COMPUTER-IMPLEMENTED METHOD FOR MAKING A SKELETON OF A MODELED BODY TAKE A POSTURE

    公开(公告)号:US20210118241A1

    公开(公告)日:2021-04-22

    申请号:US17070875

    申请日:2020-10-14

    Abstract: A computer-implemented method for making a skeleton of a modeled human or animal body take a posture, including obtaining a first and a second skeleton each comprising rotational joints connected by bones, each rotational joint of the second skeleton being associated to a respective joint of the first skeleton, determining a relative configuration of the second skeleton, mapping each joint of the first skeleton to a joint of the second skeleton, making the first skeleton take a posture defined by a rotational state for each joint of the first skeleton, and computing transformation matrices for the joints of the second skeleton such that a change is minimized, said second skeleton further including a prismatic joint on at least one of its bones, and determining rotations of the rotational joints and translation of the prismatic joint or joints of the second skeleton such that change is minimized.

    Method and Apparatus for Automatic Underhood Thermal Modeling

    公开(公告)号:US20210117597A1

    公开(公告)日:2021-04-22

    申请号:US17011088

    申请日:2020-09-03

    Abstract: Computer-implemented techniques for simulating underhood conditions for a vehicle and the like are disclosed. The computer-implemented techniques include receiving by a computer processing system digital data of a three dimensional representation of modeling of a fluid source, a fluid sink, and plural fluid nodes, executing a transient thermal model that includes an underhood fluid model, and performing a simulation to simulate fluid flow from the fluid source to the fluid sink through each of the plural fluid nodes.

    Graphical user interface tool for orienting computer-aided design model

    公开(公告)号:US10984606B1

    公开(公告)日:2021-04-20

    申请号:US16014922

    申请日:2018-06-21

    Abstract: A change in orientation or reorientation operation is applied to 3D models while maintaining constant zoom level of model display. The orientation is provided by a computer-based tool or GUI widget formed of a transparent container element and a miniaturized depiction of the 3D model. The transparent container element encapsulates the miniaturized depiction and enables see through view of the miniaturized depiction illustrating real time orientation of the 3D model. The container element is user-interactive to effect change in orientation of the 3D model concurrently displayed in a work area of a screen view. The zoom level of the displayed 3D model in the work area remains constant avoiding or omitting zoom to extents throughout user interaction with the GUI widget.

    Dataset for learning a function taking images as inputs

    公开(公告)号:US10984317B2

    公开(公告)日:2021-04-20

    申请号:US16011359

    申请日:2018-06-18

    Abstract: The disclosure notably relates to a computer-implemented method for forming a dataset. The dataset is configured for learning a function. The function takes as inputs images of instances of one or more classes of real objects. The method comprises, for each class, providing a parametric model of the class, generating a plurality of 3D modeled objects with the parametric model, and adding to the dataset, for each one of the plurality of 3D modeled objects, one or more corresponding images. The generating includes traversing one or more of the set of ranges. The method constitutes an improved solution for forming a dataset configured for learning a function.

    SYSTEM AND METHOD FOR CRASHWORTHINESS ANALYTICS IN DESIGN

    公开(公告)号:US20210081512A1

    公开(公告)日:2021-03-18

    申请号:US16573729

    申请日:2019-09-17

    Abstract: A computer-aided design system includes a display device, a memory storing a plurality of response surface models, and a processor configured to: (a) display a graphical user interface that includes a model of a vehicle frame; (b) display a section configuration panel that includes one or more section dimension values for one or more section dimensions of a first section member of the plurality of section members; (c) retrieve a first response surface model based on values of the one or more section dimensions for the first section member; (d) determine one or more predicted values associated with the first section member based on the values of the section dimensions, the predicted values include one or more predicted crash resistances for the section member; and (e) display the predicted values, thereby allowing the user to evaluate the predicted values for suitability in vehicle design.

    FORMING A DATASET FOR FULLY-SUPERVISED LEARNING

    公开(公告)号:US20210049420A1

    公开(公告)日:2021-02-18

    申请号:US17086078

    申请日:2020-10-30

    Abstract: A computer-implemented method of signal processing comprises providing images. The method comprises for each respective one of at least a subset of the images: applying a weakly-supervised learnt function, the weakly-supervised learnt function outputting respective couples each including a respective localization and one or more respective confidence scores, each confidence score representing a probability of instantiation of a respective object category at the respective localization. The method further comprises determining, based on the output of the weakly-supervised learnt function, one or more respective annotations, each annotation including a respective localization and a respective label representing instantiation a respective object category at the respective localization. The method further comprises forming a dataset including pieces of data, each piece of data including a respective image of the subset and at least a part of the one or more annotations determined for the respective image. This improves the field of object detection.

    Structural optimization of additively manufactured parts accounting for manufacturing-induced states

    公开(公告)号:US10915675B2

    公开(公告)日:2021-02-09

    申请号:US15661726

    申请日:2017-07-27

    Abstract: An example embodiment designs a real-world object by defining a first model of the object being produced using an additive manufacturing (AM) process, where behavior of the object being produced is given by a first equation which includes a first plurality of corresponding sensitivity equations for a first plurality of design variables. Similarly, such an embodiment defines a second model of the object after being produced, wherein behavior of the object after being produced is given by a second equation which includes a second plurality of corresponding sensitivity equations for a second plurality of design variables. In turn, the second model is iteratively optimized with respect to a given one of the second plurality of design variables using both the first plurality of corresponding sensitivity equations and the second plurality of corresponding sensitivity equations.

Patent Agency Ranking