Method for commissioning the calculation of at least one computational task by at least one electronic computing device of a motor vehicle, computer program product, computer-readable storage medium and motor vehicle-external electronic computing device

Abstract

The invention relates to a method for commissioning at least one computational task (2) by at least one electronic computing device (3) of a motor vehicle (4) by means of an external electronic computing device (1), comprising the steps of: determining a current operating mode (7) of the motor vehicle (4) by means of the external electronic computing device (1); determining at least one computational task (2) to be calculated by means of the external electronic computing device (1); transmitting (9) the at least one computational task (2) to be calculated to the motor vehicle (4) depending on the determined operating mode (7) by means of the external electronic computing device (1); and receiving the computational task (9) calculated by the at least one electronic computing device (3) from the motor vehicle (4) by means of the external electronic computing device (1).Furthermore, the invention relates to a computer program product, a computer-readable storage medium and an external electronic computing device (1).

Description

[0001] The following invention relates to a method for commissioning the calculation of at least one computational task by at least one electronic computing device of a motor vehicle by means of an electronic computing device external to the motor vehicle according to the applicable claim 1. Furthermore, the invention relates to a corresponding computer program product, a corresponding computer-readable storage medium and an electronic computing device external to the motor vehicle.

[0002] It is known that most computer-based tasks are performed directly on the vehicle's electronic control units (ECUs) or other electronic computing devices. Nowadays, many of these tasks are outsourced to an external electronic computing device, often referred to as the cloud. The cloud offers even better and more scalable resources. Furthermore, the cloud can provide a wide range of machine learning models.

[0003] Nevertheless, the vehicle still possesses resources and hardware that can be used if needed. These local computing resources can also be used when vehicles are idling or not being driven. This allows for savings on expensive cloud options and their associated computing resources, or their use elsewhere. Furthermore, local resource utilization allows the use of the available energy source / charging option, unlike cloud resource utilization, where the available energy source is unknown. It is therefore conceivable that local charging may have a better CO2 balance. It should also be noted that the use of local computing resources is particularly energy-intensive for electric vehicles.

[0004] US Patent 2023 / 269766 A1 describes a computer-implemented method for training a global machine learning mode using a learning server and a set of vehicle data associated with roadside units. The method includes the steps of selecting vehicle agents from a pool of vehicle agents associated with the roadside units, matching the selected vehicle agents and the roadside units based on the distance between the selected vehicle agents and the roadside units, which are configured to provide distance measurements to the learning server, and transmitting a global model of a selected agent set and deadline thresholds in their global training round to the roadside units, which are configured to transmit the global model and training deadlines to the selected vehicle agents.The associated roadside units calculate the training intervals of the corresponding selected vehicle agents, and the selected vehicle agents train the global model locally and independently using the local data sets collected by the onboard sensors of the selected vehicle agents to generate locally trained models. The procedure further includes aggregating the locally trained models from the selected vehicle agents via the associated roadside units to update the global model until the global model reaches an expected level of precision.

[0005] EP 4 020 925 A1 describes the system and techniques for an information-centric network protocol (ICN) for federated learning. An interest packet can be received on a first interface to initiate a federated learning round. The interest packet contains a participant criterion and the flow of the federated learning round. An entry is created in a PIT (Pending Interest Table) for the interest packet, containing the flow of the federated learning round. The interest packet is forwarded to a series of interfaces according to a Forwarding Information Base (FIB) before the federated learning round concludes. When a data packet is received from a node that meets the participant criterion in response to the interest packet, the data packet is forwarded on the first interface according to the PIT entry.

[0006] A disadvantage of the current state of the art is that federated learning tasks for electronic computing systems in motor vehicles cannot be used in a way that is dependent on the operating mode. Therefore, there is a need in the current state of the art to be able to use the computing resources of a motor vehicle for external computing tasks, depending on the vehicle's operating mode.

[0007] The object of the present invention is to provide a method, a computer program product, a computer-readable storage medium and a motor vehicle-external electronic computing device by means of which computing resources from a motor vehicle can be used for a motor vehicle-independent computing task.

[0008] This problem is solved by a method, a computer program product, a computer-readable storage medium, and an external electronic computing device according to the independent claims. Advantageous embodiments are specified in the dependent claims.

[0009] One aspect of the invention relates to a method for commissioning at least one computational task by at least one electronic computing device of a motor vehicle using an external electronic computing device. The current operating mode of the motor vehicle is determined using the external electronic computing device. At least one computational task to be performed is determined using the external electronic computing device. The at least one computational task to be performed is transmitted to the motor vehicle, depending on the determined operating mode, using the external electronic computing device. The computational task to be performed by the at least one electronic computing device is received by the motor vehicle using the external electronic computing device.

