be a need to improve the opening of flaps of a vehicle.

Means for Solving the Problems

[0004] Therefore, it has been found that the opening of flaps of a vehicle can be improved by comparing a user's movement profile with a predetermined movement profile. The flap can be opened when the user's movement profile matches the predetermined movement profile. In this way, it is possible to reduce misjudgments. Therefore, it is possible to improve the user experience.

[0005] Each example provides a method for improving the opening of a vehicle's flaps. The method includes identifying a user's movement profile relative to the vehicle. The movement profile represents a trajectory and the user's speed along that trajectory. The method also includes comparing the user's movement profile to a predetermined movement profile. The method further includes opening the vehicle's flaps when the user's movement profile matches the predetermined movement profile. By comparing the user's movement profile to the predetermined movement profile, it is possible to identify the user's intent. This allows for the identification of the user's intended use of the flaps in an improved manner.

[0006] In one example, the method may further include saving the user's identified roaming profile and using the saved user roaming profile to train artificial intelligence to compare it to other user roaming profiles. Thus, the comparison of a user's roaming profile with a given roaming profile can be improved by the artificial intelligence. In this way, the likelihood of misclassification events can be further reduced.

[0007] In one example, the method may further include determining the user's distance to the flap. At least one of identifying or comparing the user's movement profile is based on the identified distance. Thus, the user's movement profile can be compared to a given movement profile within a given range. For example, the given range may be a range adjacent to the vehicle where the user's movement profile may be more relevant to identifying the intended use of the flap. This allows for improved identification of user intent, which in turn allows for improved opening of the vehicle's flap.

[0008] In one example, the method may further include identifying a cancellation parameter that indicates a trigger event for canceling the identification of a user's roaming profile. The method may also include canceling the identification of the user's roaming profile based on the cancellation parameter. This makes it possible to identify situations where identifying a user's roaming profile is no longer necessary, and thus the identification of the user's roaming profile can be canceled. In this way, it is possible to reduce the energy consumption for the user's roaming profile.

[0009] In one example, the method may further include receiving profile data representing a general, predetermined mobility profile, and generating custom profile data representing a customized, predetermined mobility profile. The custom profile data is generated based on the profile data. The custom profile data may be customized for the vehicle and / or user. This makes it possible to fit the comparison to the vehicle and / or user. In this way, it is possible to further improve the identification of the user's intent.

[0010] In one example, the method may further include receiving environmental data indicating the vehicle's environment (surroundings) and comparing the user's movement profile based on the environmental data. In this way, a predetermined movement profile used for comparison can be adapted, and / or (for example, if the flap is obstructed by an obstacle) the opening of the vehicle's flaps can be prevented. Thus, the opening of the vehicle's flaps can be adapted to the environment.

[0011] In one example, the method may further include obtaining feedback data indicating user use of an open flap and using the feedback data to train artificial intelligence to compare the user's movement profile. Obtaining feedback data makes it possible to improve the training of the artificial intelligence. In this way, it is possible to improve the comparison of the user's movement profile with a given movement profile.

[0012] Each example relates to a device including an interface circuit and a processing circuit configured to perform the methods described above. Each example relates to a vehicle including the device described above.

[0013] Each example further relates to a computer program having program code for performing the above-described method when the computer program is executed on a computer, processor, or programmable hardware component.

[0014] Some examples of apparatus, methods, and / or computer programs are described below, for illustrative purposes only, with reference to the attached drawings. [Brief explanation of the drawing]

[0015] [Figure 1] This figure shows an example of a method to improve the opening of vehicle flaps. [Figure 2a] This is a diagram showing the proof of the principle. [Figure 2b] This is a diagram showing the proof of the principle. [Figure 2c] This is a diagram showing the proof of the principle. [Figure 2d] This is a diagram showing the proof of the principle. [Figure 2e] This is a diagram showing the proof of the principle. [Figure 2f] This is a diagram showing the proof of the principle. [Figure 3] This is a block diagram of an example of a device, such as a part of a vehicle. [Modes for carrying out the invention]

