Here Global B.v.

Daniel Schmidt

Ofri Rom

Alexander Maryanovsky

Marina Ousov Fridin

Yelena Shnaider

Inna Branevich

Marcelo Savignano

Silviu Zilberman

Harel Primack

Ron Begleiter

Herman Ravkin

Natalia Skorokhod

An approach is provided for discovery of semantic nodes for map-based dynamic location sampling. The approach, for instance, involves identifying a semantic node occurring on a road segment. The semantic node is a point of interest on or near the road segment that is different from beginning node and end node of the road segment. The approach also involves calculating an estimated time of arrival at the semantic node based on historical traversal time data for the road segment. The approach further involves determining a sampling rate for a location sensor of vehicle traveling the road segment based on the estimated time of arrival. The approach further involves configuring the location sensor to collect location data using the sampling rate.

Method and apparatus for discovery of semantic nodes for map-based dynamic location sampling

An approach is provided for path recovery when using map-based dynamic location sampling. The approach, for instance, involves initiating a capture of a current location of a vehicle on a road segment by a location sensor based on a keep-alive sampling rate. The location sensor is configured to operate at a sampling rate that is reduced from a default sampling rate in addition to the keep-alive sampling rate. The approach also involves determining a predicted location of the vehicle based on an estimated time of arrival of the vehicle at an end node of the road segment. The estimated time of arrival is based on historical traversal time data for the road segment. The approach further involves reconfiguring the location sensor to operate at the default sampling frequency based on determining that the predicted location differs from the current location by more than a threshold distance.

Method and apparatus for path recovery when using map-based dynamic location sampling

An approach is provided for map-based dynamic location sampling. The approach, for instance, involves calculating an estimated time of arrival at an end node of a road segment from a beginning node of the road segment based on historical traversal time data for the road segment. The approach also involves determining a sampling rate for a location sensor of a vehicle traveling the road segment based on the estimated time of arrival. The approach further involves configuring the location sensor to collect location data using the sampling rate.

Method and apparatus for map-based dynamic location sampling

An approach is provided for performing ride-sharing functions based on joint motion using multiple sensor data. The approach, for example, involves retrieving a joint motion prediction indicating whether at least two devices are traveling in a same transportation vehicle. The joint motion prediction is computed based on sensor data collected from the at least two devices using at least one sensor type from among a plurality of sensor types. Each sensor type of the plurality of sensor types is associated with a respective joint motion classifier configured to compute a sensor-type joint motion prediction that is used for generating the joint motion prediction. The approach also involves initiating a ride-sharing function for respective users of the at least two devices based on the joint motion prediction.

Method, apparatus, and system for providing ride-sharing functions based on joint motion

An approach is provided for recommending services based on map-based dynamic location sampling. The approach, for instance, involves determining a predicted location of a vehicle on a road segment based on an estimated time of arrival at an end node of the road segment. The approach also involves calculating a difference between the predicted location and an actual location sensed by a location of the vehicle. The approach further involves recommending a service for installation on or near the road segment based on the difference.

Method and apparatus for recommending services based on map-based dynamic location sampling

An approach is provided for detecting joint motion using multiple sensor data. The approach, for example, involves retrieving sensor data at least two devices. The sensor data, for instance, is collected using at least one sensor type from among a plurality of sensor types and wherein, and each sensor type of the plurality of sensor types is associated with a respective joint motion classifier. The approach also involves processing the sensor data using the respective joint motion classifier for said each sensor type of the least one sensor type to compute a respective sensor-type joint motion prediction. The approach further involves processing the respective sensor-type joint motion prediction for said each sensor type using a unified classifier to compute a unified joint motion prediction for the at least two devices. The approach further involves providing the unified joint motion prediction as an output.

Growing community of inventors

Raanana, Israel

Daniel Schmidt