Metraipolis › archive › dc_5ffc530d0eee
Stabilizing Trajectory Outputs in End-to-End Autonomous Driving via SC-IMM Based Teacher Signals — arXiv:2609.21404
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.21404
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-10T02:30:08.796Z
- SHA-256 of the archived text
7c1cbb9b95d37c5f600c6f4efe8dc0de23b6847009570397dd94511cede14732- Stable URL of this page
https://metraipolis.com/documento/dc_5ffc530d0eee
How to cite
Stabilizing Trajectory Outputs in End-to-End Autonomous Driving via SC-IMM Based Teacher Signals — arXiv:2609.21404 — arXiv (en), https://arxiv.org/abs/2609.21404 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5ffc530d0eee (Metraipolis archive dc_5ffc530d0eee, sha256 7c1cbb9b95d37c5f600c6f4efe8dc0de23b6847009570397dd94511cede14732)
BibTeX
@misc{dc5ffc530d0eee,
title = {Stabilizing Trajectory Outputs in End-to-End Autonomous Driving via SC-IMM Based Teacher Signals — arXiv:2609.21404},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.21404},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5ffc530d0eee; sha256 7c1cbb9b95d37c5f600c6f4efe8dc0de23b6847009570397dd94511cede14732},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.21404. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
End-to-End autonomous driving models commonly predict future waypoints from sensor inputs and convert them into vehicle 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 paper, we propose an offline teacher-signal generation and learning method for trajectory-output stabilization based on a Scene-Conditioned Interacting Multiple Model (SC-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 are added to the original trajectory loss as auxiliary supervision during training, while the inference structure and waypoint controller remain unchanged. In closed-loop evaluation on 100 short routes in CARLA Town12, the proposed method improved the driving score by 28.0% and reduced Collision/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. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-21 in cs.RO). Categorie arXiv: Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2609.21404 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-10T02:09:55.343Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).