METHOD AND CONTROL DEVICE FOR SUPPORTING A USER OF A BATTERY-POWERED MOTOR VEHICLE WHEN USING A CHARGING INFRASTRUCTURE

Abstract

A control device (12) is provided to assist a user (14) of a battery-electric vehicle (10) when using a charging infrastructure. The control device (12) is configured to determine a destination specified by the user (14) for a planned trip with the battery-electric vehicle (10) and to determine an estimated duration of the user's (14) stay at the determined destination.Furthermore, the control device (12) is configured to identify a charging infrastructure in the vicinity of the identified destination in which a battery of the battery electric vehicle (10) can be at least partially charged during the estimated duration of the user's (14) stay at the identified destination, and to provide a control signal for an output of a proposal of the identified charging infrastructure as a modified destination for the user (14) in order to enable the user (14) to at least partially charge the battery of the battery electric vehicle (10) using the proposed charging infrastructure during a stay of the user (14) at the specified destination.

Description

[0001] The present disclosure relates to a control device for assisting a user of a battery-electric vehicle in using a charging infrastructure; a vehicle with a control device as disclosed; the use of an overview matrix with estimated dwell times of several different users at several different destinations to assist a user of a battery-electric vehicle in using a charging infrastructure; and a computer-implemented method for assisting a user of a battery-electric vehicle in using a charging infrastructure. Additionally, or alternatively, a computer program is provided which includes instructions that, when executed by a computer, cause the computer to execute the method, at least partially.Additionally, or alternatively, a computer-readable medium is provided containing instructions which, when executed by a computer, cause it to carry out the procedure at least partially.

[0002] Users of battery-electric vehicles are often interested in maximizing their vehicle's range. In this regard, it can be advantageous to utilize available charging infrastructure and parking times as efficiently as possible to at least partially charge the battery. This can often be challenging or even impossible for users, as they don't always have a complete overview of available charging infrastructure near specific destinations, nor do they always have the opportunity to optimize charging in relation to their intended stay at a particular destination.

[0003] It is known in the prior art to use matrix factorization for generating recommendations and / or suggestions, for example, of films and / or products offered for sale. Matrix factorization can be used to suggest potentially interesting films and / or products to a user based on available data from the same user and / or other users, even though no information about the user's individual preference for the suggested products and / or films is available. An overview of a recommendation system used by Netflix to generate recommendations for video content is described, for example, in an article entitled "Netflix recommendation system: How it works," published online on April 5, 2022, at the following website: https: / / Irecoai.netlnetflix-recommendation-system-how-it-works /

[0004] Background information on the use of matrix factorization in data preparation is described, for example, in a publication by Handschutter et al. entitled “Deep Matrix Factorizations”, published on October 3, 2020 on www.arxiv.orq.

[0005] Against the background of this prior art, the purpose of the present disclosure is to specify a device and / or a method which are each suitable to enrich the prior art.

[0006] The problem is solved by the features of the independent claims. The dependent and subordinate claims each contain optional further developments of the disclosure.

[0007] The task is then solved by a control device to assist a user of a battery-electric vehicle in using a charging infrastructure. The control device is configured to determine a user-specified destination for a planned trip with the battery-electric vehicle. The control device is further configured to determine the user's estimated duration of stay at the determined destination and to identify charging infrastructure in the vicinity of the determined destination where the battery of the battery-electric vehicle can be at least partially recharged during the user's estimated duration of stay at the determined destination.Furthermore, the control device is designed to provide a control signal for the output of a suggestion of the identified charging infrastructure as a modified destination for the user, in order to enable the user to at least partially charge the battery of the battery electric vehicle using the suggested charging infrastructure during a stay of the user at the specified destination.

[0008] The control device or control unit can be part of the driver assistance system or constitute the system itself. The control device can, for example, be an electronic control unit (ECU). The electronic control unit can be an intelligent, processor-controlled unit that can communicate with other modules via a central gateway (CGW) and may form the vehicle's electrical network via fieldbuses such as CAN bus, LIN bus, MOST bus, FlexRay, and / or Automotive Ethernet, for example, together with telematics control units and / or environmental sensors.