[0016] When used herein, the term "or" refers to a non-exclusive "or" unless otherwise specified (e.g., "instead" or "alternatively"). Furthermore, when used herein, words used to describe relationships between elements should be interpreted broadly to include direct relationships or the presence of intervening elements unless otherwise specified. For example, when an element is said to be "connected" or "joined" to another element, the element can be directly connected or joined to the other element, or an intervening element may exist. On the other hand, when an element is said to be "directly connected" or "directly joined" to another element, no intervening element exists. Similarly, "between," "adjacent to," and similar words should be interpreted in the same way.

[0017] The terms used herein are for the sole purpose of describing specific embodiments and are not intended to limit the exemplary embodiments. Where used herein, the singular forms "a," "an" (indefinite article), and "the" (definite article) are also intended to include the plural form unless otherwise specified in the context. Furthermore, where the terms "comprise," "comprising," "includes," or "including" are used, they identify the presence of the described feature, integer, step, operation, element, or component, but are not intended to exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, or groups thereof.

[0018] Unless otherwise specified, all terms used herein (including technical and scientific terms) have the same meaning as those generally understood by those skilled in the art to which the exemplary embodiments belong. Furthermore, terms defined, for example, in commonly used dictionaries should be interpreted as having the same meaning as their meaning in the context of the relevant technology, and should not be interpreted in an idealized or overly formal sense unless otherwise explicitly specified herein.

[0019] Figure 1 shows an example of a method 100 for improving the opening of a flap of a vehicle. The method 100 includes identifying 110 a movement profile of a user with respect to the vehicle. The movement profile indicates a trajectory and the user's movement speed in the trajectory. The movement profile can be identified based on sensor data received from sensors, such as sensors of the vehicle or sensors of the infrastructure. For example, the method 100 can include receiving sensor data from the sensors. The sensors of the vehicle and / or the infrastructure can be, for example, ultra-wideband sensors, cameras, RADAR sensors. For example, the movement profile of the user can be identified based on a digital key. The digital key for the vehicle is a digital authentication method that enables the user to access and operate their vehicle without using a physical key. The digital key is in the form of an electronic key that can be stored and transmitted by a user device. For example, the position or trajectory of the digital key can be identified based on ultra-wideband sensor data. The flap can be, for example, a door, a trunk lid, a hood lid.

[0020] Also, the method 100 includes comparing the movement profile of the user with a predetermined movement profile. A predetermined profile can be obtained by a control unit that executes the method 100, for example, by a processing circuit of the control unit. The predetermined movement profile can be loaded from a database, for example, can be obtained from a communication device such as a network node, and can be identified based on the user's previous movement profile.

[0021] The predetermined movement profile can be, for example, a movement profile related to the user, the vehicle, the vehicle type, the vehicle group. The predetermined movement profile can be associated with the user and / or the vehicle. Instead, the predetermined movement profile can be independent of the user or the vehicle. For example, the predetermined movement profile can be a general predetermined movement profile.

[0022] A predetermined movement profile can be identified based on a previous movement profile. For example, a predetermined movement profile can be identified by artificial intelligence. For example, it is possible to identify a predetermined movement profile by a machine learning model.

[0023] A machine learning model is a data structure and / or a set of rules that represent a statistical model used by a processing circuit to identify a predetermined movement profile by relying on the model and inference without using explicit instructions. The data structure and the set of rules represent learned knowledge (information) (e.g., based on training performed by a machine learning algorithm). For example, in machine learning, instead of transformation of data based on rules, transformation of data inferred from analysis of historical data and / or training data can be used. In the proposed technology, the content of the movement profile is analyzed using a machine learning model (e.g., a data structure and / or a set of rules representing the model).

