Abstract: A system in a vehicle includes a personal thermal device. The personal thermal device provides heating or cooling to an individual occupant of the vehicle. The system also includes a controller implementing reinforcement learning to control the personal thermal device. The controller obtains states, from one or more sensors, indicating current conditions, to obtain a score that is determined according to the states and that represents a reward used in the reinforcement learning. The controller provides a stochastic policy indicating a probability of taking a particular action to control the personal thermal device based on the score acting as a feedback for feedback control of the personal thermal device using the reinforcement learning.

Abstract: Aspects of the disclosed technology provide solutions for generating synthetic driving scenarios using text-based inputs that describe an intended operating goal. A process of the disclosed technology can include steps for generating a first synthetic scene for testing an autonomous vehicle (AV), providing the first synthetic scene to a first machine-learning model to generate a first text description of the synthetic scene, and providing the first text description to a second machine-learning model to determine if the first text description aligns with the predetermined operating goal for the AV. In some aspects, the process can further include generating a second text description for the synthetic scene, if the first text description does not align with the predetermined operating goal for the AV and providing the second text description to a third machine-learning model to generate a second synthetic scene. Systems and machine-readable media are also provided.

Abstract: A computer-aided method of comparing legal requirements, including: comparing a first legal requirement from a first jurisdiction to a second legal requirement from a second jurisdiction, including applying a natural language processing (NLP) algorithm to the first and second legal requirements; computing a distance between the first and second legal requirements; determining from the distance that the second legal requirement belongs to a same subject matter category as the first legal requirement; and providing a user interface (UI) to display the first and second legal requirements to a user, with the computed distance.

Abstract: A visual perception system includes a scanning camera, color sensor with color filter array (CFA), and a classifier node. The camera captures full color pixel images of a target object, e.g., a traffic light, and processes the pixel images through a narrow band pass filter (BPF), such that the narrow BPF outputs monochromatic images of the target object. The color sensor and CFA receive the monochromatic images. The color sensor has at least three color channels each corresponding to different colors of spectral data in the monochromatic images. The classifier node uses a predetermined classification decision tree to classify constituent pixels of the monochromatic images into different color bins as a corresponding color of interest. The color of interest may be used to perform a control action, e.g., via an automated driver assist system (ADAS) control unit or an indicator device.

Abstract: A method includes using sensory data produced by at least one onboard sensor of a witness vehicle to predict an imminent collision in an environment of the witness vehicle, the predicted imminent collision involving at least one participant vehicle; and alerting the least one participant vehicle to the predicted imminent collision, wherein the alerting is performed by the witness vehicle and prompts the at least one participant vehicle to perform at least one action to mitigate the predicted imminent collision.

Abstract: System, methods, and computer-readable media for a calibration check process of sensors on an autonomous vehicle (AV) via a drive-through environment mapped with a series of targets. The targets are used to check the calibration of the sensors on the AV as a quality check before the AV is determined fit to drive autonomously. Supervising a calibration process that collects data from the sensors on the AV based on exposure to a series of targets or augmented camera targets. The collected data may be used for extrinsic calibration aimed to determine that extrinsic parameters that define the rigid relationship between sensors are in set checker bounds.

Abstract: Methods and systems are provided for controlling a vehicle comprising an Electric Power Steering System (EPS). In an embodiment, a method includes determining, by the processor, a lateral acceleration reference based on reference path data and vehicle dynamics data; determining, by the processor, coefficient data based on at least one of measured lateral acceleration data and measured steering angle data, and measured torque data; determining, by the processor, a torque command based on the coefficient and the reference lateral acceleration data; and generating, by the processor, a steering command to the EPS based on the torque command.

Abstract: The present technology pertains to validating a virtual camera in a simulation environment by utilizing an improved camera model to provide quantitative measurements of the model's performance. A method of validating a virtual camera in a simulation environment comprises presenting at least one reference chart in the simulated environment and capturing images of the reference chart in the simulated environment using a virtual camera. The method further includes interrupting an image pipeline of the virtual camera after at least one simulated process in the image pipeline to extract a RAW image. The method analyzes the RAW image to derive measurements of metrics to characterize the virtual camera. The measured metrics are compared to metrics of a calibrated real-world camera to verify that the metrics are within a threshold delta that is indicative that the virtual camera sufficiently approximates the real-world camera.

Abstract: The present technology is directed to determining an accuracy of an infrared (IR) camera, and more particularly, validating a distortion accuracy of an IR camera. The present technology can receive one or more images of a calibration harp captured by the IR camera, wherein the one or more images include a plurality of lines corresponding to a plurality of strings of the calibration harp. The present technology can further determine a degree of distortion of the plurality of lines based on a distortion error coefficient, wherein the distortion error coefficient is computed based on edge points of the plurality of lines on the one or more images.

Abstract: Techniques are provided for activating a plurality of power features of a vehicle. In one embodiment, the techniques involve controlling a plurality of switches of a multi-function converter unit configuration to activate at least one of the plurality of power features of the vehicle, wherein the multi-function converter unit configuration includes a multi-function converter unit, at least one charge port, and a load.

