Patents by Inventor Alex Averbuch

Alex Averbuch 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: 11386068
    Abstract: A method is provided for verifying and/or updating map geometry based on a probe data. A method may include: receiving probe data from a plurality of probes within a region, where the probe data includes at least one of heading information and location information for each probe data point; matching the probe data to a link segment to generate map-matched probe data; calculating a difference between the at least one of heading information and location information of the map-matched probe data points and of the link segment; determining a statistical mean of the data; determining an error of the statistical mean of the data; and flagging the link segment for manual review in response to the statistical mean being greater than the error of the statistical mean multiplied by a biasing factor.
    Type: Grant
    Filed: October 27, 2016
    Date of Patent: July 12, 2022
    Assignee: HERE GLOBAL B.V.
    Inventors: Gavril Giurgiu, Alex Averbuch
  • Publication number: 20220178711
    Abstract: System, method and computer program products are provided for detecting an environmental zone, generating a time schedule of an environmental zone in a region and providing route navigation instructions. The method may include obtaining at least one observation associated with the environmental zone in a region. The method may further include determining a confidence value associated with the at least one observation in the region and detecting the environmental zone in the region based on the confidence value associated with the at least one observation. The detection of the environmental zone comprises determining either one of a presence or an absence of the environmental zone in the region. Further, the detection of the environmental zone may be used to generate a time schedule indicating presence or absence of the environmental zone in the region for different time intervals.
    Type: Application
    Filed: December 4, 2020
    Publication date: June 9, 2022
    Inventors: Advait Mohan RAUT, Leon STENNETH, Bruce BERNHARDT, Amarnath NAYAK, Alex AVERBUCH
  • Publication number: 20220172612
    Abstract: A system, a method, and a computer program product are disclosed for detecting a driving direction. The system may include: a memory to store computer-executable instructions; and one or more processors to execute the instructions to receive sensor data associated with a plurality of locations and determine trajectory data associated with the plurality of locations based on the sensor data and map data. Further, the one or more processors may execute the instructions to identify, based on the trajectory data, a set of unmatched locations from the plurality of locations. The set of unmatched locations comprises at least a first predetermined number of unmatched locations. Furthermore, the one or more processors may execute the instructions to detect the driving direction based on the set of unmatched locations and the map data.
    Type: Application
    Filed: December 2, 2020
    Publication date: June 2, 2022
    Inventors: Amarnath NAYAK, Leon STENNETH, Alex AVERBUCH
  • Patent number: 11335192
    Abstract: A system, a method, and a computer program product are disclosed for detecting a driving direction. The system may include: a memory to store computer-executable instructions; and one or more processors to execute the instructions to receive sensor data associated with a plurality of locations and determine trajectory data associated with the plurality of locations based on the sensor data and map data. Further, the one or more processors may execute the instructions to identify, based on the trajectory data, a set of unmatched locations from the plurality of locations. The set of unmatched locations comprises at least a first predetermined number of unmatched locations. Furthermore, the one or more processors may execute the instructions to detect the driving direction based on the set of unmatched locations and the map data.
    Type: Grant
    Filed: December 2, 2020
    Date of Patent: May 17, 2022
    Assignee: HERE Global B.V.
    Inventors: Amarnath Nayak, Leon Stenneth, Alex Averbuch
  • Publication number: 20220135043
    Abstract: A method, apparatus and computer program product for determining a rain event warning are described herein. In the context of a method, an indication of the rain event warning for one or more locations may be received. The method may obtain, for a respective rain event warning, sensor data corresponding to a weather condition within a region that includes the location with which the respective rain event warning is associated. The method may evaluate the sensor data to determine whether the sensor data is indicative of the weather condition (e.g., rain). The method may determine a rain event warning confidence based at least in part on evaluation of the sensor data. The method may cause the rain event warning to be published in an instance in which the rain event warning confidence satisfies a confidence threshold.
    Type: Application
    Filed: November 2, 2020
    Publication date: May 5, 2022
    Inventors: Leon Stenneth, Amarnath Nayak, Alex Averbuch, Ram Marappan
  • Patent number: 11249984
    Abstract: A method, a system, and a computer program product may be provided for updating map data in a map database to indicate presence of a road sign. The method may include obtaining first sensor data associated with a road sign. The first sensor data may comprise at least one of one or more first positive observations of a road sign or one or more first negative observations of the road sign. The method may further include obtaining second sensor data for the road sign, for example, based on the first sensor data. The second sensor data may comprise cumulative historic road sign observation data for time duration. The method may include determining a sign confidence ratio based on the first sensor data and the second sensor data. The method may include updating the map data based on the sign confidence ratio.
    Type: Grant
    Filed: May 22, 2019
    Date of Patent: February 15, 2022
    Assignee: HERE Global B.V.
    Inventors: Alex Averbuch, Leon Stenneth
  • Publication number: 20210261165
    Abstract: A method, apparatus and computer program product for activating a flood event warning are described herein. In the context of a method, a location may be identified as a flood prone location. Data relating to the flood prone location may be received from one or more remote devices. The method may determine a flood confidence for the flood prone location based upon the data. The method may identify an active flood event for the flood prone location based on the flood confidence and cause a flood event warning to be activated in an instance in which the active flood event is identified.
