Abstract: An apparatus, method and computer program product are provided for predicting events in which vehicles damage roadside objects. In one example, the apparatus receives input data indicating a first roadside object and contextual information associated with the first roadside object. The apparatus causes a machine learning model to generate output data as a function of the input data, wherein the output data indicate a likelihood in which one or more first vehicles will damage the first roadside object. The machine learning model is trained to generate the output data as a function of the input data by using historical data indicating events in which second vehicles damaged second roadside objects. The historical data indicate first attributes associated with surroundings of the second roadside objects, second attributes associated with the second vehicles, and route maneuver information associated with the second vehicles.

Abstract: An apparatus, method and computer program product are provided for predicting events in which drivers fail to see curbs while the drivers are maneuvering vehicles. In one example, the apparatus receives vehicle attribute data associated with a first vehicle, map data indicating one or more attributes of a road portion including a first curb, and sensor data indicating an orientation of a first driver within the first vehicle. The apparatus causes a machine learning model to render an output as a function of the vehicle attribute data, the map data, and the sensor data. The output indicates a likelihood of which the first driver will not be able to see the first curb at the road portion when the first driver is maneuvering the first vehicle. The machine learning model is trained to predict the output based on historical data indicating events in which second drivers maneuvered second vehicles to encounter the first curb or one or more second curbs.

Abstract: An apparatus, method and computer program product are provided for predicting events in which drivers render aggressive behaviors while maneuvering vehicles. In one example, the apparatus receives input data indicating a target location and including attribute data associated with the target location. The apparatus causes a machine learning model to generate output data as a function of the input data. The output data indicate a likelihood in which a target driver will render an aggressive behavior at the target location while maneuvering a target vehicle. The machine learning model is trained to generate the output data as a function of the input data by using historical data indicating events in which drivers rendered the aggressive behavior while maneuvering vehicles.

Abstract: A network apparatus, for example, obtains probe data corresponding to a respective vehicle making a late lane change while traversing a TME of a traversable network. Location information indicating a location of the late lane change is extracted from the probe data. Map, weather, and/or traffic data for the location is obtained. A late lane change feature description is generated based on information extracted from the probe data and the map, weather, and/or traffic data. A model is trained using a machine learning technique and training data comprising the late lane change feature description. The model is executed to generate a late lane change prediction corresponding to a TME of a digital map. The network apparatus causes at least one of (a) the digital map to be updated, (b) traffic data corresponding to the TME to be updated, or (c) a navigation-related function to be performed based on the prediction.

Abstract: A method, apparatus, and user interface for providing a carjacking detection and prediction system is disclosed. For example, image data of at least one vehicle may be obtained and a carjacking indicator for the vehicle based on the obtained image data is determined. One or more road segments may then be identified, and the determined indicator is associated with the one or more identified road segments to update a map layer of a geographic database and/or perform other actions.

Abstract: An apparatus, method and computer program product are provided for predicting overtaking maneuver events. In one example, the apparatus receives input data including attribute data associated with a location and first travel data associated with a first occupant of a first vehicle. The apparatus causes a machine learning model to generate output data as a function of the input data. The output data indicate a likelihood in which the first vehicle will execute an overtaking maneuver at the location. The machine learning model is trained to generate the output data as a function of the input data by using historical data indicating events in which second vehicles executed the overtaking maneuver. The historical data include second travel data associated with second occupants of the second vehicles.

Abstract: An approach is provided for machine learning of vehicular wait events. The approach, for instance, involves processing a sensor observation to determine a wait event. The wait event indicates that at least one person is in a wait state. The approach also involves processing the sensor observation to determine one or more contextual features associated with a location of the wait event, a time of the wait event, the at least one person, or a combination thereof. The approach further involves determining a ground truth of the wait state. The approach further involves vectorizing the one or more contextual features and the ground truth into a training vector. The approach further involves using the training vector to train a machine learning model to determine predicted waiting data based on one or more input vectors. The approach further involves providing the trained machine learning model as an output.

Abstract: An apparatus, method and computer program product are provided for predicting slipping events for micromobility vehicles. In one example, the apparatus receives input data indicating a target location and including contextual data associated with the target location. The apparatus causes a machine learning model to generate output data as a function of the input data. The output data indicate a likelihood in which a target micromobility vehicle will slip at the target location. The machine learning model is trained to generate the output data as a function of the input data by using historical data indicating events in which micromobility vehicles have slipped. The historical data indicate slip-inducing objects within locations of the events, proximity of sources of the slip-inducing objects relative to the locations, and one or more factors that cause the slip-inducing objects to be disposed within the locations.

Abstract: A method, apparatus, and user interface for a vehicle window damage detection system comprising obtaining image data of at least one vehicle window and determining a window damage indicator based on the obtained image data, identifying one or more road segments, and associating the determined window damage indicator with one or more identified road segments to update a map layer of a geographic database.

Abstract: An approach is provided for determining placement location(s) in a public space for a shared micro-mobility vehicle. The approach involves identifying a candidate placement location in the sidewalk area. The approach also involves determining factor(s) associated with the location and/or nearby location(s) in the sidewalk area. The approach further involves making a determination of whether the location is suitable for temporary placement of a shared micro-mobility vehicle based on whether the location enables: (i) avoiding interference between the vehicle and a current/predicted people flow, a bicycle lane, and/or one or more objects, (ii) preventing the vehicle from hindering usage of a point of interest, a vehicle parking area, and/or a transit station, or (iii) accommodating the vehicle to a sidewalk configuration. The approach further involves based on the determination, outputting an indication of whether the location is suitable for temporary placement of the vehicle.

