Abstract: One embodiment can provide a photovoltaic roof tile module. The photovoltaic roof tile module can include a front cover, a back cover assembly, photovoltaic structures positioned between the front cover and back cover assembly, and an internal circuit component electrically coupled to the photovoltaic structures. The internal circuit component is positioned between the front cover and the back cover assembly. The back cover assembly can include at least one through hole and a metallic plug inserted inside the through hole. A first surface of the metallic plug can electrically couple to the internal circuit component, and a second opposite surface of the metallic plug can be exposed to surroundings external to the photovoltaic roof tile module, thereby facilitating electrical coupling between the photovoltaic roof tile module and another photovoltaic roof tile module.

Abstract: A structure for forming inductor windings includes a first portion and a second portion of a clamshell casing. The first portion includes a first set of electrically conductive segments, a first inner carrier, and a first outer carrier. The second portion includes a second set of electrically conductive segments, a second inner carrier, and a second outer carrier. An inductor core is mountable between the first inner carrier and the first outer carrier within the first portion. A control assembly aligns and joins the first portion to the second portion of the clamshell casing such that the first set of electrically conductive segments arranged in the first pattern that correspond to first half-turns of the inductor windings, are attached to the second set of electrically conductive segments arranged in the second pattern that correspond to second half-turns of the inductor windings, to form continuous turns around the inductor core.

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 processor coupled to memory is configured to receive image data based on an image captured by a camera of a vehicle. The image data is used as a basis of an input to a trained machine learning model trained to predict a three-dimensional trajectory of a machine learning feature. The three-dimensional trajectory of the machine learning feature is provided for automatically controlling the vehicle.

Abstract: Provided herein are energy storage device electrode films comprising a hybrid electrode film, and methods of forming such multilayer hybrid electrode films and energy storage devices comprising multilayer hybrid electrode films. Each hybrid electrode film may comprise a self-supporting dry coated active layer and a wet cast active layer, wherein each active layer comprises a binder and an active material. The binder and/or active material may be the same or different as any other active layer. The hybrid multilayer electrode film may further comprise at least one additional layer, and the hybrid multilayer electrode film may be laminated with a current collector to form an electrode.

Abstract: A method of communication in a vehicle network is provided. An example method includes transmitting a network allocation map in a TDMA cycle, indicating reservation of time slots in the TDMA cycle. The method further includes transmitting a synchronization signal in the TDMA cycle, to synchronize the timing of nodes in the vehicle network. Each of the reserved time slots is identified by at least a network ID of a transmitting node in the vehicle network, and a slot type comprising one of a low latency traffic slot, and a bulk traffic slot. Further, the low latency traffic slots are repeated in the TDMA cycle at least as frequently as a guaranteed QoS latency parameter. Further, the bulk traffic slots are at least as long as a guaranteed QoS throughput parameter.

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 generate an occupancy data indicating whether different voxels within the ego's surroundings are occupied by an object having mass. A method comprises inputting, using a camera 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, an occupancy attribute of a plurality of voxels; and generating a dataset based on the plurality of voxels and their corresponding occupancy attribute.

Abstract: Systems and methods for enhanced object detection for autonomous vehicles based on field of view. An example method includes obtaining an image from an image sensor of one or more image sensors positioned about a vehicle. A field of view for the image is determined, with the field of view being associated with a vanishing line. A crop portion corresponding to the field of view is generated from the image, with a remaining portion of the image being downsampled. Information associated with detected objects depicted in the image is outputted based on a convolutional neural network, with detecting objects being based on performing a forward pass through the convolutional neural network of the crop portion and the remaining portion.

Abstract: Systems and methods for training machine models with augmented data. An example method includes identifying a set of images captured by a set of cameras while affixed to one or more image collection systems. For each image in the set of images, a training output for the image is identified. For one or more images in the set of images, an augmented image for a set of augmented images is generated. Generating an augmented image includes modifying the image with an image manipulation function that maintains camera properties of the image. The augmented training image is associated with the training output of the image. A set of parameters of the predictive computer model are trained to predict the training output based on an image training set including the images and the set of augmented images.

