Metraipolis › archive › dc_30ca6bc017be

Compliance for Free: Learning Identifiable Impedance via Bilateral Teleoperation — arXiv:2609.19976

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.19976
License (as archived): CC0-1.0
Archived: 2026-10-10T05:25:37.578Z
SHA-256 of the archived text: 318e65dfb9d915989e339772c53488714682435448ae59a154ce4cfc66eca84b
Stable URL of this page: https://metraipolis.com/documento/dc_30ca6bc017be

How to cite

Compliance for Free: Learning Identifiable Impedance via Bilateral Teleoperation — arXiv:2609.19976 — arXiv (en), https://arxiv.org/abs/2609.19976 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_30ca6bc017be (Metraipolis archive dc_30ca6bc017be, sha256 318e65dfb9d915989e339772c53488714682435448ae59a154ce4cfc66eca84b)

BibTeX

@misc{dc30ca6bc017be,
  title = {Compliance for Free: Learning Identifiable Impedance via Bilateral Teleoperation — arXiv:2609.19976},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.19976},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_30ca6bc017be; sha256 318e65dfb9d915989e339772c53488714682435448ae59a154ce4cfc66eca84b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.19976. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Vision-language-action models tell a robot where to move, but not how hard to push. Contact-rich tasks depend on that second quantity, compliance, yet no widely used demonstration interface records it. The obstacle is identifiability as realized pose and measured force cannot separate the operator's intended equilibrium from their stiffness, so VR controllers, SpaceMouse and handheld grippers cannot supply compliance supervision even in principle. Prior compliance-output policies work around this with hand-specified task structure, privileged simulation contact state, or dedicated force and tactile hardware. Four-channel bilateral teleoperation removes the ambiguity directly by using the leader arm as a separate measurement of the intended equilibrium, making per-axis stiffness identifiable by regression using only the joint-torque sensing already on the manipulator. This yields per-timestep, direction-dependent compliance labels at zero annotation cost, which we use to fine-tune a VLA to emit stiffness alongside pose. On a Franka Research 3 wiping task, ours is the only policy of five whose contact force changes when the instruction asks for a firm wipe rather than a normal one (6.4N (normal) to 9.1N (firm) RMS, Cohen's d = 0.89, p = 0.023

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/2609.19976 — 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 2026-10-10T04:47:38.871Z 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).