[0024] Machine learning models are trained by machine learning algorithms. A “machine learning algorithm” represents a set of instructions used to create, train, or use a machine learning model. For a machine learning model to analyze the contents of a roaming profile, it can be trained using training roaming profiles and / or historical roaming profiles as input, and training content information (e.g., labels for a given roaming profile) as output. By training a machine learning model with a set of training roaming profiles and associated training content information (e.g., annotation labels), the machine learning model “learns” to recognize the contents of roaming profiles, and therefore can be used to recognize the contents of roaming profiles that are not included in the training data. By training a machine learning model with training roaming profiles and desired outputs, the machine learning model “learns” the transformation between roaming profiles and outputs, and this transformation can be used to provide outputs based on untrained roaming profiles provided to the machine learning model.

[0025] Machine learning models can be trained using training input data (e.g., training movement profiles). For example, machine learning models can be trained using a training method called "supervised learning." In supervised learning, a machine learning model is trained using multiple training samples, each of which can contain multiple input data values ​​and multiple desired output values, for example, each training sample is associated with a desired output value. By specifying the training samples and desired output values, the machine learning model "learns" which output values ​​to provide based on input samples similar to the samples provided during training. For example, a training sample can contain a training movement profile as input data and one or more labels as desired output data. The labels represent a given movement profile.

[0026] Apart from supervised learning, semi-supervised learning can be used. In semi-supervised learning, some training samples lack corresponding desired output values. Supervised learning can be based on supervised learning algorithms (e.g., classification algorithms or similarity learning algorithms). Classification algorithms are limited to a restricted set of values, where the input is classified into one of a restricted set of values ​​(training type, execution quality), and can be used as the desired output of the machine learning model being trained. Similarity learning algorithms are similar to classification algorithms, but are based on learning from multiple examples using a similarity function that measures how similar or related two objects are.

[0027] Apart from supervised or semi-supervised learning, unsupervised learning can be used to train machine learning models. In unsupervised learning, only the input data is provided, and an unsupervised learning algorithm is used to find structures in the input data, such as training movement profiles and / or historical movement profiles (for example, by grouping or clustering the input data to find commonalities in the data). Clustering is the process of assigning input data containing multiple input values ​​into subsets (clusters) such that input values ​​within the same cluster are similar according to one or more (predetermined) similarity criteria, while input values ​​in other clusters are not similar.

[0028] Reinforcement learning is a third group of machine learning algorithms. In other words, reinforcement learning can be used to train machine learning models. In reinforcement learning, one or more software actors (called "software agents") are trained to perform actions in an environment. Rewards are calculated based on the actions performed. Reinforcement learning is based on training one or more software agents to choose actions that increase cumulative rewards, resulting in software agents that become better at a given task (as evidenced by the increasing rewards).

[0029] Furthermore, additional techniques can be applied to several machine learning algorithms. For example, feature learning may be used. In other words, machine learning models can be trained using feature learning, at least partially, and / or machine learning algorithms can include a feature learning component. Feature learning algorithms, which may be called representation learning algorithms, can hold information in their input and can often be transformed in a way that makes it useful as a preprocessing step before performing classification or prediction. Feature learning may be based, for example, on principal component analysis or cluster analysis.

[0030] In some cases, anomaly detection (e.g., outlier detection) can be used with the aim of identifying input values ​​that raise suspicion by being significantly different from the majority of the input or training data. In other words, machine learning models can be trained with anomaly detection, at least partially, and / or machine learning algorithms can include an anomaly detection component.

[0031] In some cases, machine learning algorithms can use decision trees as predictive models. In other words, machine learning models can be based on decision trees. In a decision tree, observations of items (e.g., a set of input movement profiles) can be represented by branches of the decision tree, and output values ​​corresponding to items can be represented by leaves of the decision tree. Decision trees support discrete and continuous values ​​as output values. When discrete values ​​are used, the decision tree represents a classification tree, and when continuous values ​​are used, the decision tree represents a regression tree.

