中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

54 records (took 0.017 seconds)

    ENHANCING MOVEMENT TRAINING WITH AN AUGMENTED REALITY MIRROR
    21.
    发明申请
    ENHANCING MOVEMENT TRAINING WITH AN AUGMENTED REALITY MIRROR 审中-公开
    增强运动训练与现实的镜子

    公开(公告)号：US20150099252A1

    公开(公告)日：2015-04-09

    申请号：US14315574

    申请日：2014-06-26

    Applicant: AUTODESK, INC.

    Inventor： Fraser ANDERSON ,  Tovi GROSSMAN ,  Justin Frank MATEJKA ,  George FITZMAURICE

    IPC: A63B24/00 ,  G09B5/02 ,  G09B19/00

    CPC classification number: G09B5/02 ,  G06F19/00 ,  G06F19/3481 ,  G06K9/00342 ,  G06T7/0014 ,  G06T7/251 ,  G06T11/00 ,  G06T2207/30196 ,  G06T2207/30221 ,  G09B19/003

    Abstract: One embodiment of the invention disclosed herein provides techniques for controlling a movement training environment. A movement training system retrieves a movement object from a set of movement objects. The movement training system attains first motion capture data associated with a first user performing a movement based on the movement object. The movement training system generates a first articulable representation based on the first motion capture data. The movement training system compares at least one first joint position related to the first articulable representation with at least one second joint position related to a second articulable representation associated with the movement object. The movement training system calculates a first similarity score based on a difference between the at least one first joint position and the at least one second joint position.

    Abstract translation: 本文公开的本发明的一个实施例提供了用于控制运动训练环境的技术。 运动训练系统从一组运动对象中检索运动对象。 移动训练系统获得与基于移动对象执行移动的第一用户相关联的第一运动捕获数据。 运动训练系统基于第一运动捕获数据产生第一可表达的表示。 所述运动训练系统将与所述第一可铰接表示相关的至少一个第一关节位置与与所述运动对象相关联的第二可铰接表示相关的至少一个第二关节位置进行比较。 运动训练系统基于至少一个第一关节位置与至少一个第二关节位置之间的差异来计算第一相似度得分。

    MULTI-USER PROMPTS FOR GENERATIVE ARTIFICIAL INTELLIGENCE SYSTEMS
    23.
    发明申请
    MULTI-USER PROMPTS FOR GENERATIVE ARTIFICIAL INTELLIGENCE SYSTEMS 有权

    公开(公告)号：US20250118022A1

    公开(公告)日：2025-04-10

    申请号：US18765122

    申请日：2024-07-05

    Applicant: AUTODESK, INC.

    Inventor： George William FITZMAURICE ,  Jo Karel VERMEULEN ,  Justin Frank MATEJKA

    IPC: G06T17/10 ,  G06T19/00

    Abstract: In various embodiments, a computer-implemented method for generating digital content comprises generating a multiparty interface that communicates with at least a trained machine learning (ML) model, a first client device, and a second client device; combining at least a first input from the first client device and a second input from the second client device to generate a composite prompt, transmitting the composite prompt to the trained ML model for execution, receiving a digital content item from the trained ML model that was generated in response to the composite prompt, and displaying the digital content item in the multiparty interface.

    DESIGN SPACE WITH INTEGRATED PROMPT SPACE FOR MACHINE LEARNING MODELS
    25.
    发明申请
    DESIGN SPACE WITH INTEGRATED PROMPT SPACE FOR MACHINE LEARNING MODELS 有权

    公开(公告)号：US20250045473A1

    公开(公告)日：2025-02-06

    申请号：US18748946

    申请日：2024-06-20

    Applicant: AUTODESK, INC.

    Inventor： George William FITZMAURICE ,  Jo Karel VERMEULEN ,  Justin Frank MATEJKA

    IPC: G06F30/12 ,  G06F30/27

    Abstract: In various embodiments, a computer-implemented method for displaying a prompt space, the method comprising displaying a design space comprising one or more design objects, receiving a selection of a current location within the design space, and displaying the prompt space at a placement location within the design space based on the current location. In other embodiments, a computer-implemented method for displaying a prompt history, the method comprising displaying a design space that includes a first design object, displaying a first prompt-history marker within the design space, the first prompt-history marker representing a first prompt history associated with the first design object, and in response to receiving a selection for viewing the first prompt history, displaying the first prompt history in a prompt space within the design space.

    TECHNIQUES FOR USING MULTIMODAL MACHINE LEARNING MODELS TO GENERATE DESIGN ALTERNATIVES FOR THREE-DIMENSIONAL OBJECTS
    26.
    发明公开
    TECHNIQUES FOR USING MULTIMODAL MACHINE LEARNING MODELS TO GENERATE DESIGN ALTERNATIVES FOR THREE-DIMENSIONAL OBJECTS 审中-公开

    公开(公告)号：US20240104275A1

    公开(公告)日：2024-03-28

    申请号：US18446339

    申请日：2023-08-08

    Applicant: AUTODESK, INC.

