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: Systems and methods can include a computing system obtaining data including a plurality of data elements associated with a plurality of indices, where each index is associated with one or more data elements, generating a data file storing the plurality of data elements according to a predefined file format including a header and a plurality of data rows, where each data row corresponds to a respective index and storing the one or more data elements associated with the respective index, and the header includes, for each row, an association between the respective index and a corresponding data offset indicative of a memory position of the data row, determining, using an indication of a first index and the header, a first memory position of a data row corresponding to the first index; and accessing, using the first memory position, at least one data element associated with the first index.

Abstract: Disclosed herein are methods and systems for using artificial intelligence modeling techniques to train and execute an artificial intelligence model to analyze camera feed received from an ego to predict surface data for various surfaces surrounding the ego. A method comprises inputting, using one or more cameras of an ego object, image data of a space around the ego object into an artificial intelligence model; predicting, by executing the artificial intelligence model, a surface attribute of one or more surfaces of the space around the ego object; and generating a dataset based on the one or more surfaces and their corresponding surface attribute.

Abstract: A unitary busbar provides power from one connection point in an electric vehicle to another connection point. The unitary busbar includes a central solid core conductor, an insulation layer over the solid core conductor, and an electromagnetic shield fitted around the insulator. The unitary busbar is capable of being bent into specific configurations that allow it to conform to the body of an electric vehicle.

Abstract: A cold plate with an integrated sliding pedestal and a processing system including the same are provided. In one aspect, the processing system includes a printed circuit board (PCB), a first electronic component arranged over the PCB, and a thermal interface material (TIM) arranged over the first electronic component. The system includes at least one sliding pedestal arranged over the TIM. The sliding pedestal is configured to be spaced a variable distance from the PCB. The system also includes a cold plate arranged over the sliding pedestal and configured to provide a coolant to the sliding pedestal and to cool a second electronic component.

Abstract: One or more aspects of the present disclosure relate to methods, systems, and devices related to a system for pre-heating an electrode foil, including a chimney and a heating device. The chimney formed between an inner surface of a heated wall and an inner surface of a passive wall, the chimney having a foil inlet at a first end and a foil outlet at a second end adjacent to a nip of a heated calender roll device. The heating device may be configured to heat the electrode foil and positioned adjacent to an outer surface of the heated wall, where the heating device includes a gas inlet, a heater and a nozzle adjacent to the foil outlet and in fluid communication with the heater, the nozzle including a bend configured to direct a flow of gas to the inner surface of the heated wall and towards the foil inlet.

Abstract: The present disclosure pertains to a glare shield designed to enhance the performance of vehicle camera systems, particularly those used in autonomous and semi-autonomous vehicles. The glare shield features a textured surface composed of an array of micro-cones, or cone-shaped formations, which serve to scatter incident light in various directions, thereby reducing glare and improving camera vision. The micro-cones are optimized in size, angle, and orientation to minimize Total Hemispherical Reflectance (THR) and reflection penalty, enhancing the camera's ability to accurately interpret visual data. Additionally, the glare shield may include an electromechanical system for dynamic orientation adjustment in response to the position of external light sources, such as the sun. The manufacturing process of the glare shield utilizes a sintered tool steel insert, facilitating venting during molding and ensuring the precision of the cone-shaped texture.

Abstract: The systems and methods of the present disclosure can include an interlock system. The interlock system can include a plate defining a first aperture, a second aperture, and a third aperture, a spacer removably coupled to the plate and extending at least partially through the second aperture, the spacer including a first adjustable tab and a second adjustable tab, the spacer movable through the second aperture via the first adjustable tab and the second adjustable tab, a first electrical connector coupled to the plate and extending at least partially through the first aperture, the first electrical connector configured to rotate to form an electrical connection, and a second electrical connector coupled to the plate and extending at least partially through the third aperture, the second electrical connector configured to rotate to form the electrical connection.

Abstract: Various vehicle technologies for improving positioning accuracy despite various factors that affect signals from navigation satellites. Such positioning accuracy is increased via determining an offset and communicating the offset in various ways or via sharing of raw positioning data between a plurality of devices, where at least one knows its location sufficiently accurately, for use in differential algorithms.

Abstract: Disclosed herein are three-dimensional (3D) tactile sensors and methods for manufacturing the same. A method includes providing a first substrate material for the 3D tactile sensor, defining a set of first conductive regions for the 3D tactile sensor on the first substrate material, coupling a separator layer between the first substrate material including the set of first conductive regions and a second substrate material having a set of second conductive regions to create a stack, and forming the stack according to a target 3D structure. The substrate materials can include flexible polymers, and the conductive regions can be defined by processes such as screen printing, etching, laser-direct structuring, pad-printing, or 3D deposition. The separator layer can comprise a dielectric or piezoresistive material. The 3D tactile sensors can conform to curved geometries and can be used for measuring surface force, touch, and pressure.

