Abstract:
Automatic scanning and representing an environment with collision avoidance includes, for example, obtaining a first representation of the environment using a first scanning path, determining a second scanning path based on the first representation of the environment operable to avoid contact with the environment when obtaining a second representation of the environment, obtaining the second representation of the environment based on the second scanning path, and wherein the second representation of the environment is different from the first representation of the environment. The method may be employed in imaging and/or representing a rock wall having a plurality of spaced-apart holes for receiving charges for mining.
Abstract:
A method for robotic adaptive production includes modifying program instructions online while performing production activities in response to detecting a change in the production environment. A robotic adaptive production method includes modifying program instructions online while performing production activities to minimize a production task cycle time or improve a production task quality. A robotic adaptive production method includes estimating a relationship between a control parameter and a sensor input; and modifying the control parameter online to achieve an updated parameter based on the estimating. A robotic adaptive production method includes receiving sensor input relating to robotic performance during the performance of production tasks and online optimizing a process parameter based on robotic performance during the performance of the production tasks. A robotic adaptive production method includes determining the position and/or orientation of a feature based on a learned position and/or orientation of another feature and on a geometric relationship.
Abstract:
A robotic 3D printing system has a six degree of freedom (DOF) robot that holds the platform on which the 3D part is built on. The system uses the dexterity of the 6 DOF robot to move and rotate the platform relative to the 3D printing head, which deposits the material on the platform. The system allows the part build in 3D directly with a simple printing head and depositing the material along the gravity direction. The 3D printing head can be fixed relative to robot base, or moved in the X-Y plane with 2 or 3 DOF, or held by another robot or robots. The robot movement can be calibrated to improve the accuracy and efficiency for high precision 3D part printing.
Abstract:
Robot positioning is facilitated by obtaining, for each time of a first sampling schedule, a respective indication of a pose of a camera system of a robot relative to a reference coordinate frame, the respective indication of the pose of the camera system being based on a comparison of multiple three-dimensional images of a scene of an environment, the obtaining providing a plurality of indications of poses of the camera system; obtaining, for each time of a second sampling schedule, a respective indication of a pose of the robot, the obtaining providing a plurality of indications of poses of the robot; and determining, using the plurality of indications of poses of the camera system and the plurality of indications of poses of the robot, an indication of the reference coordinate frame and an indication of a reference point of the camera system relative to pose of the robot.
Abstract:
A machine that has at least one actuated mechanism is remotely located from a control station. A two way real-time communication link connects the machine location with the control station. An interface at the control station allows an operator to select one or more virtual constraints on operation of the machine when the machine is performing a predetermined function. The virtual constraints are transmitted over the two way real-time communication link to the machine location. The machine has predetermined safety limits that are stored in a controlling device at the machine location. The stored predetermined safety limits are extracted and automatically mapped to the control station using the two way real-time communication link. The controlling device maps the predetermined safety limits to the virtual constraints.
Abstract:
Three-dimensional visual servoing for positioning a robot in an environment is facilitated. Three-dimensional point cloud data of a scene of the environment is obtained, the scene including a feature. The three-dimensional point cloud data is converted into a two-dimensional image, and a three-dimensional position of the feature is identified based on the two-dimensional image. An indication of the identified three-dimensional position of the feature is then provided.
Abstract:
A machine that has at least one actuated mechanism is remotely located from a control station. A two way real-time communication link connects the machine location with the control station. An interface at the control station allows an operator to select one or more virtual constraints on operation of the machine when the machine is performing a predetermined function. The virtual constraints are transmitted over the two way real-time communication link to the machine location. The machine has predetermined safety limits that are stored in a controlling device at the machine location. The stored predetermined safety limits are extracted and automatically mapped to the control station using the two way real-time communication link. The controlling device maps the predetermined safety limits to the virtual constraints.
Abstract:
A teleoperated robot system has a watchdog to determine if the rate of data transmission from a computing device such as a robot controller located in the station used by the operator of the teleoperated robot to the remotely located industrial robot has fallen below a minimum data rate or the time for transmission of data has exceeded a maximum time. Upon the occurrence of either or both of the foregoing, one or more types of corrective action are undertaken to bring the teleoperated robot and the processes performed by the robot.
Abstract:
Three-dimensional visual servoing for positioning a robot in an environment is facilitated. Three-dimensional point cloud data of a scene of the environment is obtained, the scene including a feature. The three-dimensional point cloud data is converted into a two-dimensional image, and a three-dimensional position of the feature is identified based on the two-dimensional image. An indication of the identified three-dimensional position of the feature is then provided.
Abstract:
A machine remotely located from a control station has at least one actuated mechanism. A two way real-time communication link connects the machine location with the control station. A controller at the machine location has program code that includes an instruction which when executed transfers control of the machine from the controller to the control station. The program code can have a task frame associated with the predetermined function performed by the machine with the task frame divided into a first set controlled by the controller and a second set controlled from the control station. The system can also have two or more remotely located control stations only one of which can control the machine at a given time.