Abstract: In an example embodiment, a computer-implemented method is disclosed that generates a spectral signature describing one or more dynamic objects and a scene layout of a current road scene; identifies, from among one or more scene clusters included in a familiarity graph associated with a user, a road scene cluster corresponding to the current road scene; determine a position of the spectral signature relative to other spectral signatures comprising the identified road scene cluster; and generates a familiarity index estimating familiarity of the user with the current road scene based on the position of the spectral signature. The method can further include determining an assistance level based on the familiarity index of the user; and providing one or more of an auditory instruction, a visual instruction, and a tactile instruction to the user via one or more output devices of a vehicle at the determined assistance level.

Abstract: In an example embodiment, a computer-implemented method is disclosed that receives road scene data and vehicle operation data from one or more sensors associated with a first vehicle on a road segment; receives situation ontology data; automatically generates a semantic road scene description of the road segment using the road scene data, the vehicle operation data, and the situation ontology data; and transmits, via a communication network, the semantic road scene description to one or more other vehicles associated with the road segment. Automatically generating the semantic road scene description of the road segment can include determining lane-level activity information for each lane based on lane information and dynamic road object information and determining a lane-level spatial layout for each lane based on the lane information and the dynamic road object information.

Abstract: In an example embodiment, a computer-implemented method is disclosed that generates a spectral signature describing one or more dynamic objects and a scene layout of a current road scene; identifies, from among one or more scene clusters included in a familiarity graph associated with a user, a road scene cluster corresponding to the current road scene; determine a position of the spectral signature relative to other spectral signatures comprising the identified road scene cluster; and generates a familiarity index estimating familiarity of the user with the current road scene based on the position of the spectral signature. The method can further include determining an assistance level based on the familiarity index of the user; and providing one or more of an auditory instruction, a visual instruction, and a tactile instruction to the user via one or more output devices of a vehicle at the determined assistance level.

Abstract: In an example embodiment, a computer-implemented method is disclosed that receives road scene data and vehicle operation data from one or more sensors associated with a first vehicle on a road segment; receives situation ontology data; automatically generates a semantic road scene description of the road segment using the road scene data, the vehicle operation data, and the situation ontology data; and transmits, via a communication network, the semantic road scene description to one or more other vehicles associated with the road segment. Automatically generating the semantic road scene description of the road segment can include determining lane-level activity information for each lane based on lane information and dynamic road object information and determining a lane-level spatial layout for each lane based on the lane information and the dynamic road object information.

Abstract: A system and method for estimating a place affinity for a user is disclosed. The system comprises a gathering module, a communication module and a scoring module. The gathering module receives a place and retrieves rich place data associated with the place. The communication module retrieves user profile data associated with a user and a place affinity model associated with the user. The scoring module estimates an affinity score for the place using the place affinity model based at least in part on the rich place data and the user profile data.

Abstract: A system and method for estimating a place affinity for a user is disclosed. The system comprises a gathering module, a communication module and a scoring module. The gathering module receives a place and retrieves rich place data associated with the place. The communication module retrieves user profile data associated with a user and a place affinity model associated with the user. The scoring module estimates an affinity score for the place using the place affinity model based at least in part on the rich place data and the user profile data.