Abb Schweiz Ag

Abb Research Ltd.

Other

Georgetown Rail Equipment Company

Scalable Robotics Inc.

Questar Inc.

Carlos Martinez

Thomas A Fuhlbrigge

Gregory F Rossano

Jianjun Wang

Biao Zhang

Remus Boca

Carlos Winsor Morato

Sangeun Choi

William John Eakins

Sang Joon Choi

Heping Chen

Jinmiao Huang

Charles Wayne Aaron

Daniel T Lasko

Harald Staab

Will J Eakins

Jan Nyqvist

Steven West

Thomas Andrew Fuhlbrigge

Gregory A Cole

George Q Zhang

Xiongzi Li

Joel Scott Howard

Charles R Figueroa

David Rozacky

William C Shell

H Lynn Turner

Jorge Vazquez

George Zhang

Harald Josef Staab

Wanli Jiang

Johnny Holmberg

Arnold Bell

Maciej Orman

Jeremy Newkirk

Soenke Kock

Jordi Artigas

Jianmin He

Magnus Wahlström

Brian Roger VanVoorst

John Shackleton

Brian R Van Voorst

Zhou Teng

Eduardo Botelho

Carlos W Morato

John Joseph Shackleton, Jr

Jonathan Paul Schewe

Nathan Bachman

Harald Josef Stabb

Jacek Plesnar

Sang Choi

Brian Roger Vanvoorst

John Joseph Shackleton

Harald Joseph Stabb

A system that uses 3D scanning, movable devices, and pose selecting means, either in or outside the robot workspace, in order to create a robot program.

Robot teaching with scans in and out of robot workspace

A system that uses 3D scanning and a process agnostic pointing device that is used in conjunction with user input to create a robot program.

Process agnostic robot teaching using 3D scans

A system that uses 3D scanning, a process agnostic pointing device used in conjunction with user input, and geometric analysis of the 3D information to create a robot program.

Robot teaching with scans and geometries

Systems and methods for automatic restocking different items in retail store environments having POS locations for the items are disclosed. The method includes, for a first item of the different items, storing at least one first item parameter uniquely identifying the first item. The method includes determining, based on the at least one first item parameter, a first autonomous movement control scheme for manipulation of the first item by a robotic arm. The method includes executing, by the robotic arm, the first control scheme, the executing including shelving the first item on the shelf. The method includes evaluating, by a processor or a user of the robotic arm, the executing for the first item according to at least one predetermined first performance criteria. The method includes determining and storing, based on the evaluating, an updated first control scheme for subsequent executing by the robotic arm for the first item.

Robotic manipulation intelligence systems and methods for automatic restocking of items in retail store environments

For training an object picking robot with real and simulated grasp performance data, grasp locations on an object are assigned based on object physical properties. A simulation experiment for robot grasping is performed using a first set of assigned locations. Based on simulation data from the simulation, a simulated object grasp quality of the robot is evaluated for each of the assigned locations. A first set of candidate grasp locations on the object is determined based on data representative of simulated grasp quality from the evaluation. Based on sensor data from an actual experiment for the robot grasping using each of the candidate grasp locations, an actual object grasp quality is evaluated for each of the candidate locations.

Hybrid machine learning-based systems and methods for training an object picking robot with real and simulated performance data

A robot is configured to perform a task on an object using a method for generating a 3D model sufficient to determine a collision free path and identify the object in an industrial scene. The method includes determining a predefined collision free path and scanning an industrial scene around the robot. Stored images of the industrial scene are retrieved from a memory and analyzed to construct a new 3D model. After an object is detected in the new 3D model, the robot can further scan the image in the industrial scene while moving along a collision free path until the object is identified at a predefined certainty level. The robot can then perform a robot task on the object.

Method and system to generate a 3D model for a robot scene

A grasping system includes a robotic arm having a gripper. A fixed sensor monitors a grasp area and an onboard sensor moves with the gripper also monitors the area. A controller receives information indicative of a position of an object to be grasped and operates the robotic arm to bring the gripper into a grasp position adjacent the object based on information provided by the fixed sensor. The controller is also programmed to operate the gripper to grasp the object in response to information provided by the first onboard sensor.

