Amazon Technologies, Inc.

Xin Wang

Andrew Stubbs

Pavan Kumar Surishetty

Jason Makuch

Aaron Joseph Parness

Kimberly Nicole Hunter

Baoyuan Liu

Parker Owan

Sisir Babu Karumanchi

Kristina Lisa Klinkner

Joshua Rosenberg Hooks

Richard W Kim

Rahul Balakrishna Warrier

Andres Camilo Cortes

Radhika Suresh Karandikar

James Schmidt

Siyu Dai

Aaron Nicholas Olsen

James Shu

Shinji Kimura

Techniques and systems for performing a perception analysis for a robotic stowing operation are described. An example technique includes obtaining, via multiple sensors, multiple first images, wherein each first image is an image of a different container of an inventory holder within a robotic workcell. A first machine learning (ML) and image processing pipeline is performed with the first images to determine displacement locations for the containers of the inventory holder. A second ML and image processing pipeline is performed with the first images to determine content signatures for the containers. A plan is generated for stowing a first item into a first container, based at least in part on the plurality of content signatures and the plurality of displacement locations. A robotic apparatus is controlled to stow the first item into the first container, based on the plan.

Visual perception and techniques for placing inventory into pods with a robotic workcell

Systems, methods, and computer-readable media are disclosed for voice-based content searching. The systems, methods, and computer-readable media described herein may improve user experiences by providing voice-based content searching using mobile devices. In an example method described herein, a computer system may receive a voice search initiation signal from a mobile device over a WiFi protocol connection or a Bluetooth protocol connection. The computer system may monitor a WiFi receiver and a Bluetooth receiver of the computer system for first voice data. The computer system may determine that the first voice data is being received at the WiFi receiver. The computer system may determine that second voice data is received at the Bluetooth receiver while the first voice data is being received at the WiFi receiver, and discard the second voice data.

Voice-based content searching on a television based on receiving candidate search strings from a remote server

Described are techniques and systems for providing a virtual controller user interface. The virtual controller user interface of a source media device accepts user input and provides control data based on that input to a target media device. The target media device may process the control data, injecting input events into an operating system of the target media device. An application executing on the target media device may use these inputs.

Virtual controller for touchscreen

Growing community of inventors

San Mateo, CA, United States of America

Xin Wang