Patents by Inventor Suhas E. Chelian
Suhas E. Chelian 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: 10984314Abstract: Described is a system for selecting among intelligence elements of a neural model. An intelligence element is selected from a set of intelligence elements which change group attack probability estimates and processed via multiple operations. A semantic memory component learns group probability distributions and rules based on the group probability distributions. The rules determine which intelligence element related to the groups to select. Given an environment of new probability distributions, the semantic memory component recalls which rule to select to receive a particular intelligence element. An episodic memory component recalls a utility value for each information element A procedural memory component recalls and selects the information element considered to have the highest utility. A list of intelligence elements is published to disambiguate likely attackers.Type: GrantFiled: June 25, 2015Date of Patent: April 20, 2021Assignee: HRL Laboratories, LLCInventors: Suhas E. Chelian, Giorgio A. Ascoli, James Benvenuto, Michael D. Howard, Rajan Bhattacharyya
-
Patent number: 10635971Abstract: Described is a system for proactive and reactive cognitive control using a neural module. The system calculates, for each hypothesis of a set of hypotheses, a probability that an event will occur. The neural module comprises a plurality of neurons and includes the PC module, a prefrontal cortex (PFC) module, an anterior cingulate cortex (ACC) module, a locus coeruleus (LC) module, and a basal forebrain (BF) module. The set of hypotheses are related to tasks to be performed by a plurality of groups, each group having a corresponding hypothesis. For each probability, the system calculates a conflict value across all hypotheses with the ACC module, compares each conflict value to a predetermined threshold using the BF and LC modules. A determination is made whether to directly output the calculated probability or perform an additional probability calculation and output an updated probability.Type: GrantFiled: December 1, 2015Date of Patent: April 28, 2020Assignee: HRL Laboratories, LLCInventors: Suhas E. Chelian, Matthias Ziegler, James Benvenuto, Jeffrey Lawrence Krichmar, Randall C. O'Reilly, Rajan Bhattacharyya
-
Patent number: 10562432Abstract: A vehicle for transporting and communicating with a robot includes a vehicle body and a robot dock mechanically coupled to the vehicle body and configured to mechanically couple the robot to the vehicle body. The vehicle also includes an input/output port configured to be electrically coupled to the robot. The vehicle also includes an electronic control unit (ECU) coupled to the input/output port and configured to transmit a signal to the robot via the input/output port to at least one of program the robot or control the robot.Type: GrantFiled: August 1, 2016Date of Patent: February 18, 2020Assignee: TOYOTA MOTOR ENGINEERING & MANUFACTURING NORTH AMERICA, INC.Inventor: Suhas E. Chelian
-
Patent number: 10546233Abstract: Described is a system for explaining how the human brain represents conceptual knowledge. A semantic model is developed, and a behavioral exam is performed to assess a calibration subject into a cohort and reveal semantic relationships to modify a personalized semantic space developed by the semantic model. Semantic features are extracted from the personalized semantic space. Neural features are extracted from neuroimaging of the human subject. A neuroceptual lattice is created having nodes representing attributes by aligning the semantic features and the neural features. Structures in the neuroceptual lattice are identified to quantify an extent to which the set of neural features represents a target concept. The identified structures are used to interpret conceptual knowledge in the brain of a test subject.Type: GrantFiled: December 22, 2015Date of Patent: January 28, 2020Assignee: HRL Laboratories, LLCInventors: Rajan Bhattacharyya, James Benvenuto, Matthew E. Phillips, Matthias Ziegler, Michael D. Howard, Suhas E. Chelian, Rashmi N. Sundareswara, Vincent De Sapio, David L. Allen
-
Patent number: 10535155Abstract: Systems and methods for articulated pose estimation are provided. Some embodiments include training a convolutional neural network for object pose estimation, which includes receiving a two-dimensional training image of an articulated object that has a plurality of components and identifying, from the two-dimensional training image, at least one key point for each of the plurality of components. Some embodiments also include testing the accuracy of the object pose estimation, which includes visualizing a three or more dimensional pose of each of the plurality of components of the articulated object from a two-dimensional testing image and providing data related to the visualization for output.Type: GrantFiled: October 24, 2017Date of Patent: January 14, 2020Assignees: Toyota Motor Engineering & Manufacturing North America, Inc., Carnegie Mellon UniversityInventors: Zhe Cao, Qi Zhu, Yaser Sheikh, Suhas E. Chelian
