Patents by Inventor Paul J. Ozog
Paul J. Ozog 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: 11168990Abstract: A map object management system including object information for objects in the environment around a location. The objects generally relating to the roadway on which a user is travelling. The map object management system provides a user with queries regarding detected objects that fail to meet confidence thresholds regarding the identification of the object. The map object management system receives answers to the queries to crowdsource uncertain or inaccurate object identifications for use in a map service to provide accurate map information to users.Type: GrantFiled: March 11, 2019Date of Patent: November 9, 2021Assignee: Toyota Research Institute, Inc.Inventors: Paul J. Ozog, Ryan W. Wolcott
-
Patent number: 11138465Abstract: System, methods, and other embodiments described herein relate to associating coordinates between separate coordinate systems. In one embodiment, a method includes acquiring location coordinates of a vehicle in a surrounding environment according to sensor data from at least one sensor of the vehicle. The method includes transforming reference coordinates associated with the location coordinates into first intermediate coordinates associated with a first coordinate system that is based, at least in part, on a distorted two-dimensional map projection, and second intermediate coordinates associated with a second coordinate system that is a Cartesian coordinate system associated with a Geodetic datum. The method includes generating, using the first intermediate coordinates and the second intermediate coordinates, an estimated transform for converting between the first coordinate system and the second coordinate system.Type: GrantFiled: December 10, 2019Date of Patent: October 5, 2021Assignee: Toyota Research Institute, Inc.Inventors: Paul J. Ozog, Schuyler H. Cohen
-
Publication number: 20210174139Abstract: System, methods, and other embodiments described herein relate to associating coordinates between separate coordinate systems. In one embodiment, a method includes acquiring location coordinates of a vehicle in a surrounding environment according to sensor data from at least one sensor of the vehicle. The method includes transforming reference coordinates associated with the location coordinates into first intermediate coordinates associated with a first coordinate system that is based, at least in part, on a distorted two-dimensional map projection, and second intermediate coordinates associated with a second coordinate system that is a Cartesian coordinate system associated with a Geodetic datum. The method includes generating, using the first intermediate coordinates and the second intermediate coordinates, an estimated transform for converting between the first coordinate system and the second coordinate system.Type: ApplicationFiled: December 10, 2019Publication date: June 10, 2021Inventors: Paul J. Ozog, Schuyler H. Cohen
-
Patent number: 10989562Abstract: System, methods, and other embodiments described herein relate to improving calibration of an onboard sensor of a vehicle. In one embodiment, a method includes, in response to acquiring sensor data from a surrounding environment of the vehicle using the onboard sensor, analyzing the sensor data to determine calibration parameters for the onboard sensor. The method includes identifying a suitability parameter that characterizes how well the surrounding environment provides for determining the calibration parameters. The method includes generating annotations within a map that specify at least the suitability parameter for a location associated with the sensor data. In further aspects, the method includes identifying, from the map, a calibration route for the vehicle that is a deviation from a current route in response to determining that the calibration state of the onboard sensor does not satisfy the calibration threshold.Type: GrantFiled: July 12, 2018Date of Patent: April 27, 2021Assignee: Toyota Research Institute, inc.Inventors: Paul J. Ozog, Ryan W. Wolcott, Schuyler H. Cohen
-
Patent number: 10875535Abstract: The systems and methods described herein disclose localization of a vehicle based on tactile events. As described here, the vibrations produced by objects in an environment as a vehicle encounters them can be used to determine the position and orientation of the vehicle. The systems and methods can include detecting at least one tactile event in an environment, during the operation of a vehicle. A tactile survey map can then be accessed to correlate surveyed tactile events to an event location in the environment. The detected tactile events can then be compared to the tactile survey map. Then, the event location and the tactile correlation can be applied to determine the vehicle location in the environment.Type: GrantFiled: July 27, 2018Date of Patent: December 29, 2020Assignee: Toyota Research Institute, Inc.Inventor: Paul J. Ozog
-
Publication number: 20200292322Abstract: A map object management system including object information for objects in the environment around a location. The objects generally relating to the roadway on which a user is travelling. The map object management system provides a user with queries regarding detected objects that fail to meet confidence thresholds regarding the identification of the object. The map object management system receives answers to the queries to crowdsource uncertain or inaccurate object identifications for use in a map service to provide accurate map information to users.Type: ApplicationFiled: March 11, 2019Publication date: September 17, 2020Applicant: Toyota Research Institute, Inc.Inventors: Paul J. OZOG, Ryan W. WOLCOTT
-
