Patents by Inventor Peter O'Connor
Peter O'Connor 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: 20240085571Abstract: A communication system, includes a satellite receiver in operable communication with a central server, a cellular node configured to operate within a proximity of the satellite receiver, and at least one mobile communication device configured to communicate (i) with the cellular node, (ii) within the proximity of the satellite receiver, and (iii) using a transmission signal capable of causing interference to the satellite receiver. The satellite receiver is configured to detect a repeating portion of the transmission signal and determine a potential for interference from the at least one mobile communication device based on the detected repeating portion.Type: ApplicationFiled: June 26, 2023Publication date: March 14, 2024Inventors: Belal Hamzeh, Peter Paul Smyth, Lin Cheng, Jim O'Connor, Eric Winkelman, Thomas H. Williams, Steve Arendt
-
Publication number: 20240058020Abstract: A positioning guide system for guiding a surgical tool comprising a positioning guide and a user interface. The positioning guide comprising: an interface to correspond to a plurality of anatomic landmarks of a patient; a plurality of sensors to provide an output indicative of the proximity of the interface and one or more of the plurality of anatomic landmarks; and a tool guide, for a surgical tool, positioned relative to the interface. The user interface provides a user output indicative of correct positioning of the positioning guide and the anatomic landmarks of the patient based on the output of the plurality of sensors.Type: ApplicationFiled: October 30, 2023Publication date: February 22, 2024Inventors: Jason Keith HOGAN, Willy THEODORE, Brad Peter MILES, Peter O'CONNOR
-
Patent number: 11600483Abstract: A method of carrying out mass spectrometry, comprising: using an electrostatic or electrodynamic ion trap to contain a plurality of ions, each ion having a mass to charge ratio, the ions having a first plurality of mass to charge ratios, each ion following a path within the electrostatic or electrodynamic ion trap having a radius; and for each of a second plurality of the mass to charge ratios: modulating the radii of the ions in a mass to charge ratio-dependent fashion dependent upon the mass to charge ratio; fragmenting the ions thus modulated in a radius-dependent fashion; and determining a mass spectrum of the ions.Type: GrantFiled: September 12, 2017Date of Patent: March 7, 2023Assignee: The University Of WarwickInventors: Peter O'Connor, Maria A. Van Agthoven
-
Patent number: 11357660Abstract: A medical device for repositioning tissue within an animal has a main body with a first end portion, a second end portion, and a middle portion. The first end portion defines a series of passageways and the second end portion defines a bulbous shape, a slot, and a tab portion. Methods of treating obstructive sleep apnea are also described.Type: GrantFiled: June 28, 2018Date of Patent: June 14, 2022Assignees: Cook Medical Technologies, LLC, Cook Biotech IncorporatedInventors: Peter O'Connor, Wade Colburn, Chelsea McKiernan, Andrew P. Isch, Alexander Brethauer
-
Patent number: 10843338Abstract: Robots have the capacity to perform a broad range of useful tasks, such as factory automation, cleaning, delivery, assistive care, environmental monitoring and entertainment. Enabling a robot to perform a new task in a new environment typically requires a large amount of new software to be written, often by a team of experts. It would be valuable if future technology could empower people, who may have limited or no understanding of software coding, to train robots to perform custom tasks. Some implementations of the present invention provide methods and systems that respond to users' corrective commands to generate and refine a policy for determining appropriate actions based on sensor-data input. Upon completion of learning, the system can generate control commands by deriving them from the sensory data. Using the learned control policy, the robot can behave autonomously.Type: GrantFiled: May 3, 2019Date of Patent: November 24, 2020Assignee: Brain CorporationInventors: Philip Meier, Jean-Baptiste Passot, Borja Ibarz Gabardos, Patryk Laurent, Oleg Sinyavskiy, Peter O'Connor, Eugene Izhikevich
-
