Dual-Channel Tomographic Tactile Skin with Pneumatic Pressure Sensing for Improved Force Estimation

TL;DR

This work tackles nonuniform sensitivity in Electrical Impedance Tomography (EIT) tactile skins by introducing a dual-channel skin that combines a tomographic EIT layer for contact localization with a pneumatic pressure layer for robust force estimation. A single-session calibration learns smooth location-aware gain and offset fields to correct the pneumatic–force mapping while distributing total pressure across multi-contact ROIs using EIT-derived conductivity sums. The approach yields high localization accuracy (≈4.4 mm) and substantially improved force estimation, with Pneumatic-LocAware achieving an RMSE of 0.59 N for 10–25 mm indenters and a 39.6% reduction in per-contact RMSE in multi-contact scenarios. The method offers a practical, scalable alternative to heavy learning pipelines, maintaining EIT’s multi-contact localization while leveraging pneumatics for reliable force sensing across large-area robotic skins.

Abstract

Tactile skins based on Electrical Impedance Tomography (EIT) enable large-area contact localization with few electrodes, but suffer from nonuniform sensitivity that limits force estimation accuracy. This work introduces a dual-channel tactile skin that integrates an EIT layer with a pneumatic pressure layer and a calibration framework that leverages their complementary strengths. The EIT layer provides robust multi-contact localization, while the pneumatic pressure layer supplies a stable scalar measurement that serves as contact force estimation. A location-aware correction method is introduced, learning smooth spatial gain and offset fields from a single-session calibration, enabling spatially consistent multi-contact force estimation. The proposed system achieves accurate force estimation across diverse contact configurations, generalizes to varying indenter sizes, and preserves EIT's inherent advantages in multi-contact localization. By letting the pneumatic pressure layer handle the force estimation and using the EIT layer to determine where each contact occurs, the method avoids the need for large datasets, complicated calibration setups, and heavy machine-learning pipelines often required by previous EIT-only approaches. This dual-channel design provides a practical, scalable, and easy-to-calibrate solution for building large-area robotic skins.

Figures (13)

• Figure 1: Overview of the proposed dual-channel tactile skin incorporating an EIT layer and a pneumatic pressure layer.
• Figure 2: Overview of the proposed dual-channel calibration framework using EIT layer and pneumatic pressure layer.
• Figure 3: Fabrication process of the flexible EIT-based and pneumatic pressure-based dual-channel tactile sensor.
• Figure 4: Single-contact experimental setup.
• Figure 5: Signal–force relationships between signals and ground-truth force. (a) EIT conductivity change sum vs. force at the center location. (b) Pneumatic pressure vs. force at the center location. (c) EIT conductivity change sum vs. force using all locations across the sensing area. (d) Pneumatic pressure vs. force using all locations. EIT conductivity change sum refers to the summation of the conductivity change within the detected contact ROI. Under applied force, ionic liquid is expelled from the porous structure in the contact region, which increases the local impedance and results in a negative conductivity change.