Abstract: Techniques are presented for the detection and management of collision warning (CW) events. A training dataset comprising videos of vehicle collisions and non-collisions, sensor readings, environmental conditions, and more is utilized to train a CW classification model for detecting potential collision events in vehicles. A backend CW classification model, with greater computational resources, employs a more complex neural network to review CW events received by the Behavioral Monitoring System (BMS) based on video data, achieving higher precision and reducing false positives. The CW model is installed in vehicles for real-time detection, while the backend model is deployed at the BMS. The BMS validates detected CW events, filters out false positives, and streamlines the review process for fleet administrators and customers. Additional BMS filtering operations include assessing non-proximity-related CW events and camera impairments, with the filtered CW events presented for review in the safety inbox.

Abstract: Methods, systems, and computer programs are presented for monitoring tailgating when a vehicle follows another vehicle at an unsafe distance. A method for enhancing a Following Distance (FD) machine learning (ML) model is disclosed. The method includes providing a management user interface (UI) for configuring FD parameters, followed by receiving FD events. A UI for manual FD annotation and another for customer review of filtered FD events are also provided. Annotations and customer review information are collected to improve the training set for the FD ML model. The FD model is then trained with the new data and downloaded to a vehicle. Once installed, the FD model is utilized to detect FD events within the vehicle, thereby enhancing the vehicle's safety and performance in driving scenarios by improving the accuracy and reliability of FD event predictions or detections.

Abstract: A computer-implemented method for machine learning model operation can include, by one or more processors executing program instructions: providing a first training dataset comprising a plurality of images and associated object detection labels, providing a second training dataset comprising a plurality of images and associated classification labels, and providing a machine learning model comprising a model backbone, an object detection task head, and a classification task head. The method can further include training the machine learning model by training the object detection task head using the first training dataset and training the classification task head using the second training dataset. The method can further include deploying the trained machine learning model that includes the trained model backbone and the trained object detection task head but does not include the trained classification task head.

Abstract: Methods and apparatus for etching high aspect ratio features in substrates having mixed material stacks are provided herein. Methods involve using low plasma power, high chamber pressure, and/or low temperature while exposing the substrate to a metal-containing additive gas during etching using a fluorocarbon gas.

Abstract: Methods, systems, and computer programs are presented for the management of lane-departure (LD) events. One method includes training a classifier for LD events and loading the classifier into a vehicle. LD events are detected based on outward images using the classifier, while the turn signal is monitored to prevent false triggers. If an LD event is detected, rules are checked for alerting the driver and deciding whether to alert the driver or not. Subsequently, additional rules are checked for reporting the event and deciding whether to report the event to a Behavior Monitoring System (BMS) or to discard it. The method also includes a solid line departure model that identifies crossing dashed, solid-white, and solid-yellow lanes, delaying alerts and event generation until a significant portion of the vehicle crosses over the lane. The model also outputs a confidence score reflecting the amount of vehicle deviation from the driving lane.

Abstract: A method for coating an optical substrate with an anti-reflection multilayered stack is provided. The method includes depositing a stack of dielectric layers having alternate index of refraction over a substrate, to form an anti-reflective coating. The method also includes depositing a first layer of low refractive index material on top of the stack of dielectric layers, etching the first layer of low refractive index material with a solvent at a selected temperature, and conformally depositing a sealant material over the first layer of low refractive index material to complete the anti-reflective coating. A headset for virtual reality, augmented reality, or mixed reality applications including optical components having an anti-reflection coating fabricated per the above method is also provided.

Abstract: Techniques are presented for detecting when drivers drive while drowsy. In some implementations, a drowsiness model is trained with data associated with inward videos and outward videos captured during a trip. The inward videos capture the inside of the cabin with the driver, and the outward videos capture the view in front of the vehicle in the direction of travel. Further, a device at the vehicle periodically calculates a drowsiness scale index value that indicates the level of drowsiness of the driver. Calculating the drowsiness scale index value includes obtaining a set of inward frames from the inward videos; for each inward frame, creating a face image by cropping the inward frame; obtaining a set of outward frames from the outward videos; calculating inward embeddings of the face images and outward embeddings of the outward frames; and calculating, by the drowsiness model, the drowsiness scale index value.

Abstract: A method for etching in plasma processing in a plasma chamber, including continually rotating between a first etch cycle and a second etch cycle for a period of time to etch a feature in a masked substrate. The method including performing the first etch cycle on the masked substrate using a first etching chemistry for a first sub-period. The first etch cycle is continually rotated between a first state configured for passivation, a second state, and third state configured for etching the masked substrate. During the second state of the first etch cycle, a first tuning step is performed by tuning the first etching chemistry, a high frequency RF power and a low frequency RF power to provide extended passivation to the feature in the masked substrate. The method including performing the second etch cycle on the masked substrate using a second etching chemistry for a second sub-period.

