A method for recognizing a deburring trajectory, relevant to be performed by a controller or a computer, includes the steps of: according to a process flow of a workpiece, analyzing a CAD file of the workpiece, determining a burr processing area and obtaining a mathematical model of boundary contour curve; applying a linear contour sensor to scan the workpiece to obtain contour section information of the workpiece; performing curve fitting upon the contour section information of the workpiece and the mathematical model of boundary contour curve so as to obtain a boundary curve function; and, utilizing the boundary curve function to determine deburring position information of the workpiece and to further generate a processing path. In addition, a system for recognizing a deburring trajectory is also provided.

A processing control device controls a tool for processing a first workpiece. The processing control device includes a driving unit to drive the tool, an output unit, and a control unit to control the driving unit and the output unit. Processing information obtained by performing preliminary processing on a second workpiece before performing first processing on the first workpiece is transmitted by the control unit to the output unit and accordingly the processing information is outputted from the output unit. The control unit generates a control command for performing second processing that is performed on the first workpiece after the first processing. The control unit controls the driving unit according to the control command.

A robotic deburring process that automatically, accurately, and efficiently removes burrs from a workpiece. The robotic deburring process uses CAM location data to establish deburring trajectory, physics based machining models to predict burr type and size, and force control functions to compensate inaccuracies due of inaccuracies of robots arms.

A machine learning apparatus includes a first information acquiring unit that acquires first information including at least one of a shape of a workpiece, a material of the workpiece, a cutting path of a cutting process, a type of a tool, and an amount of wear of the tool; a second information acquiring unit that acquires second information correlated with an evaluation of a burr occurring on the workpiece due to the cutting process; and a learning unit that executes learning processing using a plurality of pieces of the first information and a plurality of pieces of the second information, and generates a learning model that outputs a cutting condition, according to another piece of first information that is different from the plurality of pieces of first information.

A process of deburring a workpiece comprising installing a workpiece onto a machine table proximate a robot, the workpiece having a surface, the robot having at least one force sensor and a spindle load sensor associated with a spindle coupled to a cutting tool, the robot having at least one joint configured to be actuated by a joint actuator; the robot being coupled to a controller; generating joint encoder signals with the controller, the joint encoder signals configured to direct the joint actuator; sensing contact forces between the cutting tool of the robot and the surface of the workpiece; determining a deburring path of the cutting tool to deburr the workpiece; and controlling the robotic deburring process by use of the joint encoder signals, a physics based model of burr size and material removal, a nominal trajectory and an actual trajectory of the cutting tool center point position.

A robotic deburring process that automatically, accurately, and efficiently removes burrs from a workpiece. The robotic deburring process uses CAM location data to establish deburring trajectory, physics based machining models to predict burr type and size, and force control functions to compensate inaccuracies due of inaccuracies of robots arms.

A deburring apparatus including: a robot that uses a deburring tool to deburr an object supported by a support in a machine tool, a visual sensor, a relative movement mechanism for causing relative movement between the visual sensor and the object supported by the support; and a controller, wherein the controller is configured to conduct: an operation process that operates the relative movement mechanism based on a visual sensor relative movement program for controlling an operation of the relative movement mechanism so that a ridge of the object supported by the support is detected by the visual sensor during the relative movement; and a deburring operation program generation process which generates a deburring operation program by using the detected ridge obtained by the visual sensor when the relative movement mechanism is operated based on the visual sensor relative movement program.

A controller includes a machine learning device for learning machining conditions when deburring is performed by controlling the robot. The machine learning device observes workpiece information indicating a shape or material of a workpiece, burr information indicating a shape or position of a burr, and machining conditions including tool information indicating a type of a tool, a feed rate of the tool and a rotational speed of the tool, as a state variable representing a current state of an environment, and acquires determination data indicating an evaluation result of the deburring. Then, using the observed state variable and the acquired determination data, the machine learning device performs learning by associating the machining conditions with the workpiece information and the burr information.

A method for deburring a gear blank includes correcting chamfer sizes, chamfer shapes and chamfer symmetry at tooth edges which were produced with a deburring cutter with a strongly asymmetric tooth shape (ChamferCut). The chamfers are semi-automatically corrected by coupling the movement of several axes of a gear cutting machine, including a workpiece axis of rotation C.sub.1, spatial shifting axes of a machine column Z.sub.1, X.sub.1, and Y.sub.1, and a V.sub.1-axis corresponding to the tool axis. The method further includes specifying a correction in the axial direction in one of the axes Z.sub.1, V.sub.1 and C.sub.1, and calculating the correction amount of further axes by the controller depending on the specified axis.

A robot control device is configured to perform, during movement of an end effector of a robot in a movement direction of a target object, force control by which a force acts on the target object based on an output of a force detection unit included in the robot to cause the robot to perform work on the target object by the end effector. Whether the work is able to be started is determined in a process where the end effector follows the movement of the target object, and when it is determined that the work is able to be started, the work is caused to start.