Metraipolis › archive › dc_ff30af015fca

DODGER: Safety-Guided Reinforcement Learning for Robot Navigation Among Dynamic Obstacles — arXiv:2609.38873

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.38873
License (as archived): CC0-1.0
Archived: 2026-10-07T15:11:44.132Z
SHA-256 of the archived text: 80d6b75f9f9468ffa25f7d23aaea3642264054bc5af4a593f7dc6cecad355bc3
Stable URL of this page: https://metraipolis.com/documento/dc_ff30af015fca

How to cite

DODGER: Safety-Guided Reinforcement Learning for Robot Navigation Among Dynamic Obstacles — arXiv:2609.38873 — arXiv (en), https://arxiv.org/abs/2609.38873 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ff30af015fca (Metraipolis archive dc_ff30af015fca, sha256 80d6b75f9f9468ffa25f7d23aaea3642264054bc5af4a593f7dc6cecad355bc3)

BibTeX

@misc{dcff30af015fca,
  title = {DODGER: Safety-Guided Reinforcement Learning for Robot Navigation Among Dynamic Obstacles — arXiv:2609.38873},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.38873},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ff30af015fca; sha256 80d6b75f9f9468ffa25f7d23aaea3642264054bc5af4a593f7dc6cecad355bc3},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.38873. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Robots operating in human-centered environments must safely navigate among multiple dynamic obstacles to avoid collisions with people and surrounding infrastructure. Control barrier functions (CBFs) provide an effective mechanism for safety filtering, and recent CBF-based reinforcement learning (RL) methods embed such safety information into learned policies. However, executing only safety-filtered actions during training can restrict policy exploration, a limitation that becomes particularly consequential in dynamic scenes where safety depends on relative robot-obstacle motion. We propose DODGER, a safety-guided RL framework that directly executes policy-generated actions to drive training rollouts while using CBF-filtered references and constraint violations to shape the policy toward collision-avoidance behavior. We evaluate DODGER through a Dubins-car safety analysis and demonstrate goal-directed navigation among multiple dynamic obstacles in full-order humanoid simulation and real-world humanoid experiments using LiDAR-based perception, without a runtime safety filter.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-10-01 in cs.RO).
Categorie arXiv: Robotics (cs.RO) ; Systems and Control (eess.SY).
Pagina del lavoro: https://arxiv.org/abs/2609.38873 — 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 2026-10-07T14:44:47.386Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).