EUVIMEDEUVIMED entdecken
Crossref

Cross-platform learnable fuzzy gain-scheduled proportional-integral-derivative controller tuning via physics-constrained meta-learning and reinforcement learning adaptation

JiaHao Wu, ShengWen Yu

Robotica · 2026-04 · 44 (4) · 1231-1272

DOI: 10.1017/s0263574726103518 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Robotica, online erschienen am 11.06.2026. Verfasst von JiaHao Wu und 1 weiteren Autor:innen. Die Arbeit nennt 40 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Motivation and gap: PID-family controllers remain a pragmatic choice for many robotic systems due to their simplicity and interpretability, but tuning stable, high-performing gains is time consuming and typically non-transferable across robot morphologies, payloads, and deployment conditions. Fuzzy gain scheduling can provide interpretable online adjustment, yet its per-joint scaling and consequent parameters are platform dependent and difficult to tune systematically. Proposed approach: We propose a hierarchical framework for cross-platform tuning of a learnable fuzzy gain-scheduled PID (LF-PID). The controller uses shared fuzzy membership partitions to preserve common error semantics, while learning per-joint scaling and Takagi–Sugeno consequent parameters that schedule PID gains online. Combined with physics-constrained virtual robot synthesis, meta-learning provides cross-platform initialization from robot physical features, and a lightweight reinforcement learning (RL) stage performs deployment-specific refinement under dynamics mismatch. Starting from three base simulated platforms, we generate 232 physically valid training variants via bounded perturbations of mass ( plus or minus ± $\pm$ 10%), inertia ( plus or minus ± $\pm$ 15%), friction ( plus or minus ± $\pm$ 20%), and damping ( plus or minus ± $\pm$ 30%). Results and insight: We evaluate cross-platform generalization on two distinct systems (a 9-DOF serial manipulator and a 12-DOF quadruped) under multiple disturbance scenarios. The RL adaptation stage improves tracking performance on top of the meta-initialized controller, with up to 80.4% error reduction in challenging high-load joints (12.36 Superscript ring ∘ $^\circ$ right arrow → $\rightarrow$ 2.42 Superscript ring ∘ $^\circ$ ) and 19.2% improvement under parameter uncertainty. We further identify an optimization ceiling effect : online refinement yields substantial gains when the meta-initialized baseline exhibits localized deficiencies, but provides limited improvement when baseline quality is already uniformly strong.

Zitieren

APA

Wu, J., & Yu, S. (2026). Cross-platform learnable fuzzy gain-scheduled proportional-integral-derivative controller tuning via physics-constrained meta-learning and reinforcement learning adaptation. Robotica, 44(4), 1231-1272. https://doi.org/10.1017/s0263574726103518

Vancouver

Wu J, Yu S. Cross-platform learnable fuzzy gain-scheduled proportional-integral-derivative controller tuning via physics-constrained meta-learning and reinforcement learning adaptation. Robotica. 2026;44(4):1231-1272. doi:10.1017/s0263574726103518

BibTeX
@article{Wu2026,
  author = {Wu, JiaHao and Yu, ShengWen},
  title = {Cross-platform learnable fuzzy gain-scheduled proportional-integral-derivative controller tuning via physics-constrained meta-learning and reinforcement learning adaptation},
  journal = {Robotica},
  year = {2026},
  volume = {44},
  number = {4},
  pages = {1231--1272},
  doi = {10.1017/s0263574726103518}
}
Kostenlos starten →