Abstract: An approach is provided for optimizing imagery for map feature extraction. The approach involves, for instance, receiving a plurality of drives. Each drive is a continuous data collection event in which imagery is captured by a sensor of a vehicle or device as the vehicle or device travels along a path. Each drive comprises the imagery and metadata indicating location coordinates and timestamp data for each captured image or video. The approach also involves determining a quantified redundancy between each drive and one or more selected drives. The quantified redundancy is based on a percentage of overlap between each drive and one of the selected drives. The approach further involves performing a classification of each drive as redundant or not redundant based on a redundancy threshold. The approach further involves filtering the plurality of drives based on the classification, and providing the filtered plurality of drives as an output.

Abstract: An approach is provided for providing localization through multiple triangulation processes. The approach, for instance, involves detecting a plurality of objects from a set of images, performing 3-point triangulation on the plurality of objects to generate a 3-point triangulation result, and performing one or more triangulations on the 3-point triangulation result to generate one or more triangulation results. The one or more triangulations is 4-or-more-point triangulation, 2-point triangulation, or a combination thereof. The one or more triangulation results is a 4-or-more-point triangulation result, a 2-point triangulation result, or a combination thereof. The approach further involves using a clustering model to consolidate the 3-point triangulation result and the one or more triangulation results as a consolidated localization result and outputting the consolidated localization result.

Abstract: A system, method, and apparatus for generating specification data of one or more charging units are provided. The system retrieves training data associated with each charging unit of the one or more charging units. The training data of each charging unit of the one or more charging units comprises charging event data pertaining to one or more charging events associated with the corresponding charging unit of the one or more charging units. The system trains a machine learning model to predict specification data of a charging unit based on the training data. The system receives input data associated with the charging unit and causes the machine learning model to predict the specification data of the charging unit based on the input data. The system generates a vehicle navigation function for a vehicle based on the specification data.

Abstract: A system, method, apparatus, etc., for retrieving or receiving historical graphical user interface (GUI) interaction data based on a received search query from a first user. The search query includes a request for map data of a geographical region. A cluster is determined for at least one location in the geographical region based on the historical GUI interaction data and the search query. The rendering of the map data is controlled on a map user-interface (UI), based on the at least one location of the cluster.

Abstract: An apparatus and a method for determining a status period of a charging point are provided. The apparatus receives charging point data associated with a charging point. The charging point data indicates one or more status types associated with the charging point and one or more periods associated with each of the one or more status types. The apparatus further determines error data associated with each of the one or more status types based on the charging point data. The apparatus further determines status period data associated with each of the one or more status types based on the error data, the status period data indicating an estimated period of each of the one or more status types. The apparatus further outputs the status period data.

Abstract: A system, method, apparatus, etc. for controlling a platoon of vehicles comprising receiving location data for at least a first vehicle of the platoon of vehicles; map matching the location data for the first vehicle to a road network, and identifying a slope or a curve in the road network in response to the matched location data, wherein the slope exceeds a road grade threshold or the curve exceeds as road curve threshold. The system, method, apparatus, etc. may then calculate, by a processor, a distance to the slope or curve for the first vehicle of the platoon of vehicles; and then calculate, by the processor, a platoon command, wherein the order of vehicles or spacing between at least two vehicles in the platoon is modulated within the distance to the slope or curve for the first vehicle of the platoon.

Abstract: The disclosure provides a system, a method, and a computer program product for detecting a road work zone. The method comprises detecting a road object based on sensor data and map data. The method may include determining a first location associated with the road object based on location of a vehicle capturing the road object at a time of road object sighting and the sensor data. The method may include, based on image data captured by the vehicle at the time of road object sighting, determining a road object type and supplemental information associated with the road object. The method further includes, detecting the road work zone based on the first location, the road object type, and the supplemental information.

Abstract: An approach is provided for map matching a vehicle path network to a road topology network of a digital map. The approach, for instance, involves aggregating vehicle trajectory data into a vehicle path network that is a directed graph comprising a plurality of nodes. The approach also involves segmenting the vehicle path network into a plurality of linear features. Each linear feature of the plurality of linear features connects two nodes of the plurality of nodes in the vehicle path network. The approach further involves using a path-based map matcher to separately match each linear feature by incorporating context of the vehicle path network to a map topology of a digital map to generate map matching results. The approach further involves aggregating the map matching results of each linear feature into an overall map matching result for the directed graph, and providing the overall map matching result as an output.

Abstract: A method, apparatus, and computer program product are provided for anonymizing a trajectory. Methods may include: receiving a sequence of probe data points defining a trajectory having an origin location and a destination location; determining, from the origin location, an origin area that includes the origin location; determining, from the destination location, a destination location that includes the destination location; determining an origin timestamp based on a first probe data point of the trajectory outside of the origin area; determining a destination timestamp based on a last probe data point of the trajectory outside of the destination area; generating a shared trajectory beginning with the first probe data point of the trajectory outside of the origin area and ending with the last probe data point of the trajectory outside of the destination area; and publishing the shared trajectory including the origin timestamp and the destination timestamp to a service provider.

Abstract: An approach is provided for an electric vehicle navigation system. For example, a destination is received as input. A geographic database is accessed to obtain data that represents a first road segment of a route to the destination. The data of the first road segment includes a first elevation coefficient of energy consumption associated with a first elevation change. The geographic database is accessed to obtain data that represents a second road segment of the route. The data of the second road segment includes a second elevation coefficient of energy consumption associated with a second elevation change. The first elevation coefficient is different than the second elevation coefficient. Energy consumption by the vehicle along the route is calculated based on the first elevation coefficient and the second elevation coefficient. Data representing energy consumption for the route is outputted as a function of the calculated energy consumption.

