EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Data-driven discovery of performance boundaries in robotic systems through extreme quantile estimation

Hadi Jahanshahi iD, Zheng Hong Zhu iD

PLOS One · 10.11.2026 · 21 (11) · e0352196

DOI: 10.1371/journal.pone.0352196 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, online erschienen am 10.11.2026. Verfasst von Hadi Jahanshahi und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Mechanical Engineering, York University, Toronto, Ontario, Canada. Hauptthemen laut MEDLINE: Robotics. Die Arbeit nennt 58 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Sciences and Engineering Research Council of Canada.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Characterizing the performance limits of physical systems from experimental data is essential for engineering decision-making, design optimization, and reliability analysis, yet conventional regression models estimate average behavior rather than the boundary of what is achievable. This paper develops a data-driven methodology for discovering nonlinear performance boundaries from experimental observations. The problem is formulated as extreme conditional quantile estimation. A nonparametric binned percentile estimator recovers low-quantile boundary points, and the Bayesian Information Criterion selects an interpretable closed-form law from a library of physically motivated families. Non-asymptotic guarantees are stated in the fixed-design regime the experiments occupy. The method is validated on two real robotic datasets. For UR10e trajectory tracking (30,600 observations), it discovers a saturation boundary E = 7 . 7 4 ( 1 − e − 1 3 . 2 7 S ) mm ( R 2 = 0 . 9 6 2 ; bootstrap 95% CI for E max of [7.05, 9.10] mm) and separates it from a steady-state envelope obeying the lag law e = t lag · v with t lag = 6 5 ms ( R 2 = 0 . 9 9 7 ) once start-up transients are excluded. For planar pushing (40,378 pushes from the MIT MCube dataset), it discovers a power-law boundary with exponent α = 2 . 0 2 (95% CI [1.88, 2.17]), indicating that the root-mean-square force fluctuation grows linearly with speed, consistent with momentum-transfer scaling at the breakdown of the quasi-static contact assumption. Family selection is stable across quantile levels and bootstrap resampling schemes, recovers the correct family in every synthetic replicate at the experimental configurations for the two family classes discovered here, and is confirmed by a prospectively specified experiment. Six of six extrapolation predictions at never-tested speeds landed within 1.2 mm, and a repeat of the protocol reproduced the per-episode 2nd percentiles to a mean absolute deviation of 0.039 mm. Compared with quantile regression, Gaussian process, support vector, and frontier-estimation baselines, the framework provides the tightest interpretable boundary estimates while approaching the target validity level, and it extrapolates where nonparametric envelopes cannot.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

RoboticsBayes TheoremAlgorithmsReproducibility of Results

Autor:innen und Institutionen

  • Department of Mechanical Engineering, York University, Toronto, Ontario, Canada.

ORCID-Profile: Hadi Jahanshahi, Zheng Hong Zhu

Förderung

  • Natural Sciences and Engineering Research Council of Canada

Zitieren

APA

Jahanshahi, H., & Zhu, Z. H. (2026). Data-driven discovery of performance boundaries in robotic systems through extreme quantile estimation. PLOS One, 21(11), e0352196. https://doi.org/10.1371/journal.pone.0352196

Vancouver

Jahanshahi H, Zhu ZH. Data-driven discovery of performance boundaries in robotic systems through extreme quantile estimation. PLOS One. 2026;21(11):e0352196. doi:10.1371/journal.pone.0352196

BibTeX
@article{Jahanshahi2026,
  author = {Jahanshahi, Hadi and Zhu, Zheng Hong},
  title = {Data-driven discovery of performance boundaries in robotic systems through extreme quantile estimation},
  journal = {PLOS One},
  year = {2026},
  volume = {21},
  number = {11},
  pages = {e0352196},
  doi = {10.1371/journal.pone.0352196}
}
Kostenlos starten →