Abstract: One or more aspects of the present disclosure relate to the configuration and management of data communications associated with a vehicle. By way of illustrative example, aspects of the present application correspond to management of data communications to obtain data generated or collected by a vehicle (e.g., “vehicle data”), which can include, but is not limited to, logs of information previously collected or generated by sensor and processing components, current vehicle data, or third-party data collected by the vehicle, and the like. In another illustrative examples, aspects of the present application correspond to management of data communications to provide configuration data or executable code to a vehicle, such as diagnostic applications, repair applications, and the like.

Abstract: Systems and methods for training machine learning algorithms utilized for autonomous driving. An example method includes creating driving environments based at least on vision based image data received from a vehicle; simulating driving a virtual vehicle by importing driving environment scenario; in response to completing the simulation, analyzing simulated results; determining optimized driving parameters associated with the driving environment scenario; and generating a set of machine learning algorithms training data based on the determined optimized driving parameters. The driving environment scenario is based at least on the created driving environment.

Abstract: Disclosed herein are systems and methods for quantizing floating-point values during operation of robotic systems. For example, a system can be configured to receive input data having multiple values represented in a floating-point format and determine a maximum absolute value from these values. The system can adjust the representation of each value by removing at least one bit from the exponent portion and redistributing it to the mantissa portion. In examples, the system can also extract a sign bit and align each value by shifting each bit. Based on the adjusted values, the system can perform dynamic quantization of the input data based at least in part on a scaling value determined using the maximum absolute value. The input data can then be provided as an input to at least a portion of a neural network during execution of one or more operations by the neural network.

Abstract: Disclosed herein are methods and systems for a navigation paradigm. One method includes receiving a set of quantized values resulting from a matrix multiplication of quantized query and key vectors, the set of quantized values corresponding to sensor data associated with the ego; identifying a maximum value using an integer comparison operation; for at least one quantized value in the set of quantized values, computing a difference between the quantized value and the maximum value; executing a bit shift operation, on the difference between the quantized value and the maximum value, corresponding to a power-of-two quantization scale to generate bit-shifted values; executing a base-2 exponentiation operation to the bit shifted values to generate base-2 exponentiated values; aggregating the base-2 exponentiated values to generate an aggregated value; and executing a model using the aggregated value to output a navigational instruction to be executed by the ego.

Abstract: Embodiments described herein provide for computing masked scores in transformer models without materializing a full mask. A matrix is partitioned into submatrices based on available processing elements. At least one element is initialized with row and column index values and evaluates a masking condition using a comparison operation, which is fused into the softmax computation. This approach supports causal and batched masks with minimal overhead and is well-suited for applications such as autonomous navigation, where computed weights guide downstream decision-making.

Abstract: Embodiments include systems and methods for processing sensor data and generating operational instructions for automated devices. The automated device includes hardware (e.g., INT8 MAC units, FP32 SIMD processors) and software operations executing a machine-learning architecture having transformer architectures implementing mixed-precision quantization for ingesting and analyzing various types of sensor data. The machine-learning architecture implements a transformer that includes dynamic quantization layers that dynamically quantize tensors, per-token, for downstream operations of the transformer and machine-learning architecture.

Abstract: Embodiments include systems and methods for processing sensor data and generating operational instructions for automated devices. The automated device includes hardware (e.g., INT8 MAC units, FP32 SIMD processors) and software operations executing a machine-learning architecture having transformer architectures implementing mixed-precision quantization for ingesting and analyzing various types of sensor data. The machine-learning architecture implements a transformer that includes dynamic quantization layers that dynamically quantize tensors, per-token, for downstream operations of the transformer and machine-learning architecture.

Abstract: An electric vehicle comprising a ducted fan system configured to increase downforce and reduce drag. The ducted fan system can include a diffuser extending from an input on an underbody of the vehicle and to an outlet on a rear side of the vehicle. The ducted fan system can be connected to a high voltage battery and a control system of the electric vehicle. The electric vehicle can further include a second diffuser to enhance downforce.

Abstract: A voltage regulating module design is provided. In one aspect, a voltage regulating module (VRM) includes a first layer configured to output a regulated voltage that is based on a stepped down voltage, and a second layer stacked with the first layer, and a plurality of contacts, such as a ball grid array (BGA), on the first layer. The second layer includes a plurality of active components configured to provide the stepped down voltage to the first layer. The first and second layers have overlapping recesses, and the recess of the first layer has a larger footprint than the recess of the second layer. A plurality of the VRMS can be arranged to form an opening including a counterbore. A faster, such as a bolt, can be positioned in the opening. The first layer can have a larger clearance from the fastener positioned in the opening than the second layer.

