Toward Geometry-Scalable Whole-Body Touch for Humanoids: A 3D-Printed Conformal EIT Skin

2026-08-03

AI Summary

This work addresses the limitations of conventional tactile sensor arrays—poor scalability, complex wiring, and inadequate conformity to curved surfaces—when deployed over the full body of humanoid robots. The authors propose a flexible, conformal tactile skin based on electrical impedance tomography (EIT), integrating 3D-printed conductive thermoplastic polyurethane (TPU) structures with customizable geometry, a porous sensing layer, and contact-enhancing patches. Contact perception is achieved by measuring boundary voltage changes, and contact locations are efficiently reconstructed using a one-step Gauss–Newton algorithm. The design eliminates the need for robot-specific redesign, enabling scalable, large-area tactile coverage compatible with arbitrary curved surfaces. Validation on planar, U-shaped, and iCub face-mimicking prototypes demonstrates an average localization error of 6 mm across 18 contact points on curved surfaces, without requiring supervised post-processing.

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.

Problem

• whole-body tactile sensing
• scalability
• humanoid robots
• conformal sensing
• contact-rich environments

Innovation

• conformal EIT skin
• additive manufacturing
• whole-body tactile sensing
• geometry-scalable
• contact localization