    Inventor： Vivian LIU ,  Jo Karel VERMEULEN ,  George William FITZMAURICE ,  Justin Frank MATEJKA

    IPC: G06F30/27

    CPC classification number: G06F30/27

    Abstract: In various embodiments, a design exploration application generates images that represent design alternatives for three-dimensional (3D) objects. The design exploration application generates a keyword prompt based on design intent text that describes a 3D object. The design exploration application executes a first machine learning model on the keyword prompt to generate a first set of keywords. The design exploration application generates a rephrase prompt based on a second set of keywords that includes at least one keyword from the first set of keywords. The design exploration application executes the first machine learning model on the rephrase prompt to generate a final text prompt. The design exploration application executes a second machine learning model on the final text prompt to generate a set of images.

    GENERATIVE DESIGN TECHNIQUES FOR ROBOT BEHAVIOR
    28.
    发明申请
    GENERATIVE DESIGN TECHNIQUES FOR ROBOT BEHAVIOR 审中-公开

    公开(公告)号：US20200030988A1

    公开(公告)日：2020-01-30

    申请号：US16134863

    申请日：2018-09-18

    Applicant: AUTODESK, INC.

    Inventor： Fraser ANDERSON ,  Stelian COROS ,  Ruta DESAI ,  Tovi GROSSMAN ,  Justin Frank MATEJKA ,  George FITZMAURICE

    IPC: B25J11/00 ,  G06F17/50 ,  G06N3/00

    Abstract: An automated robot design pipeline facilitates the overall process of designing robots that perform various desired behaviors. The disclosed pipeline includes four stages. In the first stage, a generative engine samples a design space to generate a large number of robot designs. In the second stage, a metric engine generates behavioral metrics indicating a degree to which each robot design performs the desired behaviors. In the third stage, a mapping engine generates a behavior predictor that can predict the behavioral metrics for any given robot design. In the fourth stage, a design engine generates a graphical user interface (GUI) that guides the user in performing behavior-driven design of a robot. One advantage of the disclosed approach is that the user need not have specialized skills in either graphic design or programming to generate designs for robots that perform specific behaviors or express various emotions.

    TECHNIQUES FOR CROWDSOURCING AND DYNAMICALLY UPDATING COMPUTER-AIDED SCHEDULES
    29.
    发明申请
    TECHNIQUES FOR CROWDSOURCING AND DYNAMICALLY UPDATING COMPUTER-AIDED SCHEDULES 审中-公开

    公开(公告)号：US20180322471A1

    公开(公告)日：2018-11-08

    申请号：US15925632

    申请日：2018-03-19

    Applicant: AUTODESK, INC.

    Inventor： Fraser ANDERSON ,  George FITZMAURICE ,  Justin Frank MATEJKA

    IPC: G06Q10/10

    CPC classification number: G06Q10/1095 ,  G06F3/0482 ,  G06Q10/107

    Abstract: In various embodiments, a scheduling application automatically determines the timing of linearly dependent events. In operation, the scheduling application detects that a first event included in an original scheduled sequence of events has not completed by a scheduled completion time based on a current time. The scheduling application then determines that a second event included in the original scheduled sequence of events has a dependency on the completion of the first event. Subsequently, the scheduling application updates one or more temporal properties associated with the second event based on the current time to generate a third event. The scheduling application then generates, via a processor, a modified scheduled sequence of events that includes the third event instead of the second event. Advantageously, automatically adjusting the timing of linear dependent events based on the current time reduces inefficiencies associated with conventional scheduling techniques.

    PERTURBATION-BASED TECHNIQUES FOR ANONYMIZING DATASETS
    30.
    发明申请
    PERTURBATION-BASED TECHNIQUES FOR ANONYMIZING DATASETS 审中-公开

    公开(公告)号：US20180322309A1

    公开(公告)日：2018-11-08

    申请号：US15972085

    申请日：2018-05-04

    Applicant: AUTODESK, INC.

    Inventor： Justin Frank MATEJKA ,  George FITZMAURICE

    IPC: G06F21/62 ,  G06F17/18 ,  G06K9/62 ,  G06F17/30

    CPC classification number: G06F21/6254 ,  G06F17/18 ,  G06F17/30536 ,  G06K9/6215

    Abstract: In various embodiments, a dataset generation application generates a new dataset based on an original dataset. The dataset generation engine perturbs a first data item included in the original dataset to generate a second data item. The dataset generation application then generates a test dataset based on the original dataset and the second data item. The test dataset includes the second data item instead of the first data item. Subsequently, the dataset generation application determines that the test dataset is characterized by a first property value that is substantially similar to a second property value that characterizes the original dataset. The first property value and the second property value are associated with the same property. Finally, the dataset generation application generates a new dataset based on the test dataset. The new dataset conveys aspect(s) of the original dataset without revealing the first data item.

Patent Agency Ranking