Abstract: A system may include a camera assembly, a fluid dispensing assembly, a wiper assembly, and a controller. The camera assembly can include a lens. The controller can be in communication with the camera assembly, the fluid dispensing assembly, and/or the wiper assembly. In some examples, the controller can be configured to determine, based on image quality data generated by the camera assembly, that a debris is attached to the lens. In response to determining that the debris is attached to the lens, the controller can trigger the fluid dispensing assembly to dispense liquid onto the lens, and activate the wiper assembly to remove the debris from the lens.

Abstract: Aspects of the present application correspond to utilization of a combined set of inputs from simulation systems to generate or train machine learned algorithms for utilization in vehicles with vision system-only based processing. Aspects of the present application correspond to utilization of a set of inputs from sensors or sensing systems and simulation systems to create updated training sets for use in machine learning algorithms. The combined set of inputs includes a first set of data corresponding to vision system from a plurality of cameras configured in a vehicle. The combined set of inputs further includes a second set of data corresponding to simulated content systems that generate additional training set data including visual images and data labels to supplement the vision system data.

Abstract: A system and methods for manufacturing a dry electrode for an energy storage device are disclosed. The system includes a first dry electrode material delivery system configured to deliver a dry electrode material, a first calendering roll, a second calendering roll, and a controller. The second calendering roll is configured to form a first nip between the first calendering roll and the second calendering roll. The first nip is configured to receive the dry electrode material from the first dry electrode material delivery system, and form a dry electrode film from the dry electrode material. The controller is configured to control a rotational velocity of the second calendering roll to be greater than a rotational velocity of the first calendering roll.

Abstract: Generally described, one or more aspects of the present disclosure relate to the configuration and management of one or more components to facilitate dual axis rotation. More specifically, one or more aspects of the present application relate to the configuration or management of a rotation mechanism to facilitate the dual axis rotation of a display device. Illustratively, the display device is mounted on rotation mechanism that facilitates a dual axis rotation utilizing a single actuator, dual rotation joints, and associated linkages. The rotation component further includes at least one additional floating joint that provides additional tension forces relative to a third axis. Still further, in accordance with further embodiments, a control component can be utilized to generate control signals relating to rotation of the single actuators, such as establishing control positions and duty cycles.

Abstract: Systems and methods for fail-safe corrective actions based on vision information for autonomous driving. An example method is implemented by a processor system included in a vehicle, with the method comprising obtaining images from image sensors positioned about the vehicle. Visibility information is determined for at least a portion of the images. Adjustment of operation of an autonomous vehicle is caused based on the visibility information.

Abstract: Systems and methods are described herein for a system to automatically execute actions associated with moveable closures of one or more trunk compartments of a vehicle. The system may detect a user device is within proximity of the vehicle using ultra-wideband signals. The system may then determine a location of the user device, and based on the location of the user device, whether the user device is within a trigger zone. A trigger zone may represent a real-world area positioned about a trunk compartment of the vehicle, the trunk compartment comprising a moveable closure. Based on determining that the user device is within a trigger zone, the system may execute an action associated with the moveable closure.

Abstract: Systems and methods are described herein for a system to automatically execute actions associated with one or more moveable closures of a vehicle. The system may detect a user device is within proximity of the vehicle using ultra-wideband signals. The system may then determine a location of the user device, and based on the location of the user device, whether the user device is within a trigger zone. A trigger zone may represent a real-world area positioned about the vehicle. Based on determining that the user device is within a trigger zone, the system may execute an action associated with the one or more moveable closures.

Abstract: Systems and methods for a vision-based machine learning model for autonomous driving with adjustable virtual camera. An example method includes obtaining images from a multitude of image sensors positioned about a vehicle. Features associated with the images are determined, with the features being output based on a forward pass through a first portion of a machine learning model. The features are projected into a vector space associated with a virtual camera at a particular height. The projected features are aggregated with other projected features associated with prior images. A plurality of objects which are positioned according to the virtual camera are determined.

Abstract: An annotation system uses annotations for a first set of sensor measurements from a first sensor to identify annotations for a second set of sensor measurements from a second sensor. The annotation system identifies reference annotations in the first set of sensor measurements that indicates a location of a characteristic object in the two-dimensional space. The annotation system determines a spatial region in the three-dimensional space of the second set of sensor measurements that corresponds to a portion of the scene represented in the annotation of the first set of sensor measurements. The annotation system determines annotations within the spatial region of the second set of sensor measurements that indicates a location of the characteristic object in the three-dimensional space.

Abstract: Presented herein are systems and methods for generating pathways for autonomously navigating through an environment. A computing system can identify a tensor comprising encodings derived from sensor data from an ego and map data defining a topology of an environment surrounding the ego. The computing system can determine, by applying at least a first portion of encodings to a machine learning (ML) model, a first index value defining a point within a first grid. The computing system can determine, by applying at least a second portion of encodings and the first index value to the ML model, a second index value defining the point within a second grid within the first grid. The computing system can generate a token for a pathway through the environment based on the first index value and the second index value for the point. The computing system can store a graph to include the token.

