A control apparatus that generates a control signal for controlling a robot arm that performs a process on an object, a first imaging apparatus that outputs first image data, and a second imaging apparatus that outputs second image data are mounted. The control apparatus: generates first information indicating a position and a pose of the object by using the first image data generated by the first imaging apparatus; generates second information indicating a position and a pose of the object by using three-dimensional position data, which is generated from the second image data generated by the second imaging apparatus imaging the object and which indicates a three-dimensional position of each of a plurality of points of the object, and three-dimensional model data of the object having a position and a pose that are determined based on the first information; and generates the control signal based on the second information.

A robot arrangement includes at least a movable robot arm arrangement configured to move within a workspace defining a 3D motion range; a sensor arrangement installed on the robot arm arrangement comprising at least a first sensor device providing at least a first field of view; wherein the sensor arrangement is configured to be moved in such a way that the at least first field of view of the sensor arrangement covers at least a first portion of the workspace defining a first region of movement of the robot arm arrangement.

A machine learning method for learning an action of a robot including a hand to pick out a workpiece from a container containing a plurality of the workpieces stacked in bulk and install the workpiece such that the workpiece is in a predetermined installation state includes learning a reverse-order action of removing, by the hand, the workpiece in the predetermined installation state after completion of installation, and learning an installation order of the workpiece based on a learning result of the reverse-order action of removing the workpiece.