-
Patent number: 10431107Abstract: A device for providing feedback includes an imaging device configured to capture an image of a subject, a feedback device, and a controller communicatively coupled to the imaging device and the feedback device. The controller includes at least one processor and at least one memory storing computer readable and executable instructions that, when executed by the processor, cause the controller to determine one or more identifying characteristics of the subject, set one or more parameters for determining a facial expression of the subject in the image based on the one or more identifying characteristics of the subject, determine the facial expression of the subject in the image based on the one or more parameters, and provide the feedback with the feedback device based on the determined facial expression.Type: GrantFiled: March 7, 2017Date of Patent: October 1, 2019Assignee: TOYOTA MOTOR ENGINEERING & MANUFACTURING NORTH AMERICA, INC.Inventor: Suhas E. Chelian
-
Patent number: 10391844Abstract: A system for improving safety while providing privacy for a vehicle. The system includes a display screen located within the vehicle, configured to alternate between a displaying state and a non-displaying state. The system includes a window configured to alternate between an opaque state and a transparent state. The system includes an electronic control unit (ECU) configured to determine whether the display screen is powered on. The ECU is configured to alternate the display screen between the displaying state and the non-displaying state at a predetermined frequency when the display screen is powered on. The ECU is configured to alternate the window between the opaque state and the transparent state at the predetermined frequency, the display screen being in the displaying state when the window is in the opaque state and the display screen being in the non-displaying state when the window is in the transparent state.Type: GrantFiled: April 30, 2018Date of Patent: August 27, 2019Assignee: TOYOTA MOTOR ENGINEERING & MANUFACTURING NORTH AMERICA, INC.Inventor: Suhas E. Chelian
-
Patent number: 10315492Abstract: Methods, systems, and apparatus for controlling air filtration, circulation, climate control and/or other adjustable components. The air control system includes an air filtration or circulation unit for filtering or circulating air. The air control system includes a navigation unit for providing at least one of a navigational map information or environment information including a current location of the vehicle. The air control system includes an electronic control unit connected to the air filtration or circulation unit. The electronic control unit is configured to determine an air control event based on at least one of static air quality information or dynamic air quality information. The electronic control unit is configured to determine that the air control event is within a range of the current location and is approaching. The electronic control unit is configured to activate the air filtration or circulation unit before the air control event reaches the vehicle.Type: GrantFiled: May 15, 2017Date of Patent: June 11, 2019Assignee: TOYOTA MOTOR ENGINEERING & MANUFACTURING NORTH AMERICA, INC.Inventors: Suhas E. Chelian, Tiffany Chen
-
Publication number: 20190126730Abstract: A system for improving safety while providing privacy for a vehicle. The system includes a display screen located within the vehicle, configured to alternate between a displaying state and a non-displaying state. The system includes a window configured to alternate between an opaque state and a transparent state. The system includes an electronic control unit (ECU) configured to determine whether the display screen is powered on. The ECU is configured to alternate the display screen between the displaying state and the non-displaying state at a predetermined frequency when the display screen is powered on. The ECU is configured to alternate the window between the opaque state and the transparent state at the predetermined frequency, the display screen being in the displaying state when the window is in the opaque state and the display screen being in the non-displaying state when the window is in the transparent state.Type: ApplicationFiled: April 30, 2018Publication date: May 2, 2019Inventor: Suhas E. Chelian
-
Publication number: 20190122380Abstract: Systems and methods for articulated pose estimation are provided. Some embodiments include training a convolutional neural network for object pose estimation, which includes receiving a two-dimensional training image of an articulated object that has a plurality of components and identifying, from the two-dimensional training image, at least one key point for each of the plurality of components. Some embodiments also include testing the accuracy of the object pose estimation, which includes visualizing a three or more dimensional pose of each of the plurality of components of the articulated object from a two-dimensional testing image and providing data related to the visualization for output.Type: ApplicationFiled: October 24, 2017Publication date: April 25, 2019Applicants: Toyota Motor Engineering & Manufacturing North America, Inc., Carnegie Mellon UniversityInventors: Zhe Cao, Qi Zhu, Yaser Sheikh, Suhas E. Chelian
