Amazon Technologies, Inc.

Timothy Stallman

Tye Michael Brady

Frank Preiswerk

Michael R Calder

Michael Robert Bocamazo

Mafalda Ghira Borges

Harris Scott Davidson

Anders Richard Johnson

Abigail Phyllis Rodrigues

Mindy Tieu

John Gregory Longtine

Andrew M Sweeney

Gregory Longtine

Elisha Gallaudet

Yuzhong Huang

Hunter Normandeau

Ziyu Wang

Menashe Garber

Armon Shariati

Anna Buchele

Juan Carlos Del Rio

Rocco DiVerdi

Systems and techniques for performing a scan-free reading of a structured identifier are provided. One technique involves obtaining a first set of images of an object within a scanning volume of an environment. The object is passed through the scanning volume without an explicit presentation of the structured identifier to an optical scanner within the environment. For each image of a plurality of the first set of images, an indication of a first region of interest of the structured identifier on the object within the image is obtained, based in part on a second set of images of the object having a lower quality than the first set of images. The first region of interest of the structured identifier is extracted from a first image of the plurality of the first set of images. The structured identifier within the first region of interest within the first image is decoded.

Scan-free barcode reading

High density, robotic warehouse systems and processes may include one or more blocks of a storage system, each block including a plurality of floors, and each floor including a plurality of storage grid locations for respective totes. A plurality of first robotic drive units may transfer barges carrying totes between various processing stations and the storage system. A plurality of second robotic drive units may operate within the storage system and traverse the storage grid locations using a plurality of highway grids and elevators to move totes between barges and storage grid locations. The freely movable robotic drive units, barges, and totes enable high flexibility, modularity, scalability, and serviceability of the high density, robotic warehouse systems.

High density, robotic warehouse system

Image data from a camera is used to identify one or more items in a dynamic field of view for item identification and tracking. The camera focus setting may be adjusted to different depth of field based on estimated distances to the items within the image data. After adjusting the focus setting, additional image data may be collected to capture a sharper image of the item and ensure sufficient clarity for item recognition based on item identifiers visible on the items within the image data.

High speed continuously adaptive focus and deblur

Features are disclosed for an overpackage that can contain an object and provide for automated identification and handling of the object by a robotic retrieval system. The automated identification and handling are enabled through self-identifying marks on the overpackage that indicate the identity of the overpackage as well as the relative location of the mark on the overpackage. Using the location information, a robot or other autonomous actor of the robotic retrieval system can identify a path to a pick point and detect whether the proper pick point is engaged through additional identifiers on the overpackage or a pick point.

Self-identifying overpackage for robotic retrieval

Techniques are described for processing digital video data using one or more machine learning models to determine an outcome of an item placement operation within a fulfillment center environment. Video data is processed using one or more machine learning models to determine an estimated likelihood that an occurrence of a particular fulfillment center operation is depicted within the two or more instances of digital video data. Upon determining that the estimated likelihood exceeds a predefined threshold confidence level, the video data is processed using second one or more machine learning models to determine a bin placement prediction and a confidence value. A data repository for a control system for the fulfillment center environment is updated, based on the bin placement prediction and the confidence value.

Computer vision and machine learning techniques for item tracking

A modular sorting station includes a frame defining an inbound bay and an outbound bay, each of the bays being sized to receive an inventory holder containing inventory. A robotic grasper is mounted to the frame and positioned above one of the inbound and outbound bays and operable to transfer inventory items from the inbound bay to the outbound bay, and a sensor mounted to one of the frame or robotic grasper and operable to identify inventory at the inbound bay when the inventory holder is present in the inbound bay. The frame is sized and arranged to align with a material handling grid and permit drive units to transport inventory holders into and out of the inbound bay and/or outbound bays while moving along the material handling grid; and the frame is portable such that the modular sorting station can be moved as a modular unit for deployment.

Modular automated inventory sorting and retrieving

Features are disclosed for an end effector for automated identification and handling of an object. The end effector includes an end effector that can be positioned over a pick point of an overpackage in which a desired object is location using sensors. Using the location information, the end effector can identify a path to the pick point and detect whether the pick point is engaged by detecting environmental changes at the end effector.

End effector for autonomous object retrieval

A technology is provided for robot implemented item manipulation. In one example, a method includes analyzing one or more items including a target item for manipulation, using machine vision rules, to identify the target item. When a determination is made that the robot is unable to perform the manipulation, a request may be transmitted requesting human assistance. An electronic response may be received in response to the request which includes an instruction for manipulating the target item. The robot may manipulate the target item using the instruction.

Robot implemented item manipulation

A modular sorting station includes a frame defining an inbound bay and an outbound bay, each of the inbound and outbound bays being sized to receive an inventory holder containing inventory thereon. A robotic grasper is mounted to the frame and positioned above one of the inbound and outbound bays and operable to transfer inventory items from the inbound bay to the outbound bay, and a sensor mounted to one of the frame or robotic grasper and operable to identify inventory at the inbound bay when the inventory holder is present in the inbound bay. The frame is sized and arranged to align with a material handling grid and permit drive units to transport inventory holders into and out of the inbound bay and/or outbound bays while moving along the material handling grid; and the frame is portable such that the modular sorting station can be moved as a modular unit for rapid deployment.

Growing community of inventors

Groton, MA, United States of America

Timothy Stallman