    Type: Application
    Filed: February 26, 2020
    Publication date: August 26, 2021
    Inventors: Alex AVERBUCH, Kun LEE, Leon STENNETH
  • Publication number: 20210216076
    Abstract: A system, a method and a computer program product are provided for evaluating quality of data, such as sensor data and map data, using a machine learning model. The system may include at least one memory configured to store computer executable instructions and at least one processor configured to execute the computer executable instructions to obtain first sensor features of the first sensor data associated with a road object in a first geographic region, first map features of the first map data associated with the road object and ground truth data associated with the road object. The processor may be configured to generate the machine learning model by configuring the ground truth data and calculating first information scores for each of the first sensor features and the first map features by recursively splitting each of the first sensor features and the first map features.
    Type: Application
    Filed: January 9, 2020
    Publication date: July 15, 2021
    Inventors: Amarnath NAYAK, Leon STENNETH, Alex AVERBUCH
  • Patent number: 10943152
    Abstract: An approach is provided for detecting a presence of a physical divider on a road segment. The approach, for example, involves receiving sensor data from a vehicle traveling a road segment. The sensor data indicates a distance from the vehicle to the physical divider, a cross-sensor consistency of detecting the physical divider between at least two sensors of the vehicle, or a combination thereof. The approach also involves determining that the sensor data indicates the presence of the physical divider based on determining that the distance is within distance criteria, the cross-sensor consistency is within consistency criteria, or a combination thereof. The approach further involves updating data provided by a physical divider signal from the vehicle to indicate the presence of the physical divider on the road segment.
    Type: Grant
    Filed: May 23, 2018
    Date of Patent: March 9, 2021
    Assignee: HERE Global B.V.
    Inventors: Alex Averbuch, Leon Stenneth
  • Patent number: 10907980
    Abstract: An approach is provided for detecting false positive slippery road reports. For example, the approach involves receiving a slippery road report from a vehicle. The slippery road report, for instance, indicates that a slippery road event is detected at a location based on sensor information collected by the vehicle. The approach also involves map matching the location of the slippery road report to the mapping data to evaluate a proximity of the location to at least one geographic feature that is designated as an area where driver behavior is expected to be at least one cause of the slippery road event. The approach further involves classifying the slippery road report as the slippery road false positive report based on the evaluation.
    Type: Grant
    Filed: August 11, 2017
    Date of Patent: February 2, 2021
    Assignee: HERE Global B.V.
    Inventors: Robert Camp, Leon Stenneth, Alex Averbuch
  • Patent number: 10896334
    Abstract: A method is provided for prediction of a physical divider on a road. The method comprises retrieving vehicular sensor data, map data, or a combination thereof captured over a predefined period of time for at least one segment of the road. The method further comprises aggregating the respective vehicular sensor data, map data, or the combination thereof for the at least one segment of the road to generate one or more aggregated values. The method further comprises generating output data corresponding to presence of the physical divider in the at least one segment of the road by a machine learning model based on the one or more aggregated values as an input to the machine learning model.
    Type: Grant
    Filed: November 28, 2018
    Date of Patent: January 19, 2021
    Assignee: HERE Global B.V.
    Inventors: Amarnath Nayak, Leon Stenneth, Alex Averbuch
  • Patent number: 10859731
    Abstract: An approach is provided for interpolating weather forecast reports for a forecast location having limited weather station access. The approach involves segmenting a plurality of weather forecast reports according to a plurality of segmentation categories, the plurality of segmentation categories representing respective one or more forecast parameters. The approach also involves determining respective values of the plurality of segmentation categories from each of the plurality of weather forecasts. The approach further involves selecting a representative value from the respective values for each of the one or more segmentation categories. The approach further involves combining the representative value for said each of the plurality of segmentation categories to generate an interpolated weather forecast report.
    Type: Grant
    Filed: August 11, 2017
    Date of Patent: December 8, 2020
    Assignee: HERE Global B.V.
    Inventors: Alex Averbuch, Leon Stenneth
  • Publication number: 20200372012
    Abstract: A method, a system, and a computer program product may be provided for updating map data in a map database to indicate presence of a road sign. The method may include obtaining first sensor data associated with a road sign. The first sensor data may comprise at least one of one or more first positive observations of a road sign or one or more first negative observations of the road sign. The method may further include obtaining second sensor data for the road sign, for example, based on the first sensor data. The second sensor data may comprise cumulative historic road sign observation data for time duration. The method may include determining a sign confidence ratio based on the first sensor data and the second sensor data. The method may include updating the map data based on the sign confidence ratio.
    Type: Application
    Filed: May 22, 2019
    Publication date: November 26, 2020
    Inventors: Alex AVERBUCH, Leon STENNETH
  • Patent number: 10677598
    Abstract: A method, apparatus and computer program product are provided to process probe data in accordance with a map-centric map matching technique. Methods may include obtaining a road link from a database of a plurality of road links; calculating a boundary separation distance for spacing vertices along a length of the road link; determining a sequence of vertices along the road link according to the boundary separation distance; generating, for each vertex, a spatial boundary where an overlap between spatial boundaries of adjacent vertices extends a first distance from the road link, where the first distance is a minimum distance from the road link; and providing for storage of a spatial boundary structure for the road link including the plurality of spatial boundaries associated with the road link.
