US-12616899-B2 - Information processing apparatus, information processing system, and information processing method

US12616899B2US 12616899 B2US12616899 B2US 12616899B2US-12616899-B2

Abstract

An information processing apparatus according to an embodiment includes: a control unit ( 101 ) that controls display of a first virtual space, in which the control unit controls a motion of an avatar corresponding to a second operator displayed in the first virtual space on a basis of prediction information for predicting an operation by the second operator with respect to a second virtual space different from the first virtual space, the second virtual space corresponding to the second operator.

Inventors

Hiroaki Kitano
Michael Siegfried SPRANGER
Masahiro Fujita

Assignees

Sony Group Corporation

Dates

Publication Date: 20260505
Application Date: 20220224
Priority Date: 20210330

Claims (13)

1 . An information processing apparatus, comprising: circuitry configured to control display of a first virtual space corresponding to a viewpoint of a first operator, and control a motion of an avatar corresponding to a second operator displayed in the first virtual space based on prediction information for predicting an operation performed on the avatar by the second operator with respect to a second virtual space different from the first virtual space, wherein the second virtual space corresponds to a terminal of the second operator, wherein the prediction information is generated based on learning information obtained by learning the operation performed on the avatar by the second operator by machine learning, wherein the first virtual space corresponds to a terminal of the first operator, wherein the avatar is shared by the first virtual space and the second virtual space, and wherein the circuitry is further configured to execute the machine learning using a Recurrent Neural Network (RNN) on each operation with respect to the first virtual space by the first operator and environment information of the first virtual space including the avatar, generate the prediction information based on a result of the machine learning, and add the result of the machine learning to the input data of the machine learning at a predetermined ratio.
2 . The information processing apparatus according to claim 1 , wherein the viewpoint of the first operator corresponds to a terminal of the first operator.
3 . The information processing apparatus according to claim 1 , wherein the circuitry is further configured to detect a contradiction between a first motion of the avatar corresponding to the operation performed on the avatar by the second operator and a second motion of the avatar controlled based on the prediction information in the first virtual space.
4 . The information processing apparatus according to claim 3 , wherein the circuitry controls the motion of the avatar in the first virtual space based on an operation on the avatar by the second operator in a case where the contradiction is detected by the detection unit.
5 . The information processing apparatus according to claim 3 , wherein the circuitry causes a state of the avatar displayed in the first virtual space to transition to a state in which the contradiction is resolved in a case where the contradiction is detected by the detection unit.
6 . The information processing apparatus according to claim 5 , wherein the circuitry solves the contradiction by causing a state of the avatar to transition from a state of the second motion to a state of the first motion.
7 . The information processing apparatus according to claim 5 , wherein the circuitry solves the contradiction by changing a virtual environment in the first virtual space.
8 . The information processing apparatus according to claim 1 , wherein the circuitry predicts an operation by the second operator based on environment information of the first virtual space.
9 . The information processing apparatus according to claim 1 , wherein the avatar is configured to be shared by the first virtual space and the second virtual space.
10 . The information processing apparatus according to claim 1 , wherein operation information indicating an operation by the second operator is transmitted from a second local server that presents the second virtual space to a first local server that presents the first virtual space via a global server that transmits and receives data to and from the circuitry.
11 . The information processing apparatus according to claim 1 , wherein data is directly transmitted and received between a first local server configured to present the first virtual space and a second local server configured to present the second virtual space.
12 . An information processing method, executed by a processor, the method comprising: controlling display of a first virtual space corresponding to a viewpoint of a first operator; and controlling a motion of an avatar corresponding to a second operator displayed in the first virtual space based on prediction information for predicting an operation by the second operator with respect to a second virtual space different from the first virtual space, wherein the second virtual space corresponds to the second operator, wherein the prediction information is generated based on learning information obtained by learning the operation performed on the avatar by the second operator by machine learning, wherein the first virtual space corresponds to a terminal of the first operator, wherein the avatar is shared by the first virtual space and the second virtual space, and wherein the method further comprises executing the machine learning using a Recurrent Neural Network (RNN) on each operation with respect to the first virtual space by the first operator and environment information of the first virtual space including the avatar, generating the prediction information based on a result of the machine learning, and adding the result of the machine learning to the input data of the machine learning at a predetermined ratio.
13 . An information processing system, comprising: a first server configured to present a first virtual space based on a viewpoint of a first operator within a global virtual space; a second server configured to present a second virtual space based on the global virtual space; and a third server configured to present the global virtual space, wherein the third server includes circuitry configured to control display of the first virtual space presented by the first server, and control a motion of an avatar corresponding to a second operator displayed in the first virtual space based on prediction information for predicting an operation by the second operator with respect to the second virtual space corresponding to the second operator, wherein the prediction information is generated based on learning information obtained by learning the operation performed on the avatar by the second operator by machine learning, wherein the first virtual space corresponds to a terminal of the first operator, wherein the avatar is shared by the first virtual space and the second virtual space, and wherein the circuitry is further configured to execute the machine learning using a Recurrent Neural Network RNN) on each operation with respect to the first virtual space by the first operator and environment information of the first virtual space including the avatar, generate the prediction information based on a result of the machine learning, and add the result of the machine learning to the input data of the machine learning at a predetermined ratio.

