BMW

The invention relates to a method for a distance (200) and orientation (202) aware agent-to-agent communication between a first machine learning model (204) of a smart edge device (206) of a user and a second machine learning model (208) of a vehicle (210) associated with the user for aiding the user to resolve a user task associated with the vehicle (210), the method comprising the steps of: providing an established wireless communication link (212) between the smart edge device (206) and the vehicle (210); acquiring a distance (200) between the smart edge device (206) and the vehicle (210) and an orientation (202) of the smart edge device (206) with respect to the vehicle (210) using the established wireless communication link (212); and establishing the agent-to-agent communication between the first machine learning model (204) and the second machine learning model (208) based on the acquired distance (200) and orientation (202) for aiding the user to resolve the user task associated with the vehicle (210).

The present disclosure relates to maintaining a drive paths model during operation of a vehicle. The drive paths model is configured to provide environmental awareness regarding a current section of a road to one or more driving automation system features and includes at least one plurality of lane model segments, respectively approximating corresponding lane segments of a corresponding lanes and includes a fore plurality and an aft plurality. To maintain the drive paths model, a curvature profile is derived for a fore distance ahead of the vehicle, which is indicative of a curvature of the current section of the road ahead. Based on the curvature profile, sections of approximately constant curvature change are identified. Then, each fore plurality is maintained to include lane model segments based on the identified sections and each aft plurality is maintained by reassigning lane model segments to each corresponding aft plurality.

The invention relates to a method for optimizing route planning for at least two vehicles (A, B, C, D), comprising the steps of: receiving, by each of the at least two vehicles (A, B, C, D), respective tasks and/or destinations from an external entity (428); connecting, by a server computer (404), with each of the at least two vehicles (A, B, C, D); receiving, by the server computer (404) from each of the at least two vehicles (A, B, C, D), data comprising at least one of a starting point, a current location (W, Y), at least one destination (X, Z), an order of destinations for a required task, a desired schedule for reaching each destination (X, Z), and/or an ending destination for a period of time; evaluating, by the server computer (404), a respective optimized route (204, 206, 208, 210) for each of the at least two vehicles (A, B, C, D) based on an optimization parameter; and communicating (S5), by the server computer (404), the respective optimized route (204, 206, 208, 210) to the respective one of the at least two vehicles (A, B, C, D).

The invention relates to a method of granting access to a mobile device for a vehicle in a digital key vehicle access system, wherein within the vehicle access system the mobile device and the vehicle are adapted to store a digital key in a secure storage in the respective operating system; the vehicle comprises a main electronic control unit, ECU, and an access ECU controlling access to the vehicle, the method comprising the vehicle receiving a request from the mobile device for granting access to the vehicle; the vehicle determining an emergency condition of the vehicle access system; the vehicle requesting a cryptographic confirmation from the mobile device; the mobile device producing the cryptographic confirmation and sending the cryptographic confirmation to the vehicle; the vehicle verifying the cryptographic confirmation; the vehicle granting access to the vehicle depending on the result of the verification of the cryptographic confirmation. Further, the invention relates to a digital key vehicle access system and an access electronic control unit for such a digital key vehicle access system.

Method for outputting information in a vehicle; wherein the method comprises: obtaining an incoming information with a semantic content; generating, based on the semantic content, a summary of the information; wherein generating the summary is performed by a generative machine learning model; and outputting a control signal to user-perceivably output the summary in the vehicle.

Method for outputting information in a vehicle; wherein the method comprises: obtaining an incoming information with a semantic content; determining, based on the semantic content, a privacy information; determining, based on the semantic content and on the privacy information, a summary of the information; and outputting a control signal to user-perceivably output the summary in the vehicle.

The present document describes a device (110) holding a device digital key (111) for controlling one or more vehicle functions (103) of a vehicle (100). The device (110) is configured to generate device authentication data for authenticating the device (110) at the vehicle (100) based on the device digital key (111), and to send the device authentication data to the vehicle (100). Furthermore, the device (110) is configured to determine that the vehicle (100) cannot be authenticated at the device (110), and in reaction to determining that the vehicle (100) cannot be authenticated at the device (110), to limit the control to a restricted set of vehicle functions (103).

The present disclosure relates to a computer-implemented method, to a system and to a computer program for verifying tests to be used for test-driven development of at least one software component of a product, such as at least one software component of a vehicle. The method comprises obtaining (110) a natural language description of one or more requirements to be satisfied by the at least one software component, obtaining (120) a natural-language description or an executable code of one or more tests to be executed for verifying that the at least one software component satisfies the requirements, processing (130), using a large language model, LLM, the natural language description of the one or more requirements to be satisfied and the natural-language description or the executable code of the one or more tests to be executed, wherein the LLM is prompted to verify the one or more requirements to be satisfied and the one or more tests to be executed, and to provide an output based on the verification, and providing (140), via a user interface and based on the output of the large language model, information related to the verification.

The present invention relates to a method for training a machine learning model (200) having a transformer architecture (202), the method comprising: providing (S1) time series training data (203) to the machine learning model (200) as input data (204), the machine learning model (200) processing the time series training data (203) via at least one attention layer (206) of at least one encoder layer (208) of the transformer architecture (202); applying (S2) a dynamic region masking (210) of the time series training data (203) based on attention weights of the attention layer (206) to derive masked training data(212); providing (S3) the masked training data (212) to the machine learning model (200) as input data (204); performing (S4) semi-supervised contrastive learning (214) of a latent space representation (216) of the time series training data (203) and the masked training data (212) derived from the at least one encoder layer (208); and providing (S5) the thereby trained machine learning model (218) for performing a downstream task.

The present document describes a vehicle server (140) configured to manage a digital key (161) for controlling one or more vehicle functions (103) of a vehicle (100). The vehicle server (140) is configured to store target information regarding a target device (180) which is eligible to a shared digital key (181) of the digital key (161) for controlling the one or more vehicle functions (103) of the vehicle (100), and to receive a sharing request from a requesting device for a shared digital key (181) of the digital key (161). Furthermore, the vehicle server (140) is configured to verify, based on the stored target information, whether or not the requesting device is eligible to the shared digital key (181), and to cause a key sharing process for providing the shared digital key (181) on the requesting device to be performed in dependence of the verification on whether or not the requesting device is eligible to the shared digital key (181).