Toward Geometry-Scalable Whole-Body Touch for Humanoids: A 3D-Printed Conformal EIT Skin
2026-08-03 • Robotics
Robotics
AI summaryⓘ
The authors developed a flexible, touch-sensitive skin for humanoid robots that can wrap around different shapes and detect where it's being touched. Instead of using many small sensors that are hard to wire and adjust, they use a single conductive layer and electrical impedance tomography to find contact points. They tested the skin on flat and curved surfaces, including a face-shaped model, and achieved about 6 mm accuracy in locating touches. This approach could make it easier to add touch sensing to robots with complex shapes without redesigning sensors for each case.
electrical impedance tomographytactile sensinghumanoid robotsadditive manufacturingconductive TPUcontact localizationsensor fabricationflexible electronicsboundary voltage measurement
Authors
Haofeng Chen, Carson Kohlbrenner, Jiri Kubik, Lukas Rustler, Alexander Dickhans, Karel Bartunek, Alessandro Roncone, Hyosang Lee, Matej Hoffmann
Abstract
Whole-body tactile sensing is a prerequisite for humanoids that operate in contact-rich human environments, but conventional taxel arrays scale poorly with surface area, wiring complexity, and robot-specific curvature. We present a conformal electrical impedance tomography tactile skin fabricated through a geometry-adaptable additive-manufacturing workflow. A flexible conductive TPU layer forms a continuous sensing domain, while contact-induced coupling with conductive patches produces boundary voltage changes that are reconstructed using a one-step Gauss-Newton EIT solver. We first characterize the electromechanical design space of the layered structure and show that low-resistance contact-enhancement patches and a porous conductive TPU sensing layer improve sensitivity while preserving printability. We then validate contact localization on a planar prototype, a curved U-shaped prototype, and a qualitative iCub-face-shaped geometry. The curved sensor achieves a mean localization error of 6 mm over 18 contact positions without supervised post-processing. These results suggest that additively manufactured tomographic skins can reduce the morphology-specific redesign burden for humanoid tactile coverage and provide a practical route toward large-area contact sensing for human-centered deployment.