Abstract: Systems and methods for efficient selection of single instruction multiple data operations for neural processing units. An example processor system comprises a matrix processor configured to perform convolutions associated with a neural network and single instruction multiple data (SIMD) processors in communication with the matrix processors, with the SIMD processors being configured to execute a group of operations based on a current position associated with processing the neural network, and with the group of operations being selected from multiple SIMD programs, and with the group of operations being selected from the SIMD programs according to the current position.

Abstract: Systems and methods for a vision-based machine learning model for aggregation of static objects and systems for autonomous driving. An example method includes maintaining a spatial representation of an environment. Features are aggregation across a plurality of observation instances. The spatial representation is updated when the vehicle satisfies a threshold based on a motion characteristic and a contextual characteristic of the environment. Images depicting static objects are output.

Abstract: An illuminated interface system may include an illumination circuit, a switch circuit, and a controller. The illumination circuit is configured to illuminate a light source. The switch circuit is configurable into a plurality of states, where at least one of the plurality of states represents a user input. The controller is electrically connected to the illumination circuit and the switch circuit through a single signal wire. The controller includes a drive circuit and a sensing circuit. The drive circuit is configured to provide a drive signal to the illumination circuit via the single signal wire. The sensing circuit is configured to detect a state of the switch circuit.

Abstract: A conductive grease comprising a base oil, an organic lubricant additive for enhancing lubrication of the base oil, and a conductive additive for increasing electrical conductivity and thickening of the base oil. The conductive additive comprising ionic lubricant additives and/or inorganic lubricant additives. A testing method to quantitatively measure the effectiveness of conductive grease and a grounding solution utilizing the conductive grease.

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: 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: A vehicle comprising a compressor and a manifold physically and fluidly coupled to the compressor.

Abstract: A vehicular autonomous driving system includes a time division multiplexed (TDM) bus, an autonomous driving (AD) controller coupled to the TDM bus, and a plurality of AD sensors coupled to the TDM bus. The AD sensors are configured to collect AD data and transmit collected AD data to the AD controller on the TDM bus in an assigned time slot at a first power level. A first AD sensor of the plurality of AD sensors is configured to, based upon collected AD data, detect an AD emergency event. In response to the detection, the first AD sensor is configured to transmit an AD emergency message on the TDM bus in a non-assigned time slot and at a second power level that exceeds the first power level. The AD sensor may transmit the AD emergency message in a particular sub-slot of the non-assigned time slot.

Abstract: A system for dynamically managing individual suspension settings for a vehicle based on a determined suspension mode is provided. Based on the user input and obtained sensor input, the system can then determine a suspension mode for a plurality of individually controllable components by specifying values or commands for each controllable component. A first mode may correspond to a lowering of the plurality of controllable. A second mode may correspond to lowering two controllable components corresponding to the rear wheels of the vehicle and raising two controllable components corresponding to front wheels of the vehicle. A third mode may correspond to a lowering of the plurality of controllable components to effectively drop the height of the vehicle to a threshold point. The system may further implement various validation processes that can validate the determined suspension mode and make further adjustment to individual controllable portions based on load or ground measurements.

Abstract: Improved battery systems have been developed for lithium-ion based batteries. The improved battery systems consist of two-additive mixtures in an electrolyte solvent. Such battery systems are prepared by assembling a positive electrode and a negative electrode in the sealed cell, removing residual water from the sealed cell, filling the sealed cell with a nonaqueous electrolyte under an inert atmosphere, vacuum-sealing the sealed cell, carrying out a formation process comprising charging and discharging the sealed cell until the sealed cell achieves an initial capacity. The nonaqueous electrolyte includes lithium ions, a first nonaqueous solvent comprising a carbonate solvent, a second nonaquaeous solvent comprising methyl acetate, and an additive mixture of a first operative additive of either vinylene carbonate or fluoroethylene carbonate and a second operative additive of 2-furanone. Gas formation is suppressed in the battery system during the formation process.

Abstract: An autonomous control system generates synthetic data that reflect simulated environments. Specifically, the synthetic data is a representation of sensor data of the simulated environment from the perspective of one or more sensors. The system generates synthetic data by introducing one or more simulated modifications to sensor data captured by the sensors or by simulating the sensor data for a virtual environment. The autonomous control system uses the synthetic data to train computer models for various detection and control algorithms. In general, this allows autonomous control systems to augment training data to improve performance of computer models, simulate scenarios that are not included in existing training data, and/or train computer models that remove unwanted effects or occlusions from sensor data of the environment.