[0009] It is conceivable that the control unit manages functions relevant to the vehicle's driving behavior, such as steering, engine control, power transmission, and / or the braking system. Furthermore, driver assistance systems, such as a parking assistant, adaptive cruise control (ACC), lane keeping assist, lane change assist, traffic sign recognition, light signal recognition, hill start assist, night vision assist, and / or intersection assist, can also be controlled by the unit.

[0010] A battery-electric vehicle can be a motor vehicle that can be powered partially or fully electrically using electrical energy stored in a battery. The battery-electric vehicle can be powered primarily or exclusively by the electrical energy stored in the battery.

[0011] A user-defined destination can include a navigation destination specified by the user. This can optionally be entered by the user into the vehicle's navigation system.

[0012] Charging infrastructure can be a facility that enables at least partial charging of the battery of a battery-electric vehicle. Optionally, the charging infrastructure can include one or more charging stations for charging the battery.

[0013] An estimated user stay at a selected destination can be an estimated duration of the user's expected visit. This estimate can be based on the user's history of stays at similar destinations and / or on the duration of stays by other users or individuals at the same and / or similar destinations. Optionally, the estimate can consider the day of the week and / or time of day at which the destination is visited. It can also optionally consider the season and / or time of year, such as whether the destination is visited during a holiday period and / or vacation time and / or during a period of regular business. Optionally, the estimate can also take into account any opening hours of facilities at the destination.Optionally, the destination can be designated as a point of interest (POI), which is also of interest to other people and is regularly visited by other people.

[0014] The area surrounding the destination can extend to a region from which the destination is reachable on foot. Therefore, if charging infrastructure is available nearby, the user may be able to park their battery-electric vehicle at the charging station and then walk to the destination. For example, the area surrounding the destination could extend to a radius of 100 m, 200 m, 500 m, or 1 km.

[0015] The control signal for the output of a suggestion may optionally include a control signal for controlling an output unit, such as a loudspeaker to output an acoustic hint and / or a display to output a visual hint.

[0016] The device described above offers a number of advantages. Among other things, the disclosure provides the advantage that planned rest periods, during which the battery-electric vehicle is parked, can be used for charging the battery. This offers the advantage that any interruptions to a planned journey for charging the battery of the battery-electric vehicle can be reduced, minimized, or even completely avoided. In particular, this offers the advantage that additional effort for the user to charge the battery can be minimized, since charging can be shifted to periods when the user already intends to park and leave the battery-electric vehicle.This can minimize the perceived range limitation due to limited battery capacity, thereby increasing user satisfaction with the range of the battery-electric vehicle and with the battery-electric vehicle itself, and promoting the acceptance of electromobility.

[0017] Possible further developments of the device described above are explained in detail below.

[0018] Determining the estimated duration of a user's stay at a selected destination can be based on an overview matrix containing the estimated durations of stay for multiple different users at various destinations. This offers the advantage of applying existing information gathered from other users to the current user. Optionally, this data can be used in anonymized form. This allows for the collection of large datasets, which can increase the reliability of duration estimates.

[0019] The overview matrix can contain values ​​generated through extrapolation, which were generated using predicted values ​​for the length of stay of certain users at certain destinations contained in the overview matrix. Predicted values ​​can be achieved by using a predictive model, previously trained on the specific user, to forecast the expected length of stay at a location. A prerequisite for this may be that the user has already been there.

[0020] The values ​​generated by extrapolation can be generated using artificial intelligence based on the actual measured values ​​of dwell time of certain users at certain destinations contained in the overview matrix. In other words, other, non-existent values ​​can be generated based on the values ​​present in the overview matrix, optionally using artificial intelligence. Optionally, a generation procedure for unknown values ​​can be carried out, and the resulting figures can then be compared with the known values. In other words, a generation procedure can be used and optimized to generate estimates for the dwell time of individual users at specific destinations, and these estimates can be verified against previously known values.The results of such a review can then be used to further refine and / or optimize the generation process.

