A controller that controls a robot that performs grinding on a workpiece includes a machine learning device that learns grinding conditions for performing the grinding. The machine learning device observes, as state variables expressing a current state of an environment, a feature of a surface state of the workpiece after the grinding and the grinding conditions, acquires determination data indicating an evaluation result of the surface state of the workpiece after the grinding, and learns the feature of the surface state of the workpiece after the grinding and the grinding conditions in association with each other using the observed state variables and the acquired determination data.

A method includes: accessing a virtual model defining a geometry of a workpiece; navigating an optical sensor about the workpiece; accessing an image of the workpiece; detecting a marker, on the workpiece, depicted in the image; defining a first workpiece region of the workpiece bounded by the marker; defining a toolpath within the first workpiece region based on a geometry of the first workpiece region represented in the virtual model; assigning a first target force to the first toolpath; and during a processing cycle accessing a first sequence of force values output by a force sensor coupled to the sanding head, navigating the sanding head across the first workpiece region according to the first toolpath, and based on the first sequence of force values, deviating the sanding head from the first toolpath to maintain forces of the sanding head on the workpiece proximal the first target force.

A method of acquiring sensor data on a construction site by at least one sensor of a construction robot system comprising at least one construction robot is provided, wherein a sensor is controlled using a trainable agent, thus improving the quality of acquired sensor data. A construction robot system, a computer program product, and a training method are also provided.

A combined electric tool coordination system includes a main tool (4) and an auxiliary tool (1). The main tool (4) and the auxiliary tool (1) coordinate for working. A load detection module (E1) is used to detect a load parameter that is generated when the main tool (4) operates, and send the load parameter to a central control module (E2). The central control module (E2) adjusts output power of the auxiliary tool (1). The central control module (E2) controls power of the auxiliary tool (1) to increase as the load parameter of the main tool (4) increases and decrease as the load parameter decreases. An automatic adjustment function of the auxiliary tool (1) is applied to a dust collector (1). When power of the main tool (4) increases, more dust and scraps are generated, suction of the dust collector (1) is automatically adjusted to be higher, and the demand of a large quantity of dust is satisfied; and when the power of the main tool (4) decreases, less dust and scraps are generated, power of the dust collector (1) automatically decreases, the suction is reduced, and the demand of a small quantity of dust is satisfied.

The invention relates to a method for controlling an automated orbital sander, in which method an electrically powered orbital sander is moved around automatically, at constant pressure, over the surface of an object, along at least one predefined sanding path so as to perform sanding, characterized in that the instantaneous power consumed by the sander along the sanding path is measured and in that the measurement thus taken is processed in order to deduce therefrom information regarding the level of abrasion along said path and/or to detect any sanding incident that has occurred along the latter.

The occurrence of grinding unevenness is prevented even when the movement speed of a robot is changed. Provided is a grinding robot system including: a motor-driven grinder that performs grinding; a robot that grinds a grinding target by means of the grinder in a state in which one of the grinder or the grinding target is attached to a distal end thereof and is moved, and the other is set at a fixed position; and a control unit that controls the robot and the grinder, wherein the control unit calculates a rotational-speed command value for the grinder that changes according to the movement speed of the distal end of the robot and controls the rotational speed of the grinder on the basis of the calculated rotational-speed command value.

A method for automated detection of defects in a workpiece surface and generation of a robot program for the machining of the workpiece is described. In accordance with one embodiment, the method comprises the localization of defects in a surface of a workpiece as well as determining a three-dimensional topography of the localized defects and categorizing at least one localized defect based on its topography. Dependent on the defect category of the at least one defect, a machining process is selected and, in accordance with the selected machining process, a robot program for the robot-assisted machining of the at least one defect is generated with the assistance of a computer.

The invention relates to a system and method for changing liners of a mill, the configuration of which allows the automated robotic manipulation of liners of mills for ore grinding in comminution processes. The configuration and operation of the system allows the task of manipulation to be improved, having a greater degree of freedom and/or flexibility in its movements, thereby providing a greater degree of certainty and efficiency to the method and thus optimising the time that the mill is halted for maintenance, and also preventing the risks to which maintenance staff may be exposed. The system comprises at least one support structure, at least one system for supplying and moving liners, at least one robotic manipulator system for manipulating the liners, at least one liner manipulation tool, at least one artificial vision system, and at least one control system.

A robot includes a robot arm, a force sensor, and a control unit configured to control the operation of the robot art. The control unit initializes the force sensor while the robot arm is moving at uniform speed. It is preferable that the control unit initializes the force sensor while the robot arm is moving at the uniform speed and the amplitude of a detection value of the force sensor is smaller than a threshold.

A robot-supported grinding method is described. In accordance with one example of the invention, the grinding method includes contacting a surface of a workpiece with a rotating grinding tool, whereby either the grinding tool or the workpiece is mechanically coupled to the tool center point (TCP) of a manipulator. The method further includes controlling an actuator that influences the grinding tool or the workpiece to produce a grinding force between the grinding tool and the workpiece, as well as measuring an actual deflection of the actuator. The rotational velocity of the grinding tool is adjusted depending on the measured actual deflection of the actuator and a reference deflection of the actuator.