Methods and apparatuses for late lane change prediction and mitigation

An apparatus comprising at least one processor and at least one memory storing computer program code, the at least one memory and the computer program code configured to, with the processor, cause the apparatus to at least:

• generate respective late lane change feature descriptions for a plurality of late lane changes, a respective late lane change feature description comprising information regarding a respective late lane change and at least one of map data, weather data, or traffic data corresponding to a respective location of the respective late lane change;
• and
• train a late lane change model using a machine learning technique based at least in part training data comprising the respective late lane change feature descriptions;
• wherein, the late lane change model is trained such that the late lane change model is configured to receive an input feature description characterizing a prediction scenario corresponding to a traversable map element and provide a late lane change prediction corresponding to the prediction scenario, the late lane change prediction configured to be used for at least one of
• (a) updating a digital map, (b) updating traffic data corresponding to the traversable map element, or (c) used as input for performing a navigation-related function.

A computer program product comprising at least one non-transitory computer-readable storage medium having computer-readable program code portions stored therein, the computer-readable program code portions comprising executable portions configured, when executed by a processor of an apparatus, to cause the apparatus to:

• access a late lane change model that was trained using a machine learning technique based at least in part on training data comprising a plurality of late lane change feature descriptions, a respective late lane change feature description comprising information characterizing a respective late lane change and at least one of map data, weather data, or traffic data corresponding to a respective location of the respective late lane change;
• execute the late lane change model to generate a late lane change prediction corresponding to a traversable map element of a digital map that provides a representation of the traversable network;
• and
• cause at least one of (a) the digital map to be updated based at least in part on the late lane change prediction, (b) traffic data corresponding to the traversable map element to be updated based at least in part on the late lane change prediction, or (c) a navigation-related function to be performed using at least a portion of the late lane change prediction as input.