A machine learning device and a machine learning method are provided. A controller, which serves as the machine learning device and the machine learning method, is provided to perform machine learning of algorithms for arranging a flexible wire-like workpiece to a predetermined state using an industrial robot. In an embodiment, the machine learning device includes: an acquisition unit that acquires, as state variables, a state of the workpiece before arrangement starts and a state of the workpiece during arrangement; and a learning unit that performs machine learning of an algorithm for arranging the workpiece based on the state variables acquired by the acquisition unit.

A method is provided for operating a robotic device having a kinematic chain of movable components. The method includes: detecting respective values at least one characteristic of a plurality of the movable components by sensors arranged on the kinematic chain or in the vicinity of the kinematic chain; ascertaining a maximum value based on the detected values; comparing the ascertained maximum value with a predefined first safety limit by a controller of the robotic device; and adjusting the at least one characteristic or a further characteristic of the kinematic chain when the ascertained maximum value has a predefined relationship with the first safety limit, in order to increase the operating safety of the robotic device.

A method for operating a robotic device with a kinematic chain of mobile components is provided. The kinematic chain includes a function-specific end-effector at one end. Sensor values are acquired by sensors of the robotic device arranged on the kinematic chain or in the environment of the kinematic chain. A force acting on the end-effector or another component of the kinematic chain, or a variable dependent thereupon, is determined in a prespecified manner based on the acquired sensor values. The force or variable determined is compared with a prespecified first safety limit value by a control mechanism of the robotic device. A characteristic of the kinematic chain or the function-specific end-effector is adapted if the force or variable determined is in a prespecified relationship to the first safety limit value in order to increase the operational safety of a robotic device and of people in the environment of the robotic device.

A control device for a mobile robot capable of stabilizing the posture of the mobile robot while in motion is provided. A control unit (26) for a mobile robot (1) includes a required total floor reaction force central point position calculating unit which calculates a required total floor reaction force central point position (Pzmp(1) to Pzmp(7)) as a position of a total floor reaction force central point by using, as a factor, a first total floor reaction force center reference position (SP(1) to SP(7)) which is defined on the basis of a current time's supporting region (Sd1 to Sd7), i.e. a smallest convex region including ground contact surfaces of current time's supporting limbs, and a next time's supporting region (Sd2 to Sd8), i.e. a smallest convex region including ground contact surfaces of next time's supporting limbs.