Abstract: A method is provided for selective processing of sensor data, and more particularly, to parsing sensor data from a data stream to identify sensor data relevant to specific requests, and processing the relevant data based on the type of request. Methods include: receiving a campaign management request defining requested source data metrics; receiving source data from a plurality of sources within a geographic area; determining a subset of the source data that satisfies the requested source data metrics; processing the subset of the source data satisfying the requested source data metrics to obtain observations; and updating map data of a map database based on the observations.

Abstract: A method, system and computer program product for map-matching a probe to a point-of-interest (POI) during a trip by a vehicle in a region are disclosed. The method includes identifying POIs in the region; determining, for probes in the region, a latitude location of the probes, a longitude location of the probes and a data collection time stamp for the probes; determining, for each of the probes in the region, a proximity between the probes and the POIs within a predetermined radius of the probes; determining, for each of the POIs, a POI geographic coverage area; calculating an observed POI probability from the proximity and the POI geographic coverage area; and using a Hidden Markov Model to sequentially process the observed POI probability from a predetermined number of probes of the trip and to predict a most likely POI at which the probes are clustered.

Abstract: An approach is provided for a runaway vehicle detection system. The approach, for example, involves processing sensor data to detect that a vehicle is involved in or predicted to be involved in a runaway vehicle event. The approach also involves processing map data, the sensor data, or a combination thereof to determine a runaway vehicle safety location based on at least one attribute of the vehicle. The approach further involves generating an alert message indicating the runaway vehicle safety location. The approach further involves providing the alert message for display on a device associated with the vehicle. In one embodiment, the approach further involves mapping the runaway vehicle safety location, the runaway vehicle event, or a combination thereof to digital map of a geographic database.

Abstract: The disclosure provides a traffic pattern data calculation system, a method and a computer program product for calculating traffic pattern data. The traffic pattern data calculation system is configured to receive, for a road segment, historical traffic data and complementary data, for a predefined time window. The traffic pattern data calculation system is configured to extract from the received historical traffic data and the complementary data, secondary traffic data based on a filtering criterion. The traffic pattern data calculation system is configured to calculate the traffic pattern data for the road segment based on the extracted secondary traffic data. In addition, the traffic pattern data calculation system is configured to update a map database with the traffic pattern data of the road segment based on the calculation.

Abstract: An approach is provided for zone-to-zone trip reliability. The approach involves, for example, determining probe data collected from a plurality of sensors of a plurality of probe vehicles traveling in a geographic area of interest. The approach also involves processing the probe data to determine a plurality of vehicle trips. The approach further involves clustering the plurality of vehicle trips into one or more zone-to-zone trip categories based on the origin zones and destination zones of the plurality of vehicle trips. The approach further involves, for each zone-to-zone trip category of the one or more zone-to-zone trip categories, computing a zone-to-zone trip category reliability metric based on the plurality of vehicle trips clustered into each zone-to-zone trip category. The approach further involves providing the zone-to-zone trip category reliability metric for each zone-to-zone trip category as an output.

Abstract: A system for generating navigation instructions for delivery of a cargo is provided. The system is configured to obtain geographic area information relating to a geographic area, determine cargo information relating to the cargo, determine one or more aerial routes for a delivery of the cargo based on the geographic area information and the cargo information, estimate a risk value for navigation of an aerial vehicle across each of the one or more aerial routes, identify an aerial route from the one or more aerial routes having lowest estimated risk value based on the estimated risk values for the one or more aerial routes, and generate the navigation instructions for navigation of the aerial vehicle along the identified aerial route for delivery of the cargo.

Abstract: A method is inter alia disclosed, performed at least by a mobile device or a part thereof, the method comprising: providing an indication of a trajectory of the mobile device to a remote server; obtaining, from a remote server, an electronic horizon comprising electronic horizon data for one or more ADAS functions of the mobile device, wherein the electronic horizon has been constructed from map data by the server specifically for enabling the mobile device to provide or for supporting the mobile device in providing the one or more ADAS functions, wherein the electronic horizon covers one or more potential paths predicted to be taken by the mobile device based on the indication of the trajectory; and supporting or performing at least one of the one or more ADAS functions at least partially based on the electronic horizon.

Abstract: A method is provided for analyzing data to identify turning circles within a road network, and to generate map data corresponding to the identified turning circles. Methods may include: receiving data corresponding to a geographical region; identifying, from the data, a turning circle in the geographical region; determining a size of the turning circle; generating, at the point location, map data geometry of the turning circle of the size determined; and updating a digital map database to include the map data geometry of the turning circle of the size determined at the point location, where the digital map database provides for at least one of route guidance or at least semi-autonomous vehicle control. According to some embodiments, the data corresponding to the geographical region includes at least one of satellite imagery or aerial imagery.

Abstract: A method, apparatus and computer program product are configured to dynamically augment ionospheric correction data. A method receives, from a requesting device, a request for grid layout data, where the grid layout data is associated with one or more geographical areas experiencing atmospheric delay incurred with a satellite-based positioning technique. The method transmits, in response to the request for the grid layout data, a grid layout definition message comprising a grid layout definition associated with the grid layout data associated with the one or more geographical areas. The method generates correction data based in part on the grid layout data, where the correction data is configured to correct the atmospheric delay incurred with the satellite-based positioning technique. The method also generates correction messages comprising at least a portion of the correction data and transmits the correction messages to the requesting device based on a dynamic correction data update rate.

Abstract: A method, system and computer program product for automated detection of map road segments requiring speed limit correction is disclosed. The method includes receiving a request from a quality estimation scheduler; initiating a computer program that automatically: receives a set of map road segments for a given region; receives a speed traffic report for the map road segments during a predefined time interval; identifies a subset of the map road segments that satisfy a predefined traffic speed criteria; further reduces the subset of the map road segments by corroborating with complementary speed limit signs information; compiles a list of map road segments requiring speed limit correction; comparing traffic speeds of the reduced subset with corresponding speed limit signs reported by a map database; and updating map speed limits where required based on the compared traffic speeds.