Abstract: A telematics system for a mobile UE includes a telematics controller that is configured to communicate via a plurality of communication channels. The telematics controller determines, for each of the communication channels, a parameter related to data throughput and energy consumption to effect an uplink communication between the telematics controller and a second device when the mobile UE is in a low-power operating mode. The parameter related to data throughput and energy consumption to effect the uplink communication is compared with a threshold. One of the communication channels is selected based upon the parameter related to data throughput and energy consumption to effect the uplink communication. The telematics controller communicates with the second device via the one of the plurality of communication channels when the mobile UE is in the low-power operating mode.

Abstract: A vehicle assist system includes an imager coupled to a vehicle body. The imager is configured to capture a vehicle environment, and a GPS processor is configured to detect a geographical location of a vehicle. The vehicle assist system also includes a controller that stores vehicle data and a coastdown procedure. The controller is communicatively coupled to the imager and the GPS processor and is configured to detect a trigger event. In response to the trigger event, the controller is configured to execute the coastdown procedure based on the vehicle data, the vehicle environment from the imager, and the geographical location of the vehicle.

Abstract: Methods and systems are provided for correlating mobile platform data with secondary device data. In an exemplary embodiment, mobile platform data and secondary device data are obtained. The mobile platform data pertains to a mobile platform. The secondary device data originates from a secondary device that is movably disposed within the mobile platform at certain times. The obtaining of the secondary device data is independent from the obtaining of the mobile platform data. The mobile platform data is correlated with the secondary device data, via a processor.

Abstract: A system includes a first webbing payout sensor configured to detect a first webbing payout of a seatbelt associated with a vehicle seat, the first webbing payout being a length of webbing extended from a retractor of the seatbelt, an occupant detection module configured to identify a state of the vehicle seat, the occupant detection module identifying an occupied state when an occupant is seated on the vehicle seat and an unoccupied state when the vehicle seat is free from an occupant, and a seatbelt wear condition module in communication with the first webbing payout sensor and the occupant detection module and configured to identify whether a seatbelt buckle extender is used in conjunction with the seatbelt based on the first webbing payout and the state of the vehicle seat identified by the occupant detection module.

Abstract: A method of controlling a reservation at a charging station for a vehicle includes a controller in communication with a remote advisory unit. The method includes positioning a ground lock at the charging slot, the ground lock being controllable through a station command unit. The method includes generating an identification number through the remote advisory unit and transmitting the identification number to the controller and the station command unit. The identification number is randomly generated. The ground lock is moved to a blocking position when an estimated time of arrival of the vehicle is less than a first threshold. The method includes broadcasting a message to the station command unit with the identification number, via the controller, when the estimated time of arrival is less than a second threshold. The ground lock is moved to a non-blocking position when an authentication process is completed.

Abstract: A fuel cell stack includes end plate units each having a metal plate, a dielectric plate, and a perimeter groove defined by the dielectric plate and an edge of the metal plate. The stack also includes a gas inlet and a coolant inlet configured to receive a reactant gas and coolant into the fuel cell stack, respectively, fuel cells having a pair of bipolar plates, and a multi-layer seal disposed within the fuel cell stack on the end plate units or the bipolar plates. The multi-layer seal includes a first layer constructed of a first material that is substantially impermeable to the reactant gas, and a second layer constructed of a second material that is more resistant to corrosion than is the first material.

Abstract: Methods and systems are provided for a vehicle towing a trailer. In one embodiment, a method includes: receiving, by a processor, sensor data from one or more sensors of the vehicle; estimating, by a processor, a steering torque value based on the sensor data; estimating, by the processor, a steering angle value based on the sensor data; determining, by the processor, a trailer tongue value based on the steering torque value and the steering angle value; and generating, by the processor, a control signal to control the vehicle based on the trailer tongue value.

Abstract: A method for performing direct logging of sensor data in a vehicle network logging system (VNLS) installed on an autonomous vehicle (AV), the VNLS comprising a network switch connected between an onboard sensor of the AV and an onboard computer of the AV, the network switch comprising a logger for logging sensor data to a disk, is described and includes providing a converter node on the network switch; receiving, using the converter node, data generated by the onboard sensor; and converting, using the converter node, the received data to a data record suitable for logging by the logger to the disk.

Abstract: A battery cell having an anode and a cathode with a catalyzed separator interposed therebetween, and sealed within a cell case is described. The catalyzed separator is a substrate having a catalyzed coating arranged thereon. The catalyzed coating includes a bimetallic catalyst arranged on a support material. The bimetallic catalyst includes rhodium or ruthenium and a second transition metal. Lithium in zeolite functions as a catalyst promoter to accelerate a hydroformylation reaction.

Abstract: A system includes an occupant detection module configured to identify an occupied state when an occupant is seated on a vehicle seat and an unoccupied state when the vehicle seat is free from an occupant. The system also includes a buckle sensor configured to identify a time of buckling when a latch plate is initially secured to a buckle. A seatbelt wear condition module is configured to identify the occupied state at the time of buckling and after buckling regardless of whether the occupant detection module detects the occupied state at the time of buckling and after buckling or the unoccupied state at the time of buckling and after buckling based on the occupant detection module identifying the occupied state within a predetermined timeframe prior to the time of buckling and disregarding any unoccupied state produced from the occupant detection module while the seatbelt remains buckled.