Abstract: An approach is provided for generating and leveraging map layer(s) representing information associated with Light Detection and Ranging (LiDAR) usage on mobile devices. The approach, for instance, involves determining LiDAR usage data generated by one or more mobile devices. The approach also involves generating a map layer of a geographic database based on the LiDAR usage data. The map layer indicates one or more locations where a LiDAR device was used by the one or more mobile devices based on the LiDAR usage data. The approach further involves providing the map layer as an output.

Abstract: Provided herein is a method for quantifying and measuring human mobility within defined geographic regions and sub-regions. Methods may include: identifying sub-regions within a region; identifying static information associated with the sub-regions from one or more static information sources; obtaining dynamic information associated with the sub-regions from one or more dynamic information sources; determining correlations between elements of the static information associated with a respective sub-region and elements of the dynamic information associated with the respective sub-regions; generating a mobility score for the respective sub-region based, at least in part, on the correlations between the elements of the static information and the elements of the dynamic information associated with the respective sub-region; and providing the mobility score to one or more clients for guiding an action relative to the mobility score.

Abstract: An approach is provided for determining a lane marking confusion index based on lane confusion event detections. The approach, for example, involves detecting, by at least one processor, a number of instances of a lane confusion event associated with a location in a road network. The lane confusion event indicates presence of temporary lane markings in addition to standard lane markings at the location. The approach also involves determining, by the at least on processor, a lane marking confusion index for the location based on the detected number of instances of the lane confusion event in association with the location. The approach further involves storing, by the at least one processor, the lane marking confusion index as a map attribute of the location in a geographic database.

Abstract: An apparatus, method and computer program product are provided for predicting events in which drivers fail to see curbs while the drivers are maneuvering vehicles. In one example, the apparatus receives vehicle attribute data associated with a first vehicle, map data indicating one or more attributes of a road portion including a first curb, and sensor data indicating an orientation of a first driver within the first vehicle. The apparatus causes a machine learning model to render an output as a function of the vehicle attribute data, the map data, and the sensor data. The output indicates a likelihood of which the first driver will not be able to see the first curb at the road portion when the first driver is maneuvering the first vehicle. The machine learning model is trained to predict the output based on historical data indicating events in which second drivers maneuvered second vehicles to encounter the first curb or one or more second curbs.

Abstract: An approach is provided for providing a navigation route for a requesting entity to meet other entities at flexible meeting locations. The approach, for example, involves receiving a request to generate a navigation route to visit a plurality of entities, wherein one or more mobile entities of the plurality of entities are capable of moving from a current location during the navigation route. The approach also involves computing respective isolines around each mobile entity based on a travel distance, a travel time, or a combination thereof that each mobile entity is ready to travel from the current location of each mobile entity during the navigation route. The approach further involves connecting the respective isolines around each mobile entity to determine the navigation route. The approach further involves providing the navigation route as an output.

Abstract: A method, system, and computer readable storage medium are provided for predicting behavior of a vehicle. More specifically, image data of the vehicle is obtained by generating class prediction data for the vehicle and then identifying one or more related points of interest. The method, system, and computer readable storage medium then predict the behavior of the vehicle based upon the one or more points of interest and the class prediction data.

Abstract: An apparatus, method and computer program product are provided for predicting road locations that are likely to induce tire pressure changes. In one example, the apparatus receives historical data of an event in which a first vehicle is impacted by a first tire pressure change at a first road segment. The historical data indicates point-of-interest (POI) information associated with the first road segment. The apparatus trains a prediction model using the historical data. The prediction model is configured to determine a likelihood in which a second road segment induces a second tire pressure change for a second vehicle based on POI information associated with the second road segment.

Abstract: An approach is provided for extracting point-of-interest features based on depth sensor data captured by mobile devices. The approach involves, for instance, receiving a Light Detection and Ranging (LiDAR) scan of a location captured using a LiDAR sensor of a portable device. The approach also involves determining a context of the location, a point of interest (POI) associated with the location, or a combination thereof. The approach further involves selecting a feature recognition parameter based on the context. The feature recognition parameter performs a feature detection analysis of a scenery depicted in the scan. The approach further involves initiating the feature detection analysis of the scan based on the feature recognition parameter to identify a feature, an attribute of the feature, or a combination thereof in the scenery.

Abstract: A method, apparatus, and user interface for providing a vehicle change of direction detection system is disclosed. For example, image data of at least one vehicle may be obtained and a change of direction indicator for the vehicle based on the obtained image data is determined. One or more road segments may then be identified and the determined indicator is associated with the one or more identified road segments to update a map layer of a geographic database and/or perform other actions.

Abstract: An apparatus, method and computer program product are provided for predicting charging efficiency rates for solar-powered vehicles. In one example, the apparatus receives historical data of events in which solar-powered vehicles equipped with solar panels were electrically charged by receiving solar beams at the solar panels. The historical data indicate factors of the events that induced objects forming on the solar panels and obstructing, at least in part, the solar beams. The apparatus uses the historical data to train a machine learning model to output a charging efficiency rate of a target solar-powered vehicle as a function of at least one attribute associated with a location.