Publication number: 20200335321Abstract: A method of carrying out mass spectrometry, comprising: using an electrostatic or electrodynamic ion trap to contain a plurality of ions, each ion having a mass to charge ratio, the ions having a first plurality of mass to charge ratios, each ion following a path within the electrostatic or electrodynamic ion trap having a radius; and for each of a second plurality of the mass to charge ratios: modulating the radii of the ions in a mass to charge ratio-dependent fashion dependent upon the mass to charge ratio; fragmenting the ions thus modulated in a radius-dependent fashion; and determining a mass spectrum of the ions.Type: ApplicationFiled: September 12, 2017Publication date: October 22, 2020Applicants: THE UNIVERSITY OF WARWICK, THE UNIVERSITY OF WARWICKInventors: Peter O'Connor, Maria A. Van Agthoven
-
Publication number: 20190321973Abstract: Robots have the capacity to perform a broad range of useful tasks, such as factory automation, cleaning, delivery, assistive care, environmental monitoring and entertainment. Enabling a robot to perform a new task in a new environment typically requires a large amount of new software to be written, often by a team of experts. It would be valuable if future technology could empower people, who may have limited or no understanding of software coding, to train robots to perform custom tasks. Some implementations of the present invention provide methods and systems that respond to users' corrective commands to generate and refine a policy for determining appropriate actions based on sensor-data input. Upon completion of learning, the system can generate control commands by deriving them from the sensory data. Using the learned control policy, the robot can behave autonomously.Type: ApplicationFiled: May 3, 2019Publication date: October 24, 2019Inventors: Philip Meier, Jean-Baptiste Passot, Borja Ibarz Gabardos, Patryk Laurent, Oleg Sinyavskiy, Peter O'Connor, Eugene Izhikevich
-
Patent number: 10322507Abstract: Robots have the capacity to perform a broad range of useful tasks, such as factory automation, cleaning, delivery, assistive care, environmental monitoring and entertainment. Enabling a robot to perform a new task in a new environment typically requires a large amount of new software to be written, often by a team of experts. It would be valuable if future technology could empower people, who may have limited or no understanding of software coding, to train robots to perform custom tasks. Some implementations of the present invention provide methods and systems that respond to users' corrective commands to generate and refine a policy for determining appropriate actions based on sensor-data input. Upon completion of learning, the system can generate control commands by deriving them from the sensory data. Using the learned control policy, the robot can behave autonomously.Type: GrantFiled: October 16, 2017Date of Patent: June 18, 2019Assignee: Brain CorporationInventors: Philip Meier, Jean-Baptiste Passot, Borja Ibarz Gabardos, Patryk Laurent, Oleg Sinyavskiy, Peter O'Connor, Eugene Izhikevich
-
Publication number: 20190000661Abstract: A medical device for repositioning tissue within an animal has a main body with a first end portion, a second end portion, and a middle portion. The first end portion defines a series of passageways and the second end portion defines a bulbous shape, a slot, and a tab portion. Methods of treating obstructive sleep apnea are also described.Type: ApplicationFiled: June 28, 2018Publication date: January 3, 2019Inventors: Peter O'Connor, Wade Colburn, Chelsea McKiernan, Andrew P. Isch, Alexander Brethauer
-
Publication number: 20180336469Abstract: A method for processing temporally redundant data in an artificial neural network (ANN) includes encoding an input signal, received at an initial layer of the ANN, into an encoded signal. The encoded signal comprises the input signal and a rate of change of the input signal. The method also includes quantizing the encoded signal into integer values and computing an activation signal of a neuron in a next layer of the ANN based on the quantized encoded signal. The method further includes computing an activation signal of a neuron at each layer subsequent to the next layer to compute a full forward pass of the ANN. The method also includes back propagating approximated gradients and updating parameters of the ANN based on an approximate derivative of a loss with respect to the activation signal.Type: ApplicationFiled: September 14, 2017Publication date: November 22, 2018Inventors: Peter O'CONNOR, Max WELLING
-
Publication number: 20180121791Abstract: A method of computation in a deep neural network includes discretizing input signals and computing a temporal difference of the discrete input signals to produce a discretized temporal difference. The method also includes applying weights of a first layer of the deep neural network to the discretized temporal difference to create an output of a weight matrix. The output of the weight matrix is temporally summed with a previous output of the weight matrix. An activation function is applied to the temporally summed output to create a next input signal to a next layer of the deep neural network.Type: ApplicationFiled: May 9, 2017Publication date: May 3, 2018Inventors: Peter O'CONNOR, Max WELLING
