Here Global B.v.

Gm Global Technolgoy Operations, Inc.

Jane MacFarlane

Bo Xu

Matei Stroila

Jeffrey Minoru Adachi

Robert Grossman

Collin Bennett

James Pivarski

Andrew Lewis

Antonio Haro

Stephen C Habermas

Davide Pietrobon

Kai-Ten Feng

Ole Henry Dorum

Aaron J Dannenbring

Xiaoqing Liu

Ognjen Todic

Craig Barnes

Tiffany Barkley

Robert Berry

An approach is provided for next token prediction based on previously observed tokens. The approach involves receiving an observed time series of tokens, wherein each of the tokens represents an observed data pattern. The approach also involves adding a most recent token from the observed time series of tokens into a variable token set. The approach further involves processing a historical token set to determine a historical token sequence comprising the variable token set followed by a next token. The approach further involves recursively adding a next most recent token from the observed time series of tokens into the variable token set for processing until the next token following the variable token set in the determined historical token sequence is unique or meets a target number of possible predictions. The approach further involves presenting the next token as a predicted next token of the observed time series of tokens.

Method and apparatus for next token prediction based on previously observed tokens

An approach is provided for semantic-free traffic prediction. The approach involves dividing a travel-speed data stream into a plurality of travel-speed patterns. The travel-speed data stream represents vehicle travel speeds occurring in a road network. The approach also involves representing each of the plurality of travel-speed patterns by a respective token. The respective token is selected from a dictionary of tokens representing a plurality of travel-speed templates determined from historical travel-speed data. The approach further involves matching a sequence of the respective tokens corresponding to said each of the plurality of travel-speed patterns to a best-fit sequence of tokens determined from the historical travel-speed data. The approach further involves determining a predicted sequence of tokens based on the best-fit sequence of tokens, and generating a traffic prediction for the road network based on the predicted sequence of tokens.

Method and apparatus for providing semantic-free traffic prediction

Drone space is defined according to a building model and a buffer space. At least one three-dimensional geometry is identified from the building model. The buffer space is calculated from the three-dimensional geometry. Coordinates for a drone air space are defined based on the buffer space. At least one path segment may be identified based on the coordinates for the drone air space, and the coordinates for drone air space are stored in a map database in association with the at least one path segment.

Air space maps

A method comprising determining speed-time cluster application histogram data set for a link segment that comprises a plurality of speed-time cluster application histogram data elements, each speed-time cluster application histogram data element identifying a speed-time cluster and an applicable duration of the speed-time cluster for the link segment throughout a histogram duration, for each speed-time cluster application histogram data element, determining a free-flow speed that is representative of a non-congestion speed indicated by the speed-time cluster, determining a historically normalized free-flow speed for the link segment that is a weighted average of the free-flow speed determined for each speed-time cluster application histogram data element weighted by the applicable duration of the speed-time cluster application histogram data element, and identifying a transit speed of the link segment as being the historically normalized free-flow speed is disclosed.

Determination of a free-flow speed for a link segment

The disclosed embodiments relate to prediction of traffic dynamics. A descriptive model is provided that uses historical probe data to create 'tidal-like' patterns for the usual dynamics on the road network and creates a framework for taking a future time, e.g. in terms of month, day, time, and suggesting a typical speed for the specified road network link at that specific time. With this model, better predictions for estimated time of arrival will be derived. As opposed to blindly extrapolating from a static model, the disclosed embodiments dynamically adapt to current conditions using real time data to adapt, based on current conditions, the model from which a predicted speed may be determined.

Adaptive traffic dynamics prediction

An approach is provided for classifying probe data into qualitative categories to determine a point of interest. The approach involves processing and/or facilitating a processing of probe data to determine one or more trajectories associated with one or more probes. The approach also involves determining one or more clips of the one or more trajectories associated with one or more locations at which the one or more probes lingered based, at least in part, on at least one space threshold value, at least one time threshold value, or a combination thereof. The approach further involves causing, at least in part, an extraction of one or more probe parameter values from the one or more clips. The approach also involves causing, at least in part, a classification of the one or more probe parameter values into one or more qualitative categories. The approach further involves determining one or more points of interest, one or more characteristics of the one or more points of interest, or a combination thereof associated with the one or more locations based, at least in part, on the one or more qualitative categories.