Patent number: 10740645Abstract: System, methods, and other embodiments described herein relate to improving an electronic representation of lines. In one embodiment, a method includes, in response to acquiring sensor data from at least one sensor representing a surrounding environment of a robotic device, extracting a feature representation of an observed line feature in the sensor data by providing a probability distribution that is defined based, at least in part, on feature parameters that overparameterize the observed line feature. The method includes converting the feature representation of the observed line feature into reduced parameters to avoid the feature parameters overparameterizing the observed line feature. The reduced parameters include an observation uncertainty for the line feature that is based, at least part, on the probability distribution. The method includes providing a detection distribution according to a correlation between the reduced parameters and a mapped line feature.Type: GrantFiled: June 29, 2018Date of Patent: August 11, 2020Assignee: Toyota Research Institute, Inc.Inventor: Paul J. Ozog
-
Patent number: 10710599Abstract: System, methods, and other embodiments described herein relate to identifying changes within a surrounding environment of a vehicle. In one embodiment, a method includes collecting, using at least one sensor of the vehicle, sensor data about the surrounding environment. The method includes analyzing the sensor data to identify features of the surrounding environment. The features are landmarks of the surrounding environment that are indicated within a map of the surrounding environment. The sensor data indicates at least measurements associated with the features as acquired by the at least one sensor. The method includes computing persistence likelihoods for the features according to a persistence model that characterizes at least prior observations of the features and relationships between the features. The persistence likelihoods indicate estimated persistences of the features to indicate whether the features likely still exist.Type: GrantFiled: February 27, 2018Date of Patent: July 14, 2020Assignee: Toyota Research Institute, Inc.Inventors: Fernando Nobre, Jeffrey M. Walls, Paul J. Ozog
-
Publication number: 20200031356Abstract: The systems and methods described herein disclose localization of a vehicle based on tactile events. As described here, the vibrations produced by objects in an environment as a vehicle encounters them can be used to determine the position and orientation of the vehicle. The systems and methods can include detecting at least one tactile event in an environment, during the operation of a vehicle. A tactile survey map can then be accessed to correlate surveyed tactile events to an event location in the environment. The detected tactile events can then be compared to the tactile survey map. Then, the event location and the tactile correlation can be applied to determine the vehicle location in the environment.Type: ApplicationFiled: July 27, 2018Publication date: January 30, 2020Inventor: Paul J. Ozog
-
Publication number: 20200018618Abstract: System, methods, and other embodiments described herein relate to improving calibration of an onboard sensor of a vehicle. In one embodiment, a method includes, in response to acquiring sensor data from a surrounding environment of the vehicle using the onboard sensor, analyzing the sensor data to determine calibration parameters for the onboard sensor. The method includes identifying a suitability parameter that characterizes how well the surrounding environment provides for determining the calibration parameters. The method includes generating annotations within a map that specify at least the suitability parameter for a location associated with the sensor data. In further aspects, the method includes identifying, from the map, a calibration route for the vehicle that is a deviation from a current route in response to determining that the calibration state of the onboard sensor does not satisfy the calibration threshold.Type: ApplicationFiled: July 12, 2018Publication date: January 16, 2020Inventors: Paul J. Ozog, Ryan W. Wolcott, Schuyler H. Cohen
-
Publication number: 20200005068Abstract: System, methods, and other embodiments described herein relate to improving an electronic representation of lines. In one embodiment, a method includes, in response to acquiring sensor data from at least one sensor representing a surrounding environment of a robotic device, extracting a feature representation of an observed line feature in the sensor data by providing a probability distribution that is defined based, at least in part, on feature parameters that overparameterize the observed line feature. The method includes converting the feature representation of the observed line feature into reduced parameters to avoid the feature parameters overparameterizing the observed line feature. The reduced parameters include an observation uncertainty for the line feature that is based, at least part, on the probability distribution. The method includes providing a detection distribution according to a correlation between the reduced parameters and a mapped line feature.Type: ApplicationFiled: June 29, 2018Publication date: January 2, 2020Inventor: Paul J. Ozog
-
Publication number: 20190084577Abstract: System, methods, and other embodiments described herein relate to identifying changes within a surrounding environment of a vehicle. In one embodiment, a method includes collecting, using at least one sensor of the vehicle, sensor data about the surrounding environment. The method includes analyzing the sensor data to identify features of the surrounding environment. The features are landmarks of the surrounding environment that are indicated within a map of the surrounding environment. The sensor data indicates at least measurements associated with the features as acquired by the at least one sensor. The method includes computing persistence likelihoods for the features according to a persistence model that characterizes at least prior observations of the features and relationships between the features. The persistence likelihoods indicate estimated persistences of the features to indicate whether the features likely still exist.Type: ApplicationFiled: February 27, 2018Publication date: March 21, 2019Inventors: Fernando Nobre, Jeffrey M. Walls, Paul J. Ozog