Patents Assigned to Carnegie Mellon University
  • Patent number: 12038756
    Abstract: An intelligent, autonomous interior cleaning robot capable of autonomously mapping and cleaning multiple rooms in a house in an intelligent manner is described. Various combinations of passive and active sensors may be used to perform mapping, localization, and obstacle avoidance. In particular, the robot uses stereo cameras with a static projected light pattern to generate 3D data. In addition, the robot may use optical sensors in various locations, laser ToF sensors, inertial measurement units and visual odometry to enhance the localization and mapping capabilities.
    Type: Grant
    Filed: December 19, 2018
    Date of Patent: July 16, 2024
    Assignee: Carnegie Mellon University
    Inventors: Herman Herman, Karl Muecke, Jose Gonzalez-Mora, Raphael Bouterige, Jason Kulk, Jaime Bourne, Jean-Phillipe Tardif
  • Publication number: 20240233095
    Abstract: Disclosed here are various techniques for improving the testing and training of datasets comprising sequences of skeletal representations performing various actions. The dataset can be denoised by applying various techniques to determine noisy frames within each sequence and eliminating the sequences from the dataset when the number of noisy frames in the sequence is too large. In addition, the dataset may be augmented by various data augmentation techniques to manipulate the skeletal representations, after denoising.
    Type: Application
    Filed: October 20, 2023
    Publication date: July 11, 2024
    Applicants: CARNEGIE MELLON UNIVERSITY, AnyVision Interactive Technologies, Ltd.
    Inventors: Marios Savvides, Yu Kai Huang, Eddie Yu
  • Publication number: 20240217391
    Abstract: Disclosed herein is a system and method implementing a battery avionics system for integrating battery monitoring, control, and management functions with an avionics system of an aircraft. The system uses a model implementing a battery pack digital twin, which is a continuous simulation of the operation of the battery pack within the aircraft, receives data regarding the battery pack generated by the digital twin model and provides optimized parameters to the battery avionics system. The system enables high precision, cell-level resolution control of the battery pack. The system estimates the state of charge, state of health, state of safety, and state of function of the cells and the battery pack as a whole and uses this information to manage the battery pack, given a particular flight profile of the aircraft.
    Type: Application
    Filed: May 31, 2022
    Publication date: July 4, 2024
    Applicant: CARNEGIE MELLON UNIVERSITY
    Inventors: Venkatasubramanian Viswanathan, Alexander Bills, Shashank Sripad
  • Patent number: 12026226
    Abstract: Disclosed herein is an improved few-shot detector which utilizes semantic relation reasoning to learn novel objects from both visual information and the semantic relation of base class objects Specifically, a semantic space is constructed using word embeddings. Guided by the word embeddings of the classes, the detector is trained to project the objects from the visual space to the semantic space and to align their image representations with the corresponding class embeddings.
    Type: Grant
    Filed: August 23, 2021
    Date of Patent: July 2, 2024
    Assignee: Carnegie Mellon University
    Inventors: Marios Savvides, Chenchen Zhu, Fangyi Chen, Uzair Ahmed, Ran Tao
  • Patent number: 12027858
    Abstract: A computer implemented method for controlling a load aggregator for a grid includes receiving a predicted power demand over a horizon of time steps associated with one of at least two buildings, aggregating the predicted power demand at each time step to obtain an aggregate power demand, applying a learnable convolutional filter on the aggregate power demand to obtain a target load, computing a difference between the predicted power demand of the one building with the target load to obtain a power shift associated with the one building over the horizon of time steps, apportioning the power shift according to a learnable weighted vector to obtain an apportioned power shift, optimizing the learnable weighted vector and the learnable convolutional filter via an evolutionary strategy based update to obtain an optimized apportioned power shift, and transmitting the optimized apportioned power shift to a building level controller associated with the one building.
    Type: Grant
    Filed: July 1, 2021
    Date of Patent: July 2, 2024
    Assignees: Robert Bosch GmbH, Carnegie Mellon University
    Inventors: Jonathan Francis, Bingqing Chen, Weiran Yao
  • Patent number: 12022597
    Abstract: Provided is a system and method for heating an item in a microwave oven. The method includes capturing, with at least one electromagnetic field sensor, at least one electromagnetic field measurement of a microwave chamber, each electromagnetic field measurement of the at least one electromagnetic field measurement corresponding to a region in the microwave chamber, generating an electromagnetic field map of the microwave chamber based on the at least one electromagnetic field measurement, capturing, with at least one sensor, a plurality of thermal measurements of the item being heated in the microwave chamber, each thermal measurement of the plurality of thermal measurements corresponding to a region on the item, and controlling at least one of a position of the item and the electromagnetic field while the item is being heated in the microwave chamber based on the electromagnetic field map and the plurality of thermal measurements.
