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.
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.
arXiv:2602.16365v2 Announce Type: replace-cross Abstract: Flexible endoscopic continuum manipulators offer high dexterity and access to complex anatomy, but nonlinear hysteresis limits feedforward co...
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.
arXiv:2602. 17750v2 Announce Type: replace-cross Abstract: A key problem of solid mechanics is the identification of the constitutive law of a material, that is, the relation between strain history and stress.
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.
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.
arXiv:2607. 06479v1 Announce Type: new Abstract: Physics-informed neural networks (PINNs) provide a promising framework for solving partial differential equations while embedding the underlying physical laws directly into the learning process.
Physics-informed neural networks (PINNs) provide a promising framework for solving partial differential equations while embedding the underlying physical laws directly into the learning process. This study presents a PINN-based framework for modeling transient elastodynamic wave propagation in bimaterial systems governed by the axisymmetric equations of linear elasticity.
arXiv:2609.07294v1 Announce Type: new Abstract: Data-driven constitutive models for path-dependent plasticity are commonly formulated using nonlinear recurrent neural networks, whose sequential state...
The paper introduces a data‑driven framework for modeling the hyperelastic and viscoelastic behavior of digital materials made by multi‑material 3D printing. It extends a classical constitutive formulation by Bergström and Boyce, preserving multiplicative kinematics and invariant‑based strain‑energy functions while learning equilibrium and nonequilibrium parameters from multi‑rate uniaxial compression data across different compositions. The approach can either predict closed‑form model parameters as functions of composition or construct polyconvex strain‑energy functions using neural ordinary differential equations, ensuring thermodynamic consistency and capturing rate‑dependent stiffness and hysteresis.
arXiv:2607. 06740v1 Announce Type: cross Abstract: Soft robots have attracted significant attention in applications such as medical intervention, rehabilitation, and robotic manipulation due to their inherent compliance, flexibility, and high degrees of freedom.
The paper presents a method for accurately simulating soft tissue deformation and predicting forces across varying material stiffnesses and geometries. It calibrates hyperelastic constitutive models in the SOFA Framework using gravity‑loaded silicone beams, then trains a softness‑conditioned equivariant graph neural network on the calibrated simulations. The resulting model achieves sub‑millimeter deformation accuracy with 0.010 s inference time, and demonstrates that force prediction quality depends on consistent upstream calibration.