Metraipolis › archive › dc_90587fd7210f

Imitation Learning for Autonomous Driving in CARLA — arXiv:2609.17757

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.17757
License (as archived)
CC0-1.0
Archived
2026-10-15T16:59:08.109Z
SHA-256 of the archived text
25ebf70ed86706c4c8e2d84dd350928a969e5ce5c43a2b2505ed9eaddd736aed
Stable URL of this page
https://metraipolis.com/documento/dc_90587fd7210f

How to cite

Imitation Learning for Autonomous Driving in CARLA — arXiv:2609.17757 — arXiv (en), https://arxiv.org/abs/2609.17757 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_90587fd7210f (Metraipolis archive dc_90587fd7210f, sha256 25ebf70ed86706c4c8e2d84dd350928a969e5ce5c43a2b2505ed9eaddd736aed)
BibTeX
@misc{dc90587fd7210f,
  title = {Imitation Learning for Autonomous Driving in CARLA — arXiv:2609.17757},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.17757},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_90587fd7210f; sha256 25ebf70ed86706c4c8e2d84dd350928a969e5ce5c43a2b2505ed9eaddd736aed},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.17757. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Behavioral cloning trains a policy offline on expert demonstrations, but deployment is closed loop: each action affects the observations the policy receives next. We study how much closed-loop driving competence a compact multimodal policy can acquire from offline demonstrations in the CARLA simulator. The policy uses five-frame histories of RGB images, LiDAR, vehicle telemetry, and lane waypoints to predict throttle, brake, and steering at 20 Hz. Demonstrations were collected in three stages, ending with a systematic route-generation procedure that enumerates spawn points and feasible maneuvers and verifies completed autopilot routes. The released 1.36 million parameter policy was trained on 236,882 windows, representing about 3.3 hours of driving from 448 captures. The resulting policy drives autonomously for hours on training and held-out routes. In our runs, it did so without collisions and also transferred qualitatively to an unseen CARLA town with different road geometry. We also observed recovery from large trajectory deviations, although we do not claim systematic recovery without controlled evaluation. We report offline metrics and distinguish measured results from qualitative closed-loop observations. We release the code, trained checkpoint, ONNX model, data sample, and an evidence audit for the reported claims.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-17 in cs.RO).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.17757 — 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 2026-10-15T16:13:27.349Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).