Physics-Informed Neural Network of a Flexible Robotic Manipulator: Closed-Loop Experimental Validation
Abstract
The demand for robotic manipulators has increased because of their precision, speed, and cost-efficiency in complex or hazardous tasks. Flexible robotic manipulators, unlike rigid ones, offer lower mass and energy consumption, enabling advanced applications across various fields. Despite these advantages, the mass reduction of these manipulators can lead to undesired effects, including decreased precision, increased sensitivity to parametric uncertainties, coupled dynamics, and increased oscillations caused by their inherent flexibility. Moreover, the modeling complexity of such mechanical systems represents a significant challenge, since multiple degrees of freedom must be considered. In this study, a physics-informed neural network (PINN) is designed to estimate the dynamic behavior of a flexible-link manipulator. First, a dataset is created by executing different trajectories (i.e., different rotation angles) of the flexible manipulator. Based on the dataset, the PINN is then trained using time and strain signals as inputs to estimate the angular displacement, combining a data-driven loss with a physics-based loss derived from the system’s dynamic model. Finally, the PINN model is investigated experimentally to assess the closed-loop strategy and evaluate its efficiency and reproducibility in recognizing the mechanical system behavior. Therefore, the results show that the PINN and closed-loop experimental validations are consistent with the proposed method.
Related
- Experimental validation of a fast control-oriented, physics-informed surrogate model for plasma equilibrium reconstruction in the TCV tokamak
- Physics-guided machine learning for predicting complete tool influence functions in flexible ball-end polishing
- Accelerating noisy variational quantum algorithms with physics-informed denoising networks
- Active matter within flexible boundaries: a novel experimental approach with T. aceti nematodes
- [SUPERSEDED] Physics-Informed AI and Quantum Technologies for Certifiable Real-Time Control of Compact Fusion Generators
BibTeX
@article{tanaka2026physicsinformed,
title = {{Physics-Informed Neural Network of a Flexible Robotic Manipulator: Closed-Loop Experimental Validation}},
author = {Tony Jun Tanaka and Renan Sanches Geronel and Rafaël Teloli and Maíra Martins da Silva},
journal = {Machines},
year = {2026},
month = jul,
doi = {10.3390/machines14080854},
url = {https://hal.science/hal-05805111v1},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Physics-Informed Neural Network of a Flexible Robotic Manipulator: Closed-Loop Experimental Validation
AU - Tony Jun Tanaka
AU - Renan Sanches Geronel
AU - Rafaël Teloli
AU - Maíra Martins da Silva
PY - 2026
DA - 2026/07/28
JO - Machines
DO - 10.3390/machines14080854
UR - https://hal.science/hal-05805111v1
AB - The demand for robotic manipulators has increased because of their precision, speed, and cost-efficiency in complex or hazardous tasks. Flexible robotic manipulators, unlike rigid ones, offer lower mass and energy consumption, enabling advanced applications across various fields. Despite these advantages, the mass reduction of these manipulators can lead to undesired effects, including decreased precision, increased sensitivity to parametric uncertainties, coupled dynamics, and increased oscillations caused by their inherent flexibility. Moreover, the modeling complexity of such mechanical systems represents a significant challenge, since multiple degrees of freedom must be considered. In this study, a physics-informed neural network (PINN) is designed to estimate the dynamic behavior of a flexible-link manipulator. First, a dataset is created by executing different trajectories (i.e., different rotation angles) of the flexible manipulator. Based on the dataset, the PINN is then trained using time and strain signals as inputs to estimate the angular displacement, combining a data-driven loss with a physics-based loss derived from the system’s dynamic model. Finally, the PINN model is investigated experimentally to assess the closed-loop strategy and evaluate its efficiency and reproducibility in recognizing the mechanical system behavior. Therefore, the results show that the PINN and closed-loop experimental validations are consistent with the proposed method.
SN - 2075-1702
ER -