Abstract: A vehicle includes an engine, an electric machine, a torque converter, a weldment, an engine disconnect clutch, and a torque converter lockup clutch. The engine has a crankshaft. The electric machine has a rotor. The torque converter has an impeller and a turbine. The weldment is configured to rotate about an axis and to transfer power from the crankshaft and the rotor to the impeller. The weldment has a first hub, a second hub, a torque converter cover, an impeller housing, and a third hub. The engine disconnect clutch is configured to rotatably connect and disconnect the crankshaft to and from the weldment. The torque converter lockup clutch is configured to rotatably connect and disconnect the turbine to and from the weldment.

Abstract: A system comprises an image sensor with a field of view of an exterior of a vehicle; a human machine interface (HMI) in the vehicle arranged to display images based on data from the image sensor; and a first computer that includes a processor and a memory. The first computer is programmed to provide data from the image sensor to a machine learning program that outputs a bounding box around an object; cause the bounding box around the object to be displayed via the HMI; and transmit object data including an inputted label identifying the object to a second computer that is remote from the vehicle.

Abstract: A system may receive point cloud data that includes one or more data points associated with an object that was detected by sensors of an autonomous vehicle. The system may identify a subset of the point cloud data having data points that are associated with a likelihood of a pedestrian entering a scene with the object, determine a current probability value using a logistic function that is associated with the subset of the point cloud data, determine, based at least in part on the current probability value, a probability value representing a likelihood of the pedestrian actually being present for the subset of the point cloud data, determine whether the probability value exceeds a false alarm threshold value, and in response to the probability value exceeding the false alarm threshold value, assign data points of the subset an attribute value indicative of the pedestrian being present.

Abstract: A system for damping control for a vehicle includes a parameter component and a damping adjustment component. The parameter component is configured to determine one or more driving parameters of a vehicle. The one or more driving parameters include a velocity of the vehicle. The damping adjustment component is configured to adjust damping of suspension of the vehicle during driving based on the one or more driving parameters. The damping adjustment component is also configured to adjust damping of suspension at a zero velocity for a threshold time period in response to transitioning from a non-zero velocity to the zero velocity.

Abstract: Systems and methods for operating an engine that may be selectively automatically stopped and started are described. In one example, the method adjusts an amount of time that the engine may be inhibited from automatically stopping based on driver inputs such as driver demand pedal position, vehicle speed, and braking torque.

Abstract: A sensor is disclosed. The sensor may comprise: a housing, comprising a transmitting coil; and an optic assembly, comprising a body supporting at least one receiving coil and a conductive film that is in electrical contact with the at least one receiving coil, wherein, when the transmitting coil is energized, the at least one receiving coil is wirelessly energized causing a temperature of the film to increase.

Abstract: A deep neural network can provide output from a selected biometric analysis task that is one of a plurality of biometric analysis tasks based on an image. The selected biometric analysis task can be performed in a deep neural network that includes a common feature extraction neural network, a plurality of biometric task-specific neural networks, a plurality of segmentation mask neural networks and an expert pooling neural network that perform the plurality of biometric analysis tasks by inputting the image to the common feature extraction network to determine latent variables. The latent variables can be input to the plurality of biometric task-specific neural networks to determine a plurality of biometric analysis task outputs. The latent variables can be input to a segmentation neural network to determine a facial feature segmentation output. The facial feature segmentation output can be output to a plurality of segmentation mask neural networks.

Abstract: A fleet charging method and system include a plurality of chargers and a controller programmed to predict charge demand for fleet vehicles over a predetermined time interval and generate a charging strategy for the predetermined time interval including selecting at least one of a plurality of power sources for the plurality of chargers from at least a utility grid and a subset of fleet vehicles having stored charge capacity exceeding an associated threshold in response to: a predicted power factor of the utility grid during the predetermined time interval; meeting the predicted charge demand for the fleet vehicles; and minimizing a total energy expense for meeting the predicted charge demand.

Abstract: A system includes a fuel cell stack (FCS) and a controller. The controller adjusts a stack current of the FCS to a desired amount to cause the FCS to provide a power commensurate with a power request. The controller employs a stack power model of the FCS in adjusting the stack current.

