Abstract: A method for quantitatively measuring a psychological complexity of a response to visual stimuli is described. The method includes generating, by a trained machine learning model, different dataset types of reference text descriptions and/or representations of the visual stimuli. The method also includes collecting input response text descriptions from an individual after perceiving the visual stimuli. The method further includes scoring a difference between the input response text descriptions and the different dataset types of reference text descriptions and/or representations of the visual stimuli, in which a score is generated based on the different dataset types of reference text descriptions. The method also includes generating a complexity score representative of a cognitive complexity of the input response text description from the individual based on the score generated based on the different dataset types of reference text descriptions.

Abstract: A method for synchronizing neighboring tiles in an electronic map is described. The method includes grouping neighboring tiles of the electronic map into a plurality of tile groups. The method also includes selecting a first tile group and a second tile group that border one another on at least a first tile in the first tile group and a second tile in the second tile group. The method further includes independently optimizing the first tile group and the second tile group if a feature crosses between the first tile group and the second tile group. The method also includes shifting a border of the first tile group and a border of the second tile group to join the first tile and the second tile in the second tile group or the first tile group.

Abstract: In accordance with one embodiment, a system includes a processor, a memory module communicatively coupled to the processor, an NLP module communicatively coupled to the processor, and a set of machine-readable instructions stored in the memory module. The machine-readable instructions, when executed by the processor, direct the processor to perform operations including receiving a text data, and receiving a training text data for training one or more models of the NLP module. The operations also include generating, with a novice model of the NLP module, a novice suggestion based on the text data and the training text data to present an idea related to the text data, generating, with an expert model of the NLP module, an expert suggestion based on the text data and the training text data to present an idea elaborating on the text data, and outputting the novice suggestion and/or the expert suggestion.

Abstract: Systems and methods for predicting a trajectory of a moving object are disclosed herein. One embodiment downloads, to a robot, a probabilistic hybrid discrete-continuous automaton (PHA) model learned as a deep neural network; uses the deep neural network to infer a sequence of high-level discrete modes and a set of associated low-level samples, wherein the high-level discrete modes correspond to candidate maneuvers for the moving object and the low-level samples are candidate trajectories; uses the sequence of high-level discrete modes and the set of associated low-level samples, via a learned proposal distribution in the deep neural network, to adaptively sample the sequence of high-level discrete modes to produce a reduced set of low-level samples; applies a sample selection technique to the reduced set of low-level samples to select a predicted trajectory for the moving object; and controls operation of the robot based, at least in part, on the predicted trajectory.

Abstract: A method for managing autonomous operation of a vehicle includes detecting, while the vehicle is operating in an autonomous mode, an assistance condition that triggers activation of an assistance component of a set of assistance components associated with a driver assistance system. The method also includes determining whether the operation of the vehicle in the autonomous mode satisfies a safety condition associated with the assistance component. The method further includes adjusting an activation signal that triggers the activation of the assistance component based on determining the operation of the vehicle in the autonomous mode satisfies the safety condition.

Abstract: System, methods, and other embodiments described herein relate to vehicle maneuvering using predictive control with automated driving and contingency planning to preserve safety and increase comfort. In one embodiment, a method includes receiving, by a controller, an operator command associated with a vehicle maneuver while automated driving is engaged. The method also includes adjusting a motion command associated with the vehicle maneuver by applying a predictive control according to motion estimates outputted from the automated driving and the operator command, the predictive control using motion constraints that are constant between time intervals for the vehicle maneuver. The method also includes controlling, by the controller, a vehicle using the motion command for a time step during the time intervals.

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 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: Robots and sensor systems having a compliant member for maintaining the position of a sensor are disclosed. In one embodiment, a robot includes a rigid surface, one or more compliant members attached to the rigid surface, and a sensor device. The sensor device includes an inflatable diaphragm operable to be disposed around the one or more compliant members, the inflatable diaphragm having a port, and a pressure sensor fluidly coupled to the port and operable to detect a pressure within the inflatable diaphragm. The one or more compliant members prevent lateral movement and rotational movement of the sensor device.

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: 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 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 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: 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 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: 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: 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).