[0021] Furthermore, a motor vehicle equipped with the control unit or control device described above will be provided.

[0022] The motor vehicle can be a passenger car, in particular an automobile, or a commercial vehicle, such as a truck.

[0023] The motor vehicle may be automated. The motor vehicle may be designed to take over longitudinal and / or lateral control, at least partially and / or at least temporarily, by means of the control device during automated driving.

[0024] Automated driving can be implemented in such a way that the vehicle's movement is (largely) autonomous. Automated driving can also be controlled at least partially and / or temporarily by the control device.

[0025] It is conceivable that the vehicle actively intervenes in the lateral guidance of the vehicle through a driver assistance system, e.g. by adjusting the actual steering wheel position, and optionally passively, e.g. by displaying a turning instruction.

[0026] The motor vehicle can be a Level 0 autonomous vehicle, i.e., the driver takes over the dynamic driving task, even if support systems (e.g., ABS or ESP) are present.

[0027] The motor vehicle may be a Level 1 autonomous vehicle, i.e., it may have certain driver assistance systems that support the driver in operating the vehicle, such as adaptive cruise control (ACC).

[0028] The motor vehicle can be a Level 2 autonomous vehicle, i.e., so semi-automated that functions such as automatic parking, lane keeping or lateral guidance, general longitudinal guidance, acceleration and / or braking are taken over by driver assistance systems.

[0029] The vehicle can be a Level 3 autonomous vehicle, meaning it is so conditionally automated that the driver does not need to continuously monitor the vehicle system. The vehicle independently performs functions such as activating the turn signals, changing lanes, and / or maintaining lane position. The driver can attend to other tasks but will be prompted by the system to take over driving duties within a reasonable warning period if necessary.

[0030] The vehicle can be a Level 4 autonomous vehicle, meaning it can be so highly automated that the vehicle's control system is permanently taken over. If the system can no longer handle the driving tasks, the driver may be prompted to take over.

[0031] The vehicle can be a Level 5 autonomous vehicle, meaning it is so fully automated that a driver is not required to perform the driving task. No human intervention is necessary except for setting the destination and starting the system. The vehicle can operate without a steering wheel and pedals.

[0032] The above description with reference to the control device also applies analogously to the motor vehicle and vice versa.

[0033] Furthermore, a summary matrix with estimated dwell times of several different users at several different destinations is provided to assist a user of a battery-electric vehicle when using charging infrastructure. The summary matrix contains values ​​generated by extrapolation, which were generated using actual measured dwell times of some users at certain destinations contained in the summary matrix.

[0034] What has been described above with reference to the control device and the motor vehicle also applies analogously to its use and vice versa.

[0035] Furthermore, a computer-implemented method is provided to assist a user of a battery-electric vehicle in using charging infrastructure. The method includes determining a user-specified destination for a planned trip with the battery-electric vehicle. The method also includes determining the user's estimated duration of stay at the determined destination, as well as identifying charging infrastructure in the vicinity of the determined destination where the battery of the battery-electric vehicle can be at least partially recharged during the user's estimated duration of stay at the determined destination.Furthermore, the procedure includes issuing a proposal for the identified charging infrastructure as a modified travel destination for the user, in order to enable the user to at least partially charge the battery of the battery electric vehicle using the proposed charging infrastructure during a stay of the user at the specified travel destination.

[0036] The method can be a computer-implemented method, i.e., one, several or all steps of the method can be performed at least partially by a computer or a data processing device, optionally the control device.

[0037] The above description relating to the control device, the motor vehicle and the use also applies analogously to the procedure and vice versa.

[0038] Furthermore, a computer program comprising commands that, when executed by a computer, cause it to at least partially execute the procedure described above is provided.

[0039] The program code of a computer program can be in any type of code, especially code suitable for controlling motor vehicles.

[0040] What has been described above with reference to the control device, the motor vehicle and the procedure also applies analogously to the computer program and vice versa.

[0041] Furthermore, a computer-readable medium, in particular a computer-readable storage medium, is provided. The computer-readable medium comprises instructions which, when executed by a computer, cause it to at least partially execute the procedure described above.

