Metraipolis › archive › dc_e459a67e60e4

CALM: Current Aligned Link Manipulation for Single Arm Oversized Object Lifting — arXiv:2609.29017

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.29017
License (as archived): CC0-1.0
Archived: 2026-10-08T07:16:38.225Z
SHA-256 of the archived text: 075bc6c3ac07832017b799099dc65fba8b52b161907732c3277ba56e925caea2
Stable URL of this page: https://metraipolis.com/documento/dc_e459a67e60e4

How to cite

CALM: Current Aligned Link Manipulation for Single Arm Oversized Object Lifting — arXiv:2609.29017 — arXiv (en), https://arxiv.org/abs/2609.29017 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e459a67e60e4 (Metraipolis archive dc_e459a67e60e4, sha256 075bc6c3ac07832017b799099dc65fba8b52b161907732c3277ba56e925caea2)

BibTeX

@misc{dce459a67e60e4,
  title = {CALM: Current Aligned Link Manipulation for Single Arm Oversized Object Lifting — arXiv:2609.29017},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.29017},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e459a67e60e4; sha256 075bc6c3ac07832017b799099dc65fba8b52b161907732c3277ba56e925caea2},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.29017. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Most robots manipulate objects solely with their end effectors, whereas humans flexibly leverage different body parts, such as the forearm and elbow, especially when handling oversized objects. Learning such whole-arm manipulation is chal-lenging due to long-horizon sparse rewards, limited contact sens-ing, and the sim-to-real gap in contact and actuator dynamics. To address these challenges, we propose Current-Aligned Link Manipulation, a framework for learning long-horizon contact-rich manipulation using motor current as joint load related feedback. Three stage-specific policies first learn repositioning, grasping, and lifting using privileged simulation information, and a stage router sequences them to generate complete task demonstrations. For sim-to-real transfer, a causal current mapper predicts physical motor current from simulated joint histories, aligning the actuator current observation between simulation and hardware. A unified student policy then learns from these demonstrations using only deployable sensor observations and is further refined with DAgger. The task policies are trained entirely in simulation, and the final student is deployed on hardware. Experiments demonstrate 76.2% (762/1000 trials) complete-task success in simulation and 73.3% success (22/30 trials) on the physical robot for sequential oversized-object lifting.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-25 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.29017 — 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 2026-10-08T06:38:53.766Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).