中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

80 records (took 0.024 seconds)

    Temporal foveated rendering using motion estimation
    13.
    发明授权
    Temporal foveated rendering using motion estimation 有权

    公开(公告)号：US10169843B1

    公开(公告)日：2019-01-01

    申请号：US15818072

    申请日：2017-11-20

    Applicant: ADVANCED MICRO DEVICES, INC. ,  ATI TECHNOLOGIES ULC

    Inventor： Ihab Amer ,  Guennadi Riguer ,  Ruijin Wu ,  Skyler J. Saleh ,  Boris Ivanovic ,  Gabor Sines

    IPC: G06T3/40 ,  G06T7/136 ,  G06T7/13 ,  G06T7/246

    Abstract: A processing system selectively renders pixels or blocks of pixels of an image and leaves some pixels or blocks of pixels unrendered to conserve resources. The processing system generates a motion vector field to identify regions of an image having moving areas. The processing system uses a rendering processor to identify as regions of interest those units having little to no motion, based on the motion vector field, and a large amount of edge activity, and to minimize the probability of unrendered pixels, or “holes”, in these regions. To avoid noticeable patterns, the rendering processor applies a probability map to determine the possible locations of holes, assigning to each unit a probability indicating the percentage of pixels within the unit that will be holes, and assigning a lower probability to units identified as regions of interest.

    Detecting personal-space violations in artificial intelligence based non-player characters
    14.
    发明授权
    Detecting personal-space violations in artificial intelligence based non-player characters 有权

    公开(公告)号：US12172081B2

    公开(公告)日：2024-12-24

    申请号：US17709904

    申请日：2022-03-31

    Applicant: Advanced Micro Devices, Inc. ,  ATI Technologies ULC

    Inventor： Mehdi Saeedi ,  Ian Charles Colbert ,  Thomas Daniel Perry ,  Gabor Sines

    IPC: A63F13/56

    Abstract: Systems, apparatuses, and methods for detecting personal-space violations in artificial intelligence (AI) based non-player characters (NPCs) are disclosed. An AI engine creates a NPC that accompanies and/or interacts with a player controlled by a user playing a video game. During gameplay, measures of context-dependent personal space around the player and/or one or more NPCs are generated. A control circuit monitors the movements of the NPC during gameplay and determines whether the NPC is adhering to or violating the measures of context-dependent personal space. The control circuit can monitor the movements of multiple NPCs simultaneously during gameplay, keeping a separate score for each NPC. After some amount of time has elapsed, the scores of the NPCs are recorded, and then the scores are provided to a machine learning engine to retrain the AI engines controlling the NPCs.

    Adaptive audio mixing
    17.
    发明授权
    Adaptive audio mixing 有权

    公开(公告)号：US11839815B2

    公开(公告)日：2023-12-12

    申请号：US17132827

    申请日：2020-12-23

    Applicant: Advanced Micro Devices, Inc. ,  ATI Technologies ULC

    Inventor： Carl Kittredge Wakeland ,  Mehdi Saeedi ,  Thomas Daniel Perry ,  Gabor Sines

    IPC: A63F13/67 ,  A63F13/79 ,  A63F13/54 ,  G06N3/08 ,  G06F16/635 ,  A63F13/428 ,  G06F3/01 ,  G11B27/02

    CPC classification number: A63F13/54 ,  A63F13/428 ,  G06F3/011 ,  G06F3/017 ,  G06N3/08 ,  G11B27/02 ,  A63F2300/105 ,  A63F2300/6081

    Abstract: Systems, apparatuses, and methods for performing adaptive audio mixing are disclosed. A trained neural network dynamically selects and mixes pre-recorded, human-composed music stems that are composed as mutually compatible sets. Stem and track selection, volume mixing, filtering, dynamic compression, acoustical/reverberant characteristics, segues, tempo, beat-matching and crossfading parameters generated by the neural network are inferred from the game scene characteristics and other dynamically changing factors. The trained neural network selects an artist's pre-recorded stems and mixes the stems in real-time in unique ways to dynamically adjust and modify background music based on factors such as game scenario, the unique storyline of the player, scene elements, the player's profile, interest, and performance, adjustments made to game controls (e.g., music volume), number of viewers, received comments, player's popularity, player's native language, player's presence, and/or other factors. The trained neural network creates unique music that dynamically varies according to real-time circumstances.

    HUMAN-LIKE NON-PLAYER CHARACTER BEHAVIOR WITH REINFORCEMENT LEARNING
    18.
    发明申请
    HUMAN-LIKE NON-PLAYER CHARACTER BEHAVIOR WITH REINFORCEMENT LEARNING 有权

    公开(公告)号：US20220309364A1

    公开(公告)日：2022-09-29

    申请号：US17215437

    申请日：2021-03-29

    Applicant: Advanced Micro Devices, Inc. ,  ATI Technologies ULC

    Inventor： Thomas Daniel Perry ,  Mehdi Saeedi ,  Gabor Sines

    IPC: G06N5/04 ,  G06N20/00 ,  A63F13/56

    Abstract: Systems, apparatuses, and methods for creating human-like non-player character (NPC) behavior with reinforcement learning (RL) are disclosed. An artificial intelligence (AI) engine creates a NPC that has seamless movement when accompanying a player controlled by a user playing a video game. The AI engine is RL-trained to stay close to the player but not get in the player's way while acting in a human-like manner. Also, the AI engine is RL-trained to evaluate the quality of information that is received over time from other AI engines and then to act on the evaluated information quality. Each AI agent is trained to evaluate the other AI agents and determine whether another AI agent is a friend or a foe. In some cases, groups of AI agents collaborate together to either help or hinder the player. The capabilities of each AI agent are independent from the capabilities of other AI agents.

    ADAPTIVE AUDIO MIXING
    19.
    发明申请
    ADAPTIVE AUDIO MIXING 有权

    公开(公告)号：US20220193549A1

    公开(公告)日：2022-06-23

    申请号：US17132827

    申请日：2020-12-23

    Applicant: Advanced Micro Devices, Inc. ,  ATI Technologies ULC

    Inventor： Carl Kittredge Wakeland ,  Mehdi Saeedi ,  Thomas Daniel Perry ,  Gabor Sines

    IPC: A63F13/54 ,  A63F13/428 ,  G06F3/01 ,  G11B27/02 ,  G06N3/08

    Abstract: Systems, apparatuses, and methods for performing adaptive audio mixing are disclosed. A trained neural network dynamically selects and mixes pre-recorded, human-composed music stems that are composed as mutually compatible sets. Stem and track selection, volume mixing, filtering, dynamic compression, acoustical/reverberant characteristics, segues, tempo, beat-matching and crossfading parameters generated by the neural network are inferred from the game scene characteristics and other dynamically changing factors. The trained neural network selects an artist's pre-recorded stems and mixes the stems in real-time in unique ways to dynamically adjust and modify background music based on factors such as game scenario, the unique storyline of the player, scene elements, the player's profile, interest, and performance, adjustments made to game controls (e.g., music volume), number of viewers, received comments, player's popularity, player's native language, player's presence, and/or other factors. The trained neural network creates unique music that dynamically varies according to real-time circumstances.

Patent Agency Ranking