[0042] This means that a computer-readable medium can be provided that contains a computer program as defined above. The computer-readable medium can be any digital data storage device, such as a USB flash drive, a hard drive, a CD-ROM, an SD card, or an SSD card (or SSD drive / SSD hard drive).

[0043] The computer program does not necessarily have to be stored on such a computer-readable storage medium in order to be made available to the motor vehicle, but can also be obtained via the Internet or other external sources.

[0044] The above description relating to the procedure, the control device, the computer program and the motor vehicle also applies analogously to the computer-readable medium and vice versa.

[0045] The following describes an optional embodiment with reference to Fig. 1 to 6 described. Fig. Figure 1 schematically shows a motor vehicle with a control device as disclosed, according to an optional embodiment; Fig. Figure 2 schematically shows a flowchart of a procedure as disclosed for controlling the operation of the motor vehicle; Fig. Figure 3 schematically shows a matrix factorization; Fig. Figure 4 schematically shows a distribution of user dwell times at a travel destination; Fig. Figure 5 schematically shows an overview matrix; according to an optional embodiment; Fig. Figure 6 schematically shows an extrapolation of values ​​in an overview matrix according to an optional embodiment.

[0046] The in Fig. The motor vehicle 10, shown only schematically, has a control device 10 according to an optional embodiment. The motor vehicle 10 is designed as a battery-electric vehicle.

[0047] The control device 12 according to the optional embodiment is designed to assist a user 14 of the battery-electric vehicle 10 when using a charging infrastructure. The control device 12 is configured to determine a destination specified by the user 14 for a planned trip with the battery-electric vehicle 10.

[0048] Furthermore, the control device 12 is configured to determine an estimated duration of stay of the user at the determined destination and to identify a charging infrastructure in an environment of the determined destination in which a battery of the battery-electric vehicle 10 can be at least partially charged during the estimated duration of stay of the user at the determined destination.

[0049] Furthermore, the control device 12 is configured to provide a control signal for an output of a proposal of the identified charging infrastructure as a modified destination for the user 14, in order to enable the user 14 to at least partially charge the battery of the battery electric vehicle 12 using the proposed charging infrastructure during a stay of the user 14 at the specified destination.

[0050] Determining the estimated length of stay of user 14 at the identified destination can be done on the basis of an overview matrix with estimated lengths of stay of several different users at several different destinations.

[0051] The overview matrix may contain values ​​generated by extrapolation, which were generated using actually measured values ​​of the length of stay of some users at some destinations contained in the overview matrix.

[0052] The values ​​generated by extrapolation may have been generated using matrix factorization.

[0053] The values ​​generated by extrapolation may have been generated using artificial intelligence based on the actual measured values ​​of the length of stay of some users at some destinations contained in the overview matrix.

[0054] Therefore, the control device 12 is designed to also achieve the following with reference to Fig. to carry out the two procedures described in detail.

[0055] The computer-implemented method 200 according to the shown, optional embodiment serves to support a user 14 of a battery-electric motor vehicle 10 when using a charging infrastructure.

[0056] The procedure 200 includes determining 202 a destination specified by the user 14 for a planned journey with the battery-electric vehicle 10.

[0057] Furthermore, the procedure 200 includes determining 204 an estimated duration of stay of the user 14 at the determined travel destination.

[0058] Furthermore, the procedure includes identifying a charging infrastructure in the vicinity of the identified destination, in which a battery of the battery-electric vehicle can be at least partially recharged during the estimated duration of the user's stay at the identified destination.

[0059] Furthermore, the procedure 200 includes issuing 208 a proposal of the identified charging infrastructure as a modified destination for user 14, in order to enable user 14 to at least partially charge the battery of the battery electric vehicle 10 using the proposed charging infrastructure during a stay of user 14 at the specified destination.

[0060] The above can be expressed in other words, and in a possible more concrete form of revelation, as follows, with reference to the Fig. 3 to 6 summarize, whereby the following description is to be interpreted as not restrictive for the disclosure.

