Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Yang, Xuanxuan, Zhang, Xiuyang, Chen, Haofeng, Ma, Gang, Wang, Xiaojie
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2512.03512
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866918229737209856
author Yang, Xuanxuan
Zhang, Xiuyang
Chen, Haofeng
Ma, Gang
Wang, Xiaojie
author_facet Yang, Xuanxuan
Zhang, Xiuyang
Chen, Haofeng
Ma, Gang
Wang, Xiaojie
contents Electrical impedance tomography (EIT) provides an attractive solution for large-area tactile sensing due to its minimal wiring and shape flexibility, but its nonlinear inverse problem often leads to severe artifacts and inaccurate contact reconstruction. This work presents PhyDNN, a physics-driven deep reconstruction framework that embeds the EIT forward model directly into the learning objective. By jointly minimizing the discrepancy between predicted and ground-truth conductivity maps and enforcing consistency with the forward PDE, PhyDNN reduces the black-box nature of deep networks and improves both physical plausibility and generalization. To enable efficient backpropagation, we design a differentiable forward-operator network that accurately approximates the nonlinear EIT response, allowing fast physics-guided training. Extensive simulations and real tactile experiments on a 16-electrode soft sensor show that PhyDNN consistently outperforms NOSER, TV, and standard DNNs in reconstructing contact shape, location, and pressure distribution. PhyDNN yields fewer artifacts, sharper boundaries, and higher metric scores, demonstrating its effectiveness for high-quality tomographic tactile sensing.
format Preprint
id arxiv_https___arxiv_org_abs_2512_03512
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Physics-Driven Learning Framework for Tomographic Tactile Sensing
Yang, Xuanxuan
Zhang, Xiuyang
Chen, Haofeng
Ma, Gang
Wang, Xiaojie
Machine Learning
Artificial Intelligence
Electrical impedance tomography (EIT) provides an attractive solution for large-area tactile sensing due to its minimal wiring and shape flexibility, but its nonlinear inverse problem often leads to severe artifacts and inaccurate contact reconstruction. This work presents PhyDNN, a physics-driven deep reconstruction framework that embeds the EIT forward model directly into the learning objective. By jointly minimizing the discrepancy between predicted and ground-truth conductivity maps and enforcing consistency with the forward PDE, PhyDNN reduces the black-box nature of deep networks and improves both physical plausibility and generalization. To enable efficient backpropagation, we design a differentiable forward-operator network that accurately approximates the nonlinear EIT response, allowing fast physics-guided training. Extensive simulations and real tactile experiments on a 16-electrode soft sensor show that PhyDNN consistently outperforms NOSER, TV, and standard DNNs in reconstructing contact shape, location, and pressure distribution. PhyDNN yields fewer artifacts, sharper boundaries, and higher metric scores, demonstrating its effectiveness for high-quality tomographic tactile sensing.
title Physics-Driven Learning Framework for Tomographic Tactile Sensing
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2512.03512