Metraipolis › archive › dc_ac096cff48eb
Nine Trials to Recover: A Reproducible Benchmark for Repertoire-Free Soft-Robot Damage Adaptation — arXiv:2610.07616
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.07616
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T13:12:00.667Z
- SHA-256 of the archived text
6ba4f22f85f4eace28a9c0b089adb4b484f54b241cc767a392b11f258e6f6d3a- Stable URL of this page
https://metraipolis.com/documento/dc_ac096cff48eb
How to cite
Nine Trials to Recover: A Reproducible Benchmark for Repertoire-Free Soft-Robot Damage Adaptation — arXiv:2610.07616 — arXiv (en), https://arxiv.org/abs/2610.07616 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ac096cff48eb (Metraipolis archive dc_ac096cff48eb, sha256 6ba4f22f85f4eace28a9c0b089adb4b484f54b241cc767a392b11f258e6f6d3a)
BibTeX
@misc{dcac096cff48eb,
title = {Nine Trials to Recover: A Reproducible Benchmark for Repertoire-Free Soft-Robot Damage Adaptation — arXiv:2610.07616},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.07616},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ac096cff48eb; sha256 6ba4f22f85f4eace28a9c0b089adb4b484f54b241cc767a392b11f258e6f6d3a},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.07616. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We present a repertoire-free benchmark for soft-robot damage recovery under nine online trials. The protocol pairs damage masks within each morphology, retains a measured nominal fallback, and separates method development from evaluation on new bodies. A Gaussian-process expected-improvement (GP-EI) reference controller adapts actuator phases using three initialization probes and six feedback-selected rollouts. Across two disjoint 75-body cohorts, it outperforms random search, Sobol, CEM, and CMA-ES under equal budgets. GP-EI improves the worst-mask gain on 69/75 confirmation bodies and exceeds these four baselines by 0.235-0.310 mean worst-mask reward. A TuRBO-style local GP is the closest comparator; the paired confidence interval includes zero. Post-confirmation fixed-controller replay finds 5.06 voxel widths of mean recovery together with a 0.0031 increase in worst-mask p99 geometric edge strain; a strict no-added-demand deployment gate retains 48.7% of mean gain. In a frozen development stress test that physically removes 10% of occupied voxels, GP-EI improves 71/75 bodies and exceeds official BoTorch TuRBO by 0.356 mean worst-mask gain. Together, the replayable controllers, body-level inference, and frozen-cohort evaluation provide a reference for measuring the added value of learned damage priors and future adaptation methods. Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.RO, nuovi lavori del giorno). Categorie arXiv: Robotics (cs.RO) ; Systems and Control (eess.SY). Pagina del lavoro: https://arxiv.org/abs/2610.07616 — 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 2026-10-07T12:42:33.551Z dalla pagina https://arxiv.org/list/cs.RO/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).