[0010] Thus, the computing resources of the vehicle's at least one electronic computing unit can also be used for computing tasks independent of the vehicle. In particular, the vehicle's external electronic computing unit, which is often implemented as a cloud service, can determine which computing task is transmitted to the vehicle. The vehicle can have at least one electronic computing unit or multiple electronic computing units providing computing resources. Furthermore, it is also possible for multiple computing tasks to be transmitted to the vehicle's electronic computing unit or multiple electronic computing units.

[0011] For example, the vehicle can transmit its status, such as "parked," "loading," or similar, to the external electronic computing device, enabling the device to determine the vehicle's current operating mode. Furthermore, the external electronic computing device can also determine the current operating mode based on the vehicle's position data.

[0012] Furthermore, it can also be provided that, for example, the electronic computing device takes into account which form of energy is used by the vehicle to perform the corresponding calculations. If, for example, predominantly green electricity is used in a vehicle that is at least partially electrically powered to perform the calculations, the vehicle-external electronic computing device can preferentially send the calculation task to the vehicle's electronic computing device, as this ensures that the calculation can be performed with a minimal CO2 footprint.

[0013] In particular, the invention proposes that local computing resources of motor vehicles, especially electric vehicles, be used when they are normally switched off, for example when idling, during a parking process or when charging, for example at one's own charging station with green electricity.

[0014] The goal of the corresponding external electronic computing unit, provided, for example, by a vehicle manufacturer, is to conserve the vehicle's own computing resources. Cloud resources are typically very expensive and are often required by other systems. Vehicles already possess a significant amount of computing resources and electronic computing equipment that could be used for this purpose. It is therefore possible to implement a scheduling system, in particular, whereby the vehicle's local computing resources are used precisely when the vehicle is charging, for example, at a charging station. If a vehicle is connected to a charging station all night, this can be taken into account within the charging management system.The calculation option can be activated when it makes sense from the perspective of load management.

[0015] In particular, a method for the intelligent and efficient distribution of computing resources is provided.

[0016] According to an advantageous embodiment, the calculation task is transmitted when the vehicle is in park mode, which is the operating mode. Specifically, in park mode, the corresponding electronic computing devices, or the vehicle's electronic computing device, are not used for driving. If the vehicle is in park mode, the external electronic computing device can instruct the vehicle's electronic computing device to perform the calculation task. Thus, a period of vehicle inactivity can be used to perform the calculation task.

[0017] Another advantageous design involves transmitting the computational task during charging mode, which is the operating mode. In charging mode, the vehicle is essentially in an idle state. During charging, the vehicle's electronic computing devices can be used to solve the computational task. Furthermore, if, for example, charging takes place at a home charging station powered by green electricity or self-generated solar power, the computational task can be completed in a virtually CO2-neutral manner. This allows for reliable and CO2-neutral processing of the computational task. Additionally, the vehicle's computing resources can be utilized accordingly.

[0018] Furthermore, it can be stipulated that parking time and / or charging time are also taken into account when determining the calculation task to be performed. In particular, this allows, for example, complex calculation tasks to be transmitted to the vehicle according to the parking time and / or charging time. However, if only a short parking time or charging time is planned, only simple calculation tasks can be transmitted to the vehicle. This ensures that the parking time and / or charging time is not extended and that the calculation task can be reliably processed by the vehicle's internal electronic computing unit.

[0019] Another advantageous design feature provides that the computational task to be calculated is transmitted during downhill driving (the operating mode) and / or during future downhill driving (the operating mode). Particularly during downhill driving, or during future downhill driving, an electric vehicle can essentially recover energy through recuperation. This is "green" energy. Therefore, during downhill driving, or during future downhill driving, the corresponding computational task can be calculated in a virtually energy-neutral manner. Thus, for example, the vehicle's computing resources can be made available for navigation planning.For example, if the vehicle has a battery charge capacity of 100 percent and a journey with a correspondingly high level of recuperation is planned, the energy from the recuperation can also be used to calculate at least one of the computational tasks. This allows the calculation to be performed with maximum energy efficiency.

[0020] In a further advantageous embodiment, the current downhill slope and / or the future downhill slope are determined based on navigation data from the vehicle. For example, the navigation data could be the vehicle's current position data. Furthermore, a planned navigation route can be used to determine the current or future downhill slope. This allows for a highly reliable determination of the downhill slope.

