Touch100k: A Large-Scale Touch-Language-Vision Dataset for Touch-Centric Multimodal Representation

TL;DR

Touch100k introduces a large-scale touch-language-vision dataset and a novel pre-training method, enabling improved multimodal tactile understanding for robots and humans, with state-of-the-art results in touch-centric tasks.

Contribution

The paper presents Touch100k, a comprehensive dataset and a curriculum-based pre-training approach for tactile, language, and visual multimodal learning.

Findings

Enhanced tactile representation for robots

State-of-the-art zero-shot touch understanding

Improved performance in material and grasping tasks

Abstract

Touch holds a pivotal position in enhancing the perceptual and interactive capabilities of both humans and robots. Despite its significance, current tactile research mainly focuses on visual and tactile modalities, overlooking the language domain. Inspired by this, we construct Touch100k, a paired touch-language-vision dataset at the scale of 100k, featuring tactile sensation descriptions in multiple granularities (i.e., sentence-level natural expressions with rich semantics, including contextual and dynamic relationships, and phrase-level descriptions capturing the key features of tactile sensations). Based on the dataset, we propose a pre-training method, Touch-Language-Vision Representation Learning through Curriculum Linking (TLV-Link, for short), inspired by the concept of curriculum learning. TLV-Link aims to learn a tactile representation for the GelSight sensor and capture the relationship between tactile, language, and visual modalities. We evaluate our representation's performance across two task categories (namely, material property identification and robot grasping prediction), focusing on tactile representation and zero-shot touch understanding. The experimental evaluation showcases the effectiveness of our representation. By enabling TLV-Link to achieve substantial improvements and establish a new state-of-the-art in touch-centric multimodal representation learning, Touch100k demonstrates its value as a valuable resource for research. Project page: https://cocacola-lab.github.io/Touch100k/.