Robot control device

A robot control device for controlling a robot, the robot control device comprising:

• a machine learning model configured to receive an input of an item of situation information selected from among items of situation information, and output an output value that is one of a binary value, a continuous value, or a multidimensional vector value indicating success or failure or a degree of success of an operation of an operation control in a situation indicated by the item of situation information which has been received, the items of situation information being information about the robot or a first object, and the items of situation information including:
• (i) physical characteristics including a physical structure and a shape;
• and (ii) a present status of at least one of a position, a posture, or a temperature that is a temporally varying characteristic;
• an operation control selector configured to obtain the output value for at least one operation control by providing the machine learning model with the item of situation information, when the item of situation information is received, and identify, based on the output value, an operation control to be executed;
• and
• an operation control executor configured to execute the operation control which has been identified by the operation control selector,
• wherein:
• the operation control is a control routine for the robot to achieve an operation objective by the robot sensing the first object using a sensor with interaction with a second object;
• and
• the machine learning model is configured to output the output value for the at least one operation control when the item of situation information is provided, the at least one operation control:
• (i) not being a primitive motion determined by a single motion vector or a single target position;
• and (ii) being a series of primitive motions for achieving the operation objective using a result obtained from the sensor as feedback information.