Abstract: An end-of-arm tool for attachment to a robotic arm, includes a housing, an outer suction cup assembly that includes an outer suction cup located at the distal end of the housing, and an inner suction cup assembly that extends centrally through the outer suction cup assembly. The inner suction cup assembly includes a lower suction tube, an inner suction cup that is positioned at a distal end of the lower suction tube and is in fluid communication with the lower suction tube. The inner suction cup is concentrically located relative to the outer suction cup. The tool includes an actuator configured to selectively extend and retract the lower suction tube with respect to the outer suction cup.

Abstract: A head-mounted wearable device provides many functions to a user. The functions may be provided based in part on whether the device is being worn (donned) or not worn (doffed). Force sensing resistors in the device provide output indicative of forces associated with wearing the device. A time series of values indicative of the magnitude of a force may be determined. An increase or decrease in force values measured at different times may indicate that the device has been donned or doffed, respectively. If a subsequent force value does not differ substantially from a previous force value, this may indicate that the device has remained donned or doffed.

Abstract: Systems and methods for adaptive information packet transmission are disclosed. For example, one or more backup packets may be generated for a given data packet and a packet-spacing value and/or packet-sending order may be determined based at least in part on packet-loss data and/or other factors. The data packets and backup packets may be sent according to the packet-spacing value and packet-sending order, and feedback data may be provided by the receiving device. The feedback data may be utilized by the sending device to adapt the packet transmission parameters.

Abstract: A system of one or more processors receives information from a computing device associated with a user profile, the information identifying a first list of content items including first episode in a series. The system determines that the first episode has been played using a content state of the first episode. The system determines a second list of content items, including a second episode in the series as an unsolicited content item and removing the first episode from the second list. The system sends the second list to the computing device and the computing device deletes the first episode and downloads the second episode in the series without first receiving a download request from a user or application of the computing device.

Abstract: Hybrid sortation systems and methods may include a floor having a plurality of transfer locations, a plurality of container drive units or pods that may be positioned at respective transfer locations to receive packages, and a plurality of overdrive units that may travel over and sort packages to respective transfer locations. The overdrive units may be configured to travel over container drive units or pods, such that operations or movements of container drive units or pods may be substantially decoupled or independent from operations or movements of overdrive units. In this manner, sort density and throughput of such hybrid sortation systems may be increased, while also reducing congestion associated with operations or movements of robotic drive units.

Abstract: A laminate includes an outer liner having a resin layer disposed on a paper sheet. The resin layer extends between first and second opposed lateral edges of the sheet and defines a moisture barrier. A cushion layer is disposed over the resin layer. An inner liner of kraft paper is disposed over the cushion layer. A region of the resin layer is activated into an adhesive bonding the cushion layer and inner liner to the sheet. The laminate defines first and second longitudinally adjacent portions. The outer liner in the first portion has opposed first and second peripheral portions extending laterally outward from opposed lateral edges of the cushion layer and inner liner to the first and second lateral edges of the sheet, whereby a first width between the lateral edges along the first portion exceeds a second width measured the lateral edges along the second portion.

Abstract: Systems, methods, and computer-readable media are disclosed for automated balancing and flow management of items in multi-item orders to packing equipment. In one embodiment, an example method may include determining a first order identifier associated with a first item identifier and a second item identifier, determining that a first sorting load associated with a first item sorting machine is less than a second sorting load associated with a second item sorting machine, and determining a first tote identifier associated with the first item sorting machine. The method may include determining that a first item associated with the first item identifier is placed in a first tote associated with the first tote identifier, causing the first tote to be routed to the first item sorting machine, and determining that the first item and a second item associated with the second item identifier are ready for packing into a shipment.

Abstract: Disclosed are systems and methods for in-transit or in-flight error correction in state prediction of the vehicle. Natural patterns, such as fields, residential neighborhoods, business areas (e.g., downtown), etc., and/or objects, such as streets, cars, houses, trees, buildings, bridges, roads, parking lots, etc., that are naturally within the environment may be determined and used to correct any error in the aerial vehicle state prediction, while the vehicle is in transit, thereby eliminating or reducing the cumulative error involved in traditional systems.