-
Patent number: 10255548Abstract: Described is a system for modeling probability matching in human subjects. Features related to probability matching are extracted from a set of human subject responses from behavioral tasks. Neural network model instances are trained on the set of features, resulting in a set of trained neural network model instances. A set of model parameters are derived from the set of trained neural network instances, and the set of derived model parameters are used to emulate human performance on novel data.Type: GrantFiled: November 5, 2015Date of Patent: April 9, 2019Assignee: HRL Laboratories, LLCInventors: Suhas E. Chelian, Rajan Bhattacharyya
-
Patent number: 10181100Abstract: Described is system and method for cognitive recognition. The system receives a multi-dimensional scene array as input data. A foveation module divides the multi-dimensional scene array into a plurality of sub-arrays and outputs contents of a currently selected sub-array. The contents are clustered with a hierarchical clustering module to generate a spatially invariant hierarchical cluster of the contents comprising a plurality of components which are based on a statistical distribution of co-occurrence of features across the currently selected sub-array. Task-relevant components are selectively gated and robustly maintained into a component memory location of a pattern bank with a working memory module with an input gating module. If the task-relevant components activate an abstract category module based on pattern matching, then a category recognition label is generated for the contents of the currently selected sub-array with an executive control module.Type: GrantFiled: March 10, 2014Date of Patent: January 15, 2019Assignee: HRL Laboratories, LLCInventors: James Benvenuto, Suhas E. Chelian, Rajan Bhattacharyya, Matthias Ziegler, Michael D. Howard
-
Patent number: 10176382Abstract: Described is system and method for visual media reasoning. An input image is filtered using a first series of kernels tuned to represent objects of general categories, followed by a second series of sparse coding filter kernels tuned to represent objects of specialized categories, resulting in a set of sparse codes. Object recognition is performed on the set of sparse codes to generate object and semantic labels for the set of sparse codes. Pattern completion is performed on the object and semantic labels to recall relevant meta-data in the input image. Bi-directional feedback is used to fuse the input data with the relevant meta-data. An annotated image with information related to who is in the input image, what is in the input image, when the input image was captured, and where the input image was captured is generated.Type: GrantFiled: September 14, 2016Date of Patent: January 8, 2019Assignee: HRL Laboratories, LLCInventors: Yuri Owechko, Shanka R. Rao, Shinko Y. Cheng, Suhas E. Chelian, Rajan Bhattacharyya, Michael D. Howard
-
Patent number: 10133983Abstract: Described is system for modeling probability matching and loss sensitivity among human subjects. A set of features related to probability matching and loss sensitivity is extracted from collected human responses. The set of features are processed with a genetic algorithm to fit the collected human responses with a set of neural network model instances. A set of model parameters are generated from the genetic algorithm and used to generate at least one of an explanatory and predictive model of human behavior.Type: GrantFiled: April 22, 2015Date of Patent: November 20, 2018Assignee: HRL Laboratories, LLCInventors: Suhas E. Chelian, Stephanie E. Goldfarb, Rajan Bhattacharyya
-
Patent number: 10130311Abstract: Described is a system for patient-specific rehabilitation that can be performed outside a clinic. The system monitors a patient in real-time to generate a quantitative assessment of a physical state and a motivational state of the patient using sensor data obtained from sensors. Predictions related to the patient are generated utilizing patient-specific biomechanical and neurocognitive models implemented with predictive simulations. Video feed of the patient is registered with sensor data and a set of simulation data. Rehabilitation guidance instructions are conveyed to the patient through dialog-based interactions.Type: GrantFiled: May 18, 2016Date of Patent: November 20, 2018Assignee: HRL Laboratories, LLCInventors: Vincent De Sapio, Suhas E. Chelian, Rajan Bhattacharyya, Matthew E. Phillips, Matthias Ziegler, David W. Payton
-
