A Probabilistic Framework for Trajectory Prediction in Traffic Utilizing Driver Characterization

While autonomously operated vehicles are on the horizon, they will be required to share the road with human drivers for a foreseeable future. To ensure safe operation beyond human capabilities, interaction with other traffic participants will be required to navigate cooperatively through complex traffic situations. Identification and characterization of driving styles in combination with the behavior of other traffic participants is anticipated to aid in effectively analyzing risks under autonomous driving. This study presents a novel, interaction-aware framework fulfilling this need for combined behavior identification and driving style characterization of other participants.