Abstract: Techniques for dataset schema and metadata management are described. A data model management service provides a logically centralized repository that allows discovery of datasets via exploration of dataset metadata. The data model management service can ensure the validity of the datasets and the associated metadata by enforcing dataset validation rules and/or requiring dataset metadata to be provided and limiting visibility into non-compliant datasets.

Abstract: Embodiments herein describe a controller for a machine that wirelessly transmits a destination address to a robot which is tasked with transporting an item to the destination corresponding to the received address. Using the address, the robot can select a predefined path stored in its memory for that address. Because multiple robots can move items in the machine at the same time, the robots may collide if their predefined paths intersect. The machine can use a variety of different techniques to prevent collisions between the robots as the robots deliver items to different locations along their predefined paths.

Abstract: Methods and systems for provisioning computing resource instances among implementation resources based on trust to reduce interference between computing resource instances implemented by the same implementation resources. In an embodiment, a trust rating is determined for a computing resource instance based at least in part on one or more trust factors. The suitability of an implementation resource to implement the given computing resource instance may be evaluated based at least in part on the trust rating of the computing resource instance and a trust rating of the implementation resource. In some embodiments, the trust rating of the implementation resource may be predefined or based on trust ratings of computing resource instances that are currently implemented by the implementation resource. An implementation resource may be selected to implement the computing resource instance based at least in part on its suitability thus determined.

Abstract: A synthetic document generator that obtains a configuration for a synthetic document derived from real-world documents. The configuration specifies element templates to be included in the synthetic document and weights for the specified element templates. The system generates synthetic documents based on the configuration; the synthetic documents include diversified versions of the element templates specified in the configuration. Annotation documents are generated for the synthetic documents that include information describing the respective synthetic documents. A machine learning model for analyzing real-world documents can then be trained using the synthetic and annotation documents. Feedback from the analysis of real-world documents by the machine learning model can be used to generate a new configuration for generating additional synthetic and annotation documents which are used to further train the model.

Abstract: Edge functions at an edge location of a content delivery network (CDN) may access data from a back-end database without the need to make high-latency network calls to the back-end databases. When a client sends a query to the edge location, an edge function is triggered. The requested data may be retrieved from a read-only local table at the edge location (populated from a back-end database) and the retrieved data is provided to the edge function's memory for low-latency access during function execution.

Abstract: A resource management system of a computing resource service provider supports the provisioning of multiple identical or substantially similar virtual computing resource instances using a single resource definition by creating a resource set entity to which the provisioned instances belong. The resource management system controls the provisioning based on a template containing the resource definition and designed to service a situation where the intent is to create a group of similar or closely-related resources. The group of instances (i.e., items in the resource set) can be dimensioned by specifying the size of the set, or by mapping the set to another set of keys associated with a different context. A resource set definition in the template can include a program expression that the system evaluates to produce a list of the keys, and the instances may be created based on the number of keys and their associated values.

Abstract: Scaling events may be detected for hosting hierarchical data structures. Scaling events may be detected to modify the capacity of a data store for hierarchical data structures to handle changing write workloads, read workloads, or storage capacity. Hierarchical data structures may be moved from one group of storage hosts to another group of storage hosts according to a filtered snapshot that includes the hierarchical data structures to be moved that is provided to the destination storage hosts. Changes made to the hierarchical data structures made at the source storage hosts during the move can be applied to the filtered snapshot so that the hierarchical data structures may be made available at the destination storage hosts inclusive of the changes.

Abstract: A media storage service may maintain an asset including information to indicate a specific media content and a specific number of replicas to be stored by the media storage service for the specific media content. The media storage service may receive content recording-related requests from a recording manager to define or update the specific number for the specific media content. The media storage service may receive one or more segments specific to the media content from an encoder. The media storage service may create and store the specific number of replicas, as indicated in the asset, for the media content.

