Abstract: Systems and methods are provided for an advanced driver-assistance system (ADAS) that obtains data from a plurality of sensors. In some embodiments, the system can retrieve data regarding a user's past interactions and analyze the data with the sensor data to determine the user's behavior. In some embodiments, the ADAS can determine whether a user is unaware of an ADAS feature based on this behavior and a prompt that recommends the ADAS feature. The user's response to this prompt may be incorporated into the user's behavior for future recommendations.

Abstract: A method for controlling an acceleration rate of a vehicle includes monitoring a first current speed and a first acceleration rate of the vehicle based on the vehicle moving from a standstill. The method also includes setting an initial target acceleration rate to an adjusted target acceleration rate based on the first acceleration rate satisfying a first acceleration adjustment condition and the first current speed satisfying a second acceleration adjustment condition. The method further includes monitoring a second acceleration rate and a second current acceleration rate of the vehicle based on setting the initial target acceleration rate to the adjusted target acceleration rate. The method still further includes setting the adjusted target acceleration rate to the initial target acceleration rate based on the second acceleration rate satisfying a first target acceleration condition or the second current speed satisfying a second target acceleration condition.

Abstract: Systems and methods are provided for optimizing vehicle setups through predictive determinations on subjective driver preferences. Examples provided herein include training a driver specific model based on first vehicle setups and subjective driver feedback of a driver on each first vehicle setup; applying the driver specific model on a second vehicle setup; generating, by the driver specific model, predicted subjective driver feedback on the second vehicle setup predictive of an opinion of the driver on the second vehicle setup; and selecting an optimal vehicle setup based on the predicted subjective driver feedback.

Abstract: A system is provided for implementing steering wheel controls, namely steering wheel rotation locking. In accordance with embodiments of the disclosed technology, a system may comprise a steering wheel rotation locking device; and a controller communicatively connected to the steering wheel rotation locking device to determine a presence and location of one or more objects or conditions surrounding a vehicle, and produce steering wheel control feedback to physically prevent rotational movement of a steering wheel.

Abstract: Systems and methods for use of operator state conditions to generate, adapt or otherwise produce visual signals relaying information to the operator are disclosed. A monitoring system may observe and analyze a vehicle operator to determine an operator state. The monitoring system may transmit the observed driver state to an operator alert system that generates, conditions and controls the transmission of signals to the operator.

Abstract: A method may include receiving a first image of a scene captured by a first camera at a first time step and plurality of other images of the scene captured by a plurality of other cameras at a plurality of time steps, determining a geometric relationship between the first camera at the first time step and each of the other cameras at the plurality of time steps, determining a cost volume for the first image captured by the first camera at the first time step based on the first image, the plurality of other images, and the geometric relationship between the first camera at the first time step and each of the other cameras at the plurality of time steps, and determining a depth map for the first image based on the cost volume, the depth map comprises a depth value of each pixel of the first image.

Abstract: A method for triggering capture of diverse driving data from captions is described. The method includes training a discriminator network to identify similarities between a received text description and a received scene description. The method also includes feeding a trained discriminator network with real scene information along with text/sentence descriptions to verify whether the real scene information matches the text/sentence description. The method further includes generating a dataset of diverse driving scenarios retrieved from a dataset of vehicle driving log data in response to a text/sentence query.

Abstract: A method for estimating depth of a scene includes capturing a first image of the scene via one or more sensors associated with a first agent. The method also includes selecting one or more second images from a group of previously captured images of the scene, each second image of the one or more second images satisfying a depth criteria, each image of the group of previously captured images being captured prior to the first image. The method further includes estimating the depth of the scene based on the first image and the one or more second images.

Abstract: A method of metal gapfill including depositing a metal layer on a dielectric layer present on a field and/or in an opening of a feature via plasma enhanced atomic layer deposition utilizing a metal halide precursor and a plasma comprising hydrogen and a noble gas; and depositing a metal gapfill material on the field and in the opening directly over the metal layer, wherein the metal gapfill material completely fills the opening.

Abstract: Systems and methods are provided trajectory prediction that leverages game-theory to improve coverage of multi-modal predictions. Examples of the systems and methods include obtaining training data including first trajectories for a first plurality of agent devices and first map information of a first environment for a past time horizon and applying the training data to a game-theoretic mode-finding algorithm to generate a mode-finding model for each agent device that predicts modes of the first trajectories. A trajectory prediction model can be trained on the predicted modes as a coverage loss term between predicted modes. Future trajectories can be predicted for a second plurality of agent devices based on applying observed data to the trajectory prediction model. A control signal can then be generated to effectuate an autonomous driving command on an agent device of the second plurality of agent devices based on the predicted future trajectories.

