Stabilizing Trajectory Outputs in End-to-end Autonomous Driving via SC-IMM Based Teacher Signals

End-to-end autonomous driving models commonly predict future waypoints from sensor inputs and convert them into vehicular control commands through a downstream controller. However, conventional waypoint-based imitation learning mainly minimizes coordinate-level errors, making it difficult to capture scene-dependent path-speed changes and temporal instability across waypoint outputs. In this study, we propose an offline teacher-signal generation and learning method for trajectory-output stabilization based on a scene-conditioned interacting multiple model (IMM) to mitigate this issue. The proposed method converts expert trajectories into path-speed states and performs IMM updates conditioned on scene cues to generate path-speed teacher labels and mode posterior probabilities. The generated signals were added to the original trajectory loss as auxiliary supervision during training, while the inference structure and waypoint controller remained unchanged. In closed-loop evaluation on 100 short routes in CARLA Town12, the proposed method improved the driving score by 28.0% and reduced collisions/km by 62.3% compared with the baseline, while also improving jerk and trajectory-variation metrics. These results demonstrate that offline teacher signals embedding scene-conditioned motion-model cues can guide trajectory-output driving models toward more stable closed-loop behavior.