Abstract: Large-scale anodes containing high weight percentages of silicon suitable for use in lithium-ion energy storage devices and batteries, and methods of manufacturing the same, are described. The anode material described herein can include a film cast on a current collector substrate, with the film including a plurality of active material particles and a conductive polymer membrane coated over the active material particles. In some embodiments, the conductive polymer membrane comprises polyacrylonitrile (PAN). The method of manufacturing the anode material can include preparation of a slurry including the active material particles and the conductive polymer material, casting the slurry on a current collector substrate, and subjecting the composite material to drying and heat treatments.

Abstract: Provided herein are energy storage device electrode films comprising multiple active layers, and methods of forming such multiple active layer energy storage device electrode films. Each active layer may be a self-supporting active layer comprising a binder and an active material. The binder and/or active material may be the same or different as any other active layer. The active layers may be stacked to form an electrode film, and the electrode film may be laminated with a current collector to form an electrode.

Abstract: Provided are methods of preparing 3-R-1,4,2-dioxazol-5-one compounds using convenient and efficient methods. Also provided are 3-R-1,4,2-dioxazol-5-one compounds produced using the methods described.

Abstract: A neural network architecture is used that reduces the processing load of implementing the neural network. This network architecture may thus be used for reduced-bit processing devices. The architecture may limit the number of bits used for processing and reduce processing to prevent data overflow at individual calculations of the neural network. To implement this architecture, the number of bits used to represent inputs at levels of the network and the related filter masks may also be modified to ensure the number of bits of the output does not overflow the resulting capacity of the reduced-bit processor. To additionally reduce the load for such a network, the network may implement a “starconv” structure that permits the incorporation of nearby nodes in a layer to balance processing requirements and permit the network to learn from context of other nodes.

Abstract: Described is a multi-chip module that may include a Redistribution Layer (RDL) substrate having Integrated Circuit (IC) dies mounted to a first surface of the RDL substrate. A second plurality of IC dies may be mounted to an opposite second surface. A plurality of sockets can be mounted upon the second plurality of IC dies and a cold plate then mounted to the first plurality of IC dies. The mounting structure may include socket frames coupled to the plurality of sockets.

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 nonaqueous electrolyte for a lithium ion battery includes a lithium salt, a first nonaqueous solvent, and an additive mixture comprising a first operative additive of lithium difluorophosphate and a second operative additive of either fluoro ethylene carbonate or vinylene carbonate. A lithium-ion battery includes a negative electrode, a positive electrode comprising NMC with micrometer-scale grains, a nonaqueous electrolyte having lithium ions dissolved in a first nonaqueous solvent, and an additive mixture having a first operative additive of either fluoro ethylene carbonate or vinylene carbonate and a second operative additive of either 1,3,2-dioxathiolane-2,2-dioxide, another sulfur-containing additive, or lithium difluorophosphate.

Abstract: An integrated, unitary battery pack may be formed and used as part of the structural support for a vehicle frame. The unitary battery pack includes arrays cells having all positive and negative electrical terminals aligned in-plane on a common face of the product assembly. The unitary battery pack includes cooling components for passively or actively cooling the cell arrays. The unitary battery pack is encased in a potting material that allows that forms part of the structure support for the unitary battery pack. The unitary batter pack may be integrated into the vehicle with or without additional support structures.

Abstract: An autonomous driving controller includes a plurality of parallel processors operating on common input data. Each of the plurality of parallel processors includes a general processor, a security processor subsystem (SCS), and a safety subsystem (SMS). The general processors, the SCSs, and the SMSs of the plurality of parallel processors are configured to first, boot the plurality of SCSs from ROM second, boot the plurality of SMSs of the plurality of parallel processors from RAM or ROM, and, third, boot the plurality of general processors of the plurality of parallel processors from RAM. Between booting of the SCSs and the SMSs, at least one of the plurality of SCSs may load SMS boot code into the RAM that is dedicated to the plurality of SMSs.

Abstract: One embodiment can provide a photovoltaic roof tile. The photovoltaic roof tile can include a transparent front cover, a transparent back cover, and a plurality of polycrystalline-Si-based photovoltaic structures positioned between the front cover and the back cover. A respective polycrystalline-Si-based photovoltaic structure has a front surface facing the front cover and a back surface facing the back cover. The photovoltaic roof tile can further include a paint layer positioned on a back surface of the back cover facing away from the front cover. A color of the paint layer substantially matches a color of the front surface of the respective polycrystalline-Si-based photovoltaic structure.