Metraipolis › archive › dc_d629b8fbc0f2

Learning Reliable Parking Policies via Offline Reinforcement Learning with Quantized Action Representations — arXiv:2609.19894

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.19894
License (as archived)
CC0-1.0
Archived
2026-10-10T05:25:35.737Z
SHA-256 of the archived text
88ff13df5538636c01ffcca0df626871b314ad2f7d82b10aa39d45c7bc9e424e
Stable URL of this page
https://metraipolis.com/documento/dc_d629b8fbc0f2

How to cite

Learning Reliable Parking Policies via Offline Reinforcement Learning with Quantized Action Representations — arXiv:2609.19894 — arXiv (en), https://arxiv.org/abs/2609.19894 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d629b8fbc0f2 (Metraipolis archive dc_d629b8fbc0f2, sha256 88ff13df5538636c01ffcca0df626871b314ad2f7d82b10aa39d45c7bc9e424e)
BibTeX
@misc{dcd629b8fbc0f2,
  title = {Learning Reliable Parking Policies via Offline Reinforcement Learning with Quantized Action Representations — arXiv:2609.19894},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.19894},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d629b8fbc0f2; sha256 88ff13df5538636c01ffcca0df626871b314ad2f7d82b10aa39d45c7bc9e424e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.19894. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Parking is a routine yet safety-critical task for autonomous vehicles operating in urban environments. However, cluttered and weakly structured parking spaces, compounded by the interactive uncertainty from surrounding vehicles, hinder reliable maneuver generation. To address these challenges, we develop a waypoint-level offline reinforcement learning framework for interaction-aware autonomous parking. Specifically, a dedicated parking dataset is constructed from hierarchical expert rollouts with rotational waypoint augmentation, covering both non-interactive scenarios and interactive ones. The policy is then conditioned on a compact state representation, in which LiDAR-based obstacle features are adapted to the target pose via feature-wise linear modulation. A state-conditioned tokenizer further quantizes continuous waypoint sequences into discrete action tokens, over which conservative Q-learning is performed to suppress value overestimation on poorly supported actions. Extensive closed-loop experiments are conducted in the high-fidelity CARLA simulator. The proposed framework attains the highest parking success rate among all baselines and transfers reliably to unseen parking slots.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-18 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.19894 — 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 2026-10-10T04:47:38.862Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).