Method for producing complementary model
AssigneeKomatsu Ltd.
InventorsShun Kawamoto, Shintaro Hamada, Yosuke Kajihara
Life of this patent
Estimating the term…
Abstract
A method for producing a complementary model includes acquiring distribution information and incomplete distribution information as a dataset for learning and training the complementary model using the dataset. The distribution information indicates a distribution of an amount of a transport object in a drop target of a work machine, and the incomplete distribution information is information from which some values of the distribution information are missing. The complementary model is trained using the dataset such that when the incomplete distribution information is used as an input value, the complementary model complements the missing values and outputs the distribution information an output value.
Claims8
A method for producing a complementary model, the method comprising:
- acquiring distribution information indicating a distribution of an amount of a transport object in a drop target of a work machine and incomplete distribution information in which some values of the distribution information are missing, the distribution information and the incomplete distribution information constituting a dataset for learning;
- and
- training the complementary model using the dataset for learning such that when the incomplete distribution information is used as an input value to the complementary model, the complementary model outputs the distribution information as an output value,
- the values of the distribution information that are missing corresponding to a shielded part of the distribution information that is shielded by an obstacle,
- the distribution information outputted from complementary model complementing a value of the shielded part based on a rate of change or a pattern of change in a three-dimensional position of the transport object near the shielded part, and
- the complementary model estimating a distribution of an amount of the transport object in the shielded part based on a type of the transport object.
A device for producing a complementary model, the device comprising:
- a processor;
- and
- a storage,
- the processor being configured to execute a program stored in the storage to:
- acquire distribution information indicating a distribution of an amount of a transport object in a drop target of a work machine and incomplete distribution information in which some values of the distribution information are missing, the distribution information and the incomplete distribution information constituting a dataset for learning;
- and
- train the complementary model using the dataset for learning such that when the incomplete distribution information is used as an input value to the complementary model, the complementary model outputs the distribution information as an output value,
- the values of the distribution information that are missing corresponding to a shielded part of the distribution information that is shielded by an obstacle,
- the distribution information outputted from complementary model complementing a value of the shielded part based on a rate of change or a pattern of change in a three-dimensional position of the transport object near the shielded part, and
- the complementary model estimating a distribution of an amount of the transport object in the shielded part based on a type of the transport object.
Dependencies are inferred from the claim text.