Multimodal Zero-Shot Learning for Tactile Texture Recognition

TL;DR

This paper introduces a multimodal zero-shot learning framework for tactile texture recognition in robotics, enabling the recognition of unseen materials by synthesizing tactile features from visual and semantic data.

Contribution

It proposes a novel generative model that synthesizes tactile features from visual and semantic inputs, allowing zero-shot recognition of unknown materials.

Findings

Achieves 83.06% accuracy on unseen materials

Demonstrates effective multimodal feature synthesis

Provides a new dataset and robotic demo for tactile zero-shot learning

Abstract

Tactile sensing plays an irreplaceable role in robotic material recognition. It enables robots to distinguish material properties such as their local geometry and textures, especially for materials like textiles. However, most tactile recognition methods can only classify known materials that have been touched and trained with tactile data, yet cannot classify unknown materials that are not trained with tactile data. To solve this problem, we propose a tactile zero-shot learning framework to recognise unknown materials when they are touched for the first time without requiring training tactile samples. The visual modality, providing tactile cues from sight, and semantic attributes, giving high-level characteristics, are combined together to bridge the gap between touched classes and untouched classes. A generative model is learnt to synthesise tactile features according to corresponding visual images and semantic embeddings, and then a classifier can be trained using the synthesised tactile features of untouched materials for zero-shot recognition. Extensive experiments demonstrate that our proposed multimodal generative model can achieve a high recognition accuracy of 83.06% in classifying materials that were not touched before. The robotic experiment demo and the dataset are available at https://sites.google.com/view/multimodalzsl.