Abstract: A vehicle, and a system a method of navigating a vehicle. The system includes a trajectory planning module and a trajectory tracking module. The trajectory planning module operates at a processor of the vehicle to generate a trajectory for the vehicle. The trajectory tracking module operates at the processor to track the trajectory to navigate the vehicle. The trajectory planning module and the trajectory tracking module run asynchronously from each other.

Abstract: An electric machine includes: a first stator winding including first and second stator winding portions; a second stator winding including third and fourth stator winding portions; a third stator winding including fifth and sixth stator winding portions, where inputs of the stator windings are configured to be connected to phases, respectively, of an inverter; and switches connected between the stator winding portions and outputs of a power source.

Abstract: A system for key absence management in a vehicle configured to be started by an electronic key fob includes a key absence management controller that implements a method configured to authorize starting of the vehicle by monitoring presence and absence of the electronic key fob in the vehicle. If the controller finds the electronic key fob to be present in the vehicle, then the controller authorizes starting of the vehicle. If the controller finds the electronic key fob to be absent from the vehicle, then the controller authorizes starting of the vehicle based on detection of a keyless authority indicator. A vehicle configured to be started by an electronic key fob includes the system with the controller that implements the method.

Abstract: Disclosed are embodiments for a deep learning optimizer for fine-tuning while dynamically mitigating catastrophic forgetting. In some aspects, a method includes saving an original state of a model to a buffer, the original state comprising original weights of the model; apply new gradients to intermediate model states of the model during at least one intermediate training step of training of the model; calculate, at a final training step of the training, a displacement vector representing a difference between current weights of the model and the original weights of the model; responsive to the displacement vector and a final gradient of the final training step being inconsistent in terms of gradient direction, perform an orthogonal projection of the final gradient on the displacement vector to generate an orthogonal gradient; and applying the orthogonal gradient to the original state of the model at the final training step of the training.

Abstract: An electrochemical cell that cycles lithium ions includes a positive electrode that includes a positive electroactive material, a negative electrode that includes a silicon-containing negative electroactive material, a separating layer disposed between the positive electrode and the negative electrode, and an electrolyte that is in contact with at least one of the positive electroactive material, the negative electroactive material, and the separating layer. The electrolyte includes greater than or equal to about 0.1 wt. % to less than or equal to about 10 wt. % of a phosphite-type additive.

Abstract: An AV may determine a degradation score based on data indicating a condition of an environment where the AV operates to provide a service. The degradation score may indicate a degradation in a performance of the AV (e.g., one or more sensors of the AV) under the condition. After determining that the degradation score is higher than a threshold, the AV may pause the service, e.g., by moving out of the traffic lane or pulling over. The AV may re-check the condition later and determine a new degradation score. After determining that degradation score is lower than the threshold, the AV may resume the service, e.g., by moving back to the traffic lane. The AV may determine that the degradation score is higher than another threshold and in response to the determination, stops where it is, e.g., in a traffic lane. The AV may request remote assistance or retrieval.

Abstract: A method and system for estimating state of health (SOH) of a battery configured for providing electrical power to a motor for driving a vehicle. The method and system configured for measuring an enhanced SOH for the battery according to an enhanced SOH process. The enhanced SOH process including maximizing a discharge depth of the battery to maximize accuracy of the enhanced SOH measurement.

Abstract: A method that includes obtaining reflective radar signals regarding a scene monitored by a radar sensor system having an antenna array that is characterized by effecting a reflection-ghost offset in one or more domains, determining a reflective-intensity (RI) spectrum in three domains based on the reflective radar signals, producing a filtered RI spectrum by applying a trained convolutional neural network (CNN) to the RI spectrum by, at least in part, filtering the RI spectrum using one or more CNN kernels that incorporate the reflection-ghost offset; and detecting objects in the monitored scene based, at least in part, on the filtered RI spectrum.

Abstract: A method to create a battery cell is provided. The method includes, within a vacuum or an inert atmosphere, utilizing an etching process to remove a passivation layer from a primary surface of a solid electrolyte. The method further includes applying a surface coating to the primary surface. The method further includes, within the battery cell, disposing the solid electrolyte including the surface coating between an anode and a cathode.

Abstract: A cell temperature measurement system for a battery includes a heat spreader and a temperature sensor. The heat spreader is configured to thermally conduct energy through a substrate from a cell contact to a sensor contact. The temperature sensor is configured to generate a measurement reflective of a cell or another component temperature of the battery. The temperature sensor may generate the temperature measurement according to readings taken with a probe positioned proximate the sensor contact.

Abstract: Systems and methods are provided for building a product by additive manufacturing and creating hollow volumes without including build supports in the hollow volume for the layers above the hollow volume. An additive manufacturing cell includes a material handling device, a printer a material delivery system and an energy source to feed the sheets, print on the sheets, apply a powder on the printed sheets, build a hollow volume into the sheets and consolidate the sheets into a product with a contiguous structure.

Abstract: A vehicle underbody includes a system of connected unitized underbody components including a front quadrant system having a left front unitized underbody component and a right front unitized underbody component, a center system, and a rear quadrant system having a left rear unitized underbody component and a right rear unitized underbody component. A first rail element is loosely connected to the left front unitized underbody component and the left rear unitized underbody component, and a second rail element is loosely connected to the right front unitized underbody component and the right rear unitized underbody component.

Abstract: A vehicle, an electrical system of the vehicle and a method of operating the vehicle. The electrical system includes a battery, an electrical load that draws power from the battery, a switch between the battery and the electrical load, and a processor. The processor is configured to measure a power drawn from the battery by the electrical load and open the switch to disconnect the battery from the electrical load when the power drawn by the electrical load matches a selected criterion.

Abstract: Systems and methods for a vehicle are provided. In one embodiment, a method includes: receiving image data defining a plurality of images associated with an environment of the vehicle; receiving vehicle data indicating a velocity of the vehicle, wherein the vehicle data is associated with the image data; determining, by a processor, feature points within at least one image based on the vehicle data and a three dimensional projection method; selecting, by the processor, a subset of the feature points as ground points; determining, by the processor, a ground plane based on the subset of feature points; determining, by the processor, a ground normal vector from the ground plane; determining, by the processor, a camera to ground alignment value based on the ground normal vector; and generating, by the processor, second image data based on the camera to ground alignment value.

Abstract: A battery clamp system for a battery includes a terminal receiving portion configured to be coupled to a terminal of the battery. The battery clamp system includes an anti-rotation projection coupled to the terminal receiving portion. The anti-rotation projection is configured to be coupled to the battery. The anti-rotation projection extends along an axis that is parallel to a longitudinal axis of the battery clamp system. The battery clamp system includes a first flange coupled to the terminal receiving portion that extends along a first flange axis substantially perpendicular to the longitudinal axis. The battery clamp system includes a second flange coupled to the terminal receiving portion so as to be spaced apart from the first flange. The first flange is configured to cooperate with the second flange to couple the terminal receiving portion to the battery.

Abstract: A method for surveilling with a vehicle includes receiving an area-of-interest data from a vehicle user. The area-of-interest data delineates a virtual fence around the vehicle. The virtual fence is boundary of an area of interest around the vehicle. The vehicle is parked adjacent to an infrastructure. The method further includes receiving sensor data from a sensor of the vehicle that is monitoring the area of interest. Further, the method includes detecting a predetermined activity by a predetermined object of interest within the area of interest based on the sensor data received from the sensor of the vehicle. Also, the method includes notifying the vehicle user of the predetermined activity sensed using the sensor of the vehicle.