Description

CROSS REFERENCE TO PRIOR APPLICATION This application is a National Stage Patent Application of PCT International Patent Application No. PCT/JP2022/007502 (filed on Feb. 24, 2022) under 35 U.S.C. § 371, which claims priority to Japanese Patent Application No. 2021-057039 (filed on Mar. 30, 2021), which are all hereby incorporated by reference in their entirety. FIELD The present disclosure relates to an information processing apparatus, an information processing system, and an information processing method. BACKGROUND In recent years, metaverse, which is a kind of virtual world constructed on a communication network such as the Internet, has attracted attention. A large number of users from various places can participate in the metaverse at the same time, and each user participates in the metaverse using, for example, his or her own avatar. Each user operates an avatar using a controller or the like, so that the user can freely act in the metaverse. One of the problems in metaverse is a delay when an avatar operated by a user participating from each place interacts with the virtual world or another avatar in the virtual world. Roughly two types of the delay are conceivable, which are a delay that occurs when the user operates the user's own avatar, and a delay until a reaction from the environment in the virtual world or another avatar returns. Conventionally, it has been common to eliminate these delays by reducing communication delays, such as a reduction in the amount of communication by a codec and an appropriate routing setting. On the other hand, there is disclosed a technique of separating a virtual world into multiple virtual worlds having the same spatial coordinate system, and independently updating each virtual world to suppress occurrence of discrepancies between the respective virtual worlds (for example, Patent Literature 1). Patent Literature 1 proposes a technique of superimposing images of multiple virtual spaces with a delay allowed, so as to eliminate the delay in appearance. CITATION LIST Patent Literature Patent Literature 1: JP 2010-172732 A SUMMARY Technical Problem However, in the virtual world such as a metaverse, for example, a delay related to a user's operation due to a physical distance to the global data center cannot be theoretically avoided. In addition, since there is a delay in the network, the user feels uncomfortable or inconvenient in the interaction operation. Furthermore, Patent Literature 1 rather actively uses a delay, and elimination of the delay is merely an apparent matter. An object of the present disclosure is to provide an information processing apparatus, an information processing system, and an information processing method capable of eliminating a delay with respect to an operation in a virtual world. Solution to Problem For solving the problem described above, an information processing apparatus, according to one aspect of the present disclosure has a control unit that controls display of a first virtual space, wherein the control unit controls a motion of an avatar corresponding to a second operator displayed in the first virtual space on a basis of prediction information for predicting an operation by the second operator with respect to a second virtual space different from the first virtual space, the second virtual space corresponding to a terminal of the second operator. BRIEF DESCRIPTION OF DRAWINGS FIG. 1 is a schematic diagram illustrating a configuration of an example of an information processing system for achieving a metaverse according to an existing technology. FIG. 2 is a schematic diagram illustrating a configuration of an example of an information processing system according to a first embodiment of the present disclosure. FIG. 3 is a block diagram illustrating a configuration of an example of a local server applicable to the first embodiment. FIG. 4 is a block diagram illustrating a configuration of an example of an HMI applicable to the first embodiment. FIG. 5 is a functional block diagram of an example for describing functions of the local server according to the first embodiment. FIG. 6 is a functional block diagram of an example for describing functions of a global server according to the first embodiment. FIG. 7 is a flowchart of an example for schematically describing processing according to the first embodiment. FIG. 8 is a diagram for describing prediction and contradiction with prediction according to the first embodiment. FIG. 9 is a diagram for describing processing for solving a contradiction between prediction and an actual action according to the first embodiment. FIG. 10 is a block diagram illustrating a configuration of an example for controlling a motion of an avatar according to an operation by an operator according to the first embodiment. FIG. 11 is a state transition diagram of an example illustrating an example of a state transition applicable to the first embodiment for an avatar controller to control a motion of an