Efficient trajectory planning for urban intersections is currently one of the\nmost challenging tasks for an Autonomous Vehicle (AV). Courteous behavior\ntowards other traffic participants, the AV's comfort and its progression in the\nenvironment are the key aspects that determine the performance of trajectory\nplanning algorithms. To capture these aspects, we propose a novel trajectory\nplanning framework that ensures social compliance and simultaneously optimizes\nthe AV's comfort subject to kinematic constraints. The framework combines a\nlocal continuous optimization approach and an efficient driver model to ensure\nfast behavior prediction, maneuver generation and decision making over long\nhorizons. The proposed framework is evaluated in different scenarios to\ndemonstrate its capabilities in terms of the resulting trajectories and\nruntime.\n