Amazon Technologies, Inc.

Microsoft Technology Licensing, LLC

Darren Ernest Canavor

Jesper Mikael Johansson

Jon Arron McClintock

Daniel Wade Hitchcock

Brandon William Porter

Jonathan Kozolchyk

Andrew Jay Roths

Bharath Kumar Bhimanaik

George Nikolaos Stathakopoulos

Pragyana K Mishra

Darin Keith McAdams

Gregory Branchek Roth

Hilliard Bruce Siegel

Ethan Zane Evans

Tye Michael Brady

Jeffrey J Fielding

William Alexander Strand

David James Kane-Parry

Vaibhav Mallya

Nima Sharifi Mehr

Varadarajan Gopalakrishnan

Matthew Ryan Jezorek

Allan Scott Bathurst

Brian Young Lee

Gur Kimchi

Scott Donald Gregory

Charles Edward Cartwright

Gregory Alan Rubin

Harsha Ramalingam

Marshall Friend Tappen

Robert James Hanson

Phivos Costas Aristides

Erik Resch Parker

Wesley Scott Lauka

James Christopher Curlander

Ryan Scott Russell

Arnaud Marie Froment

Jules Cook Graybill

Tushaar Sethi

Chelsea Celest Krueger

Marcel Andrew Levy

Udit Madan

Zachary Ganwise Fewtrell

Max Harwell Funderburk

Jonathan Blair Norwood

Pradeep Ramarao

Andrew Alphus Kimbrough

Vijay Rangarajan

Cory Adam Johnson

Chandra Sekhar Venkata Bhanu Vijyapurpu

Dominique Imjya Brezinski

John J Lambert

Kenneth Grey Richards

Michael Vogelsong

Priti Marappan

Blake Parker Hess

Jason Christopher Rudmann

Dylan Harris Rush

Darryl Havens

Srikanth Mantha

Jane Mooney

Brian Dang

Zachary Damen Wolfe

Moustafa Ghazal

Jon Aaron McClintock

Luan Khai Nguyen

Brad Lee Campbell

Muhammad Wasiq

Shawn Domenic Loveland

Matthew Ryan Miller

Ryan Charles Colvin

Raashid Mohammed

Ryan F Conroy

John Elias Darrow

Kevin Michael Small

James Arthur Wilson

Nishant Mittal

Scott Kenneth Bishop

Ankit Pandey

Vikram Raghavan

Farouq Halawa

Erik Roy Veilleux

Jesper Mikael Johannson

Ido Mittelman

David W Hitchcock

Nathan David Scherer

Matthew Bucher

Preyas Joshi

Eric Michael Laird

Brenda Renee' Campbell

Kallie Ryan

Patrick Conlon

Jon Arron Mcclintock

Recent location and control information received from 'lead' vehicles that traveled over a segment of land, sea, or air is captured to inform, via aggregated data, subsequent “trailing” vehicles that travel over that same segment of land, sea, or air. The aggregated data may provide the trailing vehicles with annotated road information that identifies obstacles. In some embodiments, at least some sensor control data may be provided to the subsequent vehicles to assist those vehicles in identifying the obstacles and/or performing other tasks. Besides, obstacles, the location and control information may enable determining areas traveled by vehicles that are not included in conventional maps, as well as vehicle actions associated with particular locations, such as places where vehicles park or make other maneuvers.

Annotated virtual track to inform autonomous vehicle control

When a customer places an order for a first item and a second item, delivery systems utilize an aerial vehicle to transport the first item from a first source of the first item to a second source of the second item. At the second source, the first item and the second item are transferred into a carrier vehicle and transported toward a destination of the order. Once the carrier vehicle arrives within a vicinity of the destination, an autonomous ground vehicle departs the carrier vehicle with the first item and the second item, and delivers the first item and the second item to the destination. The delivery systems effectively expand the capacity of sources of items, and simplify processes for delivering orders for items, by enabling items from multiple sources to be combined at a single source prior to delivery, and transported to a destination from the single source.

Fulfilling orders for multiple items from multiple sources via multimodal channels

Disclosed are various embodiments for implementing passenger profiles for autonomous vehicles. A passenger of the autonomous vehicle is identified. A passenger profile corresponding to the passenger and comprising a passenger preference is identified. The passenger preference is identified. A configuration setting of the autonomous vehicle corresponding to autonomous operation of the autonomous vehicle is then adjusted based at least in part on the passenger preference.

Passenger profiles for autonomous vehicles

A method of implementing a network-enabled secure door lock, comprising obtaining measurements of an environment associated with a door from a variety of sensor types; generating, based at least in part on the measurements, a set of inputs to a machine-learning model; inputting the set of inputs into the machine learning model to determine a status of the door; generating a message that indicates the status of the door; and transmitting the message to a user device.

