Learning device, learning method, learning model, detection device and grasping system
AssigneePreferred Networks, Inc.
InventorsHitoshi KUSANO, Ayaka KUME, Eiichi MATSUMOTO
Life of this patent
Estimating the term…
Abstract
An estimation device includes a memory and at least one processor. The at least one processor is configured to acquire information regarding a target object. The at least one processor is configured to estimate information regarding a location and a posture of a gripper relating to where the gripper is able to grasp the target object. The estimation is based on an output of a neural model having as an input the information regarding the target object. The estimated information regarding the posture includes information capable of expressing a rotation angle around a plurality of axes.
Claims24
1-20. (canceled)
A system comprising:
- a manipulator configured to manipulate a first object;
- and
- one or more processors configured to generate, by inputting information of the first object acquired by a detection device to a neural network model, information of at least one of a location or a posture of the manipulator;
- wherein the neural network model is learned based on information of manipulation of an object that is generated based on a simulation technique, and
- the manipulator is configured to manipulate the first object based on the generated information.
A method comprising:
- acquiring, by a detection device, information of a first object,
- generating, by one or more processors, information of at least one of a location or a posture of a manipulator by inputting the information of the first object to a neural network model, and
- manipulating, by the manipulator, the first object based on the generated information,
- wherein the neural network model is learned based on information of manipulation of an object that is generated based on a simulation technique.
A non-transitory computer readable medium storing therein a program which executes a method, when executed by one or more processors, the method comprising:
- generating, by inputting information of a first object acquired by a detection device to a neural network model, information of at least one of a location or a posture of a manipulator that manipulates the first object,
- wherein the neural network model is learned based on information of manipulation of an object that is generated based on a simulation technique.
A model learning method comprising:
- generating a neural network model inputting information of a first object and outputting information of at least one of a location or a posture of a manipulator,
- wherein the neural network model is learned based on information of manipulation of an object that is generated based on a simulation technique.
Dependencies are inferred from the claim text.