    Type: Grant
    Filed: June 22, 2020
    Date of Patent: June 25, 2024
    Assignee: Carnegie Mellon University
    Inventors: Jason I Hong, Haojian Jin, Swarun Kumar Suresh Kumar, Jingxian Wang
  • Patent number: 12016634
    Abstract: Disclosed herein are methods and apparatus for the imaging of brain electrical activity from electromagnetic measurements, using deep learning neural networks where a simulation process is designed to model realistic brain activation and electromagnetic signals to train generalizable neural networks and a residual convolutional neural network and/or a recurrent neural network is trained using the simulated data, capable of estimating source distributions from electromagnetic measurements, and their temporal dynamics over time, for pathological signals in diseased brains, such as interictal activity and ictal signals, and physiological brain signals such as evoked brain responses and spontaneous brain activity.
    Type: Grant
    Filed: May 10, 2021
    Date of Patent: June 25, 2024
    Assignee: Carnegie Mellon University
    Inventors: Bin He, Rui Sun, Abbas Sohrabpour
  • Patent number: 12014533
    Abstract: A method includes acquiring with a scanning device a scan frame including a point cloud comprising a first plurality of points and describing a spatial characteristic of an environment, attributing each of the first plurality of points with a spatial confidence metric, discarding a portion of the first plurality of points when the spatial confidence metric of at least one of the first plurality of points is below a predefined threshold value and directing a user of the scanning device to acquire a second point cloud approximately coincident with the discarded portion of the first plurality of points.
    Type: Grant
    Filed: October 1, 2020
    Date of Patent: June 18, 2024
    Assignee: CARNEGIE MELLON UNIVERSITY
    Inventor: Steven Huber
  • Patent number: 12013285
    Abstract: A near-field probe (and associated method) compatible with near-infrared electromagnetic radiation and high temperature applications above 300° C. (or 500° C. in some applications) includes an optical waveguide and a photonic thermal emitting structure comprising a near-field thermally emissive material coupled to or part of the optical waveguide. The photonic thermal emitting structure is structured and configured to emit near-field energy responsive to at least one environmental parameter of interest, and the near-field probe is structured and configured to enable extraction of the near-field energy to a far-field by coupling the near-field energy into one or more guided modes of the optical waveguide.
    Type: Grant
    Filed: April 19, 2021
    Date of Patent: June 18, 2024
    Assignees: UNIVERSITY OF PITTSBURGH—OF THE COMMONWEALTH SYSTEM OF HIGHER EDUCATION, CARNEGIE MELLON UNIVERSITY
    Inventors: Paul Richard Ohodnicki, Sheng Shen
  • Patent number: 12005800
    Abstract: A method for the efficient management of a fleet of electric vehicles in a target area couples vehicle dynamics and battery dynamics modeling with environmental factors to accurately incorporate the impact that the environment has on the range of the battery into the placement of the chargers by simulating trips of fleets of electric vehicles. The vehicles can be of various types, for example, motorcycles, cars, trucks or aircraft, and will each have their battery state of charge monitored as they traverse a simulated trip through the target area.
    Type: Grant
    Filed: March 31, 2023
    Date of Patent: June 11, 2024
    Assignee: Carnegie Mellon University
    Inventors: Venkatasubramanian Viswanathan, Matthew Guttenberg, Shashank Sripad
  • Patent number: 12009903
    Abstract: A system and method of controlling a constellation of nanosatellites colocates processing resources with sensors in each satellite. Latencies in data transmission are addressed by organizing the constellation of satellites into computational pipelines. An orbital edge computing module simulates system design for mission design, planning and analysis in addition to supporting online autonomy.
    Type: Grant
    Filed: April 1, 2021
    Date of Patent: June 11, 2024
    Assignee: CARNEGIE MELLON UNIVERSITY
    Inventors: Brandon Lucia, Bradley Denby
  • Patent number: 12001003
    Abstract: An accessory optic is described which enables a non-immersed, long working distance microscope objective to be used as a higher-power immersion objective. This is particularly useful for biological imaging of specimens in an index-matching clarification medium. The accessory approach is the opposite of conventional unitized immersion objective design and presents several advantages over conventional design. The front lens element of the accessory may be selected to have precisely the refractive index of the specimen immersion medium and the accessory may be designed for use with immersion media that are incompatible with conventional immersion objectives. A dual accessory enables two such modified objectives to be optimized for light-sheet microscopy.
    Type: Grant
    Filed: June 26, 2019
    Date of Patent: June 4, 2024
    Assignee: Carnegie Mellon University
    Inventor: Frederick Lanni
  • Publication number: 20240177427
    Abstract: Disclosed herein is a system providing a mixed reality combination system that pairs augmented reality technology and an inertial measurement unit sensor with 3D printed objects such that user motions tracked by the inertial measurement unit as the user interacts with the 3D printed object is reflected in a virtual environment display of dynamic 3D imagery and augmented reality imagery.