-
Publication number: 20180099409Abstract: Robots have the capacity to perform a broad range of useful tasks, such as factory automation, cleaning, delivery, assistive care, environmental monitoring and entertainment. Enabling a robot to perform a new task in a new environment typically requires a large amount of new software to be written, often by a team of experts. It would be valuable if future technology could empower people, who may have limited or no understanding of software coding, to train robots to perform custom tasks. Some implementations of the present invention provide methods and systems that respond to users' corrective commands to generate and refine a policy for determining appropriate actions based on sensor-data input. Upon completion of learning, the system can generate control commands by deriving them from the sensory data. Using the learned control policy, the robot can behave autonomously.Type: ApplicationFiled: October 16, 2017Publication date: April 12, 2018Inventors: Philip Meier, Jean-Baptiste Passot, Borja Ibarz Gabardos, Patryk Laurent, Oleg Sinyavskiy, Peter O'Connor, Eugene Izhikevich
-
Patent number: 9789605Abstract: Robots have the capacity to perform a broad range of useful tasks, such as factory automation, cleaning, delivery, assistive care, environmental monitoring and entertainment. Enabling a robot to perform a new task in a new environment typically requires a large amount of new software to be written, often by a team of experts. It would be valuable if future technology could empower people, who may have limited or no understanding of software coding, to train robots to perform custom tasks. Some implementations of the present invention provide methods and systems that respond to users' corrective commands to generate and refine a policy for determining appropriate actions based on sensor-data input. Upon completion of learning, the system can generate control commands by deriving them from the sensory data. Using the learned control policy, the robot can behave autonomously.Type: GrantFiled: June 6, 2016Date of Patent: October 17, 2017Assignee: BRAIN CORPORATIONInventors: Philip Meier, Jean-Baptiste Passot, Borja Ibarz Gabardos, Patryk Laurent, Oleg Sinyavskiy, Peter O'Connor, Eugene Izhikevich
-
Publication number: 20170291301Abstract: A robotic device may be operated by a learning controller comprising a feature learning configured to determine control signal based on sensory input. An input may be analyzed in order to determine occurrence of one or more features. Features in the input may be associated with the control signal during online supervised training. During training, learning process may be adapted based on training input and the predicted output. A combination of the predicted and the target output may be provided to a robotic device to execute a task. Feature determination may comprise online adaptation of input, sparse encoding transformations. Computations related to learning process adaptation and feature detection may be performed on board by the robotic device in real time thereby enabling autonomous navigation by trained robots.Type: ApplicationFiled: April 24, 2017Publication date: October 12, 2017Inventors: Borja Ibarz Gabardos, Andrew Smith, Peter O'Connor
-
Publication number: 20170228646Abstract: A method of training a neural network with back propagation includes generating error events representing a gradient of a cost function for the neural network. The error events may be generated based on a forward pass through the neural network resulting from input events, weights of the neural network and events from a target signal. The method further includes updating the weights of the neural network based on the error events.Type: ApplicationFiled: August 30, 2016Publication date: August 10, 2017Inventors: Peter O'CONNOR, Max WELLING
-
Patent number: 9630318Abstract: A robotic device may be operated by a learning controller comprising a feature learning configured to determine control signal based on sensory input. An input may be analyzed in order to determine occurrence of one or more features. Features in the input may be associated with the control signal during online supervised training. During training, learning process may be adapted based on training input and the predicted output. A combination of the predicted and the target output may be provided to a robotic device to execute a task. Feature determination may comprise online adaptation of input, sparse encoding transformations. Computations related to learning process adaptation and feature detection may be performed on board by the robotic device in real time thereby enabling autonomous navigation by trained robots.Type: GrantFiled: November 14, 2014Date of Patent: April 25, 2017Assignee: Brain CorporationInventors: Borja Ibarz Gabardos, Andrew Smith, Peter O'Connor