Abstract: Devices having touchscreen displays or other types of sensors may be placed adjacent to one another to form a larger display area for content. A relative position and alignment between these adjacent devices are determined using a touch gesture by a user. For example, a user may draw a line, circle, or other shape that provides input to the touch sensors of the devices. Touch data received from each device indicates the coordinates where contact was provided to the touch sensor. By matching the coordinates positioned near the borders of adjacent devices based on the time of their input, the relative position and alignment between the devices is determined. A corresponding portion of the content is provided to each device based on its relative position and alignment to form a consistent display area.

Abstract: Generally described, one or more aspects of the present application relate to a public snapshot service for associating a block-level snapshot with certain snapshot properties that indicate a block load order, and creating a block storage volume from the snapshot by loading the blocks in the snapshot onto the block storage volume in the block load order indicated by the snapshot properties associated with the snapshot.

Abstract: A communication system and methods for data compression and the management of data transmitted between computing devices in a communication network are provided. Compression dictionaries generated from data previously maintained at a recipient computing device and a transmitting computing device are maintained at each respective device. The compression dictionaries are made up of fixed length data chunks from the data previously maintained on the computing device that can be matched to data to be compressed or de-compressed. Data can be transmitted without requiring the exchange of the compression dictionaries between the recipient computing device and the transmitting computing device.

Abstract: A device comprises a crossmember. The crossmember is supported by one or more weight sensors, such that a total weight of the crossmember and any supported load may be measured. One or more strain gauges are affixed to the crossmember. An accessory may comprise a portion to support an inventory item, such as a hook, shelf, bin, basket, and so forth. The accessory also includes an engagement feature to mechanically engage a portion of the crossmember. Several accessories may be engaged to the crossmember. As the load on the accessory changes, such as due to a pick or place of items, a total weight change may be determined by summing the output from the weight sensors. Data from the strain gauges may be used to allocate the total weight change to a particular accessory, allowing for the determination of the weight change for that particular accessory.

Abstract: A resource request is received by a network device from a virtual machine running on a host. The resource request includes a requested resource size. The network device allocates resources of the network device in response to the resource request. A resource response is sent by the network device to the virtual machine that generated the resource request. The resource response includes a location of the allocated resource.

Abstract: Techniques for employing user interfaces to output information indicative of events occurring in an inventory facility, and receive feedback from a human regarding the events are described herein. In one implementation, an event may take place in an inventory facility, such as a customer taking an item from an inventory location, returning an item to an inventory location, and so forth. An automated system of an inventory management system may process sensor data collected by sensors in the inventory facility to determine details of the event. In some examples, the inventory management system is unable to determine with a high level of confidence what occurred during the event. The inventory management system may provide the sensor data to a human associate through an associate interface, and receive input regarding details of the event from the human associate through the associate interface.

Abstract: In response to a determination that a first logical table is to be created in a data sheet, a respective row identifier is generated and stored for individual rows of the first logical table. To indicate a relationship between a particular cell of another logical table and a particular row of the first logical table, the row identifier of the particular row is stored. After a modification of a value stored in the particular row, the row identifier is used to determine an updated value to be displayed in the particular cell of the other logical table.

Abstract: A user interacts with an inventory location, such as a lane on a shelf, picking items or placing items to that inventory location. A neural network (NN) is trained using a subset of reference images to determine parameters, such as node weights. An image of the user interaction is acquired and processed by the NN to determine if an item in a test image matches an item in a candidate set of items. During use, the parameters are used to dynamically instantiate an ad hoc neural network having a graph that is based on a number of items in a candidate set. The candidate set of items may comprise items within reach of a user at the time the test image was acquired, such as on a nearby shelf or tote. The NN output indicates if the test image is deemed to match one of the candidate set of items.

Abstract: Sensors at an inventory location can be used to detect the occurrence of an event at the inventory location. For example, capacitive sensors can gather capacitance values, which can then be analyzed for changes that indicate an event has occurred at the inventory location. When an event has been detected, event data is generated and used as a possible trigger to collect additional sensor data. As an example, if an event involving items at an inventory location is detected, such an action can trigger the collection and analysis of additional sensor data, such as weight sensor data, to determine a quantity of the items added or removed from the inventory location.

