Preferred Networks, Inc.

Tokyo Electron Limited

Tomoki Komatsu

Masaki Watanabe

Kosuke Nakago

Daisuke Motoki

Masanobu Honda

Takahiko Kato

Tomohiko Niizeki

Hironori Moki

There is proposed a device capable of performing processing regarding decision of optimum loading positions even if it does not know all packages to be loaded beforehand. One embodiment of the present invention includes: at least one memory; and at least one processing circuitry. The at least one processing circuitry is configured to execute: generating loading state information regarding an object loading state of a predetermined space where a plurality of objects will be loaded, under an assumption that a first object to be loaded is loaded at a loading position candidate in the predetermined space; and inputting the loading state information into a loading state evaluation model that outputs, when the loading state information is input therein, an evaluation value with respect to the object loading state of the predetermined space, and acquiring the evaluation value.

Information processing system, model generation processing system, and information processing method

With respect to an inference method performed by at least one processor, the method includes inputting, by the at least one processor, into a learned model, second non-processed image data and second parameter data of a simulator, and inferring, by the at least one processor using the learned model, second processed image data. The learned model has been trained so that first processed image data, obtained as an output in response to first non-processed image data and first parameter data of the simulator for the first non-processed image data being input, approaches first simulator processed image data, obtained as a result of the simulator for the first non-processed image data by using the first parameter data.

Learning device, inference device, learning model generation method, and inference method

With respect to an inference method performed by at least one processor, the method includes inputting, by the at least one processor, into a learned model, non-processed object image data of a second object and data related to a second process for the second object, and inferring, by the at least one processor using the learned model, processed object image data of the second object on which the second process has been performed. The learned model has been trained so that an output obtained in response to non-processed object image data of a first object and data related to a first process for the first object being input approaches processed object image data of the first object on which the first process has been performed.

Learning device, inference device, and learned model

Growing community of inventors

Tokyo, Japan

Tomoki Komatsu