Techniques for analyzing vehicle design deviations using deep learning with neural networks

    公开(公告)号:US11842262B2

    公开(公告)日:2023-12-12

    申请号:US18045809

    申请日:2022-10-11

    Applicant: AUTODESK, INC.

    CPC classification number: G06N3/045 G06F17/15 G06F30/15 G06N3/08

    Abstract: A design application is configured to generate a latent space representation of a fleet of pre-existing vehicles. The design application encodes vehicle designs associated with the fleet of pre-existing vehicles into the latent space representation to generate a first latent space location. The first latent space location represents the characteristic style associated with the fleet of pre-existing vehicles. The design application encodes a sample design provided by a user into the latent space representation to produce a second latent space location. The design application then determines a distance between the first latent space location and the second latent space location. Based on the distance, the design application generates a style metric that indicates the aesthetic similarity between the sample design and the vehicle designs associated with the fleet of pre-existing vehicles. The design application can also generate new vehicle designs based on the latent space representation and the sample design.

    Reality capture graphical user interface

    公开(公告)号:US11809681B2

    公开(公告)日:2023-11-07

    申请号:US17826963

    申请日:2022-05-27

    Applicant: Autodesk, Inc.

    Abstract: A method, system, apparatus, and article of manufacture provide the ability to perform multiple actions based on a reality captured image. An adjustable splitter splits a viewport into viewing panes with the ability to freely adjust the splitter angle. A sphere represents a view of a scene from a viewpoint and used to render an interactive preview of the view without moving to the viewpoint. A series of 2D images may be used to simulate the navigation of a 3D model in an expedited manner. A 3D mesh error scroll bar is used navigate unsorted errors resulting from mesh creation. An interactive gradient map can be used to select a points based on a range of values for non-geometric parameters. An irregularly shaped mesh selection boundary can be directly modified by stretching. An elevation slice of a 3D model can be defined and isolated for viewing/manipulation.

    Three dimensional visual programming interface for a network of devices

    公开(公告)号:US11809678B2

    公开(公告)日:2023-11-07

    申请号:US15717876

    申请日:2017-09-27

    Applicant: AUTODESK, INC.

    CPC classification number: G06F3/04815 G06F3/011 H04L41/22

    Abstract: Approaches for generating virtual representations of smart objects in a 3D visual programming interface. The interface displays a 3D virtual environment containing virtual objects that represents a real-world environment containing smart objects. The 3D virtual environment displays virtual objects in a manner that is spatially accurate relative to the physical objects in the real-world environment. For each virtual object representing a physical object, a logic node (port node) is displayed, the port node representing the set of functions associated with the physical object. The interface enables users to create, delete, or modify different types of logic nodes (representing functions) and create, delete, or modify links (representing data connections) between logic nodes within the 3D virtual environment. The authoring of the logic nodes and links produces an executable program. Upon executing the program, data flows between the logic nodes are visually represented as particles moving between the logic nodes.

    Computer aided generative design with tool size control to facilitate 2.5-axis subtractive manufacturing processes

    公开(公告)号:US11789429B2

    公开(公告)日:2023-10-17

    申请号:US17592372

    申请日:2022-02-03

    Applicant: Autodesk, Inc.

    CPC classification number: G05B19/4155 G06F30/10 G05B2219/37355

    Abstract: Methods, systems, and apparatus, including medium-encoded computer program products, for computer aided design of physical structures include: obtaining a density-based representation of a modeled object, the density-based representation comprising multiple different subsets of elements, each subset having a starting element at a milling depth, which is one of three or more milling depths for three or more corresponding discrete layers that are each perpendicular to a milling direction for the modeled object; and reassigning milling depths of at least a portion of the multiple different subsets of elements, the reassigning for a current starting element in a current layer for an element subset comprising moving the milling depth for the element subset of the current starting element when an angular difference between other starting elements, which are associated with the current starting element and are located in a different layer, meets or exceeds a threshold value.

    GENERATING STYLES FOR NEURAL STYLE TRANSFER IN THREE-DIMENSIONAL SHAPES

    公开(公告)号:US20230326159A1

    公开(公告)日:2023-10-12

    申请号:US18149609

    申请日:2023-01-03

    Applicant: AUTODESK, INC.

    Abstract: One embodiment of the present invention sets forth a technique for performing style transfer. The technique includes determining a distribution associated with a plurality of style codes for a plurality of three-dimensional (3D) shapes, where each style code included in the plurality of style codes represents a difference between a first 3D shape and a second 3D shape, and where the second 3D shape is generated by applying one or more augmentations to the first 3D shape. The technique also includes sampling from the distribution to generate an additional style code and executing a trained machine learning model based on the additional style code to generate an output 3D shape having style-based attributes associated with the additional style code and content-based attributes associated with an object. The technique further includes generating a 3D model of the object based on the output 3D shape.

    MONETARY VULNERABILITY ASSESSMENT (MVA)  OF A REPARABLE INFRASTRUCTURE SYSTEM

    公开(公告)号:US20230318920A1

    公开(公告)日:2023-10-05

    申请号:US17708971

    申请日:2022-03-30

    Applicant: Autodesk, Inc.

    Inventor: Junje Ro

    CPC classification number: H04L41/0836 H04L41/142 H04L41/145 H04L41/0826

    Abstract: A method and system provide the ability to estimate the vulnerability of a repairable infrastructure system. A survival curve is constructed for one or more assets. A rehabilitation plan is prescribed for one or more failure states of the repairable infrastructure system. A cost estimation model is constructed for costs associated with the repairs for each of the failure states. A planning basis is specified. A multiple probability simulation is conducted that estimates a potential restoration cost for a possible failure. The simulation is repeated to acquire a distribution of potential restoration costs. A vulnerability estimation is determined and provided based on the distribution.

Patent Agency Ranking