Abstract: An assembly for a vehicle includes a front subframe having two frame rails and a control arm connector on each frame rail. The assembly includes a panel supported on the frame rails and spaced vehicle-rearward of the control arm connector. The panel extends cross-vehicle from one of the frame rails to the other of the frame rails. The panel includes a channel elongated along the vehicle-longitudinal axis. The assembly includes a vehicle component spaced vehicle-rearward of the panel. The channel is aimed at the vehicle component.

Abstract: A liveliness prediction output is provided from a liveliness biometric analysis task that is determined by a deep neural network based on an image provided from an image sensor wherein the liveliness biometric analysis task is performed in a deep neural network that includes a common feature extraction neural network and a plurality of task-specific neural networks including a face detection neural network, a body pose neural network and a liveliness neural network including a region of interest (ROI) detection neural network and a texture analysis neural network to determine the liveliness biometric analysis task by inputting the image to the common feature extraction neural network to determine latent variables. The latent variables can be input to the face detection neural network and the liveliness neural network. Output from the face detection neural network can be input to the ROI detection neural network.

Abstract: A fuel cell vehicle includes a bypass valve positioned downstream of a compressor and upstream of a fuel cell stack to selectively direct airflow from the compressor to an exhaust bypassing the fuel cell in an attempt to clear a partially or fully obstructed exhaust pipe. The bypass valve may be opened by a controller when an exhaust throttle valve is at or near a wide-open throttle position. The controller may also increase compressor flow and adjust airflow to the fuel cell stack until compressor pressure, speed, or temperature exceed corresponding limits.

Abstract: A method for producing a multi-layer coating on a substrate for an anode or cathode includes preparing a first mixture including a first solvent and a first active material, preparing a second mixture including a second solvent and a second active material, combining the first mixture and the second mixture to form a slurry, and coating the substrate with the slurry. The first solvent and the second solvent are immiscible.

Abstract: A selected biometric analysis task is performed in a deep neural network that includes a common feature extraction neural network, a plurality of task-specific neural networks, a segmentation neural network, a landmark mesh neural network, a plurality of soft target segmentation neural networks, and a plurality of expert pooling neural networks that perform the plurality of biometric analysis tasks by inputting the image to the common feature extraction network to determine latent variables. The latent variables can be input to the plurality of biometric task-specific neural networks to determine a plurality of first biometric analysis task outputs. The latent variables can be input to a landmark mesh neural network to determine a landmark mesh. The landmark mesh and the first biometric task outputs to a plurality of expert pooling neural networks to determine a plurality of second biometric task outputs.

Abstract: Output can be provided from a selected biometric analysis task that is one of a plurality of biometric analysis tasks based on an image provided from an image sensor. The selected biometric analysis task can be performed in a deep neural network that includes a common feature extraction neural network, a plurality of biometric task-specific neural networks and a plurality of expert pooling neural networks that perform the plurality of biometric analysis tasks by inputting the image to the common feature extraction network to determine latent variables. The latent variables can be input to the plurality of biometric task-specific neural networks to determine a plurality of first outputs. Concatenated first output results can be formed and the concatenated plurality of first result outputs and the latent variables can be input to the plurality of expert pooling neural networks to determine one or more biometric analysis task outputs.

Abstract: A control assembly for a thermal management system for a high voltage battery of a plug-in electric vehicle may include a control valve and a control module. The control valve may be operable to control a flow of battery coolant to the high voltage battery from a refrigerant cooling circuit and from a cabin heater core cooling circuit. The control module may be configured to selectively operate the control valve to select a cooling mode, including a refrigerant only mode, a core mode, and a combined mode in which both the refrigerant cooling circuit and the cabin heater core cooling circuit provide cooling to the high voltage battery.

Abstract: Methods and systems are provided for an accessory drive device. In one example, the accessory drive device comprises an input belt coupled to a pulley of a two-speed device and an output pulley coupled to an output belt configured to provide energy to an alternator or a belt integrated starter generator.

Abstract: A computer-implemented simulation of a virtual hand in a virtual environment can include reading in a hand dataset that is representative of a shape of a real hand of a user, applying the hand dataset to a trained, artificial neural network, and determining an output dataset with the artificial neural network to which the dataset has been applied indicative of forces acting on a virtual object.

Abstract: Methods and systems are provided for an exhaust system. In one example, a method includes heating an aftertreatment device during an engine off. The heating includes utilizing one or more of an injector, a heater, and a recirculation fan.