Physics-Driven Learning Framework for Tomographic Tactile Sensing
This work addresses the challenge of improving tactile sensing accuracy for robotics or human-computer interaction applications, representing an incremental advancement by integrating physics into deep learning for EIT reconstruction.
The paper tackles the problem of severe artifacts and inaccurate contact reconstruction in electrical impedance tomography (EIT) for tactile sensing by introducing PhyDNN, a physics-driven deep reconstruction framework that embeds the EIT forward model into the learning objective. The result shows that PhyDNN consistently outperforms baseline methods like NOSER, TV, and standard DNNs in simulations and real experiments on a 16-electrode soft sensor, yielding fewer artifacts, sharper boundaries, and higher metric scores.
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.