AUTOMATIC DESIGN OF MECHANICAL ASSEMBLIES USING ESTIMATION OF DISTRIBUTION ALGORITHM

    公开(公告)号:US20200334337A1

    公开(公告)日:2020-10-22

    申请号:US16434085

    申请日:2019-06-06

    Applicant: AUTODESK, INC.

    Abstract: A design engine implements a probabilistic approach to generating designs for computer-aided design (CAD) assemblies. The design engine initially generates a population of designs based on a problem definition associated with a design problem. Each design includes a randomly-generated set of design values assigned to various design variables. The design engine repairs any infeasible designs in the population of designs and then executes a dynamic simulation with the population of designs. The design engine selects the most performant designs and identifies, based on those performant designs, design variables that are dependent on one another. The design engine generates a probability model indicating conditional probabilities between design values associated with dependent design variables. The design engine then iteratively samples the probability model to generate a subsequent population of designs. In this manner, the design engine can automatically generate designs for mechanical assemblies significantly faster than possible with conventional algorithmic design techniques.

    HYBRID STRUCTURAL-GEOMETRIC TECHNIQUE FOR PERFORMING DRAPING SIMULATION OF WOVEN FABRIC COMPOSITES

    公开(公告)号:US20190259192A1

    公开(公告)日:2019-08-22

    申请号:US15953351

    申请日:2018-04-13

    Applicant: AUTODESK, INC.

    Abstract: One embodiment of the present invention sets forth a technique for performing a draping simulation of a fabric that includes obtaining a problem definition that includes a fabric cell size, a spring constant ratio, and a three-dimensional (3D) surface. The technique also includes representing the fabric as a set of fabric cells with dimensions that adhere to the fabric cell size, modeling the fabric cells based on a set of side springs and a set of diagonal springs, and setting a first spring constant of the side springs and a second spring constant of the diagonal springs based on the spring constant ratio. The technique further includes propagating the fabric cells along the 3D surface according to the fabric cell size, the first spring constant, and the second spring constant to generate a result of the draping simulation.

    CONSTRAINT-ORIENTED PROGRAMMING APPROACH TO MECHANICAL ASSEMBLY DESIGN

    公开(公告)号:US20190213300A1

    公开(公告)日:2019-07-11

    申请号:US15866398

    申请日:2018-01-09

    Applicant: AUTODESK, INC.

    CPC classification number: G06F17/5086 G06F17/5095 G06F2217/06

    Abstract: A design engine systematically explores a design space associated with a design problem related to mechanical assemblies. The design engine implements a constraint programming approach to produce mechanical assembly configurations that adhere to a set of design constraints. For each feasible configuration, the design engine then optimizes various parameters to generate design options that meet a set of design objectives. With these techniques, the design space can be explored very quickly to generate significantly more feasible design options for the mechanical assembly than possible with conventional manual approaches. Accordingly, numerous design options can be generated that may otherwise never be produced using those conventional approaches.

    GENERATIVE DESIGN TECHNIQUES FOR SOFT ROBOT MANIPULATORS

    公开(公告)号:US20220108046A1

    公开(公告)日:2022-04-07

    申请号:US17344710

    申请日:2021-06-10

    Applicant: AUTODESK, INC.

    Abstract: A computer-implemented method for generating a design for a continuum robot includes: generating a first plurality of candidate designs for the continuum robot, wherein each candidate design included in the first plurality of candidate designs is based on a first set of values for a set of design parameters; determining a first performance value for each candidate design included in the first plurality of candidate designs; based at least in part on the first performance values, selecting a subset of candidate designs from the first plurality of candidate designs; and based on the subset of candidate designs, generating a second plurality of candidate designs for the continuum robot, wherein each candidate design included in the second plurality of candidate designs is based on a second set of values for the set of design parameters.

    SINGULARITY-FREE KINEMATIC PARAMETERIZATION OF SOFT ROBOT MANIPULATORS

    公开(公告)号:US20220105627A1

    公开(公告)日:2022-04-07

    申请号:US17319502

    申请日:2021-05-13

    Applicant: AUTODESK, INC.

    Abstract: A computer-implemented method for controlling a robot, the method comprising: determining a first value for a first joint parameter associated with a first continuum joint included in the robot and a first value for a second joint parameter associated with the first continuum joint, wherein the first joint parameter indicates a bending radius of a flexible portion of the continuum joint, and the second joint parameter indicates a rotation of the flexible portion of the continuum joint with respect to a base portion of the first continuum joint; and positioning an end portion of the robot at a final target location based on the first value of the first joint parameter and the first value of the second joint parameter.

    TECHNIQUES FOR DESIGNING STRUCTURES USING TORSION-DEFORMABLE SPATIAL BEAM ELEMENTS

    公开(公告)号:US20220083702A1

    公开(公告)日:2022-03-17

    申请号:US16950669

    申请日:2020-11-17

    Applicant: AUTODESK, INC.

    Abstract: Techniques are disclosed for designing structures using a torsion-deformable spatial beam element. The beam element can be represented using the absolute nodal coordinate formulation, or any other technically feasible formulation. At each of one or more time steps, the Bishop frame is used to generate local coordinate systems along a center line of the beam element, which are used to compute a potential energy of the beam element. Thereafter, a derivative of the potential energy is plugged into equations of motion that are solved to determine an updated state of the beam element. A representation of the updated beam element can also be rendered and displayed via a graphical user interface.

    EFFICIENT SENSITIVITY ANALYSIS FOR GENERATIVE PARAMETRIC DESIGN OF DYNAMIC MECHANICAL ASSEMBLIES

    公开(公告)号:US20190286786A1

    公开(公告)日:2019-09-19

    申请号:US15924138

    申请日:2018-03-16

    Applicant: AUTODESK, INC.

    Abstract: A design engine generates a configuration option that includes a specific arrangement of interconnected mechanical elements adhering to one or more design constraints. Each element within a given configuration option is defined by a set of design variables. The design engine implements a parametric optimizer to optimize the set of design variables associated with each configuration option. For a given configuration option, the parametric optimizer discretizes continuous equations governing the physical dynamics of the configuration. The parametric optimizer then determines the gradient of an objective function based on the discretized equations the gradient of objective and constraint functions based on discrete direct differentiation method or discrete adjoint variable method derived directly from the discretized motion equations. Then, the parametric optimizer traverses a design space where the configuration option resides to reduce improve the objective function, thereby optimizing the design variables.

Patent Agency Ranking