Robot system and workpiece picking method
AssigneesFanuc Corporation, Preferred Networks, Inc.
InventorsTakashi Yamazaki, Daisuke Okanohara, Eiichi Matsumoto
Life of this patent
Estimating the term…
Abstract
To select a picking position of a workpiece in a simpler method. A robot system includes a three-dimensional measuring device for generating a range image of a plurality of workpieces, a robot having a hand for picking up at least one of the plurality of workpieces, a display part for displaying the range image generated by the three-dimensional measuring device, and a reception part for receiving a teaching of a picking position for picking-up by the hand on the displayed range image. The robot picks up at least one of the plurality of workpieces by the hand on the basis of the taught picking position.
Claims22
An image processing apparatus comprising:
- at least one memory;
- and
- at least one processor configured to:
- acquire, from a user, before learning of a learning model has been completed, a teaching of a position in an image including a plurality of objects in order to learn the learning model, the position taught serving for selecting at least one object from the plurality of objects, the selected at least one object to be picked up by a robot;
- impart an evaluation value, based on at least one of the teaching or a result of the picking up the selected at least one object based on the teaching, to information of the selected at least one object at least at the position taught;
- and
- learn the learning model that outputs an evaluation value for picking up an object on information inputted, by performing machine learning using the information of the selected at least one object and using the imparted evaluation value as a label.
A machine learning method performed by an image processing apparatus, the machine learning method comprising:
- acquiring, from a user, before learning of a learning model has been completed, a teaching of a position in an image including a plurality of objects in order to learn the learning model, the position taught serving for selecting at least one object from the plurality of objects, the selected at least one object to be picked up by a robot;
- imparting an evaluation value based on at least one of the teaching or a result of the picking up the selected at least one object based on the teaching, to information of the selected at least one object at least at the position taught;
- and
- learning the learning model that outputs an evaluation value for picking up an object on information inputted, by performing machine learning using the information of the selected at least one object and using the imparted evaluation value as a label.
A non-transitory computer readable medium storing a machine learning program for causing an image processing apparatus to execute a machine learning method comprising:
- acquiring, from a user, before learning of a learning model has been completed, a teaching of a position in an image including a plurality of objects in order to learn the learning model, the position taught serving for selecting at least one object from the plurality of objects, the selected at least one object to be picked up by a robot;
- imparting an evaluation value based on at least one of the teaching or a result of the picking up the selected at least one object based on the teaching, to information of the selected at least one object at least at the position taught;
- and
- learning the learning model that outputs an evaluation value for picking up an object on information inputted, by performing machine learning using the information of the selected at least one object and using the imparted evaluation value as a label.
Dependencies are inferred from the claim text.