Abstract: A method, system and computer program product for probe provider attribution are disclosed. The method includes receiving from speed probe sensors, for a given region and within a predefined time window, speed probe data from a plurality of corresponding probe providers reporting both consumer vehicle speed probe data and truck speed probe data; combining the speed probe data from the plurality of corresponding probe providers into a single speed probe set; identifying an optimal number of speed clusters for the combined speed probe set; mapping each of the speed probe data from a plurality of corresponding probe providers to one of the optimal number of speed clusters and calculate a distribution of probe provider probes among the speed clusters; and assigning an attribute to each of the plurality of corresponding probe providers based on the distribution of probe provider probes and according to predefined criterion.

Abstract: A method, system and computer program product for map-matching a probe to a point-of-interest (POI) during a trip by a vehicle in a region are disclosed. The method includes identifying POIs in the region; determining, for probes in the region, a latitude location of the probes, a longitude location of the probes and a data collection time stamp for the probes; determining, for each of the probes in the region, a proximity between the probes and the POIs within a predetermined radius of the probes; determining, for each of the POIs, a POI geographic coverage area; calculating an observed POI probability from the proximity and the POI geographic coverage area; and using a Hidden Markov Model to sequentially process the observed POI probability from a predetermined number of probes of the trip and to predict a most likely POI at which the probes are clustered.

Abstract: A system for automated charging of electric vehicles obtains a first route between a source and a destination of the vehicle and computes charging data for the vehicle based on the first route. The system determines one or more private charging stations along the first route, each private charging station being associated with a respective host user. Using one or more constraints associated with each private charging station, the charging data, and a host mobility graph of the host user of each private charging station, the system filters the one or more private charging stations. The system further generates navigation recommendation data for the vehicle, based on the first route and the result of the filtration and outputs the navigation recommendation data.

Abstract: In an example embodiment, an apparatus obtains map information corresponding to an event location. Based at least in part on the map information corresponding to the event location, the apparatus determines at least one event action to be performed by a vehicle responsive to a vehicle location indicating a location of the vehicle satisfying a proximity criteria corresponding to the event location. The apparatus causes one or more components of the vehicle to perform the at least one event action responsive to determining that the vehicle location satisfies the proximity criteria corresponding to the event location.

Abstract: Systems and methods for optimizing routes for vehicles are provided. For example, a method for optimizing routes for vehicles includes receiving electric vehicle charging constraints of one or more vehicles. The method also includes receiving information corresponding to one or more navigation constraints associated with the one or more vehicles. The method also includes determining a route that satisfies the electric vehicle charging constraints of the one or more vehicles and at least one of the one or more navigation constraints associated with the one or more vehicles. The method also includes providing the route to the one or more vehicles.

Abstract: A system for determination of accessibility of a usage of vehicles in a geographical region is provided. The system obtains a first set of parameters associated with a consumption of a battery by a set of vehicles in a first geographical region. The system further obtains a second set of parameters associated with at least one of the set of vehicles or a set of charging points within the first geographical region. The system further determines a first index based on the obtained first set of parameters. The system further determines a second index based on the obtained second set of parameters. The system further determines a first accessibility score based on the first index and the second index. The first accessibility score is indicative of an accessibility of a usage of the set of vehicles in the first geographical region. The system further outputs the determined first accessibility score.

Abstract: A method, apparatus and computer program product are provided to determine one or more probe point data objects and/or validate one or more probe point data objects for use with determination of traffic conditions. A determined probe point data object may be determined and/or updated with one or more probe point data objects which exclude any probe point data objects determined to correspond to an off-road location. A validated probe point data object may additionally or alternatively be determined using one or more first validation sequence check operations and using one or more second validation sequence check operations. The determined probe point data object and/or validated probe point data object may be used to determine one or more traffic conditions, and as a result, traffic condition determinations may be determined more accurately and efficiently.

Abstract: A method is provided to using a generative adversarial network to generate map geometry from images representing probe data. Methods may include: receiving a rasterized image representative of probe data within a geographic area, where each pixel of the rasterized image includes a property representing at least one component of the probe data; generating a prediction image of road features within the geographic area using a generative adversarial network based on trained model parameters and the rasterized image; determining one or more map elements based, at least in part, on the prediction image and georeferenced locations of the road features within the prediction image; and updating a map of the geographic area with one or more map elements.

Abstract: A method, system and computer program product for determining personalized recommendations of EVCPs based on contextual charging behavior of a user are disclosed. The method includes determining that the user needs to charge the electric vehicle; determining contextual conditions related to personal preferences of the user, a vehicle type of the electric vehicle and/or a location of the electric vehicle; determining features and contextual conditions related to the EVCPs; preparing a list of EVCPs in a predetermined distance from the location of the electric vehicle; ranking, by a trained machine learning model, the list of EVCPs based on the contextual conditions related to personal preferences of the user, the vehicle type of the electric vehicle and/or the location of the electric vehicle; and providing, by a vehicle interface system, a portion of the ranked list of the one or more EVCPs.

Abstract: An approach is provided for detecting objects and associated pose from imagery data. The approach, for instance, involves processing an image using a feature representation network to generate a set of points representing the object detected in the image. Each point, for instance, has an attribute indicating a geometric part of the object. The approach also involves using the feature representation network to construct a bounding box around the set of points. The approach further involves determining a pose of the object based on the bounding box and the attribute indicating the geometric part of the object for each point. The approach further involves providing the object, the pose, or a combination thereof as an output.