Tactile Exploration-Enabled Shape Recognition With Multiperspective Feature Representation

Shape recognition is essential in multifarious manipulations, such as object grasping, block building, and parts assembly, which most frequently rely on visual perception. However, it inevitably suffers from the adverse impact of illumination intensity, visual distortion from different views, and frequent occlusions in dynamic scenes. To tackle this problem, this article proposes recognizing different shapes via tactile exploration, mimicking the human manner of touch in dark environments. Based on our designed tactile fingertip, which comprises four sensing elements (SEs) and a fingerprint structure, we employed the signal processing framework consisting of data preprocessing, feature pool establishment, selection of the most discriminative feature combination, and recognition model using a shallow neural network (NN). Particularly, the feature pool was extended to comprise 386 multiperspective features spanning different domains and scales. When the nine features with the highest weights were selected using neighborhood component analysis (NCA), our extreme learning machine (ELM)-based recognition model achieved an accuracy as high as 99.72%. To contextualize this performance, a comprehensive benchmark was conducted against several state-of-the-art deep learning (DL) paradigms, including end-to-end and transfer learning models. The analysis reveals that for data-constrained and resource-sensitive tactile sensing applications, our proposed and interpretable feature engineering approach not only achieves superior accuracy but also offers significant advantages in computational efficiency. This work validates the practical value of tailored feature engineering and sheds light on more efficient utilization of tactile signals in real-world robotic recognition tasks.