公开(公告)号：EP3712776A1

公开(公告)日：2020-09-23

申请号：EP18889977.7

申请日：2018-10-25

申请人： SONY Corporation

发明人： TAKANO, Hiroaki ,  SATO, Naoyuki ,  KANEMOTO, Katsuyoshi ,  SAITO, Erika ,  SUZUKI, Hirotaka ,  YUKI, Taichi

IPC分类号： G06F13/00

摘要： An optimal network is constructed in a case in which a plurality of IoT standards or IoT platforms coexist.
According to the present disclosure, provided is a terminal management device including a receiving unit that receives, from a terminal that collects information from a sensor, access timing information related to an accessible timing to the terminal and a transmitting unit that transmits the access timing information to a server that searches for the information. With this configuration, it is possible to construct an optimal network in a case in which a plurality of IoT standards or IoT platforms coexist.

公开(公告)号：EP3584750A1

公开(公告)日：2019-12-25

申请号：EP17896366.6

申请日：2017-11-09

申请人： Sony Corporation

发明人： NAKAHASHI, Ryo ,  SUZUKI, Hirotaka ,  NARIHIRA, Takuya ,  NODA, Atsushi

IPC分类号： G06N99/00

摘要： Provided are an apparatus and a method enabling efficient reinforcement learning to be performed by input of an annotation. Included are a database configured to store respective pieces of information of a state, an action, and a reward of a processing execution unit, a learning execution unit configured to execute learning processing in accordance with a reinforcement learning algorithm to which the information stored in the database is applied, and an annotation input unit configured to input annotation information including sub reward setting information and store the annotation information in the database. The learning execution unit executes learning processing to which the respective pieces of information of the state, the action, and the reward input from the processing execution unit and the sub reward setting information are applied. The learning execution unit derives an action determination rule for estimating an action to be executed to raise an expected reward and determines an action which the processing execution unit is caused to execute in accordance with the action determination rule.

公开(公告)号：EP3835008A1

公开(公告)日：2021-06-16

申请号：EP19846081.8

申请日：2019-07-25

申请人： Sony Corporation

发明人： IRIE, Atsushi ,  SUZUKI, Hirotaka ,  KASAI, Takara ,  NAKAMURA, Masanobu ,  SHIN, Andrew

IPC分类号： B25J19/06

摘要： The present technology relates to a control device, a control method, and a program that can prevent failure of an operation of a robot.
A control device according to an aspect of the present technology includes a state transition determination section that controls an operation of a robot to perform a predetermined process before a task results in failure in a case where a state transition of the robot in performing the task follows a failure state transition that is preset as a state transition that results in the failure of the task. The present technology can be applied to a robot capable of autonomous operation.

公开(公告)号：EP2605153B1

公开(公告)日：2019-04-03

申请号：EP11816334.4

申请日：2011-08-02

申请人： Sony Corporation

发明人： SUZUKI, Hirotaka ,  ITO, Masato

IPC分类号： G06F17/30 ,  G06N3/00 ,  G06K9/00 ,  H04N9/87