Patents by Inventor Miguel Sainz

Miguel Sainz 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).

  • Publication number: 20210224556
    Abstract: In various examples, sensor data representative of an image of a field of view of a vehicle sensor may be received and the sensor data may be applied to a machine learning model. The machine learning model may compute a segmentation mask representative of portions of the image corresponding to lane markings of the driving surface of the vehicle. Analysis of the segmentation mask may be performed to determine lane marking types, and lane boundaries may be generated by performing curve fitting on the lane markings corresponding to each of the lane marking types. The data representative of the lane boundaries may then be sent to a component of the vehicle for use in navigating the vehicle through the driving surface.
    Type: Application
    Filed: April 5, 2021
    Publication date: July 22, 2021
    Inventors: Yifang Xu, Xin Liu, Chia-Chih Chen, Carolina Parada, Davide Onofrio, Minwoo Park, Mehdi Sajjadi Mohammadabadi, Vijay Chintalapudi, Ozan Tonkal, John Zedlewski, Pekka Janis, Jan Nikolaus Fritsch, Gordon Grigor, Zuoguan Wang, I-Kuei Chen, Miguel Sainz
  • Patent number: 10997435
    Abstract: In various examples, object fence corresponding to objects detected by an ego-vehicle may be used to determine overlap of the object fences with lanes on a driving surface. A lane mask may be generated corresponding to the lanes on the driving surface, and the object fences may be compared to the lanes of the lane mask to determine the overlap. Where an object fence is located in more than one lane, a boundary scoring approach may be used to determine a ratio of overlap of the boundary fence, and thus the object, with each of the lanes. The overlap with one or more lanes for each object may be used to determine lane assignments for the objects, and the lane assignments may be used by the ego-vehicle to determine a path or trajectory along the driving surface.
    Type: Grant
    Filed: August 8, 2019
    Date of Patent: May 4, 2021
    Assignee: NVIDIA Corporation
    Inventors: Josh Abbott, Miguel Sainz Serra, Zhaoting Ye, David Nister
  • Patent number: 10997433
    Abstract: In various examples, sensor data representative of an image of a field of view of a vehicle sensor may be received and the sensor data may be applied to a machine learning model. The machine learning model may compute a segmentation mask representative of portions of the image corresponding to lane markings of the driving surface of the vehicle. Analysis of the segmentation mask may be performed to determine lane marking types, and lane boundaries may be generated by performing curve fitting on the lane markings corresponding to each of the lane marking types. The data representative of the lane boundaries may then be sent to a component of the vehicle for use in navigating the vehicle through the driving surface.
    Type: Grant
    Filed: February 26, 2019
    Date of Patent: May 4, 2021
    Assignee: NVIDIA Corporation
    Inventors: Yifang Xu, Xin Liu, Chia-Chih Chen, Carolina Parada, Davide Onofrio, Minwoo Park, Mehdi Sajjadi Mohammadabadi, Vijay Chintalapudi, Ozan Tonkal, John Zedlewski, Pekka Janis, Jan Nikolaus Fritsch, Gordon Grigor, Zuoguan Wang, I-Kuei Chen, Miguel Sainz
  • Publication number: 20210042535
    Abstract: In various examples, object fence corresponding to objects detected by an ego-vehicle may be used to determine overlap of the object fences with lanes on a driving surface. A lane mask may be generated corresponding to the lanes on the driving surface, and the object fences may be compared to the lanes of the lane mask to determine the overlap. Where an object fence is located in more than one lane, a boundary scoring approach may be used to determine a ratio of overlap of the boundary fence, and thus the object, with each of the lanes. The overlap with one or more lanes for each object may be used to determine lane assignments for the objects, and the lane assignments may be used by the ego-vehicle to determine a path or trajectory along the driving surface.
    Type: Application
    Filed: August 8, 2019
    Publication date: February 11, 2021
    Inventors: Josh Abbott, Miguel Sainz Serra, Zhaoting Ye, David Nister
  • Publication number: 20190266418
    Abstract: In various examples, sensor data representative of an image of a field of view of a vehicle sensor may be received and the sensor data may be applied to a machine learning model. The machine learning model may compute a segmentation mask representative of portions of the image corresponding to lane markings of the driving surface of the vehicle. Analysis of the segmentation mask may be performed to determine lane marking types, and lane boundaries may be generated by performing curve fitting on the lane markings corresponding to each of the lane marking types. The data representative of the lane boundaries may then be sent to a component of the vehicle for use in navigating the vehicle through the driving surface.