Abstract: A method includes: determining, based, at least in part, on a predicted driver characteristic, a first energy-versus-distance measure for a planned driving route of a vehicle, the first energy-versus-distance measure determined using an energy model; presenting the first energy-versus-distance measure on a user interface associated with the vehicle; identifying an already-driven part of the planned driving route; determining, based on information associated with the already-driven part of the planned driving route, a model error associated with the energy model; determining a second energy-versus-distance measure by modifying the first energy-versus-distance measure to account for the model error; and presenting the second energy-versus-distance measure on the user interface associated with the vehicle.

Abstract: The systems, methods, and devices disclosed herein relate to a multi-layer structures arranged in a vertically orientation. In some embodiments, a computing assembly can include a first cooling system, a first electronics layer, a second cooling system, and a second electronics layer. The first cooling system can be disposed on top of and can be in thermal communication with the first electronics layer. The first electronics layer array includes an array of integrated circuit dies that are in electronic communication with each other in a plane that is orthogonal to power delivery. The first electronics layer can be disposed on top of and can be in thermal communication with the second cooling system, and the second cooling system can be disposed on top of and can be in thermal communication with the second electronics layer. The second electronics layer includes an array of power delivery modules. In some embodiments, at least one layer can use system on wafer packaging.

Abstract: A method for forming a skin-foam architecture for a seat. The method includes loading a backing cover into a first portion of the tool. The method includes applying and curing a skin on a second portion of the tool, the skin including a first layer, and a second layer under the first layer. The method includes laminating a mesh under the skin. The method includes attaching and curing a foam layer under the mesh and the skin. The method includes mating the first and second portions of the tool. The method includes introducing foam between the mated first and second portions of the tool.

Abstract: Systems, methods, and controllers for a global headlamp. An example method includes obtaining configuration information indicative of a jurisdiction and a vehicle model associated with a vehicle. Headlamp state information is generated based on the vehicle model and jurisdiction. A propagation is output via a pixelated light source in a headlamp of the vehicle, the propagation representing a particular beam pattern which is compliant with the jurisdiction.

Abstract: A vehicle seat with enhanced ventilation, and construction techniques for the enhanced ventilation, are described herein. An example vehicle seat includes an exterior formed of an air permeable mesh and a molded foam below the exterior. The molded foam has first holes which allow air to pass therethrough. The vehicle seat further includes a rigid duct connected to the molded foam, with the rigid duct having second holes which line up with the first holes. The vehicle seat further includes a fan, with the fan drawing air from an ambient source through the exterior and into the rigid duct.

Abstract: The present disclosure relates to the synthesis and evaluation of difluorophosphate additives for use in energy storage devices. The difluorophosphate additive may be selected from the group consisting of lithium difluorophosphate (LFO), sodium difluorophosphate (NaFO), ammonium difluorophosphate (AFO), tetramethylammonium difluorophosphate (MAFO), potassium difluorophosphate (KFO), and combinations thereof. In some instances, the difluorophosphate additive is not lithium difluorophosphate (LFO).

Abstract: Systems and methods for enhanced user interface generation for parking based on occupancy machine learning model. An example method includes obtaining images from a multitude of image sensors positioned about a vehicle; computing a forward pass through an occupancy network to output, at least, information reflecting, for individual angular ranges about the vehicle, whether an object is within a threshold distance of the vehicle for an individual range along with an estimated distance to the object; and causing presentation, via a display of the vehicle, of a user interface depicting a graphical representation of the vehicle and the output information.

Abstract: This invention provides a method for the production of high capacity cathode materials for use in rechargeable lithium batteries. Traditional methods for producing lithium mixed metal oxide cathode materials typically generate large amounts of effluent which effluent must be treated prior to discharge. The present process uses mixed metals as raw materials in a wet chemical reaction in order to make high-quality precursors which can be used to prepare high-quality cathode materials after lithiation. As a key feature, in the precursor preparation process, the bulk of the aqueous solution used for the wet chemical reaction is recycled back to the reactor, so that the total process has little or no effluent generated during production of the cathode precursor material.

Abstract: Various vehicle technologies for improving positioning accuracy despite various factors that affect signals from navigation satellites. Such positioning accuracy is increased via determining an offset and communicating the offset in various ways or via sharing of raw positioning data between a plurality of devices, where at least one knows its location sufficiently accurately, for use in differential algorithms.

