A geometry-aware and customizable multimodal sensing system for texture and material identification in prosthetics

The restoration of natural somatosensation remains largely absent in upper-limb prostheses. Current electronic skins are still limited by coarse resolution, planar form factors, and high fabrication cost. Here, we present a geometry-aware and customizable multimodal sensing system for prostheses that functions as a sensing component for mimicking human skin. The system integrates high-resolution and high-rate pressure and temperature mapping in conformal, free-form modules. A "scan-model-print" workflow converts a patient's prosthesis topography into 3D sensor curvature for seamless surface conformity. Self-aligning snap-fit interconnects enable on-demand reconfiguration, while interlaced pressure and temperature matrices maximize spatial utilization. Compared with commercial glove sensors, the system achieves ∼10-fold finer spatial resolution for pressure and temperature. A multihead neural network performs real-time calibration and denoising, thereby reducing per-pixel error and improving signal fidelity. The system enables texture and material identification and provides a sensing platform toward personalized prostheses with integrated sensing and haptic feedback.