Abstract: A hub device of a network receives a data model that includes a secure portion that is encrypted and one or more unsecure portions. The hub device deploys the one or more unsecure portions of the data model to respective edge devices of the network. The hub device decrypts the secure portion of the data model. The edge devices collect data (e.g., from sensors) and process the data using the unsecure portions of the data model. The edge devices send the processed data to the hub device. The hub device performs operations on the received processed data using the decrypted secure portion of the data model in a secure execution environment (e.g., a TPM or other secure module). The secure portion of the data model generates a result, which is then transmitted to an endpoint.

Abstract: Techniques for Scalable parallel elimination of approximately subsumed sets are described. A method for Scalable parallel elimination of approximately subsumed sets includes identifying a first plurality of blocks based at least on a plurality of records stored in a storage service of a provider network, determining a plurality of subsumption relationships between blocks from the first plurality of blocks, retaining a first subset of the first plurality of blocks and demoting a second subset of the first plurality of blocks based at least on the plurality of subsumption relationships, and iteratively performing dynamic blocking based at least on the first subset of the plurality of matching blocks and the second subset of the plurality of matching blocks to generate a subsequent pluralities of blocks.

Abstract: Systems and methods are provided herein for synchronizing content across multiple user devices. Content packets may be individually provided to user devices associated with a group. Each content packet may include a portion of content (e.g., media content) and a content index (e.g., an index that indicates a sequence by which the content packets are to be presented). The user device may begin to play the content packets according to the sequence. The user device may receive a particular content index identifying a particular content packet that occurs latest in the sequence and that has been received by all of the devices of the group. The user device may modify playback of the content packets based at least in part on the particular content index to synchronize playback of the content at the user device with respect to playback at the one or more devices.

Abstract: Techniques for authenticating users at devices that interact with the users via voice input. For instance, the described techniques may allow a voice-input device to safely verify the identity of a user by engaging in a back-and-forth conversation. The device or another device coupled thereto may then verify the accuracy of the responses from the user during the conversation, as well as compare an audio signature associated with the user's responses to a pre-stored audio signature associated with the user. By utilizing multiple checks, the described techniques are able to accurately and safely authenticate the user based solely on an audible conversation between the user and the voice-input device.

Abstract: Technologies directed to vertical coupling structures for antenna feeds of phased array antennas are described. One circuit board includes a first layer with a first portion of a RF coupling structure, a second layer with a second portion of the RF coupling structure, and a first insulation layer located between the first layer and the second layer. The RF coupling structure is configured to electromagnetically couple a first conductive trace on the first layer and a second conductive trace on the second layer at RF frequencies. The circuit board also includes a third layer with a first antenna element and a second insulation layer located between the third layer and the first layer, the second insulation layer including a first via through which the first antenna element is coupled to the first conductive trace.

Abstract: A user interface that facilitates the selection and purchase of an item may be presented on a display. The user interface includes a presentation section and one or more other sections, such as a title section, buy section, alternate image section, package art section, review section, rating section, or other section. The presentation section may extend a full-width of a display or window available for display, while maintaining a desired aspect ratio. Video, slideshows, or other visual information may be played within the presentation section. One or more sections may overlay the presentation section. For example, at least a portion of the buy section may overlay at least a portion of the presentation section.

Abstract: Systems, methods, and computer-readable media are disclosed for caching selected data for use in real-time content selection. In one embodiment, an example method may include determining a first set of user identifiers for users that are eligible to be presented with content associated with a first product identifier, the first set having a first number of user identifiers, determining a second set of user identifiers for users that are eligible to be presented with content associated with a second product identifier, the second set having a second number of user identifiers, and determining that the first number is greater than the second number. Example methods may include determining first content associated with the first product identifier, determining first product information associated with the first product identifier, and caching the first content and the first product information at a server instead of second content associated with the second product identifier.

