Abstract: Various implementations include road noise cancelation (RNC) systems and related approaches for RNC. Certain implementations include a RNC system having: a position sensor configured to detect a position of an occupant in a vehicle; a transducer configured to receive a cancelation signal and produce a cancelation audio signal in the vehicle; a microphone configured to provide an error signal representative of acoustic energy at a first location in the vehicle; a set of projection filters configured to filter the error signal to provide an estimated error signal at the position of the occupant in the vehicle, wherein the set of projection filters are selected from a predefined library of projection filters associated with a set of occupant positions in the vehicle; and an adaptive module that adjusts the cancelation signal based on the estimated error signal.

Abstract: In various examples, systems and methods are disclosed that use one or more machine learning models (MLMs)—such as deep neural networks (DNNs)—to compute outputs indicative of an estimated visibility distance corresponding to sensor data generated using one or more sensors of an autonomous or semi-autonomous machine. Once the visibility distance is computed using the one or more MLMs, a determination of the usability of the sensor data for one or more downstream tasks of the machine may be evaluated. As such, where an estimated visibility distance is low, the corresponding sensor data may be relied upon for less tasks than when the visibility distance is high.

Abstract: In various examples, methods and systems are provided for determining, using a machine learning model, one or more of the following operational domain conditions related to an autonomous and/or semi-autonomous machine: amount of camera blindness, blindness classification, illumination level, path surface condition, visibility distance, scene type classification, and distance to a scene. Once one or more of these conditions are determined, an operational level of the machine may be determined, and the machine may be controlled according to the operational level.

Abstract: In various examples, detecting line segments of traffic features for autonomous and/or semi-autonomous systems and applications. Systems and methods described herein may determine locations of line segments (e.g., dashed markings) associated with road markings within environments. For instance, one or more machine learning models may process sensor data (e.g., image data, etc.) in order to determine points associated with the line segments as represented by the sensor data and/or directional indicators (e.g., directional vectors) associated with the points. As described herein, the points may be associated with edges of the line segments, centers of the line segments, and/or other locations of the line segments. Systems and methods are then further described herein that perform operations based on the locations of these line segments, such as updating a localization map, performing localization, and/or determining trajectories to navigate.

Abstract: The present disclosure relates to determining a first illumination level corresponding to an area based at least on a first illumination detection obtained using a first illumination detector corresponding to a machine. A second illumination level corresponding to the area may be determined based at least on a second illumination detection obtained using a second illumination detector corresponding to the machine. Based at least on the first illumination level and the second illumination level, a scene illumination state of the area may be determined. Based at least on the scene illumination state, one or more lights of the machine may be controlled.

Abstract: In various examples, systems and methods are disclosed that use one or more machine learning models (MLMs)—such as deep neural networks (DNNs)—to compute outputs indicative of an estimated visibility distance corresponding to sensor data generated using one or more sensors of an autonomous or semi-autonomous machine. Once the visibility distance is computed using the one or more MLMs, a determination of the usability of the sensor data for one or more downstream tasks of the machine may be evaluated. As such, where an estimated visibility distance is low, the corresponding sensor data may be relied upon for less tasks than when the visibility distance is high.

Abstract: In various examples, methods and systems are provided for determining, using a machine learning model, one or more of the following operational domain conditions related to an autonomous and/or semi-autonomous machine: amount of camera blindness, blindness classification, illumination level, path surface condition, visibility distance, scene type classification, and distance to a scene. Once one or more of these conditions are determined, an operational level of the machine may be determined, and the machine may be controlled according to the operational level.

Abstract: The present disclosure relates to determining a first illumination level corresponding to an area based at least on a first illumination detection obtained using a first illumination detector corresponding to a machine. A second illumination level corresponding to the area may be determined based at least on a second illumination detection obtained using a second illumination detector corresponding to the machine. Based at least on the first illumination level and the second illumination level, a scene illumination state of the area may be determined. Based at least on the scene illumination state, one or more lights of the machine may be controlled.

Abstract: The present disclosure relates to determining a first illumination level corresponding to an area based at least on a first illumination detection obtained using a first illumination detector corresponding to a machine. A second illumination level corresponding to the area may be determined based at least on a second illumination detection obtained using a second illumination detector corresponding to the machine. Based at least on the first illumination level and the second illumination level, a scene illumination state of the area may be determined. Based at least on the scene illumination state, one or more lights of the machine may be controlled.

Abstract: A method of operating a heating, air conditioning, and ventilation (HVAC) system includes determining one or more user preferences for environmental conditions in a structure. The method also includes determining one or more interior environmental parameters measured for the interior space, the one or more environmental parameters including at least one of interior temperature, interior humidity, or interior air quality. The method also includes determining one or more exterior environmental parameters measured for an exterior space outside the structure, the one or more exterior environmental parameters including at least one of exterior temperature, exterior humidity, and exterior air quality. Further, the method includes determining a ventilation decision.

