Abstract: A regression model is trained, and sensor data of a vehicle is processed. Sensor data of an environment is obtained, and a segmentation model is applied to the sensor data to obtain segmented sensor data of an object in the environment. Further, a regression model is applied to the segmented sensor data to determine a steering angle for the vehicle.

Abstract: First fused sensor data is generated by fusing sensor data of the first sensor and of the second sensor. The sensor data for the first fused sensor data is in a first processing state. Second fused sensor data is generated by fusing the sensor data of the first sensor and of the second sensor. The sensor data for the second fused sensor data is in a second processing state. An accuracy of the first and the second fused sensor data is determined. Based on the determined accuracy, the first processing state or the second processing state is selected for fusing sensor data of the first and second sensors.

Abstract: A microkernel-based operating system in a vehicle is initially operated in a first criticality mode of multiple supported criticality modes. In case a condition is determined that requires a transition to a second criticality mode of the multiple supported criticality modes, settings of the microkernel-based operating system are adapted in accordance with the second criticality mode. The microkernel-based operating system is then operated in the second criticality mode.

Abstract: An autonomous/assisted driving system (ADS) obtains a top view representation of labels of a traffic environment in Cartesian coordinates from sample data. The system obtains a transformation matrix for transforming Cartesian coordinates in an observation coordinate system of a perspective of an environmental sensor of the ADS. The transformation matrix is applied to the top-view representation of the labels to obtain a perspective representation of the traffic environment in the observation coordinate system.

Abstract: The present invention relates to a method, to a computer program containing instructions and to an apparatus for performing a boot process for a system that supports redundant copies of boot images. In a first step, an active copy of the boot images is determined (S1). Then the active copy of the boot images is processed (S2). In response to a successful boot process, another copy of the boot images is then set (S3) as the active copy for a subsequent boot process.

Abstract: The present invention is related to a computing device (CD), in particular for automotive applications, with a safe and secure coupling between virtual machines (VMi) and a peripheral component interconnect express device (PCIe-D). The invention is further related to a vehicle comprising such a computing device (CD). The computing device (CD) comprises one or more virtual machines (VMi) and a virtual switch (VS). The virtual switch (VS) is configured to provide a safe and secure coupling between the one or more virtual machines (VMi) and at least one peripheral component interconnect express device (PCIe-D) configured to support single-root input/output virtualization, to which the computing device (CD) is connected.

Abstract: A controller for an agent of a group of agents, in particular for a group of autonomous or semi-autonomous vehicles, and to a computer program implementing such a controller. A temporal deep network for such a controller and to a method, a computer program and an apparatus for training the temporal deep network. The controller includes a temporal deep network designed to calculate a desired trajectory for the agent, a nonlinear model predictive controller designed to calculate commands for the agent based on the desired trajectory and desired trajectories of the other agents of the group of agents, and an augmented memory designed to integrate historic system states of the group of agents for the temporal deep network.

Abstract: A method, a computer program comprising instructions, and a device for processing sensor data in a motor vehicle. An assistance system for a motor vehicle in which a method is implemented, and a motor vehicle having such a system. Sensor data is received. At least one algorithm is applied to the sensor data to determine a first intermediate result. At least one rule is applied to the first intermediate result to determine a second intermediate result. The second intermediate result is evaluated with regard to plausibility. If the second intermediate result is implausible, one or more of the rules applied to the first intermediate result is reversed until the second intermediate result is plausible. The second intermediate result thereby obtained is finally output as an end result.

Abstract: A calibration matrix is determined for a camera for an automotive vehicle. In a first step, at least one object is detected, which moves in a sequence of camera images between image areas having different levels of distortion. In particular, feature tracking can be carried out for the at least one object. To determine the calibration matrix, first an expected perspective-related distortion of the at least one object is calculated. Moreover, an observed distortion of the at least one object is determined. A camera-related distortion of the at least one object is calculated from the observed distortion and the expected perspective-related distortion. A calibration matrix can then be calculated from the camera-related distortion. This matrix can be applied to the camera images. The method steps can then be iteratively repeated until a minimal camera-related distortion is achieved.