Abstract: A system, method, apparatus, etc., for electric vehicle supply equipment management. More specifically, at least an apparatus which may detect and/or predict the various data points such as availability data or wait time(s) of one of more vehicle supply equipment(s) such as a charge point, charge plug, etc. This information may be deduced from charge point data operators or generated by independent analysis.

Abstract: A system, method, apparatus, etc., for crowdsourced determination of queuing times of charging stations for electric vehicles (EVs), wherein the queuing and charging statistics may be determined based on queuing times of EVs at charging stations. Location data of an EV and a charging station may be received by the apparatus. Based on these location data, charging station metadata, and other data, the queuing times may be determined. The queuing and times may be used to generate and transmit recommendation data for EVs.

Abstract: A method, apparatus and computer program product are provided to automatically detect changes in width of road segments in real-time or near real-time using probe data, such as probe data collected from vehicle and/or mobile devices traveling along a road segment. Probe data collected in real-time or near real-time is partitioned in order to identify width-defining portions of the probe data. The width-defining portions may be representative of the laterally-extreme lanes of the road segment, such as the left-most lane and the right-most lane. The width-defining portions are compared to corresponding width-defining portions of historical probe data to determine measures indicative of whether a road segment has expanded or narrowed. Indications of detected segment width changes may be provided to drivers and/or other systems or users. For example, map data for the road segment may be updated to reflect a detected width expansion or narrowing of the road segment.

Abstract: An approach is provided for securing vehicles from relay attacks using map database. The approach, for example, involves determining a first location of a vehicle and a first location of a user associated with the vehicle. The approach further involves determining, using a map database, at least one signal dead zone within a first pre-determined distance from the first location of the vehicle. A distance between the first location of the user associated with the vehicle and the first location of the vehicle exceeds the first pre-determined distance. The approach further involves generating a validation output in response to the first location of the user associated with the vehicle exceeding the first pre-determined distance from the first location of the vehicle.

Abstract: A system to determine a stranded electric vehicle resilience index of an area for an electric vehicle (EV) is disclosed. The system may use an API to determine areas in a region with minimal EV charging capabilities; generate a first trained machine learning model to predict a first probability for a given EV to be stranded in the areas based on a training feature dataset and the areas with minimal EV charging capabilities; label the areas as critical areas based on the first probability; generate a second trained machine learning model based on the labelled critical areas; and predict, using the second trained machine learning model and current features of a link to be traveled by the EV as derived from a map and one or more sensors along the link, a second probability for the EV to be stranded on the link.

Abstract: An apparatus, method and computer program product are provided for determining a location for deploying an electric vehicle charging unit (EVCU). In one example, an apparatus divides a zone into a plurality of subregions and causes a machine learning model to output a probability of which an EVCU is needed at each of the plurality of subregion based on one or more attributes associated with the subregion. The apparatus generates one or more clusters within the zone, where each of the one or more clusters include one or more of the plurality of subregions. The apparatus calculates a value for each of the one or more clusters based on the probability associated with each subregion within said cluster. The apparatus selects one of the one or more clusters based on the value and assigns a location within the one of the one or more clusters for deploying the EVCU.

Abstract: An approach is disclosed for verifying a lane closure using probe data. The approach involves, for example, receiving probe data collected from a probe device traveling a road link. The approach also involves performing a spatial clustering of the probe data with respect to a longitudinal axis of the road link. The approach further involves comparing the spatial clustering of the probe data to a historical spatial clustering of historical probe data of the road link to determine a cluster shift, wherein the cluster shift indicates that a cluster of the spatial clustering has shifted spatially to the left or right relative to at least one other cluster of the historical clustering. The approach also involves detecting a lane closure on the road link based on determining that the cluster shift is greater than a shift distance threshold. The approach further involves providing the detected lane closure as an output.

Abstract: A system is disclosed for estimating intersection connection point. The system, for example, obtains first feature data for a first feature line, obtains second feature data for a second feature line. The second feature line is within a first predefined threshold from the first feature line. The system identifies an intersection area based on the first feature data and the second feature data, the intersection area comprising a candidate intersection point; estimates an offset value for the first feature line and the second feature line within the intersection area; estimates heading information for the candidate intersection point based on the first feature data, the second feature data and the intersection area; and estimates the intersection connection point for the first feature line and the second feature line based on the candidate intersection point, the offset value and the heading information.

Abstract: A method, apparatus and computer program product for determining a road work event confidence are described herein. In the context of a method, the method may determine a road network speed profile corresponding with a road work event location. The method may determine, based at least in part on probe data corresponding with the road work event location, a probe speed profile. The method may determine the road work event confidence based at least in part on evaluation of the road network speed profile and the probe speed profile. Evaluation of the road network speed profile and the probe speed profile may comprise identifying a plurality of road segments corresponding with the road work event location and correlating road network speed profile characteristics and probe data characteristics for each respective road segment.

Abstract: The disclosure provides a method, a system, and a computer program product for generating map data. The method comprises obtaining, from one or more user equipment, user preference data associated with a region, wherein the user preference data is associated with an indication of at least one of routing of traffic through a region or not routing of traffic through the region. The method may further include calculating, by a processor, an aggregate value for the region based on the obtained user preference data and generating map data indicative of the calculated aggregate value for the region.