Patents by Inventor Fabio Tozeto Ramos

Fabio Tozeto Ramos 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: 20240037367
    Abstract: Apparatuses, systems, and techniques to infer a sequence of actions to perform using one or more neural networks trained, at least in part, by optimizing a probability distribution function using a cost function, wherein the probability distribution represents different sequences of actions that can be performed. In at least one embodiment, a model predictive control problem is formulated as a Bayesian inference task to infer a set of solutions.
    Type: Application
    Filed: April 12, 2023
    Publication date: February 1, 2024
    Inventors: Alexander Conrad Lambert, Adam Harper Fishman, Dieter Fox, Byron Boots, Fabio Tozeto Ramos
  • Publication number: 20230405820
    Abstract: Apparatuses, systems, and techniques to generate a predicted outcome of an object resulting from a robotic component applying a force. In at least one embodiment, a predicted outcome of an object resulting from a robotic component applying a force is generated based on, for example, a neural network.
    Type: Application
    Filed: June 12, 2023
    Publication date: December 21, 2023
    Inventors: Isabella Huang, Yashraj Narang, Tucker Ryer Hermans, Fabio Tozeto Ramos, Ankur Handa, Miles Andrew Macklin, Dieter Fox
  • Publication number: 20230398686
    Abstract: Apparatuses, systems, and techniques to update a machine learning model associated with an object. In at least one embodiment, the machine learning model is updated based at least in part on, for example, one or more distributions associated with the machine learning model.
    Type: Application
    Filed: February 24, 2023
    Publication date: December 14, 2023
    Inventors: Fabio Tozeto Ramos, Animesh Garg, Krishna Murthy Jatavallabhula, Miles Macklin
  • Publication number: 20230169329
    Abstract: Systems and methods related to incorporating uncertain inputs into a neural network are described herein. A distribution is obtained and processed by a Reproducing Kernel Hilbert Space (RKHS) module to generate an embedding that represents the distribution. The features of the embedding may correspond to a number of Random Fourier Features (RFFs). The embedding can be added to additional features to form an aggregate input for the neural network. The neural network then processes the aggregate input to generate an output based on, at least in part, the embedding of the distribution. In some embodiments, a simulation can be run to generate a distribution for a feature, where each simulator instance generates a different sample for the feature over a plurality of time steps of the simulation. In some embodiments, the output neural network can be used to control robotic systems, vehicles, or other systems.
    Type: Application
    Filed: December 1, 2021
    Publication date: June 1, 2023
    Inventors: Fabio Tozeto Ramos, Rika Antonova, Ankur Handa, Dieter Fox
  • Patent number: 11645492
    Abstract: Apparatuses, systems, and techniques to infer a sequence of actions to perform using one or more neural networks trained, at least in part, by optimizing a probability distribution function using a cost function, wherein the probability distribution represents different sequences of actions that can be performed. In at least one embodiment, a model predictive control problem is formulated as a Bayesian inference task to infer a set of solutions.
    Type: Grant
    Filed: April 28, 2020
    Date of Patent: May 9, 2023
    Assignee: NVIDIA Corporation
    Inventors: Alexander Conrad Lambert, Adam Harper Fishman, Dieter Fox, Byron Boots, Fabio Tozeto Ramos
  • Publication number: 20220383019
    Abstract: Apparatuses, systems, and techniques generate poses of an object based on image data of the object obtained from a first viewpoint of the object and a second viewpoint of the object. The poses can be evaluated to determine a portion of the image data usable by an estimator to generate a pose of the object.
    Type: Application
    Filed: May 26, 2021
    Publication date: December 1, 2022
    Inventors: Jonathan Tremblay, Fabio Tozeto Ramos, Yuke Zhu, Anima Anandkumar, Guanya Shi
  • Publication number: 20220379484
    Abstract: Apparatuses, systems, and techniques generate poses of an object based on data of the object observed from a first viewpoint and a second viewpoint. The poses can be evaluated to determine a portion of the data usable by an estimator to generate a pose of the object.
    Type: Application
    Filed: May 26, 2021
    Publication date: December 1, 2022
    Inventors: Jonathan Tremblay, Fabio Tozeto Ramos, Yuke Zhu, Anima Anandkumar, Guanya Shi
  • Publication number: 20220382246
    Abstract: A differentiable simulator for simulating the cutting of soft materials by a cutting instrument is provided. In accordance with one aspect of the disclosure, a method for simulating a cutting operation includes: receiving a mesh for an object, modifying the mesh to add virtual nodes associated with a predefined cutting plane, optimizing a set of parameters associated with a simulator based on ground-truth data, and running a simulation via the simulator to generate outputs that include trajectories associated with a cutting instrument. Optimizing the set of parameters can include performing inference based on a set of ground-truth trajectories captured using sensors to measure real-world cutting operations. The inference techniques can employ stochastic gradient descent, stochastic gradient Langevin dynamics, or a Bayesian approach. In an embodiment, the simulator can be utilized to generate control signals for a robot based on the simulated trajectories.
