A robot controller making a robot execute tasks including several work units in a parallel manner for several workpieces, in accordance with several operation programs for individually commanding the work units. The robot controller includes an information collecting section collecting state information showing, in real time, a state of an environment of the robot; a program selecting section selecting a first executable program satisfying a task starting condition, from operation programs ready to be executed for workpieces, based on the state information; a processing section processing, for execution, the first executable program; and a program-completion judging section judging whether the processing section has completed a processing of the first executable program. The program selecting section selects, based on the state information, a second executable program satisfying the task starting condition, from the operation programs ready to be executed, so as to satisfy a judgment of the program-completion judging section.

A control method for a robot system includes setting a robot arm in a first attitude, performing work in a first region of an object while moving a tool relative to the object by a moving stage with the first attitude maintained, setting the robot arm in a second attitude, imaging the object using a camera and correcting a position of the tool by driving of the moving stage based on an imaging result with the second attitude maintained, and performing the work in a second region of the object while moving the tool relative to the object by the moving stage with the second attitude maintained.

A controller is provided for performing dynamic grasping of a target object using visual sensory inputs. The controller includes a robotic interface connected to a robotic arm including links connected by joints having actuators and encoders, and a gripper of the end-effector of the robotic arm configured to grasp the target object in response to robot control signals, and a vision sensor configured to continuously provide visual observations for tracking poses of the target object in a workspace and compute grasp poses, wherein the vision sensor is mounted on a distal end of the robotic arm adjacent to the gripper. The controller trains the Eye-on-Hand reinforcement learner policy, tracks the poses of the target object, and generates robot control signals to follow the target object while keeping it in the field of view of the vision sensor and grasp the target object in the workspace.

A robot control system, comprising: one or more robots configured to perform work on a material including a content; and circuitry configured to: cause the one or more robots to move at least one of a cutter and the material so that a cut is made in the material with the cutter; and cause the one or more robots to rotate the material so that the cut faces downward.

A methodology for estimating a pick pose for an arbitrarily sized robotic end effector. The end effector is modeled as a 2D shape with specified dimensions indicative of its footprint on an object being picked. A pick point is first estimated on an object mask of a selected object, produced by performing instance segmentation on one or more input images of a scene. A pick surface is determined utilizing neighboring points around the pick point in the object mask. A set of points in the object mask, which define an extent of the pick surface, are reprojected with respect to a normal of the pick surface, to create a planar representation of the pick surface. A yaw-oriented pick pose is computed based on alignment of a longer dimension of the end effector model with a longer dimension of the planar representation of the pick surface.

A control device of a robot includes a robot control section configured to control the robot so as to sequentially position the robot at a plurality of target positions, which are set based on shape data representing a shape of a workpiece, and cause the robot to execute a work along a work target portion on the workpiece, and cause the robot to continue the work beyond a final target position of the plurality of target positions after the robot reaches the final target position, the final target position being set to correspond to an end of the work target portion in the shape data.

This control device for a robot device comprises: an imaging control unit that changes exposure conditions of a two-dimensional camera; and a position information generation unit that generates three-dimensional position information of an object on the basis of a two-dimensional image captured by the two-dimensional camera. The control device further comprises a synthesis unit that synthesizes a plurality of pieces of three-dimensional position information. While the robot is operating, the imaging control unit captures two-dimensional images at predetermined intervals under predetermined exposure conditions. When the robot stops, the imaging control unit changes the exposure conditions and captures a plurality of two-dimensional images, and the synthesis unit synthesizes a plurality of pieces of three-dimensional position information.

A robot system including: a robot with one or more movable elements respectively rotatable about one or more rotation axes; a control device that controls the robot; and a visual sensor attached to any of the movable elements of the robot, where the control device uses any of the movable elements of the robot as a subject element, compares a position of a predetermined target in a first image at an arbitrary first orientation of the robot at which the target fixed at a predetermined position is disposed inside a field of view of the visual sensor, and the position of the predetermined target in a second image at a second orientation at which the subject element is rotated about a rotation axis of the subject element with respect to the first orientation, and determines that the visual sensor is attached to the subject element.

A method for training a neural network to derive, from a force and a moment exerted on an object when pressed on a plane in which an insertion for inserting the object is located, a movement vector to insert an object into an insertion. The method includes, for a plurality of positions in which the object or the part of the object held by the robot touches a plane in which the insertion is located, controlling the robot to move to the position, controlling the robot to press the object onto the plane, measuring the force and moment experienced by the object, scaling the pair of force and moment by a number randomly chosen between zero and a predetermined positive maximum number and labelling the scaled pair by a movement vector between the position and the insertion, and training the neural network using the labelled pairs of force and moment.

A parts fastening system using a cooperative robot that fastens a module part to a fastening target includes: a jig to load the module part at a predetermined position; a loading robot to grip the module part loaded on the jig, and to move and align the module part to a fastening area in which the module part is fastened to the fastening target; a fastening robot including a first camera, the fastening robot to fasten the module part to the fastening target; and a control device to control movements of the loading robot and the fastening robot.