Amazon Technologies, Inc.

Andrew Stubbs

Matthew David Verminski

Ennio Claretti

John Gregory Longtine

Robert Michael Shydo, Jr

Andrew Dominic Marchese

Parris S Wellman

Brett Allen Skaloud

Nicolas Kurczewski

Peter K Mansfield

Nicolas Guillaume Hostein

Boris Aronchik

Peter R Wurman

Russell Toris

Stephen Caldara

Sarath Krishnaswamy

Moses Theodore Ort

Aaron Joseph Parness

Jacob Taylor Wachlin

Diane Grieselhuber Mills

Emily Dunne

Barry James O'Brien

James Christopher Curlander

Michael T Barbehenn

Jonathan Evan Cohn

Robert Alexander Colburn

Patrick R Dingle

Timothy Aaron Bragg

William James Watt

Samuel Rubin Barrett

Andrew Brenden Tinka

Oliver Christoph Purwin

Parker Owan

Sean Hugh Breheny

Sisir Babu Karumanchi

Don Frank Ruffatto

Rahul Balakrishna Warrier

Joshua Rosenberg Hooks

John P Dugan

Jeongseok Lee

Christopher C Jones

Sean Michael Scott

Gregory Edward Tierney

Scott M Waters

Robert Brian Curtis

Baoyuan Liu

Gregory Katz

Benjamin Bedard

Kristina Lisa Klinkner

Emanuel Moshouris

Kyle Michael Washabaugh

Ying Xu

Andres Camilo Cortes Lopez

Curt Salisbury

Peter Johnson

Suvesha Chandrasekaran

Rachel Lynn Muhlbauer

Nikhil Bole

Mike Hector

Andres Camilo Cortes

James Schmidt

Siyu Dai

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

Item consolidation tools are described. In one example, an item consolidator includes first and second bay doors, a door displacement system, and a controller. The door displacement system includes first and second drive systems secured to the undersides of the first and second bay doors. The drive systems provide angular and a lateral degrees of freedom, to move the first and second bay doors. The controller is configured to direct the door displacement system to form a bay door vertex between leading edges of the bay doors. Items can be placed on the doors and will rest at the vertex between the doors. The controller can also determine drop locations for the items. The controller can then direct the door displacement system to reposition the bay door vertex based on the drop locations and drop the items by opening or retracting the doors.

Item consolidator

Tray flipper automation tools are described. In one example, a tray flipper includes a flip arm positioned along a conveyor, a tamper arm, a drive system, and a controller. The controller is configured to detect alignment of a tray on the conveyor with the flip arm, direct the drive system to rotate the tamper arm to a position over the tray, and actuate a tamper plate of the tamper arm to secure contents in the tray. The controller is also configured to rotate the tamper arm and the flip arm, with the tray secured between them, to an inverted position off of the conveyor. Items positioned within the tray can be flipped over when the tamper arm and the flip arm rotate away from the conveyor. The flip arm and tray can then be rotated back, leaving the items resting on the tamper plate for inspection and materials handling steps.

Tray flipper

Techniques and apparatus describe a robotic workcell for performing a robotic stowing operation. The robotic workcell includes a mechanism system, which includes a first robotic gantry, a second robotic gantry, and a controller. The first robotic gantry includes a first mount and a robotic end effector(s) attached to the first mount. The second robotic gantry includes a second mount and at least one end effector attached to the second mount. The controller controls movement of the first mount, the second mount, and the robotic end effector(s), based in part on an analysis of an environment with one or more perception sensors.

Robotic workcell for interacting with goods to person systems

A skid-steer delivery autonomous ground vehicle has a drive train and suspension that aids in maneuverability. The AGV has six wheels, each of which is powered by its own motor. The AGV has features that diminish the dragging effect on the wheels, either by choice of wheel features or by taking weight off the front wheels during turning.

Autonomous ground vehicle

Embodiments herein describe a pick or stow system that uses a mechanical system to stow an item into a container, retrieve an item from the container, or both. In one embodiment, the mechanical system includes a gantry or a robotic arm that permits various sensors, tools, or end effectors to interact with a plurality of containers. For example, the plurality of containers may be supported by a rack where each container may have any number of types of items. The gantry or robotic arm can move the sensors, tools, or end effectors to a particular container to either stow an item into the container or pick an item from the container.

Interacting with and inspecting of movable inventory systems

A chassis and skin of a delivery Autonomous Ground Vehicle include discrete upper and lower thermal management systems. The lower thermal management system is indirect, as is moves air through a closed duct that is in contact with high-heat dissipating components via heat sinks. The upper thermal management system is direct, as it moves air into the interior cavity of the AGV to cool sensors and other electronic equipment.

Thermal management for a delivery autonomous ground vehicle

Systems, methods, and computer-readable media are disclosed for robotic picking assemblies configured to grasp multiple items. In one embodiment, an example system may include a picking assembly coupled to a vacuum system, the picking assembly having a first suction cup assembly with a first suction cup and a first sensor, and a second suction cup assembly with a second suction cup and a second sensor. The example system may include a controller configured to cause the picking assembly to grasp a plurality of items, where the plurality of items includes a first item and a second item. The controller may be further configured to cause the picking assembly to move from a first position to a second position, and cause the picking assembly to release the first item at a first time and the second item at a second time.

Robotic picking assemblies configured to grasp multiple items

Drive train and suspension for an autonomous ground vehicle

Energy absorbing means on an autonomous ground robot, which is intended for delivering packages in an uncontrolled and unprotected environment, include elastically deformable padding, crushable material, and spring-loaded or like mechanical devices.

Energy absorbing means for an autonomous ground vehicle

A delivery AGV has a hybrid braking system. An emergency electrical brake shorts between motor contacts to stop the AGV quickly, but it doesn't work well to keep the AGV stopped, such as when on a hill. A mechanical parking brake is electrically actuated to lock the wheels. Both systems can be used at once for stopping the AGV.

Braking systems for an autonomous ground vehicle

Delivery autonomous ground vehicle

Techniques for controlling mobile drive units (e.g., robots) in proximity to humans in a physical area are described. A management device may send an activity message to the mobile drive units instructing the mobile drive units to perform a set of activities. If a human is detected in the physical area, the management device or another mobile drive unit may send an activity command instructing a mobile drive unit to stop, reduce the speed at which it is traveling, to change its path of travel, or to continue performing its set of activities. If the mobile drive units do not receive the activity command, the mobile drive units may stop performing the set of activities. After the management device determines that the human has left the physical area, the management device may resume sending the activity message.

Safety compliance for mobile drive units

A chassis and skin of a delivery Autonomous Ground Vehicle include an aluminum structure and polymer panels affixed to the AGV by fasteners. The panels are mutually overlapping. A method of assembly includes hooks and clips to put and hold the panels in place during assembly.

Chassis assembly for autonomous ground vehicle

A grasp management system and corresponding methods are described. In some examples, information about a set of grasps of a robotic manipulator is accessed. The information is used by the robotic manipulator to attempt to grasp an item using the set of grasps associated with a first grasping orientation. An orientation of the robotic manipulator can be adjusted into a second grasping orientation and the robotic manipulator can attempt to grasp the item using the set of grasps associated with the second grasping orientation. Information about the attempts can be recorded and used to determine a richness measure that may represent a richness of the set of grasps for the item.

Feature identification and extrapolation for robotic item grasping

Growing community of inventors

Waltham, MA, United States of America

Andrew Stubbs