[0061] One purpose of matrix factorization is to factor a summary matrix so that the result consists of vectors and matrices in a latent space, optionally in a lower dimension. This can reduce the storage space required for the summary matrix and also fill in missing values ​​in the matrix. An m-dimensional matrix X ∈ ℝ m×n can therefore be expressed by two matrices of the form W ∈ ℝ m×r and H ∈ ℝ r×n can be described so that each value in the matrix X can be approximated as follows: X(:,j)≈∑k=1rW(:,k)H(k,j)for rj=1,…,n

[0062] This can optionally be done using singular value decomposition and / or deep learning approaches. Such a process is possible for r=1, i.e., the latent subspace has dimension 1, in Fig. 3 shown schematically.

[0063] To predict user dwell time, the data can be clustered. This involves using an unsupervised learning method that identifies similarities in the data based on spatial information before calculating an average dwell time within each cluster. The reliability of such a model can be optionally enhanced by adding features such as the time of day and / or day of the week on which the user is expected to visit the specific destination. User habits can also be optionally considered. For example, the model can take into account whether a user is more likely to travel to work at 8:00 AM on a Monday than at 8:00 PM on a Sunday. Therefore, if a user travels to one of the clusters that can be geographically mapped to the points of interest (POIs) or predefined destinations, the model can optionally predict their dwell time.The points of interest (POIs) or destinations can optionally be known locations of interest on an instance basis (e.g., a specific supermarket) and / or simply classified clusters (e.g., a set of points that can represent a supermarket). Providing information about the type of destination, such as an associated POI class, is not strictly required by the disclosure, but can optionally increase the reliability of determining dwell time. If the model only uses information regarding the historical data of the respective user, this can primarily determine the user's dwell time at a destination or POI known to the user.

[0064] To extrapolate the knowledge of different users, an overview matrix can be created containing information on the various users and destinations, optionally including a length-of-stay quantile (e.g., q1). The length-of-stay quantile can represent a quantile of the length-of-stay distribution at the respective destination and optionally describe it semantically. In the case of the 1st percent quantile, this could mean that the user will spend at least the length of stay determined by q1 at the destination in 99% of cases. Fig. Figure 4 illustrates this in a schematic diagram. The horizontal axis shows an approximate dwell time, and the vertical axis shows the probability that the user will leave the destination after the respective dwell time has elapsed. The vertical lines represent a lower and an upper limit of a defined reliability interval.

[0065] If this is done for multiple destinations and multiple users, a corresponding overview matrix of 500 dwell times can be created, as schematically shown in Fig. Figure 5 illustrates this. The vertical columns of the matrix are assigned to different users, and the horizontal rows to different destinations. The overview matrix 500 is not completely populated with values ​​because many destinations are unknown to some users. To generate the missing information—that is, the length of stay of users at a destination they have never visited—the entries of the overview matrix 500 can be extrapolated using matrix factorization (MF) to generate the remaining values ​​as described above. This is shown schematically in Figure 5. Fig. 6 shown.

[0066] The aim of the procedure can be to increase the benefit for the user by providing the user with suggestions for using charging infrastructure in a way that the user would otherwise only be able to have with comprehensive knowledge of the charging infrastructure at the destination.

[0067] An example use case would be a user driving their battery-electric vehicle to a supermarket while on vacation. The supermarket is a destination completely unknown to the user, and they have no information about nearby charging infrastructure. A backend-calculated overview matrix (500) containing dwell times can be used to compare the user's dwell times at other locations with those of other users at the same locations, suggesting that the user is likely to stay for at least 15 minutes. An optional radius search allows the model to detect that a DC fast charging station is located just a two-minute walk from the supermarket.By optionally considering a user's past response to charging offers, it may be possible to calculate a user-specific threshold that describes their willingness to travel to a different location than their originally planned destination. This can be helpful because, optionally, users with a home charging station are less interested in available public charging infrastructure than other users, as they can recharge their battery upon returning home, potentially at a lower price.

