Robot control device
AssigneeDaily Color Inc.
InventorYasunori KAMIYA
Life of this patent
Estimating the term…
Abstract
A robot control device that controls a robot and includes: a machine learning (ML) model that is used to describe ranges of environments, or in other words, situations in each of which control for a control routine (operation control) executing an operation to achieve an operation objective is achievable; an operation control selector that selects, based on an output value from the ML model, an appropriate operation control for the present situation; and an operation control executor that executes the operation control selected. The operation control is a control routine for a robot to achieve an operation objective by the robot sensing an object in the vicinity of the robot with interaction with another object.
Claims5
A robot control device that controls a robot, the robot control device comprising:
- a machine learning model that receives an input of any given item of situation information selected from among items of situation information, and outputs an output value that is one of a binary value, a continuous value, and a multidimensional vector value indicating success or failure or a degree of success of an operation of a provided operation control in a situation indicated by the any given item of situation information received, the items of situation information being information about the robot or an object in a vicinity of the robot and including:
- (i) physical characteristics including a physical structure and a shape;
- (ii) a present status of at least one of a position, a posture, or a temperature that is a temporally varying characteristic;
- (iii) a relative relationship between the physical characteristics or between the present statuses;
- and (iv) a combination of the physical characteristics, a combination of the present statuses, or a combination of the physical characteristics and the present status;
- an operation control selector that obtains the output value for at least one operation control by providing the machine learning model with the any given item of situation information, when the any given item of situation information is received, and identifies, based on the output value, an operation control to be executed;
- and
- an operation control executor that executes the operation control 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 an object in the vicinity of the robot using a sensor with interaction with another object.
Dependencies are inferred from the claim text.