[0032] Correlation rules are a further technique that can be used in machine learning algorithms. In other words, a machine learning model can be based on one or more correlation rules. Correlation rules are created by identifying relationships between variables in a large amount of data. A machine learning algorithm can identify and / or utilize one or more related rules that represent knowledge derived from the data. These rules can be used, for example, to store, manipulate, or apply knowledge.

[0033] For example, a machine learning model can be an artificial neural network (ANN). An ANN is a system inspired by biological neural networks (neural circuits) that can be seen in the retina or brain. An ANN consists of multiple interconnected nodes and multiple connections between nodes, so-called edges. Typically, there are three types of nodes: input nodes that receive input values ​​(e.g., movement profiles, especially the user's position or trajectory and movement speed / velocity), hidden nodes that are connected (only) to other nodes, and output nodes that provide output values ​​(e.g., a given movement profile). Each node represents an artificial neuron. Each edge can transmit information from one node to another. The output of a node can be defined as a (nonlinear) function of its input (e.g., the sum of its inputs). The input of a node can be used in a function based on the "weights" of the edges or nodes that provide the input. The weights of nodes and / or edges can be adjusted during the learning process. In other words, training an ANN may involve adjusting the weights of the ANN's nodes and / or edges to obtain a desired output for a given input, for example.

[0034] Alternatively, the machine learning model may be a support vector machine, a random forest model, or a gradient boosting model. A support vector machine (e.g., a support vector network) is a supervised learning model with a relevant learning algorithm that can be used to analyze data (e.g., classification or regression analysis). A support vector machine can be trained by providing inputs having multiple training input values ​​(e.g., movement profiles, particularly the user's position or trajectory and movement speed / velocity) that belong to one of two categories (e.g., a given movement profile with a high likelihood and a movement profile with a low likelihood of accessing / releasing a flap). A support vector machine can be trained to assign new input values ​​to one of the two categories. Alternatively, the machine learning model may be a Bayesian network, which is a stochastic directed acyclic graphical model. A Bayesian network can represent conditional dependencies using a set of random variables and a directed acyclic graph. Alternatively, the machine learning model may be based on a search algorithm and a genetic algorithm, which is a heuristic method that mimics the process of natural selection. In some examples, the machine learning model may be a combination of the above examples.

[0035] Method 100 further includes opening the vehicle's flap when the user's movement profile matches a predetermined movement profile. The predetermined movement profile may represent the user's intention to access / open the flap. Therefore, when the user's movement profile matches a predetermined movement profile, it can be inferred that the user intends to access / open the flap. Thus, the flap can be opened based on the match between the user's movement profile and the predetermined movement profile. In this way, the user's intention can be identified in an improved manner, and therefore, the opening of the flap can be improved.

[0036] By comparing a user's movement profile with a predetermined movement profile, predictions can be obtained. For example, it is possible to provide automation of vehicle actions, such as opening flaps when a user walks around the vehicle. In this way, the user experience can be improved. For example, it is possible to make the user's life easier because interaction with the flaps is unnecessary. The comparison can be used to activate the flap opening "in a timely manner" if the user is on their path and close enough to the flap.

[0037] By linking the user's trajectory and movement speed, it is possible to improve the reliability of identifying the user's intent. For example, if a user follows a typical trajectory toward a flap without intending to open it (e.g., because the user is passing near the flap), some false opening events may remain. On the other hand, by linking the trajectory and movement speed, it is possible to reduce false opening events. In addition to the user's trajectory, the user's movement speed is considered. For example, movement speed can represent the user's velocity, acceleration, and / or deceleration. Therefore, movement speed can be used as a further indicator to identify the user's intent to access / open the flap.

[0038] In this way, it is possible to identify the user's intention to open and / or access the flaps as early as possible. Furthermore, by considering the user's movement speed, it is possible to reduce the number of false opening events where the user approaches each flap but does not intend to open it.

