Abstract: Methods and systems are provided for increasing an accuracy of anomaly detection in assets such as vehicle components. In one example, a method provides for continuous health monitoring of connected physical assets, comprising adapting thresholds for anomaly detection and root cause analysis algorithms for the connected assets based on an aggregation of new connected data using machine learning; updating and ranking advanced statistical and machine learning models based on their performance using connected data until confirming a best performing model; and deploying the best performing model to monitor the connected physical assets.

Abstract: A method includes obtaining state information from one or more sensors of a digital twin. The method includes determining an action at the first routing control location based on the state information, where the action includes one of a pallet merging operation and a pallet splitting operation, and determining a consequence state based on the action. The method includes calculating a transient production value based on the consequence state and a transient objective function, calculating a steady state production value based on the consequence state and a steady state objective function, and selectively adjusting one or more reinforcement parameters of the reinforcement learning system based on the transient production value and the steady state production value.

Abstract: A computer includes a processor and a memory, the memory storing instructions executable by the processor to input a signal received from a portable device to a machine learning program trained to output a location of the portable device relative to a vehicle, collect operating data of one or more vehicle components, predict an action of a vehicle user based on the predicted location, and, based on the predicted action of the vehicle user, actuate one or more vehicle components. The machine learning program is trained with a training dataset that is updatable to include the signal, the output predicted location, the collected operating data, the predicted action, and an identified action performed by the vehicle user.

Abstract: A computer, including a processor and a memory, the memory including instructions to be executed by the processor to train a neural network included in a memory augmented neural network based on one or more images and corresponding ground truth in a training dataset by transforming the one or more images to generate a plurality of one-hundred or more variations of the one or more images including variations in the ground truth and process the variations of the one or more images and store feature points corresponding to each variation of the one or more images in memory associated with the memory augmented neural network. The instructions can include further instructions to process an image acquired by a vehicle sensor with the memory augmented neural network, including comparing a feature variance set for the image acquired by the vehicle sensor to the stored processing parameters for each variation of the one or more images, to obtain an output result.

Abstract: Systems and methods for automotive shape design by combining computational fluid dynamics (CFD) and Generative Adversarial Network (GAN). CFD simulations may be performed to determine aerodynamic properties and identify a set of candidate vehicle outline shapes. Vehicle shape outlines may be provided as input to a generative adversarial network (GAN) that is trained to learn aesthetic preferences for vehicle attributes. The GAN may be used to determine, by based on the vehicle outline shape, a set of vehicle attributes. The GAN may be used to generate photo-realistic images with the vehicle shape outline and filling in additional aesthetic styles for the given outline, such as different colors, lighting, visual appearance, wheel design, aspect ratio, etc.

Abstract: A method includes obtaining sensor data from a plurality of sensors disposed at a plurality of routing control locations of an environment, where the sensor data is indicative of a number of a plurality of pallets at the plurality of routing control locations. The method includes calculating a plurality of difference values based on the sensor data, calculating a transient production value based on the sensor data and a transient objective function, and calculating a steady state production value based on the sensor data and a steady state objective function. The method includes generating a state vector based on the plurality of difference values, the transient production value, and the steady state production value, and defining a set of routes for a set of pallets from among the plurality of pallets based on the state vector and a digital twin of the environment.

Abstract: A method includes obtaining state information from one or more sensors of a digital twin. The method includes determining an action at the first routing control location based on the state information, where the action includes one of a pallet merging operation and a pallet splitting operation, and determining a consequence state based on the action. The method includes calculating a transient production value based on the consequence state and a transient objective function, calculating a steady state production value based on the consequence state and a steady state objective function, and selectively adjusting one or more reinforcement parameters of the reinforcement learning system based on the transient production value and the steady state production value.

Abstract: A method includes defining a sensor layout of a digital twin based on one or more sensor parameters and one or more routing control locations of the digital twin. The method includes simulating a manufacturing routine of a plurality of pallets and a plurality of workstations based on one or more pallet parameters associated with the plurality of pallets and one or more workstation parameters associated with the plurality of workstations and calculating, for each routing control location from among the one or more routing control locations, a transient production value and a steady state production value based on the manufacturing routine. The method includes iteratively adjusting the sensor layout of the digital twin until each transient production value is less than or equal to a threshold transient production value and each steady state production value is less than or equal to a threshold steady state production value.

Abstract: A server includes an interface configured to communicate with a plurality of vehicles; and a processor, programmed to, send a query to the plurality of vehicles, the query identifying types of vehicle data and indicating an initial sampling rate, responsive to receiving the vehicle data sampled by the vehicles, process the vehicle data to obtain a feature result including an estimated value and a variance extending from the estimated value, and responsive to the variance being greater than a first threshold, send a first updated query indicating an increased sampling rate to the plurality of vehicles.

Abstract: A method including generating a plurality of synthetic images of a material, where each synthetic image from among the plurality of synthetic images is associated with a feasibility value greater than a threshold synthetic feasibility value. The method includes determining, for each synthetic image from among the plurality of synthetic images, one or more material properties of the material and one or more process parameters of the material based on the synthetic image and generating a plurality of data points and a pareto surface based on the one or more material properties and the one or more process parameters. The method includes selecting a target data point based on the plurality of data points and a distance between a set of data points from among the plurality of data points and the pareto surface.

