Magnet-Based Soft Robotic Skin Using a 3D-Printed Multi-Lattice Structure and CNN-Based Tactile Super-Resolution
Yunseong Bang, Joowon Park, Suan Sim, Youngjun Ryu, Sukho Park, Kyungseo Park
AI summary
Problem
Scalable whole-body robotic skin requires wide-area tactile perception without blind spots or dense, fragile sensor arrays, which existing pneumatic, vision-based, and magnetized-film approaches struggle to achieve.
Approach
A compliant multi-lattice TPU structure spreads localized contact forces to embedded permanent magnets, creating overlapping magnetic receptive fields that a sparse Hall-effect sensor array measures for CNN-driven tactile reconstruction.
Key results
- Tunable soft multi-lattice structure creating overlapping receptive fields
- SLS 3D-printed magnet-embedded TPU lattice for rapid conformal fabrication
- Sub-millimeter contact localization (mean XY: 1.13 mm, Z: 0.55 mm) using only 16 sparse sensors
- Real-time tactile super-resolution and scalable cylindrical skin integration on a robot forearm
Why it matters
Provides a scalable, robust pathway to whole-body tactile perception for safe human-robot interaction and collaborative robotics.
Abstract
This paper presents a magnet-based robotic skin that integrates a multilayer soft lattice with distributed Hall- effect sensor arrays and a tactile super-resolution model. Ex- ternal contact forces are converted to magnetic field changes by embedded permanent magnets, and the lattice spreads these changes across the sensing domain. This gives each sensor a large, overlapping receptive field and enables a large sensing area with minimal blind spots. Lattice parameters are tunable, enabling joint adjustment of mechanical compliance and transduction characteristics. An implicit modeling workflow and selective laser sintering (SLS) 3D printing support rapid fabrication of conformal, high-complexity structures. A convo- lutional neural network trained on experimental measurements estimates contact location and normal force in real time. Exper- iments validate localization accuracy and indicate scalability to larger surfaces, suggesting applicability to whole-body robotic skin and safe human-robot interaction.