[0039] For example, a user's deceleration while approaching a flap and subsequent stopping near the flap may represent a typical movement profile of a user who intends to access / release the flap. Therefore, movement speed can help distinguish between use cases where the user intends to access / release the flap and those where they do not.

[0040] For example, a machine learning model used to identify a predetermined movement profile can be used to compare a user's movement profile to that predetermined movement profile. For example, artificial intelligence can be used to compare a user's movement profile to that predetermined movement profile. Alternatively, a different type of artificial intelligence than the one used to identify the predetermined movement profile can be used to compare a user's movement profile to that predetermined movement profile.

[0041] In one example, method 100 may further include saving identified user roaming profiles and using the saved user roaming profiles to train artificial intelligence to compare user roaming profiles. Identified user roaming profiles can be saved in the memory device of a control unit running method 100. In addition to or instead of this, identified user roaming profiles can be saved in a database of other communication devices, such as a server or infrastructure. By using saved user roaming profiles, it is possible to train artificial intelligence so that a given roaming profile is associated with a user. In this way, it is possible to improve the comparison between a user's roaming profile and a given roaming profile. For example, the input values ​​for a machine learning model may be saved user roaming profiles. By using saved roaming profiles, it is possible to adapt a universal approach to identifying user intent to a user-specific approach. Thus, it is possible to consider the user's normal roaming speed / velocity and / or typical approach.

[0042] In one example, method 100 may further include determining the user's distance to the flap. At least one of identifying the user's movement profile or comparing the user's movement profiles is based on the identified distance. For example, the user's distance to the vehicle may be a trigger to initiate the identification and / or comparison of the user's movement profiles. This makes it possible, for example, to identify the user's movement profile only when the user is within a certain distance, e.g., less than 3m from the flap. In this case, only input data obtained within a certain distance, e.g., sensor data indicating the movement profile, can be used to identify the user's movement profile. In this way, energy consumption can be reduced, and the accuracy of the comparison can be improved.

[0043] Furthermore, it is possible to save only the movement profiles that are identified within a certain distance of the user relative to the flap. This could potentially allow for the classification of the user's past behavior as soon as the user approaches the flap below a threshold, for example, less than 2 meters.

[0044] The comparison of the user's movement profile with a predetermined movement profile can be performed multiple times while identifying the user's movement profile. For example, the identification of the user's movement profile can be adjusted by any new received data points, such as some of the sensor data received from a sensor. Therefore, the comparison can also be adjusted by any new received data points. The identification and / or comparison of the user's movement profile may be performed until the classification output indicates the user's intention to access / release the flap.

[0045] For example, the comparison can be based on already identified portions of the user's roaming profile. As soon as a match is detected between a given portion of the identified roaming profile and a given portion of the roaming profile, the flap can be opened. This allows the flap to be opened as soon as the user's intention to access / open the flap is detected.

[0046] In one example, method 100 may further include identifying a cancellation parameter that indicates a trigger event that cancels the identification of a user's movement profile. Method 100 may also include canceling the identification of a user's movement profile based on the cancellation parameter. The cancellation parameter may be a stop trigger that stops tracking of the user's behavior. For example, the cancellation parameter can be used to cancel the identification of a user's intent. The cancellation parameter may be, for example, the user's distance from the flap, or the user's movement speed (especially when the user is close to the flap). For example, if the user is far enough away from the flap, the user will no longer be tracked until the next start trigger, for example, when the user is again within a certain distance from the flap. Thus, if the user's distance from the flap is greater than a threshold, it is possible to cancel the identification and comparison of the movement profile. In this way, it is possible to reduce energy consumption.

[0047] In one example, method 100 may further include receiving profile data representing a user's general predetermined mobility profile and generating custom profile data representing a user's customized predetermined mobility profile. The custom profile data is generated based on the profile data. A user's general predetermined mobility profile can be identified based on training data for multiple users and / or vehicles. For example, a user's general predetermined mobility profile can be used for different users and / or vehicles. This makes it possible to use a user's standard predetermined mobility profile without intensively training resources for each user / vehicle.