Abstract: A machine learning engine may correlate characteristics of obstacles identified during remotely piloted UAV flights with manual course deviations performed for obstacle avoidance. An obstacle detection application may access computer vision footage to determine notable characteristics (e.g. a direction of travel and/or velocity) of obstacles identified during the piloted UAV flights. A deviation characteristics application may access flight path information identify course deviations performed by a pilot in response to the obstacles. A machine learning engine may use the obstacle characteristic data and the deviation characteristics data as training data to generate an optimal course deviation model to use by an autopilot module to autonomously avoid obstacles during autonomous UAV flights.

Abstract: A system, method, and computer readable storage medium for inter-process rendering pipeline for shared process remote web content rendering. The method includes obtaining an image rendering request through an inter-process communication channel established by an application in which the image rendering request including a content area. The method further includes selecting a content rendering engine based on one or more image resources needed to generate web content as specified in the image rendering request, determining the one or more image resources corresponding to the image rendering request by using the content rendering engine, and generating the web content on the content area based at least in part on the one or more image resources.

Abstract: A speech interface device is configured to receive response data from a remote speech processing system for responding to user speech. This response data may be enhanced with information such as remote NLU data. The response data from the remote speech processing system may be compared to local NLU data to improve a speech processing model on the device. Thus, the device may perform supervised on-device learning based on the remote NLU data. The device may determine differences between the updated speech processing model and an original speech processing model received from the remote system and may send data indicating these differences to the remote system. The remote system may aggregate data received from a plurality of devices and may generate an improved speech processing model.

Abstract: A technology is described for modifying a message frequency of a device. In one example, a network connection is identified between a device and a service provider environment. A message frequency is set for which to send reachability messages between the device and the service provider environment to maintain the network connection. The reachability messages may be sent between the device and the service provider environment at the message frequency. After testing whether the networking connection is maintained at the message frequency, the message frequency may be modified to a modified message frequency.

Abstract: Systems and methods are described herein for generating adaptive feedback in response to a user request. Input indicative of a user request may be received and utilized to identify an item in an electronic catalog. A title for the item may be retrieved and provided, as input, to a machine-learning model. The machine-learning model may be trained to identify one or more segments of an input title. A shortened title may be generated from these identified segments and provided as output at the user device (e.g., via audible output provided at a speaker of the user device). In some embodiments, the length and content of the shortened title may vary based at least in part on the contextual intent of the user's request.

Abstract: Technology for content distribution in wireless mesh network is described. In one embodiment, the wireless mesh network includes a plurality of mesh nodes, wherein each of the mesh nodes includes a content agent configured to receive a content command from a cloud computing content management service communicatively coupled to the wireless mesh network, the content command identifying one or more segments of a media content file corresponding to a media title to be stored on the mesh node. Each mesh node includes a storage system configured to store the one or more segments of the media content file specified in the content command. Each mesh node further includes a content server configured to service requests for playback of the media title from one or more mesh clients. The mesh nodes also include a mesh communication component configured to communicate with other mesh nodes in the wireless mesh network to retrieve segments of the media content file stored on the other nodes.

Abstract: Methods and apparatus for token-based admission control for replicated writes are disclosed. Data objects are divided into partitions, and corresponding to each partition, at least a master replica and a slave replica are stored. A determination as to whether to accept a write request directed to the partition is made based at least in part on one or more of (a) available throughput capacity at the master replica, and (b) an indication, obtained using a token-based protocol, of available throughput capacity at the slave replica. If the write request is accepted, one or more data modification operations are initiated.

Abstract: Clients within a computing environment may establish a secure communication session. Sometimes, a client may trust another client to read, but not modify, a message. Clients may utilize a cryptography service to generate a message protected against improper modification. Clients may utilize a cryptography service to verify whether a protected message has been improperly modified.

Abstract: Techniques are described for adaptive encoding different portions of media content based on content. Characteristics of GOPs of media content can be determined and used to set encoding parameters for the GOs. The GOPs can be encoded such that one GOP is encoded differently than another GOP if they have different characteristics.

