公开(公告)号：US20210183051A1

公开(公告)日：2021-06-17

申请号：US17189592

申请日：2021-03-02

Applicant: Preferred Networks, Inc.

Inventor： Kosuke NAKAGO ,  Daisuke MOTOKI ,  Masaki WATANABE ,  Tomoki KOMATSU

IPC: G06T7/00 ,  G06N3/08

Abstract: 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.

公开(公告)号：US20210150353A1

公开(公告)日：2021-05-20

申请号：US17137149

申请日：2020-12-29

Applicant: Preferred Networks, Inc.

Inventor： Masaki WATANABE ,  Tomoki KOMATSU

IPC: G06N3/08 ,  G06N3/04

Abstract: 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.