公开(公告)号：US20190275672A1

公开(公告)日：2019-09-12

申请号：US16463707

申请日：2017-11-16

Applicant: SONY CORPORATION

Inventor： Shingo TAKAMATSU ,  Yoshiyuki KOBAYASHI ,  Atsushi NODA ,  Yasufumi TANAKA

IPC: B25J9/16 ,  G06N5/04 ,  G06N20/00

Abstract: There is provided an information processing apparatus and an information processing method each enabling a transmission apparatus which transmits observation information to be used in prediction to be readily selected from a plurality of transmission apparatuses. A selection section selects a sensor which transmits observation information to be used in prediction as a use sensor from a plurality of sensors on the basis of pieces of information associated with the plurality of sensors, respectively. The present disclosure, for example, can be applied to an information processing apparatus or the like which performs prediction of failure probability of an industrial robot by using observation information which is transmitted from a predetermined sensor of a plurality of sensors installed in an industrial robot.

公开(公告)号：US20190332951A1

公开(公告)日：2019-10-31

申请号：US16475540

申请日：2017-11-09

Applicant: SONY CORPORATION

Inventor： Ryo NAKAHASHI ,  Hirotaka SUZUKI ,  Takuya NARIHIRA ,  Atsushi NODA

IPC: G06N5/02 ,  G06F16/906 ,  A63F13/46

Abstract: 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, derives an action determination rule, and determines an action which is caused to be executed in accordance with the action determination rule.

公开(公告)号：US20190308317A1

公开(公告)日：2019-10-10

申请号：US16467597

申请日：2017-12-01

Applicant: SONY CORPORATION

Inventor： Atsushi NODA ,  Yasufumi TANAKA ,  Yoshiyuki KOBAYASHI ,  Hideyuki MATSUNAGA ,  Shingo TAKAMATSU

IPC: B25J9/16 ,  G05B13/02 ,  B25J9/00

Abstract: There is provided an information processing apparatus and an information processing method that enable agents with different skills to cooperate with each other to efficiently execute a task, the information processing apparatus including: an allocation section configured to assign at least a part of a task to two or more agents on the basis of a skill model indicating a skill of each of the agents. An information processing method includes an allocation step of assigning at least a part of a task to two or more agents on the basis of a skill model indicating a skill of each of the agents. The present technology can be applied to, for example, an agent system in which a plurality of agents cooperates with each other to execute a task.