← Back to all news
arXiv Machine Learning By Rana Danesh, Pari Qarehdaghi, Farrokh Janabi-Sharifi

Constraint-Aware Physics-Informed Neural Networks for Static Shape Estimation of Co-Manipulative Continuum Robots

Read the original on arXiv Machine Learning →

The paper introduces a constraint‑aware physics‑informed neural network (PINN) for estimating the static shape of co‑manipulative continuum robots (CCRs). By integrating projected static equilibrium and geometric loop‑closure residuals, the PINN enforces both mechanical and closed‑chain constraints. Experiments show that, even with limited and noisy data, the PINN outperforms a purely data‑driven ANN, achieving markedly lower configuration, equilibrium, and closed‑chain errors, and delivering inference times orders of magnitude faster than traditional nonlinear solvers.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv AI
Jun 6

Finite Element-Based Material Learning via Automatic Differentiation: Learning constitutive neural network models from full-field deformation data

arXiv:2606. 05199v1 Announce Type: cross Abstract: The identification of constitutive neural network models from heterogeneous full-field deformation data provides a robust alternative to traditional calibration methods based on homogeneous stress-strain experiments, particularly given the high dimensionality of trainable parameters.

By Matthias Knipper, Chenyi Ji, Malte Brand, Kevin Linka
More like this →
arXiv Machine Learning
Sep 10

Hyperelastic constitutive model discovery with differentiable finite elements and structure-preserving neural networks

The paper introduces a differentiable finite element framework that discovers hyperelastic constitutive laws from limited experimental data, such as boundary-only displacement measurements and global reaction forces. By embedding the nonlinear finite element equilibrium problem into the learning loop, the method evaluates candidate strain‑energy densities through the deformation fields they produce, enforcing mechanical equilibrium as a constraint. The constitutive response is modeled with Hyperelastic Neural Networks, a structure‑preserving class that guarantees physical admissibility, including residual energy and stress‑free conditions, frame indifference, isotropic symmetry, polyconvexity, coercivity, and controlled volumetric growth. Numerical experiments in two and three dimensions show accurate recovery of hyperelastic isotropic responses, robustness to noise, and generalization across geometries, loading, and boundary conditions.

By Francesco Regazzoni
More like this →
arXiv Machine Learning
Jun 19

Physics-Informed Discovery of Yield Functions in Plasticity via Convex Neural Representations

arXiv:2606. 19375v1 Announce Type: new Abstract: Identifying anisotropic yield functions remains challenging since yielding is not directly observed in full-field mechanical measurements, directional calibration can require many loading directions, and selecting an appropriate analytical form is nontrivial.

By Hyeonbin Moon, Donghyuk Cho, Jecheon Yu, Jeong Whan Yoon, Seunghwa Ryu
benchmarks
More like this →
arXiv Machine Learning
Sep 25

AFT Neural Function Approximators for 1D Nonlinear Force Laws

The paper proposes using neural networks to replace the iterative force evaluation in the harmonic balance method for systems with nonlinear contacts and friction. These networks map displacement Fourier coefficients directly to nonlinear force coefficients and supply Jacobians via automatic differentiation, allowing the existing solver and continuation algorithms to remain unchanged. By learning individual nonlinear elements—such as cubic, unilateral, and Jenkins springs—under physics‑based nondimensionalization and phase normalization, a single trained network can handle a wide range of parameters, enabling a reusable library of nonlinear‑element surrogates for complex mechanical systems.

By Miriam Goldack, Johann Gro{\ss}, Malte Krack, Merten Stender
More like this →