SPATIALLY ARRANGED PROMPT VOLUMES TO GENERATE THREE-DIMENSIONAL DESIGNS

    公开(公告)号:US20250045494A1

    公开(公告)日:2025-02-06

    申请号:US18649872

    申请日:2024-04-29

    Applicant: AUTODESK, INC.

    Abstract: In various embodiments, a computer-implemented method for generating a design object comprises generating a prompt within a design space generated by a design exploration application, wherein the prompt has a prompt definition that includes at least design intent text, and a prompt volume that occupies a portion of the design space and exerts a sphere of influence within the prompt volume, executing a trained machine learning (ML) model on the prompt to generate the design object, and displaying the design object within the prompt volume.

    Hybrid Reinforcement Learning (RL) to Control a Water Distribution Network

    公开(公告)号:US20250021060A1

    公开(公告)日:2025-01-16

    申请号:US18760741

    申请日:2024-07-01

    Applicant: Autodesk, Inc.

    Abstract: A method and system control a water distribution network. A database is maintained of prior states based on a residential water demand, a tank level, and an energy tariff. A current state of the water distribution network is determined. Rewards are determined and include a tank level constraint, an energy cost, and a toggle count. A query based model is used to determine a set of control points used to control a first prior state. An RL agent is trained based on the prior states and rewards. The RL agent determines a control setpoint (that changes the pump speed) that maintains the tank level, minimizes the energy cost, and complies with the toggle count. The RL agent determines time slots and selects one of the time slots. Hybrid setpoints are generated to control the water distribution network within the selected time slot.

    EFFICIENT MODELING OF ASSEMBLIES USING GENERATIVE DESIGN

    公开(公告)号:US20240346204A1

    公开(公告)日:2024-10-17

    申请号:US18348303

    申请日:2023-07-06

    Applicant: AUTODESK, INC.

    CPC classification number: G06F30/20

    Abstract: One embodiment of the present invention sets forth a technique for modeling assemblies using generative design techniques. The technique includes determining a portion of an assembly to model as a superelement and computing a mathematical model representing the superelement. The technique further includes eliminating one or more interior degrees of freedom from the mathematical model and computing a reduced stiffness matrix corresponding to the superelement by solving one or more equations associated with the mathematical model using an iterative sparse matrix solver.

    INTEGRATION OF A TWO-DIMENSIONAL INPUT DEVICE INTO A THREE-DIMENSIONAL COMPUTING ENVIRONMENT

    公开(公告)号:US20240319801A1

    公开(公告)日:2024-09-26

    申请号:US18732106

    申请日:2024-06-03

    Applicant: AUTODESK, INC.

    CPC classification number: G06F3/0346 G02B30/50 G06F3/038 G06T19/006

    Abstract: A workstation enables operation of a 2D input device with a 3D interface. A cursor position engine determines the 3D position of a cursor controlled by the 2D input device as the cursor moves within a 3D scene displayed on a 3D display. The cursor position engine determines the 3D position of the cursor for a current frame of the 3D scene based on a current user viewpoint, a current mouse movement, a CD gain value, a Voronoi diagram, and an interpolation algorithm, such as the Laplacian algorithm. A CD gain engine computes CD gain optimized for the 2D input device operating with the 3D interface. The CD gain engine determines the CD gain based on specifications for the 2D input device and the 3D display. The techniques performed by the cursor position engine and the techniques performed by the CD gain engine can be performed separately or in conjunction.

Patent Agency Ranking