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

    公开(公告)号:US11468292B2

    公开(公告)日:2022-10-11

    申请号:US16362555

    申请日:2019-03-22

    Applicant: AUTODESK, INC.

    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.

    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.

    Techniques for generating comprehensive information models for automobile designs

    公开(公告)号:US11775709B2

    公开(公告)日:2023-10-03

    申请号:US16387526

    申请日:2019-04-17

    Applicant: AUTODESK, INC.

    CPC classification number: G06F30/23 G06F30/15 G06T19/00 G06T2210/36

    Abstract: In various embodiments, an automobile modeling application generates automobile designs. In operation, the automobile modeling application determines a first parameter value associated with a first instance of a first parameterized automobile component. The automobile modeling application then computes a second parameter value associated with a second instance of a second parameterized automobile component based on a structural relationship between the first instance and the second instance. Subsequently, the automobile modeling application generates a computer-aided design (CAD) geometry model for an automobile based on the first parameter value, the second parameter value, and one or more functional relationships defined between two or more instances included in a set of parameterized automobile component instances. Advantageously, because the automobile modeling application automatically propagates changes throughout the automobile design, the amount of time required to make significant changes to the automobile design can be substantially reduced.

Patent Agency Ranking