[0021] Furthermore, it has proven advantageous to create a schedule for calculating at least one computational task based on historical data regarding the vehicle's operating modes. In other words, a corresponding schedule can be created based on historical data, such as when the vehicle is parked, how long it is parked, when it is charged, how long it is charged, and the like. This allows the scheduling of the computational task to be carried out via the vehicle's external electronic computing device. Thus, it can be determined with a high degree of reliability when, and especially which computational task, is transmitted to the electronic computing device.

[0022] It is also advantageous to consider a potential transmission method for the at least one computational task to be performed, from the vehicle-external electronic computing device to the electronic computing device, and / or the potential transmission method for this at least one computed computational task from the electronic computing device to the vehicle-external electronic computing device. In particular, if, for example, the vehicle is located on a home local network, the computational task can preferably be transmitted to the vehicle, or the computed computational task can be transferred to the vehicle-external electronic computing device. This eliminates the need for complex, slow, and expensive mobile network connections, ensuring that the computational task can be reliably calculated and transmitted to the vehicle-external electronic computing device.

[0023] In a further advantageous embodiment, the transmission of the calculation task is additionally dependent on the vehicle's ambient temperature. In particular, the electronic computing unit generates heat while performing the calculation. If, for example, the ambient temperature is cold, the waste heat from the electronic computing unit can be used to heat the vehicle's interior. Thus, the process can be carried out with maximum energy efficiency.

[0024] Furthermore, it can be stipulated that the time for calculating the computational task is additionally determined based on the vehicle's outside temperature and the date of future vehicle use. In particular, the date of future use can thus be used, for example, to reliably utilize waste heat to heat the vehicle or its interior. This allows the process to be carried out in an energy-efficient manner.

[0025] It is also advantageous if a distributed learning task is transmitted as the computational task to be performed. This distributed learning task is specifically known as federated learning. Vehicles can then further train models they have received, for example, from an external electronic computing unit, particularly at the appropriate time, and the results can then be sent back to the cloud. This allows the corresponding models to be trained in an energy-efficient manner.

[0026] It has also proven advantageous to calculate the weights of the distributed learning task using the electronic computing device. In particular, the results of the calculation, in the form of the weights, can then be sent to the electronic computing device external to the vehicle. Especially when very large amounts of data need to be transmitted, this can preferably be done via a connection in the home network, Wi-Fi, or even in a workshop.

[0027] The presented method is essentially a computer-implemented method. Therefore, a further aspect of the invention relates to a computer program product with program code means which, when the program code means are executed by the electronic computing device, cause it to carry out a method according to the preceding aspect.

[0028] Furthermore, the invention also relates to a computer-readable storage medium containing at least the computer program product according to the preceding aspect.

[0029] A further aspect of the invention relates to an external electronic computing device for commissioning at least one computational task to be performed by at least one electronic computing device of a motor vehicle, wherein the external electronic computing device is configured to carry out the method. In particular, the method is carried out by means of the external electronic computing device.

[0030] Advantageous embodiments of the process are to be regarded as advantageous embodiments of the computer program product, the computer-readable storage medium, and the vehicle-external electronic computing device. The vehicle-external electronic computing device, in particular, possesses tangible features to enable the execution of the corresponding process steps.

[0031] In the present disclosure, a computing unit can be understood, for example, as a data processing device with processing circuits. A computing unit can therefore perform arithmetic operations to process data. These arithmetic operations can also include indexed access to a data structure, such as a lookup table (LUT).

[0032] A computing unit / electronic computing device may, in particular, comprise one or more computers, one or more microcontrollers, and / or one or more integrated circuits, for example, one or more application-specific integrated circuits (ASICs), one or more field-programmable gate arrays (FPGAs), and / or one or more systems on a chip (SoCs). The computing unit may also include one or more processors, for example, one or more microprocessors, one or more central processing units (CPUs), one or more graphics processing units (GPUs), and / or one or more signal processors, in particular one or more digital signal processors (DSPs).The computing unit can also include a physical or virtual cluster of computers or other units mentioned above.

[0033] A processing unit can also include one or more hardware and / or software interfaces and / or one or more memory units. A memory unit can be implemented as volatile data storage, for example as dynamic random access memory (DRAM) or static random access memory (SRAM), or as non-volatile data storage, for example as read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), flash memory or flash EEPROM, or ferromagnetic random access memory (FRAM).a magnetoresistive random access memory, MRAM (magnetoresistive random access memory), or a phase-change random access memory, PCRAM (phase-change random access memory).

