Operation prediction system and operation prediction method
View Patent ↗The automatic operation system includes a plurality of learned imitation models and a model selecting unit. The learned imitation models are constructed by machine learning of operation history data, the operation history data being classified into several groups by an automatic classification system algorithm, the operation history data of each group being learned by the imitation model corresponding to the group. The operation history data include data indicating a surrounding environment and data indicating an operation of an operator in the surrounding environment. The model selecting unit selects one imitation model from several imitation models based on a result of classifying data indicating a given surrounding environment by the automatic classification algorithm of the classification system. The automatic operation system inputs data indicating the surrounding environment to the imitation model selected by the model selecting unit to predict an operation of the operator with respect to the surrounding environment.
1. An operation prediction system comprising:
a plurality of learned operation prediction models constructed by machine learning of leaning operation case data, the learning operation case data being classified into a plurality of groups by an automatic classification algorithm, the learning operation case data belonging to each group being learned by the operation prediction model corresponding to the group, the learning operation case data including data indicating a surrounding environment and data indicating a human operation in the surrounding environment; and
a model selecting unit for selecting one operation prediction model from a plurality of the operation prediction models based on a result of classifying data indicating a given surrounding environment by the automatic classification algorithm; wherein
the data indicating the surrounding environment are input to the operation prediction model selected by the model selecting unit to predict a human operation with respect to the surrounding environment.
2. The operation prediction system according to claim 1 , wherein
the data indicating the surrounding environment include image data.
3. The operation prediction system according to claim 1 ,
performing an operation prediction of an operation involving contact with the surrounding environment.
4. The operation prediction system according to claim 1 , further comprising:
an evaluation unit for evaluating a result of the prediction of the human operation output from the operation prediction model selected by the model selecting unit; and
an additional learning unit for making the learned operation prediction model learn additionally by machine learning.
5. A robot operation system as the operation prediction system according to claim 1 .
6. A plant operation system as the operation prediction system according to claim 1 .
7. An operation prediction method comprising:
a classification step for classifying learning operation case data including data indicating a surrounding environment and data indicating a human operation in the surrounding environment into a plurality of groups by an automatic classification algorithm;
a learning step, on a computer having a plurality of operation prediction models, for making each of the operation prediction models corresponding to the group learn the learning operation case data belonging to each group classified in the classification step, by machine learning, to construct a plurality of learned operation prediction models;
a model selecting step of selecting one operation prediction model from the plurality of the operation prediction models based on a result of classifying data indicating a given surrounding environment by the automatic classification algorithm; and
a prediction step for inputting data indicating the surrounding environment to the operation prediction model selected in the model selecting step to predict a human operation with respect to the surrounding environment.
8. The operation prediction method according to claim 7 , wherein
the data indicating the surrounding environment include image data.
9. The operation prediction method according to claim 7 ,
performing an operation prediction of an operation involving contact with the surrounding environment.
10. The operation prediction method according to claim 7 , further comprising:
an evaluation step for evaluating a result of human operation prediction output from the operation prediction model selected in the model selecting step;
an additional learning step for making the learned operation prediction model learn additionally by machine learning.