-
Publication number: 20160279790Abstract: Robots have the capacity to perform a broad range of useful tasks, such as factory automation, cleaning, delivery, assistive care, environmental monitoring and entertainment. Enabling a robot to perform a new task in a new environment typically requires a large amount of new software to be written, often by a team of experts. It would be valuable if future technology could empower people, who may have limited or no understanding of software coding, to train robots to perform custom tasks. Some implementations of the present invention provide methods and systems that respond to users' corrective commands to generate and refine a policy for determining appropriate actions based on sensor-data input. Upon completion of learning, the system can generate control commands by deriving them from the sensory data. Using the learned control policy, the robot can behave autonomously.Type: ApplicationFiled: June 6, 2016Publication date: September 29, 2016Inventors: Philip Meier, Jean-Baptiste Passot, Borja Ibarz Gabardos, Patryk Laurent, Oleg Sinyavskiy, Peter O'Connor, Eugene Izhikevich
-
Patent number: 9358685Abstract: Robots have the capacity to perform a broad range of useful tasks, such as factory automation, cleaning, delivery, assistive care, environmental monitoring and entertainment. Enabling a robot to perform a new task in a new environment typically requires a large amount of new software to be written, often by a team of experts. It would be valuable if future technology could empower people, who may have limited or no understanding of software coding, to train robots to perform custom tasks. Some implementations of the present invention provide methods and systems that respond to users' corrective commands to generate and refine a policy for determining appropriate actions based on sensor-data input. Upon completion of learning, the system can generate control commands by deriving them from the sensory data. Using the learned control policy, the robot can behave autonomously.Type: GrantFiled: February 3, 2014Date of Patent: June 7, 2016Assignee: BRAIN CORPORATIONInventors: Philip Meier, Jean-Baptiste Passot, Borja Ibarz Gabardos, Patryk Laurent, Oleg Sinyavskiy, Peter O'Connor, Eugene Izhikevich
-
Patent number: 9346167Abstract: A robotic vehicle may be operated by a learning controller comprising a trainable convolutional network configured to determine control signal based on sensory input. An input network layer may be configured to transfer sensory input into a hidden layer data using a filter convolution operation. Input layer may be configured to transfer sensory input into hidden layer data using a filter convolution. Output layer may convert hidden layer data to a predicted output using data segmentation and a fully connected array of efficacies. During training, efficacy of network connections may be adapted using a measure determined based on a target output provided by a trainer and an output predicted by the network. A combination of the predicted and the target output may be provided to the vehicle to execute a task. The network adaptation may be configured using an error back propagation method. The network may comprise an input reconstruction.Type: GrantFiled: April 29, 2014Date of Patent: May 24, 2016Assignee: Brain CorporationInventors: Peter O'Connor, Eugene Izhikevich
-
Publication number: 20160096270Abstract: A robotic device may be operated by a learning controller comprising a feature learning configured to determine control signal based on sensory input. An input may be analyzed in order to determine occurrence of one or more features. Features in the input may be associated with the control signal during online supervised training. During training, learning process may be adapted based on training input and the predicted output. A combination of the predicted and the target output may be provided to a robotic device to execute a task. Feature determination may comprise online adaptation of input, sparse encoding transformations. Computations related to learning process adaptation and feature detection may be performed on board by the robotic device in real time thereby enabling autonomous navigation by trained robots.Type: ApplicationFiled: November 14, 2014Publication date: April 7, 2016Inventors: Borja Ibarz Gabardos, Andrew Smith, Peter O'Connor