Method and apparatus for providing qualitative trajectory analytics to classify probe data

An approach is provided for generating trajectory bundles for map data analysis. The approach involves receiving probe data associated with the bounded geographic area. The probe data are collected from sensors of a plurality of devices traveling in the bounded geographic area, and includes probe points indicating a position, a heading, a speed, a time, or a combination thereof. The approach also involves constructing a plurality of trajectories from the probe points to represent respective movement paths of said each of the plurality of devices. The approach further involves computing similarities among a plurality of curves represented by the plurality of trajectories. The approach further involves clustering the plurality of trajectories into trajectory bundles based on the similarities with each bundle representing a possible maneuver within the bounded geographic area. The approach further involves generating a map of the bounded geographic area based on the trajectory bundles.

Method and apparatus for providing trajectory bundles for map data analysis

An approach is provided for identifying objects present in mesh representation of a geo-location, generating accurate 3D models for the objects, and aligning the 3D models to their corresponding objects in an application. The approach comprises processing and/or facilitating a processing of textured three-dimensional mesh data in one or more regions of interest to cause, at least in part, a generation of at least one two-dimensional depth image representation. The approach further comprises causing, at least in part, a filtering of the textured three-dimensional mesh data in the one or more regions of interest to remove mesh data below at least one threshold height based, at least in part, on the at least one two-dimensional depth image representation. Additionally, the approach comprises processing and/or facilitating a processing of the filtered textured three-dimensional mesh data to cause, at least in part, a generation of at least one partial three-dimensional model, including one or more upper facades above the at least one threshold height, of one or more objects located within the one or more regions of interest.

Method and apparatus for identifying buildings in textured 3D mesh data and generating 3D building models

An approach is provided for providing adaptive location sampling in mobile devices. The approach involves determining one or more maneuvers from among a plurality of one or more links representing a localized area of a transportation network. Each of the one or more maneuvers is a combination of two or more adjacent links of the one or more links. The approach also involves determining a road length and a speed attribute for each link in said each maneuver. The approach further involves calculating a travel time for said each maneuver based on the road length and the speed attribute of said each link. The approach further involves calculating a sampling interval for the mobile device traveling in the localized area based on the travel time. The mobile device is configured to collect probe data using one or more sensors at the sampling interval while traveling in the localized area.

Method and apparatus for providing adaptive location sampling in mobile devices

An approach is provided for sharing annotations and recalling geospatial information. The approach involves processing and/or facilitating a processing of communication information exchanged between a plurality of devices engaged in a communication session to cause, at least in part, a parsing of geospatial information from the communication information. The approach also involves determining whether the geospatial information meet, at least in part, one or more logic thresholds. The one or more logic thresholds are for determining a potential relevance of the geospatial information to the communication session, the plurality of devices, one or more users of the plurality of devices, or a combination thereof. The approach further involves causing, at least in part, a presentation of the geospatial information to the plurality of devices, the one or more users, or a combination thereof based, at least in part, on the determination.

Method and apparatus for providing shared annotations and recall of geospatial information

An approach is provided for classifying a traffic jam from probe data. The approach involves receiving the probe data that is map-matched to a roadway on which the traffic jam is detected. The probe data is collected from one or more vehicles traveling the roadway. The approach also involves determining a jam area of the roadway based on the probe data. The jam area corresponds to one or more segments of the roadway affected by the traffic jam. The approach further involves determining a set of features indicated by the probe data from a portion of the probe data collected from the jam area. The approach further involves classifying, using a machine learning classifier, the traffic jam as either a recurring traffic jam or a non-recurring traffic jam based on the set of features.

Method and apparatus for classifying a traffic jam from probe data

An approach is provided for processing and/or facilitating a processing of probe trace data to determine one or more mode indicators, wherein the one or more mode indicators include, at least in part, one or more attributes of the probe trace data. The approach involves causing, at least in part, a modeling of one or more statistical patterns of at least one pedestrian mode of transport, at least one non-pedestrian mode of transport, or a combination thereof based, at least in part, on determining one or more probabilities that one or more mode indicators are associated with the at least one pedestrian mode of transport, the at least one non-pedestrian mode of transport, or a combination thereof. The approach also involves causing, at least in part, a classification of other probe trace data as being associated with the at least one pedestrian mode of transport or the at least one non-pedestrian mode of transport based, at least in part, on the one or more mode indicators that are associated with the other probe trace data and the one or more statistical patterns.

Growing community of inventors

Oakland, CA, United States of America

Jane MacFarlane