Metraipolis › archive › dc_2e1ad9bf8380

Safety-aware Skill Adaptation for Reinforcement Learning in Dynamic Environments — arXiv:2609.11433

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.11433
License (as archived)
CC0-1.0
Archived
2026-10-16T06:35:58.784Z
SHA-256 of the archived text
ebc6e2f96eefd4c7827fd203c99d7133491aa5962c7423df6298e6e49d1e7f4a
Stable URL of this page
https://metraipolis.com/documento/dc_2e1ad9bf8380

How to cite

Safety-aware Skill Adaptation for Reinforcement Learning in Dynamic Environments — arXiv:2609.11433 — arXiv (en), https://arxiv.org/abs/2609.11433 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2e1ad9bf8380 (Metraipolis archive dc_2e1ad9bf8380, sha256 ebc6e2f96eefd4c7827fd203c99d7133491aa5962c7423df6298e6e49d1e7f4a)
BibTeX
@misc{dc2e1ad9bf8380,
  title = {Safety-aware Skill Adaptation for Reinforcement Learning in Dynamic Environments — arXiv:2609.11433},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.11433},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2e1ad9bf8380; sha256 ebc6e2f96eefd4c7827fd203c99d7133491aa5962c7423df6298e6e49d1e7f4a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.11433. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Skill adaptation frameworks based on reinforcement learning often require restrictive assumptions to maintain stability, such as fixed observations or tightly controlled exploration schedules. In cluttered and dynamic environments, however, unrestricted exploration can lead to unsafe behaviour and unstable learning, particularly when task-relevant observations lie near obstacles or involve moving objects. In this work, we present Dist-GPRL, a distance-aware and safety-guided reinforcement learning framework for structured robot skill adaptation. Building upon Gaussian Process (GP)-based skill parameterisation, our framework sequentially adapts overlapping local windows of sparse trajectory via-points rather than modifying the complete skill at every policy step. Raw policy outputs are correlated through the GP covariance structure, producing temporally coherent trajectory updates while reducing the action-space and credit-assignment difficulties associated with global trajectory adaptation. Safety is incorporated through two complementary forms of guidance. A safe-subspace prior derived from the Hausdorff Approximation Planner (HAP) biases policy exploration toward feasible regions, while dynamically updated distance field clearance and gradient rewards provide local obstacle awareness. A trajectory-kinematics similarity regulariser further preserves the demonstrated velocity and acceleration characteristics during adaptation. We evaluate the framework on two dynamic object-manipulation tasks in simulation and transfer the learned policy to real-world robot execution. Experimental results demonstrate higher task success, lower collision frequency, and more stable learning than the baselines, while preserving the kinematic characteristics of the demonstrated skill.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-11 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.11433 — 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 2026-10-16T06:10:18.226Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).