[0048] Custom profile data is customized for the vehicle and / or user. By customizing a user's general, predetermined mobility profile, a single classification model can be adapted to multiple vehicle models with different dimensions and / or different users. In this way, it is possible to easily identify the user's mobility offerings.

[0049] For example, to save time in model development and data generation, such as identifying or generating a given user movement profile, it is possible to develop a single model applicable to multiple vehicle models with different dimensions. The trajectory of a general given user movement profile can be specifically preprocessed for the vehicle type. For example, the trajectory can be displaced by a vehicle bounding box. In addition to or instead of this, a flap can be set as the origin of the coordinate system. A vehicle bounding box can be a rectangular box drawn around the outline of a vehicle in an image frame or video frame. Bounding boxes are used in computer vision and machine learning applications for object detection and tracking, and are a means of representing the position and size of an object in an image. A bounding box is defined by its top-left and bottom-right coordinates, which define the corners of the rectangle. The top-left coordinate is the coordinate of the top-left corner of the rectangle, and the bottom-right coordinate is the coordinate of the bottom-right corner of the rectangle. The use of bounding boxes can make it possible to tailor a single model to a specific model for a vehicle type. For example, a user's customized movement profile can be identified based on the user's general movement profile and the vehicle bounding box.

[0050] In one example, the method may further include receiving environmental data indicating the vehicle's environment (surroundings) and comparing the user's movement profile based on the environmental data. In this way, a predetermined movement profile used for comparison can be adapted, and / or (for example, if the flap is obstructed by an obstacle) the opening of the vehicle's flaps can be prevented. Thus, the opening of the vehicle's flaps can be adapted to the environment.

[0051] In one example, the method may further include obtaining feedback data indicating user usage of an open flap and using that feedback data to train artificial intelligence to compare user movement profiles. For example, the feedback data can be used as input data for a machine learning model. In this way, the reliability of the comparison can be improved.

[0052] This method can be performed by a processing circuit, for example, part of a vehicle. The processing circuit may be part of a control unit, for example, a central control unit of the vehicle (such as an engine control unit). The processing circuit can be communicatively connected to a sensor via an interface circuit, for example, to receive sensor data or to determine the position of a digital key.

[0053] Further details and embodiments will be mentioned in relation to the embodiments described later. The example shown in Figure 1 may include one or more additional features of one or more options corresponding to one or more embodiments mentioned in relation to the proposed concept or one or more examples described later (e.g., Figures 2-3).

[0054] Figures 2a to 2f illustrate the proof in principle. Figures 2a to 2c show use cases where the user's trajectory and speed indicate an intention to access / open a flap, such as the trunk lid. Figure 2a shows a vehicle 200 and a trajectory 210a along the rear of the vehicle 200. Figures 2b and 2c show the user's speed at different points on the trajectory 210a. As can be seen in Figures 2b and 2c, the user's speed decreases with increasing point number on the trajectory toward the trunk. Therefore, approaching the trunk may be for the purpose of accessing / opening the trunk lid. Accordingly, for the movement profiles shown in Figures 2a to 2c, opening the trunk should be performed.

[0055] On the other hand, Figures 2d to 2f show a use case with a trajectory 210 that may indicate an intention to access / open a flap, such as the trunk lid. However, the user's speed may not indicate an intention to access / open the trunk lid. As can be seen in Figures 2e and 2f, the user's speed accelerates after a certain point N. Therefore, the speed may be reduced to surround the vehicle 200, but not to access / open the trunk lid. Therefore, since the user does not intend to access / open the trunk lid, the speed may accelerate after passing point N. Thus, by linking the speed of movement to the trajectory, it is possible to reduce the occurrence of misjudgments.

[0056] Further details and embodiments will be mentioned in connection with the embodiments described below. The example shown in Figure 2 may include one or more additional optional features corresponding to one or more embodiments mentioned in connection with the proposed concept or one or more of the above-described (e.g., Figure 1) and / or the (e.g., Figure 3) examples described below.

