Metraipolis › archive › dc_7a18042727cd

Potential-Field Action Representation for Reinforcement Learning in Contact-Rich Manipulation — arXiv:2609.21609

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.21609
License (as archived)
CC0-1.0
Archived
2026-10-10T01:12:43.972Z
SHA-256 of the archived text
d4b98d30262d157ad9fb637d32cbf67e1963aa1883c943fd131058c977a9212f
Stable URL of this page
https://metraipolis.com/documento/dc_7a18042727cd

How to cite

Potential-Field Action Representation for Reinforcement Learning in Contact-Rich Manipulation — arXiv:2609.21609 — arXiv (en), https://arxiv.org/abs/2609.21609 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7a18042727cd (Metraipolis archive dc_7a18042727cd, sha256 d4b98d30262d157ad9fb637d32cbf67e1963aa1883c943fd131058c977a9212f)
BibTeX
@misc{dc7a18042727cd,
  title = {Potential-Field Action Representation for Reinforcement Learning in Contact-Rich Manipulation — arXiv:2609.21609},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.21609},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7a18042727cd; sha256 d4b98d30262d157ad9fb637d32cbf67e1963aa1883c943fd131058c977a9212f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.21609. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Model-free reinforcement learning can acquire contact-rich robotic manipulation skills through trial-and-error interaction, but it often requires the policy to learn both task strategy and low-level motion generation. In this setting, the action representation is critical because it determines how policy outputs are converted into robot motion, shaping both exploration and physical execution. Direct Cartesian command interfaces require the policy to generate motion at every decision step, coupling task-level adaptation with continuous low-level control and increasing the learning burden. We propose PA-RL, a reinforcement-learning framework that uses artificial potential fields as the action representation. Instead of commanding motion directly, the policy adapts the parameters of an energy-like potential field, which generates a state-dependent guidance direction executed through a Cartesian impedance controller. We evaluate PA-RL on peg-in-hole insertion, a representative contact-rich task with nonlinear dynamics and discontinuous contact transitions. In simulation, PA-RL is compared with Cartesian velocity, Cartesian pose, and variable-impedance action spaces using the same RL algorithm. PA-RL is the only method to reach a 100% evaluation success rate within the allotted training time, while the best baseline reaches 92.6%. It also reduces joint-torque variation by 55.4% and Cartesian acceleration variation by 70.8% relative to the best baseline, without explicit motion-quality penalties in the reward. The simulation-trained policy further completes 9/9 real-robot insertions without fine-tuning, demonstrating the deployment feasibility of the learned potential-field interface.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-21 in cs.AI).
Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.21609 — 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 2026-10-10T00:23:42.549Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).