Reproduce “Flexible Piezoelectric Tactile Sensing System for Intelligent Object Recognition” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Razan Khalifeh, Mohamad Yaacoub, Christian Gianoglio, Moustafa Saleh, Maurizio Valle, Yahya Abbass
The authors classify objects during grasping using flexible piezoelectric sensor arrays on both sides of a robot gripper. Their heatmap-and-2D-CNN method converts 50 samples from 32 sensors into spatial patterns. In tests on six objects, it achieved an F1-score of 0.9903; deployed end-to-end latency was 101.0879 ms. The score is for windowed evaluation, not first-window-only accuracy.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.