Metraipolis › archive › dc_d569d4e603ec

The Robot Is Not Its Description: GaugeBench for Representation Robustness in Morphology-Aware Policies — arXiv:2610.07597

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.07597
License (as archived)
CC0-1.0
Archived
2026-10-07T11:42:31.018Z
SHA-256 of the archived text
df644934e727e1c6e8db48b2ff2e46e13b41bdd9eed18ca635a0070faa2483e1
Stable URL of this page
https://metraipolis.com/documento/dc_d569d4e603ec

How to cite

The Robot Is Not Its Description: GaugeBench for Representation Robustness in Morphology-Aware Policies — arXiv:2610.07597 — arXiv (en), https://arxiv.org/abs/2610.07597 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d569d4e603ec (Metraipolis archive dc_d569d4e603ec, sha256 df644934e727e1c6e8db48b2ff2e46e13b41bdd9eed18ca635a0070faa2483e1)
BibTeX
@misc{dcd569d4e603ec,
  title = {The Robot Is Not Its Description: GaugeBench for Representation Robustness in Morphology-Aware Policies — arXiv:2610.07597},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.07597},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d569d4e603ec; sha256 df644934e727e1c6e8db48b2ff2e46e13b41bdd9eed18ca635a0070faa2483e1},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.07597. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

A robot description does more than specify a physical mechanism: it also encodes arbitrary conventions, such as joint-axis direction, joint-angle zero, and the order and names of links and joints. Morphology-aware policies consume interfaces built from these descriptions, yet cross-embodiment evaluation typically changes the robot while keeping those conventions fixed. This leaves a simple question unanswered: does behavior survive when the robot stays fixed but its description changes? GaugeBench isolates this case by rewriting a fixed mechanism under physically equivalent conventions, verifying that its physics and policy interface are preserved, and then evaluating the same policy weights. The result is stark: three MetaMorph policies score 4030.6 on 80 familiar robots, but only 51.6 when those same robots are equivalently re-described, while 98 genuinely held-out robots score 1489.6. A new description can therefore be more damaging than a new robot. Tracing the failure reveals that axis reversal alone reproduces the collapse, joint-angle zero changes are nearly harmless, and reordering lies between them; moreover, changing joint-state and torque coordinates alone is sufficient to cause the failure, while changing description-derived features alone is not. The same phenomenon appears in ModuMorph and an unrelated PyBullet framework. Yet it is not irreversible: exact two-description transport restores the original controller, and training across equivalent axis conventions raises retained return under axis reversal from 3.6% to 80.6%. Together, these results separate mechanism robustness from representation robustness and show that cross-embodiment evaluation should test both.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Robotics (cs.RO) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.07597 — 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 2026-10-07T11:19:24.903Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).