Abstract: Described systems and techniques enable anonymous collection of sensor data related to vehicle driving events of a vehicle. A start event of the vehicle may be detected, and an anonymous name may be generated, based on the start event. A subset of the sensor data related to a start-specific event of the vehicle may be extracted. The subset of the sensor data may be stored in an event file for the start-specific event that is designated using the anonymous name, and the event file may be uploaded from the vehicle to an external network.

Abstract: A method comprises: receiving data generated by at least one sensor of a vehicle arranged to generate the data regarding at least one first component of the vehicle; providing the data to at least one failure mode component associated with the at least one first component and configured to determine a likelihood that a condition exists with regard to the at least one first component; quantifying, based on the likelihood, a first state of at least one first system of the vehicle, the first system including the at least one first component; performing, based on the first state, a prognostication that indicates i) a SOH for the at least one first system, and ii) a RUL for the at least one first system; and performing, based at least in part on the SOH and the RUL, at least one action with regard to the vehicle.

Abstract: A method of adapting an automotive audio system to support surround sound comprises: configuring an application program for creation of an audio track object that specifies passthrough mode as a playback mode, wherein the application program is installed to operate under an operating system that is not configured for surround sound; configuring a framework of the operating system with a bypass past a mixer of the operating system, wherein the bypass allows surround-sound data of the audio track object to bypass the mixer; and configuring a hardware abstraction layer with a separate channel for the surround-sound data received from the operating system, wherein the hardware abstraction layer processes the surround-sound data before providing the processed surround-sound data to a decoder.

Abstract: An electric vehicle comprises: a vehicle body; a cavity in the vehicle body, the cavity formed by at least one wall of the vehicle body and by an opening in the vehicle body; a closure configured for closing the opening; an electric motor for propulsion of the electric vehicle; and components that comprise a high voltage battery system, the components mounted to the vehicle body inside the cavity, the high voltage battery system including electrochemical cells powering the electric motor, the high voltage battery system being enclosed by the wall of the vehicle body and the closure and having no standalone pack enclosure.

Abstract: An apparatus comprises: a clamshell configured for holding an electrochemical cell having first and second terminals, the clamshell comprising at least first and second portions hinged to each other; first and second contacts positioned for contacting the first and second terminals, respectively; and a thermoelectric device mounted to the clamshell for controlling a temperature of the electrochemical cell.

Abstract: A vehicle includes a body structure defining an interior cabin and a multi-position seat that is attached to the body structure and includes a seat cushion and a seatback, and a coupling between the seat cushion and the seatback that positions the seatback between an upright position and a maximum reclined position. Left and right halo members are fixedly attached to the body structure, the left halo member having a first restraining surface above, rearward from, and adjacent to a left shoulder of an occupant of the seat when the seatback is positioned in the maximum reclined position, and the right halo member having a second restraining surface above, rearward from, and adjacent to a right shoulder of the occupant when the seatback is positioned in the maximum reclined position.

Abstract: A vehicle includes individual light sources that are separated in space from neighboring light sources. Collimators can collimate light emitted from the light sources, and a first diffusing surface is configured to receive the collimated light and to diffuse the collimated light in a first direction transverse to a first propagation direction of the collimated light. A second diffusing surface is configured to receive the light diffused by the first diffusing surface and to diffuse the received light in a second direction transverse to a second propagation direction of the collimated light.

Abstract: A device comprises: a first fluid channel for a first fluid, the first fluid channel including first barriers; a second fluid channel for a second fluid, the second fluid channel including second barriers; and a thermoelectric module between the first and second fluid channels, the thermoelectric module thermally coupled to each of the first and second fluid channels.

Abstract: In some embodiments, an electric vehicle (EV) includes an energy storage, a navigation system, and a vehicle management system configured to receive, from the navigation system, parameters associated with preconditioning the energy storage for charging, precondition, while travelling to a destination charger and based on the parameters, the energy storage to a target temperature, and charge the energy storage to a target state of energy using the destination charger.

Abstract: A policy file may be received at a vehicle outfitted with a plurality of sensors, the policy file governing a policy for capturing and uploading sensor data from at least one of the plurality of sensors characterizing a driving event of the vehicle. An over the air (OTA) update of a policy manager installed at the vehicle may be executed to install the policy file, the policy manager being configured to analyze the sensor data to detect and capture a subset of the sensor data related to the driving event, based on the policy file. The subset of the sensor data may be recorded in an event file, and the event file may be uploaded to the external network, based on the policy file. Consequently, it is possible to identify, transmit, and analyze driving events, while continuing to use sensor data for autonomous driving and control of a vehicle.