Object grasp system and method

Methods, systems, and software for controlling object picking and placement by a robot system are disclosed. The method includes assigning machine learning training data of a machine learning model for an object. The machine learning training data includes a plurality of known grasp location labels assigned to the object positioned in a plurality of different object poses. The method includes providing the object in a work space of the robot system. For the object in the work space in a first pose of the plurality of different object poses, the method includes: mapping a first candidate grasp location on the object; executing robotic movements for the first candidate grasp location on the object; and evaluating a result of the executing for the first candidate grasp location according to at least one predetermined performance criteria.

Machine learning-based systems and methods for controlling robotic object picking and placement in training and run time environments

A product manipulation tool for interacting with products and containers at, for example, a retail facility can include a securing mechanism to secure an exposed portion of the container with respect to a horizontal surface such as a shelf. The product manipulation tool can also include a stabilizing device to stabilize the container with respect to the horizontal surface prior to securing the container. The product manipulation tool can also include a support structure for insertion underneath the container to support the load. The stabilizing mechanism may lift or tilt the container prior to insertion of the support structure. In an example, the product manipulation tool may be disposed on a mobile unit configured for locomotion about the retail facility.

Product manipulation tool

A modular canopy structure is disclosed. The modular canopy structure may utilize component parts of industry standard scaffolding portions attached to a specifically designed bow beam (roof support portion). The bow beam mates with industry standard scaffolding portions that form a side wall of the canopy structure. Construction of the canopy structure (e.g., on-site assembly) is simplified over prior art temporary structures and the disclosed canopy structure provides strength and near 100% water resistance as well as other improvements based, in part, on sidewall sleeves, overlapping techniques, material usage, and other design considerations. In some cases, the disclosed canopy structure may be suitable for onsite construction projects (including welding), temporary housing in a disaster, or as a suitable temporary to semi-permanent structure for outdoor events (e.g., wedding, party, temporary building). The disclosed modular canopy structure provides for functional windows and doors not available in prior art implementations.

Modular canopy structure

Unique systems, methods, techniques and apparatuses of a robot training system are disclosed. One exemplary embodiment is an industrial robot training system comprising a mixed reality display device structured to superimpose a virtual scene on a real-world view of a real-world scene including a plurality of physical objects including an industrial robot, a video input device, and a computing device. The computing device is structured to detect physical objects using video output from the video input device, generate virtual objects using the detected physical objects, simulate a virtual robot path, determine one movement of the series of robot movements causes a collision, adjust the virtual robot path so as to avoid the collision between the two virtual objects of the plurality of virtual objects, and program the industrial robot to perform a real robot path using the adjusted virtual robot path.

Industrial robot training using mixed reality

A teleoperated robotic system that utilizes a graphical user interface (GUI) to perform work on a workpiece(s) using a robot. A coordinate system of the GUI is correlated to the tool center point (TCP) of the robot and the TCP or workspace of a teleoperated member, such as a haptic joystick. Operable manipulation of the teleoperated member is correlated to a movement at a particular location in the robot station, such as movement of the TCP of the robot. The GUI can also provide digital representations of the workpiece, which is based on inputted and/or scanned information relating to a reference workpiece and/or the particular workpiece on which the robot is performing work. The GUI can further provide indications of the various stages of assembly of the workpiece, as well as an indication of work already, or to be, performed on the workpiece.

User interface for a teleoperated robot

In one embodiment, the present disclosure provides a robot automated mining method. In one embodiment, a method includes a robot positioning a charging component for entry into a drill hole. In one embodiment, a method includes a robot moving a charging component within a drill hole. In one embodiment, a method includes a robot filling a drill hole with explosive material. In one embodiment, a method includes operating a robot within a mining environment.

Robot automated mining

Growing community of inventors

South Windsor, CT, United States of America

Carlos Martinez