Sensor-based door lock confidence

A machine learning system builds and uses control policies for controlling robotic performance of a task. Such control policies may be trained using targeted updates. For example, two trials identified as similar may be compared and evaluated to determine which trial achieved a greater degree of task success; a control policy update may then be generated based on identified differences between the two trials.

Artificial intelligence system for efficiently learning robotic control policies

In some implementations, tokens that are representative of sensitive data may be used in place of the sensitive data to maintain the security of the sensitive data. For example, data may be separated into sensitive data and nonsensitive data, and at least the sensitive data is securely delivered to a data storage service. The data storage service generates a token that is representative of the sensitive data and stores the sensitive data as secure data. The data storage service may deliver the token to an entity that also receives the nonsensitive data, and the entity may use the token in place of the sensitive data. In some implementations, different tokens are generated each time the same piece of sensitive data is submitted for storage as secure data. Further, in some implementations, An expiration time may be assigned to sensitive data, and expired data and associated tokens may be deleted.

Token-based secure data management

Disclosed are various embodiments for managing security credentials. In one embodiment, knowledge-based questions are selected in response to failing to receive a valid master security credential in a request to authenticate a user account for access to account data. In response to receiving the request, the plurality of knowledge-based questions are provided to an application. Answers to the knowledge-based questions are received and scored. Access is granted to establish a new master security credential based at least in part on the score meeting or exceeding a predetermined threshold.

Managing security credentials

Recent location and control information received from 'lead' vehicles that traveled over a segment of land, sea, or air is captured to inform, via aggregated data, subsequent 'trailing' vehicles that travel over that same segment of land, sea, or air. The aggregated data may provide the trailing vehicles with annotated road information that identifies obstacles. In some embodiments, at least some sensor control data may be provided to the subsequent vehicles to assist those vehicles in identifying the obstacles and/or performing other tasks. Besides, obstacles, the location and control information may enable determining areas traveled by vehicles that are not included in conventional maps, as well as vehicle actions associated with particular locations, such as places where vehicles park or make other maneuvers.

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.

Autonomous vehicle networks

Autonomous vehicles may be deployed to areas where an item is in demand, and configured to fulfill orders for the item received from the areas. The autonomous vehicles are loaded with the item and dispatched to the area under their own power or in a carrier. When an order for the item is received, an autonomous vehicle delivers the item to a location in the area. Autonomous vehicles may also be equipped with a 3D printer or other equipment and loaded with materials for manufacturing the item. When an order for the item is received, the autonomous vehicle manufactures the item from such materials, and delivers the item. Autonomous vehicles may be configured for collaboration, such as to deliver or manufacture items in multiple stages and to transfer the items between vehicles. Autonomous vehicles may also be configured to automatically access locations in the area, e.g., using wireless access codes.

Delivering hems using autonomous vehicles

A security service enables service providers to register available services. Prospective service consumers may register with the security service to access a particular registered service, and may specify conditions for access that are subject to approval by the corresponding service provider. Based on the registrations of the service provider and the service consumer, the security service can define access policies that may be enforced to control the conditions under which a service consumer accesses or utilizes the particular service. Additionally, changes to the access policies may be propagated to running services in near real time. Some implementations enable masking of information provided to particular service consumers based on determined needs of each service consumer for access to particular information. In some instances, the service providers may provide log information to the security service, which may be monitored to identify anomalies, security breaches or the like.

Securing services and intra-service communications

Embodiments herein describe a system for providing visual feedback to an associate when stowing packages into containers. As an associate carries a package towards a container, a camera disposed over the container captures an image of the package that a computer vision system uses to identify a barcode on the package. Using the barcode, the system can determine the desired destination of the package and whether the container the associate is approaching is the correct destination of the package. If so, the feedback system can activate a directional light on above the container which outputs a first color (e.g., green), thereby informing the associate that the container she is approaching is the correct container. However, if container is not the correct destination of the package, the directional light outputs a different color light (e.g., red) which informs the associate the container is the wrong destination for the package.

Method and system for identifying packages

Systems, methods, and computer-readable media are described for a network address block treatment server. The network address block treatment server identifies blocks of network addresses, associates them with treatments, and generates compact representations of the network address blocks. Blocks may be identified based on network activity data or on the treatment of individual network addresses, and treatments may be associated with address blocks based on address-level and/or block-level criteria. Treatments may include, for example, denying service requests, throttling, queueing, issuing a challenge-response, or limiting the number or scope of services. The network address block treatment server may review treatments periodically or upon receipt of additional network activity data. The server may implement treatments in connection with firewall or routing services, or may transmit address block representations and associated treatments to network service providers for implementation.

Group-based treatment of network addresses

Growing community of inventors

Redmond, WA, United States of America

Darren Ernest Canavor