[0034] For use cases or application situations that may arise during the procedure and are not explicitly described here, it may be provided that, according to the procedure, an error message and / or a request for user feedback is issued and / or a default setting and / or a predetermined initial state is set.

[0035] The invention also includes combinations of the features of the described embodiments.

[0036] The following describes exemplary embodiments of the invention. The single figure shows: Fig. 1 A schematic flowchart according to one embodiment of the method.

[0037] The embodiments described below are preferred embodiments of the invention. In these embodiments, the described components each represent individual features of the invention that can be considered independently of one another. Each of these features further develops the invention independently and can therefore be considered part of the invention individually or in a combination other than that shown. Furthermore, the described embodiments can also be supplemented by other features of the invention already described.

[0038] In the figure, identical or functionally equivalent elements are provided with the same reference symbols.

[0039] Fig. Figure 1 shows a schematic flowchart according to an embodiment of an external electronic computing device 1, which is particularly depicted in the form of a cloud. The external electronic computing device 1 is configured to commission at least one computational task 2 to be performed by at least one electronic computing device 3 of a motor vehicle 4.

[0040] For this purpose, the vehicle-external electronic computing device 1 has at least one communication module 5 which can communicate with another communication module 6 of the vehicle 4.

[0041] In one embodiment of the method according to the invention, the current operating mode 7 of the motor vehicle 4 is determined by means of the vehicle-external electronic computing device 1. At least one computational task 2 to be calculated is determined by means of the vehicle-external electronic computing device 1. Depending on the determined operating mode 7, the vehicle-external electronic computing device 1 transmits 8 of the at least one computational task 2 to the motor vehicle 4, and the vehicle 4 receives the computational task 9 calculated by the at least one electronic computing device by means of the vehicle-external electronic computing device 1.

[0042] In particular, as in the Fig.Figure 1 shows that in charging mode 10, operating mode 7, the calculation task 2 is transmitted. For example, in this case, the vehicle 4 is connected to a charging station 11 to charge an electrical energy storage device 12 of the at least partially electrically powered vehicle 4. Alternatively or additionally, the calculation task 2 can be transmitted in parking mode, operating mode 7. In this case, it can be provided that a parking time and / or a charging time are also taken into account when determining the calculation task 2. Alternatively or additionally, the calculation task 2 can be transmitted during downhill travel, operating mode 7, and / or during a future downhill travel, operating mode 7. In this case, the current downhill travel and / or the future downhill travel can be determined based on navigation data from the vehicle 4.

[0043] In particular, it may also be provided that, depending on historical data regarding the operating modes 7 of the motor vehicle 4, a schedule for calculating at least one calculation task 2 is created.

[0044] Furthermore, it may also be provided that a potential transmission method of the at least one calculation task 2 to be calculated from the vehicle-external electronic computing device 1 to the electronic computing device 3 and / or a potential transmission method of the at least one calculated calculation task 9 from the electronic computing device 3 to the vehicle-external electronic computing device 1 are taken into account.

[0045] Furthermore, it may be provided that the transmission of the calculation task 2 is additionally dependent on the outside temperature of the vehicle 4. It may also be provided that a time for calculating the calculation task 2 is additionally determined depending on the outside temperature of the vehicle 4 and on the time of a future use of the vehicle 4.

[0046] Furthermore, it may be provided that a distributed learning task is transmitted as the calculation task 2. In particular, it may be provided that the weights of the distributed learning task are calculated using the electronic computing device 3 as the calculation task 2.

[0047] In particular, it is thus described that the local computing resources of the motor vehicle 4, especially designed as an electric vehicle, are used when these would normally be switched off, and, for example, the motor vehicle 4 is idling, parked or charging.

[0048] The primary objective of the vehicle-external electronic computing unit 1 is to conserve corresponding computing resources. These computing resources are typically very expensive. Motor vehicles already possess a significant amount of computing resources, particularly electronic computing units 3, which can be used for this purpose.

[0049] This makes it possible to implement time-based scheduling, whereby the local computing resources of vehicle 4 are used precisely when vehicle 4 is connected to charging station 11, for example. If vehicle 4 remains connected to charging station 11 for the entire night, this can be factored into the charging management process. The computing resources can then be activated when it appears beneficial from a charging management perspective.