Abstract: A substrate processing apparatus includes a vacuum chamber with upper and lower electrodes and a processing zone for processing a substrate using plasma. The upper electrode includes a surface that is substantially parallel to a surface of the substrate when the substrate is positioned in the chamber. The apparatus includes at least one magnetic field source configured to generate one or more active magnetic fields through the processing zone, and a controller coupled to the at least one magnetic field source and the upper electrode. The controller is configured to apply RF power between the upper and lower electrodes to generate the plasma using a process gas. The controller controls the current through the at least one magnetic field source during the processing of the substrate, where the current is based on a target value corresponding to at least one characteristic of the one or more active magnetic fields.

Abstract: Arrangements described herein relate to systems, apparatuses, and methods for a disposable kit containing medical items configured for a medical device including a head cradle to support a head of a subject, the disposable kit includes a container that encloses a head cradle pad configured to be affixed to the head cradle, at least one fiducial marker configured to be disposed on a location at the head of the subject, and at least one enclosure configured to cover a portion of the medical device.

Abstract: Lithographic methodologies involving, and apparatuses suitable for, inline circuit edits are described. In an example, an integrated circuit structure includes a plurality of conductive structures along corresponding ones of a plurality of line tracks along a first direction. The integrated circuit structure also includes a white space track included within the plurality of line tracks, the white space track having a width along a second direction greater than a width of an individual one of the plurality of line tracks, the second direction orthogonal to the first direction. A conductive structure is along the white space track.

Abstract: Lithographic methodologies involving, and apparatuses suitable for, inline circuit edits are described. In an example, an integrated circuit structure includes a first conductive line and a second conductive line in a first dielectric layer, the second conductive line laterally spaced apart from the first conductive line. The integrated circuit structure also includes a first conductive via and a second conductive via in a second dielectric layer, the second dielectric layer over the first dielectric layer, the second conductive via laterally spaced apart from the first conductive via, the first conductive via vertically over and connected to the first conductive line, and the second conductive via vertically over but separated from the second conductive line.

Abstract: Lithographic methodologies involving, and apparatuses suitable for, inline circuit edits are described. In an example, an integrated circuit structure includes a plurality of conductive lines in a dielectric layer, individual ones of the plurality of conductive lines along a direction and spaced at a same interval. A conductive structure is in the dielectric layer, the conductive structure laterally between but not in contact with a pair of the plurality of conductive lines.

Abstract: An interconnect structure is disclosed. The interconnect structure includes a first line of interconnects and a second line of interconnects. The first line of interconnects and the second line of interconnects are staggered. The individual interconnects of the second line of interconnects are laterally offset from individual interconnects of the first line of interconnects. A dielectric material is adjacent to at least a portion of the individual interconnects of at least one of the first line of interconnects and the second line of interconnects.

Abstract: Interconnect structures are disclosed. An example includes conductive traces over a first dielectric layer, dielectric helmet structures over top surfaces of the conductive traces, and a second dielectric layer over the helmet structures. Spaces between adjacent ones of conductive traces are devoid of material. A bottom surface of the second dielectric layer is between top surfaces of the dielectric structures and bottom surfaces of the helmet structures, or co-planar with the top surface of the helmet structures, but the airgap extends above tops of the conductive traces. Another example includes a dielectric adjacent to upper sections but not lower sections of conductive traces, so as to provide airgaps between adjacent lower sections. Alternatively, a first dielectric material is adjacent the upper sections and a second compositionally different dielectric material is adjacent the lower sections. In either case, the sidewalls of the upper sections of the interconnect features may include scalloping.

Abstract: Arrangements described herein relate to systems, apparatuses, and methods for a disposable kit containing medical items configured for a medical device including a head cradle to support a head of a subject, the disposable kit includes a container that encloses a head cradle pad configured to be affixed to the head cradle, at least one fiducial marker configured to be disposed on a location at the head of the subject, and at least one enclosure configured to cover a portion of the medical device.

Abstract: Arrangements described herein relate to systems, apparatuses, and methods for a disposable kit containing medical items configured for a medical device including a head cradle to support a head of a subject, the disposable kit includes a container that encloses a head cradle pad configured to be affixed to the head cradle, at least one fiducial marker configured to be disposed on a location at the head of the subject, and at least one enclosure configured to cover a portion of the medical device.

Abstract: Embodiments of the disclosure are in the field of integrated circuit structure fabrication. In an example, an integrated circuit structure includes a plurality of conductive interconnect lines above a substrate, individual ones of the conductive interconnect lines having a top and sidewalls. An etch stop layer is on the top and along an entirety of the sidewalls of the individual ones of the conductive interconnect lines.

Abstract: Via connections for staggered interconnect lines are disclosed. An interconnect structure includes a first plurality of interconnects and a second plurality of interconnects, wherein the first plurality of interconnects and the second plurality of interconnects are staggered such that individual interconnects of the second plurality of interconnects are laterally offset from individual interconnects of the first plurality of interconnects. The interconnect structure also includes a via coupling an individual interconnect of the first plurality of interconnects to an individual interconnect of the second plurality of interconnects.

Abstract: The invention pertains the methods and compositions for generating methyl-seq NGS libraries, for whole genome sequencing or targeted resequencing. Additionally, the invention pertains the methods and compositions for determining methylation profiles of target nucleic acids.