Abstract: Vehicular seat suspension systems that do not include scissor mechanisms or pivot joints to improve lateral stability and substantially eliminate deflection during operation, testing and/or crashes. In particular, the seat suspension systems include an inner element that is able to slide within a static outer element, allowing the system to bear high loads while ensuring lateral stability and substantially eliminating deflection experienced by convention seat suspension systems.

Abstract: Embodiments include systems and methods for processing sensor data and generating operational instructions of hardware of egos (e.g., autonomous vehicles, robots). The ego includes any number of machine-learning architectures, often neural network architectures, for processing sensor data and recognizing the environment around the ego and making decisions on the ego's behavior. The neural network architectures of the ego ingest sensor data and execute any number of operations related to a particular domain or task, such as object recognition or path planning, using the sensor data. A graph partitioner is trained to assign functions in the software of the neural networks and the sensor data to certain hardware processing units. Several compilers are used to generate the instructions based upon the assigned type of processing unit.

Abstract: A method comprises detecting one or more agent objects in a space around an ego object using image data captured by a camera of the ego object; storing a hierarchical nodal graph comprising a goal layer comprising one or more goal nodes and a plurality of interaction layers of interaction nodes subsequent to the goal layer; adding an interaction node to an interaction layer of interaction nodes of the plurality of interaction layers; determining a trajectory score for each of a plurality of trajectories based on one or more node scores of one or more nodes corresponding to the trajectory within the hierarchical nodal graph; and selecting a trajectory of the plurality of trajectories for the ego object based on the trajectory score for the trajectory.

Abstract: Disclosed herein are methods and systems for automatic labeling of image data for machine learning training purposes. A method comprises retrieving navigation data and image data from a set of egos navigating through an environment comprising at least one feature; generating a three-dimensional (3D) model of the environment using the navigation data and image data of at least a subset of the set of egos, the 3D model comprising a virtual representation of the at least one feature of the environment; identifying a machine learning label associated with the at least one feature within the image data; receiving second navigation data and second image data from a second ego not included within the set of egos, the second ego navigating the environment, the second image data including the at least one feature; automatically generating a machine learning label for the at least one feature depicted within the second image data.

Abstract: Systems and methods can include a computing system receiving a bitstream of a video sequence and one or more indications indicative of one or more image frames of the video sequence, determining, by parsing the bitstream, timestamps, positions within the bitstream and types of image frames of the video sequence and determining, using the one or more indications and the timestamps, positions within the bitstream and types of the image frames of the video sequence, one or more segments of the bitstream for decoding to extract the one or more image frames. For an image frame of the one or more image frames, a corresponding segment represents a corresponding referencing chain of image frames of the video sequence. The computing system can decode the one or more segments of the bitstream and use the one or more image frames to train the ML model.

Abstract: Systems and methods for enhanced techniques for analyzing induction motors. An example method includes accessing circuit model information associated with an induction motor (IM), the circuit model information representing rotor bars of the IM as each including respective rotor segments. Rotor segment nominal currents associated with the rotor segments are determined, with the determination being based on performing finite element analysis (FEA) over a grid and use of a linearized circuit model. Rotor segment ripple currents associated with the rotor segments are determined, with the determination being based on performance of FEA to extract flux ripple samples over the grid, with the flux ripple samples being transformed into a time-varying rotor flux ripple signal, and with the rotor segment ripple currents being determined based on the time-varying rotor flux ripple signal. Losses associated with the IM are determined.

Abstract: Disclosed herein is a knee joint assembly including a first link member having a first end mechanically coupled to an upper leg of a robot and configured to rotate around a first pivot relative to the upper leg, and a second link member having a first end mechanically coupled to a lower leg of the robot. The lower leg can be mechanically coupled to the upper leg and configured to rotate around a second pivot relative to the upper leg. A linear actuator device can be mechanically coupled to a second end of the first link member and a second end of the second link member, and when actuated can cause the first link member to rotate around the first pivot relative to the upper leg of the robot and cause the leg to rotate around the second pivot relative to the upper leg.

Abstract: Disclosed herein are methods and systems for using artificial intelligence modeling techniques to generate a path for an ego. In an embodiment, a method comprises retrieving image data of a space around an ego, the image data captured by a camera of the ego; predicting by executing an artificial intelligence model, an occupancy attribute of a plurality of voxels corresponding to the space around the ego; generating a 3D model corresponding to the space around the ego and each voxel's occupancy attribute; upon receiving a destination, localizing, by the processor, the ego by identifying a current location of the ego using a key image feature within the image data corresponding to the 3D model without receiving a location of the ego from a location tracking sensor; and generating a path for the ego to travel from the current location to the destination.

Abstract: Systems and methods for vehicle suspension control. An example method includes obtaining a road roughness map associated with a geographic area in which the vehicle is located, the road roughness map reflecting road condition metrics for road segments that form roads included in the geographic area. Based on the road roughness map, it is determined that a threshold percentage of road segments along an upcoming threshold distance of a navigable route exceed a threshold road condition metric. Suspension of the vehicle is adjusted, with the suspension being adjusted to reduce the effects of road roughness.