[0057] Figure 3 shows a block diagram of an example of a device 30 for, for example, a vehicle 40. The device 30 includes an interface circuit 32 and a processing circuit 34 configured to perform the method described above, for example, the method for a vehicle described with reference to Figure 1. For example, the device 30 may be part of the vehicle 40, for example, part of the control unit of the vehicle 40.

[0058] For example, vehicle 40 may be a road vehicle, passenger car, automobile, off-road vehicle, motor vehicle, bus, robotaxis, van, truck, or heavy-duty truck. Alternatively, vehicle 40 may be another type of vehicle, such as a railway, subway, boat, or ship. For example, the proposed concept can be applied to public transport (railways, buses) and future modes of transportation (e.g., robotaxis).

[0059] As shown in Figure 3, each interface circuit 32 is connected to each processing circuit 34 in the apparatus 30. In the example, the processing circuit 34 can be implemented using one or more processing units, one or more processing devices, and any means for processing, such as a processor, a computer, or a programmable hardware component that can be operated by appropriately adapted software. Similarly, the above-described functions of the processing circuit 34 can also be implemented in software, which is executed on one or more programmable hardware components. Such hardware components may include a general-purpose processor, a digital signal processor (DSP), a microcontroller, and the like. The processing circuit 34 can control the interface circuit 32 so that any data transmission occurring through the interface circuit 32 and / or any interaction in which the interface circuit 32 may be involved can be controlled by the processing circuit 34.

[0060] In one embodiment, the device 30 may include a memory and at least one processing circuit 34 operably connected to the memory and configured to perform the method described above.

[0061] In each example, the interface circuit 32 can accommodate any means for acquiring, receiving, transmitting, or providing analog or digital signals or information, such as any connectors, contacts, pins, registers, input ports, output ports, conductors, lanes, etc., that enable the provision or acquisition of signals or information. The interface circuit 32 may be wireless or wired and can be configured to communicate with other internal or external components, such as transmitting or receiving signals or information.

[0062] The device 30 may be a computer, a processor, a control unit, a (field)programmable logic array ((F)PLA), a (field)programmable gate array ((F)PGA), a graphics processing unit (GPU), an application-specific integrated circuit (ASIC), an integrated circuit (IC), or a system-on-a-chip (SoC) system.

[0063] Further details and embodiments are referred to in connection with the embodiments described above. The example shown in Figure 3 may include one or more additional features of one or more options corresponding to one or more embodiments referred to in connection with the proposed concept or one or more examples described above (e.g., Figures 1-2).

[0064] The aspects and features described in relation to one particular example above may be combined with one or more of the other examples to replace identical or similar features in another example, or to introduce additional features to another example.

[0065] Each example may be, or relate to, a (computer) program containing program code for performing one or more of the methods described above when the program is executed on a computer, processor, or other programmable hardware component. Thus, steps, operations, or processes of different methods described above may also be performed by a programmed computer, processor, or other programmable hardware component. Each example may also cover program storage devices such as digital data storage media, which are machine-readable, processor-readable, or computer-readable encoded and / or machine-executable processor-executable or computer-executable programs and instructions. Program storage devices may be, for example, digital storage devices, magnetic storage media such as magnetic disks and magnetic tapes, hard disk drives, or optically readable digital data storage media, or may include these. Other examples may include computers, processors, control units, (field)programmable logic arrays ((F)PLAs), (field)programmable gate arrays ((F)PGAs), graphics processing units (GPUs), application-specific integrated circuits (ASICs), integrated circuits (ICs), or system-on-a-chip (SoC) systems programmed to perform the steps of the method described above.