Abstract: A flash memory device is re-partitioned over-the-air. A software component responsible for re-partitioning is received. The software component then generates a re-partitioning control structure in the flash memory device and executes re-partitioning steps. The executed re-partitioning steps and currently valid locations of data that needs to be moved in the flash memory device during re-partitioning are recorded in the re-partitioning control structure.

Abstract: A system for checking an inertial measurement unit of a vehicle, in particular a land vehicle, during driving includes the inertial measurement unit having: a first acceleration sensor configured to measure a translational acceleration along a first sensor axis and/or a first rate-of-rotation sensor configured to measure a rate of rotation about the first sensor axis and also a second acceleration sensor configured to measure a translational acceleration along a second sensor axis and/or a second rate-of-rotation sensor configured to measure a rate of rotation about the second sensor axis. A sensing device senses a movement of the vehicle in a first vehicle direction and/or about the first vehicle direction. Both the first sensor axis and the second sensor axis are tilted with respect to the first vehicle direction.

Abstract: A method, a computer program with instructions, and a device for predicting a course of a road based on radar data of a motor vehicle. The radar data to be processed is received and then accumulated in a measuring grid. Subsequently, clusters are formed for objects in the measuring grid. Cluster descriptions are generated for the clusters. The resulting clusters are processed to determine polynomials for describing the road edges. The polynomials are finally output for further use.

Abstract: A threat is detected for a processing system of a motor vehicle. In a first step, driving context data associated with a driving context of the motor vehicle are received. In addition, driving pattern data may be received. Simulated network messages of the motor vehicle are then generated from the driving context data and, if available, the driving pattern data. Finally, by comparing the simulated network messages with actual network messages of the motor vehicle, a threat is detected. In addition, a threat may be predicted from the simulated network messages. In case a threat is detected or predicted, appropriate counter measures may be initiated.

Abstract: A generative adversarial network performs face anonymization. In a first step, an input image showing a face to be anonymized is received. Furthermore, an input vector with control data for face anonymization is received. The generative adversarial network then generates an output image in which the face is anonymized in accordance with the control data of the input vector.

Abstract: To generate code for a system, in a first step, configuration information for the system is retrieved, which describes a system management scheme. Based on this configuration information, code is generated for managers of the system, the code comprising a system management library for each manager, which contains interfaces required by the manager for sending and receiving messages. In addition, code for software platforms of the system is generated, the code comprising a system management router for each software platform, which enables an exchange of messages between managers. Optionally, system management tests may be generated for the system management libraries or the system management routers.

Abstract: A method, a computer program code, an apparatus for processing environmental data of an environment of a vehicle, a driver assistance system, which makes use of such a method or apparatus, and an autonomous or semi-autonomous vehicle comprising such a driver assistance system. Depth data of the environment of the vehicle is received from at least one depth sensor of the vehicle. Furthermore, thermal data of the environment of the vehicle is received from at least one thermal sensor of the vehicle. The depth data and the thermal data are then fused to generate fused environmental data.

Abstract: A processing unit is customized to prevent remote code execution of the processing unit. In a first step, a permutation of an instruction set of the processing unit is determined. Adaptations of the processing unit for implementing the permutation of the instruction set are then determined. Finally, the processing unit is customized in accordance with the determined adaptations.

Abstract: A method, a computer program containing instructions, and an apparatus for qualifying a device driver for a device. After a test environment is initiated, a test on the device driver is performed. This involves a device emulator emulating a behavior of the device under stipulated conditions. During the test, the device emulator performs an error injection or a test on at least one rarely occurring case.

Abstract: Playback of audio data is controlled by: receiving a speech signal to be conveyed to a user simultaneously with playback of the audio data. Volume and/or spectral appearance of selected elements of the audio data are then modified to obtain adjusted audio data, and the adjusted audio data is played back. The received speech signal may then be played back simultaneously with the adjusted audio data.

Abstract: A method to a computer program containing instructions and to a module for monitoring a component of a control system for a transport. In a first step, a function call is sent to the component to execute a function used by the component using defined input data. Then a response from the component to the function call is received. The response is subsequently compared with an expected response. Finally, an action is performed in response to a result of the comparison.