Abstract: Systems and methods are described herein for generating potential feature combinations for a new item. A neural network may be utilized to identify positive and/or negative sentiment phrases from textual data. Each sentiment phrase may correspond to particular features of existing items. A machine-learning model may utilize the sentiment phrases and their corresponding features to generate a set of potential feature combinations for a new item. The potential feature combinations may be scored, for example, based on an amount by which a potential feature combination differs from known feature combinations of existing items. One or more potential feature combinations may be provided in a feature recommendation. Feedback (e.g., human feedback, sales data, page views for similar items, and the like) may be obtained and utilized to retrain the machine-learning model to better identify subsequent feature combinations that may be desirable and/or practical to manufacture.

Abstract: Systems and methods relating to generations of models to facilitate safe, automated handling and maneuvering of vehicles, such as unmanned aerial vehicles (UAV), by robotic systems, such as a robotic arm. The described systems and methods can include a robotic system, such as a robotic arm, having a load cell to measure certain forces and torques to generate models representing the behavior of vehicles and surfaces on which the vehicles may be placed and/or from which the vehicles may be removed.

Abstract: A vehicle or another object is grasped by a robotic arm of a handling system and caused to undergo one or more movements or manipulations resulting in a change of position, orientation, velocity or acceleration of the vehicle. Sensors provided in the robotic arm capture data representative of forces or torques imparted upon the robotic arm by the vehicle during or after the movement, or power or energy levels of vibration resulting from the movement. A signature representative of an inertial or vibratory response of the vehicle to the movement is derived based on the data. The signature may be compared to a baseline signature similarly derived for a vehicle that is known to be structurally and aerodynamically sound. If the signature is sufficiently similar to the baseline signature, the vehicle may also be determined to be structurally and aerodynamically sound.

Abstract: Systems and methods relating to automated handline of aerial vehicles are disclosed. The described systems and methods can include a plurality of robots operating on a continuous, closed-loop track. A plurality of aerial vehicle handling stations can be disposed along the continuous, closed-loop track, and each of the plurality of robots can engage an aerial vehicles and transport it to the aerial vehicle handling station, as needed, in accordance with a workflow associated with the aerial vehicle. The described systems and methods can provide a fully automated system for the ground handling of multiple aerial vehicles simultaneously.

Abstract: Prediction of outcomes of disruptive treatments are enabled utilizing sequenced training of a machine learning model over ordered bins of treatment candidates. Treatment candidates may be assigned to candidate characterization bins with an ordering, and the model may be trained with a sequence of training steps corresponding to the ordering of the candidate characterization bins, in each training step the model having untreated candidate features from a corresponding bin and aggregate metrics from one or more previous steps as input. The predicted outcome for a selected bin may be generated with the trained model having treated candidate features and aggregate metrics from one or more previous steps as input. The predicted outcome may be a counterfactual prediction for a bin with insufficient control candidates, and may represent a nonlinear extrapolation from control data in prior bins in the bin ordering.

Abstract: Disclosed are systems and methods to determine preferred delivery points within a parcel that are available to receive an aerial delivery of an item. For each delivery point a plurality of criteria scores may be determined for various criteria based on a processing of parcel data, image data, and/or sensor data corresponding to the parcel. The criteria may be aerial navigation related criteria or user preference criteria. The criteria scores may then be used to determine a suitability score for each delivery point. In some implementations, a user may specify a preferred delivery point and/or indicate one user criteria as more important than another criteria.

Abstract: Model-based dubbing techniques are implemented to generate a translated version of a source video. Spoken audio portions of a source video may be extracted and semantic graphs generated that represent the spoken audio portions. The semantic graphs may be used to produce translations of the spoken portions. A machine learning model may be implemented to generate replacement audio for the spoken portions using the translation of the spoken portion. A machine learning model may be implemented to generate modifications to facial image data for a speaker of the replacement audio.

Abstract: Disclosed are systems and methods to determine and rank large areas encompassing many parcels (e.g., neighborhoods, cities, towns) for aerial item delivery availability, without the use of image data of the areas. In some implementations, publicly available two-dimensional parcel maps that indicate parcel boundaries and outlines of structures on those parcels may be obtained and processed. For example, parcels within the area may be processed to determine deliverable area shapes, such as rectangles, within the parcel, excluding the area of the structure. A determination is then made as to whether one or more of the deliverable area shapes exceed a deliverable area threshold. If one or more of the deliverable area shapes of the parcel exceed the threshold, the parcel is considered to be available for aerial item delivery. This processing may be done for all parcels within an area or all customer parcels of customers of a service within the area (or any other selection criteria).

Abstract: A pervasive search architecture that indexes personal content of a querying user and made accessible to the user by other users. A compute node of a personal content location facilitates index generation and serve of the index. The index is generated for personal content stored at the personal content location. For a given content location, the index may encapsulate content stored in a set of locations with access permissions. The indexing application runs periodically at the personal content location and incrementally indexes content that is added to the shared locations. The same application allows the user to configure locations with the desired access permissions for participation in the search.

Abstract: Directed audio-encoded data emissions systems and methods may include one or more sensors, one or more audio transmitters, and a controller configured to cause emission of directed audio-encoded data toward various objects, such as vehicles, user devices, audio input/output devices, or others. For example, responsive to detecting a potential safety situation and/or a potential intended communication situation associated with one or more detected objects, audio-encoded data having selected audio characteristics may be emitted toward the detected objects using selected audio transmitters. The audio characteristics may be selected to encode one or more instructions to be executed by the detected objects, and the instructions may cause emission of audio, visual, or haptic notifications and/or initiation of various functions or operations by the objects.

