Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2605.05053 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909017826131968 |
|---|---|
| author | Guo, Yuhu Shen, Zhikai Qu, Jiasheng Qian, Chenghao Huang, Yuming Chen, Bin Fang, Guoxing |
| author_facet | Guo, Yuhu Shen, Zhikai Qu, Jiasheng Qian, Chenghao Huang, Yuming Chen, Bin Fang, Guoxing |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_05053 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Reduced-order Neural Modeling with Differentiable Simulation for High-Detail Tactile Perception Guo, Yuhu Shen, Zhikai Qu, Jiasheng Qian, Chenghao Huang, Yuming Chen, Bin Fang, Guoxing Robotics Computer Vision and Pattern Recognition 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. |
| title | Reduced-order Neural Modeling with Differentiable Simulation for High-Detail Tactile Perception |
| topic | Robotics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.05053 |