    Type: Application
    Filed: April 18, 2022
    Publication date: May 30, 2024
    Applicant: CARNEGIE MELLON UNIVERSITY
    Inventors: Jonathan CAGAN, Philip LEDUC
  • Patent number: 11995761
    Abstract: A method of generating virtual sensor data of a virtual single-photon avalanche diode (SPAD) lidar sensor includes generating a two-dimensional (2D) lidar array having a plurality of cells. The method further includes interpolating image data from a virtual camera with the 2D lidar array to define auxiliary image data, generating a virtual ambient image based on a red-channel (R-channel) data of the auxiliary image data, identifying a plurality of virtual echoes of the virtual SPAD lidar sensor based on the R-channel data and a defined photon threshold, defining a virtual point cloud indicative of virtual photon measurements of the virtual SPAD lidar sensor based on the plurality of virtual echoes, and outputting data indicative of the virtual ambient image, the virtual photon measurements, the virtual point cloud, or a combination thereof, as the virtual sensor data of the virtual SPAD lidar sensor.
    Type: Grant
    Filed: March 30, 2022
    Date of Patent: May 28, 2024
    Assignees: DENSO CORPORATION, Carnegie Mellon University
    Inventors: Prasanna Sivakumar, Kris Kitani, Matthew O'Toole, Xinshuo Weng, Shawn Hunt, Yunze Man
  • Publication number: 20240164742
    Abstract: Provided is a system, method, and computer program product for tracking a needle. The method includes determining a visibility of the needle being inserted into a subject in an image of a sequence of images, in response to determining that the visibility satisfies a visibility threshold, detecting a location of the needle based on at least one first algorithm and a detected curvature of the needle, in response to determining that the visibility does not satisfy the visibility threshold, detecting the location of the needle being inserted based on at least one second algorithm, and tracking the location of the needle in the sequence of images based on locations detected with the at least one first algorithm and the at least one second algorithm.
    Type: Application
    Filed: March 24, 2022
    Publication date: May 23, 2024
    Applicants: Carnegie Mellon University
    Inventors: John Michael Galeotti, Wanwen Chen
  • Publication number: 20240169748
    Abstract: A hierarchical deep-learning object detection framework provides a method for identifying objects of interest in high-resolution, high pixel count images, wherein the objects of interest comprise a relatively a small pixel count when compared to the overall image. The method uses first deep-learning model to analyze the high pixel count images, in whole or as a patchwork, at a lower resolution to identify objects, and a second deep-learning model to analyze the objects at a higher resolution to classify the objects.
    Type: Application
    Filed: December 21, 2023
    Publication date: May 23, 2024
    Applicant: CARNEGIE MELLON UNIVERSITY
    Inventors: JONATHAN CAGAN, PHILIP LeDUC, DANIEL CLYMER
  • Publication number: 20240169666
    Abstract: Provided is a system, method, and computer program product for determining a needle injection site. The method includes segmenting, with at least one computing device, an image of a sequence of images into at least one object based on a machine-learning model configured to estimate its uncertainty for each segmentation, generating, with the at least one computing device, a 3D model of the at least one object, and determining, with the at least one computing device, an insertion location of the at least one object based at least partially on an output of the machine-learning model.
    Type: Application
    Filed: March 25, 2022
    Publication date: May 23, 2024
    Applicant: Carnegie Mellon University
    Inventors: John Michael Galeotti, Edward Chen
  • Patent number: 11989933
    Abstract: The invention proposes a method of training a convolutional neural network in which, at each convolutional layer, weights for one seed convolutional filter per layer are updated during each training iteration. All other convolutional filters are polynomial transformations of the seed filter, or, alternatively, all response maps are polynomial transformations of the response map generated by the seed filter.
    Type: Grant
    Filed: April 29, 2019
    Date of Patent: May 21, 2024
    Assignee: Carnegie Mellon University
    Inventors: Felix Juefei Xu, Marios Savvides
  • Publication number: 20240161469
    Abstract: Disclosed herein are training strategies for query-based object detectors, referred to herein as Query Recollection (QR). In one variation or QR, dense query recollection, every intermediate query is collected and independently forwarded to every downstream stage. In a second variation or QR, selective query recollection, intermediate queries are collected from the two nearest previous stages and forwarded to the next downstream stage. This eliminates the phenomena wherein intermediate stages of the decoder produce more accurate results than later stages of the decoder.
    Type: Application
    Filed: November 14, 2023
    Publication date: May 16, 2024
    Applicant: CARNEGIE MELLON UNIVERSITY
    Inventors: Fangyi CHEN, Marios SAVVIDES, Han ZHANG, Kai HU
  • Publication number: 20240161376
    Abstract: In an example, a method may include obtaining, from a data source, first data including multiple frames each including a human face. The method may include automatically detecting, in each of the multiple frames, one or more facial landmarks and one or more action units (AUs) associated with the human face. The method may also include automatically generating one or more semantic masks based at least on the one or more facial landmarks, the one or more semantic masks individually corresponding to the human face. The method may further include obtaining a facial hyperspace using at least the first data, the one or more AUs, and the semantic masks. The method may also include generating a synthetic image of the human face using a first frame of the multiple frames and one or more AU intensities individually associated with the one or more AUs.
    Type: Application
    Filed: March 29, 2023
    Publication date: May 16, 2024
    Applicants: Fujitsu Limited, CARNEGIE MELLON UNIVERSITY
    Inventors: Heng YU, Koichiro NIINUMA, Laszlo JENI