Abstract: Disclosed are systems and methods that collect travel related data, which includes, but is not limited to, characteristics of obstacles, environmental conditions (e.g., wind speed, rain, barometric pressure, humidity), crowds of people, magnetic interference, etc., and operational characteristics of the aerial vehicle that result from the environmental conditions. The travel related data is then used to determine and/or optimize flight plans for aerial vehicles between a source location and a destination location.

Abstract: Played audio frames included in first audio content may be received over one or more networks. The first audio content may further include a replaced audio frame. The first audio content may correspond to video content that includes video of a face of a person as the person utters speech that is captured in the first audio content. Location data may also be received over the one or more networks. The location data may indicate locations of facial features of the face of the person in a video frame of the video content. The video frame may correspond to the replaced audio frame. Audio output may be generated that approximates a portion of the speech corresponding to the replaced audio frame. The audio output may be inserted into a replacement audio frame. Second audio content may be played including the played audio frames and the replacement audio frame.

Abstract: The Earth's oceans naturally distribute items aboard barges or other carrying vessels in an efficient manner. Carrying vessels are inserted into gyres, currents, eddies or other sources of flow by support vessels, which may be manned or autonomous. A carrying vessel may be transported from a port or other origin to a point within a naturally occurring flow of seawater by a support vessel, and permitted to travel at speeds and in directions defined by natural factors, from one point to another point, for extended durations. A carrying vessel may be removed from a naturally occurring flow of seawater by a support vessel and transported to a port or other destination. Flow rates, transit times and points within naturally occurring flows at which a carrying vessel may engage with or disengage from a support vessel may be determined according to a machine learning model or in any other manner.

Abstract: A vibration amplification and detection device may include a coiled diaphragm coupled to a pin that is also coupled to a substrate. The coiled diaphragm may be coupled to the pin via at least one axle and a fulcrum disc, and the vibration detection device may be coupled to a surface via the substrate. Responsive to vibration associated with or proximate the surface, the coiled diaphragm may receive and amplify the received vibration. In addition, a sensor associated with the vibration detection device may capture or detect the received and amplified vibration. Further, the detected vibration may be processed and compared with known vibrations and associated properties. Moreover, one or more actions may be instructed based on the detected vibration and associated properties.

Abstract: Audio content and played frames may be received. The audio content may correspond to first video content. The played frames may be included in the first video content. The first video content may further include a replaced frame. The played frames and the replaced frame may include a face of a person. Location data may also be received that indicates locations of facial features of the face of the person within the replaced frame. A replacement frame may be generated, such as by rendering the facial features in the replacement frame based at least in part on the locations indicated by the location data and positions indicated by a portion of the audio content that is associated with the replaced frame. Second video content may be played including the played frames and the replacement frame. The replacement frame may replace the replaced frame in the second video content.

Abstract: Techniques for managing notifications may be described. In an example, the notifications may relate to an item and may be provided to a user device. An active device may be associated with the item. The active device may store a token for communication with a local area network associated with a location. Based on the communication, a determination may be made that the item may be in proximity to the location. Corresponding notifications may be sent to the user device.

Abstract: Systems and methods are provided for using a machine learning model to analyze customers data for each of a number of customers interacting with electronic commerce, and determining whether the customers are high value customers. For the high value customers, one or more high value actions are then determined by the machine learning model, the one or more high value actions representing actions previously performed by or with respect to the customers and that correlate with a likelihood of the customers reaching high value customers status. Non-high value customers may then be prompted to perform the high value action which may elevate the non-high value customers to high value customers status.

Abstract: Techniques for generating an automated guide for exploring content of a content streaming platform based on inferred intent are described herein. For example, click stream data from interactions with a content streaming platform during a session, along with historical click stream data of historical interactions with the content streaming platform during historical sessions may be obtained. A score for each piece of content from a plurality of content offered by the content streaming platform may be determined based on the click stream data and the historical click stream data. The plurality of content may be ranked based on the associated scores for each piece of content. Media content may be generated that includes a portion of an associated trailer from a subset of the ranked plurality of content based on the score for each piece of content of the subset. The media content may be presented via a user interface.

Abstract: The present disclosure is directed to a network of autonomous vehicles, such as autonomous ground vehicles (“AGVs”) that deliver items to and/or from a destination location and/or perform a service. For example, a community (e.g., neighborhood, apartment complex) may include a plurality of autonomous vehicles that deliver payloads to different locations (e.g., homes, apartments) within the community for use or consumption. Some of the payloads are community items (e.g., microwave, stove top, cooking utensils) that are shared by members of the community and transferred between locations within the community by autonomous vehicles.

Abstract: An intermediary device may be configured to allow an authorized visitor to access a secure facility (such as a home) on behalf of an owner. The intermediary device may generate an authenticator and provide the authenticator to a service provider, who may then present the authenticator to the intermediary device upon arriving at the facility. The intermediary device may unlock or open, or lock and close, any doors within the facility as necessary in order to grant access to a specific portion of the facility and restrict access to other portions of the facility. The intermediary device may also capture, or cause the capture of, images or other data regarding actions taken by the service provider, and establish a communications channel with the owner for the exchange of information or data regarding such actions, or any events or conditions of the facility.