Abstract: A deformable sensor comprises an enclosure comprising a deformable membrane, the enclosure configured to be filled with a medium, and an imaging sensor, disposed within the enclosure, having a field of view configured to be directed toward a bottom surface of the deformable membrane. The imaging sensor is configured to capture an image of the deformable membrane. The deformable sensor is configured to determine depth values for a plurality of points on the deformable membrane based on the image captured by the imaging sensor and a trained neural network.

Abstract: A method for controlling a comfort component of a vehicle includes setting a comfort component, while a passenger is occupying the vehicle, to an active state to adjust a temperature within the vehicle to a passenger desired temperature based on receiving an input from the passenger. The method further includes maintaining, after the passenger exited the vehicle, the comfort component in an active state based on a likelihood of the passenger returning to the vehicle satisfying an active state condition. The method still further includes capturing, after the passenger exited the vehicle, an image of a person approaching the vehicle via one or more sensors of the vehicle. The method also includes adjusting the comfort component from the active state to a default state based on an identity of the person being different from an identity of the passenger, the identity of the person being determined based on the image.

Abstract: An approach to forecasting battery health as a dynamic time-series problem as opposed to a static prediction problem is presented. Systems and methods disclosed herein forecast a trajectory to failure by predicting a path to failure as opposed to only predicting when the battery may fail. A machine-learning model is implemented that extracts unique features taken from time-series data, such as time snippets of charging data. The raw time-series data may include current voltage and temperature with complex transformations and without capturing a full cycle, which permits wider applicability to instances of varying depth of discharge (DoD).

Abstract: Systems, methods, and other embodiments described herein relate to training a vehicle driver based on in-cabin or external light triggers. In one embodiment, a system includes a processor and a memory storing machine-readable instructions. The instructions, when executed by the processor, cause the processor to monitor a vehicle location along a roadway. A map of the roadway indicates a target location for a driving maneuver to be performed. When the vehicle location is within a threshold distance from a target location on the map, the instructions, when executed by the processor, cause the processor to control a vehicle light based on a vehicle light setting associated with the driving maneuver.

Abstract: A method for monitoring user purchase making activity is described. The method includes logging a potential user purchase and purchase communications corresponding to a potential option available for purchase by a user. The method also includes predicting whether loss aversion is a factor in a purchase making process of the potential option available for purchase by the user. The method further includes determining a purchase recommendation in response to identifying that the loss aversion is the factor in the potential purchase making process of the potential option available for purchase by the user. The method also includes displaying the purchase recommendation based on a use frequency of the option purchased by the user.

Abstract: A method for generating a dense light detection and ranging (LiDAR) representation by a vision system includes receiving, at a sparse depth network, one or more sparse representations of an environment. The method also includes generating a depth estimate of the environment depicted in an image captured by an image capturing sensor. The method further includes generating, via the sparse depth network, one or more sparse depth estimates based on receiving the one or more sparse representations. The method also includes fusing the depth estimate and the one or more sparse depth estimates to generate a dense depth estimate. The method further includes generating the dense LiDAR representation based on the dense depth estimate and controlling an action of the vehicle based on identifying a three-dimensional object in the dense LiDAR representation.

Abstract: Systems and Methods for controlling an autonomous vehicle, may include: receiving sensor data, the sensor data comprising vehicle parameter information for the autonomous vehicle; using the sensor data to determine a vehicle state for the autonomous vehicle, wherein the vehicle state comprises information regarding a magnitude of an actual or predicted effective understeer gradient for the vehicle; computing a yaw moment required to correct the effective understeer gradient based on the magnitude of the effective understeer gradient; and determining a combination of one or more vehicle control inputs, including applying a brake torque, to correct the effective understeer gradient; applying the brake torque to a single wheel of the vehicle, wherein an amount of brake torque applied is sufficient to lock up the single wheel to create a yaw moment on the vehicle to achieve the computed yaw moment required to correct the effective understeer gradient.

Abstract: Systems, methods, and other embodiments described herein relate to keeping a vehicle within a safety envelope. In one embodiment, a method includes determining a safety envelope having a boundary, determining a risk level for an environment surrounding the vehicle, and associating an index value with a location within the safety envelope based on at least one of the risk level and a relationship between the location and the boundary. The method includes, in response to a vehicle being located at the location, tilting a vehicle seat to a tilt angle relative to a floor of the vehicle. The tilt angle can be based on the index value associated with the location.

Abstract: Systems, methods, and other embodiments described herein relate to generating vehicle design using a diffusion model. In one embodiment, a method includes generating a plurality of images based on a textual artistic guidance and a numerical constraint using a diffusion model.

Abstract: Systems, methods, and other embodiments described herein relate to generating vehicle design using a diffusion model. In one embodiment, a method includes generating an image based on a reference image and a text description of the reference image using a diffusion model. The method includes, based on whether the image meets a predetermined constraint, generating an intermediate image based on the image and the predetermined constraint using an analysis model such that the intermediate image is incrementally closer to meeting the predetermined constraint than the image, regenerating the image based on the intermediate image using the diffusion model, and outputting the image.