Abstract: A method for an interactive storytelling system is described. The method includes parsing collected story narratives into a plurality of story narratives linked by story development questions. The method also includes presenting a selected story narrative, including a selected story development question regarding a prediction of a story development in the selected narrative. The method further includes determining a difference between the story development in the selected narrative and an answer received in response to the selected story development question. The method also includes selecting a next, selected story narrative of the story development based on the difference, including a next selected story development question regarding a next prediction of the story development in the next, selected narrative.

Abstract: A method for 3D object detection is described. The method includes predicting, using a trained monocular depth network, an estimated monocular input depth map of a monocular image of a video stream and an estimated depth uncertainty map associated with the estimated monocular input depth map. The method also includes feeding back a depth uncertainty regression loss associated with the estimated monocular input depth map during training of the trained monocular depth network to update the estimated monocular input depth map. The method further includes detecting 3D objects from a 3D point cloud computed from the estimated monocular input depth map based on seed positions selected from the 3D point cloud and the estimated depth uncertainty map. The method also includes selecting 3D bounding boxes of the 3D objects detected from the 3D point cloud based on the seed positions and an aggregated depth uncertainty.

Abstract: Systems and methods are provided for personalizing autonomous driving. The system can receive historical data on a driver of the vehicle's performance and population data indicating a population driving style. Speed data can be recorded as the driver of the vehicle drives the vehicle during a trial period. The historical data, population data, and speed data can be input into a machine learning model to determine a style for the driver. The system can receive one or more parameters from the machine learning model indicating the style. These parameters can be applied to the vehicle's automated driving system.

Abstract: Systems and methods are provided systems and methods for driver training that modulate driver-training feedback on the fly based on a driver's ability to successfully perform vehicular maneuvers. In examples, sensor data is received from sensors on a vehicle. The sensor data is indicative of operation conditions of the vehicle executing a vehicular maneuver. An attribute of driver-training feedback can be adjusted based on a comparison of the operating conditions to a set of performance criteria associated with the vehicular maneuver that are representative of a successful execution of the vehicular maneuver.

Abstract: A method for a replay driver skill improvement system is described. The method includes logging vehicle commands requested by a vehicle operator of an ego vehicle to perform a selected driving maneuver. The method also includes identifying one or more of the logged vehicle commands in which operation of the ego vehicle is outside of a predetermined threshold while performing the selected driving maneuver. The method further includes operating the ego vehicle according to the logged vehicle commands until the one or more of the logged vehicle commands in which operation of the ego vehicle is outside of the predetermined threshold are reached. The method also includes performing, through shared control with the vehicle operator, improved vehicle commands to complete the selected driving maneuver while operating the ego vehicle at or within the predetermined threshold.

Abstract: Systems and methods are provided for determining vehicle configurations. The system can receive simulation data or actual driving data of a driving track corresponding to a driver and associate the simulation data or actual driving data with one or more driving parameters. A driver style can be determined based on the one or more driving parameters. A vehicle configuration can be determined for a vehicle of the driver based on the determined driver style. The system can display one or more vehicle settings associated with the vehicle configuration on a user interface.

Abstract: Systems, methods, and other embodiments described herein relate to generating designs using learning models for analogics that process text and sketch-based inputs. In one embodiment, a method includes estimating analogical suggestions using a transformer model for a text prompt having design parameters. The method also includes generating an image using a learning model for an expression selected from the analogical suggestions and a sketched stroke inputted. The method also includes manipulating a modified sketch by the learning model and the modified sketch is derived from a sketched conversion of the image by an edge model.

Abstract: A system includes a processor and a memory communicably coupled to the processor and storing machine-readable instructions that, when executed by the processor, cause the processor to calculate joint probability functions for electronic chemical potential and oxidation states for ion types of a solid inorganic material, calculate a likelihood score for a plurality of oxidation state sets for the individual ion types in the solid inorganic material, and select one set of oxidation state from the plurality of oxidation state sets for the individual ion types as a function of the likelihood score. In some variations, the joint probability functions are calculated with a trained machine learning module.

Abstract: A system includes a processor and a memory in communication with the processor. The memory has a human-machine interface module having instructions that, when executed by the processor, cause the processor to identify, influenced by sensor data regarding a vehicle and an environment in which the vehicle operates, an event in which the vehicle should perform an autonomous steering maneuver determined by an autonomous driving system. The instructions further cause the processor to, in response to identifying the event, decouple control of a steering rack of the vehicle by a handwheel of the vehicle and lock the handwheel to prevent the handwheel from substantially moving. The instructions further cause the processor to determine, by the autonomous driving system, the autonomous steering maneuver to be performed by the vehicle influenced by an isometric torque input applied to the handwheel and detected by the processor when the handwheel is locked.

Abstract: Systems, methods, and other embodiments described herein relate to identifying and generating mechanisms from natural processes by a learning model for accelerating design development. In one embodiment, a method includes identifying mechanisms for a design task using a prompt transformer with seeds from biological processes, and the prompt transformer forms a taxonomy tree using the mechanisms. The method also includes generating functional solutions that expand sparse branches of the taxonomy tree for the mechanisms using the prompt transformer. The method also includes clustering the mechanisms using text embedding for the design task. The method also includes inspecting the mechanisms with the prompt transformer to select a solution associated with the design task.