    Type: Grant
    Filed: May 25, 2018
    Date of Patent: June 9, 2020
    Assignee: HERE Global B.V.
    Inventors: Eric Linder, Dongwook Jang, Alex Averbuch
  • Publication number: 20200167575
    Abstract: A method is provided for prediction of a physical divider on a road. The method comprises retrieving vehicular sensor data, map data, or a combination thereof captured over a predefined period of time for at least one segment of the road. The method further comprises aggregating the respective vehicular sensor data, map data, or the combination thereof for the at least one segment of the road to generate one or more aggregated values. The method further comprises generating output data corresponding to presence of the physical divider in the at least one segment of the road by a machine learning model based on the one or more aggregated values as an input to the machine learning model.
    Type: Application
    Filed: November 28, 2018
    Publication date: May 28, 2020
    Inventors: Amarnath NAYAK, Leon STENNETH, Alex AVERBUCH
  • Patent number: 10551847
    Abstract: An approach is provided for machine learning of physical dividers. The approach, for instance, involves retrieving map data, sensor data, or a combination thereof for a segment of a road. The approach also involves retrieving ground truth data for the segment of the road. The ground truth data, for instance, indicates a true presence or a true absence of the physical divider on the segment of the road. The approach further involves processing the map data, the sensor, or a combination thereof and the ground truth data to train a machine learning model to predict the physical divider using the map data, the sensor data, or a combination thereof as an input. The approach further involves using the trained machine learning model to a generate a physical divider overlay of a map representation of a road network.
    Type: Grant
    Filed: February 6, 2018
    Date of Patent: February 4, 2020
    Assignee: HERE Global B.V.
    Inventors: Leon Stenneth, Alex Averbuch
  • Patent number: 10546200
    Abstract: An approach is provided for detecting a presence of a physical divider on a road segment. The approach, for example, involves determining a number of positive observations of the physical divider on the road segment based on sensor data collected from one or more vehicles traveling the road segment. The approach also involves determining a number of negative observations of the physical divider on the road segment based on the sensor data. The approach further involves calculating a probability of the presence of the physical divider based on the number of the positive observations and the number of the negative observations. The approach further involves updating map data for the road segment to indicate the presence of the physical divider based on determining that the probability of the presence of the physical divider is greater than a threshold value.
    Type: Grant
    Filed: May 23, 2018
    Date of Patent: January 28, 2020
    Assignee: HERE Global B.V.
    Inventors: Alex Averbuch, Leon Stenneth
  • Publication number: 20190360818
    Abstract: A method, apparatus and computer program product are provided to process probe data in accordance with a map-centric map matching technique. Methods may include obtaining a road link from a database of a plurality of road links; calculating a boundary separation distance for spacing vertices along a length of the road link; determining a sequence of vertices along the road link according to the boundary separation distance; generating, for each vertex, a spatial boundary where an overlap between spatial boundaries of adjacent vertices extends a first distance from the road link, where the first distance is a minimum distance from the road link; and providing for storage of a spatial boundary structure for the road link including the plurality of spatial boundaries associated with the road link.
    Type: Application
    Filed: May 25, 2018
    Publication date: November 28, 2019
    Inventors: Eric LINDER, Dongwook JANG, Alex AVERBUCH
  • Publication number: 20190362162
    Abstract: An approach is provided for detecting a presence of a physical divider on a road segment. The approach, for example, involves determining a number of positive observations of the physical divider on the road segment based on sensor data collected from one or more vehicles traveling the road segment. The approach also involves determining a number of negative observations of the physical divider on the road segment based on the sensor data. The approach further involves calculating a probability of the presence of the physical divider based on the number of the positive observations and the number of the negative observations. The approach further involves updating map data for the road segment to indicate the presence of the physical divider based on determining that the probability of the presence of the physical divider is greater than a threshold value.
    Type: Application
    Filed: May 23, 2018
    Publication date: November 28, 2019
    Inventors: Alex AVERBUCH, Leon STENNETH
  • Publication number: 20190362198
    Abstract: An approach is provided for detecting a presence of a physical divider on a road segment. The approach, for example, involves receiving sensor data from a vehicle traveling a road segment. The sensor data indicates a distance from the vehicle to the physical divider, a cross-sensor consistency of detecting the physical divider between at least two sensors of the vehicle, or a combination thereof. The approach also involves determining that the sensor data indicates the presence of the physical divider based on determining that the distance is within distance criteria, the cross-sensor consistency is within consistency criteria, or a combination thereof. The approach further involves updating data provided by a physical divider signal from the vehicle to indicate the presence of the physical divider on the road segment.
    Type: Application
    Filed: May 23, 2018
    Publication date: November 28, 2019
    Inventors: Alex AVERBUCH, Leon STENNETH