Abstract: An image including a vehicle seat and a seatbelt webbing for the vehicle seat is obtained. The image is input to a neural network trained to, upon determining a presence of an occupant in the vehicle seat, output a physical state of the occupant and a seatbelt webbing state. Respective classifications for the physical state and the seatbelt webbing state are determined. The classifications are one of preferred or nonpreferred. A vehicle component is actuated based on the classification for at least one of the physical state of the occupant or the seatbelt webbing state being nonpreferred.

Abstract: Methods and systems are provided for increasing an accuracy of anomaly detection in assets such as vehicle components. In one example, a method provides for continuous health monitoring of connected physical assets, comprising adapting thresholds for anomaly detection and root cause analysis algorithms for the connected assets based on an aggregation of new connected data using machine learning; updating and ranking advanced statistical and machine learning models based on their performance using connected data until confirming a best performing model; and deploying the best performing model to monitor the connected physical assets.

Abstract: Methods and systems are provided for monitoring a health of a vehicle component. In one embodiment, a method is provided, comprising dividing a population of vehicles of a connected vehicle population into a plurality of vehicle classes; for each vehicle class of the plurality of vehicle classes, training a class-specific model of the vehicle class to predict a health status variable of a vehicle component included in the vehicle class based on labelled data from historic databases and calibration data; and for each vehicle class of the plurality of vehicle classes, using a first Federated Learning strategy to request local model data from each vehicle of a plurality of vehicles of the vehicle class; receive the local model data from the plurality of vehicles; update the class-specific model based on the received local model data; and send updated parameters of the class-specific model to vehicles included in the vehicle class.

Abstract: A plurality of thermal images forward of a vehicle are collected. Thermal data in the plurality of thermal images is normalized based on an ambient air temperature to generate a plurality of normalized thermal images. The plurality of normalized thermal images are input to a machine learning program trained to output an identification of an object based on the ambient air temperature and a risk of collision between the vehicle and the object. A vehicle component is actuated based on the identification of the object and the risk of collision with the object.

Abstract: A vehicle includes an engine, a clutch, and a controller. The clutch is configured to crank the engine during an engine start. The controller is programmed to, in response to a command to start the engine, adjust a clutch actuator pressure to drive a disconnect clutch torque toward a desired value. The controller is further programmed to, in response to variances of the disconnect clutch torque relative to the clutch actuator pressure exceeding a threshold, issue a disconnect clutch fault.

Abstract: A method includes detecting, for each of a plurality of images, a plurality of key points, where each of the plurality of images represents an object of an assembly system. The method includes generating, for each of the plurality of images, a correspondence between the plurality of key points, and generating, for each of the plurality of images, a reference region based on the correspondence between the plurality of key points. The method includes identifying, for each of the plurality of images, a reference key point among the plurality of key points based on the reference region, and determining a pose of the object based on the reference key point of each of the plurality of images and a reference pose of the object.

Abstract: An identifier for first set of display content on a vehicle display is input to a statistical model that outputs a plurality of probabilities that a user input will select each of a plurality of second set of display contents for display after the first set of display content is displayed. A first probability is identified for a predicted set of display content that is a highest probability in the plurality of probabilities. The plurality of probabilities are provided to at least one of an optimization model and a neural network upon determining an accuracy of the statistical model is below a threshold. Upon receiving, from the at least one of the optimization model and the neural network, a second probability for the predicted set of display content, the display content is selected based on the first and second probabilities. The vehicle display is updated based on the selected set of display content.

Abstract: A computer includes a processor and a memory, the memory storing instructions executable by the processor to input a signal received from a portable device to a machine learning program trained to output a location of the portable device relative to a vehicle, collect operating data of one or more vehicle components, predict an action of a vehicle user based on the predicted location. and, based on the predicted action of the vehicle user, actuate one or more vehicle components. The machine learning program is trained with a training dataset that is updatable to include the signal, the output predicted location, the collected operating data, the predicted action, and an identified action performed by the vehicle user.

Abstract: A method includes detecting, for each of a plurality of images, a plurality of key points, where each of the plurality of images represents an object of an assembly system. The method includes generating, for each of the plurality of images, a correspondence between the plurality of key points, and generating, for each of the plurality of images, a reference region based on the correspondence between the plurality of key points. The method includes identifying, for each of the plurality of images, a reference key point among the plurality of key points based on the reference region, and determining a pose of the object based on the reference key point of each of the plurality of images and a reference pose of the object.

Abstract: A computer, including a processor and a memory, the memory including instructions to be executed by the processor to train a neural network included in a memory augmented neural network based on one or more images and corresponding ground truth in a training dataset by transforming the one or more images to generate a plurality of one-hundred or more variations of the one or more images including variations in the ground truth and process the variations of the one or more images and store feature points corresponding to each variation of the one or more images in memory associated with the memory augmented neural network. The instructions can include further instructions to process an image acquired by a vehicle sensor with the memory augmented neural network, including comparing a feature variance set for the image acquired by the vehicle sensor to the stored processing parameters for each variation of the one or more images, to obtain an output result.