    Type: Application
    Filed: April 28, 2022
    Publication date: December 1, 2022
    Inventors: Eric Heiden, Fabio Tozeto Ramos, Yashraj Narang, Miles Macklin, Dieter Fox, Animesh Garg, Mike Skolones
  • Publication number: 20220055689
    Abstract: A framework for offline learning from a set of diverse and suboptimal demonstrations operates by selectively imitating local sequences from the dataset. At least one embodiment recovers performant policies from large manipulation datasets by decomposing the problem into a goal-conditioned imitation and a high-level goal selection mechanism.
    Type: Application
    Filed: August 20, 2020
    Publication date: February 24, 2022
    Inventors: Ajay Uday Mandlekar, Fabio Tozeto Ramos, Byron Boots, Animesh Garg, Dieter Fox
  • Publication number: 20210334630
    Abstract: Apparatuses, systems, and techniques to infer a sequence of actions to perform using one or more neural networks trained, at least in part, by optimizing a probability distribution function using a cost function, wherein the probability distribution represents different sequences of actions that can be performed. In at least one embodiment, a model predictive control problem is formulated as a Bayesian inference task to infer a set of solutions.
    Type: Application
    Filed: April 28, 2020
    Publication date: October 28, 2021
    Inventors: Alexander Conrad Lambert, Adam Harper Fishman, Dieter Fox, Byron Boots, Fabio Tozeto Ramos
  • Publication number: 20210327584
    Abstract: A method for cluster-based recommendation generation regarding sleep disorders. A server system transmitting query program code to a client device, wherein the query program code is executable by the client device to transmit one or more response objects encoding a response and further responses to the server system. The server system receiving the one or more response objects from the client device and determining the response and further responses encoded in the response objects. A clustering module of the server system identifying one or more clusters of sleep disorder user data that most closely relate to the determined responses. A recommendation module of the server system identifying a sleep disorder based on the determined responses and clusters. The recommendation module generating one or more recommendations based on the identified sleep disorder, the determined responses and the identified clusters.
    Type: Application
    Filed: October 22, 2019
    Publication date: October 21, 2021
    Inventors: Andrew VAKULIN, Peter Guthrie CATCHESIDE, Nicole LOVATO, Ronald Douglas MCEVOY, Angus Keith WALLACE, Karen Jane SMALL, Bryn JEFFRIES, Fabio Tozeto RAMOS, Christopher GORDON, Tracey Leanne SLETTEN, Leon Colburn LACK, Greg Nelson GARCIA MOLINA, Yash Parag MOKASHI, Jesse SALAZAR, Monica H BUSH, Kousalya RONDINELLI, Jenna M. SCHABDACH, Craig OAKS
  • Publication number: 20210146531
    Abstract: A robot is controlled using a combination of model-based and model-free control methods. In some examples, the model-based method uses a physical model of the environment around the robot to guide the robot. The physical model is oriented using a perception system such as a camera. Characteristics of the perception system may be are used to determine an uncertainty for the model. Based at least in part on this uncertainty, the system transitions from the model-based method to a model-free method where, in some embodiments, information provided directly from the perception system is used to direct the robot without reliance on the physical model.
    Type: Application
    Filed: February 3, 2020
    Publication date: May 20, 2021
    Inventors: Jonathan Tremblay, Dieter Fox, Michelle Lee, Carlos Florensa, Nathan Donald Ratliff, Animesh Garg, Fabio Tozeto Ramos
  • Publication number: 20210110089
    Abstract: Apparatuses, systems, and techniques to identify at least one physical characteristic of materials from computer simulations of manipulations of materials. In at least one embodiment, physical characteristics are determined by comparing measured statistics of observed manipulations to simulations of manipulations using a simulator trained with a likelihood-free inference engine.
    Type: Application
    Filed: June 29, 2020
    Publication date: April 15, 2021
    Inventors: Carolyn Linjon Chen, Yashraj Shyam Narang, Fabio Tozeto Ramos, Dieter Fox
  • Publication number: 20200368906
    Abstract: In an embodiment, a system calculates a distribution of possible parameters for a simulation that cause the simulation to match a measured behavior in the real world. In an embodiment, the system selects a plurality of simulation parameters based on a statistical distribution that represents an initial estimate of possible parameter values. In an embodiment, using the results produced by the simulation, an updated distribution of possible parameters is constructed based on a density of the results modeled using Fourier features. In an embodiment, the updated distribution of possible parameters can be used to select a particular set of parameters for the simulation, which cause the simulator approximate the measured behavior.
