Object Shape Recognition Using Sparse Soft Capacitive Tactile Sensors for Robotic Hands.

Reliable tactile object shape recognition on robotic hands is often achieved using dense sensor arrays or vision-based tactile skins, which increase fabrication complexity and computational cost. This work demonstrates that high-recognition performance can instead be achieved through principled sparse sensing. A minimal multimodal tactile system is developed by fusing soft capacitive stretch sensors at the proximal interphalangeal and metacarpophalangeal joints of the fingers with a sparse six-element palmar pressure array, integrated into a human-like hand mechanically constrained to emulate robotic grasping under a controlled and repeatable protocol. Using an ANOVA-based channel selection, low-informative metacarpophalangeal signals are identified and removed, reducing the number of sensors at the finger joints while improving classification accuracy. A lightweight multi-layer perceptron operating on this low-dimensional input achieves 95.4% size-invariant recognition accuracy across 12 rigid objects representing four geometric primitives-cuboid, sphere, cylinder, and cone-outperforming the denser baseline. Ablation studies confirm the complementary roles of finger-joint deformation, which encodes curvature cues, and palmar force distribution, which captures contact topology; neither modality alone achieves comparable performance. Beyond accuracy, the proposed design reduces sensor count, wiring, and computational requirements, enabling embedded-ready deployment. The results show that data-driven sensor placement, rather than sensors at all finger joints, can yield sufficient grasp-based shape recognition, offering practical guidance for tactile perception in resource-constrained robotic hands.