[0050] Especially in cooler ambient temperatures, it can be advantageous to preheat vehicle 4 using waste heat before starting the journey. This means that sufficient computing power can be made available and utilized in vehicle 4 before the journey begins to generate the necessary waste heat.

[0051] Furthermore, in so-called federated learning, it is possible to further train corresponding models, which are transferred from the cloud to vehicle 4, for example, using vehicle 4, particularly at the appropriate time. The results can then be sent back to the vehicle-external electronic computing device 1 in the form of weights. If, for example, very large amounts of data need to be sent, this can preferably be done via a connection to Wi-Fi, the home network, or in the workshop.

[0052] It remains possible that an owner or the vehicle itself will be rewarded for providing local computing resources; this can be done in the form of discounts or by unlocking new features.

[0053] The computing resources of vehicle 4 can also be made available for navigation planning. For example, if vehicle 4 has a battery charge capacity of 1 percent and a journey with a lot of recuperation is imminent, such as a downhill drive, the energy from the recuperation can also be used for computing resources. Reference symbol list 1 vehicle-external electronic computing device 2. Arithmetic problem 3 electronic computing device 4 Motor vehicle 5 Communication module 6 additional communication modules 7 Operating mode 8. Transmit 9 calculated arithmetic problem 10 Charging mode 11 charging stations 12 electrical energy storage devices 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 patent literature

[0000] US 2023 / 269766 A1

[0004] EP 4 020 925 A1

[0005]

Claims

[1] Method for commissioning a calculation of at least one computational task (2) by at least one electronic computing device (3) of a motor vehicle (4) by means of an electronic computing device (1) external to the motor vehicle, comprising the steps: - Determining a current operating mode (7) of the motor vehicle (4) using the motor vehicle external electronic computing device (1); - Determining at least one calculation task (2) using the vehicle-external electronic computing device (1); - Transmitting (9) the at least one computational task (2) to be calculated to the motor vehicle (4) depending on the specific operating mode (7) by means of the motor vehicle-external electronic computing device (1); and - Receiving the computational task (9) calculated by the at least one electronic computing device (3) from the motor vehicle (4) by means of the motor vehicle-external electronic computing device (1). [2] Method according to claim 1, characterized by , that in a parking mode as the operating mode (7) the calculation task (2) to be calculated is transmitted. [3] Method according to claim 1 or 2, characterized by , that in a charging mode (10) the operating mode (7) the calculation task (2) to be calculated is transmitted. [4] Method according to claim 2 or 3, characterized by , that additionally a parking time and / or a charging time is taken into account when determining the calculation task (2). [5] Method according to any one of the preceding claims, characterized by , that in the case of a downhill run as the operating mode (7) and / or a future downhill run as the operating mode (7) the calculation task (2) to be calculated is transmitted. [6] Method according to claim 5, characterized by , that the current downhill run and / or the future downhill run is determined on the basis of navigation data from the motor vehicle (4). [7] Method according to any one of the preceding claims, characterized by , that depending on historical data regarding the operating mode (7) of the motor vehicle (4), a schedule is created for calculating at least one computational task (2) to be calculated. [8] Method according to any one of the preceding claims, characterized by , that a potential transmission method of the at least one computational task (2) to be calculated from the vehicle-external electronic computing device (1) to the electronic computing device (3) and / or a potential transmission method of the at least one computational task (9) from the electronic computing device (3) to the vehicle-external electronic computing device (1) is taken into account. [9] Method according to any one of the preceding claims, characterized by , that the transmission of the calculation task (2) is additionally carried out depending on an outside temperature of the motor vehicle (4). [10] Method according to any one of the preceding claims, characterized by , that a time for calculating the calculation task (2) is additionally determined depending on an outside temperature of the motor vehicle (4) and depending on a time of future use of the motor vehicle (4). [11] Method according to any one of the preceding claims, characterized by , that a distributed learning task is transmitted as the calculation task (2). [12] Method according to claim 11, characterized by , that the calculation task (2) is to be performed by calculating the weights of the distributed learning task using the electronic computing device (3). [13] Computer program product with program code means which cause an external electronic computing device (1) to perform a method according to one of claims 1 to 12 when the program code means are processed by the external electronic computing device (1). [14] Computer-readable storage medium comprising at least one computer program product according to claim 13. [15] Motor vehicle external electronic computing device (1) for commissioning a calculation of at least one computational task (2) by at least one electronic computing device (3) of a motor vehicle (4), wherein the motor vehicle external electronic computing device (1) is configured to carry out a method according to one of claims 1 to 12.

Images