    Type: Application
    Filed: May 20, 2019
    Publication date: November 26, 2020
    Inventors: Fabio Tozeto Ramos, Dieter Fox
  • Patent number: 9297256
    Abstract: Methods and systems are described for generating a data representation of a geographical region as an adjunct to conducting autonomous operations within the region. The method comprises receiving information specifying a plurality of localized caused zones having operation-defined geographical boundaries within the region; receiving heterogeneous data descriptive of the region; associating the received data with respective localized zones; fusing the received data associated with the localized zones into data representations of the localized zones; and integrating the data representations of the localized zones into a common data representation of the geographical region.
    Type: Grant
    Filed: April 30, 2010
    Date of Patent: March 29, 2016
    Assignee: The University of Sydney
    Inventors: Eric Nettleton, Ross Hennessy, Hugh Durrant-Whyte, Ali Haydar Göktogan, Peter James Hatherly, Fabio Tozeto Ramos
  • Patent number: 8849622
    Abstract: A system for large scale data modelling is described. The system includes at least one data measurement sensor (230) for generating measured data, a training processor (240) to determine optimized hyperparameter values in relation to a Gaussian process covariance function including a sparse covariance function that is smooth and diminishes to zero outside of a characteristic hyperparameter length. An evaluation processor (260) determines model data from the Gaussian process covariance function with optimised hyperparameter values and measured data. Also described is methods for modelling date, including a method using a Gaussian process including a sparse covariance function that diminishes to zero outside of a characteristic length, wherein the characteristic length is determined from the data to be modelled.
    Type: Grant
    Filed: December 30, 2009
    Date of Patent: September 30, 2014
    Assignee: The University of Sydney
    Inventors: Arman Melkumyan, Fabio Tozeto Ramos
  • Patent number: 8825456
    Abstract: A method of computerized data analysis and synthesis is described. First and second datasets of a quantity of interest are stored. A Gaussian process model is generated using the first and second datasets to compute optimized kernel and noise hyperparameters. The Gaussian process model is applied using the stored first and second datasets and hyperparameters to perform Gaussian process regression to compute estimates of unknown values of the quantity of interest. The resulting computed estimates of the quantity of interest result from a non-parametric Gaussian process fusion of the first and second measurement datasets. The first and second datasets may be derived from the same or different measurement sensors. Different sensors may have different noise and/or other characteristics.
    Type: Grant
    Filed: September 15, 2010
    Date of Patent: September 2, 2014
    Assignee: The University of Sydney
    Inventors: Shrihari Vasudevan, Fabio Tozeto Ramos, Eric Nettleton, Hugh Durrant-Whyte
  • Patent number: 8768659
    Abstract: A method for modelling a dataset includes a training phase, wherein the dataset is applied to a non-stationary Gaussian process kernel in order to optimize the values of a set of hyperparameters associated with the Gaussian process kernel, and an evaluation phase in which the dataset and Gaussian process kernel with optimized hyperparameters are used to generate model data. The evaluation phase includes a nearest neighbor selection step. The method may include generating a model at a selected resolution.
    Type: Grant
    Filed: September 18, 2009
    Date of Patent: July 1, 2014
    Assignee: The University of Sydney
    Inventors: Shrihari Vasudevan, Fabio Tozeto Ramos, Eric Nettleton, Hugh Durrant-Whyte
  • Patent number: 8438121
    Abstract: A system (100) for analyzing and synthesizing a plurality of sources of sample data (310, 320) by automated learning and regression. The system includes data storage (110) with a stored multi-task covariance function, and an evaluation processor (102) in communication with the data storage (110). The evaluation processor (102) performs regression using the stored sample data and multi-task covariance function and synthesizes prediction data for use in graphical display or digital control.
    Type: Grant
    Filed: May 13, 2010
    Date of Patent: May 7, 2013
    Assignee: The University of Sydney
    Inventors: Arman Melkumyan, Fabio Tozeto Ramos
  • Patent number: 8315838
    Abstract: A system and method are described for generating a model of an environment in which a plurality of equipment units are deployed for the extraction of at least one resource from the environment. The system comprises a pre-extraction modeling unit configured to receive data from a first plurality of heterogeneous sensors in the environment and to fuse the data into a pre-extraction model. An equipment modeling unit is configured to receive equipment data relating to the plurality of equipment units and to combine the equipment data into an equipment model. A post-extraction modeling unit is configured to receive data from a second plurality of sensors and to fuse the data into a post-extraction model. Information from the pre-extraction model, the equipment model and/or the post-extraction model is communicable to the equipment units for use in controlling operation of the equipment units in the environment.
    Type: Grant
    Filed: March 4, 2009
    Date of Patent: November 20, 2012
    Assignee: The University of Sydney
    Inventors: Hugh Durrant-Whyte, Fabio Tozeto Ramos, Peter James Hatherly