Abstract: A computer-implemented method comprises: receiving camera images and three dimensional (3D) data captured by a first vehicle during travel; obtaining, by providing the camera images to a two-dimensional (2D) object detection algorithm, 2D bounding boxes corresponding to first objects visible in the camera images; obtaining 3D bounding boxes corresponding to second objects in the 3D data; performing association of the 2D bounding boxes with corresponding ones of the 3D bounding boxes using a first neural network; and generating, using the camera images and the 2D bounding boxes associated with corresponding ones of the 3D bounding boxes, training data for training a second neural network to perform 2D and 3D object detection in an advanced driver assistance system (ADAS) for a second vehicle.

Abstract: A computer-implemented method comprises: receiving sensor data collected during operation of a vehicle, the sensor data including images from at least one camera on the vehicle and other sensor data from at least one other sensor on the vehicle; identifying, based on the sensor data, a corner case for a first neural network model of an advanced driver assistance system (ADAS) of the vehicle; filtering the images to identify a subset of the images depicting the corner case, the filtering performed using a second neural network model; labeling the subset of the images with regard to the corner case, wherein a remainder of the images are not labeled; and retraining the first neural network model using the labeled subset of the images and a subset of the other sensor data corresponding to the subset of the images.

Abstract: A system for detecting an anomaly of a vehicle pump. The system receives input parameters comprising at least a pump speed command to a pump of a vehicle at a time t, and an electric current of the pump prior to the time t. The system applies, to the input parameters, a machine learning model, configured to determine one or more output parameters comprising at least a predicted electric current of the pump at the time t, in response to the pump speed command. The system determines, based at least on the predicted electric current of the pump and a sensed electric current of the pump at the time t, whether an anomaly is associated with the pump of the vehicle.

Abstract: Managing camera outputs in an interactive multi-display surrounding view system comprises: receiving outputs from at least four cameras of the vehicle; stitching together the outputs into a first image of a top-down view of vehicle surroundings; adding a three-dimensional (3D) model of the vehicle to the first image, based on the vehicle surroundings, to generate a first enhanced image; and simultaneously presenting (i) the first enhanced image on a first display device of the vehicle, the first display device providing a first touchscreen input control for a first aspect of the first enhanced image, and (ii) a second image on a second display device of the vehicle, the second image comprising one of the outputs, the second display device providing a second touchscreen input control for a second aspect of the second image, wherein the first and second touchscreen input controls accept inputs simultaneously and non-simultaneously with each other.

Abstract: A method comprises: providing, in an onboard charger of an electric vehicle, a direct current (DC) to DC stage including a dual-active bridge having switches arranged in multiple legs, each of the multiple legs controlled by a corresponding one of pulse width modulation (PWM) signals; and dynamically modulating the PWM signals to improve zero voltage switching (ZVS) in the onboard charger.

Abstract: A method comprises: applying, by a motor controller of an electric motor, a bandpass filter to a signal from a sensor on a rotor of the electric motor, the signal indicating rotational speed of the rotor to detect a torsional oscillation or vibration in a driveline of the electric motor to be attenuated; providing the filtered signal to a proportional derivative controller configured for disturbance rejection; generating, by the proportional derivative controller, an attenuation signal for attenuating the torsional oscillation or vibration in the driveline; combining the attenuation signal with a driver torque command signal to produce a combined torque command signal, the driver torque command signal indicating an amount of torque requested from the electric motor; and producing torque with the electric motor based on the combined torque command signal.

Abstract: A vehicle comprises: an advanced driver assistance system (ADAS) generating a command for an aspect of vehicle motion; an actuator for controlling the aspect of the vehicle motion, the actuator connected to the ADAS; and a bias estimator circuit that estimates a bias between the command for the aspect of vehicle motion and an effective vehicle motion aspect, the bias estimator circuit estimating the bias using an operator that predicts a next timestep of nonlinear functions of vehicle state, wherein the command for the aspect of vehicle motion is corrected using the bias estimated by the bias estimator circuit to provide a corrected command for the aspect of vehicle motion for use by the actuator.