Abstract: A system including an enclosure is described herein, the enclosure having a housing and a lid coupled to the housing, the housing defining a first aperture and a second aperture. The system may include a pass-through connector coupled to an interior surface of the enclosure. The pass-through connector may comprise a body having an interior curved edge; a cap coupled to the body and comprising a pivot pin, wherein the pivot pin and the interior curved edge define a channel in the interior; a contact spring positioned in part within the channel; a terminal having a fastening region and a contact region; and an actuator having a first end and a second end, wherein the second end is in contact with the contact spring.

Abstract: The present disclosure generally relates to systems and methods for managing a battery of an electric vehicle. In some embodiments, a system initiates battery discharging on a battery pack, where the battery discharging continues until the battery pack reaches a first threshold level of charge. The system then estimates a first state of charge of the battery pack based at least on a first sensor reading associated with the battery pack. The system initiates battery charging on the battery pack, where the battery charging continues until the battery pack reaches a second threshold level of charge. The system estimates a second state of charge of the battery pack based at least on a second sensor reading associated with the battery pack. The system generates a processing result that indicates a capacity of the battery pack based at least on the first state of charge and the second state of charge.

Abstract: The present disclosure related to the configuration and management of accessibility of vehicle data communications provided to a service technician or other third party. The service technician requests access to the vehicle data with authentication information. The network service provider can facilitate an initial authentication for access to vehicle data, provide access to the vehicle data for authenticated and authorized users, and manage revocation of vehicle data access rights via a common interface provided through the vehicle without requiring customized software, applications or external computing devices.

Abstract: Building integrated photovoltaic (BIPV) systems provide for solar panel arrays that can be aesthetically pleasing and appear seamless to an observer. Micro louvered structures can be incorporated into photovoltaic (PV) stacks, such that light entering a PV stack that is reflected off of embedded solar cells is not directed out at angles at which a typical observer would normally view the PV stack or roof on which a solar array is installed. Further, portions of the micro louvered structures can be coated with reflective, refractive, dielectric, and/or colored films such that underlying solar cells within the PV stack are obscured from the sightlines of a typical observer.

Abstract: A personalization system for a vehicle includes an image-capture device configured to capture a plurality of images of one or more occupants in the vehicle and control circuitry configured to estimate a plurality of Z-heights of a plurality of body portions of each of the one or more occupants from a reference position in the vehicle, based on the plurality of images captured from the image-capture device, determine an associative relationship between the plurality of Z-heights of the plurality of body portions of each of the one or more occupants in the vehicle and a plurality of in-vehicle systems, based on defined user-preferences, and control the plurality of in-vehicle systems to direct an output from a corresponding in-vehicle system to a specific body portion of each of the one or more occupants in the vehicle, based on the estimated plurality of Z-heights and the determined associative relationship.

Abstract: A personalization system for a vehicle includes an image-capture device configured to capture a plurality of images of one or more occupants in the vehicle and control circuitry configured to estimate a plurality of Z-heights of a plurality of body portions of each of the one or more occupants from a reference position in the vehicle, based on the plurality of images captured from the image-capture device, determine an associative relationship between the plurality of Z-heights of the plurality of body portions of each of the one or more occupants in the vehicle and a plurality of in-vehicle systems, based on defined user-preferences, and control the plurality of in-vehicle systems to direct an output from a corresponding in-vehicle system to a specific body portion of each of the one or more occupants in the vehicle, based on the estimated plurality of Z-heights and the determined associative relationship.

Abstract: A configuration for a foot for a photovoltaic (PV) roofing tile is described. The foot includes multiple retaining features that are engaged by hooks or brackets of adjacent roofing tiles to prevent upward movement of roofing tiles located up roof from the foot. The foot also positions the PV roofing tile a fixed distance above a roofing substrate without the need for applying a set of battens atop the roofing substrate. Non-PV roofing tiles compatible with the describe foot are also described. The non-PV roofing tile is configured so that it can be cut into smaller pieces as needed to fill small openings on a roof top.

Abstract: A vehicle thermal management system includes a vehicle heat pump system, a battery system coolant loop, a drive train coolant loop, and control electronics. The vehicle heat pump system includes a compressor, a cabin condenser, a cabin evaporator, a cabin blower, and a chiller. The battery system coolant loop is in thermal communication with a battery system and with the chiller and selectively in thermal communication with the drive train coolant loop. The control electronics control the components of the vehicle thermal management system to heat the cabin, cool the cabin, heat the battery system, cool the battery system, and cool the drive train. The control electronics may control the compressor to operate in an efficient mode or a lossy mode in which the compressor generates heat. The control electronics may also control the components of the vehicle thermal management system to precondition the battery.