Abstract: Systems and devices for correcting a periodic signal includes receiving index light detection data from an optical scanner, determining a bias error of a moveable mirror in optical scanner based on the index light detection data, determining a phase shift error of the moveable mirror based on the index light detection data, and determining an amplitude error of the moveable mirror based on the index light detection data.

Abstract: In various examples, methods and systems are provided for determining, using a machine learning model, one or more of the following operational domain conditions related to an autonomous and/or semi-autonomous machine: amount of camera blindness, blindness classification, illumination level, path surface condition, visibility distance, scene type classification, and distance to a scene. Once one or more of these conditions are determined, an operational level of the machine may be determined, and the machine may be controlled according to the operational level.

Abstract: A replaceability index for an artwork is calculated. Search terms relating to the artwork, such as artist name, title, date of work, among several others, are used to search various data sources. These searches retrieve records representing other artworks that are market comparables to the subject artwork. Each record is assigned a score. The total of all the scores is calculated. This sum is divided by the total number of records found and the result is a replaceability index, a value that indicates how abundant or how scarce the subject artwork is. This index may be used by a human appraiser to determine a fair market value of the subject artwork. A search term ranking for an artwork and multiple records representing market comparable artworks are used to identify the most relevant market comparables using what is referred to as ordinal priorities.

Abstract: In various examples, systems and methods are disclosed that use one or more machine learning models (MLMs) - such as deep neural networks (DNNs) - to compute outputs indicative of an estimated visibility distance corresponding to sensor data generated using one or more sensors of an autonomous or semi-autonomous machine. Once the visibility distance is computed using the one or more MLMs, a determination of the usability of the sensor data for one or more downstream tasks of the machine may be evaluated. As such, where an estimated visibility distance is low, the corresponding sensor data may be relied upon for less tasks than when the visibility distance is high.

Abstract: A process for determining open interest in an artwork and creating an emerging demand graph or chart is described. This is done by displaying information on the artwork for the public to view. An absentee bidding period is set wherein the online platform accepts absentee bids for the artwork. Certain absentee bids are used to calculate an open interest index in the artwork which is used to adjust the emerging demand graph. This open interest index can be used to measure interest in the artwork before the actual auction of the artwork begins. The actual auction is a modified Dutch auction that uses data from the absentee bidding period, such as the highest absentee bid.

Abstract: Systems and methods for predicting the trajectory of an object are disclosed herein. One embodiment receives sensor data that includes a location of the object in an environment of the object; accesses a location-specific latent map, the location-specific latent map having been learned together with a neural-network-based trajectory predictor during a training phase, wherein the neural-network-based trajectory predictor is deployed in a robot; inputs, to the neural-network-based trajectory predictor, the location of the object and the location-specific latent map, the location-specific latent map providing, to the neural-network-based trajectory predictor, a set of location-specific biases regarding the environment of the object; and outputs, from the neural-network-based trajectory predictor, a predicted trajectory of the object.

Abstract: Systems and methods for predicting the trajectory of an object are disclosed herein. One embodiment receives sensor data that includes a location of the object in an environment of the object; accesses a location-specific latent map, the location-specific latent map having been learned together with a neural-network-based trajectory predictor during a training phase, wherein the neural-network-based trajectory predictor is deployed in a robot; inputs, to the neural-network-based trajectory predictor, the location of the object and the location-specific latent map, the location-specific latent map providing, to the neural-network-based trajectory predictor, a set of location-specific biases regarding the environment of the object; and outputs, from the neural-network-based trajectory predictor, a predicted trajectory of the object.

Abstract: Provided is a split-gate embedded flash memory cell and method for forming the same. The flash memory cell includes split-gate transistors in which the control gate is aligned with respect to the floating gate without the use of a photolithographic patterning operation to pattern the material from which the control gates are formed. An anisotropic blanket etching operation is used to form the floating gates of the split-gate floating gate transistors alongside sidewalls of a sacrificial layer. Local oxidation of silicon (LOCOS) methods are not needed to form the inter-gate dielectric and therefore high integrity is maintained for the floating transistor gates. The floating transistor gates are formed of charge storage material such as silicon nitride, Si3N4 in some embodiments.

Abstract: Provided is a split-gate embedded flash memory cell and method for forming the same. The flash memory cell includes split-gate transistors in which the control gate is aligned with respect to the floating gate without the use of a photolithographic patterning operation to pattern the material from which the control gates are formed. An anisotropic blanket etching operation is used to form the floating gates of the split-gate floating gate transistors alongside sidewalls of a sacrificial layer. Local oxidation of silicon (LOCOS) methods are not needed to form the inter-gate dielectric and therefore high integrity is maintained for the floating transistor gates.

Abstract: Apparatus and methods for collecting information may include receiving one or more inputs of information related to a business experience. In addition, the apparatus and methods may include storing the received business information. The methods may also include analyzing the received information to generate one or more targeted recommendations; and forwarding the one or more targeted recommendations to management of the business.