Abstract: Functionality is disclosed for defining an auto-reply message while defining an appointment on a calendar associated with a user. A request may be received by way of a personal information management (PIM) client application to define a new appointment on a calendar associated with a user. A UI for defining the new appointment may be presented that includes a UI control for defining a time period for the new appointment and a UI control for defining an auto-reply message to be transmitted in response to email messages received during the time period. In response to the user defining the appointment and the auto-reply message, a request may be transmitted to a PIM server application to create the appointment along with an auto-reply message definition that defines the auto-reply message. The auto-reply message is then transmitted in response to email messages received during the time period associated with the meeting.

Abstract: Methods and apparatus that allow clients to establish sub private networks as resources within private networks on a provider network. A sub private network may be owned and controlled by a different entity than the owner of its parent private network. A parent private network controls access to its sub private networks, and each sub private network also controls access to its resources. This enables a layered topology in which a parent private network may establish access control rules for its sub private networks; the sub private networks may supplement the access control according to their specific needs. Sub private networks may share resources of their parent private network, and a sub private network may allow or restrict access to its resources by its parent private network, by its sibling private networks, and/or by its own sub private network(s).

Abstract: A technology is provided for delivering a data object to device. Data delivery instructions to distribute a data object to a device may be received at a delivery service and include a storage location of the data object, a messaging topic, and a size of data receivable by the device. The data object is then divided into blocks corresponding to the size of data receivable by the device. A messaging topic is identified to which the device is subscribed via a messaging service. The blocks are sent to the device using the messaging topic and a network protocol installed on the device.

Abstract: Systems and methods are provided to add flow identification information to packets of network traffic. Each packet can have flow identification information added based on the packet being sent to a full-proxy mode appliance. A stateful network routing service may intercept packets and determine the packets are to be sent to a full-proxy mode appliance. Based on this determination, the stateful network routing service may obtain or generate flow identification information to identify the packet. The stateful network routing service may add the information to the packet and transmit the enriched packet to a full-proxy mode network appliance. The stateful network routing service may receive a second enriched packet from the network appliance. The stateful network routing service can parse the second enriched packet for flow identification information and identify the second enriched packet based on the flow identification information.

Abstract: A technology is provided for synchronizing data with delayed subscriptions. A request may be received at a data proxy for a data snapshot for an application that has been offline at the client. A subscription may be held for a pre-determined amount of time after the request for the snapshot. The data snapshot may be sent to the client. The data for the subscription may be sent after the pre-determined amount of time.

Abstract: A technology is described for a device shadowing service that manages device states. An example method may include receiving a state change message associated with a device that a subcomponent of the device has assumed a first state. In response to the state change message, a subcomponent representation associated with a device representation may be updated to indicate the first state received, where the device representation represents the device and the subcomponent representation represent the subcomponent of the device. Thereafter, a request may be received for the first state of the subcomponent of the device. The first state indicated by the subcomponent representation associated with the device representation may be determined, and the first state may be returned in response to the request.

Abstract: A system includes a provider network and a client network connected via a dedicated physical connection. The client network and the provider network exchange routing information using routing protocol messages, such as border gateway protocol (BGP) update messages exchanged during a BGP session. A provider network includes tag field values in outgoing routing protocol messages that indicate a portion of the provider network wherein resources of the provider network associated with a corresponding route are located. The client network may use the tag field value to determine whether to add the route to a routing table of the client network. A client network may also include tag field values in outgoing routing protocol messages to a provider network. The tag field values may indicate what portions of the provider network are to receive the routes from the client network. For example a tag field value may indicate that a route is to be propagated within a limited portion of the provider network.

Abstract: Techniques for accommodating irregular timing information in streamed media data are described. According to some embodiments, at least a portion of a media stream that includes a video component is received, the video component including a plurality of video frames and video timing data, and wherein the media stream includes an indication of a video frame rate. A first duration of a first video frame of the plurality of video frames is determined to be different than an expected video frame duration, wherein the expected video frame duration is based at least in part on the indication of the video frame rate. A timestamp of at least one video frame of the plurality of video frames is adjusted to change the first duration.