[0066] It is further understood that the disclosure of certain steps, processes, operations, or functions disclosed herein or in the claims shall not be construed as implying that these operations necessarily depend on the order in which they are described, unless otherwise explicitly stated in the individual cases or required for technical reasons. Therefore, the foregoing description does not limit the execution of any step or function to a particular order. Furthermore, in further examples, a single step, function, process, or operation may include and / or be divided into several substeps, subfunctions, subprocesses, or suboperations.

[0067] If certain embodiments are not described in relation to a device or system, those embodiments should also be understood as descriptions of the corresponding methods. For example, a functional embodiment of a block, device, or device or system may correspond to a feature such as a method step of the corresponding method. Therefore, embodiments described in relation to a method should also be understood as descriptions of the characteristics or functional features of the corresponding block, corresponding element, corresponding device, or corresponding system.

[0068] When several embodiments are described in relation to a device or system, those embodiments should also be understood as descriptions of the corresponding methods, and vice versa. For example, a functional embodiment of a block, device, or device or system may correspond to a feature such as a method step of the corresponding method. Therefore, embodiments described in relation to a method should also be understood as descriptions of the characteristics or functional features of the corresponding block, corresponding element, corresponding device, or corresponding system.

[0069] Each of the following claims is thus included in the detailed description, and each claim may stand alone as a separate example. It should be noted that even if each claim refers to a specific combination of an independent claim with one or more other claims, other examples may also include combinations of the independent claim with any other dependent or independent claim configuration. Thus, such combinations are explicitly proposed unless it is stated in each case that a particular combination is not intended. Furthermore, the configuration of each claim should also include any other independent claim, even if that other independent claim is not directly defined as dependent on the other independent claim.

[0070] The aspects and features described in relation to one particular example above may be combined with one or more of the other examples to replace identical or similar features in another example, or to introduce additional features to another example. [Explanation of Symbols]

[0071] 30 equipment 32 Processing Circuits 34 Interface Circuit 40 vehicles 100 Methods to improve flap opening 110 Identify the mobility profile Comparing 120 movement profiles 130 Open the vehicle's flaps. 200 vehicles 210a,210b orbit

Claims

1. A method (100) for improving the opening of a vehicle's flap, Identifying the user's movement profile relative to the vehicle, which shows the track and the user's movement speed on the track (110), Comparing the user's roaming profile with a predetermined roaming profile (120), and Open the flap of the vehicle when the user's movement profile matches the predetermined movement profile (130) A method (100) characterized by including the following.

2. To save the predetermined roaming profile of the identified user, and Use the saved user's roaming profile to train artificial intelligence to compare the user's roaming profile. The method according to 1 (100), further comprising:

3. The method (100) of 1 or 2, further comprising determining the user's distance to the flap, wherein at least one of determining the user's movement profile or comparing the user's movement profiles is based on the determined distance.

4. Identifying a cancellation parameter that indicates a trigger event for canceling the identification of the user's roaming profile, and Based on the cancellation parameter, the identification of the user's roaming profile is canceled. The method according to 1 or 2 (100), further comprising the following:

5. Receiving profile data that represents a typical, predetermined roaming profile of the user, and Based on the profile data, generate custom profile data that represents a predetermined customized roaming profile for the user. The method according to any one of claims 1 to 4 (100), further comprising the custom profile data being customized for at least one of the vehicle or the user.

6. Receiving environmental data indicating the environment of the vehicle, and Comparing the user's mobility profile based on the environmental data. The method according to any one of claims 1 to 5 (100), further comprising:

7. To obtain feedback data indicating the use of the opened flap by the user, and The feedback data is used to train artificial intelligence in order to compare the user's mobility profile. The method according to any one of claims 1 to 6 (100), further comprising:

8. An apparatus (30) comprising an interface circuit (32) and a processing circuit (34) configured to perform the method described in any one of claims 1 to 7.

9. A vehicle (40; 200) comprising the device (30) described in claim 8.

10. A computer program having program code for executing the method (100) according to any one of claims 1 to 7 when the computer program is executed in a computer, processor or programmable hardware component.

Images