Reduced-order Neural Modeling with Differentiable Simulation for High-Detail Tactile Perception
This work addresses the computational bottleneck of high-resolution tactile simulation for robotic manipulation, enabling efficient and differentiable tactile perception for optimization and control.
The authors propose a reduced-order neural simulation framework that couples coarse-grained MPM dynamics with an implicit neural decoder to reconstruct sub-particle tactile details, achieving over 65% faster simulation and 40% lower memory usage than TacIPC while improving geometric fidelity and tactile rendering accuracy by 25%.
Tactile perception is key to dexterous manipulation, yet simulating high-resolution elastomer deformation remains computationally prohibitive. Finite element methods (FEM) deliver high fidelity but demand costly remeshing, while Material Point Methods (MPM) suffer from heavy particle-memory tradeoffs. We propose a {reduced-order neural simulation framework} that couples coarse-grained MPM dynamics with an implicit neural decoder to reconstruct sub-particle tactile details from compact latent states. The framework learns a continuous deformation manifold from paired high- and low-resolution simulations, enabling physically consistent, differentiable inference. Compared to the TacIPC, our method achieves over 65\% faster simulation and {40\% lower memory usage}, while maintaining better geometric fidelity. In tactile rendering and 3D surface reconstruction, our methods further improve accuracy by 25\% and produce realistic depth images and surface mesh within a faster inference speed. These results demonstrate that the proposed reduced-order neural model enables high-detail, physically grounded tactile simulation with substantial efficiency gains for robotic interaction and optimization.