Abstract: A method for designing polymers includes translating polymer representations of a training dataset and a test dataset into a format comprehensible by a generative pretraining transformer (GPT)-based model, training the GPT-based model with the translated polymer representations, generating new polymer representations, in a predefined format, using the trained GPT-based model, predicting at least one property of the generated new polymer representations using a machine learning (ML) property predictive model and selecting a first subset of the generated new polymer representations as a function of the at least one predicted property, and calculating the at least one property of the first subset of the generated new polymer representations using a molecular dynamics (MD) module.

Abstract: Systems and methods described herein relate to self-supervised scale-aware learning of camera extrinsic parameters. One embodiment processes instantaneous velocity between a target image and a context image captured by a first camera; jointly training a depth network and pose network based on scaling by the instantaneous velocity; produce depth map using the depth network; produce ego-motion of the first camera using the pose network; generate synthesized image from the target image using a reprojection operation based on the depth map, the ego-motion, the context image and camera intrinsics; determine photometric loss by comparing the synthesized image to the target image; generate photometric consistency constraint using a gradient from the photometric loss; determine pose consistency constraint between the first camera and a second camera; and optimize the photometric consistency constraint, the pose consistency constraint, the depth network and the pose network to generate estimated extrinsic parameters.

Abstract: System, methods, and other embodiments described herein relate to NODE learned tire models. In one embodiment, a method includes calculating estimated tire forces based on vehicle measurements; solving a second order differential equation in a repetitive manner until an error calculation based on a tire force function and the estimated tire forces reaches a minimum value, by: using a first predictive model to provide one or more inflection points and initial conditions based on the vehicle measurements, using a second and third predictive model to act as, respectively, exponents to a positive and a negative exponential equation based on the one or more inflection points, the initial conditions, and the vehicle measurements, and integrating the exponential equations to obtain the tire force function; and applying the tire force function to new vehicle measurements to estimate current tire forces.

Abstract: Systems and methods for multi-view cooperative contrastive self-supervised learning, may include receiving a plurality of video sequences, the video sequences comprising a plurality of image frames; applying selected images of a first and second video sequence of the plurality of video sequences to a plurality of different encoders to derive a plurality of embeddings for different views of the selected images of the first and second video sequences; determining distances of the derived plurality of embeddings for the selected images of the first and second video sequences; detecting inconsistencies in the determined distances; and predicting semantics of a future image based on the determined distances.

Abstract: Systems and methods are provided for determining driver surprise. The system can receive image data of a driver's pupils and video data of the driver's face over a time interval and determine a diameter of the driver's pupils over the time interval based on the image data. This diameter can be used to generate a pupil confidence value based on the diameter over the time interval. The system can extract facial features from the video data and generate a facial confidence value based on the facial features. A first weight can be applied to the pupil confidence value and a second weight can be applied to the facial confidence value to determine whether the driver is expressing surprise.

Abstract: A method for controlling an ego vehicle in an environment includes associating, by a velocity model, one or more objects within the environment with a respective velocity instance label. The method also includes selectively, by a recurrent network of the taillight recognition system, focusing on a selected region of the sequence of images according to a spatial attention model for a vehicle taillight recognition task. The method further includes concatenating the selected region with the respective velocity instance label of each object of the one or more objects within the environment to generate a concatenated region label. The method still further planning a trajectory of the ego vehicle based on inferring, at a classifier of the taillight recognition system, an intent of each object of the one or more objects according to a respective taillight state of each object, as determined based on the concatenated region label.

Abstract: System, methods, and other embodiments described herein relate to steering a vehicle based during loss of traction. In one arrangement, a method for steering a vehicle during loss of traction is disclosed. The method includes, responsive to detecting a slipping tire of a vehicle losing traction with a road, automatically steering the vehicle separately from an input of a steering wheel of the vehicle to cause the vehicle to follow a path. The method also includes decoupling control of a pair of front tires of the vehicle by the steering wheel. The method further includes rotating, independently of an input to the steering wheel and in parallel with steering the vehicle, the steering wheel to match an actual yaw of the vehicle.

Abstract: A method for a shared control, dynamic driving system is described. The method includes determining a vehicle command requested by a vehicle operator of an ego vehicle. The method also includes predicting the ego vehicle entering an unstable, controllable operating range if the vehicle command is performed. The method further includes adjusting the vehicle command to maintain control of the ego vehicle in the unstable, controllable operating range. The method also includes performing an adjusted vehicle command to operate the ego vehicle in the unstable, controllable operating range while maintaining recovery stability to transition to a safe operating range.

Abstract: Methods and systems disclosed are directed to a virtual simulation of chargers in a real-world environment having a wiring system using, a camera, an augmented reality (AR) interface, and a processor operable to generate a virtual charger representing a charger superimposed on the real-world environment, receive data responsive to a user interaction using the AR interface to operate the virtual charger, update the virtual charger superimposed on the real-world environment based on the operation, and wherein the virtual charger includes a connector and a charging cable including a first end and a second end, the first end operable to be connected to the connector, and the second end operable to be connected to the wiring system.

Abstract: Systems, methods, and other embodiments described herein relate to organizing and altering selected images from a style map with learning models through factoring style dimensions. In one embodiment, a method includes generating a style map by transforming and clustering information from an image dataset with a visualization model within a computation space having reduced dimensionality, and the style map includes style features derived from the image dataset. The method also includes comparing images selected from the style map using scores for dimensions associated with semantic attributes to form a comparison map. The method also includes mixing visual styles of the images from the comparison map with a generative model that computes representation interpolations within a latent space, the generative model outputting stylized images in an array. The method also includes communicating the array to a development system.