    Type: Application
    Filed: February 26, 2019
    Publication date: August 29, 2019
    Inventors: Yifang Xu, Xin Liu, Chia-Chih Chen, Carolina Parada, Davide Onofrio, Minwoo Park, Mehdi Sajjadi Mohammadabadi, Vijay Chintalapudi, Ozan Tonkal, John Zedlewski, Pekka Janis, Jan Nikolaus Fritsch, Gordon Grigor, Zuoguan Wang, I-Kuei Chen, Miguel Sainz
  • Publication number: 20190265703
    Abstract: A system and method for an on-demand shuttle, bus, or taxi service able to operate on private and public roads provides situational awareness and confidence displays. The shuttle may include ISO 26262 Level 4 or Level 5 functionality and can vary the route dynamically on-demand, and/or follow a predefined route or virtual rail. The shuttle is able to stop at any predetermined station along the route. The system allows passengers to request rides and interact with the system via a variety of interfaces, including without limitation a mobile device, desktop computer, or kiosks. Each shuttle preferably includes an in-vehicle controller, which preferably is an AI Supercomputer designed and optimized for autonomous vehicle functionality, with computer vision, deep learning, and real time ray tracing accelerators. An AI Dispatcher performs AI simulations to optimize system performance according to operator-specified system parameters.
    Type: Application
    Filed: February 26, 2019
    Publication date: August 29, 2019
    Inventors: Gary HICOK, Michael COX, Miguel SAINZ, Martin HEMPEL, Ratin KUMAR, Timo ROMAN, Gordon GRIGOR, David NISTER, Justin EBERT, Chin SHIH, Tony TAM, Ruchi BHARGAVA
  • Patent number: 8947430
    Abstract: A method for rendering a particle-based fluid surface includes generating a depth image of a plurality of particles which form a fluid surface, and smoothing the depth image to generate a smoothed depth image. From the smoothed depth image, a smoothed surface position and a smoothed surface normal for each of a plurality of pixels included within the smoothed depth image is determined, and a shaded surface of the fluid is rendered as a function of the smoothed surface positions and the smoothed surface normals.
    Type: Grant
    Filed: February 26, 2010
    Date of Patent: February 3, 2015
    Assignee: NVIDIA Corporation
    Inventors: Simon Green, Miguel Sainz, Wladimir Van Der Laan
  • Publication number: 20140368505
    Abstract: A graphics processing subsystem for recovering projection parameters for rendering effects and a method of use thereof. One embodiment of the graphics processing subsystem includes: (1) a memory configured to store a buffer having a plurality of constants determinable upon execution of an application for which a scene is rendered, and (2) a central processing unit (CPU) operable to determine projection parameters from the buffer according to shader-reflection metadata attached to a programmable shader submitted for execution, and employ the projection parameters to cause an effect to be rendered on the scene by a graphics processing unit (GPU).
    Type: Application
    Filed: June 13, 2013
    Publication date: December 18, 2014
    Inventors: Louis Bavoil, Miguel Sainz, Byungmoon Kim
  • Patent number: 8878849
    Abstract: The method includes receiving a plurality of graphics primitives for rendering at a GPU of a computer system and rendering graphics primitives into pixel parameters of the pixels of a display, wherein the parameters include pixel depth values and pixel normal values. For each pixel of the display, an ambient occlusion process is performed. The algorithm takes as input a ND-buffer containing pixel depth values and pixel normals. Based on the pixel 3-D position and the pixel normal vector, horizon heights are computed by sampling the ND-buffer and an occlusion term is computed for each pixel based on the horizon heights. Based on the pixel 3-D position, the pixel normal vector, a normal occlusion term is computed by sampling the ND-buffer above the horizon in multiple directions. An ambient occlusion illumination value is computed by combining the horizon occlusion term and the normal occlusion term.
    Type: Grant
    Filed: December 14, 2007
    Date of Patent: November 4, 2014
    Assignee: Nvidia Corporation
    Inventors: Rouslan Dimitrov, Louis Bavoil, Miguel Sainz
  • Publication number: 20140160124
    Abstract: A visible polygon data structure and method of use thereof. One embodiment of the visible polygon data structure includes: (1) a memory configured to store a data structure containing vertices of at least partially visible polygons of the scene but lacking vertices of at least some wholly invisible polygons of the scene, and (2) a graphics processing unit (GPU) configured to employ the vertices of the at least partially visible polygons to approximate an ambient occlusive effect on a point in the scene, the effect being independent of the wholly invisible polygons.
    Type: Application
    Filed: December 12, 2012
    Publication date: June 12, 2014
    Applicant: NVIDIA CORPORATION
    Inventors: Louis Bavoil, Miguel Sainz
  • Publication number: 20090153557
    Abstract: The method includes receiving a plurality of graphics primitives for rendering at a GPU of a computer system and rendering graphics primitives into pixel parameters of the pixels of a display, wherein the parameters include pixel depth values and pixel normal values. For each pixel of the display, an ambient occlusion process is performed. The algorithm takes as input a ND-buffer containing pixel depth values and pixel normals. Based on the pixel 3-D position and the pixel normal vector, horizon heights are computed by sampling the ND-buffer and an occlusion term is computed for each pixel based on the horizon heights. Based on the pixel 3-D position, the pixel normal vector, a normal occlusion term is computed by sampling the ND-buffer above the horizon in multiple directions. An ambient occlusion illumination value is computed by combining the horizon occlusion term and the normal occlusion term.
    Type: Application
    Filed: December 14, 2007
    Publication date: June 18, 2009
    Inventors: Rouslan Dimitrov, Louis Bavoil, Miguel Sainz