Publication number: 20180326811Abstract: Methods, systems, and apparatus for controlling air filtration, circulation, climate control and/or other adjustable components. The air control system includes an air filtration or circulation unit for filtering or circulating air. The air control system includes a navigation unit for providing at least one of a navigational map information or environment information including a current location of the vehicle. The air control system includes an electronic control unit connected to the air filtration or circulation unit. The electronic control unit is configured to determine an air control event based on at least one of static air quality information or dynamic air quality information. The electronic control unit is configured to determine that the air control event is within a range of the current location and is approaching. The electronic control unit is configured to activate the air filtration or circulation unit before the air control event reaches the vehicle.Type: ApplicationFiled: May 15, 2017Publication date: November 15, 2018Inventors: Suhas E. Chelian, Tiffany Chen
-
Publication number: 20180261114Abstract: A device for providing feedback includes an imaging device configured to capture an image of a subject, a feedback device, and a controller communicatively coupled to the imaging device and the feedback device. The controller includes at least one processor and at least one memory storing computer readable and executable instructions that, when executed by the processor, cause the controller to determine one or more identifying characteristics of the subject, set one or more parameters for determining a facial expression of the subject in the image based on the one or more identifying characteristics of the subject, determine the facial expression of the subject in the image based on the one or more parameters, and provide the feedback with the feedback device based on the determined facial expression.Type: ApplicationFiled: March 7, 2017Publication date: September 13, 2018Applicant: Toyota Motor Engineering & Manufacturing North America, Inc.Inventor: Suhas E. Chelian
-
Patent number: 10052764Abstract: Methods, systems, and apparatus for an automated platform system. The automated platform system includes a docking station and a personal device connected to an automated robot platform. The automated robot platform includes one or more arms and an adjustable platform surface. The automated robot platform includes one or more imaging devices configured to receive imaging feedback and one or more transportation components coupled to the base. The one or more transportation components are configured to move in multiple directions. The automated robot platform includes one or more data processors that are configured to obtain imaging feedback. The one or more data processors are configured to operate the one or more transportation components to move in multiple directions to a first location based on the imaging feedback, and adjust the adjustable platform surface to a first height and a first angle.Type: GrantFiled: June 16, 2016Date of Patent: August 21, 2018Assignee: TOYOTA MOTOR ENGINEERING & MANUFACUTRING NORTH AMERICA, INC.Inventors: Suhas E. Chelian, Keith J. Wells, Robert D. McClain
-
Patent number: 10052062Abstract: Described is a system for system for gait intervention and fall prevention. The system is incorporated into a body suit having a plurality of distributed sensors and a vestibulo-muscular biostim array. The sensors are operable for providing biosensor data to the analytics module, while the vestibulo-muscular biostim array includes a plurality of distributed effectors. The analytics module is connected with the body suit and sensors and is operable for receiving biosensor data and analyzing a particular user's gait and predicting falls. Finally, a closed-loop biostim control module is included for activating the vestibulo-muscular biostim array to compensate for a risk of a predicted fall.Type: GrantFiled: February 11, 2016Date of Patent: August 21, 2018Assignee: HRL Laboratories, LLCInventors: Vincent De Sapio, Michael D. Howard, Suhas E. Chelian, Matthias Ziegler, Matthew E. Phillips, Kevin R. Martin, Heiko Hoffmann, David W. Payton
-
Patent number: 10022753Abstract: Methods, systems, and apparatus for an automated mailbox system. The automated mailbox system includes a personal device configured to manage a robot. The robot includes a base that forms a foundation for the robot and is coupled to a post. The robot includes a mailbox having a door. The mailbox is configured to receive documents when in the open position. The robot includes a transportation component that moves the robot in multiple directions among multiple locations. The transportation component is configured to move the robot in a first direction to a first location.Type: GrantFiled: May 12, 2016Date of Patent: July 17, 2018Assignee: TOYOTA MOTOR ENGINEERING & MANUFACTURING NORTH AMERICA, INC.Inventors: Suhas E. Chelian, Allison Thackston, Douglas Moore