Abstract: Robotic visualization systems and methods include running and analyzing perception algorithms and models for robotic visualization systems on multiple computing platforms to obtain a successful complete an object processing request.

Abstract: An unmanned rail vehicle for surveillance, inspection, and/or maintenance of an industrial site is provided. The rail vehicle includes at least two carry rollers adapted for engaging on an upper rail side of a rail, wherein the center of gravity of the rail vehicle is vertically below the upper rail side; and at least one support roller connected to the chassis and adapted for rolling against a lateral rail side of the rail to laterally displace the center of gravity of the rail vehicle with respect to the upper rail side.

Abstract: 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.

Abstract: Apparatus and method is disclosed for determining position of a robot relative to objects in a workspace which includes the use of a camera, scanner, or other suitable device in conjunction with object recognition. The camera, etc is used to receive information from which a point cloud can be developed about the scene that is viewed by the camera. The point cloud will be appreciated to be in a camera centric frame of reference. Information about a known datum is used and compared to the point cloud through object recognition. For example, a link from a robot could be the identified datum so that, when recognized, the coordinates of the point cloud can be converted to a robot centric frame of reference since the position of the datum would be known relative to the robot.

Abstract: Technologies for producing training data for identifying degradation of physical components include a system. The system includes circuitry configured to apply an accelerated degradation process to a physical component of an industrial plant. Additionally, the circuitry of the system is configured to obtain measurement data indicative of visual characteristics of the physical component at each of multiple phases of degradation, wherein the measurement data is usable to train a neural network to identify a phase of degradation of another physical component.

Abstract: 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.

Abstract: A dummy tool is used to teach a robot the path the robot will follow to perform work on a workpiece to eliminate the possibility of damaging an actual tool during the training. The dummy tool provides the robot programmer an indication of potential collisions between the tool and the workpiece and other objects in the work cell when path is being taught. The dummy tool can have a detachable input/output device with a graphic user interface (GUI) that can communicate wirelessly with the robot controller. The dummy tool can also have a moveable camera attached thereto to track the relationship of the tool to objects in the work area.

Abstract: 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.

Abstract: Robotic visualization systems and methods include running and analyzing perception algorithms and models for robotic visualization systems on multiple computing platforms to obtain a successful complete an object processing request.

Abstract: A robotic system is provided to automatically generate and evaluate visual data used for training neural networks. The robotic system includes a first robotic cell for generating a first visual data set and a second robotic cell for generating a second visual data set for comparison to the first visual data set.

Abstract: A robotic system is provided to analyze sensor output data to generate and update a prediction model associated with a virtual scene in the workspace associated with the object.

Abstract: A robotic system includes a robot having an associated workspace; a vision sensor constructed to obtain a 3D image of a robot scene including a workpiece located in the workspace; and a control system communicatively coupled to the vision sensor and to the robot. The control system is configured to execute program instructions to filter the image by segmenting the image into a first image portion containing substantially only a region of interest within the robot scene, and a second image portion containing the balance of the robot scene outside the region of interest; and by storing image data associated with the first image portion. The control system is operative to control movement of the robot to perform work, on the workpiece based on the image data associated with the first image portion.

Abstract: A calibration article is provided for calibrating a robot and 3D camera. The calibration article includes side surfaces that are angled inward toward a top surface. The robot and camera are calibrated by capturing positional data of the calibration article relative to the robot and the camera. The captured data is used to generate correlation data between the robot and the camera. The correlation data is used by the controller to align the robot with the camera during operational use of the robot and camera.

Abstract: 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.

Abstract: One exemplary embodiment is a method comprising generating robot control code from one or more files including part geometry parameters, material addition parameters, and robot system parameters. The robot control code includes instructions to control position and material output of an additive manufacturing tool adjustable over six degrees of freedom. The method includes simulating execution of the robot control code to generate a virtual part file including virtual part geometry parameters and material addition parameters, analyzing the virtual part geometry parameters and material addition parameters relative to the one or more files, and executing the robot control code with the controller to produce the part with robot system if the analyzing indicates that the virtual part satisfies one or more conditions.

Abstract: 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.

Abstract: An unmanned rail vehicle for surveillance, inspection, and/or maintenance of an industrial site is provided. The rail vehicle includes at least two carry rollers adapted for engaging on an upper rail side of a rail, wherein the center of gravity of the rail vehicle is vertically below the upper rail side; and at least one support roller connected to the chassis and adapted for rolling against a lateral rail side of the rail to laterally displace the center of gravity of the rail vehicle with respect to the upper rail side.

Abstract: A system for generating a path to be followed by a robot used to perform a process on a workpiece has a computing device that has program code for operating the robot and obtaining information related to the workpiece and a vision system that scans the workpiece to obtain images thereof that are provided to the computing device. The computing device processes the images to obtain geometric information about the workpiece that the computing device uses in combination with process related reference parameters stored in the computing device to generate program code for a path to be followed by the robot to perform the process on the workpiece. The computing device also includes code configured to verify for quality the generated program code for the path to be followed by the robot to perform the process on the workpiece.

Abstract: A system for generating instructions for operating a robot to perform work on a workpiece has a 3D model or models of a robot scene that provides robot scene data. The system also has data of one or both hands of a gesture made with the one or both hands and a computation device that has program code configured to process the robot scene data and the gesture data to generate an instruction to operate the robot.

Abstract: 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.