Patents by Inventor Erva ULU

Erva ULU has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Patent number: 11361130
    Abstract: A three-dimensional object model is divided into a plurality of slices that are targeted for an additive manufacturing process having a minimum printable feature size. For each of the slices, a thinning algorithm is applied to one or more contours of the slice to form a meso-skeleton, where topological features of the thinned slice that are smaller than the minimum printable feature size are reduced to skeletal paths. A corrected slice is formed using the meso-skeleton by sweeping the meso-skeleton with the minimum printable feature size. The corrected slices are assembled into a corrected object model and the corrected object model is used in the additive manufacturing process.
    Type: Grant
    Filed: December 16, 2019
    Date of Patent: June 14, 2022
    Assignee: Palo Alto Research Center Incorporated
    Inventors: Erva Ulu, Nurcan Gecer Ulu, Walter Hsiao, Saigopal Nelaturi
  • Publication number: 20210286910
    Abstract: A method for producing a design includes receiving a set of design constraints. A spatial field is created based on the design constraints. The spatial field is represented with a linear combination of one or more bases. A number of the one or more bases is less than a number of elements in the spatial field. Respective weights are optimized for each of the one or more bases. A design is produced based on the spatial field and the weights.
    Type: Application
    Filed: March 13, 2020
    Publication date: September 16, 2021
    Inventors: Nurcan Gecer Ulu, Svyatoslav Korneev, Saigopal Nelaturi, Erva Ulu
  • Publication number: 20210039312
    Abstract: A three-dimensional object model is divided into a plurality of slices that are targeted for an additive manufacturing process having a minimum printable feature size. For each of the slices, a thinning algorithm is applied to one or more contours of the slice to form a meso-skeleton, where topological features of the thinned slice that are smaller than the minimum printable feature size are reduced to skeletal paths. A corrected slice is formed using the meso-skeleton by sweeping the meso-skeleton with the minimum printable feature size. The corrected slices are assembled into a corrected object model and the corrected object model is used in the additive manufacturing process.
    Type: Application
    Filed: December 16, 2019
    Publication date: February 11, 2021
    Inventors: Erva Ulu, Nurcan Gecer Ulu, Walter Hsiao, Saigopal Nelaturi
  • Publication number: 20210042455
    Abstract: A three-dimensional object model is divided into slices that are targeted for an additive manufacturing process operable to deposit material at a variable deposition size ranging between minimum and maximum printable feature sizes, For each of the slices, a thinning algorithm is applied to contours of the slice to form a meso-skeleton. Topological features of the thinned slice are reduced over a number of passes such that a portion of the meso-skeleton is reduced to a single pixel wide line. Based on the number of passes, a slice-specific printable feature size within the range of the minimum and maximum printable feature sizes is determined. An adjusted slice is formed by sweeping the meso-skeleton with the slice-specific printable feature size. The adjusted slices are assembled into an object model which is used to create a manufactured object.
    Type: Application
    Filed: December 16, 2019
    Publication date: February 11, 2021
    Inventors: Erva Ulu, Nurcan Gecer Ulu, Walter Hsiao, Saigopal Nelaturi
  • Publication number: 20200019142
    Abstract: Systems and methods may support build direction-based partitioning for construction of a physical object through additive manufacturing. In some implementations, a system may access a surface mesh representative of a 3D object and an initial build direction for construction of the object using additive manufacturing. The system may partition the surface mesh into an initial buildable segment and a non-buildable segment based on the initial build direction. The system may iteratively determine subsequent build directions and partition off subsequent buildable segments from the unbuildable segment until no portion of the non-buildable segment remains. The determined buildable segments and correlated build directions may be provided to a multi-axis 3D printer for construction of the represented 3D object through additive manufacturing.
    Type: Application
    Filed: March 30, 2018
    Publication date: January 16, 2020
    Inventors: Erva Ulu, Erhan Arisoy, Suraj Ravi Musuvathy, David Madeley, Nurcan Gecer Ulu
  • Publication number: 20190026537
    Abstract: A computer-implemented method of predicting hand positions for multi-handed grasps of objects includes receiving a plurality of three-dimensional models and for each three-dimensional model, receiving user data comprising (i) user-provided grasping point pairs and (ii) labelling data indicating whether a particular grasping point pair is suitable or unsuitable for grasping. For each three-dimensional model, geometrical features related to object grasping are extracted based on the user data corresponding to the three-dimensional model. A machine learning model is trained to correlate the geometrical features with the labelling data associated with each corresponding grasping point pair and candidate grasping point pairs are determined for a new three-dimensional model. The machine learning model may then be used to select a subset of the plurality of candidate grasping point pairs as natural grasping points of the three-dimensional model.
    Type: Application
    Filed: January 24, 2017
    Publication date: January 24, 2019
    Applicant: Siemens Product Lifecycle Management Software Inc.
    Inventors: Erhan ARISOY, Suraj Ravi MUSUVATHY, Erva ULU, Nurcan Gecer ULU