公开(公告)号：US20210116934A1

公开(公告)日：2021-04-22

申请号：US17050314

申请日：2019-01-25

Applicant: SONY CORPORATION

Inventor： Jianing WU ,  Sayaka WATANABE ,  Tatsuhito SATO ,  Natsuko OZAKI ,  Jun YOKONO

IPC: G05D1/02 ,  G05D1/00

Abstract: There is provided an information processing apparatus, an information processing method, a program, and an autonomous behavior robot control system that enable an autonomous behavior robot to perform a behavior more suitable for the surrounding environment. The information processing apparatus includes a map generating unit and a behavior control signal generating unit. The map generating unit generates a spatio-temporal map on the basis of data obtained by a data obtaining unit of an autonomous behavior robot, the autonomous behavior robot including the data obtaining unit that obtains data related to surrounding environment information. The behavior control signal generating unit generates a behavior control signal for the autonomous behavior robot to move and obtain data from the data obtaining unit in order to obtain information to be added to the spatio-temporal map.

公开(公告)号：US20210316452A1

公开(公告)日：2021-10-14

申请号：US17259693

申请日：2019-07-16

Applicant: SONY CORPORATION

Inventor： Natsuko OZAKI ,  Jun YOKONO ,  Jianing WU ,  Tatsuhito SATO ,  Sayaka WATANABE

IPC: B25J9/16

Abstract: More natural communication and interaction are enabled. The autonomous system (100) includes an action decision unit (140) that decides, based on an attention level map (40) in which an attention level indicating the degree of attention for each position in a predetermined space is set, the action which a drive mechanism is caused to perform.

公开(公告)号：US20210012205A1

公开(公告)日：2021-01-14

申请号：US16968721

申请日：2019-10-29

Applicant: SONY CORPORATION

Inventor： Natsuko OZAKI

IPC: G06N3/08 ,  G06N3/04 ,  G06N5/04

Abstract: Provided a learning device including: a first learning unit that learns parameters of a first neural network based on a first error between the same data as input data to a second neural network connected to a front stage of the first neural network and output data of the first neural network; and a second learning unit that learns at least some parameters of the second neural network based on a second error between data different from the input data and output data of the second neural network and sign-inverted data of an error transmitted from the first neural network.