Amazon Technologies, Inc.

Zebra Technologies Corporation

Fetch Robotics, Inc.

Russell Toris

Sarah Elliott

Andrew Stubbs

Melonee Wise

Andrew Dominic Marchese

John Gregory Longtine

Derek King

Brian Cairl

Sarath Krishnaswamy

Moses Theodore Ort

Jacob Taylor Wachlin

John W Stewart, Iii

Eric Diehr

Levon Avagyan

Niharika Arora

Rohan Bhargava

David G Kent

Alex Henning

A system includes: a mobile robot comprising a sensor, the robot further comprising a computer, the robot operating in an environment; a server operably connected to the robot via a communication system, the server configured to manage the robot; a controller operably connected to the robot, the controller operably connected to the server, the controller configured to control the robot; and an object of interest marked with a marker at one or more of an approximate height and an approximate field of view of the sensor, the sensor generating data describing the object of interest, the computer configured to identify one or more of the object of interest and the location using one or more of a shape of the object of interest and an intensity of data describing the object of interest.

System and method for semantically identifying one or more of an object and a location in a robotic environment

A system includes: a cart including: four legs; at least one shelf, each shelf attached to each of the legs; the cart having a generally rectangular shape, a width of the cart being longer than a length of the robot, a length of the cart being longer than a length of the robot; four wheels, each wheel attached to a different leg at a bottom of the leg, the wheels configured to roll to facilitate movement of the cart; and a robotic dock, the robotic dock comprising four docking receptacles at ninety degree angles from adjacent docking receptacles; and a robot comprising: a sensor; and a docking module, the docking module comprising retractable docking pins, each retractable docking pin configured, when extended upward, to mate with a corresponding docking receptacle, thereby securing the robot to a bottom shelf of the cart.

Robotic cart configured for effective navigation and multi-orientation docking

A method for selecting a preferred robotic grasp of an object-of-interest using pairwise ranking includes: identifying a robotic candidate grasp usable to grasp the object-of-interest, the object-of-interest situated in an environment; receiving a grasp preference for a preferred candidate grasp of the object-of-interest; calculating a heuristic to describe a relationship of the candidate grasp to one or more of the object-of-interest and the environment; and using the heuristic and using the grasp preference, computing a pairwise ranking of two candidate grasps to determine an ordering of the at least two candidate grasps.

Method and system for selecting a preferred robotic grasp of an object-of-interest using pairwise ranking

A cart-based workflow system includes: a robot operating in a facility; a server, the server operably connected to the robot, the server configured to do one or more of send the robot a cart transfer location usable for transferring the cart and instruct the robot to specify the cart transfer location; a graphic user interface (GUI) comprising a map of the facility, the GUI operably connected to the server, the GUI configured to do one or more of receive input from a human user and provide output to the human user, the GUI further configured to be usable by the user to coordinate movement of one or more of robots and carts.

System and method for robot-assisted, cart-based workflows

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

A grasp management system and corresponding methods are described. In some examples, information about a grasp by which an end of arm tool of a robotic manipulator successfully grasped an item is accessed. The grasp may be associated with contact points on the item. Other contact points may be simulated based on the contact points in order to define a grasping surface that includes at least a portion of the other contact points. Information about the grasping surface may be accessed to determine a primitive shape that represents a feature of the item. The primitive shape may be used determine other features on the item or other features on other items that may also be graspable by the end of arm tool or other end of arm tools.

A grasp management system and corresponding methods are described. In some examples, information about a grasp by which an end of arm tool of a robotic manipulator successfully grasped an item is accessed. The grasp may be associated with contact points on the item. Other contact points may be simulated based on the contact points in order to define a set of grasping surfaces that include at least a portion of the other contact points. Information about the grasping surfaces may be accessed to determine a primitive shape that represents a feature of the item. The primitive shape may be used determine other features on the item or other features on other items that may also be graspable by the end of arm tool or other end of arm tools.

A grasp management system and corresponding method are described. In some examples, it is determined whether an end of arm tool of a robotic manipulator is capable of grasping an item in a first orientation and a second orientation. Information regarding success of the attempts may be retained in a database. A richness measure for each of the first orientation and the second orientation may be determined based upon a spatial variation of successful attempted grasps in the respective orientation.

Growing community of inventors

San Jose, CA, United States of America

Russell Toris