[0068] Assuming a user's threshold for an available DC charging station is one minute, the user could receive a notification informing them of the upcoming charging opportunity and asking if they would like to change their route to the charging station instead of their current destination. If they agree, the battery could optionally be pre-conditioned so that the vehicle can charge at maximum power at the charging station, allowing the user to use their parking time for charging, which can increase the perceived range of their battery-electric vehicle. Reference symbol list 10 battery-electric motor vehicle 12 Control device 14 users 200 procedures 202 - 208 Procedural steps 500 Overview Matrix QUOTES INCLUDED IN THE DESCRIPTION

[0000] This list of documents cited by the applicant was automatically generated and is included solely for the reader's convenience. The list is not part of the German patent or utility model application. The DPMA accepts no liability for any errors or omissions. Cited non-patent literature

[0000] Netflix recommendation system: How it works”: https: / Irecoai.netlnetflix-recommendation-system-how-it-works

[0003] Handschutter et al. described “Deep Matrix Factorizations”, published on 3 October 2020 on www.arxiv.org

[0004]

Claims

[1] Control device (12) for assisting a user (14) of a battery-electric motor vehicle (10) when using a charging infrastructure, wherein the control device (12) is configured to: - to determine a destination determined by the user (14) for a planned journey with the battery-electric motor vehicle (10); characterized by that the control device (12) is further configured to: - to determine an estimated length of stay of the user (14) at the identified destination; - to determine a charging infrastructure in the vicinity of the determined travel destination in which a battery of the battery-electric motor vehicle (10) can be at least partially charged during the estimated duration of the user (14) at the determined travel destination; and - providing a control signal for outputting a suggestion of the determined charging infrastructure as a modified travel destination for the user (14) in order to enable the user (14) to at least partially charge the battery of the battery-electric motor vehicle (10) by means of the suggested charging infrastructure during a stay of the user (14) at the specific travel destination. [2] Control device (12) according to claim 1, characterized by that the determination of the estimated length of stay of the user (14) at the determined travel destination is carried out on the basis of an overview matrix (500) with estimated lengths of stay of several different users at several different travel destinations. [3] Control device (12) according to claim 2, characterized bythat the overview matrix (500) contains values generated by means of extrapolation, which were generated using actually measured values of the length of stay of some users at some travel destinations contained in the overview matrix (500). [4] Control device (12) according to claim 3, characterized by that the values generated by extrapolation were generated using matrix factorization. [5] Control device (12) according to claim 3 or 4, characterized by that the values generated by extrapolation were generated using artificial intelligence on the basis of the actually measured values of the length of stay of some users at some destinations contained in the overview matrix (500). [6] Motor vehicle (10), characterized by that the motor vehicle (10) comprises the control device (12) according to one of claims 1 to 5. [7] Use of an overview matrix (500) with estimated stay times of several different users at several different travel destinations to support a user of a battery-electric motor vehicle (10) when using a charging infrastructure, wherein the overview matrix (500) contains values generated by means of extrapolation, which were generated using actually measured values of the stay time of some users at some travel destinations contained in the overview matrix (500). [8] Computer-implemented method (200) for assisting a user (14) of a battery-electric motor vehicle (10) in using a charging infrastructure, the method (200) comprising: - determining (202) a destination determined by the user (14) for a planned journey with the battery-electric motor vehicle (10); characterized by that the method (200) further comprises: - determining (204) an estimated length of stay of the user (14) at the determined travel destination; - determining (206) a charging infrastructure in an environment of the determined travel destination in which a battery of the battery-electric motor vehicle (10) can be at least partially charged during the estimated duration of the user (14) at the determined travel destination; and - Outputting (208) a suggestion of the determined charging infrastructure as a modified travel destination for the user (14) in order to enable the user (14) to at least partially charge the battery of the battery-electric motor vehicle (10) by means of the suggested charging infrastructure during a stay of the user (10) at the specific travel destination. [9] Computer program, characterized by that the computer program comprises instructions which, when the program is executed by a computer, cause the computer to carry out the method (200) according to claim 8. [10] Computer-readable medium, characterized by that the computer-readable medium comprises instructions which, when executed by a computer, cause the computer to carry out the method (200) according to claim 8.

Images